Unsupervised learning of natural languages

PubMed Central

Solan, Zach; Horn, David; Ruppin, Eytan; Edelman, Shimon

2005-01-01

We address the problem, fundamental to linguistics, bioinformatics, and certain other disciplines, of using corpora of raw symbolic sequential data to infer underlying rules that govern their production. Given a corpus of strings (such as text, transcribed speech, chromosome or protein sequence data, sheet music, etc.), our unsupervised algorithm recursively distills from it hierarchically structured patterns. The adios (automatic distillation of structure) algorithm relies on a statistical method for pattern extraction and on structured generalization, two processes that have been implicated in language acquisition. It has been evaluated on artificial context-free grammars with thousands of rules, on natural languages as diverse as English and Chinese, and on protein data correlating sequence with function. This unsupervised algorithm is capable of learning complex syntax, generating grammatical novel sentences, and proving useful in other fields that call for structure discovery from raw data, such as bioinformatics. PMID:16087885

Unsupervised learning of natural languages.

PubMed

Solan, Zach; Horn, David; Ruppin, Eytan; Edelman, Shimon

2005-08-16

We address the problem, fundamental to linguistics, bioinformatics, and certain other disciplines, of using corpora of raw symbolic sequential data to infer underlying rules that govern their production. Given a corpus of strings (such as text, transcribed speech, chromosome or protein sequence data, sheet music, etc.), our unsupervised algorithm recursively distills from it hierarchically structured patterns. The adios (automatic distillation of structure) algorithm relies on a statistical method for pattern extraction and on structured generalization, two processes that have been implicated in language acquisition. It has been evaluated on artificial context-free grammars with thousands of rules, on natural languages as diverse as English and Chinese, and on protein data correlating sequence with function. This unsupervised algorithm is capable of learning complex syntax, generating grammatical novel sentences, and proving useful in other fields that call for structure discovery from raw data, such as bioinformatics.

Audio-based, unsupervised machine learning reveals cyclic changes in earthquake mechanisms in the Geysers geothermal field, California

NASA Astrophysics Data System (ADS)

Holtzman, B. K.; Paté, A.; Paisley, J.; Waldhauser, F.; Repetto, D.; Boschi, L.

2017-12-01

The earthquake process reflects complex interactions of stress, fracture and frictional properties. New machine learning methods reveal patterns in time-dependent spectral properties of seismic signals and enable identification of changes in faulting processes. Our methods are based closely on those developed for music information retrieval and voice recognition, using the spectrogram instead of the waveform directly. Unsupervised learning involves identification of patterns based on differences among signals without any additional information provided to the algorithm. Clustering of 46,000 earthquakes of $0.3

Testing the Nonce Borrowing Hypothesis: Counter-Evidence from English-Origin Verbs in Welsh

ERIC Educational Resources Information Center

Stammers, Jonathan R.; Deuchar, Margaret

2012-01-01

According to the nonce borrowing hypothesis (NBH), "[n]once borrowings pattern exactly like their native counterparts in the (unmixed) recipient language" (Poplack & Meechan, 1998a, p. 137). Nonce borrowings (Sankoff, Poplack & Vanniarajan, 1990, p. 74) are "lone other-language items" which differ from established borrowings in terms of frequency…

EPA UNMIX 6.0 USER GUIDE

EPA Science Inventory

The underlying philosophy of Unmix is to let the data speak for itself. Unmix seeks to solve the general mixture problem where the data are assumed to be a linear combination of an unknown number of sources of unknown composition, which contribute an unknown amount to each sample...

Hyperspectral Image Classification using a Self-Organizing Map

NASA Technical Reports Server (NTRS)

Martinez, P.; Gualtieri, J. A.; Aguilar, P. L.; Perez, R. M.; Linaje, M.; Preciado, J. C.; Plaza, A.

2001-01-01

The use of hyperspectral data to determine the abundance of constituents in a certain portion of the Earth's surface relies on the capability of imaging spectrometers to provide a large amount of information at each pixel of a certain scene. Today, hyperspectral imaging sensors are capable of generating unprecedented volumes of radiometric data. The Airborne Visible/Infrared Imaging Spectrometer (AVIRIS), for example, routinely produces image cubes with 224 spectral bands. This undoubtedly opens a wide range of new possibilities, but the analysis of such a massive amount of information is not an easy task. In fact, most of the existing algorithms devoted to analyzing multispectral images are not applicable in the hyperspectral domain, because of the size and high dimensionality of the images. The application of neural networks to perform unsupervised classification of hyperspectral data has been tested by several authors and also by us in some previous work. We have also focused on analyzing the intrinsic capability of neural networks to parallelize the whole hyperspectral unmixing process. The results shown in this work indicate that neural network models are able to find clusters of closely related hyperspectral signatures, and thus can be used as a powerful tool to achieve the desired classification. The present work discusses the possibility of using a Self Organizing neural network to perform unsupervised classification of hyperspectral images. In sections 3 and 4, the topology of the proposed neural network and the training algorithm are respectively described. Section 5 provides the results we have obtained after applying the proposed methodology to real hyperspectral data, described in section 2. Different parameters in the learning stage have been modified in order to obtain a detailed description of their influence on the final results. Finally, in section 6 we provide the conclusions at which we have arrived.

Rough Set Based Splitting Criterion for Binary Decision Tree Classifiers

DTIC Science & Technology

2006-09-26

Alata O. Fernandez-Maloigne C., and Ferrie J.C. (2001). Unsupervised Algorithm for the Segmentation of Three-Dimensional Magnetic Resonance Brain ...instinctual and learned responses in the brain , causing it to make decisions based on patterns in the stimuli. Using this deceptively simple process...2001. [2] Bohn C. (1997). An Incremental Unsupervised Learning Scheme for Function Approximation. In: Proceedings of the 1997 IEEE International

Hyperspectral remote sensing exploration of carbonatite - an example from Epembe, Kunene region, Namibia

NASA Astrophysics Data System (ADS)

Zimmermann, Robert; Brandmeier, Melanie; Andreani, Louis; Gloaguen, Richard

2015-04-01

Remote sensing data can provide valuable information about ore deposits and their alteration zones at surface level. High spectral and spatial resolution of the data is essential for detailed mapping of mineral abundances and related structures. Carbonatites are well known for hosting economic enrichments in REE, Ta, Nb and P (Jones et al. 2013). These make them a preferential target for exploration for those critical elements. In this study we show how combining geomorphic, textural and spectral data improves classification result. We selected a site with a well-known occurrence in northern Namibia: the Epembe dyke. For analysis LANDSAT 8, SRTM and airborne hyperspectral (HyMap) data were chosen. The overlapping data allows a multi-scale and multi-resolution approach. Results from data analysis were validated during fieldwork in 2014. Data was corrected for atmospherical and geometrical effects. Image classification, mineral mapping and tectonic geomorphology allow a refinement of the geological map by lithological mapping in a second step. Detailed mineral abundance maps were computed using spectral unmixing techniques. These techniques are well suited to map abundances of carbonate minerals, but not to discriminate the carbonatite itself from surrounding rocks with similar spectral signatures. Thus, geometric indices were calculated using tectonic geomorphology and textures. For this purpose the TecDEM-toolbox (SHAHZAD & GLOAGUEN 2011) was applied to the SRTM-data for geomorphic analysis. Textural indices (e.g. uniformity, entropy, angular second moment) were derived from HyMap and SRTM by a grey-level co-occurrence matrix (CLAUSI 2002). The carbonatite in the study area is ridge-forming and shows a narrow linear feature in the textural bands. Spectral and geometric information were combined using kohonen Self-Organizing Maps (SOM) for unsupervised clustering. The resulting class spectra were visually compared and interpreted. Classes with similar signatures were merged according to geological context. The major conclusions are: 1. Carbonate minerals can be mapped using spectral unmixing techniques. 2. Carbonatites are associated with specific geometric pattern 3. The combination of spectral and geometric information improves classification result and reduces misclassification. References Clausi, D. A. (2002): An analysis of co-occurrence texture statistics as a function of grey-level quantization. - Canadian Journal of Remote Sensing, 28 (1), 45-62 Jones, A. P., Genge, M. and Carmody, L (2013): Carbonate Melts and Carbonatites. - Reviews in Mineralogy & Geochemistry, 75, 289-322 Shahzad, F. & Gloaguen, R. (2011): TecDEM: A MATLAB based toolbox for tectonic geomorphology, Part 2: Surface dynamics and basin analysis. - Computers and Geosciences, 37 (2), 261-271

Distributed Unmixing of Hyperspectral Datawith Sparsity Constraint

NASA Astrophysics Data System (ADS)

Khoshsokhan, S.; Rajabi, R.; Zayyani, H.

2017-09-01

Spectral unmixing (SU) is a data processing problem in hyperspectral remote sensing. The significant challenge in the SU problem is how to identify endmembers and their weights, accurately. For estimation of signature and fractional abundance matrices in a blind problem, nonnegative matrix factorization (NMF) and its developments are used widely in the SU problem. One of the constraints which was added to NMF is sparsity constraint that was regularized by L1/2 norm. In this paper, a new algorithm based on distributed optimization has been used for spectral unmixing. In the proposed algorithm, a network including single-node clusters has been employed. Each pixel in hyperspectral images considered as a node in this network. The distributed unmixing with sparsity constraint has been optimized with diffusion LMS strategy, and then the update equations for fractional abundance and signature matrices are obtained. Simulation results based on defined performance metrics, illustrate advantage of the proposed algorithm in spectral unmixing of hyperspectral data compared with other methods. The results show that the AAD and SAD of the proposed approach are improved respectively about 6 and 27 percent toward distributed unmixing in SNR=25dB.

Lithologic analysis from multispectral thermal infrared data of the alkalic rock complex at Iron Hill, Colorado

USGS Publications Warehouse

Watson, K.; Rowan, L.C.; Bowers, T.L.; Anton-Pacheco, C.; Gumiel, P.; Miller, S.H.

1996-01-01

Airborne thermal-infrared multispectral scanner (TIMS) data of the Iron Hill carbonatite-alkalic igneous rock complex in south-central Colorado are analyzed using a new spectral emissivity ratio algorithm and confirmed by field examination using existing 1:24 000-scale geologic maps and petrographic studies. Color composite images show that the alkalic rocks could be clearly identified and that differences existed among alkalic rocks in several parts of the complex. An unsupervised classification algorithm defines four alkalic rock classes within the complex: biotitic pyroxenite, uncompahgrite, augitic pyroxenite, and fenite + nepheline syenite. Felsic rock classes defined in the surrounding country rock are an extensive class consisting of tuff, granite, and felsite, a less extensive class of granite and felsite, and quartzite. The general composition of the classes can be determined from comparisons of the TIMS spectra with laboratory spectra. Carbonatite rocks are not classified, and we attribute that to the fact that dolomite, the predominant carbonate mineral in the complex, has a spectral feature that falls between TIMS channels 5 and 6. Mineralogical variability in the fenitized granite contributed to the nonuniform pattern of the fenite-nepheline syenite class. The biotitic pyroxenite, which resulted from alteration of the pyroxenite, is spatially associated and appears to be related to narrow carbonatite dikes and sills. Results from a linear unmixing algorithm suggest that the detected spatial extent of the two mixed felsic rock classes was sensitive to the amount of vegetation cover. These results illustrate that spectral thermal infrared data can be processed to yield compositional information that can be a cost-effective tool to target mineral exploration, particularly in igneous terranes.

Mapping target signatures via partial unmixing of AVIRIS data

NASA Technical Reports Server (NTRS)

Boardman, Joseph W.; Kruse, Fred A.; Green, Robert O.

1995-01-01

A complete spectral unmixing of a complicated AVIRIS scene may not always be possible or even desired. High quality data of spectrally complex areas are very high dimensional and are consequently difficult to fully unravel. Partial unmixing provides a method of solving only that fraction of the data inversion problem that directly relates to the specific goals of the investigation. Many applications of imaging spectrometry can be cast in the form of the following question: 'Are my target signatures present in the scene, and if so, how much of each target material is present in each pixel?' This is a partial unmixing problem. The number of unmixing endmembers is one greater than the number of spectrally defined target materials. The one additional endmember can be thought of as the composite of all the other scene materials, or 'everything else'. Several workers have proposed partial unmixing schemes for imaging spectrometry data, but each has significant limitations for operational application. The low probability detection methods described by Farrand and Harsanyi and the foreground-background method of Smith et al are both examples of such partial unmixing strategies. The new method presented here builds on these innovative analysis concepts, combining their different positive attributes while attempting to circumvent their limitations. This new method partially unmixes AVIRIS data, mapping apparent target abundances, in the presence of an arbitrary and unknown spectrally mixed background. It permits the target materials to be present in abundances that drive significant portions of the scene covariance. Furthermore it does not require a priori knowledge of the background material spectral signatures. The challenge is to find the proper projection of the data that hides the background variance while simultaneously maximizing the variance amongst the targets.

Ejecta patterns of Meteor Crater, Arizona derived from the linear un-mixing of TIMS data and laboratory thermal emission spectra

NASA Technical Reports Server (NTRS)

Ramsey, Michael S.; Christensen, Philip R.

1992-01-01

Accurate interpretation of thermal infrared data depends upon the understanding and removal of complicating effects. These effects may include physical mixing of various mineralogies and particle sizes, atmospheric absorption and emission, surficial coatings, geometry effects, and differential surface temperatures. The focus is the examination of the linear spectral mixing of individual mineral or endmember spectra. Linear addition of spectra, for particles larger than the wavelength, allows for a straight-forward method of deconvolving the observed spectra, predicting a volume percent of each endmember. The 'forward analysis' of linear mixing (comparing the spectra of physical mixtures to numerical mixtures) has received much attention. The reverse approach of un-mixing thermal emission spectra was examined with remotely sensed data, but no laboratory verification exists. Understanding of the effects of spectral mixing on high resolution laboratory spectra allows for the extrapolation to lower resolution, and often more complicated, remotely gathered data. Thermal Infrared Multispectral Scanner (TIMS) data for Meteor Crater, Arizona were acquired in Sep. 1987. The spectral un-mixing of these data gives a unique test of the laboratory results. Meteor Crater (1.2 km in diameter and 180 m deep) is located in north-central Arizona, west of Canyon Diablo. The arid environment, paucity of vegetation, and low relief make the region ideal for remote data acquisition. Within the horizontal sedimentary sequence that forms the upper Colorado Plateau, the oldest unit sampled by the impact crater was the Permian Coconino Sandstone. A thin bed of the Toroweap Formation, also of Permian age, conformably overlays the Coconino. Above the Toroweap lies the Permian Kiabab Limestone which, in turn, is covered by a thin veneer of the Moenkopi Formation. The Moenkopi is Triassic in age and has two distinct sub-units in the vicinity of the crater. The lower Wupatki member is a fine-grained sandstone, while the upper Moqui member is a fissile siltstone. Ejecta from these units are preserved as inverted stratigraphy up to 2 crater radii from the rim. The mineralogical contrast between the units, relative lack of post-emplacement erosion and ejecta mixing provide a unique site to apply the un-mixing model. Selection of the aforementioned units as endmembers reveals distinct patterns in the ejecta of the crater.

MAX UnMix: Introducing a new web application for unmixing magnetic coercivity distributions

NASA Astrophysics Data System (ADS)

Feinberg, J. M.; Maxbauer, D.; Fox, D. L.

2016-12-01

Magnetic minerals are present in a wide variety of natural systems and are often indicative of the natural or anthropogenic processes that led to their deposition, formation, or transformation. Unmixing the contribution of magnetic components to bulk field-dependent magnetization curves has become increasingly common in environmental and rock magnetic studies and has enhanced our ability to fingerprint the magnetic signatures of magnetic minerals with distinct compositions, grain sizes, and origins. A variety of programs have been developed over the past two decades to allow researchers to deconvolve field-dependent magnetization curves for these purposes, however many of these programs are either outdated or have obstacles that inhibit the programs usability. MAX UnMix is a new web application (available online at http://www.irm.umn.edu/maxunmix) built using the `shiny' package for R-studio that can be used to process coercivity distributions derived from magnetization curves (acquisition, demagnetization, or backfield data) via an online user-interface. Here, we use example datasets from lake sediments and paleosols to present details of the MAX UnMix model and the programs functionality. MAX UnMix is designed to be accessible, user friendly, and should serve as a useful resource for future research.

Collected Notes on the Workshop for Pattern Discovery in Large Databases

NASA Technical Reports Server (NTRS)

Buntine, Wray (Editor); Delalto, Martha (Editor)

1991-01-01

These collected notes are a record of material presented at the Workshop. The core data analysis is addressed that have traditionally required statistical or pattern recognition techniques. Some of the core tasks include classification, discrimination, clustering, supervised and unsupervised learning, discovery and diagnosis, i.e., general pattern discovery.

Some simple guides to finding useful information in exploration geochemical data

USGS Publications Warehouse

Singer, D.A.; Kouda, R.

2001-01-01

Most regional geochemistry data reflect processes that can produce superfluous bits of noise and, perhaps, information about the mineralization process of interest. There are two end-member approaches to finding patterns in geochemical data-unsupervised learning and supervised learning. In unsupervised learning, data are processed and the geochemist is given the task of interpreting and identifying possible sources of any patterns. In supervised learning, data from known subgroups such as rock type, mineralized and nonmineralized, and types of mineralization are used to train the system which then is given unknown samples to classify into these subgroups. To locate patterns of interest, it is helpful to transform the data and to remove unwanted masking patterns. With trace elements use of a logarithmic transformation is recommended. In many situations, missing censored data can be estimated using multiple regression of other uncensored variables on the variable with censored values. In unsupervised learning, transformed values can be standardized, or normalized, to a Z-score by subtracting the subset's mean and dividing by its standard deviation. Subsets include any source of differences that might be related to processes unrelated to the target sought such as different laboratories, regional alteration, analytical procedures, or rock types. Normalization removes effects of different means and measurement scales as well as facilitates comparison of spatial patterns of elements. These adjustments remove effects of different subgroups and hopefully leave on the map the simple and uncluttered pattern(s) related to the mineralization only. Supervised learning methods, such as discriminant analysis and neural networks, offer the promise of consistent and, in certain situations, unbiased estimates of where mineralization might exist. These methods critically rely on being trained with data that encompasses all populations fairly and that can possibly fall into only the identified populations. ?? 2001 International Association for Mathematical Geology.

Supervised versus unsupervised technology-based levodopa monitoring in Parkinson's disease: an intrasubject comparison.

PubMed

Lopane, Giovanna; Mellone, Sabato; Corzani, Mattia; Chiari, Lorenzo; Cortelli, Pietro; Calandra-Buonaura, Giovanna; Contin, Manuela

2018-06-01

We aimed to assess the intrasubject reproducibility of a technology-based levodopa (LD) therapeutic monitoring protocol administered in supervised versus unsupervised conditions in patients with Parkinson's disease (PD). The study design was pilot, intrasubject, single center, open and prospective. Twenty patients were recruited. Patients performed a standardized monitoring protocol instrumented by an ad hoc embedded platform after their usual first morning LD dose in two different randomized ambulatory sessions: one under a physician's supervision, the other self-administered. The protocol is made up of serial motor and non-motor tests, including alternate finger tapping, Timed Up and Go test, and measurement of blood pressure. Primary motor outcomes included comparisons of intrasubject LD subacute motor response patterns over the 3-h test in the two experimental conditions. Secondary outcomes were the number of intrasession serial test repetitions due to technical or handling errors and patients' satisfaction with the unsupervised LD monitoring protocol. Intrasubject LD motor response patterns were concordant between the two study sessions in all patients but one. Platform handling problems averaged 4% of total planned serial tests for both sessions. Ninety-five percent of patients were satisfied with the self-administered LD monitoring protocol. To our knowledge, this study is the first to explore the potential of unsupervised technology-based objective motor and non-motor tasks to monitor subacute LD dosing effects in PD patients. The results are promising for future telemedicine applications.

A method of minimum volume simplex analysis constrained unmixing for hyperspectral image

NASA Astrophysics Data System (ADS)

Zou, Jinlin; Lan, Jinhui; Zeng, Yiliang; Wu, Hongtao

2017-07-01

The signal recorded by a low resolution hyperspectral remote sensor from a given pixel, letting alone the effects of the complex terrain, is a mixture of substances. To improve the accuracy of classification and sub-pixel object detection, hyperspectral unmixing(HU) is a frontier-line in remote sensing area. Unmixing algorithm based on geometric has become popular since the hyperspectral image possesses abundant spectral information and the mixed model is easy to understand. However, most of the algorithms are based on pure pixel assumption, and since the non-linear mixed model is complex, it is hard to obtain the optimal endmembers especially under a highly mixed spectral data. To provide a simple but accurate method, we propose a minimum volume simplex analysis constrained (MVSAC) unmixing algorithm. The proposed approach combines the algebraic constraints that are inherent to the convex minimum volume with abundance soft constraint. While considering abundance fraction, we can obtain the pure endmember set and abundance fraction correspondingly, and the final unmixing result is closer to reality and has better accuracy. We illustrate the performance of the proposed algorithm in unmixing simulated data and real hyperspectral data, and the result indicates that the proposed method can obtain the distinct signatures correctly without redundant endmember and yields much better performance than the pure pixel based algorithm.

Unsupervised learning on scientific ocean drilling datasets from the South China Sea

NASA Astrophysics Data System (ADS)

Tse, Kevin C.; Chiu, Hon-Chim; Tsang, Man-Yin; Li, Yiliang; Lam, Edmund Y.

2018-06-01

Unsupervised learning methods were applied to explore data patterns in multivariate geophysical datasets collected from ocean floor sediment core samples coming from scientific ocean drilling in the South China Sea. Compared to studies on similar datasets, but using supervised learning methods which are designed to make predictions based on sample training data, unsupervised learning methods require no a priori information and focus only on the input data. In this study, popular unsupervised learning methods including K-means, self-organizing maps, hierarchical clustering and random forest were coupled with different distance metrics to form exploratory data clusters. The resulting data clusters were externally validated with lithologic units and geologic time scales assigned to the datasets by conventional methods. Compact and connected data clusters displayed varying degrees of correspondence with existing classification by lithologic units and geologic time scales. K-means and self-organizing maps were observed to perform better with lithologic units while random forest corresponded best with geologic time scales. This study sets a pioneering example of how unsupervised machine learning methods can be used as an automatic processing tool for the increasingly high volume of scientific ocean drilling data.

Semi-supervised and unsupervised extreme learning machines.

PubMed

Huang, Gao; Song, Shiji; Gupta, Jatinder N D; Wu, Cheng

2014-12-01

Extreme learning machines (ELMs) have proven to be efficient and effective learning mechanisms for pattern classification and regression. However, ELMs are primarily applied to supervised learning problems. Only a few existing research papers have used ELMs to explore unlabeled data. In this paper, we extend ELMs for both semi-supervised and unsupervised tasks based on the manifold regularization, thus greatly expanding the applicability of ELMs. The key advantages of the proposed algorithms are as follows: 1) both the semi-supervised ELM (SS-ELM) and the unsupervised ELM (US-ELM) exhibit learning capability and computational efficiency of ELMs; 2) both algorithms naturally handle multiclass classification or multicluster clustering; and 3) both algorithms are inductive and can handle unseen data at test time directly. Moreover, it is shown in this paper that all the supervised, semi-supervised, and unsupervised ELMs can actually be put into a unified framework. This provides new perspectives for understanding the mechanism of random feature mapping, which is the key concept in ELM theory. Empirical study on a wide range of data sets demonstrates that the proposed algorithms are competitive with the state-of-the-art semi-supervised or unsupervised learning algorithms in terms of accuracy and efficiency.

ℓ0 -based sparse hyperspectral unmixing using spectral information and a multi-objectives formulation

NASA Astrophysics Data System (ADS)

Xu, Xia; Shi, Zhenwei; Pan, Bin

2018-07-01

Sparse unmixing aims at recovering pure materials from hyperpspectral images and estimating their abundance fractions. Sparse unmixing is actually ℓ0 problem which is NP-h ard, and a relaxation is often used. In this paper, we attempt to deal with ℓ0 problem directly via a multi-objective based method, which is a non-convex manner. The characteristics of hyperspectral images are integrated into the proposed method, which leads to a new spectra and multi-objective based sparse unmixing method (SMoSU). In order to solve the ℓ0 norm optimization problem, the spectral library is encoded in a binary vector, and a bit-wise flipping strategy is used to generate new individuals in the evolution process. However, a multi-objective method usually produces a number of non-dominated solutions, while sparse unmixing requires a single solution. How to make the final decision for sparse unmixing is challenging. To handle this problem, we integrate the spectral characteristic of hyperspectral images into SMoSU. By considering the spectral correlation in hyperspectral data, we improve the Tchebycheff decomposition function in SMoSU via a new regularization item. This regularization item is able to enforce the individual divergence in the evolution process of SMoSU. In this way, the diversity and convergence of population is further balanced, which is beneficial to the concentration of individuals. In the experiments part, three synthetic datasets and one real-world data are used to analyse the effectiveness of SMoSU, and several state-of-art sparse unmixing algorithms are compared.

A SOFTWARE PACKAGE FOR UNSUPERVISED PATTERN RECOGNITION AND SYNOPTIC REPRESENTATION OF RESULTS: APPLICATION TO VOLCANIC TREMOR DATA OF MT ETNA

NASA Astrophysics Data System (ADS)

Langer, H. K.; Falsaperla, S. M.; Behncke, B.; Messina, A.; Spampinato, S.

2009-12-01

Artificial Intelligence (AI) has found broad applications in volcano observatories worldwide with the aim of reducing volcanic hazard. The need to process larger and larger quantity of data makes indeed AI techniques appealing for monitoring purposes. Tools based on Artificial Neural Networks and Support Vector Machine have proved to be particularly successful in the classification of seismic events and volcanic tremor changes heralding eruptive activity, such as paroxysmal explosions and lava fountaining at Stromboli and Mt Etna, Italy (e.g., Falsaperla et al., 1996; Langer et al., 2009). Moving on from the excellent results obtained from these applications, we present KKAnalysis, a MATLAB based software which combines several unsupervised pattern classification methods, exploiting routines of the SOM Toolbox 2 for MATLAB (http://www.cis.hut.fi/projects/somtoolbox). KKAnalysis is based on Self Organizing Maps (SOM) and clustering methods consisting of K-Means, Fuzzy C-Means, and a scheme based on a metrics accounting for correlation between components of the feature vector. We show examples of applications of this tool to volcanic tremor data recorded at Mt Etna between 2007 and 2009. This time span - during which Strombolian explosions, 7 episodes of lava fountaining and effusive activity occurred - is particularly interesting, as it encompassed different states of volcanic activity (i.e., non-eruptive, eruptive according to different styles) for the unsupervised classifier to identify, highlighting their development in time. Even subtle changes in the signal characteristics allow the unsupervised classifier to recognize features belonging to the different classes and stages of volcanic activity. A convenient color-code representation shows up the temporal development of the different classes of signal, making this method extremely helpful for monitoring purposes and surveillance. Though being developed for volcanic tremor classification, KKAnalysis is generally applicable to any type of physical or chemical pattern, provided that feature vectors are given in numerical form. References: Falsaperla, S., S. Graziani, G. Nunnari, and S. Spampinato (1996). Automatic classification of volcanic earthquakes by using multy-layered neural networks. Natural Hazard, 13, 205-228. Langer, H., S. Falsaperla, M. Masotti, R. Campanini, S. Spampinato, and A. Messina (2008). Synopsis of supervised and unsupervised pattern classification techniques applied to volcanic tremor data at Mt Etna, Italy. Geophys. J. Int., doi:10.1111/j.1365-246X.2009.04179.x.

Estimating urban vegetation fraction across 25 cities in pan-Pacific using Landsat time series data

NASA Astrophysics Data System (ADS)

Lu, Yuhao; Coops, Nicholas C.; Hermosilla, Txomin

2017-04-01

Urbanization globally is consistently reshaping the natural landscape to accommodate the growing human population. Urban vegetation plays a key role in moderating environmental impacts caused by urbanization and is critically important for local economic, social and cultural development. The differing patterns of human population growth, varying urban structures and development stages, results in highly varied spatial and temporal vegetation patterns particularly in the pan-Pacific region which has some of the fastest urbanization rates globally. Yet spatially-explicit temporal information on the amount and change of urban vegetation is rarely documented particularly in less developed nations. Remote sensing offers an exceptional data source and a unique perspective to map urban vegetation and change due to its consistency and ubiquitous nature. In this research, we assess the vegetation fractions of 25 cities across 12 pan-Pacific countries using annual gap-free Landsat surface reflectance products acquired from 1984 to 2012, using sub-pixel, spectral unmixing approaches. Vegetation change trends were then analyzed using Mann-Kendall statistics and Theil-Sen slope estimators. Unmixing results successfully mapped urban vegetation for pixels located in urban parks, forested mountainous regions, as well as agricultural land (correlation coefficient ranging from 0.66 to 0.77). The greatest vegetation loss from 1984 to 2012 was found in Shanghai, Tianjin, and Dalian in China. In contrast, cities including Vancouver (Canada) and Seattle (USA) showed stable vegetation trends through time. Using temporal trend analysis, our results suggest that it is possible to reduce noise and outliers caused by phenological changes particularly in cropland using dense new Landsat time series approaches. We conclude that simple yet effective approaches of unmixing Landsat time series data for assessing spatial and temporal changes of urban vegetation at regional scales can provide critical information for urban planners and anthropogenic studies globally.

Electrotransport-induced unmixing and decomposition of ternary oxides

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chun, Jakyu; Yoo, Han-Ill, E-mail: hiyoo@snu.ac.kr; Martin, Manfred

A general expectation is that in a uniform oxygen activity atmosphere, cation electrotransport induces a ternary or higher oxide, e.g., AB{sub 1+ξ}O{sub 3+δ}, to kinetically unmix unless the electrochemical mobilities of, say, A{sup 2+}and B{sup 4+} cations are identically equal, and eventually to decompose into the component oxides AO and BO{sub 2} once the extent of unmixing exceeds the stability range of its nonmolecularity ξ. It has, however, earlier been reported [Yoo et al., Appl. Phys. Lett. 92, 252103 (2008)] that even a massive cation electrotransport induces BaTiO{sub 3} to neither unmix nor decompose even at a voltage far exceedingmore » the so-called decomposition voltage U{sub d}, a measure of the standard formation free energy of the oxide (|ΔG{sub f}{sup o}| = nFU{sub d}). Here, we report that as expected, NiTiO{sub 3} unmixes at any voltage and even decomposes if the voltage applied exceeds seemingly a threshold value larger than U{sub d}. We demonstrate experimentally that the electrochemical mobilities of Ni{sup 2+} and Ti{sup 4+} should be necessarily unequal for unmixing. Also, we show theoretically that equal cation mobilities appear to be a sufficiency for BaTiO{sub 3} only for a thermodynamic reason.« less

Multi-objective based spectral unmixing for hyperspectral images

NASA Astrophysics Data System (ADS)

Xu, Xia; Shi, Zhenwei

2017-02-01

Sparse hyperspectral unmixing assumes that each observed pixel can be expressed by a linear combination of several pure spectra in a priori library. Sparse unmixing is challenging, since it is usually transformed to a NP-hard l0 norm based optimization problem. Existing methods usually utilize a relaxation to the original l0 norm. However, the relaxation may bring in sensitive weighted parameters and additional calculation error. In this paper, we propose a novel multi-objective based algorithm to solve the sparse unmixing problem without any relaxation. We transform sparse unmixing to a multi-objective optimization problem, which contains two correlative objectives: minimizing the reconstruction error and controlling the endmember sparsity. To improve the efficiency of multi-objective optimization, a population-based randomly flipping strategy is designed. Moreover, we theoretically prove that the proposed method is able to recover a guaranteed approximate solution from the spectral library within limited iterations. The proposed method can directly deal with l0 norm via binary coding for the spectral signatures in the library. Experiments on both synthetic and real hyperspectral datasets demonstrate the effectiveness of the proposed method.

Unsupervised method for automatic construction of a disease dictionary from a large free text collection.

PubMed

Xu, Rong; Supekar, Kaustubh; Morgan, Alex; Das, Amar; Garber, Alan

2008-11-06

Concept specific lexicons (e.g. diseases, drugs, anatomy) are a critical source of background knowledge for many medical language-processing systems. However, the rapid pace of biomedical research and the lack of constraints on usage ensure that such dictionaries are incomplete. Focusing on disease terminology, we have developed an automated, unsupervised, iterative pattern learning approach for constructing a comprehensive medical dictionary of disease terms from randomized clinical trial (RCT) abstracts, and we compared different ranking methods for automatically extracting con-textual patterns and concept terms. When used to identify disease concepts from 100 randomly chosen, manually annotated clinical abstracts, our disease dictionary shows significant performance improvement (F1 increased by 35-88%) over available, manually created disease terminologies.

Unsupervised Method for Automatic Construction of a Disease Dictionary from a Large Free Text Collection

PubMed Central

Xu, Rong; Supekar, Kaustubh; Morgan, Alex; Das, Amar; Garber, Alan

2008-01-01

Concept specific lexicons (e.g. diseases, drugs, anatomy) are a critical source of background knowledge for many medical language-processing systems. However, the rapid pace of biomedical research and the lack of constraints on usage ensure that such dictionaries are incomplete. Focusing on disease terminology, we have developed an automated, unsupervised, iterative pattern learning approach for constructing a comprehensive medical dictionary of disease terms from randomized clinical trial (RCT) abstracts, and we compared different ranking methods for automatically extracting contextual patterns and concept terms. When used to identify disease concepts from 100 randomly chosen, manually annotated clinical abstracts, our disease dictionary shows significant performance improvement (F1 increased by 35–88%) over available, manually created disease terminologies. PMID:18999169

Supervised nonlinear spectral unmixing using a postnonlinear mixing model for hyperspectral imagery.

PubMed

Altmann, Yoann; Halimi, Abderrahim; Dobigeon, Nicolas; Tourneret, Jean-Yves

2012-06-01

This paper presents a nonlinear mixing model for hyperspectral image unmixing. The proposed model assumes that the pixel reflectances are nonlinear functions of pure spectral components contaminated by an additive white Gaussian noise. These nonlinear functions are approximated using polynomial functions leading to a polynomial postnonlinear mixing model. A Bayesian algorithm and optimization methods are proposed to estimate the parameters involved in the model. The performance of the unmixing strategies is evaluated by simulations conducted on synthetic and real data.

A comparative evaluation of supervised and unsupervised representation learning approaches for anaplastic medulloblastoma differentiation

NASA Astrophysics Data System (ADS)

Cruz-Roa, Angel; Arevalo, John; Basavanhally, Ajay; Madabhushi, Anant; González, Fabio

2015-01-01

Learning data representations directly from the data itself is an approach that has shown great success in different pattern recognition problems, outperforming state-of-the-art feature extraction schemes for different tasks in computer vision, speech recognition and natural language processing. Representation learning applies unsupervised and supervised machine learning methods to large amounts of data to find building-blocks that better represent the information in it. Digitized histopathology images represents a very good testbed for representation learning since it involves large amounts of high complex, visual data. This paper presents a comparative evaluation of different supervised and unsupervised representation learning architectures to specifically address open questions on what type of learning architectures (deep or shallow), type of learning (unsupervised or supervised) is optimal. In this paper we limit ourselves to addressing these questions in the context of distinguishing between anaplastic and non-anaplastic medulloblastomas from routine haematoxylin and eosin stained images. The unsupervised approaches evaluated were sparse autoencoders and topographic reconstruct independent component analysis, and the supervised approach was convolutional neural networks. Experimental results show that shallow architectures with more neurons are better than deeper architectures without taking into account local space invariances and that topographic constraints provide useful invariant features in scale and rotations for efficient tumor differentiation.

Semi-supervised clustering for parcellating brain regions based on resting state fMRI data

NASA Astrophysics Data System (ADS)

Cheng, Hewei; Fan, Yong

2014-03-01

Many unsupervised clustering techniques have been adopted for parcellating brain regions of interest into functionally homogeneous subregions based on resting state fMRI data. However, the unsupervised clustering techniques are not able to take advantage of exiting knowledge of the functional neuroanatomy readily available from studies of cytoarchitectonic parcellation or meta-analysis of the literature. In this study, we propose a semi-supervised clustering method for parcellating amygdala into functionally homogeneous subregions based on resting state fMRI data. Particularly, the semi-supervised clustering is implemented under the framework of graph partitioning, and adopts prior information and spatial consistent constraints to obtain a spatially contiguous parcellation result. The graph partitioning problem is solved using an efficient algorithm similar to the well-known weighted kernel k-means algorithm. Our method has been validated for parcellating amygdala into 3 subregions based on resting state fMRI data of 28 subjects. The experiment results have demonstrated that the proposed method is more robust than unsupervised clustering and able to parcellate amygdala into centromedial, laterobasal, and superficial parts with improved functionally homogeneity compared with the cytoarchitectonic parcellation result. The validity of the parcellation results is also supported by distinctive functional and structural connectivity patterns of the subregions and high consistency between coactivation patterns derived from a meta-analysis and functional connectivity patterns of corresponding subregions.

Unmix 6.0 Model for environmental data analyses

EPA Pesticide Factsheets

Unmix Model is a mathematical receptor model developed by EPA scientists that provides scientific support for the development and review of the air and water quality standards, exposure research, and environmental forensics.

Target Transformation Constrained Sparse Unmixing (ttcsu) Algorithm for Retrieving Hydrous Minerals on Mars: Application to Southwest Melas Chasma

NASA Astrophysics Data System (ADS)

Lin, H.; Zhang, X.; Wu, X.; Tarnas, J. D.; Mustard, J. F.

2018-04-01

Quantitative analysis of hydrated minerals from hyperspectral remote sensing data is fundamental for understanding Martian geologic process. Because of the difficulties for selecting endmembers from hyperspectral images, a sparse unmixing algorithm has been proposed to be applied to CRISM data on Mars. However, it's challenge when the endmember library increases dramatically. Here, we proposed a new methodology termed Target Transformation Constrained Sparse Unmixing (TTCSU) to accurately detect hydrous minerals on Mars. A new version of target transformation technique proposed in our recent work was used to obtain the potential detections from CRISM data. Sparse unmixing constrained with these detections as prior information was applied to CRISM single-scattering albedo images, which were calculated using a Hapke radiative transfer model. This methodology increases success rate of the automatic endmember selection of sparse unmixing and could get more accurate abundances. CRISM images with well analyzed in Southwest Melas Chasma was used to validate our methodology in this study. The sulfates jarosite was detected from Southwest Melas Chasma, the distribution is consistent with previous work and the abundance is comparable. More validations will be done in our future work.

Unsupervised Pattern Classifier for Abnormality-Scaling of Vibration Features for Helicopter Gearbox Fault Diagnosis

NASA Technical Reports Server (NTRS)

Jammu, Vinay B.; Danai, Kourosh; Lewicki, David G.

1996-01-01

A new unsupervised pattern classifier is introduced for on-line detection of abnormality in features of vibration that are used for fault diagnosis of helicopter gearboxes. This classifier compares vibration features with their respective normal values and assigns them a value in (0, 1) to reflect their degree of abnormality. Therefore, the salient feature of this classifier is that it does not require feature values associated with faulty cases to identify abnormality. In order to cope with noise and changes in the operating conditions, an adaptation algorithm is incorporated that continually updates the normal values of the features. The proposed classifier is tested using experimental vibration features obtained from an OH-58A main rotor gearbox. The overall performance of this classifier is then evaluated by integrating the abnormality-scaled features for detection of faults. The fault detection results indicate that the performance of this classifier is comparable to the leading unsupervised neural networks: Kohonen's Feature Mapping and Adaptive Resonance Theory (AR72). This is significant considering that the independence of this classifier from fault-related features makes it uniquely suited to abnormality-scaling of vibration features for fault diagnosis.

EPA Unmix 6.0 Fundamentals & User Guide

EPA Pesticide Factsheets

Unmix seeks to solve the general mixture problem where the data are assumed to be a linear combination of an unknown number of sources of unknown composition, which contribute an unknown amount to each sample.

a Maximum Entropy Model of the Bearded Capuchin Monkey Habitat Incorporating Topography and Spectral Unmixing Analysis

NASA Astrophysics Data System (ADS)

Howard, A. M.; Bernardes, S.; Nibbelink, N.; Biondi, L.; Presotto, A.; Fragaszy, D. M.; Madden, M.

2012-07-01

Movement patterns of bearded capuchin monkeys (Cebus (Sapajus) libidinosus) in northeastern Brazil are likely impacted by environmental features such as elevation, vegetation density, or vegetation type. Habitat preferences of these monkeys provide insights regarding the impact of environmental features on species ecology and the degree to which they incorporate these features in movement decisions. In order to evaluate environmental features influencing movement patterns and predict areas suitable for movement, we employed a maximum entropy modelling approach, using observation points along capuchin monkey daily routes as species presence points. We combined these presence points with spatial data on important environmental features from remotely sensed data on land cover and topography. A spectral mixing analysis procedure was used to generate fraction images that represent green vegetation, shade and soil of the study area. A Landsat Thematic Mapper scene of the area of study was geometrically and atmospherically corrected and used as input in a Minimum Noise Fraction (MNF) procedure and a linear spectral unmixing approach was used to generate the fraction images. These fraction images and elevation were the environmental layer inputs for our logistic MaxEnt model of capuchin movement. Our models' predictive power (test AUC) was 0.775. Areas of high elevation (>450 m) showed low probabilities of presence, and percent green vegetation was the greatest overall contributor to model AUC. This work has implications for predicting daily movement patterns of capuchins in our field site, as suitability values from our model may relate to habitat preference and facility of movement.

Evolution patterns and parameter regimes in edge localized modes on the National Spherical Torus Experiment

DOE Data Explorer

Smith, D. R. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); Bell, R. E. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); Podesta, M. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); Smith, D. R. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); Fonck, R. J. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); McKee, G. R. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); Diallo, A. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); Kaye, S. M. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); LeBlanc, B. P. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States); Sabbagh, S. A. [Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)

2015-09-01

We implement unsupervised machine learning techniques to identify characteristic evolution patterns and associated parameter regimes in edge localized mode (ELM) events observed on the National Spherical Torus Experiment. Multi-channel, localized measurements spanning the pedestal region capture the complex evolution patterns of ELM events on Alfven timescales. Some ELM events are active for less than 100~microsec, but others persist for up to 1~ms. Also, some ELM events exhibit a single dominant perturbation, but others are oscillatory. Clustering calculations with time-series similarity metrics indicate the ELM database contains at least two and possibly three groups of ELMs with similar evolution patterns. The identified ELM groups trigger similar stored energy loss, but the groups occupy distinct parameter regimes for ELM-relevant quantities like plasma current, triangularity, and pedestal height. Notably, the pedestal electron pressure gradient is not an effective parameter for distinguishing the ELM groups, but the ELM groups segregate in terms of electron density gradient and electron temperature gradient. The ELM evolution patterns and corresponding parameter regimes can shape the formulation or validation of nonlinear ELM models. Finally, the techniques and results demonstrate an application of unsupervised machine learning at a data-rich fusion facility.

Unsupervised classification of Space Acceleration Measurement System (SAMS) data using ART2-A

NASA Technical Reports Server (NTRS)

Smith, A. D.; Sinha, A.

1999-01-01

The Space Acceleration Measurement System (SAMS) has been developed by NASA to monitor the microgravity acceleration environment aboard the space shuttle. The amount of data collected by a SAMS unit during a shuttle mission is in the several gigabytes range. Adaptive Resonance Theory 2-A (ART2-A), an unsupervised neural network, has been used to cluster these data and to develop cause and effect relationships among disturbances and the acceleration environment. Using input patterns formed on the basis of power spectral densities (psd), data collected from two missions, STS-050 and STS-057, have been clustered.

Multispectral and Panchromatic used Enhancement Resolution and Study Effective Enhancement on Supervised and Unsupervised Classification Land – Cover

NASA Astrophysics Data System (ADS)

Salman, S. S.; Abbas, W. A.

2018-05-01

The goal of the study is to support analysis Enhancement of Resolution and study effect on classification methods on bands spectral information of specific and quantitative approaches. In this study introduce a method to enhancement resolution Landsat 8 of combining the bands spectral of 30 meters resolution with panchromatic band 8 of 15 meters resolution, because of importance multispectral imagery to extracting land - cover. Classification methods used in this study to classify several lands -covers recorded from OLI- 8 imagery. Two methods of Data mining can be classified as either supervised or unsupervised. In supervised methods, there is a particular predefined target, that means the algorithm learn which values of the target are associated with which values of the predictor sample. K-nearest neighbors and maximum likelihood algorithms examine in this work as supervised methods. In other hand, no sample identified as target in unsupervised methods, the algorithm of data extraction searches for structure and patterns between all the variables, represented by Fuzzy C-mean clustering method as one of the unsupervised methods, NDVI vegetation index used to compare the results of classification method, the percent of dense vegetation in maximum likelihood method give a best results.

A novel edge-preserving nonnegative matrix factorization method for spectral unmixing

NASA Astrophysics Data System (ADS)

Bao, Wenxing; Ma, Ruishi

2015-12-01

Spectral unmixing technique is one of the key techniques to identify and classify the material in the hyperspectral image processing. A novel robust spectral unmixing method based on nonnegative matrix factorization(NMF) is presented in this paper. This paper used an edge-preserving function as hypersurface cost function to minimize the nonnegative matrix factorization. To minimize the hypersurface cost function, we constructed the updating functions for signature matrix of end-members and abundance fraction respectively. The two functions are updated alternatively. For evaluation purpose, synthetic data and real data have been used in this paper. Synthetic data is used based on end-members from USGS digital spectral library. AVIRIS Cuprite dataset have been used as real data. The spectral angle distance (SAD) and abundance angle distance(AAD) have been used in this research for assessment the performance of proposed method. The experimental results show that this method can obtain more ideal results and good accuracy for spectral unmixing than present methods.

A fast fully constrained geometric unmixing of hyperspectral images

NASA Astrophysics Data System (ADS)

Zhou, Xin; Li, Xiao-run; Cui, Jian-tao; Zhao, Liao-ying; Zheng, Jun-peng

2014-11-01

A great challenge in hyperspectral image analysis is decomposing a mixed pixel into a collection of endmembers and their corresponding abundance fractions. This paper presents an improved implementation of Barycentric Coordinate approach to unmix hyperspectral images, integrating with the Most-Negative Remove Projection method to meet the abundance sum-to-one constraint (ASC) and abundance non-negativity constraint (ANC). The original barycentric coordinate approach interprets the endmember unmixing problem as a simplex volume ratio problem, which is solved by calculate the determinants of two augmented matrix. One consists of all the members and the other consist of the to-be-unmixed pixel and all the endmembers except for the one corresponding to the specific abundance that is to be estimated. In this paper, we first modified the algorithm of Barycentric Coordinate approach by bringing in the Matrix Determinant Lemma to simplify the unmixing process, which makes the calculation only contains linear matrix and vector operations. So, the matrix determinant calculation of every pixel, as the original algorithm did, is avoided. By the end of this step, the estimated abundance meet the ASC constraint. Then, the Most-Negative Remove Projection method is used to make the abundance fractions meet the full constraints. This algorithm is demonstrated both on synthetic and real images. The resulting algorithm yields the abundance maps that are similar to those obtained by FCLS, while the runtime is outperformed as its computational simplicity.

Unsupervised Neural Network Quantifies the Cost of Visual Information Processing.

PubMed

Orbán, Levente L; Chartier, Sylvain

2015-01-01

Untrained, "flower-naïve" bumblebees display behavioural preferences when presented with visual properties such as colour, symmetry, spatial frequency and others. Two unsupervised neural networks were implemented to understand the extent to which these models capture elements of bumblebees' unlearned visual preferences towards flower-like visual properties. The computational models, which are variants of Independent Component Analysis and Feature-Extracting Bidirectional Associative Memory, use images of test-patterns that are identical to ones used in behavioural studies. Each model works by decomposing images of floral patterns into meaningful underlying factors. We reconstruct the original floral image using the components and compare the quality of the reconstructed image to the original image. Independent Component Analysis matches behavioural results substantially better across several visual properties. These results are interpreted to support a hypothesis that the temporal and energetic costs of information processing by pollinators served as a selective pressure on floral displays: flowers adapted to pollinators' cognitive constraints.

Unsupervised learning of temporal features for word categorization in a spiking neural network model of the auditory brain.

PubMed

Higgins, Irina; Stringer, Simon; Schnupp, Jan

2017-01-01

The nature of the code used in the auditory cortex to represent complex auditory stimuli, such as naturally spoken words, remains a matter of debate. Here we argue that such representations are encoded by stable spatio-temporal patterns of firing within cell assemblies known as polychronous groups, or PGs. We develop a physiologically grounded, unsupervised spiking neural network model of the auditory brain with local, biologically realistic, spike-time dependent plasticity (STDP) learning, and show that the plastic cortical layers of the network develop PGs which convey substantially more information about the speaker independent identity of two naturally spoken word stimuli than does rate encoding that ignores the precise spike timings. We furthermore demonstrate that such informative PGs can only develop if the input spatio-temporal spike patterns to the plastic cortical areas of the model are relatively stable.

Unsupervised learning of temporal features for word categorization in a spiking neural network model of the auditory brain

PubMed Central

Stringer, Simon

2017-01-01

The nature of the code used in the auditory cortex to represent complex auditory stimuli, such as naturally spoken words, remains a matter of debate. Here we argue that such representations are encoded by stable spatio-temporal patterns of firing within cell assemblies known as polychronous groups, or PGs. We develop a physiologically grounded, unsupervised spiking neural network model of the auditory brain with local, biologically realistic, spike-time dependent plasticity (STDP) learning, and show that the plastic cortical layers of the network develop PGs which convey substantially more information about the speaker independent identity of two naturally spoken word stimuli than does rate encoding that ignores the precise spike timings. We furthermore demonstrate that such informative PGs can only develop if the input spatio-temporal spike patterns to the plastic cortical areas of the model are relatively stable. PMID:28797034

Gastric cancer differentiation using Fourier transform near-infrared spectroscopy with unsupervised pattern recognition

NASA Astrophysics Data System (ADS)

Yi, Wei-song; Cui, Dian-sheng; Li, Zhi; Wu, Lan-lan; Shen, Ai-guo; Hu, Ji-ming

2013-01-01

The manuscript has investigated the application of near-infrared (NIR) spectroscopy for differentiation gastric cancer. The 90 spectra from cancerous and normal tissues were collected from a total of 30 surgical specimens using Fourier transform near-infrared spectroscopy (FT-NIR) equipped with a fiber-optic probe. Major spectral differences were observed in the CH-stretching second overtone (9000-7000 cm-1), CH-stretching first overtone (6000-5200 cm-1), and CH-stretching combination (4500-4000 cm-1) regions. By use of unsupervised pattern recognition, such as principal component analysis (PCA) and cluster analysis (CA), all spectra were classified into cancerous and normal tissue groups with accuracy up to 81.1%. The sensitivity and specificity was 100% and 68.2%, respectively. These present results indicate that CH-stretching first, combination band and second overtone regions can serve as diagnostic markers for gastric cancer.

Applying spectral unmixing and support vector machine to airborne hyperspectral imagery for detecting giant reed

USDA-ARS?s Scientific Manuscript database

This study evaluated linear spectral unmixing (LSU), mixture tuned matched filtering (MTMF) and support vector machine (SVM) techniques for detecting and mapping giant reed (Arundo donax L.), an invasive weed that presents a severe threat to agroecosystems and riparian areas throughout the southern ...

SOURCE APPORTIONMENT OF PHOENIX PM2.5 AEROSOL WITH THE UNMIX RECEPTOR MODEL

EPA Science Inventory

The multivariate receptor model Unmix has been used to analyze a 3-yr PM2.5 ambient aerosol data set collected in Phoenix, AZ, beginning in 1995. The analysis generated source profiles and overall percentage source contribution estimates (SCE) for five source categories: ga...

Application of unsupervised pattern recognition approaches for exploration of rare earth elements in Se-Chahun iron ore, central Iran

NASA Astrophysics Data System (ADS)

Sarparandeh, Mohammadali; Hezarkhani, Ardeshir

2017-12-01

The use of efficient methods for data processing has always been of interest to researchers in the field of earth sciences. Pattern recognition techniques are appropriate methods for high-dimensional data such as geochemical data. Evaluation of the geochemical distribution of rare earth elements (REEs) requires the use of such methods. In particular, the multivariate nature of REE data makes them a good target for numerical analysis. The main subject of this paper is application of unsupervised pattern recognition approaches in evaluating geochemical distribution of REEs in the Kiruna type magnetite-apatite deposit of Se-Chahun. For this purpose, 42 bulk lithology samples were collected from the Se-Chahun iron ore deposit. In this study, 14 rare earth elements were measured with inductively coupled plasma mass spectrometry (ICP-MS). Pattern recognition makes it possible to evaluate the relations between the samples based on all these 14 features, simultaneously. In addition to providing easy solutions, discovery of the hidden information and relations of data samples is the advantage of these methods. Therefore, four clustering methods (unsupervised pattern recognition) - including a modified basic sequential algorithmic scheme (MBSAS), hierarchical (agglomerative) clustering, k-means clustering and self-organizing map (SOM) - were applied and results were evaluated using the silhouette criterion. Samples were clustered in four types. Finally, the results of this study were validated with geological facts and analysis results from, for example, scanning electron microscopy (SEM), X-ray diffraction (XRD), ICP-MS and optical mineralogy. The results of the k-means clustering and SOM methods have the best matches with reality, with experimental studies of samples and with field surveys. Since only the rare earth elements are used in this division, a good agreement of the results with lithology is considerable. It is concluded that the combination of the proposed methods and geological studies leads to finding some hidden information, and this approach has the best results compared to using only one of them.

Memristive neural network for on-line learning and tracking with brain-inspired spike timing dependent plasticity.

PubMed

Pedretti, G; Milo, V; Ambrogio, S; Carboni, R; Bianchi, S; Calderoni, A; Ramaswamy, N; Spinelli, A S; Ielmini, D

2017-07-13

Brain-inspired computation can revolutionize information technology by introducing machines capable of recognizing patterns (images, speech, video) and interacting with the external world in a cognitive, humanlike way. Achieving this goal requires first to gain a detailed understanding of the brain operation, and second to identify a scalable microelectronic technology capable of reproducing some of the inherent functions of the human brain, such as the high synaptic connectivity (~10 4 ) and the peculiar time-dependent synaptic plasticity. Here we demonstrate unsupervised learning and tracking in a spiking neural network with memristive synapses, where synaptic weights are updated via brain-inspired spike timing dependent plasticity (STDP). The synaptic conductance is updated by the local time-dependent superposition of pre- and post-synaptic spikes within a hybrid one-transistor/one-resistor (1T1R) memristive synapse. Only 2 synaptic states, namely the low resistance state (LRS) and the high resistance state (HRS), are sufficient to learn and recognize patterns. Unsupervised learning of a static pattern and tracking of a dynamic pattern of up to 4 × 4 pixels are demonstrated, paving the way for intelligent hardware technology with up-scaled memristive neural networks.

Unsupervised EEG analysis for automated epileptic seizure detection

NASA Astrophysics Data System (ADS)

Birjandtalab, Javad; Pouyan, Maziyar Baran; Nourani, Mehrdad

2016-07-01

Epilepsy is a neurological disorder which can, if not controlled, potentially cause unexpected death. It is extremely crucial to have accurate automatic pattern recognition and data mining techniques to detect the onset of seizures and inform care-givers to help the patients. EEG signals are the preferred biosignals for diagnosis of epileptic patients. Most of the existing pattern recognition techniques used in EEG analysis leverage the notion of supervised machine learning algorithms. Since seizure data are heavily under-represented, such techniques are not always practical particularly when the labeled data is not sufficiently available or when disease progression is rapid and the corresponding EEG footprint pattern will not be robust. Furthermore, EEG pattern change is highly individual dependent and requires experienced specialists to annotate the seizure and non-seizure events. In this work, we present an unsupervised technique to discriminate seizures and non-seizures events. We employ power spectral density of EEG signals in different frequency bands that are informative features to accurately cluster seizure and non-seizure events. The experimental results tried so far indicate achieving more than 90% accuracy in clustering seizure and non-seizure events without having any prior knowledge on patient's history.

A parallelized binary search tree

USDA-ARS?s Scientific Manuscript database

PTTRNFNDR is an unsupervised statistical learning algorithm that detects patterns in DNA sequences, protein sequences, or any natural language texts that can be decomposed into letters of a finite alphabet. PTTRNFNDR performs complex mathematical computations and its processing time increases when i...

Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications

PubMed Central

Chang, Hang; Han, Ju; Zhong, Cheng; Snijders, Antoine M.; Mao, Jian-Hua

2017-01-01

The capabilities of (I) learning transferable knowledge across domains; and (II) fine-tuning the pre-learned base knowledge towards tasks with considerably smaller data scale are extremely important. Many of the existing transfer learning techniques are supervised approaches, among which deep learning has the demonstrated power of learning domain transferrable knowledge with large scale network trained on massive amounts of labeled data. However, in many biomedical tasks, both the data and the corresponding label can be very limited, where the unsupervised transfer learning capability is urgently needed. In this paper, we proposed a novel multi-scale convolutional sparse coding (MSCSC) method, that (I) automatically learns filter banks at different scales in a joint fashion with enforced scale-specificity of learned patterns; and (II) provides an unsupervised solution for learning transferable base knowledge and fine-tuning it towards target tasks. Extensive experimental evaluation of MSCSC demonstrates the effectiveness of the proposed MSCSC in both regular and transfer learning tasks in various biomedical domains. PMID:28129148

Encoding Strategy Changes and Spacing Effects in the Free Recall of Unmixed Lists

ERIC Educational Resources Information Center

Delaney, P.F.; Knowles, M.E.

2005-01-01

Memory for repeated items often improves when repetitions are separated by other items-a phenomenon called the spacing effect. In two experiments, we explored the complex interaction between study strategies, serial position, and spacing effects. When people studied several unmixed lists, they initially used mainly rote rehearsal, but some people…

Nonlinear hyperspectral unmixing based on sparse non-negative matrix factorization

NASA Astrophysics Data System (ADS)

Li, Jing; Li, Xiaorun; Zhao, Liaoying

2016-01-01

Hyperspectral unmixing aims at extracting pure material spectra, accompanied by their corresponding proportions, from a mixed pixel. Owing to modeling more accurate distribution of real material, nonlinear mixing models (non-LMM) are usually considered to hold better performance than LMMs in complicated scenarios. In the past years, numerous nonlinear models have been successfully applied to hyperspectral unmixing. However, most non-LMMs only think of sum-to-one constraint or positivity constraint while the widespread sparsity among real materials mixing is the very factor that cannot be ignored. That is, for non-LMMs, a pixel is usually composed of a few spectral signatures of different materials from all the pure pixel set. Thus, in this paper, a smooth sparsity constraint is incorporated into the state-of-the-art Fan nonlinear model to exploit the sparsity feature in nonlinear model and use it to enhance the unmixing performance. This sparsity-constrained Fan model is solved with the non-negative matrix factorization. The algorithm was implemented on synthetic and real hyperspectral data and presented its advantage over those competing algorithms in the experiments.

System Biology Approach: Gene Network Analysis for Muscular Dystrophy.

PubMed

Censi, Federica; Calcagnini, Giovanni; Mattei, Eugenio; Giuliani, Alessandro

2018-01-01

Phenotypic changes at different organization levels from cell to entire organism are associated to changes in the pattern of gene expression. These changes involve the entire genome expression pattern and heavily rely upon correlation patterns among genes. The classical approach used to analyze gene expression data builds upon the application of supervised statistical techniques to detect genes differentially expressed among two or more phenotypes (e.g., normal vs. disease). The use of an a posteriori, unsupervised approach based on principal component analysis (PCA) and the subsequent construction of gene correlation networks can shed a light on unexpected behaviour of gene regulation system while maintaining a more naturalistic view on the studied system.In this chapter we applied an unsupervised method to discriminate DMD patient and controls. The genes having the highest absolute scores in the discrimination between the groups were then analyzed in terms of gene expression networks, on the basis of their mutual correlation in the two groups. The correlation network structures suggest two different modes of gene regulation in the two groups, reminiscent of important aspects of DMD pathogenesis.

Multiphoton spectral analysis of benzo[a]pyrene uptake and metabolism in a rat liver cell line

DOE Office of Scientific and Technical Information (OSTI.GOV)

Barhoumi, Rola, E-mail: rmouneimne@cvm.tamu.edu; Mouneimne, Youssef; Ramos, Ernesto

2011-05-15

Dynamic analysis of the uptake and metabolism of polycyclic aromatic hydrocarbons (PAHs) and their metabolites within live cells in real time has the potential to provide novel insights into genotoxic and non-genotoxic mechanisms of cellular injury caused by PAHs. The present work, combining the use of metabolite spectra generated from metabolite standards using multiphoton spectral analysis and an 'advanced unmixing process', identifies and quantifies the uptake, partitioning, and metabolite formation of one of the most important PAHs (benzo[a]pyrene, BaP) in viable cultured rat liver cells over a period of 24 h. The application of the advanced unmixing process resulted inmore » the simultaneous identification of 8 metabolites in live cells at any single time. The accuracy of this unmixing process was verified using specific microsomal epoxide hydrolase inhibitors, glucuronidation and sulfation inhibitors as well as several mixtures of metabolite standards. Our findings prove that the two-photon microscopy imaging surpasses the conventional fluorescence imaging techniques and the unmixing process is a mathematical technique that seems applicable to the analysis of BaP metabolites in living cells especially for analysis of changes of the ultimate carcinogen benzo[a]pyrene-r-7,t-8-dihydrodiol-t-9,10-epoxide. Therefore, the combination of the two-photon acquisition with the unmixing process should provide important insights into the cellular and molecular mechanisms by which BaP and other PAHs alter cellular homeostasis.« less

Generating High-Temporal and Spatial Resolution TIR Image Data

NASA Astrophysics Data System (ADS)

Herrero-Huerta, M.; Lagüela, S.; Alfieri, S. M.; Menenti, M.

2017-09-01

Remote sensing imagery to monitor global biophysical dynamics requires the availability of thermal infrared data at high temporal and spatial resolution because of the rapid development of crops during the growing season and the fragmentation of most agricultural landscapes. Conversely, no single sensor meets these combined requirements. Data fusion approaches offer an alternative to exploit observations from multiple sensors, providing data sets with better properties. A novel spatio-temporal data fusion model based on constrained algorithms denoted as multisensor multiresolution technique (MMT) was developed and applied to generate TIR synthetic image data at both temporal and spatial high resolution. Firstly, an adaptive radiance model is applied based on spectral unmixing analysis of . TIR radiance data at TOA (top of atmosphere) collected by MODIS daily 1-km and Landsat - TIRS 16-day sampled at 30-m resolution are used to generate synthetic daily radiance images at TOA at 30-m spatial resolution. The next step consists of unmixing the 30 m (now lower resolution) images using the information about their pixel land-cover composition from co-registered images at higher spatial resolution. In our case study, TIR synthesized data were unmixed to the Sentinel 2 MSI with 10 m resolution. The constrained unmixing preserves all the available radiometric information of the 30 m images and involves the optimization of the number of land-cover classes and the size of the moving window for spatial unmixing. Results are still being evaluated, with particular attention for the quality of the data streams required to apply our approach.

Comparing Different Approaches for Mapping Urban Vegetation Cover from Landsat ETM+ Data: A Case Study on Brussels

PubMed Central

Van de Voorde, Tim; Vlaeminck, Jeroen; Canters, Frank

2008-01-01

Urban growth and its related environmental problems call for sustainable urban management policies to safeguard the quality of urban environments. Vegetation plays an important part in this as it provides ecological, social, health and economic benefits to a city's inhabitants. Remotely sensed data are of great value to monitor urban green and despite the clear advantages of contemporary high resolution images, the benefits of medium resolution data should not be discarded. The objective of this research was to estimate fractional vegetation cover from a Landsat ETM+ image with sub-pixel classification, and to compare accuracies obtained with multiple stepwise regression analysis, linear spectral unmixing and multi-layer perceptrons (MLP) at the level of meaningful urban spatial entities. Despite the small, but nevertheless statistically significant differences at pixel level between the alternative approaches, the spatial pattern of vegetation cover and estimation errors is clearly distinctive at neighbourhood level. At this spatially aggregated level, a simple regression model appears to attain sufficient accuracy. For mapping at a spatially more detailed level, the MLP seems to be the most appropriate choice. Brightness normalisation only appeared to affect the linear models, especially the linear spectral unmixing. PMID:27879914

Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity.

PubMed

Bichler, Olivier; Querlioz, Damien; Thorpe, Simon J; Bourgoin, Jean-Philippe; Gamrat, Christian

2012-08-01

A biologically inspired approach to learning temporally correlated patterns from a spiking silicon retina is presented. Spikes are generated from the retina in response to relative changes in illumination at the pixel level and transmitted to a feed-forward spiking neural network. Neurons become sensitive to patterns of pixels with correlated activation times, in a fully unsupervised scheme. This is achieved using a special form of Spike-Timing-Dependent Plasticity which depresses synapses that did not recently contribute to the post-synaptic spike activation, regardless of their activation time. Competitive learning is implemented with lateral inhibition. When tested with real-life data, the system is able to extract complex and overlapping temporally correlated features such as car trajectories on a freeway, after only 10 min of traffic learning. Complete trajectories can be learned with a 98% detection rate using a second layer, still with unsupervised learning, and the system may be used as a car counter. The proposed neural network is extremely robust to noise and it can tolerate a high degree of synaptic and neuronal variability with little impact on performance. Such results show that a simple biologically inspired unsupervised learning scheme is capable of generating selectivity to complex meaningful events on the basis of relatively little sensory experience. Copyright © 2012 Elsevier Ltd. All rights reserved.

Visualization and unsupervised predictive clustering of high-dimensional multimodal neuroimaging data.

PubMed

Mwangi, Benson; Soares, Jair C; Hasan, Khader M

2014-10-30

Neuroimaging machine learning studies have largely utilized supervised algorithms - meaning they require both neuroimaging scan data and corresponding target variables (e.g. healthy vs. diseased) to be successfully 'trained' for a prediction task. Noticeably, this approach may not be optimal or possible when the global structure of the data is not well known and the researcher does not have an a priori model to fit the data. We set out to investigate the utility of an unsupervised machine learning technique; t-distributed stochastic neighbour embedding (t-SNE) in identifying 'unseen' sample population patterns that may exist in high-dimensional neuroimaging data. Multimodal neuroimaging scans from 92 healthy subjects were pre-processed using atlas-based methods, integrated and input into the t-SNE algorithm. Patterns and clusters discovered by the algorithm were visualized using a 2D scatter plot and further analyzed using the K-means clustering algorithm. t-SNE was evaluated against classical principal component analysis. Remarkably, based on unlabelled multimodal scan data, t-SNE separated study subjects into two very distinct clusters which corresponded to subjects' gender labels (cluster silhouette index value=0.79). The resulting clusters were used to develop an unsupervised minimum distance clustering model which identified 93.5% of subjects' gender. Notably, from a neuropsychiatric perspective this method may allow discovery of data-driven disease phenotypes or sub-types of treatment responders. Copyright © 2014 Elsevier B.V. All rights reserved.

Commodity cluster and hardware-based massively parallel implementations of hyperspectral imaging algorithms

NASA Astrophysics Data System (ADS)

Plaza, Antonio; Chang, Chein-I.; Plaza, Javier; Valencia, David

2006-05-01

The incorporation of hyperspectral sensors aboard airborne/satellite platforms is currently producing a nearly continual stream of multidimensional image data, and this high data volume has soon introduced new processing challenges. The price paid for the wealth spatial and spectral information available from hyperspectral sensors is the enormous amounts of data that they generate. Several applications exist, however, where having the desired information calculated quickly enough for practical use is highly desirable. High computing performance of algorithm analysis is particularly important in homeland defense and security applications, in which swift decisions often involve detection of (sub-pixel) military targets (including hostile weaponry, camouflage, concealment, and decoys) or chemical/biological agents. In order to speed-up computational performance of hyperspectral imaging algorithms, this paper develops several fast parallel data processing techniques. Techniques include four classes of algorithms: (1) unsupervised classification, (2) spectral unmixing, and (3) automatic target recognition, and (4) onboard data compression. A massively parallel Beowulf cluster (Thunderhead) at NASA's Goddard Space Flight Center in Maryland is used to measure parallel performance of the proposed algorithms. In order to explore the viability of developing onboard, real-time hyperspectral data compression algorithms, a Xilinx Virtex-II field programmable gate array (FPGA) is also used in experiments. Our quantitative and comparative assessment of parallel techniques and strategies may help image analysts in selection of parallel hyperspectral algorithms for specific applications.

M-estimation for robust sparse unmixing of hyperspectral images

NASA Astrophysics Data System (ADS)

Toomik, Maria; Lu, Shijian; Nelson, James D. B.

2016-10-01

Hyperspectral unmixing methods often use a conventional least squares based lasso which assumes that the data follows the Gaussian distribution. The normality assumption is an approximation which is generally invalid for real imagery data. We consider a robust (non-Gaussian) approach to sparse spectral unmixing of remotely sensed imagery which reduces the sensitivity of the estimator to outliers and relaxes the linearity assumption. The method consists of several appropriate penalties. We propose to use an lp norm with 0 < p < 1 in the sparse regression problem, which induces more sparsity in the results, but makes the problem non-convex. On the other hand, the problem, though non-convex, can be solved quite straightforwardly with an extensible algorithm based on iteratively reweighted least squares. To deal with the huge size of modern spectral libraries we introduce a library reduction step, similar to the multiple signal classification (MUSIC) array processing algorithm, which not only speeds up unmixing but also yields superior results. In the hyperspectral setting we extend the traditional least squares method to the robust heavy-tailed case and propose a generalised M-lasso solution. M-estimation replaces the Gaussian likelihood with a fixed function ρ(e) that restrains outliers. The M-estimate function reduces the effect of errors with large amplitudes or even assigns the outliers zero weights. Our experimental results on real hyperspectral data show that noise with large amplitudes (outliers) often exists in the data. This ability to mitigate the influence of such outliers can therefore offer greater robustness. Qualitative hyperspectral unmixing results on real hyperspectral image data corroborate the efficacy of the proposed method.

Unmixing the SNCs: Chemical, Isotopic, and Petrologic Components of the Martian Meteorites

NASA Technical Reports Server (NTRS)

2002-01-01

This volume contains abstracts that have been accepted for presentation at the conference on Unmixing the SNCs: Chemical, Isotopic, and Petrologic Components of Martian Meteorites, September 11-12, 2002, in Houston, Texas. Administration and publications support for this meeting were provided by the staff of the Publications and Program Services Department at the Lunar and Planetary Institute.

Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data.

PubMed

Lasko, Thomas A; Denny, Joshua C; Levy, Mia A

2013-01-01

Inferring precise phenotypic patterns from population-scale clinical data is a core computational task in the development of precision, personalized medicine. The traditional approach uses supervised learning, in which an expert designates which patterns to look for (by specifying the learning task and the class labels), and where to look for them (by specifying the input variables). While appropriate for individual tasks, this approach scales poorly and misses the patterns that we don't think to look for. Unsupervised feature learning overcomes these limitations by identifying patterns (or features) that collectively form a compact and expressive representation of the source data, with no need for expert input or labeled examples. Its rising popularity is driven by new deep learning methods, which have produced high-profile successes on difficult standardized problems of object recognition in images. Here we introduce its use for phenotype discovery in clinical data. This use is challenging because the largest source of clinical data - Electronic Medical Records - typically contains noisy, sparse, and irregularly timed observations, rendering them poor substrates for deep learning methods. Our approach couples dirty clinical data to deep learning architecture via longitudinal probability densities inferred using Gaussian process regression. From episodic, longitudinal sequences of serum uric acid measurements in 4368 individuals we produced continuous phenotypic features that suggest multiple population subtypes, and that accurately distinguished (0.97 AUC) the uric-acid signatures of gout vs. acute leukemia despite not being optimized for the task. The unsupervised features were as accurate as gold-standard features engineered by an expert with complete knowledge of the domain, the classification task, and the class labels. Our findings demonstrate the potential for achieving computational phenotype discovery at population scale. We expect such data-driven phenotypes to expose unknown disease variants and subtypes and to provide rich targets for genetic association studies.

Computational Phenotype Discovery Using Unsupervised Feature Learning over Noisy, Sparse, and Irregular Clinical Data

PubMed Central

Lasko, Thomas A.; Denny, Joshua C.; Levy, Mia A.

2013-01-01

Inferring precise phenotypic patterns from population-scale clinical data is a core computational task in the development of precision, personalized medicine. The traditional approach uses supervised learning, in which an expert designates which patterns to look for (by specifying the learning task and the class labels), and where to look for them (by specifying the input variables). While appropriate for individual tasks, this approach scales poorly and misses the patterns that we don’t think to look for. Unsupervised feature learning overcomes these limitations by identifying patterns (or features) that collectively form a compact and expressive representation of the source data, with no need for expert input or labeled examples. Its rising popularity is driven by new deep learning methods, which have produced high-profile successes on difficult standardized problems of object recognition in images. Here we introduce its use for phenotype discovery in clinical data. This use is challenging because the largest source of clinical data – Electronic Medical Records – typically contains noisy, sparse, and irregularly timed observations, rendering them poor substrates for deep learning methods. Our approach couples dirty clinical data to deep learning architecture via longitudinal probability densities inferred using Gaussian process regression. From episodic, longitudinal sequences of serum uric acid measurements in 4368 individuals we produced continuous phenotypic features that suggest multiple population subtypes, and that accurately distinguished (0.97 AUC) the uric-acid signatures of gout vs. acute leukemia despite not being optimized for the task. The unsupervised features were as accurate as gold-standard features engineered by an expert with complete knowledge of the domain, the classification task, and the class labels. Our findings demonstrate the potential for achieving computational phenotype discovery at population scale. We expect such data-driven phenotypes to expose unknown disease variants and subtypes and to provide rich targets for genetic association studies. PMID:23826094

Spectral unmixing of hyperspectral data to map bauxite deposits

NASA Astrophysics Data System (ADS)

Shanmugam, Sanjeevi; Abhishekh, P. V.

2006-12-01

This paper presents a study about the potential of remote sensing in bauxite exploration in the Kolli hills of Tamilnadu state, southern India. ASTER image (acquired in the VNIR and SWIR regions) has been used in conjunction with SRTM - DEM in this study. A new approach of spectral unmixing of ASTER image data delineated areas rich in alumina. Various geological and geomorphological parameters that control bauxite formation were also derived from the ASTER image. All these information, when integrated, showed that there are 16 cappings (including the existing mines) that satisfy most of the conditions favouring bauxitization in the Kolli Hills. The study concludes that spectral unmixing of hyperspectral satellite data in the VNIR and SWIR regions may be combined with the terrain parameters to get accurate information about bauxite deposits, including their quality.

Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns

PubMed Central

Matsubara, Takashi

2017-01-01

Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning. PMID:29209191

Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns.

PubMed

Matsubara, Takashi

2017-01-01

Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning.

Unsupervised classification of variable stars

NASA Astrophysics Data System (ADS)

Valenzuela, Lucas; Pichara, Karim

2018-03-01

During the past 10 years, a considerable amount of effort has been made to develop algorithms for automatic classification of variable stars. That has been primarily achieved by applying machine learning methods to photometric data sets where objects are represented as light curves. Classifiers require training sets to learn the underlying patterns that allow the separation among classes. Unfortunately, building training sets is an expensive process that demands a lot of human efforts. Every time data come from new surveys; the only available training instances are the ones that have a cross-match with previously labelled objects, consequently generating insufficient training sets compared with the large amounts of unlabelled sources. In this work, we present an algorithm that performs unsupervised classification of variable stars, relying only on the similarity among light curves. We tackle the unsupervised classification problem by proposing an untraditional approach. Instead of trying to match classes of stars with clusters found by a clustering algorithm, we propose a query-based method where astronomers can find groups of variable stars ranked by similarity. We also develop a fast similarity function specific for light curves, based on a novel data structure that allows scaling the search over the entire data set of unlabelled objects. Experiments show that our unsupervised model achieves high accuracy in the classification of different types of variable stars and that the proposed algorithm scales up to massive amounts of light curves.

Wavelet-based unsupervised learning method for electrocardiogram suppression in surface electromyograms.

PubMed

Niegowski, Maciej; Zivanovic, Miroslav

2016-03-01

We present a novel approach aimed at removing electrocardiogram (ECG) perturbation from single-channel surface electromyogram (EMG) recordings by means of unsupervised learning of wavelet-based intensity images. The general idea is to combine the suitability of certain wavelet decomposition bases which provide sparse electrocardiogram time-frequency representations, with the capacity of non-negative matrix factorization (NMF) for extracting patterns from images. In order to overcome convergence problems which often arise in NMF-related applications, we design a novel robust initialization strategy which ensures proper signal decomposition in a wide range of ECG contamination levels. Moreover, the method can be readily used because no a priori knowledge or parameter adjustment is needed. The proposed method was evaluated on real surface EMG signals against two state-of-the-art unsupervised learning algorithms and a singular spectrum analysis based method. The results, expressed in terms of high-to-low energy ratio, normalized median frequency, spectral power difference and normalized average rectified value, suggest that the proposed method enables better ECG-EMG separation quality than the reference methods. Copyright © 2015 IPEM. Published by Elsevier Ltd. All rights reserved.

Comparisons of a Constrained Least Squares Model versus Human-in-the-Loop for Spectral Unmixing to Determine Material Type of GEO Debris

NASA Technical Reports Server (NTRS)

Abercromby, Kira J.; Rapp, Jason; Bedard, Donald; Seitzer, Patrick; Cardona, Tommaso; Cowardin, Heather; Barker, Ed; Lederer, Susan

2013-01-01

Constrained Linear Least Squares model is generally more accurate than the "human-in-the-loop". However, "human-in-the-loop" can remove materials that make no sense. The speed of the model in determining a "first cut" at the material ID makes it a viable option for spectral unmixing of debris objects.

Classifying seismic noise and sources from OBS data using unsupervised machine learning

NASA Astrophysics Data System (ADS)

Mosher, S. G.; Audet, P.

2017-12-01

The paradigm of plate tectonics was established mainly by recognizing the central role of oceanic plates in the production and destruction of tectonic plates at their boundaries. Since that realization, however, seismic studies of tectonic plates and their associated deformation have slowly shifted their attention toward continental plates due to the ease of installation and maintenance of high-quality seismic networks on land. The result has been a much more detailed understanding of the seismicity patterns associated with continental plate deformation in comparison with the low-magnitude deformation patterns within oceanic plates and at their boundaries. While the number of high-quality ocean-bottom seismometer (OBS) deployments within the past decade has demonstrated the potential to significantly increase our understanding of tectonic systems in oceanic settings, OBS data poses significant challenges to many of the traditional data processing techniques in seismology. In particular, problems involving the detection, location, and classification of seismic sources occurring within oceanic settings are much more difficult due to the extremely noisy seafloor environment in which data are recorded. However, classifying data without a priori constraints is a problem that is routinely pursued via unsupervised machine learning algorithms, which remain robust even in cases involving complicated datasets. In this research, we apply simple unsupervised machine learning algorithms (e.g., clustering) to OBS data from the Cascadia Initiative in an attempt to classify and detect a broad range of seismic sources, including various noise sources and tremor signals occurring within ocean settings.

[Source apportionment of soil heavy metals in Jiapigou goldmine based on the UNMIX model].

PubMed

Ai, Jian-chao; Wang, Ning; Yang, Jing

2014-09-01

The paper determines 16 kinds of metal elements' concentration in soil samples which collected in Jipigou goldmine upper the Songhua River. The UNMIX Model which was recommended by US EPA to get the source apportionment results was applied in this study, Cd, Hg, Pb and Ag concentration contour maps were generated by using Kriging interpolation method to verify the results. The main conclusions of this study are: (1)the concentrations of Cd, Hg, Pb and Ag exceeded Jilin Province soil background values and enriched obviously in soil samples; (2)using the UNMIX Model resolved four pollution sources: source 1 represents human activities of transportation, ore mining and garbage, and the source 1's contribution is 39. 1% ; Source 2 represents the contribution of the weathering of rocks and biological effects, and the source 2's contribution is 13. 87% ; Source 3 is a comprehensive source of soil parent material and chemical fertilizer, and the source 3's contribution is 23. 93% ; Source 4 represents iron ore mining and transportation sources, and the source 4's contribution is 22. 89%. (3)the UNMIX Model results are in accordance with the survey of local land-use types, human activities and Cd, Hg and Pb content distributions.

Quadratic Blind Linear Unmixing: A Graphical User Interface for Tissue Characterization

PubMed Central

Gutierrez-Navarro, O.; Campos-Delgado, D.U.; Arce-Santana, E. R.; Jo, Javier A.

2016-01-01

Spectral unmixing is the process of breaking down data from a sample into its basic components and their abundances. Previous work has been focused on blind unmixing of multi-spectral fluorescence lifetime imaging microscopy (m-FLIM) datasets under a linear mixture model and quadratic approximations. This method provides a fast linear decomposition and can work without a limitation in the maximum number of components or end-members. Hence this work presents an interactive software which implements our blind end-member and abundance extraction (BEAE) and quadratic blind linear unmixing (QBLU) algorithms in Matlab. The options and capabilities of our proposed software are described in detail. When the number of components is known, our software can estimate the constitutive end-members and their abundances. When no prior knowledge is available, the software can provide a completely blind solution to estimate the number of components, the end-members and their abundances. The characterization of three case studies validates the performance of the new software: ex-vivo human coronary arteries, human breast cancer cell samples, and in-vivo hamster oral mucosa. The software is freely available in a hosted webpage by one of the developing institutions, and allows the user a quick, easy-to-use and efficient tool for multi/hyper-spectral data decomposition. PMID:26589467

Snow depth and snow cover retrieval from FengYun3B microwave radiation imagery based on a snow passive microwave unmixing method in Northeast China

NASA Astrophysics Data System (ADS)

Gu, Lingjia; Ren, Ruizhi; Zhao, Kai; Li, Xiaofeng

2014-01-01

The precision of snow parameter retrieval is unsatisfactory for current practical demands. The primary reason is because of the problem of mixed pixels that are caused by low spatial resolution of satellite passive microwave data. A snow passive microwave unmixing method is proposed in this paper, based on land cover type data and the antenna gain function of passive microwaves. The land cover type of Northeast China is partitioned into grass, farmland, bare soil, forest, and water body types. The component brightness temperatures (CBT), namely unmixed data, with 1 km data resolution are obtained using the proposed unmixing method. The snow depth determined by the CBT and three snow depth retrieval algorithms are validated through field measurements taken in forest and farmland areas of Northeast China in January 2012 and 2013. The results show that the overall of the retrieval precision of the snow depth is improved by 17% in farmland areas and 10% in forest areas when using the CBT in comparison with the mixed pixels. The snow cover results based on the CBT are compared with existing MODIS snow cover products. The results demonstrate that more snow cover information can be obtained with up to 86% accuracy.

Quadratic blind linear unmixing: A graphical user interface for tissue characterization.

PubMed

Gutierrez-Navarro, O; Campos-Delgado, D U; Arce-Santana, E R; Jo, Javier A

2016-02-01

Spectral unmixing is the process of breaking down data from a sample into its basic components and their abundances. Previous work has been focused on blind unmixing of multi-spectral fluorescence lifetime imaging microscopy (m-FLIM) datasets under a linear mixture model and quadratic approximations. This method provides a fast linear decomposition and can work without a limitation in the maximum number of components or end-members. Hence this work presents an interactive software which implements our blind end-member and abundance extraction (BEAE) and quadratic blind linear unmixing (QBLU) algorithms in Matlab. The options and capabilities of our proposed software are described in detail. When the number of components is known, our software can estimate the constitutive end-members and their abundances. When no prior knowledge is available, the software can provide a completely blind solution to estimate the number of components, the end-members and their abundances. The characterization of three case studies validates the performance of the new software: ex-vivo human coronary arteries, human breast cancer cell samples, and in-vivo hamster oral mucosa. The software is freely available in a hosted webpage by one of the developing institutions, and allows the user a quick, easy-to-use and efficient tool for multi/hyper-spectral data decomposition. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Spatial Heterogeneity and Imperfect Mixing in Chemical Reactions: Visualization of Density-Driven Pattern Formation

DOE PAGES

Sobel, Sabrina G.; Hastings, Harold M.; Testa, Matthew

2009-01-01

Imore » mperfect mixing is a concern in industrial processes, everyday processes (mixing paint, bread machines), and in understanding salt water-fresh water mixing in ecosystems. The effects of imperfect mixing become evident in the unstirred ferroin-catalyzed Belousov-Zhabotinsky reaction, the prototype for chemical pattern formation. Over time, waves of oxidation (high ferriin concentration, blue) propagate into a background of low ferriin concentration (red); their structure reflects in part the history of mixing in the reaction vessel. However, it may be difficult to separate mixing effects from reaction effects. We describe a simpler model system for visualizing density-driven pattern formation in an essentially unmixed chemical system: the reaction of pale yellow Fe 3 + with colorless SCN − to form the blood-red Fe ( SCN ) 2 + complex ion in aqueous solution. Careful addition of one drop of Fe ( NO 3 ) 3 to KSCN yields striped patterns after several minutes. The patterns appear reminiscent of Rayleigh-Taylor instabilities and convection rolls, arguing that pattern formation is caused by density-driven mixing.« less

Spatial Heterogeneity and Imperfect Mixing in Chemical Reactions: Visualization of Density-Driven Pattern Formation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sobel, Sabrina G.; Hastings, Harold M.; Testa, Matthew

Imore » mperfect mixing is a concern in industrial processes, everyday processes (mixing paint, bread machines), and in understanding salt water-fresh water mixing in ecosystems. The effects of imperfect mixing become evident in the unstirred ferroin-catalyzed Belousov-Zhabotinsky reaction, the prototype for chemical pattern formation. Over time, waves of oxidation (high ferriin concentration, blue) propagate into a background of low ferriin concentration (red); their structure reflects in part the history of mixing in the reaction vessel. However, it may be difficult to separate mixing effects from reaction effects. We describe a simpler model system for visualizing density-driven pattern formation in an essentially unmixed chemical system: the reaction of pale yellow Fe 3 + with colorless SCN − to form the blood-red Fe ( SCN ) 2 + complex ion in aqueous solution. Careful addition of one drop of Fe ( NO 3 ) 3 to KSCN yields striped patterns after several minutes. The patterns appear reminiscent of Rayleigh-Taylor instabilities and convection rolls, arguing that pattern formation is caused by density-driven mixing.« less

Zoning and exsolution in cumulate alkali feldspars from the eruption (12.9 Ka) of Laacher see volcano (Western Germany) as an indicator of time-scales and dynamics of carbonate-silicate unmixing

NASA Astrophysics Data System (ADS)

Sourav Rout, Smruti; Wörner, Gerhard

2017-04-01

Time-scales extracted from the detailed analysis of chemically zoned minerals provide insights into crystal ages, magma storage and compositional evolution, including mixing and unmixing events. This allows having a better understanding of pre-eruptive history of large and potentially dangerous magma chambers. We present a comprehensive study of chemical diffusion across zoning and exsolution patterns of alkali feldspars in carbonatite-bearing cognate syenites from the 6.3 km3 (D.R.E) phonolitic Laacher See Tephra (LST) eruption 12.9 ka ago. The Laacher See volcano is located in the Quaternary East Eifel volcanic field of the Paleozoic Rhenish Massif in Western Germany and has produced a compositionally variable sequence in a single eruption from a magma chamber that was zoned from mafic phonolite at the base to highly evolved, actively degassing phonolite magma at the top. Diffusion chronometry is applied to major and trace element compositions obtained on alkali feldspars from carbonate-bearing syenitic cumulates. Methods used were laser ablation inductively coupled plasma mass spectrometry (LA ICP-MS) in combination with energy-dispersive and wavelength-dispersive electron microprobe analyses (EDS & WDS-EMPA). The grey scale values extracted from multiple accumulations of back-scattered electron images represent the K/Na ratio owing to the extremely low concentrations of Ba and Sr (<30 ppm). The numerical grey scale profiles and the quantitative compositional profiles are anatomized using three different fitting models in MATLAB®, Mathematica® and Origin® to estimate related time-scales with minimized error for a temperature range of 750 deg C to 800 deg C (on the basis of existing experimental data on phase transition and phase separation). A distinctive uphill diffusive analysis is used specifically for the phase separation in the case of exsolution features (comprising of albite- and orthoclase-rich phases) in sanidines. The error values are aggregates of propagated error through calculations and the uncertainty in temperature values. Trace element compositional data of distinct feldspar compositions that are assumed to have grown before and after silicate-carbonate unmixing are used to estimate partition coefficients between carbonate and silicate melt. The resulting values correlate well with available experimental data from the literature. We will present a genetic model based on the compositional data on feldspar zonation for the process and timing of silicate-carbonate unmixing prior to eruption of the host phonolite magma.

Analysis of Forest Foliage Using a Multivariate Mixture Model

NASA Technical Reports Server (NTRS)

Hlavka, C. A.; Peterson, David L.; Johnson, L. F.; Ganapol, B.

1997-01-01

Data with wet chemical measurements and near infrared spectra of ground leaf samples were analyzed to test a multivariate regression technique for estimating component spectra which is based on a linear mixture model for absorbance. The resulting unmixed spectra for carbohydrates, lignin, and protein resemble the spectra of extracted plant starches, cellulose, lignin, and protein. The unmixed protein spectrum has prominent absorption spectra at wavelengths which have been associated with nitrogen bonds.

Unmixing Space Object’s Moderate Resolution Spectra

DTIC Science & Technology

2013-09-01

collection of information if it does not display a currently valid OMB control number. 1. REPORT DATE SEP 2013 2. REPORT TYPE 3. DATES COVERED 00...result of spectral unmixing. In the visible, the non- resolved spectral signature is modeled as a linear mixture of spectral reflectance signatures...1 (3) In (3), the first term expresses the Euclidian distance (l2) between the observed data and the forward model . The second term (l1

Multi-tissue partial volume quantification in multi-contrast MRI using an optimised spectral unmixing approach.

PubMed

Collewet, Guylaine; Moussaoui, Saïd; Deligny, Cécile; Lucas, Tiphaine; Idier, Jérôme

2018-06-01

Multi-tissue partial volume estimation in MRI images is investigated with a viewpoint related to spectral unmixing as used in hyperspectral imaging. The main contribution of this paper is twofold. It firstly proposes a theoretical analysis of the statistical optimality conditions of the proportion estimation problem, which in the context of multi-contrast MRI data acquisition allows to appropriately set the imaging sequence parameters. Secondly, an efficient proportion quantification algorithm based on the minimisation of a penalised least-square criterion incorporating a regularity constraint on the spatial distribution of the proportions is proposed. Furthermore, the resulting developments are discussed using empirical simulations. The practical usefulness of the spectral unmixing approach for partial volume quantification in MRI is illustrated through an application to food analysis on the proving of a Danish pastry. Copyright © 2018 Elsevier Inc. All rights reserved.

Resolving fluorophores by unmixing multispectral fluorescence tomography with independent component analysis

NASA Astrophysics Data System (ADS)

Pu, Huangsheng; Zhang, Guanglei; He, Wei; Liu, Fei; Guang, Huizhi; Zhang, Yue; Bai, Jing; Luo, Jianwen

2014-09-01

It is a challenging problem to resolve and identify drug (or non-specific fluorophore) distribution throughout the whole body of small animals in vivo. In this article, an algorithm of unmixing multispectral fluorescence tomography (MFT) images based on independent component analysis (ICA) is proposed to solve this problem. ICA is used to unmix the data matrix assembled by the reconstruction results from MFT. Then the independent components (ICs) that represent spatial structures and the corresponding spectrum courses (SCs) which are associated with spectral variations can be obtained. By combining the ICs with SCs, the recovered MFT images can be generated and fluorophore concentration can be calculated. Simulation studies, phantom experiments and animal experiments with different concentration contrasts and spectrum combinations are performed to test the performance of the proposed algorithm. Results demonstrate that the proposed algorithm can not only provide the spatial information of fluorophores, but also recover the actual reconstruction of MFT images.

Spectral Unmixing With Multiple Dictionaries

NASA Astrophysics Data System (ADS)

Cohen, Jeremy E.; Gillis, Nicolas

2018-02-01

Spectral unmixing aims at recovering the spectral signatures of materials, called endmembers, mixed in a hyperspectral or multispectral image, along with their abundances. A typical assumption is that the image contains one pure pixel per endmember, in which case spectral unmixing reduces to identifying these pixels. Many fully automated methods have been proposed in recent years, but little work has been done to allow users to select areas where pure pixels are present manually or using a segmentation algorithm. Additionally, in a non-blind approach, several spectral libraries may be available rather than a single one, with a fixed number (or an upper or lower bound) of endmembers to chose from each. In this paper, we propose a multiple-dictionary constrained low-rank matrix approximation model that address these two problems. We propose an algorithm to compute this model, dubbed M2PALS, and its performance is discussed on both synthetic and real hyperspectral images.

Variation in photosynthetic and nonphotosynthetic vegetation along edaphic and compositional gradients in northwestern Amazonia

NASA Astrophysics Data System (ADS)

Higgins, M. A.; Asner, G. P.; Perez, E.; Elespuru, N.; Alonso, A.

2014-03-01

Tropical forests vary substantially in aboveground properties such as canopy height, canopy structure, and plant species composition, corresponding to underlying variations in soils and geology. Forest properties are often difficult to detect and map in the field, however, due to the remoteness and inaccessibility of these forests. Spectral mixture analysis of Landsat imagery allows mapping of photosynthetic and nonphotosynthetic vegetation quantities (PV and NPV), corresponding to biophysical properties such as canopy openness, forest productivity, and disturbance. Spectral unmixing has been used for applications ranging from deforestation monitoring to identifying burn scars from past fires, but little is known about variations in PV and NPV in intact rainforest. Here we use spectral unmixing of Landsat imagery to map PV and NPV in northern Amazonia, and to test their relationship to soils and plant species composition. To do this we sampled 117 sites crossing a geological boundary in northwestern Amazonia for soil cation concentrations and plant species composition. We then used the Carnegie Landsat Analysis System to map PV and NPV for these sites from multiple dates of Landsat imagery. We found that soil cation concentrations and plant species composition consistently explain a majority of the variation in remotely sensed PV and NPV values. After combining PV and NPV into a single variable (PV-NPV), we determined that the influence of soil properties on canopy properties was inseparable from the influence of plant species composition. In all cases, patterns in PV and NPV corresponded to underlying geological patterns. Our findings suggest that geology and soils regulate canopy PV and NPV values in intact tropical forest, possibly through changes in plant species composition.

Variation in photosynthetic and nonphotosynthetic vegetation along edaphic and compositional gradients in northwestern Amazonia

NASA Astrophysics Data System (ADS)

Higgins, M. A.; Asner, G. P.; Perez, E.; Elespuru, N.; Alonso, A.

2014-07-01

Tropical forests vary substantially in aboveground properties such as canopy height, canopy structure, and plant species composition, corresponding to underlying variations in soils and geology. Forest properties are often difficult to detect and map in the field, however, due to the remoteness and inaccessibility of these forests. Spectral mixture analysis of Landsat imagery allows mapping of photosynthetic and nonphotosynthetic vegetation quantities (PV and NPV), corresponding to biophysical properties such as canopy openness, forest productivity, and disturbance. Spectral unmixing has been used for applications ranging from deforestation monitoring to identifying burn scars from past fires, but little is known about variations in PV and NPV in intact rainforests. Here we use spectral unmixing of Landsat imagery to map PV and NPV in northern Amazonia, and to test their relationship to soils and plant species composition. To do this we sampled 117 sites crossing a geological boundary in northwestern Amazonia for soil cation concentrations and plant species composition. We then used the Carnegie Landsat Analysis System to map PV and NPV for these sites from multiple dates of Landsat imagery. We found that soil cation concentrations and plant species composition consistently explain a majority of the variation in remotely sensed PV and NPV values. After combining PV and NPV into a single variable (PV-NPV), we determined that the influence of soil properties on canopy properties was inseparable from the influence of plant species composition. In all cases, patterns in PV and NPV corresponded to underlying geological patterns. Our findings suggest that geology and soils regulate canopy PV and NPV values in intact tropical forests, possibly through changes in plant species composition.

A Gaussian mixture model based adaptive classifier for fNIRS brain-computer interfaces and its testing via simulation

NASA Astrophysics Data System (ADS)

Li, Zheng; Jiang, Yi-han; Duan, Lian; Zhu, Chao-zhe

2017-08-01

Objective. Functional near infra-red spectroscopy (fNIRS) is a promising brain imaging technology for brain-computer interfaces (BCI). Future clinical uses of fNIRS will likely require operation over long time spans, during which neural activation patterns may change. However, current decoders for fNIRS signals are not designed to handle changing activation patterns. The objective of this study is to test via simulations a new adaptive decoder for fNIRS signals, the Gaussian mixture model adaptive classifier (GMMAC). Approach. GMMAC can simultaneously classify and track activation pattern changes without the need for ground-truth labels. This adaptive classifier uses computationally efficient variational Bayesian inference to label new data points and update mixture model parameters, using the previous model parameters as priors. We test GMMAC in simulations in which neural activation patterns change over time and compare to static decoders and unsupervised adaptive linear discriminant analysis classifiers. Main results. Our simulation experiments show GMMAC can accurately decode under time-varying activation patterns: shifts of activation region, expansions of activation region, and combined contractions and shifts of activation region. Furthermore, the experiments show the proposed method can track the changing shape of the activation region. Compared to prior work, GMMAC performed significantly better than the other unsupervised adaptive classifiers on a difficult activation pattern change simulation: 99% versus  <54% in two-choice classification accuracy. Significance. We believe GMMAC will be useful for clinical fNIRS-based brain-computer interfaces, including neurofeedback training systems, where operation over long time spans is required.

Efficient Personalized Mispronunciation Detection of Taiwanese-Accented English Speech Based on Unsupervised Model Adaptation and Dynamic Sentence Selection

ERIC Educational Resources Information Center

Wu, Chung-Hsien; Su, Hung-Yu; Liu, Chao-Hong

2013-01-01

This study presents an efficient approach to personalized mispronunciation detection of Taiwanese-accented English. The main goal of this study was to detect frequently occurring mispronunciation patterns of Taiwanese-accented English instead of scoring English pronunciations directly. The proposed approach quickly identifies personalized…

Quick fuzzy backpropagation algorithm.

PubMed

Nikov, A; Stoeva, S

2001-03-01

A modification of the fuzzy backpropagation (FBP) algorithm called QuickFBP algorithm is proposed, where the computation of the net function is significantly quicker. It is proved that the FBP algorithm is of exponential time complexity, while the QuickFBP algorithm is of polynomial time complexity. Convergence conditions of the QuickFBP, resp. the FBP algorithm are defined and proved for: (1) single output neural networks in case of training patterns with different targets; and (2) multiple output neural networks in case of training patterns with equivalued target vector. They support the automation of the weights training process (quasi-unsupervised learning) establishing the target value(s) depending on the network's input values. In these cases the simulation results confirm the convergence of both algorithms. An example with a large-sized neural network illustrates the significantly greater training speed of the QuickFBP rather than the FBP algorithm. The adaptation of an interactive web system to users on the basis of the QuickFBP algorithm is presented. Since the QuickFBP algorithm ensures quasi-unsupervised learning, this implies its broad applicability in areas of adaptive and adaptable interactive systems, data mining, etc. applications.

Unsupervised Extraction of Stable Expression Signatures from Public Compendia with an Ensemble of Neural Networks.

PubMed

Tan, Jie; Doing, Georgia; Lewis, Kimberley A; Price, Courtney E; Chen, Kathleen M; Cady, Kyle C; Perchuk, Barret; Laub, Michael T; Hogan, Deborah A; Greene, Casey S

2017-07-26

Cross-experiment comparisons in public data compendia are challenged by unmatched conditions and technical noise. The ADAGE method, which performs unsupervised integration with denoising autoencoder neural networks, can identify biological patterns, but because ADAGE models, like many neural networks, are over-parameterized, different ADAGE models perform equally well. To enhance model robustness and better build signatures consistent with biological pathways, we developed an ensemble ADAGE (eADAGE) that integrated stable signatures across models. We applied eADAGE to a compendium of Pseudomonas aeruginosa gene expression profiling experiments performed in 78 media. eADAGE revealed a phosphate starvation response controlled by PhoB in media with moderate phosphate and predicted that a second stimulus provided by the sensor kinase, KinB, is required for this PhoB activation. We validated this relationship using both targeted and unbiased genetic approaches. eADAGE, which captures stable biological patterns, enables cross-experiment comparisons that can highlight measured but undiscovered relationships. Copyright © 2017 The Author(s). Published by Elsevier Inc. All rights reserved.

Long-term retention as a function of word concreteness under conditions of free recall.

PubMed

Postman, L; Burns, S

1974-07-01

Acquisition and long-term retention of concrete (C) and abstract (A) words were investigated under conditions of multiple-trial free recall. Both unmixed and mixed lists were used in original learning. Retention was tested either 1 rain or 1 week after attainment of the learning criterion. Acquisition was faster and retention was higher for C than for A words. These differences were more pronounced for mixed than for unmixed lists.

Correlation between prescription of various dextropropoxyphene preparations and their involvement in fatal poisonings.

PubMed

Jonasson, U; Jonasson, B; Saldeen, T

1999-07-26

In Sweden, the frequency of fatal poisoning by dextropropoxyphene (DXP) ingestion is constantly high. There are seven preparations containing DXP on the Swedish market; in three of them DXP is the sole analgesic ingredient, while four of them are combinations of analgesics. In an attempt to assess the death rate attributable to each DXP preparation on the basis of toxicological analyses, altogether 834 cases of dextropropoxyphene-related death over a 5-year period (1992-1996) in Sweden have been reviewed. The ratio between number of fatal poisonings and prescription of defined daily dose/1000 inhabitants during a 12-month period (DDD) was determined. The highest ratio, 27, was attributed to unmixed preparations. The ratio for DXP + paracetamol-related deaths was 6.3, and for DXP + phenazone, 6.4, while the lowest ratio, 2, was found among the DXP + chlorzoxazone cases. The unmixed preparations, representing 26% of all DXP prescriptions during the study years, were implicated in 62% of the DXP fatalities, a considerable over-representation. Unmixed preparations, with their higher content of DXP, may be more attractive for many consumers because of their narcotic (euphoric) effects rather than for any analgetic superiority. Another possibility is that unmixed preparations may erroneously have been regarded as safer than when combined with paracetamol, as reports of poisoning with compounds containing DXP + paracetamol have been most frequently reported, probably due to their predominance on the market.

What Stroop tasks can tell us about selective attention from childhood to adulthood.

PubMed

Wright, Barlow C

2017-08-01

A rich body of research concerns causes of Stroop effects plus applications of Stroop. However, several questions remain. We included assessment of errors with children and adults (N = 316), who sat either a task wherein each block employed only trials of one type (unmixed task) or where every block comprised of a mix of the congruent, neutral, and incongruent trials. Children responded slower than adults and made more errors on each task. Contrary to some previous studies, interference (the difference between neutral and incongruent condition) showed no reaction time (RT) differences by group or task, although there were differences in errors. By contrast, facilitation (the difference between neutral and congruent condition) was greater in children than adults, and greater on the unmixed task than the mixed task. After considering a number of theoretical accounts, we settle on the inadvertent word-reading hypothesis, whereby facilitation stems from children and the unmixed task promoting inadvertent reading particularly in the congruent condition. Stability of interference RT is explained by fixed semantic differences between neutral and incongruent conditions, for children versus adults and for unmixed versus mixed task. We conclude that utilizing two tasks together may reveal more about how attention is affected in other groups. © 2016 The Authors. British Journal of Psychology published by John Wiley & Sons Ltd on behalf of the British Psychological Society.

Identifying influential individuals on intensive care units: using cluster analysis to explore culture.

PubMed

Fong, Allan; Clark, Lindsey; Cheng, Tianyi; Franklin, Ella; Fernandez, Nicole; Ratwani, Raj; Parker, Sarah Henrickson

2017-07-01

The objective of this paper is to identify attribute patterns of influential individuals in intensive care units using unsupervised cluster analysis. Despite the acknowledgement that culture of an organisation is critical to improving patient safety, specific methods to shift culture have not been explicitly identified. A social network analysis survey was conducted and an unsupervised cluster analysis was used. A total of 100 surveys were gathered. Unsupervised cluster analysis was used to group individuals with similar dimensions highlighting three general genres of influencers: well-rounded, knowledge and relational. Culture is created locally by individual influencers. Cluster analysis is an effective way to identify common characteristics among members of an intensive care unit team that are noted as highly influential by their peers. To change culture, identifying and then integrating the influencers in intervention development and dissemination may create more sustainable and effective culture change. Additional studies are ongoing to test the effectiveness of utilising these influencers to disseminate patient safety interventions. This study offers an approach that can be helpful in both identifying and understanding influential team members and may be an important aspect of developing methods to change organisational culture. © 2017 John Wiley & Sons Ltd.

Application of diffusion maps to identify human factors of self-reported anomalies in aviation.

PubMed

Andrzejczak, Chris; Karwowski, Waldemar; Mikusinski, Piotr

2012-01-01

A study investigating what factors are present leading to pilots submitting voluntary anomaly reports regarding their flight performance was conducted. Diffusion Maps (DM) were selected as the method of choice for performing dimensionality reduction on text records for this study. Diffusion Maps have seen successful use in other domains such as image classification and pattern recognition. High-dimensionality data in the form of narrative text reports from the NASA Aviation Safety Reporting System (ASRS) were clustered and categorized by way of dimensionality reduction. Supervised analyses were performed to create a baseline document clustering system. Dimensionality reduction techniques identified concepts or keywords within records, and allowed the creation of a framework for an unsupervised document classification system. Results from the unsupervised clustering algorithm performed similarly to the supervised methods outlined in the study. The dimensionality reduction was performed on 100 of the most commonly occurring words within 126,000 text records describing commercial aviation incidents. This study demonstrates that unsupervised machine clustering and organization of incident reports is possible based on unbiased inputs. Findings from this study reinforced traditional views on what factors contribute to civil aviation anomalies, however, new associations between previously unrelated factors and conditions were also found.

Discrete Wavelet Transform-Based Whole-Spectral and Subspectral Analysis for Improved Brain Tumor Clustering Using Single Voxel MR Spectroscopy.

PubMed

Yang, Guang; Nawaz, Tahir; Barrick, Thomas R; Howe, Franklyn A; Slabaugh, Greg

2015-12-01

Many approaches have been considered for automatic grading of brain tumors by means of pattern recognition with magnetic resonance spectroscopy (MRS). Providing an improved technique which can assist clinicians in accurately identifying brain tumor grades is our main objective. The proposed technique, which is based on the discrete wavelet transform (DWT) of whole-spectral or subspectral information of key metabolites, combined with unsupervised learning, inspects the separability of the extracted wavelet features from the MRS signal to aid the clustering. In total, we included 134 short echo time single voxel MRS spectra (SV MRS) in our study that cover normal controls, low grade and high grade tumors. The combination of DWT-based whole-spectral or subspectral analysis and unsupervised clustering achieved an overall clustering accuracy of 94.8% and a balanced error rate of 7.8%. To the best of our knowledge, it is the first study using DWT combined with unsupervised learning to cluster brain SV MRS. Instead of dimensionality reduction on SV MRS or feature selection using model fitting, our study provides an alternative method of extracting features to obtain promising clustering results.

Unsupervised discrimination of patterns in spiking neural networks with excitatory and inhibitory synaptic plasticity.

PubMed

Srinivasa, Narayan; Cho, Youngkwan

2014-01-01

A spiking neural network model is described for learning to discriminate among spatial patterns in an unsupervised manner. The network anatomy consists of source neurons that are activated by external inputs, a reservoir that resembles a generic cortical layer with an excitatory-inhibitory (EI) network and a sink layer of neurons for readout. Synaptic plasticity in the form of STDP is imposed on all the excitatory and inhibitory synapses at all times. While long-term excitatory STDP enables sparse and efficient learning of the salient features in inputs, inhibitory STDP enables this learning to be stable by establishing a balance between excitatory and inhibitory currents at each neuron in the network. The synaptic weights between source and reservoir neurons form a basis set for the input patterns. The neural trajectories generated in the reservoir due to input stimulation and lateral connections between reservoir neurons can be readout by the sink layer neurons. This activity is used for adaptation of synapses between reservoir and sink layer neurons. A new measure called the discriminability index (DI) is introduced to compute if the network can discriminate between old patterns already presented in an initial training session. The DI is also used to compute if the network adapts to new patterns without losing its ability to discriminate among old patterns. The final outcome is that the network is able to correctly discriminate between all patterns-both old and new. This result holds as long as inhibitory synapses employ STDP to continuously enable current balance in the network. The results suggest a possible direction for future investigation into how spiking neural networks could address the stability-plasticity question despite having continuous synaptic plasticity.

Sensitive Dual Color in vivo Bioluminescence Imaging Using a New Red Codon Optimized Firefly Luciferase and a Green Click Beetle Luciferase

DTIC Science & Technology

2011-04-01

Sensitive Dual Color In Vivo Bioluminescence Imaging Using a New Red Codon Optimized Firefly Luciferase and a Green Click Beetle Luciferase Laura...20 nm). Spectral unmixing algorithms were applied to the images where good separation of signals was observed. Furthermore, HEK293 cells that...spectral emissions using a suitable spectral unmixing algorithm . This new D-luciferin-dependent reporter gene couplet opens up the possibility in the future

Quasi-Supervised Scoring of Human Sleep in Polysomnograms Using Augmented Input Variables

PubMed Central

Yaghouby, Farid; Sunderam, Sridhar

2015-01-01

The limitations of manual sleep scoring make computerized methods highly desirable. Scoring errors can arise from human rater uncertainty or inter-rater variability. Sleep scoring algorithms either come as supervised classifiers that need scored samples of each state to be trained, or as unsupervised classifiers that use heuristics or structural clues in unscored data to define states. We propose a quasi-supervised classifier that models observations in an unsupervised manner but mimics a human rater wherever training scores are available. EEG, EMG, and EOG features were extracted in 30s epochs from human-scored polysomnograms recorded from 42 healthy human subjects (18 to 79 years) and archived in an anonymized, publicly accessible database. Hypnograms were modified so that: 1. Some states are scored but not others; 2. Samples of all states are scored but not for transitional epochs; and 3. Two raters with 67% agreement are simulated. A framework for quasi-supervised classification was devised in which unsupervised statistical models—specifically Gaussian mixtures and hidden Markov models—are estimated from unlabeled training data, but the training samples are augmented with variables whose values depend on available scores. Classifiers were fitted to signal features incorporating partial scores, and used to predict scores for complete recordings. Performance was assessed using Cohen's K statistic. The quasi-supervised classifier performed significantly better than an unsupervised model and sometimes as well as a completely supervised model despite receiving only partial scores. The quasi-supervised algorithm addresses the need for classifiers that mimic scoring patterns of human raters while compensating for their limitations. PMID:25679475

Quasi-supervised scoring of human sleep in polysomnograms using augmented input variables.

PubMed

Yaghouby, Farid; Sunderam, Sridhar

2015-04-01

The limitations of manual sleep scoring make computerized methods highly desirable. Scoring errors can arise from human rater uncertainty or inter-rater variability. Sleep scoring algorithms either come as supervised classifiers that need scored samples of each state to be trained, or as unsupervised classifiers that use heuristics or structural clues in unscored data to define states. We propose a quasi-supervised classifier that models observations in an unsupervised manner but mimics a human rater wherever training scores are available. EEG, EMG, and EOG features were extracted in 30s epochs from human-scored polysomnograms recorded from 42 healthy human subjects (18-79 years) and archived in an anonymized, publicly accessible database. Hypnograms were modified so that: 1. Some states are scored but not others; 2. Samples of all states are scored but not for transitional epochs; and 3. Two raters with 67% agreement are simulated. A framework for quasi-supervised classification was devised in which unsupervised statistical models-specifically Gaussian mixtures and hidden Markov models--are estimated from unlabeled training data, but the training samples are augmented with variables whose values depend on available scores. Classifiers were fitted to signal features incorporating partial scores, and used to predict scores for complete recordings. Performance was assessed using Cohen's Κ statistic. The quasi-supervised classifier performed significantly better than an unsupervised model and sometimes as well as a completely supervised model despite receiving only partial scores. The quasi-supervised algorithm addresses the need for classifiers that mimic scoring patterns of human raters while compensating for their limitations. Copyright © 2015 Elsevier Ltd. All rights reserved.

Unsupervised classification of major depression using functional connectivity MRI.

PubMed

Zeng, Ling-Li; Shen, Hui; Liu, Li; Hu, Dewen

2014-04-01

The current diagnosis of psychiatric disorders including major depressive disorder based largely on self-reported symptoms and clinical signs may be prone to patients' behaviors and psychiatrists' bias. This study aims at developing an unsupervised machine learning approach for the accurate identification of major depression based on single resting-state functional magnetic resonance imaging scans in the absence of clinical information. Twenty-four medication-naive patients with major depression and 29 demographically similar healthy individuals underwent resting-state functional magnetic resonance imaging. We first clustered the voxels within the perigenual cingulate cortex into two subregions, a subgenual region and a pregenual region, according to their distinct resting-state functional connectivity patterns and showed that a maximum margin clustering-based unsupervised machine learning approach extracted sufficient information from the subgenual cingulate functional connectivity map to differentiate depressed patients from healthy controls with a group-level clustering consistency of 92.5% and an individual-level classification consistency of 92.5%. It was also revealed that the subgenual cingulate functional connectivity network with the highest discriminative power primarily included the ventrolateral and ventromedial prefrontal cortex, superior temporal gyri and limbic areas, indicating that these connections may play critical roles in the pathophysiology of major depression. The current study suggests that subgenual cingulate functional connectivity network signatures may provide promising objective biomarkers for the diagnosis of major depression and that maximum margin clustering-based unsupervised machine learning approaches may have the potential to inform clinical practice and aid in research on psychiatric disorders. Copyright © 2013 Wiley Periodicals, Inc.

Rotational Spectral Unmixing of Exoplanets: Degeneracies between Surface Colors and Geography

NASA Astrophysics Data System (ADS)

Fujii, Yuka; Lustig-Yaeger, Jacob; Cowan, Nicolas B.

2017-11-01

Unmixing the disk-integrated spectra of exoplanets provides hints about heterogeneous surfaces that we cannot directly resolve in the foreseeable future. It is particularly important for terrestrial planets with diverse surface compositions like Earth. Although previous work on unmixing the spectra of Earth from disk-integrated multi-band light curves appeared successful, we point out a mathematical degeneracy between the surface colors and their spatial distributions. Nevertheless, useful constraints on the spectral shape of individual surface types may be obtained from the premise that albedo is everywhere between 0 and 1. We demonstrate the degeneracy and the possible constraints using both mock data based on a toy model of Earth, as well as real observations of Earth. Despite the severe degeneracy, we are still able to recover an approximate albedo spectrum for an ocean. In general, we find that surfaces are easier to identify when they cover a large fraction of the planet and when their spectra approach zero or unity in certain bands.

Unmixed fuel processors and methods for using the same

DOEpatents

Kulkarni, Parag Prakash; Cui, Zhe

2010-08-24

Disclosed herein are unmixed fuel processors and methods for using the same. In one embodiment, an unmixed fuel processor comprises: an oxidation reactor comprising an oxidation portion and a gasifier, a CO.sub.2 acceptor reactor, and a regeneration reactor. The oxidation portion comprises an air inlet, effluent outlet, and an oxygen transfer material. The gasifier comprises a solid hydrocarbon fuel inlet, a solids outlet, and a syngas outlet. The CO.sub.2 acceptor reactor comprises a water inlet, a hydrogen outlet, and a CO.sub.2 sorbent, and is configured to receive syngas from the gasifier. The regeneration reactor comprises a water inlet and a CO.sub.2 stream outlet. The regeneration reactor is configured to receive spent CO.sub.2 adsorption material from the gasification reactor and to return regenerated CO.sub.2 adsorption material to the gasification reactor, and configured to receive oxidized oxygen transfer material from the oxidation reactor and to return reduced oxygen transfer material to the oxidation reactor.

Rotational Spectral Unmixing of Exoplanets: Degeneracies between Surface Colors and Geography

DOE Office of Scientific and Technical Information (OSTI.GOV)

Fujii, Yuka; Lustig-Yaeger, Jacob; Cowan, Nicolas B., E-mail: yuka.fujii.ebihara@gmail.com

Unmixing the disk-integrated spectra of exoplanets provides hints about heterogeneous surfaces that we cannot directly resolve in the foreseeable future. It is particularly important for terrestrial planets with diverse surface compositions like Earth. Although previous work on unmixing the spectra of Earth from disk-integrated multi-band light curves appeared successful, we point out a mathematical degeneracy between the surface colors and their spatial distributions. Nevertheless, useful constraints on the spectral shape of individual surface types may be obtained from the premise that albedo is everywhere between 0 and 1. We demonstrate the degeneracy and the possible constraints using both mock datamore » based on a toy model of Earth, as well as real observations of Earth. Despite the severe degeneracy, we are still able to recover an approximate albedo spectrum for an ocean. In general, we find that surfaces are easier to identify when they cover a large fraction of the planet and when their spectra approach zero or unity in certain bands.« less

Rotational Spectral Unmixing of Exoplanets: Degeneracies Between Surface Colors and Geography

NASA Technical Reports Server (NTRS)

Fujii, Yuka; Lustig-Yaeger, Jacob; Cowan, Nicolas B.

2017-01-01

Unmixing the disk-integrated spectra of exoplanets provides hints about heterogeneous surfaces that we cannot directly resolve in the foreseeable future. It is particularly important for terrestrial planets with diverse surface compositions like Earth. Although previous work on unmixing the spectra of Earth from disk-integrated multi-band light curves appeared successful, we point out a mathematical degeneracy between the surface colors and their spatial distributions. Nevertheless, useful constraints on the spectral shape of individual surface types may be obtained from the premise that albedo is everywhere between 0 and 1. We demonstrate the degeneracy and the possible constraints using both mock data based on a toy model of Earth, as well as real observations of Earth. Despite the severe degeneracy, we are still able to recover an approximate albedo spectrum for an ocean. In general, we find that surfaces are easier to identify when they cover a large fraction of the planet and when their spectra approach zero or unity in certain bands.

Unsupervised Clustering of Subcellular Protein Expression Patterns in High-Throughput Microscopy Images Reveals Protein Complexes and Functional Relationships between Proteins

PubMed Central

Handfield, Louis-François; Chong, Yolanda T.; Simmons, Jibril; Andrews, Brenda J.; Moses, Alan M.

2013-01-01

Protein subcellular localization has been systematically characterized in budding yeast using fluorescently tagged proteins. Based on the fluorescence microscopy images, subcellular localization of many proteins can be classified automatically using supervised machine learning approaches that have been trained to recognize predefined image classes based on statistical features. Here, we present an unsupervised analysis of protein expression patterns in a set of high-resolution, high-throughput microscope images. Our analysis is based on 7 biologically interpretable features which are evaluated on automatically identified cells, and whose cell-stage dependency is captured by a continuous model for cell growth. We show that it is possible to identify most previously identified localization patterns in a cluster analysis based on these features and that similarities between the inferred expression patterns contain more information about protein function than can be explained by a previous manual categorization of subcellular localization. Furthermore, the inferred cell-stage associated to each fluorescence measurement allows us to visualize large groups of proteins entering the bud at specific stages of bud growth. These correspond to proteins localized to organelles, revealing that the organelles must be entering the bud in a stereotypical order. We also identify and organize a smaller group of proteins that show subtle differences in the way they move around the bud during growth. Our results suggest that biologically interpretable features based on explicit models of cell morphology will yield unprecedented power for pattern discovery in high-resolution, high-throughput microscopy images. PMID:23785265

Bio-inspired computational heuristics to study Lane-Emden systems arising in astrophysics model.

PubMed

Ahmad, Iftikhar; Raja, Muhammad Asif Zahoor; Bilal, Muhammad; Ashraf, Farooq

2016-01-01

This study reports novel hybrid computational methods for the solutions of nonlinear singular Lane-Emden type differential equation arising in astrophysics models by exploiting the strength of unsupervised neural network models and stochastic optimization techniques. In the scheme the neural network, sub-part of large field called soft computing, is exploited for modelling of the equation in an unsupervised manner. The proposed approximated solutions of higher order ordinary differential equation are calculated with the weights of neural networks trained with genetic algorithm, and pattern search hybrid with sequential quadratic programming for rapid local convergence. The results of proposed solvers for solving the nonlinear singular systems are in good agreements with the standard solutions. Accuracy and convergence the design schemes are demonstrated by the results of statistical performance measures based on the sufficient large number of independent runs.

Unsupervised daily routine and activity discovery in smart homes.

PubMed

Jie Yin; Qing Zhang; Karunanithi, Mohan

2015-08-01

The ability to accurately recognize daily activities of residents is a core premise of smart homes to assist with remote health monitoring. Most of the existing methods rely on a supervised model trained from a preselected and manually labeled set of activities, which are often time-consuming and costly to obtain in practice. In contrast, this paper presents an unsupervised method for discovering daily routines and activities for smart home residents. Our proposed method first uses a Markov chain to model a resident's locomotion patterns at different times of day and discover clusters of daily routines at the macro level. For each routine cluster, it then drills down to further discover room-level activities at the micro level. The automatic identification of daily routines and activities is useful for understanding indicators of functional decline of elderly people and suggesting timely interventions.

Unsupervised pattern recognition methods in ciders profiling based on GCE voltammetric signals.

PubMed

Jakubowska, Małgorzata; Sordoń, Wanda; Ciepiela, Filip

2016-07-15

This work presents a complete methodology of distinguishing between different brands of cider and ageing degrees, based on voltammetric signals, utilizing dedicated data preprocessing procedures and unsupervised multivariate analysis. It was demonstrated that voltammograms recorded on glassy carbon electrode in Britton-Robinson buffer at pH 2 are reproducible for each brand. By application of clustering algorithms and principal component analysis visible homogenous clusters were obtained. Advanced signal processing strategy which included automatic baseline correction, interval scaling and continuous wavelet transform with dedicated mother wavelet, was a key step in the correct recognition of the objects. The results show that voltammetry combined with optimized univariate and multivariate data processing is a sufficient tool to distinguish between ciders from various brands and to evaluate their freshness. Copyright © 2016 Elsevier Ltd. All rights reserved.

Comparisons of non-Gaussian statistical models in DNA methylation analysis.

PubMed

Ma, Zhanyu; Teschendorff, Andrew E; Yu, Hong; Taghia, Jalil; Guo, Jun

2014-06-16

As a key regulatory mechanism of gene expression, DNA methylation patterns are widely altered in many complex genetic diseases, including cancer. DNA methylation is naturally quantified by bounded support data; therefore, it is non-Gaussian distributed. In order to capture such properties, we introduce some non-Gaussian statistical models to perform dimension reduction on DNA methylation data. Afterwards, non-Gaussian statistical model-based unsupervised clustering strategies are applied to cluster the data. Comparisons and analysis of different dimension reduction strategies and unsupervised clustering methods are presented. Experimental results show that the non-Gaussian statistical model-based methods are superior to the conventional Gaussian distribution-based method. They are meaningful tools for DNA methylation analysis. Moreover, among several non-Gaussian methods, the one that captures the bounded nature of DNA methylation data reveals the best clustering performance.

Comparisons of Non-Gaussian Statistical Models in DNA Methylation Analysis

PubMed Central

Ma, Zhanyu; Teschendorff, Andrew E.; Yu, Hong; Taghia, Jalil; Guo, Jun

2014-01-01

As a key regulatory mechanism of gene expression, DNA methylation patterns are widely altered in many complex genetic diseases, including cancer. DNA methylation is naturally quantified by bounded support data; therefore, it is non-Gaussian distributed. In order to capture such properties, we introduce some non-Gaussian statistical models to perform dimension reduction on DNA methylation data. Afterwards, non-Gaussian statistical model-based unsupervised clustering strategies are applied to cluster the data. Comparisons and analysis of different dimension reduction strategies and unsupervised clustering methods are presented. Experimental results show that the non-Gaussian statistical model-based methods are superior to the conventional Gaussian distribution-based method. They are meaningful tools for DNA methylation analysis. Moreover, among several non-Gaussian methods, the one that captures the bounded nature of DNA methylation data reveals the best clustering performance. PMID:24937687

Quantitative detection of settled dust over green canopy

NASA Astrophysics Data System (ADS)

Brook, Anna

2016-04-01

The main task of environmental and geoscience applications are efficient and accurate quantitative classification of earth surfaces and spatial phenomena. In the past decade, there has been a significant interest in employing hyperspectral unmixing in order to retrieve accurate quantitative information latent in hyperspectral imagery data. Recently, the ground-truth and laboratory measured spectral signatures promoted by advanced algorithms are proposed as a new path toward solving the unmixing problem of hyperspectral imagery in semi-supervised fashion. This paper suggests that the sensitivity of sparse unmixing techniques provides an ideal approach to extract and identify dust settled over/upon green vegetation canopy using hyperspectral airborne data. Atmospheric dust transports a variety of chemicals, some of which pose a risk to the ecosystem and human health (Kaskaoutis, et al., 2008). Many studies deal with the impact of dust on particulate matter (PM) and atmospheric pollution. Considering the potential impact of industrial pollutants, one of the most important considerations is the fact that suspended PM can have both a physical and a chemical impact on plants, soils, and water bodies. Not only can the particles covering surfaces cause physical distortion, but particles of diverse origin and different chemistries can also serve as chemical stressors and cause irreversible damage. Sediment dust load in an indoor environment can be spectrally assessed using reflectance spectroscopy (Chudnovsky and Ben-Dor, 2009). Small amounts of particulate pollution that may carry a signature of a forthcoming environmental hazard are of key interest when considering the effects of pollution. According to the most basic distribution dynamics, dust consists of suspended particulate matter in a fine state of subdivision that are raised and carried by wind. In this context, it is increasingly important to first, understand the distribution dynamics of pollutants, and subsequently develop dedicated tools and measures to control and monitor pollutants in the free environment. The earliest effect of settled polluted dust particles is not always reflected through poor conditions of vegetation or soils, or any visible damages. In most of the cases, it has a quite long accumulation process that graduates from a polluted condition to long-term environmental hazard. Although conducted experiments with pollutant analog powders under controlled conditions have tended to confirm the findings from field studies (Brook, 2014), a major criticism of all these experiments is their short duration. The resulting conclusion is that it is difficult, if not impossible, to determine the implications of long-term exposure to realistic concentrations of pollutants from such short-term studies. Hyperspectral remote sensing (HRS) has become a common tool for environmental and geoscience applications. HRS has promoted new opportunities for exploring a wide range of materials and evaluating a variety of natural processes due to its detailed, specific, and extensive information on spectral and spatial disseminations. Hyperspectral unmixing (HU) is the technique of presuming the category type, which constitutes the mix-pixel, and its mixing ratio (Keshava and Mustard, 2002). In general, the task of unmixing is to decompose the reflectance spectrum of each pixel into a set of endmembers or principal combined spectra and their corresponding abundances (Bioucas-Dias et al., 2012). This study suggests that the sensitivity of sparse unmixing techniques provides an ideal approach to extract and identify dust settled over/upon green vegetation canopy using hyperspectral airborne data. Among the available techniques, this study present results of seven linear and non-linear unmixing algorithms: 1) Non-negative Matrix Factorization (NMF), 2) L1 sparsity-constrained NMF (L1-NMF), 3) L1/2 sparsity-constrained NMF (L1/2-NMF), 4) Graph regularized NMF (G-NMF), 5) Structured Sparse NMF (SS-NMF), 6) Alternating Least-Square (ALS), and 2) Lin's Projected Gradient (LPG). The performance is evaluated on real hyperspectral imagery data via detailed experimental assessment. The study showed that in certain compression tasks content-adapted sparse representation is provided by state-of-the-art solutions. The NMF algorithm estimates endmembers that are used to remove spurious information. If computationally feasible, it should include interaction terms to make the model more flexible. The optimal NMF algorithms, such as ALS and LPG, are assumed to be the simplest methods that achieve the minimum error on the test set. In summary, this work shows that sediment dust can be assessed using airborne HSI data, making it a potentially powerful tool for environmental studies. References Keshava, N., Mustard, J. (2002). Spectral unmixing. IEEE Signal Process. Mag., 19(1), 44-57. Chudnovsky, A., & Ben-Dor, E. (2009). Reflectance spectroscopy as a tool for settled dust monitoring in office environment. International Journal of Environment and Waste Management, 4(1), 32-49. Brook, A. (2014). Quantitative Detection of Settled dust over Green Canopy using Sparse Unmixing of Airborne Hyperspectral Data. IEEE-Whispers 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2014, Switzerland, 4-8. Keshava, N., Mustard, J. (2002). Spectral unmixing. IEEE Signal Process. Mag., 19(1), 44-57. Bioucas-Dias et al. (2012). Hyperspectral unmixing overview: Geometrical, statistical, and sparse regression-based approaches, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2), 354 -379.

Spectral Unmixing Based Construction of Lunar Mineral Abundance Maps

NASA Astrophysics Data System (ADS)

Bernhardt, V.; Grumpe, A.; Wöhler, C.

2017-07-01

In this study we apply a nonlinear spectral unmixing algorithm to a nearly global lunar spectral reflectance mosaic derived from hyper-spectral image data acquired by the Moon Mineralogy Mapper (M3) instrument. Corrections for topographic effects and for thermal emission were performed. A set of 19 laboratory-based reflectance spectra of lunar samples published by the Lunar Soil Characterization Consortium (LSCC) were used as a catalog of potential endmember spectra. For a given spectrum, the multi-population population-based incremental learning (MPBIL) algorithm was used to determine the subset of endmembers actually contained in it. However, as the MPBIL algorithm is computationally expensive, it cannot be applied to all pixels of the reflectance mosaic. Hence, the reflectance mosaic was clustered into a set of 64 prototype spectra, and the MPBIL algorithm was applied to each prototype spectrum. Each pixel of the mosaic was assigned to the most similar prototype, and the set of endmembers previously determined for that prototype was used for pixel-wise nonlinear spectral unmixing using the Hapke model, implemented as linear unmixing of the single-scattering albedo spectrum. This procedure yields maps of the fractional abundances of the 19 endmembers. Based on the known modal abundances of a variety of mineral species in the LSCC samples, a conversion from endmember abundances to mineral abundances was performed. We present maps of the fractional abundances of plagioclase, pyroxene and olivine and compare our results with previously published lunar mineral abundance maps.

Spectral unmixing of multi-color tissue specific in vivo fluorescence in mice

NASA Astrophysics Data System (ADS)

Zacharakis, Giannis; Favicchio, Rosy; Garofalakis, Anikitos; Psycharakis, Stylianos; Mamalaki, Clio; Ripoll, Jorge

2007-07-01

Fluorescence Molecular Tomography (FMT) has emerged as a powerful tool for monitoring biological functions in vivo in small animals. It provides the means to determine volumetric images of fluorescent protein concentration by applying the principles of diffuse optical tomography. Using different probes tagged to different proteins or cells, different biological functions and pathways can be simultaneously imaged in the same subject. In this work we present a spectral unmixing algorithm capable of separating signal from different probes when combined with the tomographic imaging modality. We show results of two-color imaging when the algorithm is applied to separate fluorescence activity originating from phantoms containing two different fluorophores, namely CFSE and SNARF, with well separated emission spectra, as well as Dsred- and GFP-fused cells in F5-b10 transgenic mice in vivo. The same algorithm can furthermore be applied to tissue-specific spectroscopy data. Spectral analysis of a variety of organs from control, DsRed and GFP F5/B10 transgenic mice showed that fluorophore detection by optical systems is highly tissue-dependent. Spectral data collected from different organs can provide useful insight into experimental parameter optimisation (choice of filters, fluorophores, excitation wavelengths) and spectral unmixing can be applied to measure the tissue-dependency, thereby taking into account localized fluorophore efficiency. Summed up, tissue spectral unmixing can be used as criteria in choosing the most appropriate tissue targets as well as fluorescent markers for specific applications.

Deep data analysis via physically constrained linear unmixing: universal framework, domain examples, and a community-wide platform.

PubMed

Kannan, R; Ievlev, A V; Laanait, N; Ziatdinov, M A; Vasudevan, R K; Jesse, S; Kalinin, S V

2018-01-01

Many spectral responses in materials science, physics, and chemistry experiments can be characterized as resulting from the superposition of a number of more basic individual spectra. In this context, unmixing is defined as the problem of determining the individual spectra, given measurements of multiple spectra that are spatially resolved across samples, as well as the determination of the corresponding abundance maps indicating the local weighting of each individual spectrum. Matrix factorization is a popular linear unmixing technique that considers that the mixture model between the individual spectra and the spatial maps is linear. Here, we present a tutorial paper targeted at domain scientists to introduce linear unmixing techniques, to facilitate greater understanding of spectroscopic imaging data. We detail a matrix factorization framework that can incorporate different domain information through various parameters of the matrix factorization method. We demonstrate many domain-specific examples to explain the expressivity of the matrix factorization framework and show how the appropriate use of domain-specific constraints such as non-negativity and sum-to-one abundance result in physically meaningful spectral decompositions that are more readily interpretable. Our aim is not only to explain the off-the-shelf available tools, but to add additional constraints when ready-made algorithms are unavailable for the task. All examples use the scalable open source implementation from https://github.com/ramkikannan/nmflibrary that can run from small laptops to supercomputers, creating a user-wide platform for rapid dissemination and adoption across scientific disciplines.

Unsupervised discrimination of patterns in spiking neural networks with excitatory and inhibitory synaptic plasticity

PubMed Central

Srinivasa, Narayan; Cho, Youngkwan

2014-01-01

A spiking neural network model is described for learning to discriminate among spatial patterns in an unsupervised manner. The network anatomy consists of source neurons that are activated by external inputs, a reservoir that resembles a generic cortical layer with an excitatory-inhibitory (EI) network and a sink layer of neurons for readout. Synaptic plasticity in the form of STDP is imposed on all the excitatory and inhibitory synapses at all times. While long-term excitatory STDP enables sparse and efficient learning of the salient features in inputs, inhibitory STDP enables this learning to be stable by establishing a balance between excitatory and inhibitory currents at each neuron in the network. The synaptic weights between source and reservoir neurons form a basis set for the input patterns. The neural trajectories generated in the reservoir due to input stimulation and lateral connections between reservoir neurons can be readout by the sink layer neurons. This activity is used for adaptation of synapses between reservoir and sink layer neurons. A new measure called the discriminability index (DI) is introduced to compute if the network can discriminate between old patterns already presented in an initial training session. The DI is also used to compute if the network adapts to new patterns without losing its ability to discriminate among old patterns. The final outcome is that the network is able to correctly discriminate between all patterns—both old and new. This result holds as long as inhibitory synapses employ STDP to continuously enable current balance in the network. The results suggest a possible direction for future investigation into how spiking neural networks could address the stability-plasticity question despite having continuous synaptic plasticity. PMID:25566045

Cluster analysis of sputum cytokine-high profiles reveals diversity in T(h)2-high asthma patients.

PubMed

Seys, Sven F; Scheers, Hans; Van den Brande, Paul; Marijsse, Gudrun; Dilissen, Ellen; Van Den Bergh, Annelies; Goeminne, Pieter C; Hellings, Peter W; Ceuppens, Jan L; Dupont, Lieven J; Bullens, Dominique M A

2017-02-23

Asthma is characterized by a heterogeneous inflammatory profile and can be subdivided into T(h)2-high and T(h)2-low airway inflammation. Profiling of a broader panel of airway cytokines in large unselected patient cohorts is lacking. Patients (n = 205) were defined as being "cytokine-low/high" if sputum mRNA expression of a particular cytokine was outside the respective 10 th /90 th percentile range of the control group (n = 80). Unsupervised hierarchical clustering was used to determine clusters based on sputum cytokine profiles. Half of patients (n = 108; 52.6%) had a classical T(h)2-high ("IL-4-, IL-5- and/or IL-13-high") sputum cytokine profile. Unsupervised cluster analysis revealed 5 clusters. Patients with an "IL-4- and/or IL-13-high" pattern surprisingly did not cluster but were equally distributed among the 5 clusters. Patients with an "IL-5-, IL-17A-/F- and IL-25- high" profile were restricted to cluster 1 (n = 24) with increased sputum eosinophil as well as neutrophil counts and poor lung function parameters at baseline and 2 years later. Four other clusters were identified: "IL-5-high or IL-10-high" (n = 16), "IL-6-high" (n = 8), "IL-22-high" (n = 25). Cluster 5 (n = 132) consists of patients without "cytokine-high" pattern or patients with only high IL-4 and/or IL-13. We identified 5 unique asthma molecular phenotypes by biological clustering. Type 2 cytokines cluster with non-type 2 cytokines in 4 out of 5 clusters. Unsupervised analysis thus not supports a priori type 2 versus non-type 2 molecular phenotypes. www.clinicaltrials.gov NCT01224938. Registered 18 October 2010.

Insights into quasar UV spectra using unsupervised clustering analysis

NASA Astrophysics Data System (ADS)

Tammour, A.; Gallagher, S. C.; Daley, M.; Richards, G. T.

2016-06-01

Machine learning techniques can provide powerful tools to detect patterns in multidimensional parameter space. We use K-means - a simple yet powerful unsupervised clustering algorithm which picks out structure in unlabelled data - to study a sample of quasar UV spectra from the Quasar Catalog of the 10th Data Release of the Sloan Digital Sky Survey (SDSS-DR10) of Paris et al. Detecting patterns in large data sets helps us gain insights into the physical conditions and processes giving rise to the observed properties of quasars. We use K-means to find clusters in the parameter space of the equivalent width (EW), the blue- and red-half-width at half-maximum (HWHM) of the Mg II 2800 Å line, the C IV 1549 Å line, and the C III] 1908 Å blend in samples of broad absorption line (BAL) and non-BAL quasars at redshift 1.6-2.1. Using this method, we successfully recover correlations well-known in the UV regime such as the anti-correlation between the EW and blueshift of the C IV emission line and the shape of the ionizing spectra energy distribution (SED) probed by the strength of He II and the Si III]/C III] ratio. We find this to be particularly evident when the properties of C III] are used to find the clusters, while those of Mg II proved to be less strongly correlated with the properties of the other lines in the spectra such as the width of C IV or the Si III]/C III] ratio. We conclude that unsupervised clustering methods (such as K-means) are powerful methods for finding `natural' binning boundaries in multidimensional data sets and discuss caveats and future work.

Estimation of tissue optical parameters with hyperspectral imaging and spectral unmixing

NASA Astrophysics Data System (ADS)

Lu, Guolan; Qin, Xulei; Wang, Dongsheng; Chen, Zhuo G.; Fei, Baowei

2015-03-01

Early detection of oral cancer and its curable precursors can improve patient survival and quality of life. Hyperspectral imaging (HSI) holds the potential for noninvasive early detection of oral cancer. The quantification of tissue chromophores by spectral unmixing of hyperspectral images could provide insights for evaluating cancer progression. In this study, non-negative matrix factorization has been applied for decomposing hyperspectral images into physiologically meaningful chromophore concentration maps. The approach has been validated by computer-simulated hyperspectral images and in vivo tumor hyperspectral images from a head and neck cancer animal model.

Sparse alignment for robust tensor learning.

PubMed

Lai, Zhihui; Wong, Wai Keung; Xu, Yong; Zhao, Cairong; Sun, Mingming

2014-10-01

Multilinear/tensor extensions of manifold learning based algorithms have been widely used in computer vision and pattern recognition. This paper first provides a systematic analysis of the multilinear extensions for the most popular methods by using alignment techniques, thereby obtaining a general tensor alignment framework. From this framework, it is easy to show that the manifold learning based tensor learning methods are intrinsically different from the alignment techniques. Based on the alignment framework, a robust tensor learning method called sparse tensor alignment (STA) is then proposed for unsupervised tensor feature extraction. Different from the existing tensor learning methods, L1- and L2-norms are introduced to enhance the robustness in the alignment step of the STA. The advantage of the proposed technique is that the difficulty in selecting the size of the local neighborhood can be avoided in the manifold learning based tensor feature extraction algorithms. Although STA is an unsupervised learning method, the sparsity encodes the discriminative information in the alignment step and provides the robustness of STA. Extensive experiments on the well-known image databases as well as action and hand gesture databases by encoding object images as tensors demonstrate that the proposed STA algorithm gives the most competitive performance when compared with the tensor-based unsupervised learning methods.

Unsupervised segmentation of lungs from chest radiographs

NASA Astrophysics Data System (ADS)

Ghosh, Payel; Antani, Sameer K.; Long, L. Rodney; Thoma, George R.

2012-03-01

This paper describes our preliminary investigations for deriving and characterizing coarse-level textural regions present in the lung field on chest radiographs using unsupervised grow-cut (UGC), a cellular automaton based unsupervised segmentation technique. The segmentation has been performed on a publicly available data set of chest radiographs. The algorithm is useful for this application because it automatically converges to a natural segmentation of the image from random seed points using low-level image features such as pixel intensity values and texture features. Our goal is to develop a portable screening system for early detection of lung diseases for use in remote areas in developing countries. This involves developing automated algorithms for screening x-rays as normal/abnormal with a high degree of sensitivity, and identifying lung disease patterns on chest x-rays. Automatically deriving and quantitatively characterizing abnormal regions present in the lung field is the first step toward this goal. Therefore, region-based features such as geometrical and pixel-value measurements were derived from the segmented lung fields. In the future, feature selection and classification will be performed to identify pathological conditions such as pulmonary tuberculosis on chest radiographs. Shape-based features will also be incorporated to account for occlusions of the lung field and by other anatomical structures such as the heart and diaphragm.

Rational Variety Mapping for Contrast-Enhanced Nonlinear Unsupervised Segmentation of Multispectral Images of Unstained Specimen

PubMed Central

Kopriva, Ivica; Hadžija, Mirko; Popović Hadžija, Marijana; Korolija, Marina; Cichocki, Andrzej

2011-01-01

A methodology is proposed for nonlinear contrast-enhanced unsupervised segmentation of multispectral (color) microscopy images of principally unstained specimens. The methodology exploits spectral diversity and spatial sparseness to find anatomical differences between materials (cells, nuclei, and background) present in the image. It consists of rth-order rational variety mapping (RVM) followed by matrix/tensor factorization. Sparseness constraint implies duality between nonlinear unsupervised segmentation and multiclass pattern assignment problems. Classes not linearly separable in the original input space become separable with high probability in the higher-dimensional mapped space. Hence, RVM mapping has two advantages: it takes implicitly into account nonlinearities present in the image (ie, they are not required to be known) and it increases spectral diversity (ie, contrast) between materials, due to increased dimensionality of the mapped space. This is expected to improve performance of systems for automated classification and analysis of microscopic histopathological images. The methodology was validated using RVM of the second and third orders of the experimental multispectral microscopy images of unstained sciatic nerve fibers (nervus ischiadicus) and of unstained white pulp in the spleen tissue, compared with a manually defined ground truth labeled by two trained pathophysiologists. The methodology can also be useful for additional contrast enhancement of images of stained specimens. PMID:21708116

Design of partially supervised classifiers for multispectral image data

NASA Technical Reports Server (NTRS)

Jeon, Byeungwoo; Landgrebe, David

1993-01-01

A partially supervised classification problem is addressed, especially when the class definition and corresponding training samples are provided a priori only for just one particular class. In practical applications of pattern classification techniques, a frequently observed characteristic is the heavy, often nearly impossible requirements on representative prior statistical class characteristics of all classes in a given data set. Considering the effort in both time and man-power required to have a well-defined, exhaustive list of classes with a corresponding representative set of training samples, this 'partially' supervised capability would be very desirable, assuming adequate classifier performance can be obtained. Two different classification algorithms are developed to achieve simplicity in classifier design by reducing the requirement of prior statistical information without sacrificing significant classifying capability. The first one is based on optimal significance testing, where the optimal acceptance probability is estimated directly from the data set. In the second approach, the partially supervised classification is considered as a problem of unsupervised clustering with initially one known cluster or class. A weighted unsupervised clustering procedure is developed to automatically define other classes and estimate their class statistics. The operational simplicity thus realized should make these partially supervised classification schemes very viable tools in pattern classification.

Geophysical phenomena classification by artificial neural networks

NASA Technical Reports Server (NTRS)

Gough, M. P.; Bruckner, J. R.

1995-01-01

Space science information systems involve accessing vast data bases. There is a need for an automatic process by which properties of the whole data set can be assimilated and presented to the user. Where data are in the form of spectrograms, phenomena can be detected by pattern recognition techniques. Presented are the first results obtained by applying unsupervised Artificial Neural Networks (ANN's) to the classification of magnetospheric wave spectra. The networks used here were a simple unsupervised Hamming network run on a PC and a more sophisticated CALM network run on a Sparc workstation. The ANN's were compared in their geophysical data recognition performance. CALM networks offer such qualities as fast learning, superiority in generalizing, the ability to continuously adapt to changes in the pattern set, and the possibility to modularize the network to allow the inter-relation between phenomena and data sets. This work is the first step toward an information system interface being developed at Sussex, the Whole Information System Expert (WISE). Phenomena in the data are automatically identified and provided to the user in the form of a data occurrence morphology, the Whole Information System Data Occurrence Morphology (WISDOM), along with relationships to other parameters and phenomena.

The Characteristics of Binary Spike-Time-Dependent Plasticity in HfO2-Based RRAM and Applications for Pattern Recognition

NASA Astrophysics Data System (ADS)

Zhou, Zheng; Liu, Chen; Shen, Wensheng; Dong, Zhen; Chen, Zhe; Huang, Peng; Liu, Lifeng; Liu, Xiaoyan; Kang, Jinfeng

2017-04-01

A binary spike-time-dependent plasticity (STDP) protocol based on one resistive-switching random access memory (RRAM) device was proposed and experimentally demonstrated in the fabricated RRAM array. Based on the STDP protocol, a novel unsupervised online pattern recognition system including RRAM synapses and CMOS neurons is developed. Our simulations show that the system can efficiently compete the handwritten digits recognition task, which indicates the feasibility of using the RRAM-based binary STDP protocol in neuromorphic computing systems to obtain good performance.

Generation, Validation, and Application of Abundance Map Reference Data for Spectral Unmixing

NASA Astrophysics Data System (ADS)

Williams, McKay D.

Reference data ("ground truth") maps traditionally have been used to assess the accuracy of imaging spectrometer classification algorithms. However, these reference data can be prohibitively expensive to produce, often do not include sub-pixel abundance estimates necessary to assess spectral unmixing algorithms, and lack published validation reports. Our research proposes methodologies to efficiently generate, validate, and apply abundance map reference data (AMRD) to airborne remote sensing scenes. We generated scene-wide AMRD for three different remote sensing scenes using our remotely sensed reference data (RSRD) technique, which spatially aggregates unmixing results from fine scale imagery (e.g., 1-m Ground Sample Distance (GSD)) to co-located coarse scale imagery (e.g., 10-m GSD or larger). We validated the accuracy of this methodology by estimating AMRD in 51 randomly-selected 10 m x 10 m plots, using seven independent methods and observers, including field surveys by two observers, imagery analysis by two observers, and RSRD using three algorithms. Results indicated statistically-significant differences between all versions of AMRD, suggesting that all forms of reference data need to be validated. Given these significant differences between the independent versions of AMRD, we proposed that the mean of all (MOA) versions of reference data for each plot and class were most likely to represent true abundances. We then compared each version of AMRD to MOA. Best case accuracy was achieved by a version of imagery analysis, which had a mean coverage area error of 2.0%, with a standard deviation of 5.6%. One of the RSRD algorithms was nearly as accurate, achieving a mean error of 3.0%, with a standard deviation of 6.3%, showing the potential of RSRD-based AMRD generation. Application of validated AMRD to specific coarse scale imagery involved three main parts: 1) spatial alignment of coarse and fine scale imagery, 2) aggregation of fine scale abundances to produce coarse scale imagery-specific AMRD, and 3) demonstration of comparisons between coarse scale unmixing abundances and AMRD. Spatial alignment was performed using our scene-wide spectral comparison (SWSC) algorithm, which aligned imagery with accuracy approaching the distance of a single fine scale pixel. We compared simple rectangular aggregation to coarse sensor point spread function (PSF) aggregation, and found that the PSF approach returned lower error, but that rectangular aggregation more accurately estimated true abundances at ground level. We demonstrated various metrics for comparing unmixing results to AMRD, including mean absolute error (MAE) and linear regression (LR). We additionally introduced reference data mean adjusted MAE (MA-MAE), and reference data confidence interval adjusted MAE (CIA-MAE), which account for known error in the reference data itself. MA-MAE analysis indicated that fully constrained linear unmixing of coarse scale imagery across all three scenes returned an error of 10.83% per class and pixel, with regression analysis yielding a slope = 0.85, intercept = 0.04, and R2 = 0.81. Our reference data research has demonstrated a viable methodology to efficiently generate, validate, and apply AMRD to specific examples of airborne remote sensing imagery, thereby enabling direct quantitative assessment of spectral unmixing performance.

Unsupervised classification of operator workload from brain signals.

PubMed

Schultze-Kraft, Matthias; Dähne, Sven; Gugler, Manfred; Curio, Gabriel; Blankertz, Benjamin

2016-06-01

In this study we aimed for the classification of operator workload as it is expected in many real-life workplace environments. We explored brain-signal based workload predictors that differ with respect to the level of label information required for training, including entirely unsupervised approaches. Subjects executed a task on a touch screen that required continuous effort of visual and motor processing with alternating difficulty. We first employed classical approaches for workload state classification that operate on the sensor space of EEG and compared those to the performance of three state-of-the-art spatial filtering methods: common spatial patterns (CSPs) analysis, which requires binary label information; source power co-modulation (SPoC) analysis, which uses the subjects' error rate as a target function; and canonical SPoC (cSPoC) analysis, which solely makes use of cross-frequency power correlations induced by different states of workload and thus represents an unsupervised approach. Finally, we investigated the effects of fusing brain signals and peripheral physiological measures (PPMs) and examined the added value for improving classification performance. Mean classification accuracies of 94%, 92% and 82% were achieved with CSP, SPoC, cSPoC, respectively. These methods outperformed the approaches that did not use spatial filtering and they extracted physiologically plausible components. The performance of the unsupervised cSPoC is significantly increased by augmenting it with PPM features. Our analyses ensured that the signal sources used for classification were of cortical origin and not contaminated with artifacts. Our findings show that workload states can be successfully differentiated from brain signals, even when less and less information from the experimental paradigm is used, thus paving the way for real-world applications in which label information may be noisy or entirely unavailable.

Advanced Treatment Monitoring for Olympic-Level Athletes Using Unsupervised Modeling Techniques

PubMed Central

Siedlik, Jacob A.; Bergeron, Charles; Cooper, Michael; Emmons, Russell; Moreau, William; Nabhan, Dustin; Gallagher, Philip; Vardiman, John P.

2016-01-01

Context Analysis of injury and illness data collected at large international competitions provides the US Olympic Committee and the national governing bodies for each sport with information to best prepare for future competitions. Research in which authors have evaluated medical contacts to provide the expected level of medical care and sports medicine services at international competitions is limited. Objective To analyze the medical-contact data for athletes, staff, and coaches who participated in the 2011 Pan American Games in Guadalajara, Mexico, using unsupervised modeling techniques to identify underlying treatment patterns. Design Descriptive epidemiology study. Setting Pan American Games. Patients or Other Participants A total of 618 US athletes (337 males, 281 females) participated in the 2011 Pan American Games. Main Outcome Measure(s) Medical data were recorded from the injury-evaluation and injury-treatment forms used by clinicians assigned to the central US Olympic Committee Sport Medicine Clinic and satellite locations during the operational 17-day period of the 2011 Pan American Games. We used principal components analysis and agglomerative clustering algorithms to identify and define grouped modalities. Lift statistics were calculated for within-cluster subgroups. Results Principal component analyses identified 3 components, accounting for 72.3% of the variability in datasets. Plots of the principal components showed that individual contacts focused on 4 treatment clusters: massage, paired manipulation and mobilization, soft tissue therapy, and general medical. Conclusions Unsupervised modeling techniques were useful for visualizing complex treatment data and provided insights for improved treatment modeling in athletes. Given its ability to detect clinically relevant treatment pairings in large datasets, unsupervised modeling should be considered a feasible option for future analyses of medical-contact data from international competitions. PMID:26794628

Unsupervised classification of operator workload from brain signals

NASA Astrophysics Data System (ADS)

Schultze-Kraft, Matthias; Dähne, Sven; Gugler, Manfred; Curio, Gabriel; Blankertz, Benjamin

2016-06-01

Objective. In this study we aimed for the classification of operator workload as it is expected in many real-life workplace environments. We explored brain-signal based workload predictors that differ with respect to the level of label information required for training, including entirely unsupervised approaches. Approach. Subjects executed a task on a touch screen that required continuous effort of visual and motor processing with alternating difficulty. We first employed classical approaches for workload state classification that operate on the sensor space of EEG and compared those to the performance of three state-of-the-art spatial filtering methods: common spatial patterns (CSPs) analysis, which requires binary label information; source power co-modulation (SPoC) analysis, which uses the subjects’ error rate as a target function; and canonical SPoC (cSPoC) analysis, which solely makes use of cross-frequency power correlations induced by different states of workload and thus represents an unsupervised approach. Finally, we investigated the effects of fusing brain signals and peripheral physiological measures (PPMs) and examined the added value for improving classification performance. Main results. Mean classification accuracies of 94%, 92% and 82% were achieved with CSP, SPoC, cSPoC, respectively. These methods outperformed the approaches that did not use spatial filtering and they extracted physiologically plausible components. The performance of the unsupervised cSPoC is significantly increased by augmenting it with PPM features. Significance. Our analyses ensured that the signal sources used for classification were of cortical origin and not contaminated with artifacts. Our findings show that workload states can be successfully differentiated from brain signals, even when less and less information from the experimental paradigm is used, thus paving the way for real-world applications in which label information may be noisy or entirely unavailable.

Comparing performance of standard and iterative linear unmixing methods for hyperspectral signatures

NASA Astrophysics Data System (ADS)

Gault, Travis R.; Jansen, Melissa E.; DeCoster, Mallory E.; Jansing, E. David; Rodriguez, Benjamin M.

2016-05-01

Linear unmixing is a method of decomposing a mixed signature to determine the component materials that are present in sensor's field of view, along with the abundances at which they occur. Linear unmixing assumes that energy from the materials in the field of view is mixed in a linear fashion across the spectrum of interest. Traditional unmixing methods can take advantage of adjacent pixels in the decomposition algorithm, but is not the case for point sensors. This paper explores several iterative and non-iterative methods for linear unmixing, and examines their effectiveness at identifying the individual signatures that make up simulated single pixel mixed signatures, along with their corresponding abundances. The major hurdle addressed in the proposed method is that no neighboring pixel information is available for the spectral signature of interest. Testing is performed using two collections of spectral signatures from the Johns Hopkins University Applied Physics Laboratory's Signatures Database software (SigDB): a hand-selected small dataset of 25 distinct signatures from a larger dataset of approximately 1600 pure visible/near-infrared/short-wave-infrared (VIS/NIR/SWIR) spectra. Simulated spectra are created with three and four material mixtures randomly drawn from a dataset originating from SigDB, where the abundance of one material is swept in 10% increments from 10% to 90%with the abundances of the other materials equally divided amongst the remainder. For the smaller dataset of 25 signatures, all combinations of three or four materials are used to create simulated spectra, from which the accuracy of materials returned, as well as the correctness of the abundances, is compared to the inputs. The experiment is expanded to include the signatures from the larger dataset of almost 1600 signatures evaluated using a Monte Carlo scheme with 5000 draws of three or four materials to create the simulated mixed signatures. The spectral similarity of the inputs to the output component signatures is calculated using the spectral angle mapper. Results show that iterative methods significantly outperform the traditional methods under the given test conditions.

The New Possibilities from "Big Data" to Overlooked Associations Between Diabetes, Biochemical Parameters, Glucose Control, and Osteoporosis.

PubMed

Kruse, Christian

2018-06-01

To review current practices and technologies within the scope of "Big Data" that can further our understanding of diabetes mellitus and osteoporosis from large volumes of data. "Big Data" techniques involving supervised machine learning, unsupervised machine learning, and deep learning image analysis are presented with examples of current literature. Supervised machine learning can allow us to better predict diabetes-induced osteoporosis and understand relative predictor importance of diabetes-affected bone tissue. Unsupervised machine learning can allow us to understand patterns in data between diabetic pathophysiology and altered bone metabolism. Image analysis using deep learning can allow us to be less dependent on surrogate predictors and use large volumes of images to classify diabetes-induced osteoporosis and predict future outcomes directly from images. "Big Data" techniques herald new possibilities to understand diabetes-induced osteoporosis and ascertain our current ability to classify, understand, and predict this condition.

Automated mapping of impervious surfaces in urban and suburban areas: Linear spectral unmixing of high spatial resolution imagery

NASA Astrophysics Data System (ADS)

Yang, Jian; He, Yuhong

2017-02-01

Quantifying impervious surfaces in urban and suburban areas is a key step toward a sustainable urban planning and management strategy. With the availability of fine-scale remote sensing imagery, automated mapping of impervious surfaces has attracted growing attention. However, the vast majority of existing studies have selected pixel-based and object-based methods for impervious surface mapping, with few adopting sub-pixel analysis of high spatial resolution imagery. This research makes use of a vegetation-bright impervious-dark impervious linear spectral mixture model to characterize urban and suburban surface components. A WorldView-3 image acquired on May 9th, 2015 is analyzed for its potential in automated unmixing of meaningful surface materials for two urban subsets and one suburban subset in Toronto, ON, Canada. Given the wide distribution of shadows in urban areas, the linear spectral unmixing is implemented in non-shadowed and shadowed areas separately for the two urban subsets. The results indicate that the accuracy of impervious surface mapping in suburban areas reaches up to 86.99%, much higher than the accuracies in urban areas (80.03% and 79.67%). Despite its merits in mapping accuracy and automation, the application of our proposed vegetation-bright impervious-dark impervious model to map impervious surfaces is limited due to the absence of soil component. To further extend the operational transferability of our proposed method, especially for the areas where plenty of bare soils exist during urbanization or reclamation, it is still of great necessity to mask out bare soils by automated classification prior to the implementation of linear spectral unmixing.

Predicting temperate forest stand types using only structural profiles from discrete return airborne lidar

NASA Astrophysics Data System (ADS)

Fedrigo, Melissa; Newnham, Glenn J.; Coops, Nicholas C.; Culvenor, Darius S.; Bolton, Douglas K.; Nitschke, Craig R.

2018-02-01

Light detection and ranging (lidar) data have been increasingly used for forest classification due to its ability to penetrate the forest canopy and provide detail about the structure of the lower strata. In this study we demonstrate forest classification approaches using airborne lidar data as inputs to random forest and linear unmixing classification algorithms. Our results demonstrated that both random forest and linear unmixing models identified a distribution of rainforest and eucalypt stands that was comparable to existing ecological vegetation class (EVC) maps based primarily on manual interpretation of high resolution aerial imagery. Rainforest stands were also identified in the region that have not previously been identified in the EVC maps. The transition between stand types was better characterised by the random forest modelling approach. In contrast, the linear unmixing model placed greater emphasis on field plots selected as endmembers which may not have captured the variability in stand structure within a single stand type. The random forest model had the highest overall accuracy (84%) and Cohen's kappa coefficient (0.62). However, the classification accuracy was only marginally better than linear unmixing. The random forest model was applied to a region in the Central Highlands of south-eastern Australia to produce maps of stand type probability, including areas of transition (the 'ecotone') between rainforest and eucalypt forest. The resulting map provided a detailed delineation of forest classes, which specifically recognised the coalescing of stand types at the landscape scale. This represents a key step towards mapping the structural and spatial complexity of these ecosystems, which is important for both their management and conservation.

Double-Barrier Memristive Devices for Unsupervised Learning and Pattern Recognition.

PubMed

Hansen, Mirko; Zahari, Finn; Ziegler, Martin; Kohlstedt, Hermann

2017-01-01

The use of interface-based resistive switching devices for neuromorphic computing is investigated. In a combined experimental and numerical study, the important device parameters and their impact on a neuromorphic pattern recognition system are studied. The memristive cells consist of a layer sequence Al/Al 2 O 3 /Nb x O y /Au and are fabricated on a 4-inch wafer. The key functional ingredients of the devices are a 1.3 nm thick Al 2 O 3 tunnel barrier and a 2.5 mm thick Nb x O y memristive layer. Voltage pulse measurements are used to study the electrical conditions for the emulation of synaptic functionality of single cells for later use in a recognition system. The results are evaluated and modeled in the framework of the plasticity model of Ziegler et al. Based on this model, which is matched to experimental data from 84 individual devices, the network performance with regard to yield, reliability, and variability is investigated numerically. As the network model, a computing scheme for pattern recognition and unsupervised learning based on the work of Querlioz et al. (2011), Sheridan et al. (2014), Zahari et al. (2015) is employed. This is a two-layer feedforward network with a crossbar array of memristive devices, leaky integrate-and-fire output neurons including a winner-takes-all strategy, and a stochastic coding scheme for the input pattern. As input pattern, the full data set of digits from the MNIST database is used. The numerical investigation indicates that the experimentally obtained yield, reliability, and variability of the memristive cells are suitable for such a network. Furthermore, evidence is presented that their strong I - V non-linearity might avoid the need for selector devices in crossbar array structures.

Glaucomatous patterns in Frequency Doubling Technology (FDT) perimetry data identified by unsupervised machine learning classifiers.

PubMed

Bowd, Christopher; Weinreb, Robert N; Balasubramanian, Madhusudhanan; Lee, Intae; Jang, Giljin; Yousefi, Siamak; Zangwill, Linda M; Medeiros, Felipe A; Girkin, Christopher A; Liebmann, Jeffrey M; Goldbaum, Michael H

2014-01-01

The variational Bayesian independent component analysis-mixture model (VIM), an unsupervised machine-learning classifier, was used to automatically separate Matrix Frequency Doubling Technology (FDT) perimetry data into clusters of healthy and glaucomatous eyes, and to identify axes representing statistically independent patterns of defect in the glaucoma clusters. FDT measurements were obtained from 1,190 eyes with normal FDT results and 786 eyes with abnormal FDT results from the UCSD-based Diagnostic Innovations in Glaucoma Study (DIGS) and African Descent and Glaucoma Evaluation Study (ADAGES). For all eyes, VIM input was 52 threshold test points from the 24-2 test pattern, plus age. FDT mean deviation was -1.00 dB (S.D. = 2.80 dB) and -5.57 dB (S.D. = 5.09 dB) in FDT-normal eyes and FDT-abnormal eyes, respectively (p<0.001). VIM identified meaningful clusters of FDT data and positioned a set of statistically independent axes through the mean of each cluster. The optimal VIM model separated the FDT fields into 3 clusters. Cluster N contained primarily normal fields (1109/1190, specificity 93.1%) and clusters G1 and G2 combined, contained primarily abnormal fields (651/786, sensitivity 82.8%). For clusters G1 and G2 the optimal number of axes were 2 and 5, respectively. Patterns automatically generated along axes within the glaucoma clusters were similar to those known to be indicative of glaucoma. Fields located farther from the normal mean on each glaucoma axis showed increasing field defect severity. VIM successfully separated FDT fields from healthy and glaucoma eyes without a priori information about class membership, and identified familiar glaucomatous patterns of loss.

A randomized, double-blind, placebo-controlled trial of single-dose ciprofloxacin versus erythromycin for the treatment of chancroid in Nairobi, Kenya.

PubMed

Malonza, I M; Tyndall, M W; Ndinya-Achola, J O; Maclean, I; Omar, S; MacDonald, K S; Perriens, J; Orle, K; Plummer, F A; Ronald, A R; Moses, S

1999-12-01

A randomized, double-blind, placebo-controlled clinical trial was conducted in Nairobi, Kenya, to compare single-dose ciprofloxacin with a 7-day course of erythromycin for the treatment of chancroid. In all, 208 men and 37 women presenting with genital ulcers clinically compatible with chancroid were enrolled. Ulcer etiology was determined using culture techniques for chancroid, serology for syphilis, and a multiplex polymerase chain reaction for chancroid, syphilis, and herpes simplex virus (HSV). Ulcer etiology was 31% unmixed chancroid, 23% unmixed syphilis, 16% unmixed HSV, 15% mixed etiology, and 15% unknown. For 111 participants with chancroid, cure rates were 92% with ciprofloxacin and 91% with erythromycin. For all study participants, the treatment failure rate was 15%, mostly related to ulcer etiologies of HSV infection or syphilis, and treatment failure was 3 times more frequent in human immunodeficiency virus-infected subjects than in others, mostly owing to HSV infection. Ciprofloxacin is an effective single-dose treatment for chancroid, but current recommendations for empiric therapy of genital ulcers may result in high treatment failure due to HSV infection.

Mapping tropical rainforest canopies using multi-temporal spaceborne imaging spectroscopy

NASA Astrophysics Data System (ADS)

Somers, Ben; Asner, Gregory P.

2013-10-01

The use of imaging spectroscopy for florisic mapping of forests is complicated by the spectral similarity among coexisting species. Here we evaluated an alternative spectral unmixing strategy combining a time series of EO-1 Hyperion images and an automated feature selection strategy in MESMA. Instead of using the same spectral subset to unmix each image pixel, our modified approach allowed the spectral subsets to vary on a per pixel basis such that each pixel is evaluated using a spectral subset tuned towards maximal separability of its specific endmember class combination or species mixture. The potential of the new approach for floristic mapping of tree species in Hawaiian rainforests was quantitatively demonstrated using both simulated and actual hyperspectral image time-series. With a Cohen's Kappa coefficient of 0.65, our approach provided a more accurate tree species map compared to MESMA (Kappa = 0.54). In addition, by the selection of spectral subsets our approach was about 90% faster than MESMA. The flexible or adaptive use of band sets in spectral unmixing as such provides an interesting avenue to address spectral similarities in complex vegetation canopies.

Visual enhancement of unmixed multispectral imagery using adaptive smoothing

USGS Publications Warehouse

Lemeshewsky, G.P.; Rahman, Z.-U.; Schowengerdt, R.A.; Reichenbach, S.E.

2004-01-01

Adaptive smoothing (AS) has been previously proposed as a method to smooth uniform regions of an image, retain contrast edges, and enhance edge boundaries. The method is an implementation of the anisotropic diffusion process which results in a gray scale image. This paper discusses modifications to the AS method for application to multi-band data which results in a color segmented image. The process was used to visually enhance the three most distinct abundance fraction images produced by the Lagrange constraint neural network learning-based unmixing of Landsat 7 Enhanced Thematic Mapper Plus multispectral sensor data. A mutual information-based method was applied to select the three most distinct fraction images for subsequent visualization as a red, green, and blue composite. A reported image restoration technique (partial restoration) was applied to the multispectral data to reduce unmixing error, although evaluation of the performance of this technique was beyond the scope of this paper. The modified smoothing process resulted in a color segmented image with homogeneous regions separated by sharpened, coregistered multiband edges. There was improved class separation with the segmented image, which has importance to subsequent operations involving data classification.

Ion-beam mixed ultra-thin cobalt suicide (CoSi2) films by cobalt sputtering and rapid thermal annealing

NASA Astrophysics Data System (ADS)

Kal, S.; Kasko, I.; Ryssel, H.

1995-10-01

The influence of ion-beam mixing on ultra-thin cobalt silicide (CoSi2) formation was investigated by characterizing the ion-beam mixed and unmixed CoSi2 films. A Ge+ ion-implantation through the Co film prior to silicidation causes an interface mixing of the cobalt film with the silicon substrate and results in improved silicide-to-silicon interface roughness. Rapid thermal annealing was used to form Ge+ ion mixed and unmixed thin CoSi2 layer from 10 nm sputter deposited Co film. The silicide films were characterized by secondary neutral mass spectroscopy, x-ray diffraction, tunneling electron microscopy (TEM), Rutherford backscattering, and sheet resistance measurements. The experi-mental results indicate that the final rapid thermal annealing temperature should not exceed 800°C for thin (<50 nm) CoSi2 preparation. A comparison of the plan-view and cross-section TEM micrographs of the ion-beam mixed and unmixed CoSi2 films reveals that Ge+ ion mixing (45 keV, 1 × 1015 cm-2) produces homogeneous silicide with smooth silicide-to-silicon interface.

Direct comparison of Fe-Cr unmixing characterization by atom probe tomography and small angle scattering

DOE Office of Scientific and Technical Information (OSTI.GOV)

Couturier, Laurent, E-mail: laurent.couturier55@ho

The fine microstructure obtained by unmixing of a solid solution either by classical precipitation or spinodal decomposition is often characterized either by small angle scattering or atom probe tomography. This article shows that a common data analysis framework can be used to analyze data obtained from these two techniques. An example of the application of this common analysis is given for characterization of the unmixing of the Fe-Cr matrix of a 15-5 PH stainless steel during long-term ageing at 350 °C and 400 °C. A direct comparison of the Cr composition fluctuations amplitudes and characteristic lengths obtained with both techniquesmore » is made showing a quantitative agreement for the fluctuation amplitudes. The origin of the discrepancy remaining for the characteristic lengths is discussed. - Highlights: •Common analysis framework for atom probe tomography and small angle scattering •Comparison of same microstructural characteristics obtained using both techniques •Good correlation of Cr composition fluctuations amplitudes from both techniques •Good correlation of Cr composition fluctuations amplitudes with classic V parameter.« less

CNN: a speaker recognition system using a cascaded neural network.

PubMed

Zaki, M; Ghalwash, A; Elkouny, A A

1996-05-01

The main emphasis of this paper is to present an approach for combining supervised and unsupervised neural network models to the issue of speaker recognition. To enhance the overall operation and performance of recognition, the proposed strategy integrates the two techniques, forming one global model called the cascaded model. We first present a simple conventional technique based on the distance measured between a test vector and a reference vector for different speakers in the population. This particular distance metric has the property of weighting down the components in those directions along which the intraspeaker variance is large. The reason for presenting this method is to clarify the discrepancy in performance between the conventional and neural network approach. We then introduce the idea of using unsupervised learning technique, presented by the winner-take-all model, as a means of recognition. Due to several tests that have been conducted and in order to enhance the performance of this model, dealing with noisy patterns, we have preceded it with a supervised learning model--the pattern association model--which acts as a filtration stage. This work includes both the design and implementation of both conventional and neural network approaches to recognize the speakers templates--which are introduced to the system via a voice master card and preprocessed before extracting the features used in the recognition. The conclusion indicates that the system performance in case of neural network is better than that of the conventional one, achieving a smooth degradation in respect of noisy patterns, and higher performance in respect of noise-free patterns.

Accuracy of un-supervised versus provider-supervised self-administered HIV testing in Uganda: A randomized implementation trial.

PubMed

Asiimwe, Stephen; Oloya, James; Song, Xiao; Whalen, Christopher C

2014-12-01

Unsupervised HIV self-testing (HST) has potential to increase knowledge of HIV status; however, its accuracy is unknown. To estimate the accuracy of unsupervised HST in field settings in Uganda, we performed a non-blinded, randomized controlled, non-inferiority trial of unsupervised compared with supervised HST among selected high HIV risk fisherfolk (22.1 % HIV Prevalence) in three fishing villages in Uganda between July and September 2013. The study enrolled 246 participants and randomized them in a 1:1 ratio to unsupervised HST or provider-supervised HST. In an intent-to-treat analysis, the HST sensitivity was 90 % in the unsupervised arm and 100 % among the provider-supervised, yielding a difference 0f -10 % (90 % CI -21, 1 %); non-inferiority was not shown. In a per protocol analysis, the difference in sensitivity was -5.6 % (90 % CI -14.4, 3.3 %) and did show non-inferiority. We conclude that unsupervised HST is feasible in rural Africa and may be non-inferior to provider-supervised HST.

Source apportionments of PM2.5 organic carbon using molecular marker Positive Matrix Factorization and comparison of results from different receptor models

NASA Astrophysics Data System (ADS)

Heo, Jongbae; Dulger, Muaz; Olson, Michael R.; McGinnis, Jerome E.; Shelton, Brandon R.; Matsunaga, Aiko; Sioutas, Constantinos; Schauer, James J.

2013-07-01

Four hundred fine particulate matter (PM2.5) samples collected over a 1-year period at two sites in the Los Angeles Basin were analyzed for organic carbon (OC), elemental carbon (EC), water soluble organic carbon (WSOC) and organic molecular markers. The results were used in a Positive Matrix Factorization (PMF) receptor model to obtain daily, monthly and annual average source contributions to PM2.5 OC. Results of the PMF model showed similar source categories with comparable year-long contributions to PM2.5 OC across the sites. Five source categories providing reasonably stable profiles were identified: mobile, wood smoke, primary biogenic, and two types of secondary organic carbon (SOC) (i.e., anthropogenic and biogenic emissions). Total primary emission factors and total SOC factors contributed approximately 60% and 40%, respectively, to the annual-average OC concentrations. Primary sources showed strong seasonal patterns with high winter peaks and low summer peaks, while SOC showed a reverse pattern with highs in the spring and summer in the region. Interestingly, smoke from forest fires which occurred episodically in California during the summer and fall of 2009 was identified and combined with the primary biogenic source as one distinct factor to the OC budget. The PMF resolved factors were further investigated and compared to a chemical mass balance (CMB) model and a second multi-variant receptor model (UNMIX) using molecular markers considered in the PMF. Good agreement between the source contribution from mobile sources and biomass burning for three models were obtained, providing additional weight of evidence that these source apportionment techniques are sufficiently accurate for policy development. However, the CMB model did not quantify primary biogenic emissions, which were included in other sources with the SOC. Both multivariate receptor models, the PMF and the UNMIX, were unable to separate source contributions from diesel and gasoline engines.

Information Compression, Multiple Alignment, and the Representation and Processing of Knowledge in the Brain.

PubMed

Wolff, J Gerard

2016-01-01

The SP theory of intelligence , with its realization in the SP computer model , aims to simplify and integrate observations and concepts across artificial intelligence, mainstream computing, mathematics, and human perception and cognition, with information compression as a unifying theme. This paper describes how abstract structures and processes in the theory may be realized in terms of neurons, their interconnections, and the transmission of signals between neurons. This part of the SP theory- SP-neural -is a tentative and partial model for the representation and processing of knowledge in the brain. Empirical support for the SP theory-outlined in the paper-provides indirect support for SP-neural. In the abstract part of the SP theory (SP-abstract), all kinds of knowledge are represented with patterns , where a pattern is an array of atomic symbols in one or two dimensions. In SP-neural, the concept of a "pattern" is realized as an array of neurons called a pattern assembly , similar to Hebb's concept of a "cell assembly" but with important differences. Central to the processing of information in SP-abstract is information compression via the matching and unification of patterns (ICMUP) and, more specifically, information compression via the powerful concept of multiple alignment , borrowed and adapted from bioinformatics. Processes such as pattern recognition, reasoning and problem solving are achieved via the building of multiple alignments, while unsupervised learning is achieved by creating patterns from sensory information and also by creating patterns from multiple alignments in which there is a partial match between one pattern and another. It is envisaged that, in SP-neural, short-lived neural structures equivalent to multiple alignments will be created via an inter-play of excitatory and inhibitory neural signals. It is also envisaged that unsupervised learning will be achieved by the creation of pattern assemblies from sensory information and from the neural equivalents of multiple alignments, much as in the non-neural SP theory-and significantly different from the "Hebbian" kinds of learning which are widely used in the kinds of artificial neural network that are popular in computer science. The paper discusses several associated issues, with relevant empirical evidence.

Open-air multispectral fluorescence-guided surgery platform for intraoperative detection of malignant tissue under ambient lighting conditions

NASA Astrophysics Data System (ADS)

Behrooz, Ali; Vasquez, Kristine O.; Waterman, Peter; Meganck, Jeff; Peterson, Jeffrey D.; Miller, Peter; Kempner, Joshua

2017-02-01

Intraoperative resection of tumors currently relies upon the surgeon's ability to visually locate and palpate tumor nodules. Undetected residual malignant tissue often results in the need for additional treatment or surgical intervention. The Solaris platform is a multispectral open-air fluorescence imaging system designed for translational fluorescence-guided surgery. Solaris supports video-rate imaging in four fixed fluorescence channels ranging from visible to near infrared, and a multispectral channel equipped with a liquid crystal tunable filter (LCTF) for multispectral image acquisition (520-620 nm). Identification of tumor margins using reagents emitting in the visible spectrum (400-650 nm), such as fluorescein isothiocyanate (FITC), present challenges considering the presence of auto-fluorescence from tissue and food in the gastrointestinal (GI) tract. To overcome this, Solaris acquires LCTF-based multispectral images, and by applying an automated spectral unmixing algorithm to the data, separates reagent fluorescence from tissue and food auto-fluorescence. The unmixing algorithm uses vertex component analysis to automatically extract the primary pure spectra, and resolves the reagent fluorescent signal using non-negative least squares. For validation, intraoperative in vivo studies were carried out in tumor-bearing rodents injected with FITC-dextran reagent that is primarily residing in malignant tissue 24 hours post injection. In the absence of unmixing, fluorescence from tumors is not distinguishable from that of surrounding tissue. Upon spectral unmixing, the FITC-labeled malignant regions become well defined and detectable. The results of these studies substantiate the multispectral power of Solaris in resolving FITC-based agent signal in deep tumor masses, under ambient and surgical light, and enhancing the ability to surgically resect them.

Use of airborne hyperspectral data to estimate residual heavy metal contamination and acidification potential in the Guadiamar floodplain Andalusia, Spain after the Aznacollar mining accident

NASA Astrophysics Data System (ADS)

Kemper, Thomas; Sommer, Stefan

2004-10-01

Field and airborne hyperspectral data was used to map residual contamination after a mining accident, by applying spectral mixture modelling. Test case was the Aznalcollar Mine (Southern Spain) accident, where heavy metal bearing sludge from a tailings pond was distributed over large areas of the Guadiamar flood plain. Although the sludge and the contaminated topsoils have been removed mechanically in the whole affected area, still high abundance of pyritic material remained on the ground. During dedicated field campaigns in two subsequent years soil samples were collected for geochemical and spectral laboratory analysis and spectral field measurements were carried out in parallel to data acquisition with the HyMap sensor. A Variable Multiple Endmember Spectral Mixture Analysis (VMESMA) tool was used providing possibilities of multiple endmember unmixing, aiming to estimate the quantities and distribution of the remaining tailings material. A spectrally based zonal partition of the area was introduced to allow the application of different submodels to the selected areas. Based on an iterative feedback process, the unmixing performance could be improved in each stage until an optimum level was reached. The sludge abundances obtained by unmixing the hyperspectral spectral data were confirmed by the field observations and chemical measurements of samples taken in the area. The semi-quantitative sludge abundances of residual pyritic material could be transformed into quantitative information for an assessment of acidification risk and distribution of residual heavy metal contamination based on an artificial mixture experiment. The unmixing of the second year images allowed identification of secondary minerals of pyrite as indicators of pyrite oxidation and associated acidification.

Arctic lead detection using a waveform unmixing algorithm from CryoSat-2 data

NASA Astrophysics Data System (ADS)

Lee, S.; Im, J.

2016-12-01

Arctic areas consist of ice floes, leads, and polynyas. While leads and polynyas account for small parts in the Arctic Ocean, they play a key role in exchanging heat flux, moisture, and momentum between the atmosphere and ocean in wintertime because of their huge temperature difference In this study, a linear waveform unmixing approach was proposed to detect lead fraction. CryoSat-2 waveforms for pure leads, sea ice, and ocean were used as end-members based on visual interpretation of MODIS images coincident with CryoSat-2 data. The unmixing model produced lead, sea ice, and ocean abundances and a threshold (> 0.7) was applied to make a binary classification between lead and sea ice. The unmixing model produced better results than the existing models in the literature, which are based on simple thresholding approaches. The results were also comparable with our previous research using machine learning based models (i.e., decision trees and random forest). A monthly lead fraction was calculated, dividing the number of detected leads by the total number of measurements. The lead fraction around Beaufort Sea and Fram strait was high due to the anti-cyclonic rotation of Beaufort Gyre and the outflows of sea ice to the Atlantic. The lead fraction maps produced in this study were matched well with monthly lead fraction maps in the literature. The areas with thin sea ice identified from our previous research correspond to the high lead fraction areas in the present study. Furthermore, sea ice roughness from ASCAT scatterometer was compared to a lead fraction map to see the relationship between surface roughness and lead distribution.

Estimation of white matter fiber parameters from compressed multiresolution diffusion MRI using sparse Bayesian learning.

PubMed

Pisharady, Pramod Kumar; Sotiropoulos, Stamatios N; Duarte-Carvajalino, Julio M; Sapiro, Guillermo; Lenglet, Christophe

2018-02-15

We present a sparse Bayesian unmixing algorithm BusineX: Bayesian Unmixing for Sparse Inference-based Estimation of Fiber Crossings (X), for estimation of white matter fiber parameters from compressed (under-sampled) diffusion MRI (dMRI) data. BusineX combines compressive sensing with linear unmixing and introduces sparsity to the previously proposed multiresolution data fusion algorithm RubiX, resulting in a method for improved reconstruction, especially from data with lower number of diffusion gradients. We formulate the estimation of fiber parameters as a sparse signal recovery problem and propose a linear unmixing framework with sparse Bayesian learning for the recovery of sparse signals, the fiber orientations and volume fractions. The data is modeled using a parametric spherical deconvolution approach and represented using a dictionary created with the exponential decay components along different possible diffusion directions. Volume fractions of fibers along these directions define the dictionary weights. The proposed sparse inference, which is based on the dictionary representation, considers the sparsity of fiber populations and exploits the spatial redundancy in data representation, thereby facilitating inference from under-sampled q-space. The algorithm improves parameter estimation from dMRI through data-dependent local learning of hyperparameters, at each voxel and for each possible fiber orientation, that moderate the strength of priors governing the parameter variances. Experimental results on synthetic and in-vivo data show improved accuracy with a lower uncertainty in fiber parameter estimates. BusineX resolves a higher number of second and third fiber crossings. For under-sampled data, the algorithm is also shown to produce more reliable estimates. Copyright © 2017 Elsevier Inc. All rights reserved.

Rational variety mapping for contrast-enhanced nonlinear unsupervised segmentation of multispectral images of unstained specimen.

PubMed

Kopriva, Ivica; Hadžija, Mirko; Popović Hadžija, Marijana; Korolija, Marina; Cichocki, Andrzej

2011-08-01

A methodology is proposed for nonlinear contrast-enhanced unsupervised segmentation of multispectral (color) microscopy images of principally unstained specimens. The methodology exploits spectral diversity and spatial sparseness to find anatomical differences between materials (cells, nuclei, and background) present in the image. It consists of rth-order rational variety mapping (RVM) followed by matrix/tensor factorization. Sparseness constraint implies duality between nonlinear unsupervised segmentation and multiclass pattern assignment problems. Classes not linearly separable in the original input space become separable with high probability in the higher-dimensional mapped space. Hence, RVM mapping has two advantages: it takes implicitly into account nonlinearities present in the image (ie, they are not required to be known) and it increases spectral diversity (ie, contrast) between materials, due to increased dimensionality of the mapped space. This is expected to improve performance of systems for automated classification and analysis of microscopic histopathological images. The methodology was validated using RVM of the second and third orders of the experimental multispectral microscopy images of unstained sciatic nerve fibers (nervus ischiadicus) and of unstained white pulp in the spleen tissue, compared with a manually defined ground truth labeled by two trained pathophysiologists. The methodology can also be useful for additional contrast enhancement of images of stained specimens. Copyright © 2011 American Society for Investigative Pathology. Published by Elsevier Inc. All rights reserved.

Intelligent Fault Diagnosis of Rotary Machinery Based on Unsupervised Multiscale Representation Learning

NASA Astrophysics Data System (ADS)

Jiang, Guo-Qian; Xie, Ping; Wang, Xiao; Chen, Meng; He, Qun

2017-11-01

The performance of traditional vibration based fault diagnosis methods greatly depends on those handcrafted features extracted using signal processing algorithms, which require significant amounts of domain knowledge and human labor, and do not generalize well to new diagnosis domains. Recently, unsupervised representation learning provides an alternative promising solution to feature extraction in traditional fault diagnosis due to its superior learning ability from unlabeled data. Given that vibration signals usually contain multiple temporal structures, this paper proposes a multiscale representation learning (MSRL) framework to learn useful features directly from raw vibration signals, with the aim to capture rich and complementary fault pattern information at different scales. In our proposed approach, a coarse-grained procedure is first employed to obtain multiple scale signals from an original vibration signal. Then, sparse filtering, a newly developed unsupervised learning algorithm, is applied to automatically learn useful features from each scale signal, respectively, and then the learned features at each scale to be concatenated one by one to obtain multiscale representations. Finally, the multiscale representations are fed into a supervised classifier to achieve diagnosis results. Our proposed approach is evaluated using two different case studies: motor bearing and wind turbine gearbox fault diagnosis. Experimental results show that the proposed MSRL approach can take full advantages of the availability of unlabeled data to learn discriminative features and achieved better performance with higher accuracy and stability compared to the traditional approaches.

Information Compression, Multiple Alignment, and the Representation and Processing of Knowledge in the Brain

PubMed Central

Wolff, J. Gerard

2016-01-01

The SP theory of intelligence, with its realization in the SP computer model, aims to simplify and integrate observations and concepts across artificial intelligence, mainstream computing, mathematics, and human perception and cognition, with information compression as a unifying theme. This paper describes how abstract structures and processes in the theory may be realized in terms of neurons, their interconnections, and the transmission of signals between neurons. This part of the SP theory—SP-neural—is a tentative and partial model for the representation and processing of knowledge in the brain. Empirical support for the SP theory—outlined in the paper—provides indirect support for SP-neural. In the abstract part of the SP theory (SP-abstract), all kinds of knowledge are represented with patterns, where a pattern is an array of atomic symbols in one or two dimensions. In SP-neural, the concept of a “pattern” is realized as an array of neurons called a pattern assembly, similar to Hebb's concept of a “cell assembly” but with important differences. Central to the processing of information in SP-abstract is information compression via the matching and unification of patterns (ICMUP) and, more specifically, information compression via the powerful concept of multiple alignment, borrowed and adapted from bioinformatics. Processes such as pattern recognition, reasoning and problem solving are achieved via the building of multiple alignments, while unsupervised learning is achieved by creating patterns from sensory information and also by creating patterns from multiple alignments in which there is a partial match between one pattern and another. It is envisaged that, in SP-neural, short-lived neural structures equivalent to multiple alignments will be created via an inter-play of excitatory and inhibitory neural signals. It is also envisaged that unsupervised learning will be achieved by the creation of pattern assemblies from sensory information and from the neural equivalents of multiple alignments, much as in the non-neural SP theory—and significantly different from the “Hebbian” kinds of learning which are widely used in the kinds of artificial neural network that are popular in computer science. The paper discusses several associated issues, with relevant empirical evidence. PMID:27857695

Terahertz spectral unmixing based method for identifying gastric cancer

NASA Astrophysics Data System (ADS)

Cao, Yuqi; Huang, Pingjie; Li, Xian; Ge, Weiting; Hou, Dibo; Zhang, Guangxin

2018-02-01

At present, many researchers are exploring biological tissue inspection using terahertz time-domain spectroscopy (THz-TDS) techniques. In this study, based on a modified hard modeling factor analysis method, terahertz spectral unmixing was applied to investigate the relationships between the absorption spectra in THz-TDS and certain biomarkers of gastric cancer in order to systematically identify gastric cancer. A probability distribution and box plot were used to extract the distinctive peaks that indicate carcinogenesis, and the corresponding weight distributions were used to discriminate the tissue types. The results of this work indicate that terahertz techniques have the potential to detect different levels of cancer, including benign tumors and polyps.

A novel highly parallel algorithm for linearly unmixing hyperspectral images

NASA Astrophysics Data System (ADS)

Guerra, Raúl; López, Sebastián.; Callico, Gustavo M.; López, Jose F.; Sarmiento, Roberto

2014-10-01

Endmember extraction and abundances calculation represent critical steps within the process of linearly unmixing a given hyperspectral image because of two main reasons. The first one is due to the need of computing a set of accurate endmembers in order to further obtain confident abundance maps. The second one refers to the huge amount of operations involved in these time-consuming processes. This work proposes an algorithm to estimate the endmembers of a hyperspectral image under analysis and its abundances at the same time. The main advantage of this algorithm is its high parallelization degree and the mathematical simplicity of the operations implemented. This algorithm estimates the endmembers as virtual pixels. In particular, the proposed algorithm performs the descent gradient method to iteratively refine the endmembers and the abundances, reducing the mean square error, according with the linear unmixing model. Some mathematical restrictions must be added so the method converges in a unique and realistic solution. According with the algorithm nature, these restrictions can be easily implemented. The results obtained with synthetic images demonstrate the well behavior of the algorithm proposed. Moreover, the results obtained with the well-known Cuprite dataset also corroborate the benefits of our proposal.

Robust Spectral Unmixing of Sparse Multispectral Lidar Waveforms using Gamma Markov Random Fields

DOE PAGES

Altmann, Yoann; Maccarone, Aurora; McCarthy, Aongus; ...

2017-05-10

Here, this paper presents a new Bayesian spectral un-mixing algorithm to analyse remote scenes sensed via sparse multispectral Lidar measurements. To a first approximation, in the presence of a target, each Lidar waveform consists of a main peak, whose position depends on the target distance and whose amplitude depends on the wavelength of the laser source considered (i.e, on the target reflectivity). Besides, these temporal responses are usually assumed to be corrupted by Poisson noise in the low photon count regime. When considering multiple wavelengths, it becomes possible to use spectral information in order to identify and quantify the mainmore » materials in the scene, in addition to estimation of the Lidar-based range profiles. Due to its anomaly detection capability, the proposed hierarchical Bayesian model, coupled with an efficient Markov chain Monte Carlo algorithm, allows robust estimation of depth images together with abundance and outlier maps associated with the observed 3D scene. The proposed methodology is illustrated via experiments conducted with real multispectral Lidar data acquired in a controlled environment. The results demonstrate the possibility to unmix spectral responses constructed from extremely sparse photon counts (less than 10 photons per pixel and band).« less

UNMIX Methods Applied to Characterize Sources of Volatile Organic Compounds in Toronto, Ontario

PubMed Central

Porada, Eugeniusz; Szyszkowicz, Mieczysław

2016-01-01

UNMIX, a sensor modeling routine from the U.S. Environmental Protection Agency (EPA), was used to model volatile organic compound (VOC) receptors in four urban sites in Toronto, Ontario. VOC ambient concentration data acquired in 2000–2009 for 175 VOC species in four air quality monitoring stations were analyzed. UNMIX, by performing multiple modeling attempts upon varying VOC menus—while rejecting the results that were not reliable—allowed for discriminating sources by their most consistent chemical characteristics. The method assessed occurrences of VOCs in sources typical of the urban environment (traffic, evaporative emissions of fuels, banks of fugitive inert gases), industrial point sources (plastic-, polymer-, and metalworking manufactures), and in secondary sources (releases from water, sediments, and contaminated urban soil). The remote sensing and robust modeling used here produces chemical profiles of putative VOC sources that, if combined with known environmental fates of VOCs, can be used to assign physical sources’ shares of VOCs emissions into the atmosphere. This in turn provides a means of assessing the impact of environmental policies on one hand, and industrial activities on the other hand, on VOC air pollution. PMID:29051416

Sparsely-sampled hyperspectral stimulated Raman scattering microscopy: a theoretical investigation

NASA Astrophysics Data System (ADS)

Lin, Haonan; Liao, Chien-Sheng; Wang, Pu; Huang, Kai-Chih; Bouman, Charles A.; Kong, Nan; Cheng, Ji-Xin

2017-02-01

A hyperspectral image corresponds to a data cube with two spatial dimensions and one spectral dimension. Through linear un-mixing, hyperspectral images can be decomposed into spectral signatures of pure components as well as their concentration maps. Due to this distinct advantage on component identification, hyperspectral imaging becomes a rapidly emerging platform for engineering better medicine and expediting scientific discovery. Among various hyperspectral imaging techniques, hyperspectral stimulated Raman scattering (HSRS) microscopy acquires data in a pixel-by-pixel scanning manner. Nevertheless, current image acquisition speed for HSRS is insufficient to capture the dynamics of freely moving subjects. Instead of reducing the pixel dwell time to achieve speed-up, which would inevitably decrease signal-to-noise ratio (SNR), we propose to reduce the total number of sampled pixels. Location of sampled pixels are carefully engineered with triangular wave Lissajous trajectory. Followed by a model-based image in-painting algorithm, the complete data is recovered for linear unmixing. Simulation results show that by careful selection of trajectory, a fill rate as low as 10% is sufficient to generate accurate linear unmixing results. The proposed framework applies to any hyperspectral beam-scanning imaging platform which demands high acquisition speed.

On the Use of FOSS4G in Land Cover Fraction Estimation with Unmixing Algorithms

NASA Astrophysics Data System (ADS)

Kumar, U.; Milesi, C.; Raja, K.; Ganguly, S.; Wang, W.; Zhang, G.; Nemani, R. R.

2014-12-01

The popularity and usage of FOSS4G (FOSS for Geoinformatics) has increased drastically in the last two decades with increasing benefits that facilitate spatial data analysis, image processing, graphics and map production, spatial modeling and visualization. The objective of this paper is to use FOSS4G to implement and perform a quantitative analysis of three different unmixing algorithms: Constraint Least-Square (CLS), Unconstraint Least-Square, and Orthogonal Subspace Projection to estimate land cover (LC) fraction estimates from RS data. The LC fractions obtained by unmixing of mixed pixels represent mixture of more than one class per pixel rendering more accurate LC abundance estimates. The algorithms were implemented in C++ programming language with OpenCV package (http://opencv.org/) and boost C++ libraries (www.boost.org) in the NASA Earth Exchange at the NASA Advanced Supercomputing Facility. GRASS GIS was used for visualization of results and statistical analysis was carried in R in a Linux system environment. A set of global endmembers for substrate, vegetation and dark objects were used to unmix the data using the three algorithms and were compared with Singular Value decomposition unmixed outputs available in ENVI image processing software. First, computer simulated data of different signal to noise ratio were used to evaluate the algorithms. The second set of experiments was carried out in an agricultural set-up with a spectrally diverse collection of 11 Landsat-5 scenes (acquired in 2008) for an agricultural setup in Frenso, California and the ground data were collected on those specific dates when the satellite passed through the site. Finally, in the third set of experiments, a pair of coincident clear sky Landsat and World View 2 data for an urbanized area of San Francisco were used to assess the algorithm. Validation of the results using descriptive statistics, correlation coefficient (cc), RMSE, boxplot and bivariate distribution function indicated that with the computer simulated data, CLS was better than other techniques. With the real world data of an agricultural landscape, CLS was superior to other techniques with a mean absolute error for all four methods close to 7.3%. For the urban setup, CLS demonstrated highest average cc of 0.64 and lowest average RMSE of 0.19 for all the endmembers.

Unsupervised Gaussian Mixture-Model With Expectation Maximization for Detecting Glaucomatous Progression in Standard Automated Perimetry Visual Fields.

PubMed

Yousefi, Siamak; Balasubramanian, Madhusudhanan; Goldbaum, Michael H; Medeiros, Felipe A; Zangwill, Linda M; Weinreb, Robert N; Liebmann, Jeffrey M; Girkin, Christopher A; Bowd, Christopher

2016-05-01

To validate Gaussian mixture-model with expectation maximization (GEM) and variational Bayesian independent component analysis mixture-models (VIM) for detecting glaucomatous progression along visual field (VF) defect patterns (GEM-progression of patterns (POP) and VIM-POP). To compare GEM-POP and VIM-POP with other methods. GEM and VIM models separated cross-sectional abnormal VFs from 859 eyes and normal VFs from 1117 eyes into abnormal and normal clusters. Clusters were decomposed into independent axes. The confidence limit (CL) of stability was established for each axis with a set of 84 stable eyes. Sensitivity for detecting progression was assessed in a sample of 83 eyes with known progressive glaucomatous optic neuropathy (PGON). Eyes were classified as progressed if any defect pattern progressed beyond the CL of stability. Performance of GEM-POP and VIM-POP was compared to point-wise linear regression (PLR), permutation analysis of PLR (PoPLR), and linear regression (LR) of mean deviation (MD), and visual field index (VFI). Sensitivity and specificity for detecting glaucomatous VFs were 89.9% and 93.8%, respectively, for GEM and 93.0% and 97.0%, respectively, for VIM. Receiver operating characteristic (ROC) curve areas for classifying progressed eyes were 0.82 for VIM-POP, 0.86 for GEM-POP, 0.81 for PoPLR, 0.69 for LR of MD, and 0.76 for LR of VFI. GEM-POP was significantly more sensitive to PGON than PoPLR and linear regression of MD and VFI in our sample, while providing localized progression information. Detection of glaucomatous progression can be improved by assessing longitudinal changes in localized patterns of glaucomatous defect identified by unsupervised machine learning.

Unsupervised laparoscopic appendicectomy by surgical trainees is safe and time-effective.

PubMed

Wong, Kenneth; Duncan, Tristram; Pearson, Andrew

2007-07-01

Open appendicectomy is the traditional standard treatment for appendicitis. Laparoscopic appendicectomy is perceived as a procedure with greater potential for complications and longer operative times. This paper examines the hypothesis that unsupervised laparoscopic appendicectomy by surgical trainees is a safe and time-effective valid alternative. Medical records, operating theatre records and histopathology reports of all patients undergoing laparoscopic and open appendicectomy over a 15-month period in two hospitals within an area health service were retrospectively reviewed. Data were analysed to compare patient features, pathology findings, operative times, complications, readmissions and mortality between laparoscopic and open groups and between unsupervised surgical trainee operators versus consultant surgeon operators. A total of 143 laparoscopic and 222 open appendicectomies were reviewed. Unsupervised trainees performed 64% of the laparoscopic appendicectomies and 55% of the open appendicectomies. There were no significant differences in complication rates, readmissions, mortality and length of stay between laparoscopic and open appendicectomy groups or between trainee and consultant surgeon operators. Conversion rates (laparoscopic to open approach) were similar for trainees and consultants. Unsupervised senior surgical trainees did not take significantly longer to perform laparoscopic appendicectomy when compared to unsupervised trainee-performed open appendicectomy. Unsupervised laparoscopic appendicectomy by surgical trainees is safe and time-effective.

Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data

DOE PAGES

McCann, Cooper; Repasky, Kevin S.; Morin, Mikindra; ...

2017-05-23

Hyperspectral image analysis has benefited from an array of methods that take advantage of the increased spectral depth compared to multispectral sensors; however, the focus of these developments has been on supervised classification methods. Lack of a priori knowledge regarding land cover characteristics can make unsupervised classification methods preferable under certain circumstances. An unsupervised classification technique is presented in this paper that utilizes physically relevant basis functions to model the reflectance spectra. These fit parameters used to generate the basis functions allow clustering based on spectral characteristics rather than spectral channels and provide both noise and data reduction. Histogram splittingmore » of the fit parameters is then used as a means of producing an unsupervised classification. Unlike current unsupervised classification techniques that rely primarily on Euclidian distance measures to determine similarity, the unsupervised classification technique uses the natural splitting of the fit parameters associated with the basis functions creating clusters that are similar in terms of physical parameters. The data set used in this work utilizes the publicly available data collected at Indian Pines, Indiana. This data set provides reference data allowing for comparisons of the efficacy of different unsupervised data analysis. The unsupervised histogram splitting technique presented in this paper is shown to be better than the standard unsupervised ISODATA clustering technique with an overall accuracy of 34.3/19.0% before merging and 40.9/39.2% after merging. Finally, this improvement is also seen as an improvement of kappa before/after merging of 24.8/30.5 for the histogram splitting technique compared to 15.8/28.5 for ISODATA.« less

Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data

DOE Office of Scientific and Technical Information (OSTI.GOV)

McCann, Cooper; Repasky, Kevin S.; Morin, Mikindra

Hyperspectral image analysis has benefited from an array of methods that take advantage of the increased spectral depth compared to multispectral sensors; however, the focus of these developments has been on supervised classification methods. Lack of a priori knowledge regarding land cover characteristics can make unsupervised classification methods preferable under certain circumstances. An unsupervised classification technique is presented in this paper that utilizes physically relevant basis functions to model the reflectance spectra. These fit parameters used to generate the basis functions allow clustering based on spectral characteristics rather than spectral channels and provide both noise and data reduction. Histogram splittingmore » of the fit parameters is then used as a means of producing an unsupervised classification. Unlike current unsupervised classification techniques that rely primarily on Euclidian distance measures to determine similarity, the unsupervised classification technique uses the natural splitting of the fit parameters associated with the basis functions creating clusters that are similar in terms of physical parameters. The data set used in this work utilizes the publicly available data collected at Indian Pines, Indiana. This data set provides reference data allowing for comparisons of the efficacy of different unsupervised data analysis. The unsupervised histogram splitting technique presented in this paper is shown to be better than the standard unsupervised ISODATA clustering technique with an overall accuracy of 34.3/19.0% before merging and 40.9/39.2% after merging. Finally, this improvement is also seen as an improvement of kappa before/after merging of 24.8/30.5 for the histogram splitting technique compared to 15.8/28.5 for ISODATA.« less

Detecting Abnormal Vehicular Dynamics at Intersections Based on an Unsupervised Learning Approach and a Stochastic Model

PubMed Central

Jiménez-Hernández, Hugo; González-Barbosa, Jose-Joel; Garcia-Ramírez, Teresa

2010-01-01

This investigation demonstrates an unsupervised approach for modeling traffic flow and detecting abnormal vehicle behaviors at intersections. In the first stage, the approach reveals and records the different states of the system. These states are the result of coding and grouping the historical motion of vehicles as long binary strings. In the second stage, using sequences of the recorded states, a stochastic graph model based on a Markovian approach is built. A behavior is labeled abnormal when current motion pattern cannot be recognized as any state of the system or a particular sequence of states cannot be parsed with the stochastic model. The approach is tested with several sequences of images acquired from a vehicular intersection where the traffic flow and duration used in connection with the traffic lights are continuously changed throughout the day. Finally, the low complexity and the flexibility of the approach make it reliable for use in real time systems. PMID:22163616

Detecting abnormal vehicular dynamics at intersections based on an unsupervised learning approach and a stochastic model.

PubMed

Jiménez-Hernández, Hugo; González-Barbosa, Jose-Joel; Garcia-Ramírez, Teresa

2010-01-01

This investigation demonstrates an unsupervised approach for modeling traffic flow and detecting abnormal vehicle behaviors at intersections. In the first stage, the approach reveals and records the different states of the system. These states are the result of coding and grouping the historical motion of vehicles as long binary strings. In the second stage, using sequences of the recorded states, a stochastic graph model based on a Markovian approach is built. A behavior is labeled abnormal when current motion pattern cannot be recognized as any state of the system or a particular sequence of states cannot be parsed with the stochastic model. The approach is tested with several sequences of images acquired from a vehicular intersection where the traffic flow and duration used in connection with the traffic lights are continuously changed throughout the day. Finally, the low complexity and the flexibility of the approach make it reliable for use in real time systems.

An unsupervised method for summarizing egocentric sport videos

NASA Astrophysics Data System (ADS)

Habibi Aghdam, Hamed; Jahani Heravi, Elnaz; Puig, Domenec

2015-12-01

People are getting more interested to record their sport activities using head-worn or hand-held cameras. This type of videos which is called egocentric sport videos has different motion and appearance patterns compared with life-logging videos. While a life-logging video can be defined in terms of well-defined human-object interactions, notwithstanding, it is not trivial to describe egocentric sport videos using well-defined activities. For this reason, summarizing egocentric sport videos based on human-object interaction might fail to produce meaningful results. In this paper, we propose an unsupervised method for summarizing egocentric videos by identifying the key-frames of the video. Our method utilizes both appearance and motion information and it automatically finds the number of the key-frames. Our blind user study on the new dataset collected from YouTube shows that in 93:5% cases, the users choose the proposed method as their first video summary choice. In addition, our method is within the top 2 choices of the users in 99% of studies.

Neurons with two sites of synaptic integration learn invariant representations.

PubMed

Körding, K P; König, P

2001-12-01

Neurons in mammalian cerebral cortex combine specific responses with respect to some stimulus features with invariant responses to other stimulus features. For example, in primary visual cortex, complex cells code for orientation of a contour but ignore its position to a certain degree. In higher areas, such as the inferotemporal cortex, translation-invariant, rotation-invariant, and even view point-invariant responses can be observed. Such properties are of obvious interest to artificial systems performing tasks like pattern recognition. It remains to be resolved how such response properties develop in biological systems. Here we present an unsupervised learning rule that addresses this problem. It is based on a neuron model with two sites of synaptic integration, allowing qualitatively different effects of input to basal and apical dendritic trees, respectively. Without supervision, the system learns to extract invariance properties using temporal or spatial continuity of stimuli. Furthermore, top-down information can be smoothly integrated in the same framework. Thus, this model lends a physiological implementation to approaches of unsupervised learning of invariant-response properties.

Model–Free Visualization of Suspicious Lesions in Breast MRI Based on Supervised and Unsupervised Learning

PubMed Central

Twellmann, Thorsten; Meyer-Baese, Anke; Lange, Oliver; Foo, Simon; Nattkemper, Tim W.

2008-01-01

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become an important tool in breast cancer diagnosis, but evaluation of multitemporal 3D image data holds new challenges for human observers. To aid the image analysis process, we apply supervised and unsupervised pattern recognition techniques for computing enhanced visualizations of suspicious lesions in breast MRI data. These techniques represent an important component of future sophisticated computer-aided diagnosis (CAD) systems and support the visual exploration of spatial and temporal features of DCE-MRI data stemming from patients with confirmed lesion diagnosis. By taking into account the heterogeneity of cancerous tissue, these techniques reveal signals with malignant, benign and normal kinetics. They also provide a regional subclassification of pathological breast tissue, which is the basis for pseudo-color presentations of the image data. Intelligent medical systems are expected to have substantial implications in healthcare politics by contributing to the diagnosis of indeterminate breast lesions by non-invasive imaging. PMID:19255616

A neural-visualization IDS for honeynet data.

PubMed

Herrero, Álvaro; Zurutuza, Urko; Corchado, Emilio

2012-04-01

Neural intelligent systems can provide a visualization of the network traffic for security staff, in order to reduce the widely known high false-positive rate associated with misuse-based Intrusion Detection Systems (IDSs). Unlike previous work, this study proposes an unsupervised neural models that generate an intuitive visualization of the captured traffic, rather than network statistics. These snapshots of network events are immensely useful for security personnel that monitor network behavior. The system is based on the use of different neural projection and unsupervised methods for the visual inspection of honeypot data, and may be seen as a complementary network security tool that sheds light on internal data structures through visual inspection of the traffic itself. Furthermore, it is intended to facilitate verification and assessment of Snort performance (a well-known and widely-used misuse-based IDS), through the visualization of attack patterns. Empirical verification and comparison of the proposed projection methods are performed in a real domain, where two different case studies are defined and analyzed.

The Convallis Rule for Unsupervised Learning in Cortical Networks

PubMed Central

Yger, Pierre; Harris, Kenneth D.

2013-01-01

The phenomenology and cellular mechanisms of cortical synaptic plasticity are becoming known in increasing detail, but the computational principles by which cortical plasticity enables the development of sensory representations are unclear. Here we describe a framework for cortical synaptic plasticity termed the “Convallis rule”, mathematically derived from a principle of unsupervised learning via constrained optimization. Implementation of the rule caused a recurrent cortex-like network of simulated spiking neurons to develop rate representations of real-world speech stimuli, enabling classification by a downstream linear decoder. Applied to spike patterns used in in vitro plasticity experiments, the rule reproduced multiple results including and beyond STDP. However STDP alone produced poorer learning performance. The mathematical form of the rule is consistent with a dual coincidence detector mechanism that has been suggested by experiments in several synaptic classes of juvenile neocortex. Based on this confluence of normative, phenomenological, and mechanistic evidence, we suggest that the rule may approximate a fundamental computational principle of the neocortex. PMID:24204224

Unsupervised Categorization in a Sample of Children with Autism Spectrum Disorders

ERIC Educational Resources Information Center

Edwards, Darren J.; Perlman, Amotz; Reed, Phil

2012-01-01

Studies of supervised Categorization have demonstrated limited Categorization performance in participants with autism spectrum disorders (ASD), however little research has been conducted regarding unsupervised Categorization in this population. This study explored unsupervised Categorization using two stimulus sets that differed in their…

Unsupervised Deep Hashing With Pseudo Labels for Scalable Image Retrieval.

PubMed

Zhang, Haofeng; Liu, Li; Long, Yang; Shao, Ling

2018-04-01

In order to achieve efficient similarity searching, hash functions are designed to encode images into low-dimensional binary codes with the constraint that similar features will have a short distance in the projected Hamming space. Recently, deep learning-based methods have become more popular, and outperform traditional non-deep methods. However, without label information, most state-of-the-art unsupervised deep hashing (DH) algorithms suffer from severe performance degradation for unsupervised scenarios. One of the main reasons is that the ad-hoc encoding process cannot properly capture the visual feature distribution. In this paper, we propose a novel unsupervised framework that has two main contributions: 1) we convert the unsupervised DH model into supervised by discovering pseudo labels; 2) the framework unifies likelihood maximization, mutual information maximization, and quantization error minimization so that the pseudo labels can maximumly preserve the distribution of visual features. Extensive experiments on three popular data sets demonstrate the advantages of the proposed method, which leads to significant performance improvement over the state-of-the-art unsupervised hashing algorithms.

Genesis of the heaviest elements in the Milky Way Galaxy.

PubMed

Sneden, Christopher; Cowan, John J

2003-01-03

We review the origin and evolution of the heavy elements, those with atomic numbers greater than 30, in the early history of the Milky Way. There is a large star-to-star bulk scatter in the concentrations of heavy elements with respect to the lighter metals, which suggests an early chemically unmixed and inhomogeneous Galaxy. The relative abundance patterns among the heavy elements are often very different from the solar system mix, revealing the characteristics of the first element donors in the Galaxy. Abundance comparisons among several halo stars show that the heaviest neutron-capture elements (including barium and heavier) are consistent with a scaled solar system rapid neutron-capture abundance distribution, whereas the lighter such elements do not conform to the solar pattern. The stellar abundances indicate an increasing contribution from the slow neutron-capture process (s-process) at higher metallicities in the Galaxy. The detection of thorium in halo and globular cluster stars offers a promising, independent age-dating technique that can put lower limits on the age of the Galaxy.

Spatiotemporal information during unsupervised learning enhances viewpoint invariant object recognition

PubMed Central

Tian, Moqian; Grill-Spector, Kalanit

2015-01-01

Recognizing objects is difficult because it requires both linking views of an object that can be different and distinguishing objects with similar appearance. Interestingly, people can learn to recognize objects across views in an unsupervised way, without feedback, just from the natural viewing statistics. However, there is intense debate regarding what information during unsupervised learning is used to link among object views. Specifically, researchers argue whether temporal proximity, motion, or spatiotemporal continuity among object views during unsupervised learning is beneficial. Here, we untangled the role of each of these factors in unsupervised learning of novel three-dimensional (3-D) objects. We found that after unsupervised training with 24 object views spanning a 180° view space, participants showed significant improvement in their ability to recognize 3-D objects across rotation. Surprisingly, there was no advantage to unsupervised learning with spatiotemporal continuity or motion information than training with temporal proximity. However, we discovered that when participants were trained with just a third of the views spanning the same view space, unsupervised learning via spatiotemporal continuity yielded significantly better recognition performance on novel views than learning via temporal proximity. These results suggest that while it is possible to obtain view-invariant recognition just from observing many views of an object presented in temporal proximity, spatiotemporal information enhances performance by producing representations with broader view tuning than learning via temporal association. Our findings have important implications for theories of object recognition and for the development of computational algorithms that learn from examples. PMID:26024454

Unsupervised Feature Selection Based on the Morisita Index for Hyperspectral Images

NASA Astrophysics Data System (ADS)

Golay, Jean; Kanevski, Mikhail

2017-04-01

Hyperspectral sensors are capable of acquiring images with hundreds of narrow and contiguous spectral bands. Compared with traditional multispectral imagery, the use of hyperspectral images allows better performance in discriminating between land-cover classes, but it also results in large redundancy and high computational data processing. To alleviate such issues, unsupervised feature selection techniques for redundancy minimization can be implemented. Their goal is to select the smallest subset of features (or bands) in such a way that all the information content of a data set is preserved as much as possible. The present research deals with the application to hyperspectral images of a recently introduced technique of unsupervised feature selection: the Morisita-Based filter for Redundancy Minimization (MBRM). MBRM is based on the (multipoint) Morisita index of clustering and on the Morisita estimator of Intrinsic Dimension (ID). The fundamental idea of the technique is to retain only the bands which contribute to increasing the ID of an image. In this way, redundant bands are disregarded, since they have no impact on the ID. Besides, MBRM has several advantages over benchmark techniques: in addition to its ability to deal with large data sets, it can capture highly-nonlinear dependences and its implementation is straightforward in any programming environment. Experimental results on freely available hyperspectral images show the good effectiveness of MBRM in remote sensing data processing. Comparisons with benchmark techniques are carried out and random forests are used to assess the performance of MBRM in reducing the data dimensionality without loss of relevant information. References [1] C. Traina Jr., A.J.M. Traina, L. Wu, C. Faloutsos, Fast feature selection using fractal dimension, in: Proceedings of the XV Brazilian Symposium on Databases, SBBD, pp. 158-171, 2000. [2] J. Golay, M. Kanevski, A new estimator of intrinsic dimension based on the multipoint Morisita index, Pattern Recognition 48(12), pp. 4070-4081, 2015. [3] J. Golay, M. Kanevski, Unsupervised feature selection based on the Morisita estimator of intrinsic dimension, arXiv:1608.05581, 2016.

Cubesat-Derived Detection of Seagrasses Using Planet Imagery Following Unmixing-Based Denoising: is Small the Next Big?

NASA Astrophysics Data System (ADS)

Traganos, D.; Cerra, D.; Reinartz, P.

2017-05-01

Seagrasses are one of the most productive and widespread yet threatened coastal ecosystems on Earth. Despite their importance, they are declining due to various threats, which are mainly anthropogenic. Lack of data on their distribution hinders any effort to rectify this decline through effective detection, mapping and monitoring. Remote sensing can mitigate this data gap by allowing retrospective quantitative assessment of seagrass beds over large and remote areas. In this paper, we evaluate the quantitative application of Planet high resolution imagery for the detection of seagrasses in the Thermaikos Gulf, NW Aegean Sea, Greece. The low Signal-to-noise Ratio (SNR), which characterizes spectral bands at shorter wavelengths, prompts the application of the Unmixing-based denoising (UBD) as a pre-processing step for seagrass detection. A total of 15 spectral-temporal patterns is extracted from a Planet image time series to restore the corrupted blue and green band in the processed Planet image. Subsequently, we implement Lyzenga's empirical water column correction and Support Vector Machines (SVM) to evaluate quantitative benefits of denoising. Denoising aids detection of Posidonia oceanica seagrass species by increasing its producer and user accuracy by 31.7 % and 10.4 %, correspondingly, with a respective increase in its Kappa value from 0.3 to 0.48. In the near future, our objective is to improve accuracies in seagrass detection by applying more sophisticated, analytical water column correction algorithms to Planet imagery, developing time- and cost-effective monitoring of seagrass distribution that will enable in turn the effective management and conservation of these highly valuable and productive ecosystems.

Predicting category intuitiveness with the rational model, the simplicity model, and the generalized context model.

PubMed

Pothos, Emmanuel M; Bailey, Todd M

2009-07-01

Naïve observers typically perceive some groupings for a set of stimuli as more intuitive than others. The problem of predicting category intuitiveness has been historically considered the remit of models of unsupervised categorization. In contrast, this article develops a measure of category intuitiveness from one of the most widely supported models of supervised categorization, the generalized context model (GCM). Considering different category assignments for a set of instances, the authors asked how well the GCM can predict the classification of each instance on the basis of all the other instances. The category assignment that results in the smallest prediction error is interpreted as the most intuitive for the GCM-the authors refer to this way of applying the GCM as "unsupervised GCM." The authors systematically compared predictions of category intuitiveness from the unsupervised GCM and two models of unsupervised categorization: the simplicity model and the rational model. The unsupervised GCM compared favorably with the simplicity model and the rational model. This success of the unsupervised GCM illustrates that the distinction between supervised and unsupervised categorization may need to be reconsidered. However, no model emerged as clearly superior, indicating that there is more work to be done in understanding and modeling category intuitiveness.

An evaluation of unsupervised and supervised learning algorithms for clustering landscape types in the United States

USGS Publications Warehouse

Wendel, Jochen; Buttenfield, Barbara P.; Stanislawski, Larry V.

2016-01-01

Knowledge of landscape type can inform cartographic generalization of hydrographic features, because landscape characteristics provide an important geographic context that affects variation in channel geometry, flow pattern, and network configuration. Landscape types are characterized by expansive spatial gradients, lacking abrupt changes between adjacent classes; and as having a limited number of outliers that might confound classification. The US Geological Survey (USGS) is exploring methods to automate generalization of features in the National Hydrography Data set (NHD), to associate specific sequences of processing operations and parameters with specific landscape characteristics, thus obviating manual selection of a unique processing strategy for every NHD watershed unit. A chronology of methods to delineate physiographic regions for the United States is described, including a recent maximum likelihood classification based on seven input variables. This research compares unsupervised and supervised algorithms applied to these seven input variables, to evaluate and possibly refine the recent classification. Evaluation metrics for unsupervised methods include the Davies–Bouldin index, the Silhouette index, and the Dunn index as well as quantization and topographic error metrics. Cross validation and misclassification rate analysis are used to evaluate supervised classification methods. The paper reports the comparative analysis and its impact on the selection of landscape regions. The compared solutions show problems in areas of high landscape diversity. There is some indication that additional input variables, additional classes, or more sophisticated methods can refine the existing classification.

Differential principal component analysis of ChIP-seq.

PubMed

Ji, Hongkai; Li, Xia; Wang, Qian-fei; Ning, Yang

2013-04-23

We propose differential principal component analysis (dPCA) for analyzing multiple ChIP-sequencing datasets to identify differential protein-DNA interactions between two biological conditions. dPCA integrates unsupervised pattern discovery, dimension reduction, and statistical inference into a single framework. It uses a small number of principal components to summarize concisely the major multiprotein synergistic differential patterns between the two conditions. For each pattern, it detects and prioritizes differential genomic loci by comparing the between-condition differences with the within-condition variation among replicate samples. dPCA provides a unique tool for efficiently analyzing large amounts of ChIP-sequencing data to study dynamic changes of gene regulation across different biological conditions. We demonstrate this approach through analyses of differential chromatin patterns at transcription factor binding sites and promoters as well as allele-specific protein-DNA interactions.

The influence of unsupervised time on elementary school children at high risk for inattention and problem behaviors.

PubMed

Na, Kyoung-Sae; Lee, Soyoung Irene; Hong, Hyun Ju; Oh, Myoung-Ja; Bahn, Geon Ho; Ha, Kyunghee; Shin, Yun Mi; Song, Jungeun; Park, Eun Jin; Yoo, Heejung; Kim, Hyunsoo; Kyung, Yun-Mi

2014-06-01

In the last few decades, changing socioeconomic and family structures have increasingly left children alone without adult supervision. Carefully prepared and limited periods of unsupervised time are not harmful for children. However, long unsupervised periods have harmful effects, particularly for those children at high risk for inattention and problem behaviors. In this study, we examined the influence of unsupervised time on behavior problems by studying a sample of elementary school children at high risk for inattention and problem behaviors. The study analyzed data from the Children's Mental Health Promotion Project, which was conducted in collaboration with education, government, and mental health professionals. The child behavior checklist (CBCL) was administered to assess problem behaviors among first- and fourth-grade children. Multivariate logistic regression analysis was used to evaluate the influence of unsupervised time on children's behavior. A total of 3,270 elementary school children (1,340 first-graders and 1,930 fourth-graders) were available for this study; 1,876 of the 3,270 children (57.4%) reportedly spent a significant amount of time unsupervised during the day. Unsupervised time that exceeded more than 2h per day increased the risk of delinquency, aggressive behaviors, and somatic complaints, as well as externalizing and internalizing problems. Carefully planned afterschool programming and care should be provided to children at high risk for inattention and problem behaviors. Also, a more comprehensive approach is needed to identify the possible mechanisms by which unsupervised time aggravates behavior problems in children predisposed for these behaviors. Copyright © 2013 Elsevier Ltd. All rights reserved.

Impact of JPEG2000 compression on endmember extraction and unmixing of remotely sensed hyperspectral data

NASA Astrophysics Data System (ADS)

Martin, Gabriel; Gonzalez-Ruiz, Vicente; Plaza, Antonio; Ortiz, Juan P.; Garcia, Inmaculada

2010-07-01

Lossy hyperspectral image compression has received considerable interest in recent years due to the extremely high dimensionality of the data. However, the impact of lossy compression on spectral unmixing techniques has not been widely studied. These techniques characterize mixed pixels (resulting from insufficient spatial resolution) in terms of a suitable combination of spectrally pure substances (called endmembers) weighted by their estimated fractional abundances. This paper focuses on the impact of JPEG2000-based lossy compression of hyperspectral images on the quality of the endmembers extracted by different algorithms. The three considered algorithms are the orthogonal subspace projection (OSP), which uses only spatial information, and the automatic morphological endmember extraction (AMEE) and spatial spectral endmember extraction (SSEE), which integrate both spatial and spectral information in the search for endmembers. The impact of compression on the resulting abundance estimation based on the endmembers derived by different methods is also substantiated. Experimental results are conducted using a hyperspectral data set collected by NASA Jet Propulsion Laboratory over the Cuprite mining district in Nevada. The experimental results are quantitatively analyzed using reference information available from U.S. Geological Survey, resulting in recommendations to specialists interested in applying endmember extraction and unmixing algorithms to compressed hyperspectral data.

Source apportionment of PM2.5 at the Lin'an regional background site in China with three receptor models

NASA Astrophysics Data System (ADS)

Deng, Junjun; Zhang, Yanru; Qiu, Yuqing; Zhang, Hongliang; Du, Wenjiao; Xu, Lingling; Hong, Youwei; Chen, Yanting; Chen, Jinsheng

2018-04-01

Source apportionment of fine particulate matter (PM2.5) were conducted at the Lin'an Regional Atmospheric Background Station (LA) in the Yangtze River Delta (YRD) region in China from July 2014 to April 2015 with three receptor models including principal component analysis combining multiple linear regression (PCA-MLR), UNMIX and Positive Matrix Factorization (PMF). The model performance, source identification and source contribution of the three models were analyzed and inter-compared. Source apportionment of PM2.5 was also conducted with the receptor models. Good correlations between the reconstructed and measured concentrations of PM2.5 and its major chemical species were obtained for all models. PMF resolved almost all masses of PM2.5, while PCA-MLR and UNMIX explained about 80%. Five, four and seven sources were identified by PCA-MLR, UNMIX and PMF, respectively. Combustion, secondary source, marine source, dust and industrial activities were identified by all the three receptor models. Combustion source and secondary source were the major sources, and totally contributed over 60% to PM2.5. The PMF model had a better performance on separating the different combustion sources. These findings improve the understanding of PM2.5 sources in background region.

Effect of UV-A and UV-B irradiation on the metabolic profile of aqueous humor in rabbits analyzed by 1H NMR spectroscopy.

PubMed

Tessem, May-Britt; Bathen, Tone F; Cejková, Jitka; Midelfart, Anna

2005-03-01

This study was conducted to investigate metabolic changes in aqueous humor from rabbit eyes exposed to either UV-A or -B radiation, by using (1)H nuclear magnetic resonance (NMR) spectroscopy and unsupervised pattern recognition methods. Both eyes of adult albino rabbits were irradiated with UV-A (366 nm, 0.589 J/cm(2)) or UV-B (312 nm, 1.667 J/cm(2)) radiation for 8 minutes, once a day for 5 days. Three days after the last irradiation, samples of aqueous humor were aspirated, and the metabolic profiles analyzed with (1)H NMR spectroscopy. The metabolic concentrations in the exposed and control materials were statistically analyzed and compared, with multivariate methods and one-way ANOVA. UV-B radiation caused statistically significant alterations of betaine, glucose, ascorbate, valine, isoleucine, and formate in the rabbit aqueous humor. By using principal component analysis, the UV-B-irradiated samples were clearly separated from the UV-A-irradiated samples and the control group. No significant metabolic changes were detected in UV-A-irradiated samples. This study demonstrates the potential of using unsupervised pattern recognition methods to extract valuable metabolic information from complex (1)H NMR spectra. UV-B irradiation of rabbit eyes led to significant metabolic changes in the aqueous humor detected 3 days after the last exposure.

Geospatiotemporal Data Mining of Remotely Sensed Phenology for Unsupervised Forest Threat Detection

NASA Astrophysics Data System (ADS)

Mills, R. T.; Hoffman, F. M.; Kumar, J.; Vulli, S. S.; Hargrove, W. W.; Spruce, J.

2010-12-01

Hargrove and Hoffman have previously developed and applied a scalable geospatiotemporal data mining approach to define a set of categorical, multivariate classes or states for describing and tracking the behavior of ecosystem properties through time within a multi-dimensional phase or state space. The method employs a standard k-means cluster analysis with enhancements that reduce the number of required comparisons, dramatically accelerating iterative convergence. In support of efforts by the USDA Forest Service to develop a National Early Warning System for Forest Disturbances, we have applied this geospatiotemporal cluster analysis procedure to annual phenology patterns derived from Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) for unsupervised change detection. We will present initial results from the analysis of seven years of 250-m MODIS NDVI data for the conterminous United States. While determining what constitutes a "normal" phenological pattern for any given location is challenging due to interannual climate variability, a spatially varying climate change trend, and the relatively short record of MODIS NDVI observations, these results demonstrate the utility of the method for detecting significant mortality events, like the progressive damage from mountain pine beetle, and suggest that the technique may be successfully implemented as a key component in an early warning system for identifying forest threats from natural and anthropogenic disturbances at a continental scale.

Accuracy assessment of linear spectral mixture model due to terrain undulation

NASA Astrophysics Data System (ADS)

Wang, Tianxing; Chen, Songlin; Ma, Ya

2008-12-01

Mixture spectra are common in remote sensing due to the limitations of spatial resolution and the heterogeneity of land surface. During the past 30 years, a lot of subpixel model have developed to investigate the information within mixture pixels. Linear spectral mixture model (LSMM) is a simper and more general subpixel model. LSMM also known as spectral mixture analysis is a widely used procedure to determine the proportion of endmembers (constituent materials) within a pixel based on the endmembers' spectral characteristics. The unmixing accuracy of LSMM is restricted by variety of factors, but now the research about LSMM is mostly focused on appraisement of nonlinear effect relating to itself and techniques used to select endmembers, unfortunately, the environment conditions of study area which could sway the unmixing-accuracy, such as atmospheric scatting and terrain undulation, are not studied. This paper probes emphatically into the accuracy uncertainty of LSMM resulting from the terrain undulation. ASTER dataset was chosen and the C terrain correction algorithm was applied to it. Based on this, fractional abundances for different cover types were extracted from both pre- and post-C terrain illumination corrected ASTER using LSMM. Simultaneously, the regression analyses and the IKONOS image were introduced to assess the unmixing accuracy. Results showed that terrain undulation could dramatically constrain the application of LSMM in mountain area. Specifically, for vegetation abundances, a improved unmixing accuracy of 17.6% (regression against to NDVI) and 18.6% (regression against to MVI) for R2 was achieved respectively by removing terrain undulation. Anyway, this study indicated in a quantitative way that effective removal or minimization of terrain illumination effects was essential for applying LSMM. This paper could also provide a new instance for LSMM applications in mountainous areas. In addition, the methods employed in this study could be effectively used to evaluate different algorithms of terrain undulation correction for further study.

Effects of band selection on endmember extraction for forestry applications

NASA Astrophysics Data System (ADS)

Karathanassi, Vassilia; Andreou, Charoula; Andronis, Vassilis; Kolokoussis, Polychronis

2014-10-01

In spectral unmixing theory, data reduction techniques play an important role as hyperspectral imagery contains an immense amount of data, posing many challenging problems such as data storage, computational efficiency, and the so called "curse of dimensionality". Feature extraction and feature selection are the two main approaches for dimensionality reduction. Feature extraction techniques are used for reducing the dimensionality of the hyperspectral data by applying transforms on hyperspectral data. Feature selection techniques retain the physical meaning of the data by selecting a set of bands from the input hyperspectral dataset, which mainly contain the information needed for spectral unmixing. Although feature selection techniques are well-known for their dimensionality reduction potentials they are rarely used in the unmixing process. The majority of the existing state-of-the-art dimensionality reduction methods set criteria to the spectral information, which is derived by the whole wavelength, in order to define the optimum spectral subspace. These criteria are not associated with any particular application but with the data statistics, such as correlation and entropy values. However, each application is associated with specific land c over materials, whose spectral characteristics present variations in specific wavelengths. In forestry for example, many applications focus on tree leaves, in which specific pigments such as chlorophyll, xanthophyll, etc. determine the wavelengths where tree species, diseases, etc., can be detected. For such applications, when the unmixing process is applied, the tree species, diseases, etc., are considered as the endmembers of interest. This paper focuses on investigating the effects of band selection on the endmember extraction by exploiting the information of the vegetation absorbance spectral zones. More precisely, it is explored whether endmember extraction can be optimized when specific sets of initial bands related to leaf spectral characteristics are selected. Experiments comprise application of well-known signal subspace estimation and endmember extraction methods on a hyperspectral imagery that presents a forest area. Evaluation of the extracted endmembers showed that more forest species can be extracted as endmembers using selected bands.

Assessing FRET using Spectral Techniques

PubMed Central

Leavesley, Silas J.; Britain, Andrea L.; Cichon, Lauren K.; Nikolaev, Viacheslav O.; Rich, Thomas C.

2015-01-01

Förster resonance energy transfer (FRET) techniques have proven invaluable for probing the complex nature of protein–protein interactions, protein folding, and intracellular signaling events. These techniques have traditionally been implemented with the use of one or more fluorescence band-pass filters, either as fluorescence microscopy filter cubes, or as dichroic mirrors and band-pass filters in flow cytometry. In addition, new approaches for measuring FRET, such as fluorescence lifetime and acceptor photobleaching, have been developed. Hyperspectral techniques for imaging and flow cytometry have also shown to be promising for performing FRET measurements. In this study, we have compared traditional (filter-based) FRET approaches to three spectral-based approaches: the ratio of acceptor-to-donor peak emission, linear spectral unmixing, and linear spectral unmixing with a correction for direct acceptor excitation. All methods are estimates of FRET efficiency, except for one-filter set and three-filter set FRET indices, which are included for consistency with prior literature. In the first part of this study, spectrofluorimetric data were collected from a CFP–Epac–YFP FRET probe that has been used for intracellular cAMP measurements. All comparisons were performed using the same spectrofluorimetric datasets as input data, to provide a relevant comparison. Linear spectral unmixing resulted in measurements with the lowest coefficient of variation (0.10) as well as accurate fits using the Hill equation. FRET efficiency methods produced coefficients of variation of less than 0.20, while FRET indices produced coefficients of variation greater than 8.00. These results demonstrate that spectral FRET measurements provide improved response over standard, filter-based measurements. Using spectral approaches, single-cell measurements were conducted through hyperspectral confocal microscopy, linear unmixing, and cell segmentation with quantitative image analysis. Results from these studies confirmed that spectral imaging is effective for measuring subcellular, time-dependent FRET dynamics and that additional fluorescent signals can be readily separated from FRET signals, enabling multilabel studies of molecular interactions. PMID:23929684

Assessing FRET using spectral techniques.

PubMed

Leavesley, Silas J; Britain, Andrea L; Cichon, Lauren K; Nikolaev, Viacheslav O; Rich, Thomas C

2013-10-01

Förster resonance energy transfer (FRET) techniques have proven invaluable for probing the complex nature of protein-protein interactions, protein folding, and intracellular signaling events. These techniques have traditionally been implemented with the use of one or more fluorescence band-pass filters, either as fluorescence microscopy filter cubes, or as dichroic mirrors and band-pass filters in flow cytometry. In addition, new approaches for measuring FRET, such as fluorescence lifetime and acceptor photobleaching, have been developed. Hyperspectral techniques for imaging and flow cytometry have also shown to be promising for performing FRET measurements. In this study, we have compared traditional (filter-based) FRET approaches to three spectral-based approaches: the ratio of acceptor-to-donor peak emission, linear spectral unmixing, and linear spectral unmixing with a correction for direct acceptor excitation. All methods are estimates of FRET efficiency, except for one-filter set and three-filter set FRET indices, which are included for consistency with prior literature. In the first part of this study, spectrofluorimetric data were collected from a CFP-Epac-YFP FRET probe that has been used for intracellular cAMP measurements. All comparisons were performed using the same spectrofluorimetric datasets as input data, to provide a relevant comparison. Linear spectral unmixing resulted in measurements with the lowest coefficient of variation (0.10) as well as accurate fits using the Hill equation. FRET efficiency methods produced coefficients of variation of less than 0.20, while FRET indices produced coefficients of variation greater than 8.00. These results demonstrate that spectral FRET measurements provide improved response over standard, filter-based measurements. Using spectral approaches, single-cell measurements were conducted through hyperspectral confocal microscopy, linear unmixing, and cell segmentation with quantitative image analysis. Results from these studies confirmed that spectral imaging is effective for measuring subcellular, time-dependent FRET dynamics and that additional fluorescent signals can be readily separated from FRET signals, enabling multilabel studies of molecular interactions. © 2013 International Society for Advancement of Cytometry. Copyright © 2013 International Society for Advancement of Cytometry.

Emission spectra profiling of fluorescent proteins in living plant cells

PubMed Central

2013-01-01

Background Fluorescence imaging at high spectral resolution allows the simultaneous recording of multiple fluorophores without switching optical filters, which is especially useful for time-lapse analysis of living cells. The collected emission spectra can be used to distinguish fluorophores by a computation analysis called linear unmixing. The availability of accurate reference spectra for different fluorophores is crucial for this type of analysis. The reference spectra used by plant cell biologists are in most cases derived from the analysis of fluorescent proteins in solution or produced in animal cells, although these spectra are influenced by both the cellular environment and the components of the optical system. For instance, plant cells contain various autofluorescent compounds, such as cell wall polymers and chlorophyll, that affect the spectral detection of some fluorophores. Therefore, it is important to acquire both reference and experimental spectra under the same biological conditions and through the same imaging systems. Results Entry clones (pENTR) of fluorescent proteins (FPs) were constructed in order to create C- or N-terminal protein fusions with the MultiSite Gateway recombination technology. The emission spectra for eight FPs, fused C-terminally to the A- or B-type cyclin dependent kinases (CDKA;1 and CDKB1;1) and transiently expressed in epidermal cells of tobacco (Nicotiana benthamiana), were determined by using the Olympus FluoView™ FV1000 Confocal Laser Scanning Microscope. These experimental spectra were then used in unmixing experiments in order to separate the emission of fluorophores with overlapping spectral properties in living plant cells. Conclusions Spectral imaging and linear unmixing have a great potential for efficient multicolor detection in living plant cells. The emission spectra for eight of the most commonly used FPs were obtained in epidermal cells of tobacco leaves and used in unmixing experiments. The generated set of FP Gateway entry vectors represents a valuable resource for plant cell biologists. PMID:23552272

Estimating forest species abundance through linear unmixing of CHRIS/PROBA imagery

NASA Astrophysics Data System (ADS)

Stagakis, Stavros; Vanikiotis, Theofilos; Sykioti, Olga

2016-09-01

The advancing technology of hyperspectral remote sensing offers the opportunity of accurate land cover characterization of complex natural environments. In this study, a linear spectral unmixing algorithm that incorporates a novel hierarchical Bayesian approach (BI-ICE) was applied on two spatially and temporally adjacent CHRIS/PROBA images over a forest in North Pindos National Park (Epirus, Greece). The scope is to investigate the potential of this algorithm to discriminate two different forest species (i.e. beech - Fagus sylvatica, pine - Pinus nigra) and produce accurate species-specific abundance maps. The unmixing results were evaluated in uniformly distributed plots across the test site using measured fractions of each species derived by very high resolution aerial orthophotos. Landsat-8 images were also used to produce a conventional discrete-type classification map of the test site. This map was used to define the exact borders of the test site and compare the thematic information of the two mapping approaches (discrete vs abundance mapping). The required ground truth information, regarding training and validation of the applied mapping methodologies, was collected during a field campaign across the study site. Abundance estimates reached very good overall accuracy (R2 = 0.98, RMSE = 0.06). The most significant source of error in our results was due to the shadowing effects that were very intense in some areas of the test site due to the low solar elevation during CHRIS acquisitions. It is also demonstrated that the two mapping approaches are in accordance across pure and dense forest areas, but the conventional classification map fails to describe the natural spatial gradients of each species and the actual species mixture across the test site. Overall, the BI-ICE algorithm presented increased potential to unmix challenging objects with high spectral similarity, such as different vegetation species, under real and not optimum acquisition conditions. Its full potential remains to be investigated in further and more complex study sites in view of the upcoming satellite hyperspectral missions.

Application of hierarchical Bayesian unmixing models in river sediment source apportionment

NASA Astrophysics Data System (ADS)

Blake, Will; Smith, Hugh; Navas, Ana; Bodé, Samuel; Goddard, Rupert; Zou Kuzyk, Zou; Lennard, Amy; Lobb, David; Owens, Phil; Palazon, Leticia; Petticrew, Ellen; Gaspar, Leticia; Stock, Brian; Boeckx, Pacsal; Semmens, Brice

2016-04-01

Fingerprinting and unmixing concepts are used widely across environmental disciplines for forensic evaluation of pollutant sources. In aquatic and marine systems, this includes tracking the source of organic and inorganic pollutants in water and linking problem sediment to soil erosion and land use sources. It is, however, the particular complexity of ecological systems that has driven creation of the most sophisticated mixing models, primarily to (i) evaluate diet composition in complex ecological food webs, (ii) inform population structure and (iii) explore animal movement. In the context of the new hierarchical Bayesian unmixing model, MIXSIAR, developed to characterise intra-population niche variation in ecological systems, we evaluate the linkage between ecological 'prey' and 'consumer' concepts and river basin sediment 'source' and sediment 'mixtures' to exemplify the value of ecological modelling tools to river basin science. Recent studies have outlined advantages presented by Bayesian unmixing approaches in handling complex source and mixture datasets while dealing appropriately with uncertainty in parameter probability distributions. MixSIAR is unique in that it allows individual fixed and random effects associated with mixture hierarchy, i.e. factors that might exert an influence on model outcome for mixture groups, to be explored within the source-receptor framework. This offers new and powerful ways of interpreting river basin apportionment data. In this contribution, key components of the model are evaluated in the context of common experimental designs for sediment fingerprinting studies namely simple, nested and distributed catchment sampling programmes. Illustrative examples using geochemical and compound specific stable isotope datasets are presented and used to discuss best practice with specific attention to (1) the tracer selection process, (2) incorporation of fixed effects relating to sample timeframe and sediment type in the modelling process, (3) deriving and using informative priors in sediment fingerprinting context and (4) transparency of the process and replication of model results by other users.

Unsupervised self-care predicts conduct problems: The moderating roles of hostile aggression and gender.

PubMed

Atherton, Olivia E; Schofield, Thomas J; Sitka, Angela; Conger, Rand D; Robins, Richard W

2016-04-01

Despite widespread speculation about the detrimental effect of unsupervised self-care on adolescent outcomes, little is known about which children are particularly prone to problem behaviors when left at home without adult supervision. The present research used data from a longitudinal study of 674 Mexican-origin children residing in the United States to examine the prospective effect of unsupervised self-care on conduct problems, and the moderating roles of hostile aggression and gender. Results showed that unsupervised self-care was related to increases over time in conduct problems such as lying, stealing, and bullying. However, unsupervised self-care only led to conduct problems for boys and for children with an aggressive temperament. The main and interactive effects held for both mother-reported and observational-rated hostile aggression and after controlling for potential confounds. Copyright © 2016 The Foundation for Professionals in Services for Adolescents. Published by Elsevier Ltd. All rights reserved.

Turbulent unmixing: how marine turbulence drives patchy distributions of motile phytoplankton

NASA Astrophysics Data System (ADS)

Durham, William; Climent, Eric; Barry, Michael; de Lillo, Filippo; Boffetta, Guido; Cencini, Massimo; Stocker, Roman

2013-11-01

Centimeter-scale patchiness in the distribution of phytoplankton increases the efficacy of many important ecological interactions in the marine food web. We show that turbulent fluid motion, usually synonymous with mixing, instead triggers intense small-scale patchiness in the distribution of motile phytoplankton. We use a suite of experiments, direct numerical simulations of turbulence, and analytical tools to show that turbulent shear and acceleration directs the motility of cells towards well-defined regions of flow, increasing local cell concentrations more than ten fold. This motility-driven `unmixing' offers an explanation for why motile cells are often more patchily distributed than non-motile cells and provides a mechanistic framework to understand how turbulence, whose strength varies profoundly in marine environments, impacts ocean productivity.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Calder, Stuart A; Cao, Guixin; Okamoto, Satoshi

The J_eff=1/2 state is manifested in systems with large cubic crystal field splitting and spin-orbit coupling that are comparable to the on-site Coulomb interaction, U. 5d transition metal oxides host parameters in this regime and strong evidence for this state in Sr2IrO4, and additional iridates, has been presented. All the candidates, however, deviate from the cubic crystal field required to provide an unmixed canonical J_eff=1/2 state, impacting the development of a robust model of this novel insulating and magnetic state. We present experimental and theoretical results that not only show Ca4IrO6 hosts the state, but furthermore uniquely resides in themore » limit required for a canonical unmixed J_eff=1/2 state.« less

Unsupervised universal steganalyzer for high-dimensional steganalytic features

NASA Astrophysics Data System (ADS)

Hou, Xiaodan; Zhang, Tao

2016-11-01

The research in developing steganalytic features has been highly successful. These features are extremely powerful when applied to supervised binary classification problems. However, they are incompatible with unsupervised universal steganalysis because the unsupervised method cannot distinguish embedding distortion from varying levels of noises caused by cover variation. This study attempts to alleviate the problem by introducing similarity retrieval of image statistical properties (SRISP), with the specific aim of mitigating the effect of cover variation on the existing steganalytic features. First, cover images with some statistical properties similar to those of a given test image are searched from a retrieval cover database to establish an aided sample set. Then, unsupervised outlier detection is performed on a test set composed of the given test image and its aided sample set to determine the type (cover or stego) of the given test image. Our proposed framework, called SRISP-aided unsupervised outlier detection, requires no training. Thus, it does not suffer from model mismatch mess. Compared with prior unsupervised outlier detectors that do not consider SRISP, the proposed framework not only retains the universality but also exhibits superior performance when applied to high-dimensional steganalytic features.

Clonal Selection Based Artificial Immune System for Generalized Pattern Recognition

NASA Technical Reports Server (NTRS)

Huntsberger, Terry

2011-01-01

The last two decades has seen a rapid increase in the application of AIS (Artificial Immune Systems) modeled after the human immune system to a wide range of areas including network intrusion detection, job shop scheduling, classification, pattern recognition, and robot control. JPL (Jet Propulsion Laboratory) has developed an integrated pattern recognition/classification system called AISLE (Artificial Immune System for Learning and Exploration) based on biologically inspired models of B-cell dynamics in the immune system. When used for unsupervised or supervised classification, the method scales linearly with the number of dimensions, has performance that is relatively independent of the total size of the dataset, and has been shown to perform as well as traditional clustering methods. When used for pattern recognition, the method efficiently isolates the appropriate matches in the data set. The paper presents the underlying structure of AISLE and the results from a number of experimental studies.

BicPAMS: software for biological data analysis with pattern-based biclustering.

PubMed

Henriques, Rui; Ferreira, Francisco L; Madeira, Sara C

2017-02-02

Biclustering has been largely applied for the unsupervised analysis of biological data, being recognised today as a key technique to discover putative modules in both expression data (subsets of genes correlated in subsets of conditions) and network data (groups of coherently interconnected biological entities). However, given its computational complexity, only recent breakthroughs on pattern-based biclustering enabled efficient searches without the restrictions that state-of-the-art biclustering algorithms place on the structure and homogeneity of biclusters. As a result, pattern-based biclustering provides the unprecedented opportunity to discover non-trivial yet meaningful biological modules with putative functions, whose coherency and tolerance to noise can be tuned and made problem-specific. To enable the effective use of pattern-based biclustering by the scientific community, we developed BicPAMS (Biclustering based on PAttern Mining Software), a software that: 1) makes available state-of-the-art pattern-based biclustering algorithms (BicPAM (Henriques and Madeira, Alg Mol Biol 9:27, 2014), BicNET (Henriques and Madeira, Alg Mol Biol 11:23, 2016), BicSPAM (Henriques and Madeira, BMC Bioinforma 15:130, 2014), BiC2PAM (Henriques and Madeira, Alg Mol Biol 11:1-30, 2016), BiP (Henriques and Madeira, IEEE/ACM Trans Comput Biol Bioinforma, 2015), DeBi (Serin and Vingron, AMB 6:1-12, 2011) and BiModule (Okada et al., IPSJ Trans Bioinf 48(SIG5):39-48, 2007)); 2) consistently integrates their dispersed contributions; 3) further explores additional accuracy and efficiency gains; and 4) makes available graphical and application programming interfaces. Results on both synthetic and real data confirm the relevance of BicPAMS for biological data analysis, highlighting its essential role for the discovery of putative modules with non-trivial yet biologically significant functions from expression and network data. BicPAMS is the first biclustering tool offering the possibility to: 1) parametrically customize the structure, coherency and quality of biclusters; 2) analyze large-scale biological networks; and 3) tackle the restrictive assumptions placed by state-of-the-art biclustering algorithms. These contributions are shown to be key for an adequate, complete and user-assisted unsupervised analysis of biological data. BicPAMS and its tutorial available in http://www.bicpams.com .

Nonlinear dimension reduction and clustering by Minimum Curvilinearity unfold neuropathic pain and tissue embryological classes.

PubMed

Cannistraci, Carlo Vittorio; Ravasi, Timothy; Montevecchi, Franco Maria; Ideker, Trey; Alessio, Massimo

2010-09-15

Nonlinear small datasets, which are characterized by low numbers of samples and very high numbers of measures, occur frequently in computational biology, and pose problems in their investigation. Unsupervised hybrid-two-phase (H2P) procedures-specifically dimension reduction (DR), coupled with clustering-provide valuable assistance, not only for unsupervised data classification, but also for visualization of the patterns hidden in high-dimensional feature space. 'Minimum Curvilinearity' (MC) is a principle that-for small datasets-suggests the approximation of curvilinear sample distances in the feature space by pair-wise distances over their minimum spanning tree (MST), and thus avoids the introduction of any tuning parameter. MC is used to design two novel forms of nonlinear machine learning (NML): Minimum Curvilinear embedding (MCE) for DR, and Minimum Curvilinear affinity propagation (MCAP) for clustering. Compared with several other unsupervised and supervised algorithms, MCE and MCAP, whether individually or combined in H2P, overcome the limits of classical approaches. High performance was attained in the visualization and classification of: (i) pain patients (proteomic measurements) in peripheral neuropathy; (ii) human organ tissues (genomic transcription factor measurements) on the basis of their embryological origin. MC provides a valuable framework to estimate nonlinear distances in small datasets. Its extension to large datasets is prefigured for novel NMLs. Classification of neuropathic pain by proteomic profiles offers new insights for future molecular and systems biology characterization of pain. Improvements in tissue embryological classification refine results obtained in an earlier study, and suggest a possible reinterpretation of skin attribution as mesodermal. https://sites.google.com/site/carlovittoriocannistraci/home.

Spike timing analysis in neural networks with unsupervised synaptic plasticity

NASA Astrophysics Data System (ADS)

Mizusaki, B. E. P.; Agnes, E. J.; Brunnet, L. G.; Erichsen, R., Jr.

2013-01-01

The synaptic plasticity rules that sculpt a neural network architecture are key elements to understand cortical processing, as they may explain the emergence of stable, functional activity, while avoiding runaway excitation. For an associative memory framework, they should be built in a way as to enable the network to reproduce a robust spatio-temporal trajectory in response to an external stimulus. Still, how these rules may be implemented in recurrent networks and the way they relate to their capacity of pattern recognition remains unclear. We studied the effects of three phenomenological unsupervised rules in sparsely connected recurrent networks for associative memory: spike-timing-dependent-plasticity, short-term-plasticity and an homeostatic scaling. The system stability is monitored during the learning process of the network, as the mean firing rate converges to a value determined by the homeostatic scaling. Afterwards, it is possible to measure the recovery efficiency of the activity following each initial stimulus. This is evaluated by a measure of the correlation between spike fire timings, and we analysed the full memory separation capacity and limitations of this system.

On the unsupervised analysis of domain-specific Chinese texts

PubMed Central

Deng, Ke; Bol, Peter K.; Li, Kate J.; Liu, Jun S.

2016-01-01

With the growing availability of digitized text data both publicly and privately, there is a great need for effective computational tools to automatically extract information from texts. Because the Chinese language differs most significantly from alphabet-based languages in not specifying word boundaries, most existing Chinese text-mining methods require a prespecified vocabulary and/or a large relevant training corpus, which may not be available in some applications. We introduce an unsupervised method, top-down word discovery and segmentation (TopWORDS), for simultaneously discovering and segmenting words and phrases from large volumes of unstructured Chinese texts, and propose ways to order discovered words and conduct higher-level context analyses. TopWORDS is particularly useful for mining online and domain-specific texts where the underlying vocabulary is unknown or the texts of interest differ significantly from available training corpora. When outputs from TopWORDS are fed into context analysis tools such as topic modeling, word embedding, and association pattern finding, the results are as good as or better than that from using outputs of a supervised segmentation method. PMID:27185919

Unsupervised clustering of gene expression data points at hypoxia as possible trigger for metabolic syndrome.

PubMed

Ptitsyn, Andrey; Hulver, Matthew; Cefalu, William; York, David; Smith, Steven R

2006-12-19

Classification of large volumes of data produced in a microarray experiment allows for the extraction of important clues as to the nature of a disease. Using multi-dimensional unsupervised FOREL (FORmal ELement) algorithm we have re-analyzed three public datasets of skeletal muscle gene expression in connection with insulin resistance and type 2 diabetes (DM2). Our analysis revealed the major line of variation between expression profiles of normal, insulin resistant, and diabetic skeletal muscle. A cluster of most "metabolically sound" samples occupied one end of this line. The distance along this line coincided with the classic markers of diabetes risk, namely obesity and insulin resistance, but did not follow the accepted clinical diagnosis of DM2 as defined by the presence or absence of hyperglycemia. Genes implicated in this expression pattern are those controlling skeletal muscle fiber type and glycolytic metabolism. Additionally myoglobin and hemoglobin were upregulated and ribosomal genes deregulated in insulin resistant patients. Our findings are concordant with the changes seen in skeletal muscle with altitude hypoxia. This suggests that hypoxia and shift to glycolytic metabolism may also drive insulin resistance.

VHR satellite multitemporal data to extract cultural landscape changes in the roman site of Grumentum

NASA Astrophysics Data System (ADS)

masini, nicola; Lasaponara, Rosa

2013-04-01

The papers deals with the use of VHR satellite multitemporal data set to extract cultural landscape changes in the roman site of Grumentum Grumentum is an ancient town, 50 km south of Potenza, located near the roman road of Via Herculea which connected the Venusia, in the north est of Basilicata, with Heraclea in the Ionian coast. The first settlement date back to the 6th century BC. It was resettled by the Romans in the 3rd century BC. Its urban fabric which evidences a long history from the Republican age to late Antiquity (III BC-V AD) is composed of the typical urban pattern of cardi and decumani. Its excavated ruins include a large amphitheatre, a theatre, the thermae, the Forum and some temples. There are many techniques nowadays available to capture and record differences in two or more images. In this paper we focus and apply the two main approaches which can be distinguished into : (i) unsupervised and (ii) supervised change detection methods. Unsupervised change detection methods are generally based on the transformation of the two multispectral images in to a single band or multiband image which are further analyzed to identify changes Unsupervised change detection techniques are generally based on three basic steps (i) the preprocessing step, (ii) a pixel-by-pixel comparison is performed, (iii). Identification of changes according to the magnitude an direction (positive /negative). Unsupervised change detection are generally based on the transformation of the two multispectral images into a single band or multiband image which are further analyzed to identify changes. Than the separation between changed and unchanged classes is obtained from the magnitude of the resulting spectral change vectors by means of empirical or theoretical well founded approaches Supervised change detection methods are generally based on supervised classification methods, which require the availability of a suitable training set for the learning process of the classifiers. Unsupervised change detection techniques are generally based on three basic steps (i) the preprocessing step, (ii) supervised classification is performed on the single dates or on the map obtained as the difference of two dates, (iii). Identification of changes according to the magnitude an direction (positive /negative). Supervised change detection are generally based on supervised classification methods, which require the availability of a suitable training set for the learning process of the classifiers, therefore these algorithms require a preliminary knowledge necessary: (i) to generate representative parameters for each class of interest; and (ii) to carry out the training stage Advantages and disadvantages of the supervised and unsupervised approaches are discuss. Finally results from the the satellite multitemporal dataset was also integrated with aerial photos from historical archive in order to expand the time window of the investigation and capture landscape changes occurred from the Agrarian Reform, in the 50s, up today.

An Improved STARFM with Help of an Unmixing-Based Method to Generate High Spatial and Temporal Resolution Remote Sensing Data in Complex Heterogeneous Regions.

PubMed

Xie, Dengfeng; Zhang, Jinshui; Zhu, Xiufang; Pan, Yaozhong; Liu, Hongli; Yuan, Zhoumiqi; Yun, Ya

2016-02-05

Remote sensing technology plays an important role in monitoring rapid changes of the Earth's surface. However, sensors that can simultaneously provide satellite images with both high temporal and spatial resolution haven't been designed yet. This paper proposes an improved spatial and temporal adaptive reflectance fusion model (STARFM) with the help of an Unmixing-based method (USTARFM) to generate the high spatial and temporal data needed for the study of heterogeneous areas. The results showed that the USTARFM had higher accuracy than STARFM methods in two aspects of analysis: individual bands and of heterogeneity analysis. Taking the predicted NIR band as an example, the correlation coefficients (r) for the USTARFM, STARFM and unmixing methods were 0.96, 0.95, 0.90, respectively (p-value < 0.001); Root Mean Square Error (RMSE) values were 0.0245, 0.0300, 0.0401, respectively; and ERGAS values were 0.5416, 0.6507, 0.8737, respectively. The USTARM showed consistently higher performance than STARM when the degree of heterogeneity ranged from 2 to 10, highlighting that the use of this method provides the capacity to solve the data fusion problems faced when using STARFM. Additionally, the USTARFM method could help researchers achieve better performance than STARFM at a smaller window size from its heterogeneous land surface quantitative representation.

The dynamics of human-induced land cover change in miombo ecosystems of southern Africa

NASA Astrophysics Data System (ADS)

Jaiteh, Malanding Sambou

Understanding human-induced land cover change in the miombo require the consistent, geographically-referenced, data on temporal land cover characteristics as well as biophysical and socioeconomic drivers of land use, the major cause of land cover change. The overall goal of this research to examine the applications of high-resolution satellite remote sensing data in studying the dynamics of human-induced land cover change in the miombo. Specific objectives are to: (1) evaluate the applications of computer-assisted classification of Landsat Thematic Mapper (TM) data for land cover mapping in the miombo and (2) analyze spatial and temporal patterns of landscape change locations in the miombo. Stepwise Thematic Classification, STC (a hybrid supervised-unsupervised classification) procedure for classifying Landsat TM data was developed and tested using Landsat TM data. Classification accuracy results were compared to those from supervised and unsupervised classification. The STC provided the highest classification accuracy i.e., 83.9% correspondence between classified and referenced data compared to 44.2% and 34.5% for unsupervised and supervised classification respectively. Improvements in the classification process can be attributed to thematic stratification of the image data into spectrally homogenous (thematic) groups and step-by-step classification of the groups using supervised or unsupervised classification techniques. Supervised classification failed to classify 18% of the scene evidence that training data used did not adequately represent all of the variability in the data. Application of the procedure in drier miombo produced overall classification accuracy of 63%. This is much lower than that of wetter miombo. The results clearly demonstrate that digital classification of Landsat TM can be successfully implemented in the miombo without intensive fieldwork. Spatial characteristics of land cover change in agricultural and forested landscapes in central Malawi were analyzed for the period 1984 to 1995 spatial pattern analysis methods. Shifting cultivation areas, Agriculture in forested landscape, experienced highest rate of woodland cover fragmentation with mean patch size of closed woodland cover decreasing from 20ha to 7.5ha. Permanent bare (cropland and settlement) in intensive agricultural matrix landscapes increased 52% largely through the conversion of fallow areas. Protected National Park area remained fairly unchanged although closed woodland area increased by 4%, mainly from regeneration of open woodland. This study provided evidence that changes in spatial characteristics in the miombo differ with landscape. Land use change (i.e. conversion to cropland) is the primary driving force behind changes in landscape spatial patterns. Also, results revealed that exclusion of intense human use (i.e. cultivation and woodcutting) through regulations and/or fencing increased both closed woodland area (through regeneration of open woodland) and overall connectivity in the landscape. Spatial characteristics of land cover change were analyzed at locations in Malawi (wetter miombo) and Zimbabwe (drier miombo). Results indicate land cover dynamics differ both between and within case study sites. In communal areas in the Kasungu scene, land cover change is dominated by woodland fragmentation to open vegetation. Change in private commercial lands was dominantly expansion of bare (settlement and cropland) areas primarily at the expense of open vegetation (fallow land).

Advanced methods in NDE using machine learning approaches

NASA Astrophysics Data System (ADS)

Wunderlich, Christian; Tschöpe, Constanze; Duckhorn, Frank

2018-04-01

Machine learning (ML) methods and algorithms have been applied recently with great success in quality control and predictive maintenance. Its goal to build new and/or leverage existing algorithms to learn from training data and give accurate predictions, or to find patterns, particularly with new and unseen similar data, fits perfectly to Non-Destructive Evaluation. The advantages of ML in NDE are obvious in such tasks as pattern recognition in acoustic signals or automated processing of images from X-ray, Ultrasonics or optical methods. Fraunhofer IKTS is using machine learning algorithms in acoustic signal analysis. The approach had been applied to such a variety of tasks in quality assessment. The principal approach is based on acoustic signal processing with a primary and secondary analysis step followed by a cognitive system to create model data. Already in the second analysis steps unsupervised learning algorithms as principal component analysis are used to simplify data structures. In the cognitive part of the software further unsupervised and supervised learning algorithms will be trained. Later the sensor signals from unknown samples can be recognized and classified automatically by the algorithms trained before. Recently the IKTS team was able to transfer the software for signal processing and pattern recognition to a small printed circuit board (PCB). Still, algorithms will be trained on an ordinary PC; however, trained algorithms run on the Digital Signal Processor and the FPGA chip. The identical approach will be used for pattern recognition in image analysis of OCT pictures. Some key requirements have to be fulfilled, however. A sufficiently large set of training data, a high signal-to-noise ratio, and an optimized and exact fixation of components are required. The automated testing can be done subsequently by the machine. By integrating the test data of many components along the value chain further optimization including lifetime and durability prediction based on big data becomes possible, even if components are used in different versions or configurations. This is the promise behind German Industry 4.0.

Spectrally Resolved Fiber Photometry for Multi-component Analysis of Brain Circuits.

PubMed

Meng, Chengbo; Zhou, Jingheng; Papaneri, Amy; Peddada, Teja; Xu, Karen; Cui, Guohong

2018-04-25

To achieve simultaneous measurement of multiple cellular events in molecularly defined groups of neurons in vivo, we designed a spectrometer-based fiber photometry system that allows for spectral unmixing of multiple fluorescence signals recorded from deep brain structures in behaving animals. Using green and red Ca 2+ indicators differentially expressed in striatal direct- and indirect-pathway neurons, we were able to simultaneously monitor the neural activity in these two pathways in freely moving animals. We found that the activities were highly synchronized between the direct and indirect pathways within one hemisphere and were desynchronized between the two hemispheres. We further analyzed the relationship between the movement patterns and the magnitude of activation in direct- and indirect-pathway neurons and found that the striatal direct and indirect pathways coordinately control the dynamics and fate of movement. Published by Elsevier Inc.

Principal component analysis-based unsupervised feature extraction applied to in silico drug discovery for posttraumatic stress disorder-mediated heart disease.

PubMed

Taguchi, Y-h; Iwadate, Mitsuo; Umeyama, Hideaki

2015-04-30

Feature extraction (FE) is difficult, particularly if there are more features than samples, as small sample numbers often result in biased outcomes or overfitting. Furthermore, multiple sample classes often complicate FE because evaluating performance, which is usual in supervised FE, is generally harder than the two-class problem. Developing sample classification independent unsupervised methods would solve many of these problems. Two principal component analysis (PCA)-based FE, specifically, variational Bayes PCA (VBPCA) was extended to perform unsupervised FE, and together with conventional PCA (CPCA)-based unsupervised FE, were tested as sample classification independent unsupervised FE methods. VBPCA- and CPCA-based unsupervised FE both performed well when applied to simulated data, and a posttraumatic stress disorder (PTSD)-mediated heart disease data set that had multiple categorical class observations in mRNA/microRNA expression of stressed mouse heart. A critical set of PTSD miRNAs/mRNAs were identified that show aberrant expression between treatment and control samples, and significant, negative correlation with one another. Moreover, greater stability and biological feasibility than conventional supervised FE was also demonstrated. Based on the results obtained, in silico drug discovery was performed as translational validation of the methods. Our two proposed unsupervised FE methods (CPCA- and VBPCA-based) worked well on simulated data, and outperformed two conventional supervised FE methods on a real data set. Thus, these two methods have suggested equivalence for FE on categorical multiclass data sets, with potential translational utility for in silico drug discovery.

Geometric Mixing, Peristalsis, and the Geometric Phase of the Stomach.

PubMed

Arrieta, Jorge; Cartwright, Julyan H E; Gouillart, Emmanuelle; Piro, Nicolas; Piro, Oreste; Tuval, Idan

2015-01-01

Mixing fluid in a container at low Reynolds number--in an inertialess environment--is not a trivial task. Reciprocating motions merely lead to cycles of mixing and unmixing, so continuous rotation, as used in many technological applications, would appear to be necessary. However, there is another solution: movement of the walls in a cyclical fashion to introduce a geometric phase. We show using journal-bearing flow as a model that such geometric mixing is a general tool for using deformable boundaries that return to the same position to mix fluid at low Reynolds number. We then simulate a biological example: we show that mixing in the stomach functions because of the "belly phase," peristaltic movement of the walls in a cyclical fashion introduces a geometric phase that avoids unmixing.

Geometric Mixing, Peristalsis, and the Geometric Phase of the Stomach

PubMed Central

Arrieta, Jorge; Cartwright, Julyan H. E.; Gouillart, Emmanuelle; Piro, Nicolas; Piro, Oreste; Tuval, Idan

2015-01-01

Mixing fluid in a container at low Reynolds number— in an inertialess environment—is not a trivial task. Reciprocating motions merely lead to cycles of mixing and unmixing, so continuous rotation, as used in many technological applications, would appear to be necessary. However, there is another solution: movement of the walls in a cyclical fashion to introduce a geometric phase. We show using journal-bearing flow as a model that such geometric mixing is a general tool for using deformable boundaries that return to the same position to mix fluid at low Reynolds number. We then simulate a biological example: we show that mixing in the stomach functions because of the “belly phase,” peristaltic movement of the walls in a cyclical fashion introduces a geometric phase that avoids unmixing. PMID:26154384

Fingerprinting Sources of Suspended Sediment in a Canadian Agricultural Watershed Using the MixSIAR Bayesian Unmixing Model

NASA Astrophysics Data System (ADS)

Smith, J. P.; Owens, P. N.; Gaspar, L.; Lobb, D. A.; Petticrew, E. L.

2015-12-01

An understanding of sediment redistribution processes and the main sediment sources within a watershed is needed to support watershed management strategies. The fingerprinting technique is increasingly being recognized as a method for establishing the source of the sediment transported within watersheds. However, the different behaviour of the various fingerprinting properties has been recognized as a major limitation of the technique, and the uncertainty associated with tracer selection needs to be addressed. There are also questions associated with which modelling approach (frequentist or Bayesian) is the best to unmix complex environmental mixtures, such as river sediment. This study aims to compare and evaluate the differences between fingerprinting predictions provided by a Bayesian unmixing model (MixSIAR) using different groups of tracer properties for use in sediment source identification. We used fallout radionuclides (e.g. 137Cs) and geochemical elements (e.g. As) as conventional fingerprinting properties, and colour parameters as emerging properties; both alone and in combination. These fingerprinting properties are being used (i.e. Koiter et al., 2013; Barthod et al., 2015) to determine the proportional contributions of fine sediment in the South Tobacco Creek Watershed, an agricultural watershed located in Manitoba, Canada. We show that the unmixing model using a combination of fallout radionuclides and geochemical tracers gave similar results to the model based on colour parameters. Furthermore, we show that a model that combines all tracers (i.e. radionuclide/geochemical and colour) gave similar results, showing that sediment sources change from predominantly topsoil in the upper reaches of the watershed to channel bank and bedrock outcrop material in the lower reaches. Barthod LRM et al. (2015). Selecting color-based tracers and classifying sediment sources in the assessment of sediment dynamics using sediment source fingerprinting. J Environ Qual. Doi:10.2134/jeq2015.01.0043 Koiter AJ et al. (2013). Investigating the role of connectivity and scale in assessing the sources of sediment in an agricultural watershed in the Canadian prairies using sediment source fingerprinting. J Soils Sediments, 13, 1676-1691.

Component Analysis of Remanent Magnetization Curves: A Revisit with a New Model Distribution

NASA Astrophysics Data System (ADS)

Zhao, X.; Suganuma, Y.; Fujii, M.

2017-12-01

Geological samples often consist of several magnetic components that have distinct origins. As the magnetic components are often indicative of their underlying geological and environmental processes, it is therefore desirable to identify individual components to extract associated information. This component analysis can be achieved using the so-called unmixing method, which fits a mixture model of certain end-member model distribution to the measured remanent magnetization curve. In earlier studies, the lognormal, skew generalized Gaussian and skewed Gaussian distributions have been used as the end-member model distribution in previous studies, which are performed on the gradient curve of remanent magnetization curves. However, gradient curves are sensitive to measurement noise as the differentiation of the measured curve amplifies noise, which could deteriorate the component analysis. Though either smoothing or filtering can be applied to reduce the noise before differentiation, their effect on biasing component analysis is vaguely addressed. In this study, we investigated a new model function that can be directly applied to the remanent magnetization curves and therefore avoid the differentiation. The new model function can provide more flexible shape than the lognormal distribution, which is a merit for modeling the coercivity distribution of complex magnetic component. We applied the unmixing method both to model and measured data, and compared the results with those obtained using other model distributions to better understand their interchangeability, applicability and limitation. The analyses on model data suggest that unmixing methods are inherently sensitive to noise, especially when the number of component is over two. It is, therefore, recommended to verify the reliability of component analysis by running multiple analyses with synthetic noise. Marine sediments and seafloor rocks are analyzed with the new model distribution. Given the same component number, the new model distribution can provide closer fits than the lognormal distribution evidenced by reduced residuals. Moreover, the new unmixing protocol is automated so that the users are freed from the labor of providing initial guesses for the parameters, which is also helpful to improve the subjectivity of component analysis.

Retrieving the hydrous minerals on Mars by sparse unmixing and the Hapke model using MRO/CRISM data

NASA Astrophysics Data System (ADS)

Lin, Honglei; Zhang, Xia

2017-05-01

The hydrous minerals on Mars preserve records of potential past aqueous activity. Quantitative information regarding mineralogical composition would enable a better understanding of the formation processes of these hydrous minerals, and provide unique insights into ancient habitable environments and the geological evolution of Mars. The Compact Reconnaissance Imaging Spectrometer for Mars (CRISM) has the advantage of both a high spatial and spectral resolution, which makes it suitable for the quantitative analysis of minerals on Mars. However, few studies have attempted to quantitatively retrieve the mineralogical composition of hydrous minerals on Mars using visible-infrared (VISIR) hyperspectral data due to their distribution characteristics (relatively low concentrations, located primarily in Noachian terrain, and unclear or unknown background minerals) and limitations of the spectral unmixing algorithms. In this study, we developed a modified sparse unmixing (MSU) method, combining the Hapke model with sparse unmixing. The MSU method considers the nonlinear mixed effects of minerals and avoids the difficulty of determining the spectra and number of endmembers from the image. The proposed method was tested successfully using laboratory mixture spectra and an Airborne Visible Infrared Imaging Spectrometer (AVIRIS) image of the Cuprite site (Nevada, USA). Then it was applied to CRISM hyperspectral images over Gale crater. Areas of hydrous mineral distribution were first identified by spectral features of water and hydroxyl absorption. The MSU method was performed on these areas, and the abundances were retrieved. The results indicated that the hydrous minerals consisted mostly of hydrous silicates, with abundances of up to 35%, as well as hydrous sulfates, with abundances ≤10%. Several main subclasses of hydrous minerals (e.g., Fe/Mg phyllosilicate, prehnite, and kieserite) were retrieved. Among these, Fe/Mg- phyllosilicate was the most abundant, with abundances ranging up to almost 30%, followed by prehnite and kieserite, with abundances lower than 15%. Our results are consistent with related research and in situ analyses of data from the rover Curiosity; thus, our method has the potential to be widely used for quantitative mineralogical mapping at the global scale of the surface of Mars.

Microimaging FT-IR of oral cavity tumours. Part III: Cells, inoculated tissues and human tissues

NASA Astrophysics Data System (ADS)

Conti, C.; Ferraris, P.; Giorgini, E.; Pieramici, T.; Possati, L.; Rocchetti, R.; Rubini, C.; Sabbatini, S.; Tosi, G.; Mariggiò, M. A.; Lo Muzio, L.

2007-05-01

The biochemistry of healthy and tumour cell cultures, inoculated tissues and oral cavity tissues have been studied by FT-IR Microscopy with the aim to relate spectral patterns with microbiological and histopathological findings. 'Supervised' and 'unsupervised' procedures of data handling afforded a satisfactory degree of accordance between spectroscopic and the other two techniques. In particular, changes in frequency and intensity of proteins, connective and nucleic acids vibrational modes as well as the visualization of biochemical single wave number or band ratio images, allowed an evaluation of the pathological changes. The spectroscopic patterns of inoculated tissues resulted quite similar to human tissues; differences of both types of sections with cellular lines could be explained by the influence of the environment.

Detection of sunn pest-damaged wheat samples using visible/near-infrared spectroscopy based on pattern recognition.

PubMed

Basati, Zahra; Jamshidi, Bahareh; Rasekh, Mansour; Abbaspour-Gilandeh, Yousef

2018-05-30

The presence of sunn pest-damaged grains in wheat mass reduces the quality of flour and bread produced from it. Therefore, it is essential to assess the quality of the samples in collecting and storage centers of wheat and flour mills. In this research, the capability of visible/near-infrared (Vis/NIR) spectroscopy combined with pattern recognition methods was investigated for discrimination of wheat samples with different percentages of sunn pest-damaged. To this end, various samples belonging to five classes (healthy and 5%, 10%, 15% and 20% unhealthy) were analyzed using Vis/NIR spectroscopy (wavelength range of 350-1000 nm) based on both supervised and unsupervised pattern recognition methods. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) as the unsupervised techniques and soft independent modeling of class analogies (SIMCA) and partial least squares-discriminant analysis (PLS-DA) as supervised methods were used. The results showed that Vis/NIR spectra of healthy samples were correctly clustered using both PCA and HCA. Due to the high overlapping between the four unhealthy classes (5%, 10%, 15% and 20%), it was not possible to discriminate all the unhealthy samples in individual classes. However, when considering only the two main categories of healthy and unhealthy, an acceptable degree of separation between the classes can be obtained after classification with supervised pattern recognition methods of SIMCA and PLS-DA. SIMCA based on PCA modeling correctly classified samples in two classes of healthy and unhealthy with classification accuracy of 100%. Moreover, the power of the wavelengths of 839 nm, 918 nm and 995 nm were more than other wavelengths to discriminate two classes of healthy and unhealthy. It was also concluded that PLS-DA provides excellent classification results of healthy and unhealthy samples (R 2  = 0.973 and RMSECV = 0.057). Therefore, Vis/NIR spectroscopy based on pattern recognition techniques can be useful for rapid distinguishing the healthy wheat samples from those damaged by sunn pest in the maintenance and processing centers. Copyright © 2018 Elsevier B.V. All rights reserved.

Best friends' interactions and substance use: The role of friend pressure and unsupervised co-deviancy.

PubMed

Tsakpinoglou, Florence; Poulin, François

2017-10-01

Best friends exert a substantial influence on rising alcohol and marijuana use during adolescence. Two mechanisms occurring within friendship - friend pressure and unsupervised co-deviancy - may partially capture the way friends influence one another. The current study aims to: (1) examine the psychometric properties of a new instrument designed to assess pressure from a youth's best friend and unsupervised co-deviancy; (2) investigate the relative contribution of these processes to alcohol and marijuana use; and (3) determine whether gender moderates these associations. Data were collected through self-report questionnaires completed by 294 Canadian youths (62% female) across two time points (ages 15-16). Principal component analysis yielded a two-factor solution corresponding to friend pressure and unsupervised co-deviancy. Logistic regressions subsequently showed that unsupervised co-deviancy was predictive of an increase in marijuana use one year later. Neither process predicted an increase in alcohol use. Results did not differ as a function of gender. Copyright © 2017 The Foundation for Professionals in Services for Adolescents. Published by Elsevier Ltd. All rights reserved.

An unsupervised classification approach for analysis of Landsat data to monitor land reclamation in Belmont county, Ohio

NASA Technical Reports Server (NTRS)

Brumfield, J. O.; Bloemer, H. H. L.; Campbell, W. J.

1981-01-01

Two unsupervised classification procedures for analyzing Landsat data used to monitor land reclamation in a surface mining area in east central Ohio are compared for agreement with data collected from the corresponding locations on the ground. One procedure is based on a traditional unsupervised-clustering/maximum-likelihood algorithm sequence that assumes spectral groupings in the Landsat data in n-dimensional space; the other is based on a nontraditional unsupervised-clustering/canonical-transformation/clustering algorithm sequence that not only assumes spectral groupings in n-dimensional space but also includes an additional feature-extraction technique. It is found that the nontraditional procedure provides an appreciable improvement in spectral groupings and apparently increases the level of accuracy in the classification of land cover categories.

An unsupervised hierarchical dynamic self-organizing approach to cancer class discovery and marker gene identification in microarray data.

PubMed

Hsu, Arthur L; Tang, Sen-Lin; Halgamuge, Saman K

2003-11-01

Current Self-Organizing Maps (SOMs) approaches to gene expression pattern clustering require the user to predefine the number of clusters likely to be expected. Hierarchical clustering methods used in this area do not provide unique partitioning of data. We describe an unsupervised dynamic hierarchical self-organizing approach, which suggests an appropriate number of clusters, to perform class discovery and marker gene identification in microarray data. In the process of class discovery, the proposed algorithm identifies corresponding sets of predictor genes that best distinguish one class from other classes. The approach integrates merits of hierarchical clustering with robustness against noise known from self-organizing approaches. The proposed algorithm applied to DNA microarray data sets of two types of cancers has demonstrated its ability to produce the most suitable number of clusters. Further, the corresponding marker genes identified through the unsupervised algorithm also have a strong biological relationship to the specific cancer class. The algorithm tested on leukemia microarray data, which contains three leukemia types, was able to determine three major and one minor cluster. Prediction models built for the four clusters indicate that the prediction strength for the smaller cluster is generally low, therefore labelled as uncertain cluster. Further analysis shows that the uncertain cluster can be subdivided further, and the subdivisions are related to two of the original clusters. Another test performed using colon cancer microarray data has automatically derived two clusters, which is consistent with the number of classes in data (cancerous and normal). JAVA software of dynamic SOM tree algorithm is available upon request for academic use. A comparison of rectangular and hexagonal topologies for GSOM is available from http://www.mame.mu.oz.au/mechatronics/journalinfo/Hsu2003supp.pdf

Automated segmentation of white matter fiber bundles using diffusion tensor imaging data and a new density based clustering algorithm.

PubMed

Kamali, Tahereh; Stashuk, Daniel

2016-10-01

Robust and accurate segmentation of brain white matter (WM) fiber bundles assists in diagnosing and assessing progression or remission of neuropsychiatric diseases such as schizophrenia, autism and depression. Supervised segmentation methods are infeasible in most applications since generating gold standards is too costly. Hence, there is a growing interest in designing unsupervised methods. However, most conventional unsupervised methods require the number of clusters be known in advance which is not possible in most applications. The purpose of this study is to design an unsupervised segmentation algorithm for brain white matter fiber bundles which can automatically segment fiber bundles using intrinsic diffusion tensor imaging data information without considering any prior information or assumption about data distributions. Here, a new density based clustering algorithm called neighborhood distance entropy consistency (NDEC), is proposed which discovers natural clusters within data by simultaneously utilizing both local and global density information. The performance of NDEC is compared with other state of the art clustering algorithms including chameleon, spectral clustering, DBSCAN and k-means using Johns Hopkins University publicly available diffusion tensor imaging data. The performance of NDEC and other employed clustering algorithms were evaluated using dice ratio as an external evaluation criteria and density based clustering validation (DBCV) index as an internal evaluation metric. Across all employed clustering algorithms, NDEC obtained the highest average dice ratio (0.94) and DBCV value (0.71). NDEC can find clusters with arbitrary shapes and densities and consequently can be used for WM fiber bundle segmentation where there is no distinct boundary between various bundles. NDEC may also be used as an effective tool in other pattern recognition and medical diagnostic systems in which discovering natural clusters within data is a necessity. Copyright © 2016 Elsevier B.V. All rights reserved.

Unmixing techniques for better segmentation of urban zones, roads, and open pit mines

NASA Astrophysics Data System (ADS)

Nikolov, Hristo; Borisova, Denitsa; Petkov, Doyno

2010-10-01

In this paper the linear unmixing method has been applied in classification of manmade objects, namely urbanized zones, roads etc. The idea is to exploit to larger extent the possibilities offered by multispectral imagers having mid spatial resolution in this case TM/ETM+ instruments. In this research unmixing is used to find consistent regression dependencies between multispectral data and those gathered in-situ and airborne-based sensors. The correct identification of the mixed pixels is key element for the subsequent segmentation forming the shape of the artificial feature is determined much more reliable. This especially holds true for objects with relatively narrow structure for example two-lane roads for which the spatial resolution is larger that the object itself. We have combined ground spectrometry of asphalt, Landsat images of RoI, and in-situ measured asphalt in order to determine the narrow roads. The reflectance of paving stones made from granite is highest compared to another ones which is true for open and stone pits. The potential for mapping is not limited to the mid-spatial Landsat data, but also may be used if the data has higher spatial resolution (as fine as 0.5 m). In this research the spectral and directional reflection properties of asphalt and concrete surfaces compared to those of paving stone made from different rocks have been measured. The in-situ measurements, which plays key role have been obtained using the Thematically Oriented Multichannel Spectrometer (TOMS) - designed in STIL-BAS.

Sediment unmixing using detrital geochronology

USGS Publications Warehouse

Sharman, Glenn R.; Johnstone, Samuel

2017-01-01

Sediment mixing within sediment routing systems can exert a strong influence on the preservation of provenance signals that yield insight into the influence of environmental forcings (e.g., tectonism, climate) on the earth’s surface. Here we discuss two approaches to unmixing detrital geochronologic data in an effort to characterize complex changes in the sedimentary record. First we summarize ‘top-down’ mixing, which has been successfully employed in the past to characterize the different fractions of prescribed source distributions (‘parents’) that characterize a derived sample or set of samples (‘daughters’). Second we propose the use of ‘bottom-up’ methods, previously used primarily for grain size distributions, to model parent distributions and the abundances of these parents within a set of daughters. We demonstrate the utility of both top-down and bottom-up approaches to unmixing detrital geochronologic data within a well-constrained sediment routing system in central California. Use of a variety of goodness-of-fit metrics in top-down modeling reveals the importance of considering the range of allowable mixtures over any single best-fit mixture calculation. Bottom-up modeling of 12 daughter samples from beaches and submarine canyons yields modeled parent distributions that are remarkably similar to those expected from the geologic context of the sediment-routing system. In general, mixture modeling has potential to supplement more widely applied approaches in comparing detrital geochronologic data by casting differences between samples as differing proportions of geologically meaningful end-member provenance categories.

Sediment unmixing using detrital geochronology

NASA Astrophysics Data System (ADS)

Sharman, Glenn R.; Johnstone, Samuel A.

2017-11-01

Sediment mixing within sediment routing systems can exert a strong influence on the preservation of provenance signals that yield insight into the effect of environmental forcing (e.g., tectonism, climate) on the Earth's surface. Here, we discuss two approaches to unmixing detrital geochronologic data in an effort to characterize complex changes in the sedimentary record. First, we summarize 'top-down' mixing, which has been successfully employed in the past to characterize the different fractions of prescribed source distributions ('parents') that characterize a derived sample or set of samples ('daughters'). Second, we propose the use of 'bottom-up' methods, previously used primarily for grain size distributions, to model parent distributions and the abundances of these parents within a set of daughters. We demonstrate the utility of both top-down and bottom-up approaches to unmixing detrital geochronologic data within a well-constrained sediment routing system in central California. Use of a variety of goodness-of-fit metrics in top-down modeling reveals the importance of considering the range of allowable that is well mixed over any single best-fit mixture calculation. Bottom-up modeling of 12 daughter samples from beaches and submarine canyons yields modeled parent distributions that are remarkably similar to those expected from the geologic context of the sediment-routing system. In general, mixture modeling has the potential to supplement more widely applied approaches in comparing detrital geochronologic data by casting differences between samples as differing proportions of geologically meaningful end-member provenance categories.

(LMRG): Microscope Resolution, Objective Quality, Spectral Accuracy and Spectral Un-mixing

PubMed Central

Bayles, Carol J.; Cole, Richard W.; Eason, Brady; Girard, Anne-Marie; Jinadasa, Tushare; Martin, Karen; McNamara, George; Opansky, Cynthia; Schulz, Katherine; Thibault, Marc; Brown, Claire M.

2012-01-01

The second study by the LMRG focuses on measuring confocal laser scanning microscope (CLSM) resolution, objective lens quality, spectral imaging accuracy and spectral un-mixing. Affordable test samples for each aspect of the study were designed, prepared and sent to 116 labs from 23 countries across the globe. Detailed protocols were designed for the three tests and customized for most of the major confocal instruments being used by the study participants. One protocol developed for measuring resolution and objective quality was recently published in Nature Protocols (Cole, R. W., T. Jinadasa, et al. (2011). Nature Protocols 6(12): 1929–1941). The first study involved 3D imaging of sub-resolution fluorescent microspheres to determine the microscope point spread function. Results of the resolution studies as well as point spread function quality (i.e. objective lens quality) from 140 different objective lenses will be presented. The second study of spectral accuracy looked at the reflection of the laser excitation lines into the spectral detection in order to determine the accuracy of these systems to report back the accurate laser emission wavelengths. Results will be presented from 42 different spectral confocal systems. Finally, samples with double orange beads (orange core and orange coating) were imaged spectrally and the imaging software was used to un-mix fluorescence signals from the two orange dyes. Results from 26 different confocal systems will be summarized. Time will be left to discuss possibilities for the next LMRG study.

Local hyperspectral data multisharpening based on linear/linear-quadratic nonnegative matrix factorization by integrating lidar data

NASA Astrophysics Data System (ADS)

Benhalouche, Fatima Zohra; Karoui, Moussa Sofiane; Deville, Yannick; Ouamri, Abdelaziz

2015-10-01

In this paper, a new Spectral-Unmixing-based approach, using Nonnegative Matrix Factorization (NMF), is proposed to locally multi-sharpen hyperspectral data by integrating a Digital Surface Model (DSM) obtained from LIDAR data. In this new approach, the nature of the local mixing model is detected by using the local variance of the object elevations. The hyper/multispectral images are explored using small zones. In each zone, the variance of the object elevations is calculated from the DSM data in this zone. This variance is compared to a threshold value and the adequate linear/linearquadratic spectral unmixing technique is used in the considered zone to independently unmix hyperspectral and multispectral data, using an adequate linear/linear-quadratic NMF-based approach. The obtained spectral and spatial information thus respectively extracted from the hyper/multispectral images are then recombined in the considered zone, according to the selected mixing model. Experiments based on synthetic hyper/multispectral data are carried out to evaluate the performance of the proposed multi-sharpening approach and literature linear/linear-quadratic approaches used on the whole hyper/multispectral data. In these experiments, real DSM data are used to generate synthetic data containing linear and linear-quadratic mixed pixel zones. The DSM data are also used for locally detecting the nature of the mixing model in the proposed approach. Globally, the proposed approach yields good spatial and spectral fidelities for the multi-sharpened data and significantly outperforms the used literature methods.

Computational discovery of pathway-level genetic vulnerabilities in non-small-cell lung cancer | Office of Cancer Genomics

Cancer.gov

Novel approaches are needed for discovery of targeted therapies for non-small-cell lung cancer (NSCLC) that are specific to certain patients. Whole genome RNAi screening of lung cancer cell lines provides an ideal source for determining candidate drug targets. Unsupervised learning algorithms uncovered patterns of differential vulnerability across lung cancer cell lines to loss of functionally related genes. Such genetic vulnerabilities represent candidate targets for therapy and are found to be involved in splicing, translation and protein folding.

NDRAM: nonlinear dynamic recurrent associative memory for learning bipolar and nonbipolar correlated patterns.

PubMed

Chartier, Sylvain; Proulx, Robert

2005-11-01

This paper presents a new unsupervised attractor neural network, which, contrary to optimal linear associative memory models, is able to develop nonbipolar attractors as well as bipolar attractors. Moreover, the model is able to develop less spurious attractors and has a better recall performance under random noise than any other Hopfield type neural network. Those performances are obtained by a simple Hebbian/anti-Hebbian online learning rule that directly incorporates feedback from a specific nonlinear transmission rule. Several computer simulations show the model's distinguishing properties.

Analytical aspects of plant metabolite profiling platforms: current standings and future aims.

PubMed

Seger, Christoph; Sturm, Sonja

2007-02-01

Over the past years, metabolic profiling has been established as a comprehensive systems biology tool. Mass spectrometry or NMR spectroscopy-based technology platforms combined with unsupervised or supervised multivariate statistical methodologies allow a deep insight into the complex metabolite patterns of plant-derived samples. Within this review, we provide a thorough introduction to the analytical hard- and software requirements of metabolic profiling platforms. Methodological limitations are addressed, and the metabolic profiling workflow is exemplified by summarizing recent applications ranging from model systems to more applied topics.

Using Machine Learning Techniques in the Analysis of Oceanographic Data

NASA Astrophysics Data System (ADS)

Falcinelli, K. E.; Abuomar, S.

2017-12-01

Acoustic Doppler Current Profilers (ADCPs) are oceanographic tools capable of collecting large amounts of current profile data. Using unsupervised machine learning techniques such as principal component analysis, fuzzy c-means clustering, and self-organizing maps, patterns and trends in an ADCP dataset are found. Cluster validity algorithms such as visual assessment of cluster tendency and clustering index are used to determine the optimal number of clusters in the ADCP dataset. These techniques prove to be useful in analysis of ADCP data and demonstrate potential for future use in other oceanographic applications.

Comprehensive Chemical Fingerprinting of High-Quality Cocoa at Early Stages of Processing: Effectiveness of Combined Untargeted and Targeted Approaches for Classification and Discrimination.

PubMed

Magagna, Federico; Guglielmetti, Alessandro; Liberto, Erica; Reichenbach, Stephen E; Allegrucci, Elena; Gobino, Guido; Bicchi, Carlo; Cordero, Chiara

2017-08-02

This study investigates chemical information of volatile fractions of high-quality cocoa (Theobroma cacao L. Malvaceae) from different origins (Mexico, Ecuador, Venezuela, Columbia, Java, Trinidad, and Sao Tomè) produced for fine chocolate. This study explores the evolution of the entire pattern of volatiles in relation to cocoa processing (raw, roasted, steamed, and ground beans). Advanced chemical fingerprinting (e.g., combined untargeted and targeted fingerprinting) with comprehensive two-dimensional gas chromatography coupled with mass spectrometry allows advanced pattern recognition for classification, discrimination, and sensory-quality characterization. The entire data set is analyzed for 595 reliable two-dimensional peak regions, including 130 known analytes and 13 potent odorants. Multivariate analysis with unsupervised exploration (principal component analysis) and simple supervised discrimination methods (Fisher ratios and linear regression trees) reveal informative patterns of similarities and differences and identify characteristic compounds related to sample origin and manufacturing step.

A Dictionary Approach to Electron Backscatter Diffraction Indexing.

PubMed

Chen, Yu H; Park, Se Un; Wei, Dennis; Newstadt, Greg; Jackson, Michael A; Simmons, Jeff P; De Graef, Marc; Hero, Alfred O

2015-06-01

We propose a framework for indexing of grain and subgrain structures in electron backscatter diffraction patterns of polycrystalline materials. We discretize the domain of a dynamical forward model onto a dense grid of orientations, producing a dictionary of patterns. For each measured pattern, we identify the most similar patterns in the dictionary, and identify boundaries, detect anomalies, and index crystal orientations. The statistical distribution of these closest matches is used in an unsupervised binary decision tree (DT) classifier to identify grain boundaries and anomalous regions. The DT classifies a pattern as an anomaly if it has an abnormally low similarity to any pattern in the dictionary. It classifies a pixel as being near a grain boundary if the highly ranked patterns in the dictionary differ significantly over the pixel's neighborhood. Indexing is accomplished by computing the mean orientation of the closest matches to each pattern. The mean orientation is estimated using a maximum likelihood approach that models the orientation distribution as a mixture of Von Mises-Fisher distributions over the quaternionic three sphere. The proposed dictionary matching approach permits segmentation, anomaly detection, and indexing to be performed in a unified manner with the additional benefit of uncertainty quantification.

Quantitative detection of settled coal dust over green canopy

NASA Astrophysics Data System (ADS)

Brook, Anna; Sahar, Nir

2017-04-01

The main task of environmental and geoscience applications are efficient and accurate quantitative classification of earth surfaces and spatial phenomena. In the past decade, there has been a significant interest in employing spectral unmixing in order to retrieve accurate quantitative information latent in in situ data. Recently, the ground-truth and laboratory measured spectral signatures promoted by advanced algorithms are proposed as a new path toward solving the unmixing problem in semi-supervised fashion. This study presents a practical implementation of field spectroscopy as a quantitative tool to detect settled coal dust over green canopy in free/open environment. Coal dust is a fine powdered form of coal, which is created by the crushing, grinding, and pulverizing of coal. Since the inelastic nature of coal, coal dust can be created during transportation, or by mechanically handling coal. Coal dust, categorized at silt-clay particle size, of particular concern due to heavy metals (lead, mercury, nickel, tin, cadmium, mercury, antimony, arsenic, isotopes of thorium and strontium) which are toxic also at low concentrations. This hazard exposes risk on both environment and public health. It has been identified by medical scientist around the world as causing a range of diseases and health problems, mainly heart and respiratory diseases like asthma and lung cancer. It is due to the fact that the fine invisible coal dust particles (less than 2.5 microns) long lodge in the lungs and are not naturally expelled, so long-term exposure increases the risk of health problems. Numerus studies reported that data to conduct study of geographic distribution of the very fine coal dust (smaller than PM 2.5) and related health impacts from coal exports, is not being collected. Sediment dust load in an indoor environment can be spectrally assessed using reflectance spectroscopy (Chudnovsky and Ben-Dor, 2009). Small amounts of particulate pollution that may carry a signature of a forthcoming environmental hazard are of key interest when considering the effects of pollution. According to the most basic distribution dynamics, dust consists of suspended particulate matter in a fine state of subdivision that are raised and carried by wind. In this context, it is increasingly important to first, understand the distribution dynamics of pollutants, and subsequently develop dedicated tools and measures to control and monitor pollutants in the free environment. The earliest effect of settled polluted dust particles is not always reflected through poor conditions of vegetation or soils, or any visible damages. In most of the cases, it has a quite long accumulation process that graduates from a polluted condition to long-term environmental and health related hazard. Although conducted experiments with pollutant analog powders under controlled conditions have tended to con- firm the findings from field studies (Brook, 2014; Brook and Ben-Dor 2016; Brook, 2016), a major criticism of all these experiments is their short duration. The resulting conclusion is that it is difficult, if not impossible, to determine the implications of long-term exposure to realistic concentrations of pollutants from such short-term studies. In general, the task of unmixing is to decompose the reflectance spectrum into a set of endmembers or principal combined spectra and their corresponding abundances (Bioucas-Dias et al., 2012). This study suggests that the sensitivity of sparse unmixing techniques provides an ideal approach to extract and identify coal dust settled over/upon green vegetation canopy using in situ spectral data collected by portable spectrometer. The optimal NMF algorithms, such as ALS and LPG, are assumed to be the simplest methods that achieve the minimum error. The suggested practical approach includes the following stages: 1. In situ spectral measurements, 2. Near-real-time spectral data analysis, 3. Estimated concentration of coal dust reported as mg/sq m. The stage 2 is completed by calculating: 1. Unmixing between the green canopy and the settle dust extraction only coal dust fraction, 2. Converting spectral feature of coal dust to concentration via PLSR spectral model. The spectral model was trained and validated PLSR model developed at laboratory using spectra across MIR (FTIR reflectance spectra) and NIR regions and XRD analysis. The obtained RMSE was satisfying for both spectral regions. Thus, it was concluded that field spectroscopy can be used for this purpose, and it can provide fully quantitative measures of settle coal dust. Nowadays this approach (both spectrometer and algorithm) has been accepted as a practical operational tool for environmental monitoring near power station Orot Rabin in Hadera and will be used by the Sharon-Carmel Districts Municipal Association for Environmental Protection, Israel as a regulatory tool. In summary, this work shows that coal dust can be assessed using in situ spectroscopy, making it a potentially powerful tool for environmental studies. References Chudnovsky, A., & Ben-Dor, E. (2009). Reflectance spectroscopy as a tool for settled dust monitoring in office environment. International Journal of Environment and Waste Management, 4(1), 32-49. Brook, A. (2014). Quantitative Detection of Settled dust over Green Canopy using Sparse Unmixing of Airborne Hyperspectral Data. IEEE-Whispers 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2014, Switzerland, 4-8. Brook, A. and Ben-Dor, E. (2016). Quantitative detection of settled dust over Green Canopy using sparse unmixing of airborne hyperspectral data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(2), pp.884-897. Brook, A. (2016). Quantitative Detection and Long-Term Monitoring of Settle Dust Using Semisupervised Learning for Spectral Data. Water, Air, & Soil Pollution, 227(3), pp.1-9. Bioucas-Dias, J.M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P. and Chanussot, J. (2012). Hyperspectral unmixing overview: Geometrical, statistical, and sparse regression-based approaches. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2), pp.354-379. Keshava, N., Mustard, J. (2002). Spectral unmixing. IEEE Signal Process. Mag., 19(1), 44-57. Bioucas-Dias et al. (2012). Hyperspectral unmixing overview: Geometrical, statistical, and sparse regression-based approaches, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2), 354 -379.

Supervised versus unsupervised categorization: two sides of the same coin?

PubMed

Pothos, Emmanuel M; Edwards, Darren J; Perlman, Amotz

2011-09-01

Supervised and unsupervised categorization have been studied in separate research traditions. A handful of studies have attempted to explore a possible convergence between the two. The present research builds on these studies, by comparing the unsupervised categorization results of Pothos et al. ( 2011 ; Pothos et al., 2008 ) with the results from two procedures of supervised categorization. In two experiments, we tested 375 participants with nine different stimulus sets and examined the relation between ease of learning of a classification, memory for a classification, and spontaneous preference for a classification. After taking into account the role of the number of category labels (clusters) in supervised learning, we found the three variables to be closely associated with each other. Our results provide encouragement for researchers seeking unified theoretical explanations for supervised and unsupervised categorization, but raise a range of challenging theoretical questions.

A new local-global approach for classification.

PubMed

Peres, R T; Pedreira, C E

2010-09-01

In this paper, we propose a new local-global pattern classification scheme that combines supervised and unsupervised approaches, taking advantage of both, local and global environments. We understand as global methods the ones concerned with the aim of constructing a model for the whole problem space using the totality of the available observations. Local methods focus into sub regions of the space, possibly using an appropriately selected subset of the sample. In the proposed method, the sample is first divided in local cells by using a Vector Quantization unsupervised algorithm, the LBG (Linde-Buzo-Gray). In a second stage, the generated assemblage of much easier problems is locally solved with a scheme inspired by Bayes' rule. Four classification methods were implemented for comparison purposes with the proposed scheme: Learning Vector Quantization (LVQ); Feedforward Neural Networks; Support Vector Machine (SVM) and k-Nearest Neighbors. These four methods and the proposed scheme were implemented in eleven datasets, two controlled experiments, plus nine public available datasets from the UCI repository. The proposed method has shown a quite competitive performance when compared to these classical and largely used classifiers. Our method is simple concerning understanding and implementation and is based on very intuitive concepts. Copyright 2010 Elsevier Ltd. All rights reserved.

Unsupervised learning of structure in spectroscopic cubes

NASA Astrophysics Data System (ADS)

Araya, M.; Mendoza, M.; Solar, M.; Mardones, D.; Bayo, A.

2018-07-01

We consider the problem of analyzing the structure of spectroscopic cubes using unsupervised machine learning techniques. We propose representing the target's signal as a homogeneous set of volumes through an iterative algorithm that separates the structured emission from the background while not overestimating the flux. Besides verifying some basic theoretical properties, the algorithm is designed to be tuned by domain experts, because its parameters have meaningful values in the astronomical context. Nevertheless, we propose a heuristic to automatically estimate the signal-to-noise ratio parameter of the algorithm directly from data. The resulting light-weighted set of samples (≤ 1% compared to the original data) offer several advantages. For instance, it is statistically correct and computationally inexpensive to apply well-established techniques of the pattern recognition and machine learning domains; such as clustering and dimensionality reduction algorithms. We use ALMA science verification data to validate our method, and present examples of the operations that can be performed by using the proposed representation. Even though this approach is focused on providing faster and better analysis tools for the end-user astronomer, it also opens the possibility of content-aware data discovery by applying our algorithm to big data.

Classification of damage in structural systems using time series analysis and supervised and unsupervised pattern recognition techniques

NASA Astrophysics Data System (ADS)

Omenzetter, Piotr; de Lautour, Oliver R.

2010-04-01

Developed for studying long, periodic records of various measured quantities, time series analysis methods are inherently suited and offer interesting possibilities for Structural Health Monitoring (SHM) applications. However, their use in SHM can still be regarded as an emerging application and deserves more studies. In this research, Autoregressive (AR) models were used to fit experimental acceleration time histories from two experimental structural systems, a 3- storey bookshelf-type laboratory structure and the ASCE Phase II SHM Benchmark Structure, in healthy and several damaged states. The coefficients of the AR models were chosen as damage sensitive features. Preliminary visual inspection of the large, multidimensional sets of AR coefficients to check the presence of clusters corresponding to different damage severities was achieved using Sammon mapping - an efficient nonlinear data compression technique. Systematic classification of damage into states based on the analysis of the AR coefficients was achieved using two supervised classification techniques: Nearest Neighbor Classification (NNC) and Learning Vector Quantization (LVQ), and one unsupervised technique: Self-organizing Maps (SOM). This paper discusses the performance of AR coefficients as damage sensitive features and compares the efficiency of the three classification techniques using experimental data.

Mastication Evaluation With Unsupervised Learning: Using an Inertial Sensor-Based System.

PubMed

Lucena, Caroline Vieira; Lacerda, Marcelo; Caldas, Rafael; De Lima Neto, Fernando Buarque; Rativa, Diego

2018-01-01

There is a direct relationship between the prevalence of musculoskeletal disorders of the temporomandibular joint and orofacial disorders. A well-elaborated analysis of the jaw movements provides relevant information for healthcare professionals to conclude their diagnosis. Different approaches have been explored to track jaw movements such that the mastication analysis is getting less subjective; however, all methods are still highly subjective, and the quality of the assessments depends much on the experience of the health professional. In this paper, an accurate and non-invasive method based on a commercial low-cost inertial sensor (MPU6050) to measure jaw movements is proposed. The jaw-movement feature values are compared to the obtained with clinical analysis, showing no statistically significant difference between both methods. Moreover, We propose to use unsupervised paradigm approaches to cluster mastication patterns of healthy subjects and simulated patients with facial trauma. Two techniques were used in this paper to instantiate the method: Kohonen's Self-Organizing Maps and K-Means Clustering. Both algorithms have excellent performances to process jaw-movements data, showing encouraging results and potential to bring a full assessment of the masticatory function. The proposed method can be applied in real-time providing relevant dynamic information for health-care professionals.

Unsupervised Learning and Pattern Recognition of Biological Data Structures with Density Functional Theory and Machine Learning.

PubMed

Chen, Chien-Chang; Juan, Hung-Hui; Tsai, Meng-Yuan; Lu, Henry Horng-Shing

2018-01-11

By introducing the methods of machine learning into the density functional theory, we made a detour for the construction of the most probable density function, which can be estimated by learning relevant features from the system of interest. Using the properties of universal functional, the vital core of density functional theory, the most probable cluster numbers and the corresponding cluster boundaries in a studying system can be simultaneously and automatically determined and the plausibility is erected on the Hohenberg-Kohn theorems. For the method validation and pragmatic applications, interdisciplinary problems from physical to biological systems were enumerated. The amalgamation of uncharged atomic clusters validated the unsupervised searching process of the cluster numbers and the corresponding cluster boundaries were exhibited likewise. High accurate clustering results of the Fisher's iris dataset showed the feasibility and the flexibility of the proposed scheme. Brain tumor detections from low-dimensional magnetic resonance imaging datasets and segmentations of high-dimensional neural network imageries in the Brainbow system were also used to inspect the method practicality. The experimental results exhibit the successful connection between the physical theory and the machine learning methods and will benefit the clinical diagnoses.

Supervised and Unsupervised Learning Technology in the Study of Rodent Behavior

PubMed Central

Gris, Katsiaryna V.; Coutu, Jean-Philippe; Gris, Denis

2017-01-01

Quantifying behavior is a challenge for scientists studying neuroscience, ethology, psychology, pathology, etc. Until now, behavior was mostly considered as qualitative descriptions of postures or labor intensive counting of bouts of individual movements. Many prominent behavioral scientists conducted studies describing postures of mice and rats, depicting step by step eating, grooming, courting, and other behaviors. Automated video assessment technologies permit scientists to quantify daily behavioral patterns/routines, social interactions, and postural changes in an unbiased manner. Here, we extensively reviewed published research on the topic of the structural blocks of behavior and proposed a structure of behavior based on the latest publications. We discuss the importance of defining a clear structure of behavior to allow professionals to write viable algorithms. We presented a discussion of technologies that are used in automated video assessment of behavior in mice and rats. We considered advantages and limitations of supervised and unsupervised learning. We presented the latest scientific discoveries that were made using automated video assessment. In conclusion, we proposed that the automated quantitative approach to evaluating animal behavior is the future of understanding the effect of brain signaling, pathologies, genetic content, and environment on behavior. PMID:28804452

Unsupervised automated high throughput phenotyping of RNAi time-lapse movies.

PubMed

Failmezger, Henrik; Fröhlich, Holger; Tresch, Achim

2013-10-04

Gene perturbation experiments in combination with fluorescence time-lapse cell imaging are a powerful tool in reverse genetics. High content applications require tools for the automated processing of the large amounts of data. These tools include in general several image processing steps, the extraction of morphological descriptors, and the grouping of cells into phenotype classes according to their descriptors. This phenotyping can be applied in a supervised or an unsupervised manner. Unsupervised methods are suitable for the discovery of formerly unknown phenotypes, which are expected to occur in high-throughput RNAi time-lapse screens. We developed an unsupervised phenotyping approach based on Hidden Markov Models (HMMs) with multivariate Gaussian emissions for the detection of knockdown-specific phenotypes in RNAi time-lapse movies. The automated detection of abnormal cell morphologies allows us to assign a phenotypic fingerprint to each gene knockdown. By applying our method to the Mitocheck database, we show that a phenotypic fingerprint is indicative of a gene's function. Our fully unsupervised HMM-based phenotyping is able to automatically identify cell morphologies that are specific for a certain knockdown. Beyond the identification of genes whose knockdown affects cell morphology, phenotypic fingerprints can be used to find modules of functionally related genes.

An Efficient Optimization Method for Solving Unsupervised Data Classification Problems.

PubMed

Shabanzadeh, Parvaneh; Yusof, Rubiyah

2015-01-01

Unsupervised data classification (or clustering) analysis is one of the most useful tools and a descriptive task in data mining that seeks to classify homogeneous groups of objects based on similarity and is used in many medical disciplines and various applications. In general, there is no single algorithm that is suitable for all types of data, conditions, and applications. Each algorithm has its own advantages, limitations, and deficiencies. Hence, research for novel and effective approaches for unsupervised data classification is still active. In this paper a heuristic algorithm, Biogeography-Based Optimization (BBO) algorithm, was adapted for data clustering problems by modifying the main operators of BBO algorithm, which is inspired from the natural biogeography distribution of different species. Similar to other population-based algorithms, BBO algorithm starts with an initial population of candidate solutions to an optimization problem and an objective function that is calculated for them. To evaluate the performance of the proposed algorithm assessment was carried on six medical and real life datasets and was compared with eight well known and recent unsupervised data classification algorithms. Numerical results demonstrate that the proposed evolutionary optimization algorithm is efficient for unsupervised data classification.

Computer-based tools for assessing micro-longitudinal patterns of cognitive function in older adults.

PubMed

Brown, Laura J E; Adlam, Tim; Hwang, Faustina; Khadra, Hassan; Maclean, Linda M; Rudd, Bridey; Smith, Tom; Timon, Claire; Williams, Elizabeth A; Astell, Arlene J

2016-08-01

Patterns of cognitive change over micro-longitudinal timescales (i.e., ranging from hours to days) are associated with a wide range of age-related health and functional outcomes. However, practical issues of conducting high-frequency assessments make investigations of micro-longitudinal cognition costly and burdensome to run. One way of addressing this is to develop cognitive assessments that can be performed by older adults, in their own homes, without a researcher being present. Here, we address the question of whether reliable and valid cognitive data can be collected over micro-longitudinal timescales using unsupervised cognitive tests.In study 1, 48 older adults completed two touchscreen cognitive tests, on three occasions, in controlled conditions, alongside a battery of standard tests of cognitive functions. In study 2, 40 older adults completed the same two computerized tasks on multiple occasions, over three separate week-long periods, in their own homes, without a researcher present. Here, the tasks were incorporated into a wider touchscreen system (Novel Assessment of Nutrition and Ageing (NANA)) developed to assess multiple domains of health and behavior. Standard tests of cognitive function were also administered prior to participants using the NANA system.Performance on the two "NANA" cognitive tasks showed convergent validity with, and similar levels of reliability to, the standard cognitive battery in both studies. Completion and accuracy rates were also very high. These results show that reliable and valid cognitive data can be collected from older adults using unsupervised computerized tests, thus affording new opportunities for the investigation of cognitive.

Unsupervised classification of cirrhotic livers using MRI data

NASA Astrophysics Data System (ADS)

Lee, Gobert; Kanematsu, Masayuki; Kato, Hiroki; Kondo, Hiroshi; Zhou, Xiangrong; Hara, Takeshi; Fujita, Hiroshi; Hoshi, Hiroaki

2008-03-01

Cirrhosis of the liver is a chronic disease. It is characterized by the presence of widespread nodules and fibrosis in the liver which results in characteristic texture patterns. Computerized analysis of hepatic texture patterns is usually based on regions-of-interest (ROIs). However, not all ROIs are typical representatives of the disease stage of the liver from which the ROIs originated. This leads to uncertainties in the ROI labels (diseased or non-diseased). On the other hand, supervised classifiers are commonly used in determining the assignment rule. This presents a problem as the training of a supervised classifier requires the correct labels of the ROIs. The main purpose of this paper is to investigate the use of an unsupervised classifier, the k-means clustering, in classifying ROI based data. In addition, a procedure for generating a receiver operating characteristic (ROC) curve depicting the classification performance of k-means clustering is also reported. Hepatic MRI images of 44 patients (16 cirrhotic; 28 non-cirrhotic) are used in this study. The MRI data are derived from gadolinium-enhanced equilibrium phase images. For each patient, 10 ROIs selected by an experienced radiologist and 7 texture features measured on each ROI are included in the MRI data. Results of the k-means classifier are depicted using an ROC curve. The area under the curve (AUC) has a value of 0.704. This is slightly lower than but comparable to that of LDA and ANN classifiers which have values 0.781 and 0.801, respectively. Methods in constructing ROC curve in relation to k-means clustering have not been previously reported in the literature.

Unsupervised learning of digit recognition using spike-timing-dependent plasticity

PubMed Central

Diehl, Peter U.; Cook, Matthew

2015-01-01

In order to understand how the mammalian neocortex is performing computations, two things are necessary; we need to have a good understanding of the available neuronal processing units and mechanisms, and we need to gain a better understanding of how those mechanisms are combined to build functioning systems. Therefore, in recent years there is an increasing interest in how spiking neural networks (SNN) can be used to perform complex computations or solve pattern recognition tasks. However, it remains a challenging task to design SNNs which use biologically plausible mechanisms (especially for learning new patterns), since most such SNN architectures rely on training in a rate-based network and subsequent conversion to a SNN. We present a SNN for digit recognition which is based on mechanisms with increased biological plausibility, i.e., conductance-based instead of current-based synapses, spike-timing-dependent plasticity with time-dependent weight change, lateral inhibition, and an adaptive spiking threshold. Unlike most other systems, we do not use a teaching signal and do not present any class labels to the network. Using this unsupervised learning scheme, our architecture achieves 95% accuracy on the MNIST benchmark, which is better than previous SNN implementations without supervision. The fact that we used no domain-specific knowledge points toward the general applicability of our network design. Also, the performance of our network scales well with the number of neurons used and shows similar performance for four different learning rules, indicating robustness of the full combination of mechanisms, which suggests applicability in heterogeneous biological neural networks. PMID:26941637

Self-supervised ARTMAP.

PubMed

Amis, Gregory P; Carpenter, Gail A

2010-03-01

Computational models of learning typically train on labeled input patterns (supervised learning), unlabeled input patterns (unsupervised learning), or a combination of the two (semi-supervised learning). In each case input patterns have a fixed number of features throughout training and testing. Human and machine learning contexts present additional opportunities for expanding incomplete knowledge from formal training, via self-directed learning that incorporates features not previously experienced. This article defines a new self-supervised learning paradigm to address these richer learning contexts, introducing a neural network called self-supervised ARTMAP. Self-supervised learning integrates knowledge from a teacher (labeled patterns with some features), knowledge from the environment (unlabeled patterns with more features), and knowledge from internal model activation (self-labeled patterns). Self-supervised ARTMAP learns about novel features from unlabeled patterns without destroying partial knowledge previously acquired from labeled patterns. A category selection function bases system predictions on known features, and distributed network activation scales unlabeled learning to prediction confidence. Slow distributed learning on unlabeled patterns focuses on novel features and confident predictions, defining classification boundaries that were ambiguous in the labeled patterns. Self-supervised ARTMAP improves test accuracy on illustrative low-dimensional problems and on high-dimensional benchmarks. Model code and benchmark data are available from: http://techlab.eu.edu/SSART/. Copyright 2009 Elsevier Ltd. All rights reserved.

Unsupervised chunking based on graph propagation from bilingual corpus.

PubMed

Zhu, Ling; Wong, Derek F; Chao, Lidia S

2014-01-01

This paper presents a novel approach for unsupervised shallow parsing model trained on the unannotated Chinese text of parallel Chinese-English corpus. In this approach, no information of the Chinese side is applied. The exploitation of graph-based label propagation for bilingual knowledge transfer, along with an application of using the projected labels as features in unsupervised model, contributes to a better performance. The experimental comparisons with the state-of-the-art algorithms show that the proposed approach is able to achieve impressive higher accuracy in terms of F-score.

An unsupervised classification technique for multispectral remote sensing data.

NASA Technical Reports Server (NTRS)

Su, M. Y.; Cummings, R. E.

1973-01-01

Description of a two-part clustering technique consisting of (a) a sequential statistical clustering, which is essentially a sequential variance analysis, and (b) a generalized K-means clustering. In this composite clustering technique, the output of (a) is a set of initial clusters which are input to (b) for further improvement by an iterative scheme. This unsupervised composite technique was employed for automatic classification of two sets of remote multispectral earth resource observations. The classification accuracy by the unsupervised technique is found to be comparable to that by traditional supervised maximum-likelihood classification techniques.

Unsupervised classification of earth resources data.

NASA Technical Reports Server (NTRS)

Su, M. Y.; Jayroe, R. R., Jr.; Cummings, R. E.

1972-01-01

A new clustering technique is presented. It consists of two parts: (a) a sequential statistical clustering which is essentially a sequential variance analysis and (b) a generalized K-means clustering. In this composite clustering technique, the output of (a) is a set of initial clusters which are input to (b) for further improvement by an iterative scheme. This unsupervised composite technique was employed for automatic classification of two sets of remote multispectral earth resource observations. The classification accuracy by the unsupervised technique is found to be comparable to that by existing supervised maximum liklihood classification technique.

Scalar entrainment in the mixing layer

NASA Technical Reports Server (NTRS)

Sandham, N. D.; Mungal, M. G.; Broadwell, J. E.; Reynolds, W. C.

1988-01-01

New definitions of entrainment and mixing based on the passive scalar field in the plane mixing layer are proposed. The definitions distinguish clearly between three fluid states: (1) unmixed fluid, (2) fluid engulfed in the mixing layer, trapped between two scalar contours, and (3) mixed fluid. The difference betwen (2) and (3) is the amount of fluid which has been engulfed during the pairing process, but has not yet mixed. Trends are identified from direct numerical simulations and extensions to high Reynolds number mixing layers are made in terms of the Broadwell-Breidenthal mixing model. In the limit of high Peclet number (Pe = ReSc) it is speculated that engulfed fluid rises in steps associated with pairings, introducing unmixed fluid into the large scale structures, where it is eventually mixed at the Kolmogorov scale. From this viewpoint, pairing is a prerequisite for mixing in the turbulent plane mixing layer.

Compliance with 14-day primaquine therapy for radical cure of vivax malaria--a randomized placebo-controlled trial comparing unsupervised with supervised treatment.

PubMed

Leslie, Toby; Rab, Mohammad Abdur; Ahmadzai, Hayat; Durrani, Naeem; Fayaz, Mohammad; Kolaczinski, Jan; Rowland, Mark

2004-03-01

The only available treatment that can eliminate the latent hypnozoite reservoir of vivax malaria is a 14 d course of primaquine (PQ). A potential problem with long-course chemotherapy is the issue of compliance after clinical symptoms have subsided. The present study, carried out at an Afghan refugee camp in Pakistan, between June 2000 and August 2001, compared 14 d treatment in supervised and unsupervised groups in which compliance was monitored by comparison of relapse rates. Clinical cases recruited by passive case detection were randomised by family to placebo, supervised, or unsupervised groups, and treated with chloroquine (25 mg/kg) over 3 days to eliminate erythrocytic stages. Individuals with glucose-6-phosphate dehydrogenase (G6PD) deficiency were excluded from the trial. Cases allocated to supervision were given directly observed treatment (0.25 mg PQ/kg body weight) once per day for 14 days. Cases allocated to the unsupervised group were provided with 14 PQ doses upon enrollment and strongly advised to complete the course. A total of 595 cases were enrolled. After 9 months of follow up PQ proved equally protective against further episodes of P. vivax in supervised (odds ratio 0.35, 95% CI 0.21-0.57) and unsupervised (odds ratio 0.37, 95% CI 0.23-0.59) groups as compared to placebo. All age groups on supervised or unsupervised treatment showed a similar degree of protection even though the risk of relapse decreased with age. The study showed that a presumed problem of poor compliance may be overcome with simple health messages even when the majority of individuals are illiterate and without formal education. Unsupervised treatment with 14-day PQ when combined with simple instruction can avert a significant amount of the morbidity associated with relapse in populations where G6PD deficiency is either absent or readily diagnosable.

True Zero-Training Brain-Computer Interfacing – An Online Study

PubMed Central

Kindermans, Pieter-Jan; Schreuder, Martijn; Schrauwen, Benjamin; Müller, Klaus-Robert; Tangermann, Michael

2014-01-01

Despite several approaches to realize subject-to-subject transfer of pre-trained classifiers, the full performance of a Brain-Computer Interface (BCI) for a novel user can only be reached by presenting the BCI system with data from the novel user. In typical state-of-the-art BCI systems with a supervised classifier, the labeled data is collected during a calibration recording, in which the user is asked to perform a specific task. Based on the known labels of this recording, the BCI's classifier can learn to decode the individual's brain signals. Unfortunately, this calibration recording consumes valuable time. Furthermore, it is unproductive with respect to the final BCI application, e.g. text entry. Therefore, the calibration period must be reduced to a minimum, which is especially important for patients with a limited concentration ability. The main contribution of this manuscript is an online study on unsupervised learning in an auditory event-related potential (ERP) paradigm. Our results demonstrate that the calibration recording can be bypassed by utilizing an unsupervised trained classifier, that is initialized randomly and updated during usage. Initially, the unsupervised classifier tends to make decoding mistakes, as the classifier might not have seen enough data to build a reliable model. Using a constant re-analysis of the previously spelled symbols, these initially misspelled symbols can be rectified posthoc when the classifier has learned to decode the signals. We compare the spelling performance of our unsupervised approach and of the unsupervised posthoc approach to the standard supervised calibration-based dogma for n = 10 healthy users. To assess the learning behavior of our approach, it is unsupervised trained from scratch three times per user. Even with the relatively low SNR of an auditory ERP paradigm, the results show that after a limited number of trials (30 trials), the unsupervised approach performs comparably to a classic supervised model. PMID:25068464

A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain.

PubMed

Hall, L O; Bensaid, A M; Clarke, L P; Velthuizen, R P; Silbiger, M S; Bezdek, J C

1992-01-01

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms, and a supervised computational neural network. Initial clinical results are presented on normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. For a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed, with fuzz-c-means approaches being slightly preferred over feedforward cascade correlation results. Various facets of both approaches, such as supervised versus unsupervised learning, time complexity, and utility for the diagnostic process, are compared.

Six weeks of unsupervised Nintendo Wii Fit gaming is effective at improving balance in independent older adults.

PubMed

Nicholson, Vaughan Patrick; McKean, Mark; Lowe, John; Fawcett, Christine; Burkett, Brendan

2015-01-01

To determine the effectiveness of unsupervised Nintendo Wii Fit balance training in older adults. Forty-one older adults were recruited from local retirement villages and educational settings to participate in a six-week two-group repeated measures study. The Wii group (n = 19, 75 ± 6 years) undertook 30 min of unsupervised Wii balance gaming three times per week in their retirement village while the comparison group (n = 22, 74 ± 5 years) continued with their usual exercise program. Participants' balance abilities were assessed pre- and postintervention. The Wii Fit group demonstrated significant improvements (P < .05) in timed up-and-go, left single-leg balance, lateral reach (left and right), and gait speed compared with the comparison group. Reported levels of enjoyment following game play increased during the study. Six weeks of unsupervised Wii balance training is an effective modality for improving balance in independent older adults.

Assessing the Linguistic Productivity of Unsupervised Deep Neural Networks

DOE Office of Scientific and Technical Information (OSTI.GOV)

Phillips, Lawrence A.; Hodas, Nathan O.

Increasingly, cognitive scientists have demonstrated interest in applying tools from deep learning. One use for deep learning is in language acquisition where it is useful to know if a linguistic phenomenon can be learned through domain-general means. To assess whether unsupervised deep learning is appropriate, we first pose a smaller question: Can unsupervised neural networks apply linguistic rules productively, using them in novel situations. We draw from the literature on determiner/noun productivity by training an unsupervised, autoencoder network measuring its ability to combine nouns with determiners. Our simple autoencoder creates combinations it has not previously encountered, displaying a degree ofmore » overlap similar to actual children. While this preliminary work does not provide conclusive evidence for productivity, it warrants further investigation with more complex models. Further, this work helps lay the foundations for future collaboration between the deep learning and cognitive science communities.« less

Continental Spatio-Temporal Data Analysis with Linear Spectral Mixture Model Using FOSS

NASA Technical Reports Server (NTRS)

Kumar, Uttam; Nemani, Ramakrishna; Ganguly, Sangram; Milesi, Cristina; Raja, Kumar; Wang, Weile; Votava, Petr; Michaelis, Andrew

2015-01-01

This work demonstrates the development and implementation of a Fully Constrained Least Squares (FCLS) unmixing model developed in C++ programming language with OpenCV package and boost C++ libraries in the NASA Earth Exchange (NEX). Visualization of the results is supported by GRASS GIS and statistical analysis is carried in R in a Linux system environment. FCLS was first tested on computer simulated data with Gaussian noise of various signal-to-noise ratio, and Landsat data of an agricultural scenario and an urban environment using a set of global end members of substrate (soils, sediments, rocks, and non-photosynthetic vegetation), vegetation that includes green photosynthetic plants and dark objects which encompasses absorptive substrate materials, clear water, deep shadows, etc. For the agricultural scenario, a spectrally diverse collection of 11 scenes of Level 1 terrain corrected, cloud free Landsat-5 TM data of Fresno, California, USA were unmixed and the results were validated with the corresponding ground data. To study an urbanized landscape, a clear sky Landsat-5 TM data were unmixed and validated with coincident World View-2 abundance maps (of 2 m spatial resolution) for an area of San Francisco, California, USA. The results were evaluated using descriptive statistics, correlation coefficient, RMSE, probability of success, boxplot and bivariate distribution function. Finally, FCLS was used for sub-pixel land cover analysis of the monthly WELD (Wen-enabled Landsat data) repository from 2008 to 2011 of North America. The abundance maps in conjunction with DMSP-OLS nighttime lights data were used to extract the urban land cover features and analyze their spatial-temporal growth.

Probability of Unmixed Young Groundwater (defined using chlorofluorocarbon-11 concentrations and tritium activities) in the Eagle River Watershed Valley-Fill Aquifer, Eagle County, North-Central Colorado, 2006-2007

USGS Publications Warehouse

Rupert, Michael G.; Plummer, Niel

2009-01-01

This raster data set delineates the predicted probability of unmixed young groundwater (defined using chlorofluorocarbon-11 concentrations and tritium activities) in groundwater in the Eagle River watershed valley-fill aquifer, Eagle County, North-Central Colorado, 2006-2007. This data set was developed by a cooperative project between the U.S. Geological Survey, Eagle County, the Eagle River Water and Sanitation District, the Town of Eagle, the Town of Gypsum, and the Upper Eagle Regional Water Authority. This project was designed to evaluate potential land-development effects on groundwater and surface-water resources so that informed land-use and water management decisions can be made. This groundwater probability map and its associated probability maps were developed as follows: (1) A point data set of wells with groundwater quality and groundwater age data was overlaid with thematic layers of anthropogenic (related to human activities) and hydrogeologic data by using a geographic information system to assign each well values for depth to groundwater, distance to major streams and canals, distance to gypsum beds, precipitation, soils, and well depth. These data then were downloaded to a statistical software package for analysis by logistic regression. (2) Statistical models predicting the probability of elevated nitrate concentrations, the probability of unmixed young water (using chlorofluorocarbon-11 concentrations and tritium activities), and the probability of elevated volatile organic compound concentrations were developed using logistic regression techniques. (3) The statistical models were entered into a GIS and the probability map was constructed.

Quantifying the Components of Impervious Surfaces

USGS Publications Warehouse

Tilley, Janet S.; Slonecker, E. Terrence

2006-01-01

This study's objectives were to (1) determine the relative contribution of impervious surface individual components by collecting digital information from high-resolution imagery, 1-meter or better; and to (2) determine which of the more advanced techniques, such as spectral unmixing or the application of coefficients to land use or land cover data, was the most suitable method that could be used by State and local governments as well as Federal agencies to efficiently measure the imperviousness in any given watershed or area of interest. The components of impervious surfaces, combined from all the watersheds and time periods from objective one were the following: buildings 29.2-percent, roads 28.3-percent, parking lots 24.6-percent; with the remaining three totaling 14-percent - driveways, sidewalks, and other, where other were any other features that were not contained within the first five. Results from objective two were spectral unmixing techniques will ultimately be the most efficient method of determining imperviousness, but are not yet accurate enough as it is critical to achieve accuracy better than 10-percent of the truth, of which the method is not consistently accomplishing as observed in this study. Of the three techniques in coefficient application tested, land use coefficient application was not practical, while if the last two methods, coefficients applied to land cover data, were merged, their end results could be to within 5-percent or better, of the truth. Until the spectral unmixing technique has been further refined, land cover coefficients should be used, which offer quick results, but not current as they were developed for the 1992 National Land Characteristics Data.

[Orthogonal Vector Projection Algorithm for Spectral Unmixing].

PubMed

Song, Mei-ping; Xu, Xing-wei; Chang, Chein-I; An, Ju-bai; Yao, Li

2015-12-01

Spectrum unmixing is an important part of hyperspectral technologies, which is essential for material quantity analysis in hyperspectral imagery. Most linear unmixing algorithms require computations of matrix multiplication and matrix inversion or matrix determination. These are difficult for programming, especially hard for realization on hardware. At the same time, the computation costs of the algorithms increase significantly as the number of endmembers grows. Here, based on the traditional algorithm Orthogonal Subspace Projection, a new method called. Orthogonal Vector Projection is prompted using orthogonal principle. It simplifies this process by avoiding matrix multiplication and inversion. It firstly computes the final orthogonal vector via Gram-Schmidt process for each endmember spectrum. And then, these orthogonal vectors are used as projection vector for the pixel signature. The unconstrained abundance can be obtained directly by projecting the signature to the projection vectors, and computing the ratio of projected vector length and orthogonal vector length. Compared to the Orthogonal Subspace Projection and Least Squares Error algorithms, this method does not need matrix inversion, which is much computation costing and hard to implement on hardware. It just completes the orthogonalization process by repeated vector operations, easy for application on both parallel computation and hardware. The reasonability of the algorithm is proved by its relationship with Orthogonal Sub-space Projection and Least Squares Error algorithms. And its computational complexity is also compared with the other two algorithms', which is the lowest one. At last, the experimental results on synthetic image and real image are also provided, giving another evidence for effectiveness of the method.

Continental Spatio-temporal Data Analysis with Linear Spectral Mixture Model using FOSS

NASA Astrophysics Data System (ADS)

Kumar, U.; Nemani, R. R.; Ganguly, S.; Milesi, C.; Raja, K. S.; Wang, W.; Votava, P.; Michaelis, A.

2015-12-01

This work demonstrates the development and implementation of a Fully Constrained Least Squares (FCLS) unmixing model developed in C++ programming language with OpenCV package and boost C++ libraries in the NASA Earth Exchange (NEX). Visualization of the results is supported by GRASS GIS and statistical analysis is carried in R in a Linux system environment. FCLS was first tested on computer simulated data with Gaussian noise of various signal-to-noise ratio, and Landsat data of an agricultural scenario and an urban environment using a set of global endmembers of substrate (soils, sediments, rocks, and non-photosynthetic vegetation), vegetation that includes green photosynthetic plants and dark objects which encompasses absorptive substrate materials, clear water, deep shadows, etc. For the agricultural scenario, a spectrally diverse collection of 11 scenes of Level 1 terrain corrected, cloud free Landsat-5 TM data of Fresno, California, USA were unmixed and the results were validated with the corresponding ground data. To study an urbanized landscape, a clear sky Landsat-5 TM data were unmixed and validated with coincident World View-2 abundance maps (of 2 m spatial resolution) for an area of San Francisco, California, USA. The results were evaluated using descriptive statistics, correlation coefficient, RMSE, probability of success, boxplot and bivariate distribution function. Finally, FCLS was used for sub-pixel land cover analysis of the monthly WELD (Wen-enabled Landsat data) repository from 2008 to 2011 of North America. The abundance maps in conjunction with DMSP-OLS nighttime lights data were used to extract the urban land cover features and analyze their spatial-temporal growth.

Scaling dimensions in spectroscopy of soil and vegetation

NASA Astrophysics Data System (ADS)

Malenovský, Zbyněk; Bartholomeus, Harm M.; Acerbi-Junior, Fausto W.; Schopfer, Jürg T.; Painter, Thomas H.; Epema, Gerrit F.; Bregt, Arnold K.

2007-05-01

The paper revises and clarifies definitions of the term scale and scaling conversions for imaging spectroscopy of soil and vegetation. We demonstrate a new four-dimensional scale concept that includes not only spatial but also the spectral, directional and temporal components. Three scaling remote sensing techniques are reviewed: (1) radiative transfer, (2) spectral (un)mixing, and (3) data fusion. Relevant case studies are given in the context of their up- and/or down-scaling abilities over the soil/vegetation surfaces and a multi-source approach is proposed for their integration. Radiative transfer (RT) models are described to show their capacity for spatial, spectral up-scaling, and directional down-scaling within a heterogeneous environment. Spectral information and spectral derivatives, like vegetation indices (e.g. TCARI/OSAVI), can be scaled and even tested by their means. Radiative transfer of an experimental Norway spruce ( Picea abies (L.) Karst.) research plot in the Czech Republic was simulated by the Discrete Anisotropic Radiative Transfer (DART) model to prove relevance of the correct object optical properties scaled up to image data at two different spatial resolutions. Interconnection of the successive modelling levels in vegetation is shown. A future development in measurement and simulation of the leaf directional spectral properties is discussed. We describe linear and/or non-linear spectral mixing techniques and unmixing methods that demonstrate spatial down-scaling. Relevance of proper selection or acquisition of the spectral endmembers using spectral libraries, field measurements, and pure pixels of the hyperspectral image is highlighted. An extensive list of advanced unmixing techniques, a particular example of unmixing a reflective optics system imaging spectrometer (ROSIS) image from Spain, and examples of other mixture applications give insight into the present status of scaling capabilities. Simultaneous spatial and temporal down-scaling by means of a data fusion technique is described. A demonstrative example is given for the moderate resolution imaging spectroradiometer (MODIS) and LANDSAT Thematic Mapper (TM) data from Brazil. Corresponding spectral bands of both sensors were fused via a pyramidal wavelet transform in Fourier space. New spectral and temporal information of the resultant image can be used for thematic classification or qualitative mapping. All three described scaling techniques can be integrated as the relevant methodological steps within a complex multi-source approach. We present this concept of combining numerous optical remote sensing data and methods to generate inputs for ecosystem process models.

On the asymptotic improvement of supervised learning by utilizing additional unlabeled samples - Normal mixture density case

NASA Technical Reports Server (NTRS)

Shahshahani, Behzad M.; Landgrebe, David A.

1992-01-01

The effect of additional unlabeled samples in improving the supervised learning process is studied in this paper. Three learning processes. supervised, unsupervised, and combined supervised-unsupervised, are compared by studying the asymptotic behavior of the estimates obtained under each process. Upper and lower bounds on the asymptotic covariance matrices are derived. It is shown that under a normal mixture density assumption for the probability density function of the feature space, the combined supervised-unsupervised learning is always superior to the supervised learning in achieving better estimates. Experimental results are provided to verify the theoretical concepts.

Massively parallel unsupervised single-particle cryo-EM data clustering via statistical manifold learning

PubMed Central

Wu, Jiayi; Ma, Yong-Bei; Congdon, Charles; Brett, Bevin; Chen, Shuobing; Xu, Yaofang; Ouyang, Qi

2017-01-01

Structural heterogeneity in single-particle cryo-electron microscopy (cryo-EM) data represents a major challenge for high-resolution structure determination. Unsupervised classification may serve as the first step in the assessment of structural heterogeneity. However, traditional algorithms for unsupervised classification, such as K-means clustering and maximum likelihood optimization, may classify images into wrong classes with decreasing signal-to-noise-ratio (SNR) in the image data, yet demand increased computational costs. Overcoming these limitations requires further development of clustering algorithms for high-performance cryo-EM data processing. Here we introduce an unsupervised single-particle clustering algorithm derived from a statistical manifold learning framework called generative topographic mapping (GTM). We show that unsupervised GTM clustering improves classification accuracy by about 40% in the absence of input references for data with lower SNRs. Applications to several experimental datasets suggest that our algorithm can detect subtle structural differences among classes via a hierarchical clustering strategy. After code optimization over a high-performance computing (HPC) environment, our software implementation was able to generate thousands of reference-free class averages within hours in a massively parallel fashion, which allows a significant improvement on ab initio 3D reconstruction and assists in the computational purification of homogeneous datasets for high-resolution visualization. PMID:28786986

Massively parallel unsupervised single-particle cryo-EM data clustering via statistical manifold learning.

PubMed

Wu, Jiayi; Ma, Yong-Bei; Congdon, Charles; Brett, Bevin; Chen, Shuobing; Xu, Yaofang; Ouyang, Qi; Mao, Youdong

2017-01-01

Structural heterogeneity in single-particle cryo-electron microscopy (cryo-EM) data represents a major challenge for high-resolution structure determination. Unsupervised classification may serve as the first step in the assessment of structural heterogeneity. However, traditional algorithms for unsupervised classification, such as K-means clustering and maximum likelihood optimization, may classify images into wrong classes with decreasing signal-to-noise-ratio (SNR) in the image data, yet demand increased computational costs. Overcoming these limitations requires further development of clustering algorithms for high-performance cryo-EM data processing. Here we introduce an unsupervised single-particle clustering algorithm derived from a statistical manifold learning framework called generative topographic mapping (GTM). We show that unsupervised GTM clustering improves classification accuracy by about 40% in the absence of input references for data with lower SNRs. Applications to several experimental datasets suggest that our algorithm can detect subtle structural differences among classes via a hierarchical clustering strategy. After code optimization over a high-performance computing (HPC) environment, our software implementation was able to generate thousands of reference-free class averages within hours in a massively parallel fashion, which allows a significant improvement on ab initio 3D reconstruction and assists in the computational purification of homogeneous datasets for high-resolution visualization.

Nutrient Losses during Winter and Summer Storage of Separated and Unseparated Digested Cattle Slurry.

PubMed

Perazzolo, Francesca; Mattachini, Gabriele; Riva, Elisabetta; Provolo, Giorgio

2017-07-01

Management factors affect nutrient loss during animal manure slurry storage in different ways. We conducted a pilot-scale study to evaluate carbon (C) and nitrogen (N) losses from unseparated and digested dairy slurry during winter and summer storage. In addition to season, treatments included mechanical separation of digestate into liquid and solid fractions and bimonthly mixing. Chemical analyses were performed every 2 wk for the mixed materials and at the start and end of storage for unmixed materials. The parameters examined allowed us to estimate C and N losses and examine the factors that determine these losses as well as emission patterns. Gas measurements were done every 2 wk to determine the main forms in which gaseous losses occurred. To evaluate the effect of separation, measured losses and emissions of separated liquid and solid fractions were mathematically combined using the mass separation efficiency of the mechanical separator. Nutrient losses were mainly affected by climatic conditions. Losses of C (up to 23%) from unseparated, unmixed digestate and of N (38% from combined separated fractions and from unseparated digestate) were much greater in summer than in winter, when C and N losses were <7%. Mixing tended to significantly increase N losses ( < 0.1) only in winter. Mechanical separation resulted in lower GHG emissions from combined separated fractions than from unseparated digestate. Results indicate that to maximize the fertilizer value of digested slurry, dairy farmers must carefully choose management practices, especially in summer. For separated digestates, practices should focus on storage of the liquid fraction, the major contributor of C and N losses (up to 64 and 90% of total losses, respectively) in summer. Moreover, management practices should limit NH, the main form of N losses (up to 99.5%). Copyright © by the American Society of Agronomy, Crop Science Society of America, and Soil Science Society of America, Inc.

Using Land Surface Phenology to Detect Land Use Change in the Northern Great Plains

NASA Astrophysics Data System (ADS)

Nguyen, L. H.; Henebry, G. M.

2017-12-01

The Northern Great Plains of the US have been undergoing many types of land cover / land use change over the past two decades, including expansion of irrigation, conversion of grassland to cropland, biofuels production, urbanization, and fossil fuel mining. Much of the literature on these changes has relied on post-classification change detection based on a limited number of observations per year. Here we demonstrate an approach to characterize land dynamics through land surface phenology (LSP) by synergistic use of image time series at two scales. Our study areas include regions of interest (ROIs) across the Northern Great Plains located within Landsat path overlap zones to boost the number of valid observations (free of clouds or snow) each year. We first compute accumulated growing degree-days (AGDD) from MODIS 8-day composites of land surface temperature (MOD11A2 and MYD11A2). Using Landsat Collection 1 surface reflectance-derived vegetation indices (NDVI, EVI), we then fit at each pixel a downward convex quadratic model linking the vegetation index to each year's progression of AGDD. This quadratic equation exhibits linearity in a mathematical sense; thus, the fitted models can be linearly mixed and unmixed using a set of LSP endmembers (defined by the fitted parameter coefficients of the quadratic model) that represent "pure" land cover types with distinct seasonal patterns found within the region, such as winter wheat, spring wheat, maize, soybean, sunflower, hay/pasture/grassland, developed/built-up, among others. Information about land cover corresponding to each endmember are provided by the NLCD (National Land Cover Dataset) and CDL (Cropland Data Layer). We use linear unmixing to estimate the likely proportion of each LSP endmember within particular areas stratified by latitude. By tracking the proportions over the 2001-2011 period, we can quantify various types of land transitions in the Northern Great Plains.

SOURCE APPORTIONMENT RESULTS, UNCERTAINTIES, AND MODELING TOOLS

EPA Science Inventory

Advanced multivariate receptor modeling tools are available from the U.S. Environmental Protection Agency (EPA) that use only speciated sample data to identify and quantify sources of air pollution. EPA has developed both EPA Unmix and EPA Positive Matrix Factorization (PMF) and ...

46 CFR 164.006-5 - Procedure for approval.

Code of Federal Regulations, 2010 CFR

2010-10-01

... the deck covering. (2) The range of thicknesses in which it is proposed to lay the deck covering... (c). (2) Sufficient bulk material (unmixed) to lay a sample one inch thick on an area of 12″×27″. If...

Dyslexic Participants Show Intact Spontaneous Categorization Processes

ERIC Educational Resources Information Center

Nikolopoulos, Dimitris S.; Pothos, Emmanuel M.

2009-01-01

We examine the performance of dyslexic participants on an unsupervised categorization task against that of matched non-dyslexic control participants. Unsupervised categorization is a cognitive process critical for conceptual development. Existing research in dyslexia has emphasized perceptual tasks and supervised categorization tasks (for which…

Housing and sexual health among street-involved youth.

PubMed

Kumar, Maya M; Nisenbaum, Rosane; Barozzino, Tony; Sgro, Michael; Bonifacio, Herbert J; Maguire, Jonathon L

2015-10-01

Street-involved youth (SIY) carry a disproportionate burden of sexually transmitted diseases (STD). Studies among adults suggest that improving housing stability may be an effective primary prevention strategy for improving sexual health. Housing options available to SIY offer varying degrees of stability and adult supervision. This study investigated whether housing options offering more stability and adult supervision are associated with fewer STD and related risk behaviors among SIY. A cross-sectional study was performed using public health survey and laboratory data collected from Toronto SIY in 2010. Three exposure categories were defined a priori based on housing situation: (1) stable and supervised housing, (2) stable and unsupervised housing, and (3) unstable and unsupervised housing. Multivariate logistic regression was used to test the association between housing category and current or recent STD. Secondary analyses were performed using the following secondary outcomes: blood-borne infection, recent binge-drinking, and recent high-risk sexual behavior. The final analysis included 184 SIY. Of these, 28.8 % had a current or recent STD. Housing situation was stable and supervised for 12.5 %, stable and unsupervised for 46.2 %, and unstable and unsupervised for 41.3 %. Compared to stable and supervised housing, there was no significant association between current or recent STD among stable and unsupervised housing or unstable and unsupervised housing. There was no significant association between housing category and risk of blood-borne infection, binge-drinking, or high-risk sexual behavior. Although we did not demonstrate a significant association between stable and supervised housing and lower STD risk, our incorporation of both housing stability and adult supervision into a priori defined exposure groups may inform future studies of housing-related prevention strategies among SIY. Multi-modal interventions beyond housing alone may also be required to prevent sexual morbidity among these vulnerable youth.

Out-of-School Time and Adolescent Substance Use.

PubMed

Lee, Kenneth T H; Vandell, Deborah Lowe

2015-11-01

High levels of adolescent substance use are linked to lower academic achievement, reduced schooling, and delinquency. We assess four types of out-of-school time (OST) contexts--unsupervised time with peers, sports, organized activities, and paid employment--in relation to tobacco, alcohol, and marijuana use at the end of high school. Other research has examined these OST contexts in isolation, limiting efforts to disentangle potentially confounded relations. Longitudinal data from the National Institute of Child Health and Human Development Study of Early Child Care and Youth Development (N = 766) examined associations between different OST contexts during high school and substance use at the end of high school. Unsupervised time with peers increased the odds of tobacco, alcohol, and marijuana use, whereas sports increased the odds of alcohol use and decreased the odds of marijuana use. Paid employment increased the odds of tobacco and alcohol use. Unsupervised time with peers predicted increased amounts of tobacco, alcohol, and marijuana use, whereas sports predicted decreased amounts of tobacco and marijuana use and increased amounts of alcohol use at the end of high school. Although unsupervised time with peers, sports, and paid employment were differentially linked to the odds of substance use, only unsupervised time with peers and sports were significantly associated with the amounts of tobacco, alcohol, and marijuana use at the end of high school. These findings underscore the value of considering OST contexts in relation to strategies to promote adolescent health. Reducing unsupervised time with peers and increasing sports participation may have positive impacts on reducing substance use. Copyright © 2015 Society for Adolescent Health and Medicine. Published by Elsevier Inc. All rights reserved.

Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees.

PubMed

Hübner, David; Verhoeven, Thibault; Schmid, Konstantin; Müller, Klaus-Robert; Tangermann, Michael; Kindermans, Pieter-Jan

2017-01-01

Using traditional approaches, a brain-computer interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be reduced or eliminated e.g., by subject-to-subject transfer of a pre-trained classifier or unsupervised adaptive classification methods which learn from scratch and adapt over time. While such heuristics work well in practice, none of them can provide theoretical guarantees. Our objective is to modify an event-related potential (ERP) paradigm to work in unison with the machine learning decoder, and thus to achieve a reliable unsupervised calibrationless decoding with a guarantee to recover the true class means. We introduce learning from label proportions (LLP) to the BCI community as a new unsupervised, and easy-to-implement classification approach for ERP-based BCIs. The LLP estimates the mean target and non-target responses based on known proportions of these two classes in different groups of the data. We present a visual ERP speller to meet the requirements of LLP. For evaluation, we ran simulations on artificially created data sets and conducted an online BCI study with 13 subjects performing a copy-spelling task. Theoretical considerations show that LLP is guaranteed to minimize the loss function similar to a corresponding supervised classifier. LLP performed well in simulations and in the online application, where 84.5% of characters were spelled correctly on average without prior calibration. The continuously adapting LLP classifier is the first unsupervised decoder for ERP BCIs guaranteed to find the optimal decoder. This makes it an ideal solution to avoid tedious calibration sessions. Additionally, LLP works on complementary principles compared to existing unsupervised methods, opening the door for their further enhancement when combined with LLP.

Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees

PubMed Central

Verhoeven, Thibault; Schmid, Konstantin; Müller, Klaus-Robert; Tangermann, Michael; Kindermans, Pieter-Jan

2017-01-01

Objective Using traditional approaches, a brain-computer interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be reduced or eliminated e.g., by subject-to-subject transfer of a pre-trained classifier or unsupervised adaptive classification methods which learn from scratch and adapt over time. While such heuristics work well in practice, none of them can provide theoretical guarantees. Our objective is to modify an event-related potential (ERP) paradigm to work in unison with the machine learning decoder, and thus to achieve a reliable unsupervised calibrationless decoding with a guarantee to recover the true class means. Method We introduce learning from label proportions (LLP) to the BCI community as a new unsupervised, and easy-to-implement classification approach for ERP-based BCIs. The LLP estimates the mean target and non-target responses based on known proportions of these two classes in different groups of the data. We present a visual ERP speller to meet the requirements of LLP. For evaluation, we ran simulations on artificially created data sets and conducted an online BCI study with 13 subjects performing a copy-spelling task. Results Theoretical considerations show that LLP is guaranteed to minimize the loss function similar to a corresponding supervised classifier. LLP performed well in simulations and in the online application, where 84.5% of characters were spelled correctly on average without prior calibration. Significance The continuously adapting LLP classifier is the first unsupervised decoder for ERP BCIs guaranteed to find the optimal decoder. This makes it an ideal solution to avoid tedious calibration sessions. Additionally, LLP works on complementary principles compared to existing unsupervised methods, opening the door for their further enhancement when combined with LLP. PMID:28407016

Parental Monitoring, Negotiated Unsupervised Time, and Parental Trust: The Role of Perceived Parenting Practices in Adolescent Health Risk Behaviors

PubMed Central

BORAWSKI, ELAINE A.; IEVERS-LANDIS, CAROLYN E.; LOVEGREEN, LOREN D.; TRAPL, ERIKA S.

2010-01-01

Purpose To compare two different parenting practices (parental monitoring and negotiated unsupervised time) and perceived parental trust in the reporting of health risk behaviors among adolescents. Methods Data were derived from 692 adolescents in 9th and 10th grades (X̄ = 15.7 years) enrolled in health education classes in six urban high schools. Students completed a self-administered paper-based survey that assessed adolescents’ perceptions of the degree to which their parents monitor their whereabouts, are permitted to negotiate unsupervised time with their friends and trust them to make decisions. Using gender-specific multivariate logistic regression analyses, we examined the relative importance of parental monitoring, negotiated unsupervised time with peers, and parental trust in predicting reported sexual activity, sex-related protective actions (e.g., condom use, carrying protection) and substance use (alcohol, tobacco, and marijuana). Results For males and females, increased negotiated unsupervised time was strongly associated with increased risk behavior (e.g., sexual activity, alcohol and marijuana use) but also sex-related protective actions. In males, high parental monitoring was associated with less alcohol use and consistent condom use. Parental monitoring had no affect on female behavior. Perceived parental trust served as a protective factor against sexual activity, tobacco, and marijuana use in females, and alcohol use in males. Conclusions Although monitoring is an important practice for parents of older adolescents, managing their behavior through negotiation of unsupervised time may have mixed results leading to increased experimentation with sexuality and substances, but perhaps in a more responsible way. Trust established between an adolescent female and her parents continues to be a strong deterrent for risky behaviors but appears to have little effect on behaviors of adolescent males. PMID:12890596

Unsupervised Cryo-EM Data Clustering through Adaptively Constrained K-Means Algorithm

PubMed Central

Xu, Yaofang; Wu, Jiayi; Yin, Chang-Cheng; Mao, Youdong

2016-01-01

In single-particle cryo-electron microscopy (cryo-EM), K-means clustering algorithm is widely used in unsupervised 2D classification of projection images of biological macromolecules. 3D ab initio reconstruction requires accurate unsupervised classification in order to separate molecular projections of distinct orientations. Due to background noise in single-particle images and uncertainty of molecular orientations, traditional K-means clustering algorithm may classify images into wrong classes and produce classes with a large variation in membership. Overcoming these limitations requires further development on clustering algorithms for cryo-EM data analysis. We propose a novel unsupervised data clustering method building upon the traditional K-means algorithm. By introducing an adaptive constraint term in the objective function, our algorithm not only avoids a large variation in class sizes but also produces more accurate data clustering. Applications of this approach to both simulated and experimental cryo-EM data demonstrate that our algorithm is a significantly improved alterative to the traditional K-means algorithm in single-particle cryo-EM analysis. PMID:27959895

Unsupervised Cryo-EM Data Clustering through Adaptively Constrained K-Means Algorithm.

PubMed

Xu, Yaofang; Wu, Jiayi; Yin, Chang-Cheng; Mao, Youdong

2016-01-01

In single-particle cryo-electron microscopy (cryo-EM), K-means clustering algorithm is widely used in unsupervised 2D classification of projection images of biological macromolecules. 3D ab initio reconstruction requires accurate unsupervised classification in order to separate molecular projections of distinct orientations. Due to background noise in single-particle images and uncertainty of molecular orientations, traditional K-means clustering algorithm may classify images into wrong classes and produce classes with a large variation in membership. Overcoming these limitations requires further development on clustering algorithms for cryo-EM data analysis. We propose a novel unsupervised data clustering method building upon the traditional K-means algorithm. By introducing an adaptive constraint term in the objective function, our algorithm not only avoids a large variation in class sizes but also produces more accurate data clustering. Applications of this approach to both simulated and experimental cryo-EM data demonstrate that our algorithm is a significantly improved alterative to the traditional K-means algorithm in single-particle cryo-EM analysis.

User Activity Recognition in Smart Homes Using Pattern Clustering Applied to Temporal ANN Algorithm.

PubMed

Bourobou, Serge Thomas Mickala; Yoo, Younghwan

2015-05-21

This paper discusses the possibility of recognizing and predicting user activities in the IoT (Internet of Things) based smart environment. The activity recognition is usually done through two steps: activity pattern clustering and activity type decision. Although many related works have been suggested, they had some limited performance because they focused only on one part between the two steps. This paper tries to find the best combination of a pattern clustering method and an activity decision algorithm among various existing works. For the first step, in order to classify so varied and complex user activities, we use a relevant and efficient unsupervised learning method called the K-pattern clustering algorithm. In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen's temporal relations. The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms. Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home.

Nonparametric Hierarchical Bayesian Model for Functional Brain Parcellation

PubMed Central

Lashkari, Danial; Sridharan, Ramesh; Vul, Edward; Hsieh, Po-Jang; Kanwisher, Nancy; Golland, Polina

2011-01-01

We develop a method for unsupervised analysis of functional brain images that learns group-level patterns of functional response. Our algorithm is based on a generative model that comprises two main layers. At the lower level, we express the functional brain response to each stimulus as a binary activation variable. At the next level, we define a prior over the sets of activation variables in all subjects. We use a Hierarchical Dirichlet Process as the prior in order to simultaneously learn the patterns of response that are shared across the group, and to estimate the number of these patterns supported by data. Inference based on this model enables automatic discovery and characterization of salient and consistent patterns in functional signals. We apply our method to data from a study that explores the response of the visual cortex to a collection of images. The discovered profiles of activation correspond to selectivity to a number of image categories such as faces, bodies, and scenes. More generally, our results appear superior to the results of alternative data-driven methods in capturing the category structure in the space of stimuli. PMID:21841977

The neural network classification of false killer whale (Pseudorca crassidens) vocalizations.

PubMed

Murray, S O; Mercado, E; Roitblat, H L

1998-12-01

This study reports the use of unsupervised, self-organizing neural network to categorize the repertoire of false killer whale vocalizations. Self-organizing networks are capable of detecting patterns in their input and partitioning those patterns into categories without requiring that the number or types of categories be predefined. The inputs for the neural networks were two-dimensional characterization of false killer whale vocalization, where each vocalization was characterized by a sequence of short-time measurements of duty cycle and peak frequency. The first neural network used competitive learning, where units in a competitive layer distributed themselves to recognize frequently presented input vectors. This network resulted in classes representing typical patterns in the vocalizations. The second network was a Kohonen feature map which organized the outputs topologically, providing a graphical organization of pattern relationships. The networks performed well as measured by (1) the average correlation between the input vectors and the weight vectors for each category, and (2) the ability of the networks to classify novel vocalizations. The techniques used in this study could easily be applied to other species and facilitate the development of objective, comprehensive repertoire models.

Monitoring intracellular oxidative events using dynamic spectral unmixing microscopy

EPA Science Inventory

There is increasing interest in using live-cell imaging to monitor not just individual intracellular endpoints, but to investigate the interplay between multiple molecular events as they unfold in real time within the cell. A major impediment to simultaneous acquisition of multip...

Unsupervised iterative detection of land mines in highly cluttered environments.

PubMed

Batman, Sinan; Goutsias, John

2003-01-01

An unsupervised iterative scheme is proposed for land mine detection in heavily cluttered scenes. This scheme is based on iterating hybrid multispectral filters that consist of a decorrelating linear transform coupled with a nonlinear morphological detector. Detections extracted from the first pass are used to improve results in subsequent iterations. The procedure stops after a predetermined number of iterations. The proposed scheme addresses several weaknesses associated with previous adaptations of morphological approaches to land mine detection. Improvement in detection performance, robustness with respect to clutter inhomogeneities, a completely unsupervised operation, and computational efficiency are the main highlights of the method. Experimental results reveal excellent performance.

Bio-Inspired Microsystem for Robust Genetic Assay Recognition

PubMed Central

Lue, Jaw-Chyng; Fang, Wai-Chi

2008-01-01

A compact integrated system-on-chip (SoC) architecture solution for robust, real-time, and on-site genetic analysis has been proposed. This microsystem solution is noise-tolerable and suitable for analyzing the weak fluorescence patterns from a PCR prepared dual-labeled DNA microchip assay. In the architecture, a preceding VLSI differential logarithm microchip is designed for effectively computing the logarithm of the normalized input fluorescence signals. A posterior VLSI artificial neural network (ANN) processor chip is used for analyzing the processed signals from the differential logarithm stage. A single-channel logarithmic circuit was fabricated and characterized. A prototype ANN chip with unsupervised winner-take-all (WTA) function was designed, fabricated, and tested. An ANN learning algorithm using a novel sigmoid-logarithmic transfer function based on the supervised backpropagation (BP) algorithm is proposed for robustly recognizing low-intensity patterns. Our results show that the trained new ANN can recognize low-fluorescence patterns better than an ANN using the conventional sigmoid function. PMID:18566679

Social networking patterns/hazards among teenagers.

PubMed

Machold, C; Judge, G; Mavrinac, A; Elliott, J; Murphy, A M; Roche, E

2012-05-01

Social Networking Sites (SNSs) have grown substantially, posing new hazards to teenagers. This study aimed to determine general patterns of Internet usage among Irish teenagers aged 11-16 years, and to identify potential hazards, including; bullying, inappropriate contact, overuse, addiction and invasion of users' privacy. A cross-sectional study design was employed to survey students at three Irish secondary schools, with a sample of 474 completing a questionnaire. 202 (44%) (n = 460) accessed the Internet using a shared home computer. Two hours or less were spent online daily by 285(62%), of whom 450 (98%) were unsupervised. 306 (72%) (n = 425) reported frequent usage of SNSs, 403 (95%) of whom were Facebook users. 42 (10%) males and 51 (12%) females experienced bullying online, while 114 (27%) reported inappropriate contact from others. Concerning overuse and the risk of addiction, 140 (33%) felt they accessed SNSs too often. These patterns among Irish teenagers suggest that SNS usage poses significant dangers, which are going largely unaddressed.

A New Approach for Mining Order-Preserving Submatrices Based on All Common Subsequences.

PubMed

Xue, Yun; Liao, Zhengling; Li, Meihang; Luo, Jie; Kuang, Qiuhua; Hu, Xiaohui; Li, Tiechen

2015-01-01

Order-preserving submatrices (OPSMs) have been applied in many fields, such as DNA microarray data analysis, automatic recommendation systems, and target marketing systems, as an important unsupervised learning model. Unfortunately, most existing methods are heuristic algorithms which are unable to reveal OPSMs entirely in NP-complete problem. In particular, deep OPSMs, corresponding to long patterns with few supporting sequences, incur explosive computational costs and are completely pruned by most popular methods. In this paper, we propose an exact method to discover all OPSMs based on frequent sequential pattern mining. First, an existing algorithm was adjusted to disclose all common subsequence (ACS) between every two row sequences, and therefore all deep OPSMs will not be missed. Then, an improved data structure for prefix tree was used to store and traverse ACS, and Apriori principle was employed to efficiently mine the frequent sequential pattern. Finally, experiments were implemented on gene and synthetic datasets. Results demonstrated the effectiveness and efficiency of this method.

Gene expression profiles of breast biopsies from healthy women identify a group with claudin-low features.

PubMed

Haakensen, Vilde D; Lingjaerde, Ole Christian; Lüders, Torben; Riis, Margit; Prat, Aleix; Troester, Melissa A; Holmen, Marit M; Frantzen, Jan Ole; Romundstad, Linda; Navjord, Dina; Bukholm, Ida K; Johannesen, Tom B; Perou, Charles M; Ursin, Giske; Kristensen, Vessela N; Børresen-Dale, Anne-Lise; Helland, Aslaug

2011-11-01

Increased understanding of the variability in normal breast biology will enable us to identify mechanisms of breast cancer initiation and the origin of different subtypes, and to better predict breast cancer risk. Gene expression patterns in breast biopsies from 79 healthy women referred to breast diagnostic centers in Norway were explored by unsupervised hierarchical clustering and supervised analyses, such as gene set enrichment analysis and gene ontology analysis and comparison with previously published genelists and independent datasets. Unsupervised hierarchical clustering identified two separate clusters of normal breast tissue based on gene-expression profiling, regardless of clustering algorithm and gene filtering used. Comparison of the expression profile of the two clusters with several published gene lists describing breast cells revealed that the samples in cluster 1 share characteristics with stromal cells and stem cells, and to a certain degree with mesenchymal cells and myoepithelial cells. The samples in cluster 1 also share many features with the newly identified claudin-low breast cancer intrinsic subtype, which also shows characteristics of stromal and stem cells. More women belonging to cluster 1 have a family history of breast cancer and there is a slight overrepresentation of nulliparous women in cluster 1. Similar findings were seen in a separate dataset consisting of histologically normal tissue from both breasts harboring breast cancer and from mammoplasty reductions. This is the first study to explore the variability of gene expression patterns in whole biopsies from normal breasts and identified distinct subtypes of normal breast tissue. Further studies are needed to determine the specific cell contribution to the variation in the biology of normal breasts, how the clusters identified relate to breast cancer risk and their possible link to the origin of the different molecular subtypes of breast cancer.

Hierarchical clustering of HPV genotype patterns in the ASCUS-LSIL triage study

PubMed Central

Wentzensen, Nicolas; Wilson, Lauren E.; Wheeler, Cosette M.; Carreon, Joseph D.; Gravitt, Patti E.; Schiffman, Mark; Castle, Philip E.

2010-01-01

Anogenital cancers are associated with about 13 carcinogenic HPV types in a broader group that cause cervical intraepithelial neoplasia (CIN). Multiple concurrent cervical HPV infections are common which complicate the attribution of HPV types to different grades of CIN. Here we report the analysis of HPV genotype patterns in the ASCUS-LSIL triage study using unsupervised hierarchical clustering. Women who underwent colposcopy at baseline (n = 2780) were grouped into 20 disease categories based on histology and cytology. Disease groups and HPV genotypes were clustered using complete linkage. Risk of 2-year cumulative CIN3+, viral load, colposcopic impression, and age were compared between disease groups and major clusters. Hierarchical clustering yielded four major disease clusters: Cluster 1 included all CIN3 histology with abnormal cytology; Cluster 2 included CIN3 histology with normal cytology and combinations with either CIN2 or high-grade squamous intraepithelial lesion (HSIL) cytology; Cluster 3 included older women with normal or low grade histology/cytology and low viral load; Cluster 4 included younger women with low grade histology/cytology, multiple infections, and the highest viral load. Three major groups of HPV genotypes were identified: Group 1 included only HPV16; Group 2 included nine carcinogenic types plus non-carcinogenic HPV53 and HPV66; and Group 3 included non-carcinogenic types plus carcinogenic HPV33 and HPV45. Clustering results suggested that colposcopy missed a prevalent precancer in many women with no biopsy/normal histology and HSIL. This result was confirmed by an elevated 2-year risk of CIN3+ in these groups. Our novel approach to study multiple genotype infections in cervical disease using unsupervised hierarchical clustering can address complex genotype distributions on a population level. PMID:20959485

GibbsCluster: unsupervised clustering and alignment of peptide sequences.

PubMed

Andreatta, Massimo; Alvarez, Bruno; Nielsen, Morten

2017-07-03

Receptor interactions with short linear peptide fragments (ligands) are at the base of many biological signaling processes. Conserved and information-rich amino acid patterns, commonly called sequence motifs, shape and regulate these interactions. Because of the properties of a receptor-ligand system or of the assay used to interrogate it, experimental data often contain multiple sequence motifs. GibbsCluster is a powerful tool for unsupervised motif discovery because it can simultaneously cluster and align peptide data. The GibbsCluster 2.0 presented here is an improved version incorporating insertion and deletions accounting for variations in motif length in the peptide input. In basic terms, the program takes as input a set of peptide sequences and clusters them into meaningful groups. It returns the optimal number of clusters it identified, together with the sequence alignment and sequence motif characterizing each cluster. Several parameters are available to customize cluster analysis, including adjustable penalties for small clusters and overlapping groups and a trash cluster to remove outliers. As an example application, we used the server to deconvolute multiple specificities in large-scale peptidome data generated by mass spectrometry. The server is available at http://www.cbs.dtu.dk/services/GibbsCluster-2.0. © The Author(s) 2017. Published by Oxford University Press on behalf of Nucleic Acids Research.

Learning spatially coherent properties of the visual world in connectionist networks

NASA Astrophysics Data System (ADS)

Becker, Suzanna; Hinton, Geoffrey E.

1991-10-01

In the unsupervised learning paradigm, a network of neuron-like units is presented with an ensemble of input patterns from a structured environment, such as the visual world, and learns to represent the regularities in that input. The major goal in developing unsupervised learning algorithms is to find objective functions that characterize the quality of the network's representation without explicitly specifying the desired outputs of any of the units. The sort of objective functions considered cause a unit to become tuned to spatially coherent features of visual images (such as texture, depth, shading, and surface orientation), by learning to predict the outputs of other units which have spatially adjacent receptive fields. Simulations show that using an information-theoretic algorithm called IMAX, a network can be trained to represent depth by observing random dot stereograms of surfaces with continuously varying disparities. Once a layer of depth-tuned units has developed, subsequent layers are trained to perform surface interpolation of curved surfaces, by learning to predict the depth of one image region based on depth measurements in surrounding regions. An extension of the basic model allows a population of competing neurons to learn a distributed code for disparity, which naturally gives rise to a representation of discontinuities.

Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition

PubMed Central

Vajda, Szilárd; Rangoni, Yves; Cecotti, Hubert

2015-01-01

For training supervised classifiers to recognize different patterns, large data collections with accurate labels are necessary. In this paper, we propose a generic, semi-automatic labeling technique for large handwritten character collections. In order to speed up the creation of a large scale ground truth, the method combines unsupervised clustering and minimal expert knowledge. To exploit the potential discriminant complementarities across features, each character is projected into five different feature spaces. After clustering the images in each feature space, the human expert labels the cluster centers. Each data point inherits the label of its cluster’s center. A majority (or unanimity) vote decides the label of each character image. The amount of human involvement (labeling) is strictly controlled by the number of clusters – produced by the chosen clustering approach. To test the efficiency of the proposed approach, we have compared, and evaluated three state-of-the art clustering methods (k-means, self-organizing maps, and growing neural gas) on the MNIST digit data set, and a Lampung Indonesian character data set, respectively. Considering a k-nn classifier, we show that labeling manually only 1.3% (MNIST), and 3.2% (Lampung) of the training data, provides the same range of performance than a completely labeled data set would. PMID:25870463

Clustervision: Visual Supervision of Unsupervised Clustering.

PubMed

Kwon, Bum Chul; Eysenbach, Ben; Verma, Janu; Ng, Kenney; De Filippi, Christopher; Stewart, Walter F; Perer, Adam

2018-01-01

Clustering, the process of grouping together similar items into distinct partitions, is a common type of unsupervised machine learning that can be useful for summarizing and aggregating complex multi-dimensional data. However, data can be clustered in many ways, and there exist a large body of algorithms designed to reveal different patterns. While having access to a wide variety of algorithms is helpful, in practice, it is quite difficult for data scientists to choose and parameterize algorithms to get the clustering results relevant for their dataset and analytical tasks. To alleviate this problem, we built Clustervision, a visual analytics tool that helps ensure data scientists find the right clustering among the large amount of techniques and parameters available. Our system clusters data using a variety of clustering techniques and parameters and then ranks clustering results utilizing five quality metrics. In addition, users can guide the system to produce more relevant results by providing task-relevant constraints on the data. Our visual user interface allows users to find high quality clustering results, explore the clusters using several coordinated visualization techniques, and select the cluster result that best suits their task. We demonstrate this novel approach using a case study with a team of researchers in the medical domain and showcase that our system empowers users to choose an effective representation of their complex data.

Mastication Evaluation With Unsupervised Learning: Using an Inertial Sensor-Based System

PubMed Central

Lucena, Caroline Vieira; Lacerda, Marcelo; Caldas, Rafael; De Lima Neto, Fernando Buarque

2018-01-01

There is a direct relationship between the prevalence of musculoskeletal disorders of the temporomandibular joint and orofacial disorders. A well-elaborated analysis of the jaw movements provides relevant information for healthcare professionals to conclude their diagnosis. Different approaches have been explored to track jaw movements such that the mastication analysis is getting less subjective; however, all methods are still highly subjective, and the quality of the assessments depends much on the experience of the health professional. In this paper, an accurate and non-invasive method based on a commercial low-cost inertial sensor (MPU6050) to measure jaw movements is proposed. The jaw-movement feature values are compared to the obtained with clinical analysis, showing no statistically significant difference between both methods. Moreover, We propose to use unsupervised paradigm approaches to cluster mastication patterns of healthy subjects and simulated patients with facial trauma. Two techniques were used in this paper to instantiate the method: Kohonen’s Self-Organizing Maps and K-Means Clustering. Both algorithms have excellent performances to process jaw-movements data, showing encouraging results and potential to bring a full assessment of the masticatory function. The proposed method can be applied in real-time providing relevant dynamic information for health-care professionals. PMID:29651365

Vibration control of building structures using self-organizing and self-learning neural networks

NASA Astrophysics Data System (ADS)

Madan, Alok

2005-11-01

Past research in artificial intelligence establishes that artificial neural networks (ANN) are effective and efficient computational processors for performing a variety of tasks including pattern recognition, classification, associative recall, combinatorial problem solving, adaptive control, multi-sensor data fusion, noise filtering and data compression, modelling and forecasting. The paper presents a potentially feasible approach for training ANN in active control of earthquake-induced vibrations in building structures without the aid of teacher signals (i.e. target control forces). A counter-propagation neural network is trained to output the control forces that are required to reduce the structural vibrations in the absence of any feedback on the correctness of the output control forces (i.e. without any information on the errors in output activations of the network). The present study shows that, in principle, the counter-propagation network (CPN) can learn from the control environment to compute the required control forces without the supervision of a teacher (unsupervised learning). Simulated case studies are presented to demonstrate the feasibility of implementing the unsupervised learning approach in ANN for effective vibration control of structures under the influence of earthquake ground motions. The proposed learning methodology obviates the need for developing a mathematical model of structural dynamics or training a separate neural network to emulate the structural response for implementation in practice.

Unsupervised discovery of microbial population structure within metagenomes using nucleotide base composition

PubMed Central

Saeed, Isaam; Tang, Sen-Lin; Halgamuge, Saman K.

2012-01-01

An approach to infer the unknown microbial population structure within a metagenome is to cluster nucleotide sequences based on common patterns in base composition, otherwise referred to as binning. When functional roles are assigned to the identified populations, a deeper understanding of microbial communities can be attained, more so than gene-centric approaches that explore overall functionality. In this study, we propose an unsupervised, model-based binning method with two clustering tiers, which uses a novel transformation of the oligonucleotide frequency-derived error gradient and GC content to generate coarse groups at the first tier of clustering; and tetranucleotide frequency to refine these groups at the secondary clustering tier. The proposed method has a demonstrated improvement over PhyloPythia, S-GSOM, TACOA and TaxSOM on all three benchmarks that were used for evaluation in this study. The proposed method is then applied to a pyrosequenced metagenomic library of mud volcano sediment sampled in southwestern Taiwan, with the inferred population structure validated against complementary sequencing of 16S ribosomal RNA marker genes. Finally, the proposed method was further validated against four publicly available metagenomes, including a highly complex Antarctic whale-fall bone sample, which was previously assumed to be too complex for binning prior to functional analysis. PMID:22180538

Unsupervised progressive elastic band exercises for frail geriatric inpatients objectively monitored by new exercise-integrated technology-a feasibility trial with an embedded qualitative study.

PubMed

Rathleff, C R; Bandholm, T; Spaich, E G; Jorgensen, M; Andreasen, J

2017-01-01

Frailty is a serious condition frequently present in geriatric inpatients that potentially causes serious adverse events. Strength training is acknowledged as a means of preventing or delaying frailty and loss of function in these patients. However, limited hospital resources challenge the amount of supervised training, and unsupervised training could possibly supplement supervised training thereby increasing the total exercise dose during admission. A new valid and reliable technology, the BandCizer, objectively measures the exact training dosage performed. The purpose was to investigate feasibility and acceptability of an unsupervised progressive strength training intervention monitored by BandCizer for frail geriatric inpatients. This feasibility trial included 15 frail inpatients at a geriatric ward. At hospitalization, the patients were prescribed two elastic band exercises to be performed unsupervised once daily. A BandCizer Datalogger enabling measurement of the number of sets, repetitions, and time-under-tension was attached to the elastic band. The patients were instructed in performing strength training: 3 sets of 10 repetitions (10-12 repetition maximum (RM)) with a separation of 2-min pauses and a time-under-tension of 8 s. The feasibility criterion for the unsupervised progressive exercises was that 33% of the recommended number of sets would be performed by at least 30% of patients. In addition, patients and staff were interviewed about their experiences with the intervention. Four (27%) out of 15 patients completed 33% of the recommended number of sets. For the total sample, the average percent of performed sets was 23% and for those who actually trained ( n  = 12) 26%. Patients and staff expressed a general positive attitude towards the unsupervised training as an addition to the supervised training sessions. However, barriers were also described-especially constant interruptions. Based on the predefined criterion for feasibility, the unsupervised training was not feasible, although the criterion was almost met. The patients and staff mainly expressed positive attitudes towards the unsupervised training. As even a small training dosage has been shown to improve the physical performance of geriatric inpatients, the proposed intervention might be relevant if the interruptions are decreased in future large-scale trials and if the adherence is increased. ClinicalTrials.gov: NCT02702557, February 29, 2016. Data Protection Agency: 2016-42, February 25, 2016. Ethics Committee: No registration needed, December 8, 2015 (e-mail correspondence).

Using hyperspectral imagery to assist federal forest monitoring and restoration projects in the Southern Rocky Mountains, Colorado

NASA Astrophysics Data System (ADS)

Wamser, Kyle

Hyperspectral imagery and the corresponding ability to conduct analysis below the pixel level have tremendous potential to aid in landcover monitoring. During large ecosystem restoration projects, being able to monitor specific aspects of the recovery over large and often inaccessible areas under constrained finances are major challenges. The Civil Air Patrol's Airborne Real-time Cueing Hyperspectral Enhanced Reconnaissance (ARCHER) can provide hyperspectral data in most parts of the United States at relatively low cost. Although designed specifically for use in locating downed aircraft, the imagery holds the potential to identify specific aspects of landcover at far greater fidelity than traditional multispectral means. The goals of this research were to improve the use of ARCHER hyperspectral imagery to classify sub-canopy and open-area vegetation in coniferous forests located in the Southern Rockies and to determine how much fidelity might be lost from a baseline of 1 meter spatial resolution resampled to 2 and 5 meter pixel size to simulate higher altitude collection. Based on analysis comparing linear spectral unmixing with a traditional supervised classification, the linear spectral unmixing proved to be statistically superior. More importantly, however, linear spectral unmixing provided additional sub-pixel information that was unavailable using other techniques. The second goal of determining fidelity loss based on spatial resolution was more difficult to determine due to how the data are represented. Furthermore, the 2 and 5 meter imagery were obtained by resampling the 1 meter imagery and therefore may not be representative of the quality of actual 2 or 5 meter imagery. Ultimately, the information derived from this research may be useful in better utilizing hyperspectral imagery to conduct forest monitoring and assessment.

Determination of sediment provenance by unmixing the mineralogy of source-area sediments: The "SedUnMix" program

USGS Publications Warehouse

Andrews, John T.; Eberl, D.D.

2012-01-01

Along the margins of areas such as Greenland and Baffin Bay, sediment composition reflects a complex mixture of sources associated with the transport of sediment in sea ice, icebergs, melt-water and turbidite plumes. Similar situations arise in many contexts associated with sediment transport and with the mixing of sediments from different source areas. The question is: can contributions from discrete sediment (bedrock) sources be distinguished in a mixed sediment by using mineralogy, and, if so, how accurately? To solve this problem, four end-member source sediments were mixed in various proportions to form eleven artificial mixtures. Two of the end-member sediments are felsic, and the other two have more mafic compositions. End member and mixed sediment mineralogies were measured for the < 2. mm sediment fractions by quantitative X-ray diffraction (qXRD). The proportions of source sediments in the mixtures then were calculated using an Excel macro program named SedUnMix, and the results were evaluated to determine the robustness of the algorithm. The program permits the unmixing of up to six end members, each of which can be represented by up to 5 alternative compositions, so as to better simulate variability within each source region. The results indicate that we can track the relative percentages of the four end members in the mixtures. We recommend, prior to applying the technique to down-core or to other provenance problems, that a suite of known, artificial mixtures of sediments from probable source areas be prepared, scanned, analyzed for quantitative mineralogy, and then analyzed by SedUnMix to check the sensitivity of the method for each specific unmixing problem. ?? 2011 Elsevier B.V..

Unmixing Magnetic Hysteresis Loops

NASA Astrophysics Data System (ADS)

Heslop, D.; Roberts, A. P.

2012-04-01

Magnetic hysteresis loops provide important information in rock and environmental magnetic studies. Natural samples often contain an assemblage of magnetic particles composed of components with different origins. Each component potentially carries important environmental information. Hysteresis loops, however, provide information concerning the bulk magnetic assemblage, which makes it difficult to isolate the specific contributions from different sources. For complex mineral assemblages an unmixing strategy with which to separate hysteresis loops into their component parts is therefore essential. Previous methods to unmix hysteresis data have aimed at separating individual loops into their constituent parts using libraries of type-curves thought to correspond to specific mineral types. We demonstrate an alternative approach, which rather than decomposing a single loop into monomineralic contributions, examines a collection of loops to determine their constituent source materials. These source materials may themselves be mineral mixtures, but they provide a genetically meaningful decomposition of a magnetic assemblage in terms of the processes that controlled its formation. We show how an empirically derived hysteresis mixing space can be created, without resorting to type-curves, based on the co-variation within a collection of measured loops. Physically realistic end-members, which respect the expected behaviour and symmetries of hysteresis loops, can then be extracted from the mixing space. These end-members allow the measured loops to be described as a combination of invariant parts that are assumed to represent the different sources in the mixing model. Particular attention is paid to model selection and estimating the complexity of the mixing model, specifically, how many end-members should be included. We demonstrate application of this approach using lake sediments from Butte Valley, northern California. Our method successfully separates the hysteresis loops into sources with a variety of terrigenous and authigenic origins.

Improving the Accuracy of Mapping Urban Vegetation Carbon Density by Combining Shadow Remove, Spectral Unmixing Analysis and Spatial Modeling

NASA Astrophysics Data System (ADS)

Qie, G.; Wang, G.; Wang, M.

2016-12-01

Mixed pixels and shadows due to buildings in urban areas impede accurate estimation and mapping of city vegetation carbon density. In most of previous studies, these factors are often ignored, which thus result in underestimation of city vegetation carbon density. In this study we presented an integrated methodology to improve the accuracy of mapping city vegetation carbon density. Firstly, we applied a linear shadow remove analysis (LSRA) on remotely sensed Landsat 8 images to reduce the shadow effects on carbon estimation. Secondly, we integrated a linear spectral unmixing analysis (LSUA) with a linear stepwise regression (LSR), a logistic model-based stepwise regression (LMSR) and k-Nearest Neighbors (kNN), and utilized and compared the integrated models on shadow-removed images to map vegetation carbon density. This methodology was examined in Shenzhen City of Southeast China. A data set from a total of 175 sample plots measured in 2013 and 2014 was used to train the models. The independent variables statistically significantly contributing to improving the fit of the models to the data and reducing the sum of squared errors were selected from a total of 608 variables derived from different image band combinations and transformations. The vegetation fraction from LSUA was then added into the models as an important independent variable. The estimates obtained were evaluated using a cross-validation method. Our results showed that higher accuracies were obtained from the integrated models compared with the ones using traditional methods which ignore the effects of mixed pixels and shadows. This study indicates that the integrated method has great potential on improving the accuracy of urban vegetation carbon density estimation. Key words: Urban vegetation carbon, shadow, spectral unmixing, spatial modeling, Landsat 8 images

Bulk mineralogy of the NE Syrtis and Jezero crater regions of Mars derived through thermal infrared spectral analyses

NASA Astrophysics Data System (ADS)

Salvatore, M. R.; Goudge, T. A.; Bramble, M. S.; Edwards, C. S.; Bandfield, J. L.; Amador, E. S.; Mustard, J. F.; Christensen, P. R.

2018-02-01

We investigated the area to the northwest of the Isidis impact basin (hereby referred to as "NW Isidis") using thermal infrared emission datasets to characterize and quantify bulk surface mineralogy throughout this region. This area is home to Jezero crater and the watershed associated with its two deltaic deposits in addition to NE Syrtis and the strong and diverse visible/near-infrared spectral signatures observed in well-exposed stratigraphic sections. The spectral signatures throughout this region show a diversity of primary and secondary surface mineralogies, including olivine, pyroxene, smectite clays, sulfates, and carbonates. While previous thermal infrared investigations have sought to characterize individual mineral groups within this region, none have systematically assessed bulk surface mineralogy and related these observations to visible/near-infrared studies. We utilize an iterative spectral unmixing method to statistically evaluate our linear thermal infrared spectral unmixing models to derive surface mineralogy. All relevant primary and secondary phases identified in visible/near-infrared studies are included in the unmixing models and their modeled spectral contributions are discussed in detail. While the stratigraphy and compositional diversity observed in visible/near-infrared spectra are much better exposed and more diverse than most other regions of Mars, our thermal infrared analyses suggest the dominance of basaltic compositions with less observed variability in the amount and diversity of alteration phases. These results help to constrain the mineralogical context of these previously reported visible/near-infrared spectral identifications. The results are also discussed in the context of future in situ investigations, as the NW Isidis region has long been promoted as a region of paleoenvironmental interest on Mars.

Comparison of receptor models for source apportionment of the PM10 in Zaragoza (Spain).

PubMed

Callén, M S; de la Cruz, M T; López, J M; Navarro, M V; Mastral, A M

2009-08-01

Receptor models are useful to understand the chemical and physical characteristics of air pollutants by identifying their sources and by estimating contributions of each source to receptor concentrations. In this work, three receptor models based on principal component analysis with absolute principal component scores (PCA-APCS), Unmix and positive matrix factorization (PMF) were applied to study for the first time the apportionment of the airborne particulate matter less or equal than 10microm (PM10) in Zaragoza, Spain, during 1year sampling campaign (2003-2004). The PM10 samples were characterized regarding their concentrations in inorganic components: trace elements and ions and also organic components: polycyclic aromatic hydrocarbons (PAH) not only in the solid phase but also in the gas phase. A comparison of the three receptor models was carried out in order to do a more robust characterization of the PM10. The three models predicted that the major sources of PM10 in Zaragoza were related to natural sources (60%, 75% and 47%, respectively, for PCA-APCS, Unmix and PMF) although anthropogenic sources also contributed to PM10 (28%, 25% and 39%). With regard to the anthropogenic sources, while PCA and PMF allowed high discrimination in the sources identification associated with different combustion sources such as traffic and industry, fossil fuel, biomass and fuel-oil combustion, heavy traffic and evaporative emissions, the Unmix model only allowed the identification of industry and traffic emissions, evaporative emissions and heavy-duty vehicles. The three models provided good correlations between the experimental and modelled PM10 concentrations with major precision and the closest agreement between the PMF and PCA models.

Hyperspectral fluorescence imaging with multi wavelength LED excitation

NASA Astrophysics Data System (ADS)

Luthman, A. Siri; Dumitru, Sebastian; Quirós-Gonzalez, Isabel; Bohndiek, Sarah E.

2016-04-01

Hyperspectral imaging (HSI) can combine morphological and molecular information, yielding potential for real-time and high throughput multiplexed fluorescent contrast agent imaging. Multiplexed readout from targets, such as cell surface receptors overexpressed in cancer cells, could improve both sensitivity and specificity of tumor identification. There remains, however, a need for compact and cost effective implementations of the technology. We have implemented a low-cost wide-field multiplexed fluorescence imaging system, which combines LED excitation at 590, 655 and 740 nm with a compact commercial solid state HSI system operating in the range 600 - 1000 nm. A key challenge for using reflectance-based HSI is the separation of contrast agent fluorescence from the reflectance of the excitation light. Here, we illustrate how it is possible to address this challenge in software, using two offline reflectance removal methods, prior to least-squares spectral unmixing. We made a quantitative comparison of the methods using data acquired from dilutions of contrast agents prepared in well-plates. We then established the capability of our HSI system for non-invasive in vivo fluorescence imaging in small animals using the optimal reflectance removal method. The HSI presented here enables quantitative unmixing of at least four fluorescent contrast agents (Alexa Fluor 610, 647, 700 and 750) simultaneously in living mice. A successful unmixing of the four fluorescent contrast agents was possible both using the pure contrast agents and with mixtures. The system could in principle also be applied to imaging of ex vivo tissue or intraoperative imaging in a clinical setting. These data suggest a promising approach for developing clinical applications of HSI based on multiplexed fluorescence contrast agent imaging.

PM2.5 pollution from household solid fuel burning practices in Central India: 2. Application of receptor models for source apportionment.

PubMed

Matawle, Jeevan Lal; Pervez, Shamsh; Deb, Manas Kanti; Shrivastava, Anjali; Tiwari, Suresh

2018-02-01

USEPA's UNMIX, positive matrix factorization (PMF) and effective variance-chemical mass balance (EV-CMB) receptor models were applied to chemically speciated profiles of 125 indoor PM 2.5 measurements, sampled longitudinally during 2012-2013 in low-income group households of Central India which uses solid fuels for cooking practices. Three step source apportionment studies were carried out to generate more confident source characterization. Firstly, UNMIX6.0 extracted initial number of source factors, which were used to execute PMF5.0 to extract source-factor profiles in second step. Finally, factor analog locally derived source profiles were supplemented to EV-CMB8.2 with indoor receptor PM 2.5 chemical profile to evaluate source contribution estimates (SCEs). The results of combined use of three receptor models clearly describe that UNMIX and PMF are useful tool to extract types of source categories within small receptor dataset and EV-CMB can pick those locally derived source profiles for source apportionment which are analog to PMF-extracted source categories. The source apportionment results have also shown three fold higher relative contribution of solid fuel burning emissions to indoor PM 2.5 compared to those measurements reported for normal households with LPG stoves. The previously reported influential source marker species were found to be comparatively similar to those extracted from PMF fingerprint plots. The comparison between PMF and CMB SCEs results were also found to be qualitatively similar. The performance fit measures of all three receptor models were cross-verified and validated and support each other to gain confidence in source apportionment results.

Manifold Learning in MR spectroscopy using nonlinear dimensionality reduction and unsupervised clustering.

PubMed

Yang, Guang; Raschke, Felix; Barrick, Thomas R; Howe, Franklyn A

2015-09-01

To investigate whether nonlinear dimensionality reduction improves unsupervised classification of (1) H MRS brain tumor data compared with a linear method. In vivo single-voxel (1) H magnetic resonance spectroscopy (55 patients) and (1) H magnetic resonance spectroscopy imaging (MRSI) (29 patients) data were acquired from histopathologically diagnosed gliomas. Data reduction using Laplacian eigenmaps (LE) or independent component analysis (ICA) was followed by k-means clustering or agglomerative hierarchical clustering (AHC) for unsupervised learning to assess tumor grade and for tissue type segmentation of MRSI data. An accuracy of 93% in classification of glioma grade II and grade IV, with 100% accuracy in distinguishing tumor and normal spectra, was obtained by LE with unsupervised clustering, but not with the combination of k-means and ICA. With (1) H MRSI data, LE provided a more linear distribution of data for cluster analysis and better cluster stability than ICA. LE combined with k-means or AHC provided 91% accuracy for classifying tumor grade and 100% accuracy for identifying normal tissue voxels. Color-coded visualization of normal brain, tumor core, and infiltration regions was achieved with LE combined with AHC. The LE method is promising for unsupervised clustering to separate brain and tumor tissue with automated color-coding for visualization of (1) H MRSI data after cluster analysis. © 2014 Wiley Periodicals, Inc.

A comparative analysis of pixel- and object-based detection of landslides from very high-resolution images

NASA Astrophysics Data System (ADS)

Keyport, Ren N.; Oommen, Thomas; Martha, Tapas R.; Sajinkumar, K. S.; Gierke, John S.

2018-02-01

A comparative analysis of landslides detected by pixel-based and object-oriented analysis (OOA) methods was performed using very high-resolution (VHR) remotely sensed aerial images for the San Juan La Laguna, Guatemala, which witnessed widespread devastation during the 2005 Hurricane Stan. A 3-band orthophoto of 0.5 m spatial resolution together with a 115 field-based landslide inventory were used for the analysis. A binary reference was assigned with a zero value for landslide and unity for non-landslide pixels. The pixel-based analysis was performed using unsupervised classification, which resulted in 11 different trial classes. Detection of landslides using OOA includes 2-step K-means clustering to eliminate regions based on brightness; elimination of false positives using object properties such as rectangular fit, compactness, length/width ratio, mean difference of objects, and slope angle. Both overall accuracy and F-score for OOA methods outperformed pixel-based unsupervised classification methods in both landslide and non-landslide classes. The overall accuracy for OOA and pixel-based unsupervised classification was 96.5% and 94.3%, respectively, whereas the best F-score for landslide identification for OOA and pixel-based unsupervised methods: were 84.3% and 77.9%, respectively.Results indicate that the OOA is able to identify the majority of landslides with a few false positive when compared to pixel-based unsupervised classification.

Feature Extraction Using an Unsupervised Neural Network

DTIC Science & Technology

1991-05-03

with this neural netowrk is given and its connection to exploratory projection pursuit methods is established. DD I 2 P JA d 73 EDITIONj Of I NOV 6s...IS OBSOLETE $IN 0102- LF- 014- 6601 SECURITY CLASSIFICATION OF THIS PAGE (When Daoes Enlered) Feature Extraction using an Unsupervised Neural Network

An Unsupervised Method for Uncovering Morphological Chains (Open Access, Publisher’s Version)

DTIC Science & Technology

2015-03-08

Consortium. Marco Baroni, Johannes Matiasek, and Harald Trost. 2002. Unsupervised discovery of morphologically re- lated words based on orthographic and...Better word representations with re- cursive neural networks for morphology. In CoNLL, Sofia, Bulgaria. Mohamed Maamouri, Ann Bies, Hubert Jin, and Tim

18 CFR 292.202 - Definitions.

Code of Federal Regulations, 2011 CFR

2011-04-01

... Definitions. For purposes of this subpart: (a) Biomass means any organic material not derived from fossil.... (c) Cogeneration facility means equipment used to produce electric energy and forms of useful thermal... all forms supplied from external sources; (k) Natural gas means either natural gas unmixed, or any...

18 CFR 292.202 - Definitions.

Code of Federal Regulations, 2014 CFR

2014-04-01

... Definitions. For purposes of this subpart: (a) Biomass means any organic material not derived from fossil.... (c) Cogeneration facility means equipment used to produce electric energy and forms of useful thermal... all forms supplied from external sources; (k) Natural gas means either natural gas unmixed, or any...

18 CFR 292.202 - Definitions.

Code of Federal Regulations, 2010 CFR

2010-04-01

... Definitions. For purposes of this subpart: (a) Biomass means any organic material not derived from fossil.... (c) Cogeneration facility means equipment used to produce electric energy and forms of useful thermal... all forms supplied from external sources; (k) Natural gas means either natural gas unmixed, or any...

18 CFR 292.202 - Definitions.

Code of Federal Regulations, 2012 CFR

2012-04-01

... Definitions. For purposes of this subpart: (a) Biomass means any organic material not derived from fossil.... (c) Cogeneration facility means equipment used to produce electric energy and forms of useful thermal... all forms supplied from external sources; (k) Natural gas means either natural gas unmixed, or any...

18 CFR 292.202 - Definitions.

Code of Federal Regulations, 2013 CFR

2013-04-01

... Definitions. For purposes of this subpart: (a) Biomass means any organic material not derived from fossil.... (c) Cogeneration facility means equipment used to produce electric energy and forms of useful thermal... all forms supplied from external sources; (k) Natural gas means either natural gas unmixed, or any...

Aliasing Signal Separation of Superimposed Abrasive Debris Based on Degenerate Unmixing Estimation Technique.

PubMed

Li, Tongyang; Wang, Shaoping; Zio, Enrico; Shi, Jian; Hong, Wei

2018-03-15

Leakage is the most important failure mode in aircraft hydraulic systems caused by wear and tear between friction pairs of components. The accurate detection of abrasive debris can reveal the wear condition and predict a system's lifespan. The radial magnetic field (RMF)-based debris detection method provides an online solution for monitoring the wear condition intuitively, which potentially enables a more accurate diagnosis and prognosis on the aviation hydraulic system's ongoing failures. To address the serious mixing of pipe abrasive debris, this paper focuses on the superimposed abrasive debris separation of an RMF abrasive sensor based on the degenerate unmixing estimation technique. Through accurately separating and calculating the morphology and amount of the abrasive debris, the RMF-based abrasive sensor can provide the system with wear trend and sizes estimation of the wear particles. A well-designed experiment was conducted and the result shows that the proposed method can effectively separate the mixed debris and give an accurate count of the debris based on RMF abrasive sensor detection.

Simulated altitude exposure assessment by hyperspectral imaging

NASA Astrophysics Data System (ADS)

Calin, Mihaela Antonina; Macovei, Adrian; Miclos, Sorin; Parasca, Sorin Viorel; Savastru, Roxana; Hristea, Razvan

2017-05-01

Testing the human body's reaction to hypoxia (including the one generated by high altitude) is important in aeronautic medicine. This paper presents a method of monitoring blood oxygenation during experimental hypoxia using hyperspectral imaging (HSI) and a spectral unmixing model based on a modified Beer-Lambert law. A total of 20 healthy volunteers (males) aged 25 to 60 years were included in this study. A line-scan HSI system was used to acquire images of the faces of the subjects. The method generated oxyhemoglobin and deoxyhemoglobin distribution maps from the foreheads of the subjects at 5 and 10 min of hypoxia and after recovery in a high oxygen breathing mixture. The method also generated oxygen saturation maps that were validated using pulse oximetry. An interesting pattern of desaturation on the forehead was discovered during the study, showing one of the advantages of using HSI for skin oxygenation monitoring in hypoxic conditions. This could bring new insight into the physiological response to high altitude and may become a step forward in air crew testing.

Kinetics of T-cell receptor-dependent antigen recognition determined in vivo by multi-spectral normalized epifluorescence laser scanning

NASA Astrophysics Data System (ADS)

Favicchio, Rosy; Zacharakis, Giannis; Oikonomaki, Katerina; Zacharopoulos, Athanasios; Mamalaki, Clio; Ripoll, Jorge

2012-07-01

Detection of multiple fluorophores in conditions of low signal represents a limiting factor for the application of in vivo optical imaging techniques in immunology where fluorescent labels report for different functional characteristics. A noninvasive in vivo Multi-Spectral Normalized Epifluorescence Laser scanning (M-SNELS) method was developed for the simultaneous and quantitative detection of multiple fluorophores in low signal to noise ratios and used to follow T-cell activation and clonal expansion. Colocalized DsRed- and GFP-labeled T cells were followed in tandem during the mounting of an immune response. Spectral unmixing was used to distinguish the overlapping fluorescent emissions representative of the two distinct cell populations and longitudinal data reported the discrete pattern of antigen-driven proliferation. Retrieved values were validated both in vitro and in vivo with flow cytometry and significant correlation between all methodologies was achieved. Noninvasive M-SNELS successfully quantified two colocalized fluorescent populations and provides a valid alternative imaging approach to traditional invasive methods for detecting T cell dynamics.

Simulated altitude exposure assessment by hyperspectral imaging.

PubMed

Calin, Mihaela Antonina; Macovei, Adrian; Miclos, Sorin; Parasca, Sorin Viorel; Savastru, Roxana; Hristea, Razvan

2017-05-01

Testing the human body’s reaction to hypoxia (including the one generated by high altitude) is important in aeronautic medicine. This paper presents a method of monitoring blood oxygenation during experimental hypoxia using hyperspectral imaging (HSI) and a spectral unmixing model based on a modified Beer–Lambert law. A total of 20 healthy volunteers (males) aged 25 to 60 years were included in this study. A line-scan HSI system was used to acquire images of the faces of the subjects. The method generated oxyhemoglobin and deoxyhemoglobin distribution maps from the foreheads of the subjects at 5 and 10 min of hypoxia and after recovery in a high oxygen breathing mixture. The method also generated oxygen saturation maps that were validated using pulse oximetry. An interesting pattern of desaturation on the forehead was discovered during the study, showing one of the advantages of using HSI for skin oxygenation monitoring in hypoxic conditions. This could bring new insight into the physiological response to high altitude and may become a step forward in air crew testing.

Band selection using forward feature selection algorithm for citrus Huanglongbing disease detection

USDA-ARS?s Scientific Manuscript database

This study attempted to classify spectrally similar data – obtained from aerial images of healthy citrus plants and the citrus greening disease (Huanglongbing) infected plants - using small differences without un-mixing the endmember components and therefore without the need for endmember library. H...

Machine Learning Approach to Deconvolution of Thermal Infrared (TIR) Spectrum of Mercury Supporting MERTIS Onboard ESA/JAXA BepiColombo

NASA Astrophysics Data System (ADS)

Varatharajan, I.; D'Amore, M.; Maturilli, A.; Helbert, J.; Hiesinger, H.

2018-04-01

Machine learning approach to spectral unmixing of emissivity spectra of Mercury is carried out using endmember spectral library measured at simulated daytime surface conditions of Mercury. Study supports MERTIS payload onboard ESA/JAXA BepiColombo.

Exploiting Redundancy for Flexible Behavior: Unsupervised Learning in a Modular Sensorimotor Control Architecture

ERIC Educational Resources Information Center

Butz, Martin V.; Herbort, Oliver; Hoffmann, Joachim

2007-01-01

Autonomously developing organisms face several challenges when learning reaching movements. First, motor control is learned unsupervised or self-supervised. Second, knowledge of sensorimotor contingencies is acquired in contexts in which action consequences unfold in time. Third, motor redundancies must be resolved. To solve all 3 of these…

Bilingual Lexical Interactions in an Unsupervised Neural Network Model

ERIC Educational Resources Information Center

Zhao, Xiaowei; Li, Ping

2010-01-01

In this paper we present an unsupervised neural network model of bilingual lexical development and interaction. We focus on how the representational structures of the bilingual lexicons can emerge, develop, and interact with each other as a function of the learning history. The results show that: (1) distinct representations for the two lexicons…

Relationships of parental monitoring and emotion regulation with early adolescents' sexual behaviors.

PubMed

Hadley, Wendy; Houck, Christopher D; Barker, David; Senocak, Natali

2015-06-01

The purpose of this study was to examine the moderating influence of parental monitoring (e.g., unsupervised time with opposite sex peers) and adolescent emotional competence on sexual behaviors, among a sample of at-risk early adolescents. This study included 376 seventh-grade adolescents (age, 12-14 years) with behavioral or emotional difficulties. Questionnaires were completed on private laptop computers and assessed adolescent Emotional Competence (including Regulation and Negativity/Lability), Unsupervised Time, and a range of Sexual Behaviors. Generalized linear models were used to evaluate the independent and combined influence of Emotional Competency and Unsupervised Time on adolescent report of Sexual Behaviors. Analyses were stratified by gender to account for the notable gender differences in the targeted moderators and outcome variables. Findings indicated that more unsupervised time was a risk factor for all youth but was influenced by an adolescent's ability to regulate their emotions. Specifically, for males and females, poorer Emotion Regulation was associated with having engaged in a greater variety of Sexual Behaviors. However, lower Negativity/Lability and >1× per week Unsupervised Time were associated with a higher number of sexual behaviors among females only. Based on the findings of this study, a lack of parental supervision seems to be particularly problematic for both male and female adolescents with poor emotion regulation abilities. It may be important to impact both emotion regulation abilities and increase parental knowledge and skills associated with effective monitoring to reduce risk-taking for these youth.

A Novel Unsupervised Segmentation Quality Evaluation Method for Remote Sensing Images

PubMed Central

Tang, Yunwei; Jing, Linhai; Ding, Haifeng

2017-01-01

The segmentation of a high spatial resolution remote sensing image is a critical step in geographic object-based image analysis (GEOBIA). Evaluating the performance of segmentation without ground truth data, i.e., unsupervised evaluation, is important for the comparison of segmentation algorithms and the automatic selection of optimal parameters. This unsupervised strategy currently faces several challenges in practice, such as difficulties in designing effective indicators and limitations of the spectral values in the feature representation. This study proposes a novel unsupervised evaluation method to quantitatively measure the quality of segmentation results to overcome these problems. In this method, multiple spectral and spatial features of images are first extracted simultaneously and then integrated into a feature set to improve the quality of the feature representation of ground objects. The indicators designed for spatial stratified heterogeneity and spatial autocorrelation are included to estimate the properties of the segments in this integrated feature set. These two indicators are then combined into a global assessment metric as the final quality score. The trade-offs of the combined indicators are accounted for using a strategy based on the Mahalanobis distance, which can be exhibited geometrically. The method is tested on two segmentation algorithms and three testing images. The proposed method is compared with two existing unsupervised methods and a supervised method to confirm its capabilities. Through comparison and visual analysis, the results verified the effectiveness of the proposed method and demonstrated the reliability and improvements of this method with respect to other methods. PMID:29064416

Developmental Self-Construction and -Configuration of Functional Neocortical Neuronal Networks

PubMed Central

Bauer, Roman; Zubler, Frédéric; Pfister, Sabina; Hauri, Andreas; Pfeiffer, Michael; Muir, Dylan R.; Douglas, Rodney J.

2014-01-01

The prenatal development of neural circuits must provide sufficient configuration to support at least a set of core postnatal behaviors. Although knowledge of various genetic and cellular aspects of development is accumulating rapidly, there is less systematic understanding of how these various processes play together in order to construct such functional networks. Here we make some steps toward such understanding by demonstrating through detailed simulations how a competitive co-operative (‘winner-take-all’, WTA) network architecture can arise by development from a single precursor cell. This precursor is granted a simplified gene regulatory network that directs cell mitosis, differentiation, migration, neurite outgrowth and synaptogenesis. Once initial axonal connection patterns are established, their synaptic weights undergo homeostatic unsupervised learning that is shaped by wave-like input patterns. We demonstrate how this autonomous genetically directed developmental sequence can give rise to self-calibrated WTA networks, and compare our simulation results with biological data. PMID:25474693

Color normalization of histology slides using graph regularized sparse NMF

NASA Astrophysics Data System (ADS)

Sha, Lingdao; Schonfeld, Dan; Sethi, Amit

2017-03-01

Computer based automatic medical image processing and quantification are becoming popular in digital pathology. However, preparation of histology slides can vary widely due to differences in staining equipment, procedures and reagents, which can reduce the accuracy of algorithms that analyze their color and texture information. To re- duce the unwanted color variations, various supervised and unsupervised color normalization methods have been proposed. Compared with supervised color normalization methods, unsupervised color normalization methods have advantages of time and cost efficient and universal applicability. Most of the unsupervised color normaliza- tion methods for histology are based on stain separation. Based on the fact that stain concentration cannot be negative and different parts of the tissue absorb different stains, nonnegative matrix factorization (NMF), and particular its sparse version (SNMF), are good candidates for stain separation. However, most of the existing unsupervised color normalization method like PCA, ICA, NMF and SNMF fail to consider important information about sparse manifolds that its pixels occupy, which could potentially result in loss of texture information during color normalization. Manifold learning methods like Graph Laplacian have proven to be very effective in interpreting high-dimensional data. In this paper, we propose a novel unsupervised stain separation method called graph regularized sparse nonnegative matrix factorization (GSNMF). By considering the sparse prior of stain concentration together with manifold information from high-dimensional image data, our method shows better performance in stain color deconvolution than existing unsupervised color deconvolution methods, especially in keeping connected texture information. To utilized the texture information, we construct a nearest neighbor graph between pixels within a spatial area of an image based on their distances using heat kernal in lαβ space. The representation of a pixel in the stain density space is constrained to follow the feature distance of the pixel to pixels in the neighborhood graph. Utilizing color matrix transfer method with the stain concentrations found using our GSNMF method, the color normalization performance was also better than existing methods.

Unsupervised discovery of information structure in biomedical documents.

PubMed

Kiela, Douwe; Guo, Yufan; Stenius, Ulla; Korhonen, Anna

2015-04-01

Information structure (IS) analysis is a text mining technique, which classifies text in biomedical articles into categories that capture different types of information, such as objectives, methods, results and conclusions of research. It is a highly useful technique that can support a range of Biomedical Text Mining tasks and can help readers of biomedical literature find information of interest faster, accelerating the highly time-consuming process of literature review. Several approaches to IS analysis have been presented in the past, with promising results in real-world biomedical tasks. However, all existing approaches, even weakly supervised ones, require several hundreds of hand-annotated training sentences specific to the domain in question. Because biomedicine is subject to considerable domain variation, such annotations are expensive to obtain. This makes the application of IS analysis across biomedical domains difficult. In this article, we investigate an unsupervised approach to IS analysis and evaluate the performance of several unsupervised methods on a large corpus of biomedical abstracts collected from PubMed. Our best unsupervised algorithm (multilevel-weighted graph clustering algorithm) performs very well on the task, obtaining over 0.70 F scores for most IS categories when applied to well-known IS schemes. This level of performance is close to that of lightly supervised IS methods and has proven sufficient to aid a range of practical tasks. Thus, using an unsupervised approach, IS could be applied to support a wide range of tasks across sub-domains of biomedicine. We also demonstrate that unsupervised learning brings novel insights into IS of biomedical literature and discovers information categories that are not present in any of the existing IS schemes. The annotated corpus and software are available at http://www.cl.cam.ac.uk/∼dk427/bio14info.html. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Effects of an off-season conditioning program on the physical characteristics of adolescent rugby union players.

PubMed

Smart, Daniel J; Gill, Nicholas D

2013-03-01

The aims of the study were to determine if a supervised off-season conditioning program enhanced gains in physical characteristics compared with the same program performed in an unsupervised manner and to establish the persistence of the physical changes after a 6-month unsupervised competition period. Forty-four provincial representative adolescent rugby union players (age, mean ± SD, 15.3 ± 1.3 years) participated in a 15-week off-season conditioning program either under supervision from an experienced strength and conditioning coach or unsupervised. Measures of body composition, strength, vertical jump, speed, and anaerobic and aerobic running performance were taken, before, immediately after, and 6 months after the conditioning. Post conditioning program the supervised group had greater improvements in all strength measures than the unsupervised group, with small, moderate and large differences between the groups\\x{2019} changes for chin-ups (9.1%; ± 11.6%), bench-press (16.9%; ± 11.7%) and box-squat (50.4%; ± 20.9%) estimated 1RM respectively. Both groups showed trivial increases in mass; however increases in fat free mass were small and trivial for supervised and unsupervised players respectively. Strength declined in the supervised group while the unsupervised group had small increases during the competition phase, resulting in only a small difference between the long-term changes in box-squat 1RM (15.9%; ± 13.2%). The supervised group had further small increases in fat free mass resulting in a small difference (2.4%; ± 2.7%) in the long-term changes. The postconditioning differences between the 2 groups may have been a result of increased adherence and the attainment of higher training loads during supervised training. The lack of differences in strength after the competition period indicates that supervision should be maintained to reduce substantial decrements in performance.

Use of Raman microscopy and band-target entropy minimization analysis to identify dyes in a commercial stamp. Implications for authentication and counterfeit detection.

PubMed

Widjaja, Effendi; Garland, Marc

2008-02-01

Raman microscopy was used in mapping mode to collect more than 1000 spectra in a 100 microm x 100 microm area from a commercial stamp. Band-target entropy minimization (BTEM) was then employed to unmix the mixture spectra in order to extract the pure component spectra of the samples. Three pure component spectral patterns with good signal-to-noise ratios were recovered, and their spatial distributions were determined. The three pure component spectral patterns were then identified as copper phthalocyanine blue, calcite-like material, and yellow organic dye material by comparison to known spectral libraries. The present investigation, consisting of (1) advanced curve resolution (blind-source separation) followed by (2) spectral data base matching, readily suggests extensions to authenticity and counterfeit studies of other types of commercial objects. The presence or absence of specific observable components form the basis for assessment. The present spectral analysis (BTEM) is applicable to highly overlapping spectral information. Since a priori information such as the number of components present and spectral libraries are not needed in BTEM, and since minor signals arising from trace components can be reconstructed, this analysis offers a robust approach to a wide variety of material problems involving authenticity and counterfeit issues.

Revisiting the "Unmixing Experiment" through Argumentation

ERIC Educational Resources Information Center

Çoban, Gul Ünal; Büber, Ayse; Saglam, Merve Kocagül

2017-01-01

This paper focuses on a series of activities for students at middle school to college level, designed to instill a sound understanding of fluids and the properties of fluids. The first activities investigate diffusion and molecular size and these are followed by tasks exploring viscosity and the factors effecting viscosity. Following this, there…

Context Dependent Spectral Unmixing

DTIC Science & Technology

2014-08-01

the tar- get sizes). The targets were made of 100% cotton fabric and were emplaced so that there would be representatives of each color type completely...method for simplex-based endmember extraction algorithm,” IEEE Transactions on Geoscience and Re- mote Sensing, vol. 44, no. 10, pp. 2804–2819, 2006. [68

Assessment of spruce (Picea obovata) abundance by spectral unmixing algorithm for sustainable forest management in highland Natural Reserve (case study of Zigalga Range, South-Ural State Natural Reserve, Russia).

NASA Astrophysics Data System (ADS)

Mikheeva, Anna; Moiseev, Pavel

2017-04-01

In mountain territories climate change affects forest productivity and growth, which results in the tree line advancing and increasing of the forest density. These changes pose new challenges for forest managers whose responsibilities include forest resources inventory, monitoring and protection of ecosystems, and assessment of forest vulnerability. These activities require a range of sources of information, including exact squares of forested areas, forest densities and species abundances. Picea obovata, dominant tree species in South-Ural State Natural Reserve, Russia has regenerated, propagated and increased its relative cover during the recent 70 years. A remarkable shift of the upper limit of Picea obovata up to 60-80 m upslope was registered by repeating photography, especially on gentle slopes. The stands of Picea obovata are monitored by Reserve inspectors on the test plots to ensure that forests maintain or improve their productivity, these studies also include projective cover measurements. However, it is impossible to cover the entire territory of the Reserve by detailed field observations. Remote sensing data from Terra ASTER imagery provides valuable information for large territories (scene covers an area of 60 x 60 km) and can be used for quantitative mapping of forest and non-forest vegetation at regional scale (spatial resolution is 15-30 m for visible and infrared bands). A case study of estimating Picea obovata abundance was conducted for forest and forest-tundra sites of Zigalga Range, using 9-band ASTER multispectral imagery of 23.08.2007, field data and spectral unmixing algorithm. This type of algorithms intends to derive object and its abundance from a mixed pixel of multispectral imagery which can be further converted to object's projective cover. Atmospheric correction was applied to the imagery prior to spectral unmixing, and then pure spectra of Picea obovata were extracted from the image in 10 points and averaged. These points located in Zigalga Range and were visited in summer 2016. We used Mixture-tuned Match Filtering (MTMF) algorithm, a non-linear subpixel classification technique which allows to separate the spectral mixture containing unknown objects, and to derive only known ones. The results of spectral unmixing classification were abundance maps of Picea obovata. The values were statistically determined (there was only selected abundances with high probabilities of presence and low probabilities of absence) and then constrained to the interval [0; 1]. Verification of maps was made at the sites of Iremel Mountains on the same ASTER image, where projective cover of Picea obovata was measured in the field in 147 points. The correlation coefficient between the spectral unmixing abundances and field-measured abundances was 0.7; not a very high value is due to the low sensitivity of the algorithm to detect abundances less than 0.25. The proposed method provides a tool for defining the Picea obovata boundaries more accurately than per-pixel automatic classification and locating new spruce islands in the mixing tree line environment. The abundances can be obtained for large areas with minimum field work which makes this approach cost-effective in providing timely information to nature reserve managers for adapting forest management actions to climate change.

Combining Unsupervised and Supervised Classification to Build User Models for Exploratory Learning Environments

ERIC Educational Resources Information Center

Amershi, Saleema; Conati, Cristina

2009-01-01

In this paper, we present a data-based user modeling framework that uses both unsupervised and supervised classification to build student models for exploratory learning environments. We apply the framework to build student models for two different learning environments and using two different data sources (logged interface and eye-tracking data).…

Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation

ERIC Educational Resources Information Center

Hinton, Geoffrey; Osindero, Simon; Welling, Max; Teh, Yee-Whye

2006-01-01

We describe a way of modeling high-dimensional data vectors by using an unsupervised, nonlinear, multilayer neural network in which the activity of each neuron-like unit makes an additive contribution to a global energy score that indicates how surprised the network is by the data vector. The connection weights that determine how the activity of…

Validation of Unsupervised Computer-Based Screening for Reading Disability in Greek Elementary Grades 3 and 4

ERIC Educational Resources Information Center

Protopapas, Athanassios; Skaloumbakas, Christos; Bali, Persefoni

2008-01-01

After reviewing past efforts related to computer-based reading disability (RD) assessment, we present a fully automated screening battery that evaluates critical skills relevant for RD diagnosis designed for unsupervised application in the Greek educational system. Psychometric validation in 301 children, 8-10 years old (grades 3 and 4; including…

Unsupervised classification of remote multispectral sensing data

NASA Technical Reports Server (NTRS)

Su, M. Y.

1972-01-01

The new unsupervised classification technique for classifying multispectral remote sensing data which can be either from the multispectral scanner or digitized color-separation aerial photographs consists of two parts: (a) a sequential statistical clustering which is a one-pass sequential variance analysis and (b) a generalized K-means clustering. In this composite clustering technique, the output of (a) is a set of initial clusters which are input to (b) for further improvement by an iterative scheme. Applications of the technique using an IBM-7094 computer on multispectral data sets over Purdue's Flight Line C-1 and the Yellowstone National Park test site have been accomplished. Comparisons between the classification maps by the unsupervised technique and the supervised maximum liklihood technique indicate that the classification accuracies are in agreement.

Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses

NASA Astrophysics Data System (ADS)

Serb, Alexander; Bill, Johannes; Khiat, Ali; Berdan, Radu; Legenstein, Robert; Prodromakis, Themis

2016-09-01

In an increasingly data-rich world the need for developing computing systems that cannot only process, but ideally also interpret big data is becoming continuously more pressing. Brain-inspired concepts have shown great promise towards addressing this need. Here we demonstrate unsupervised learning in a probabilistic neural network that utilizes metal-oxide memristive devices as multi-state synapses. Our approach can be exploited for processing unlabelled data and can adapt to time-varying clusters that underlie incoming data by supporting the capability of reversible unsupervised learning. The potential of this work is showcased through the demonstration of successful learning in the presence of corrupted input data and probabilistic neurons, thus paving the way towards robust big-data processors.

Classification of earth terrain using polarimetric synthetic aperture radar images

NASA Technical Reports Server (NTRS)

Lim, H. H.; Swartz, A. A.; Yueh, H. A.; Kong, J. A.; Shin, R. T.; Van Zyl, J. J.

1989-01-01

Supervised and unsupervised classification techniques are developed and used to classify the earth terrain components from SAR polarimetric images of San Francisco Bay and Traverse City, Michigan. The supervised techniques include the Bayes classifiers, normalized polarimetric classification, and simple feature classification using discriminates such as the absolute and normalized magnitude response of individual receiver channel returns and the phase difference between receiver channels. An algorithm is developed as an unsupervised technique which classifies terrain elements based on the relationship between the orientation angle and the handedness of the transmitting and receiving polariation states. It is found that supervised classification produces the best results when accurate classifier training data are used, while unsupervised classification may be applied when training data are not available.

Heat-enhanced peptide synthesis on Teflon-patterned paper.

PubMed

Deiss, Frédérique; Yang, Yang; Matochko, Wadim L; Derda, Ratmir

2016-06-14

In this report, we describe the methodology for 96 parallel organic syntheses of peptides on Teflon-patterned paper assisted by heating with an infra-red lamp. SPOT synthesis is an important technology for production of peptide arrays on a paper-based support for rapid identification of peptide ligands, epitope mapping, and identification of bio-conjugation reactions. The major drawback of the SPOT synthesis methodology published to-date is suboptimal reaction conversion due to mass transport limitations in the unmixed reaction spot. The technology developed in this report overcomes these problems by changing the environment of the reaction from static to dynamic (flow-through), and further accelerating the reaction by selective heating of the reaction support in contact with activated amino acids. Patterning paper with Teflon allows for droplets of organic solvents to be confined in a zone on the paper array and flow through the paper at a well-defined rate and provide a convenient, power-free setup for flow-through solid-phase synthesis and efficient assembly of peptide arrays. We employed an infra-red (IR) lamp to locally heat the cellulosic support during the flow-through delivery of the reagents to each zone of the paper-based array. We demonstrate that IR-heating in solid phase peptide synthesis shortened the reaction time necessary for amide bond formation down to 3 minutes; in some couplings of alpha amino acids, conversion rates increased up to fifteen folds. The IR-heating improved the assembly of difficult sequences, such as homo-oligomers of all 20 natural amino acids.

Discovering multi-scale co-occurrence patterns of asthma and influenza with the Oak Ridge bio-surveillance toolkit

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ramanathan, Arvind; Pullum, Laura L.; Hobson, Tanner C.

Here, we describe a data-driven unsupervised machine learning approach to extract geo-temporal co-occurrence patterns of asthma and the flu from large-scale electronic healthcare reimbursement claims (eHRC) datasets. Specifically, we examine the eHRC data from 2009 to 2010 pandemic H1N1 influenza season and analyze whether different geographic regions within the United States (US) showed an increase in co-occurrence patterns of the flu and asthma. Our analyses reveal that the temporal patterns extracted from the eHRC data show a distinct lag time between the peak incidence of the asthma and the flu. While the increased occurrence of asthma contributed to increased flumore » incidence during the pandemic, this co-occurrence is predominant for female patients. The geo-temporal patterns reveal that the co-occurrence of the flu and asthma are typically concentrated within the south-east US. Further, in agreement with previous studies, large urban areas (such as New York, Miami, and Los Angeles) exhibit co-occurrence patterns that suggest a peak incidence of asthma and flu significantly early in the spring and winter seasons. Together, our data-analytic approach, integrated within the Oak Ridge Bio-surveillance Toolkit platform, demonstrates how eHRC data can provide novel insights into co-occurring disease patterns.« less

Discovering multi-scale co-occurrence patterns of asthma and influenza with the Oak Ridge bio-surveillance toolkit

DOE PAGES

Ramanathan, Arvind; Pullum, Laura L.; Hobson, Tanner C.; ...

2015-08-03

Here, we describe a data-driven unsupervised machine learning approach to extract geo-temporal co-occurrence patterns of asthma and the flu from large-scale electronic healthcare reimbursement claims (eHRC) datasets. Specifically, we examine the eHRC data from 2009 to 2010 pandemic H1N1 influenza season and analyze whether different geographic regions within the United States (US) showed an increase in co-occurrence patterns of the flu and asthma. Our analyses reveal that the temporal patterns extracted from the eHRC data show a distinct lag time between the peak incidence of the asthma and the flu. While the increased occurrence of asthma contributed to increased flumore » incidence during the pandemic, this co-occurrence is predominant for female patients. The geo-temporal patterns reveal that the co-occurrence of the flu and asthma are typically concentrated within the south-east US. Further, in agreement with previous studies, large urban areas (such as New York, Miami, and Los Angeles) exhibit co-occurrence patterns that suggest a peak incidence of asthma and flu significantly early in the spring and winter seasons. Together, our data-analytic approach, integrated within the Oak Ridge Bio-surveillance Toolkit platform, demonstrates how eHRC data can provide novel insights into co-occurring disease patterns.« less

Automated glioblastoma segmentation based on a multiparametric structured unsupervised classification.

PubMed

Juan-Albarracín, Javier; Fuster-Garcia, Elies; Manjón, José V; Robles, Montserrat; Aparici, F; Martí-Bonmatí, L; García-Gómez, Juan M

2015-01-01

Automatic brain tumour segmentation has become a key component for the future of brain tumour treatment. Currently, most of brain tumour segmentation approaches arise from the supervised learning standpoint, which requires a labelled training dataset from which to infer the models of the classes. The performance of these models is directly determined by the size and quality of the training corpus, whose retrieval becomes a tedious and time-consuming task. On the other hand, unsupervised approaches avoid these limitations but often do not reach comparable results than the supervised methods. In this sense, we propose an automated unsupervised method for brain tumour segmentation based on anatomical Magnetic Resonance (MR) images. Four unsupervised classification algorithms, grouped by their structured or non-structured condition, were evaluated within our pipeline. Considering the non-structured algorithms, we evaluated K-means, Fuzzy K-means and Gaussian Mixture Model (GMM), whereas as structured classification algorithms we evaluated Gaussian Hidden Markov Random Field (GHMRF). An automated postprocess based on a statistical approach supported by tissue probability maps is proposed to automatically identify the tumour classes after the segmentations. We evaluated our brain tumour segmentation method with the public BRAin Tumor Segmentation (BRATS) 2013 Test and Leaderboard datasets. Our approach based on the GMM model improves the results obtained by most of the supervised methods evaluated with the Leaderboard set and reaches the second position in the ranking. Our variant based on the GHMRF achieves the first position in the Test ranking of the unsupervised approaches and the seventh position in the general Test ranking, which confirms the method as a viable alternative for brain tumour segmentation.

Pelvic floor muscle exercises utilizing trunk stabilization for treating postpartum urinary incontinence: randomized controlled pilot trial of supervised versus unsupervised training.

PubMed

Kim, Eun-Young; Kim, Suhn-Yeop; Oh, Duck-Won

2012-02-01

To investigate the effect of supervised and unsupervised pelvic floor muscle exercises utilizing trunk stabilization for treating postpartum urinary incontinence and to compare the outcomes. Randomized, single-blind controlled study. Outpatient rehabilitation hospital. Eighteen subjects with postpartum urinary incontinence. Subjects were randomized to either a supervised training group with verbal instruction from a physiotherapist, or an unsupervised training group after undergoing a supervised demonstration session. Bristol Female Lower Urinary Tract Symptom questionnaire (urinary symptoms and quality of life) and vaginal function test (maximal vaginal squeeze pressure and holding time) using a perineometer. The change values for urinary symptoms (-27.22 ± 6.20 versus -18.22 ± 5.49), quality of life (-5.33 ± 2.96 versus -1.78 ± 3.93), total score (-32.56 ± 8.17 versus -20.00 ± 6.67), maximal vaginal squeeze pressure (18.96 ± 9.08 versus 2.67 ± 3.64 mmHg), and holding time (11.32 ± 3.17 versus 5.72 ± 2.29 seconds) were more improved in the supervised group than in the unsupervised group (P < 0.05). In the supervised group, significant differences were found for all variables between pre- and post-test values (P < 0.01), whereas the unsupervised group showed significant differences for urinary symptom score, total score and holding time between the pre- and post-test results (P < 0.05). These findings suggest that exercising the pelvic floor muscles by utilizing trunk stabilization under physiotherapist supervision may be beneficial for the management of postpartum urinary incontinence.

Hyperspectral Imaging Using Flexible Endoscopy for Laryngeal Cancer Detection

PubMed Central

Regeling, Bianca; Thies, Boris; Gerstner, Andreas O. H.; Westermann, Stephan; Müller, Nina A.; Bendix, Jörg; Laffers, Wiebke

2016-01-01

Hyperspectral imaging (HSI) is increasingly gaining acceptance in the medical field. Up until now, HSI has been used in conjunction with rigid endoscopy to detect cancer in vivo. The logical next step is to pair HSI with flexible endoscopy, since it improves access to hard-to-reach areas. While the flexible endoscope’s fiber optic cables provide the advantage of flexibility, they also introduce an interfering honeycomb-like pattern onto images. Due to the substantial impact this pattern has on locating cancerous tissue, it must be removed before the HS data can be further processed. Thereby, the loss of information is to minimize avoiding the suppression of small-area variations of pixel values. We have developed a system that uses flexible endoscopy to record HS cubes of the larynx and designed a special filtering technique to remove the honeycomb-like pattern with minimal loss of information. We have confirmed its feasibility by comparing it to conventional filtering techniques using an objective metric and by applying unsupervised and supervised classifications to raw and pre-processed HS cubes. Compared to conventional techniques, our method successfully removes the honeycomb-like pattern and considerably improves classification performance, while preserving image details. PMID:27529255

User Activity Recognition in Smart Homes Using Pattern Clustering Applied to Temporal ANN Algorithm

PubMed Central

Bourobou, Serge Thomas Mickala; Yoo, Younghwan

2015-01-01

This paper discusses the possibility of recognizing and predicting user activities in the IoT (Internet of Things) based smart environment. The activity recognition is usually done through two steps: activity pattern clustering and activity type decision. Although many related works have been suggested, they had some limited performance because they focused only on one part between the two steps. This paper tries to find the best combination of a pattern clustering method and an activity decision algorithm among various existing works. For the first step, in order to classify so varied and complex user activities, we use a relevant and efficient unsupervised learning method called the K-pattern clustering algorithm. In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen’s temporal relations. The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms. Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home. PMID:26007738

Image-based spectroscopy for environmental monitoring

NASA Astrophysics Data System (ADS)

Bachmakov, Eduard; Molina, Carolyn; Wynne, Rosalind

2014-03-01

An image-processing algorithm for use with a nano-featured spectrometer chemical agent detection configuration is presented. The spectrometer chip acquired from Nano-Optic DevicesTM can reduce the size of the spectrometer down to a coin. The nanospectrometer chip was aligned with a 635nm laser source, objective lenses, and a CCD camera. The images from a nanospectrometer chip were collected and compared to reference spectra. Random background noise contributions were isolated and removed from the diffraction pattern image analysis via a threshold filter. Results are provided for the image-based detection of the diffraction pattern produced by the nanospectrometer. The featured PCF spectrometer has the potential to measure optical absorption spectra in order to detect trace amounts of contaminants. MATLAB tools allow for implementation of intelligent, automatic detection of the relevant sub-patterns in the diffraction patterns and subsequent extraction of the parameters using region-detection algorithms such as the generalized Hough transform, which detects specific shapes within the image. This transform is a method for detecting curves by exploiting the duality between points on a curve and parameters of that curve. By employing this imageprocessing technique, future sensor systems will benefit from new applications such as unsupervised environmental monitoring of air or water quality.

Hyperspectral Imaging Using Flexible Endoscopy for Laryngeal Cancer Detection.

PubMed

Regeling, Bianca; Thies, Boris; Gerstner, Andreas O H; Westermann, Stephan; Müller, Nina A; Bendix, Jörg; Laffers, Wiebke

2016-08-13

Hyperspectral imaging (HSI) is increasingly gaining acceptance in the medical field. Up until now, HSI has been used in conjunction with rigid endoscopy to detect cancer in vivo. The logical next step is to pair HSI with flexible endoscopy, since it improves access to hard-to-reach areas. While the flexible endoscope's fiber optic cables provide the advantage of flexibility, they also introduce an interfering honeycomb-like pattern onto images. Due to the substantial impact this pattern has on locating cancerous tissue, it must be removed before the HS data can be further processed. Thereby, the loss of information is to minimize avoiding the suppression of small-area variations of pixel values. We have developed a system that uses flexible endoscopy to record HS cubes of the larynx and designed a special filtering technique to remove the honeycomb-like pattern with minimal loss of information. We have confirmed its feasibility by comparing it to conventional filtering techniques using an objective metric and by applying unsupervised and supervised classifications to raw and pre-processed HS cubes. Compared to conventional techniques, our method successfully removes the honeycomb-like pattern and considerably improves classification performance, while preserving image details.

Unsupervised Ensemble Anomaly Detection Using Time-Periodic Packet Sampling

NASA Astrophysics Data System (ADS)

Uchida, Masato; Nawata, Shuichi; Gu, Yu; Tsuru, Masato; Oie, Yuji

We propose an anomaly detection method for finding patterns in network traffic that do not conform to legitimate (i.e., normal) behavior. The proposed method trains a baseline model describing the normal behavior of network traffic without using manually labeled traffic data. The trained baseline model is used as the basis for comparison with the audit network traffic. This anomaly detection works in an unsupervised manner through the use of time-periodic packet sampling, which is used in a manner that differs from its intended purpose — the lossy nature of packet sampling is used to extract normal packets from the unlabeled original traffic data. Evaluation using actual traffic traces showed that the proposed method has false positive and false negative rates in the detection of anomalies regarding TCP SYN packets comparable to those of a conventional method that uses manually labeled traffic data to train the baseline model. Performance variation due to the probabilistic nature of sampled traffic data is mitigated by using ensemble anomaly detection that collectively exploits multiple baseline models in parallel. Alarm sensitivity is adjusted for the intended use by using maximum- and minimum-based anomaly detection that effectively take advantage of the performance variations among the multiple baseline models. Testing using actual traffic traces showed that the proposed anomaly detection method performs as well as one using manually labeled traffic data and better than one using randomly sampled (unlabeled) traffic data.

Visualization of multiple influences on ocellar flight control in giant honeybees with the data-mining tool Viscovery SOMine.

PubMed

Kastberger, G; Kranner, G

2000-02-01

Viscovery SOMine is a software tool for advanced analysis and monitoring of numerical data sets. It was developed for professional use in business, industry, and science and to support dependency analysis, deviation detection, unsupervised clustering, nonlinear regression, data association, pattern recognition, and animated monitoring. Based on the concept of self-organizing maps (SOMs), it employs a robust variant of unsupervised neural networks--namely, Kohonen's Batch-SOM, which is further enhanced with a new scaling technique for speeding up the learning process. This tool provides a powerful means by which to analyze complex data sets without prior statistical knowledge. The data representation contained in the trained SOM is systematically converted to be used in a spectrum of visualization techniques, such as evaluating dependencies between components, investigating geometric properties of the data distribution, searching for clusters, or monitoring new data. We have used this software tool to analyze and visualize multiple influences of the ocellar system on free-flight behavior in giant honeybees. Occlusion of ocelli will affect orienting reactivities in relation to flight target, level of disturbance, and position of the bee in the flight chamber; it will induce phototaxis and make orienting imprecise and dependent on motivational settings. Ocelli permit the adjustment of orienting strategies to environmental demands by enforcing abilities such as centering or flight kinetics and by providing independent control of posture and flight course.

Improved regional-scale Brazilian cropping systems' mapping based on a semi-automatic object-based clustering approach

NASA Astrophysics Data System (ADS)

Bellón, Beatriz; Bégué, Agnès; Lo Seen, Danny; Lebourgeois, Valentine; Evangelista, Balbino Antônio; Simões, Margareth; Demonte Ferraz, Rodrigo Peçanha

2018-06-01

Cropping systems' maps at fine scale over large areas provide key information for further agricultural production and environmental impact assessments, and thus represent a valuable tool for effective land-use planning. There is, therefore, a growing interest in mapping cropping systems in an operational manner over large areas, and remote sensing approaches based on vegetation index time series analysis have proven to be an efficient tool. However, supervised pixel-based approaches are commonly adopted, requiring resource consuming field campaigns to gather training data. In this paper, we present a new object-based unsupervised classification approach tested on an annual MODIS 16-day composite Normalized Difference Vegetation Index time series and a Landsat 8 mosaic of the State of Tocantins, Brazil, for the 2014-2015 growing season. Two variants of the approach are compared: an hyperclustering approach, and a landscape-clustering approach involving a previous stratification of the study area into landscape units on which the clustering is then performed. The main cropping systems of Tocantins, characterized by the crop types and cropping patterns, were efficiently mapped with the landscape-clustering approach. Results show that stratification prior to clustering significantly improves the classification accuracies for underrepresented and sparsely distributed cropping systems. This study illustrates the potential of unsupervised classification for large area cropping systems' mapping and contributes to the development of generic tools for supporting large-scale agricultural monitoring across regions.

Hanging out with Which Friends? Friendship-Level Predictors of Unstructured and Unsupervised Socializing in Adolescence

ERIC Educational Resources Information Center

Siennick, Sonja E.; Osgood, D. Wayne

2012-01-01

Companions are central to explanations of the risky nature of unstructured and unsupervised socializing, yet we know little about whom adolescents are with when hanging out. We examine predictors of how often friendship dyads hang out via multilevel analyses of longitudinal friendship-level data on over 5,000 middle schoolers. Adolescents hang out…

Teacher and learner: Supervised and unsupervised learning in communities.

PubMed

Shafto, Michael G; Seifert, Colleen M

2015-01-01

How far can teaching methods go to enhance learning? Optimal methods of teaching have been considered in research on supervised and unsupervised learning. Locally optimal methods are usually hybrids of teaching and self-directed approaches. The costs and benefits of specific methods have been shown to depend on the structure of the learning task, the learners, the teachers, and the environment.

Unsupervised hierarchical partitioning of hyperspectral images: application to marine algae identification

NASA Astrophysics Data System (ADS)

Chen, B.; Chehdi, K.; De Oliveria, E.; Cariou, C.; Charbonnier, B.

2015-10-01

In this paper a new unsupervised top-down hierarchical classification method to partition airborne hyperspectral images is proposed. The unsupervised approach is preferred because the difficulty of area access and the human and financial resources required to obtain ground truth data, constitute serious handicaps especially over large areas which can be covered by airborne or satellite images. The developed classification approach allows i) a successive partitioning of data into several levels or partitions in which the main classes are first identified, ii) an estimation of the number of classes automatically at each level without any end user help, iii) a nonsystematic subdivision of all classes of a partition Pj to form a partition Pj+1, iv) a stable partitioning result of the same data set from one run of the method to another. The proposed approach was validated on synthetic and real hyperspectral images related to the identification of several marine algae species. In addition to highly accurate and consistent results (correct classification rate over 99%), this approach is completely unsupervised. It estimates at each level, the optimal number of classes and the final partition without any end user intervention.

Unsupervised learning of discriminative edge measures for vehicle matching between nonoverlapping cameras.

PubMed

Shan, Ying; Sawhney, Harpreet S; Kumar, Rakesh

2008-04-01

This paper proposes a novel unsupervised algorithm learning discriminative features in the context of matching road vehicles between two non-overlapping cameras. The matching problem is formulated as a same-different classification problem, which aims to compute the probability of vehicle images from two distinct cameras being from the same vehicle or different vehicle(s). We employ a novel measurement vector that consists of three independent edge-based measures and their associated robust measures computed from a pair of aligned vehicle edge maps. The weight of each measure is determined by an unsupervised learning algorithm that optimally separates the same-different classes in the combined measurement space. This is achieved with a weak classification algorithm that automatically collects representative samples from same-different classes, followed by a more discriminative classifier based on Fisher' s Linear Discriminants and Gibbs Sampling. The robustness of the match measures and the use of unsupervised discriminant analysis in the classification ensures that the proposed method performs consistently in the presence of missing/false features, temporally and spatially changing illumination conditions, and systematic misalignment caused by different camera configurations. Extensive experiments based on real data of over 200 vehicles at different times of day demonstrate promising results.

Learning representation hierarchies by sharing visual features: a computational investigation of Persian character recognition with unsupervised deep learning.

PubMed

Sadeghi, Zahra; Testolin, Alberto

2017-08-01

In humans, efficient recognition of written symbols is thought to rely on a hierarchical processing system, where simple features are progressively combined into more abstract, high-level representations. Here, we present a computational model of Persian character recognition based on deep belief networks, where increasingly more complex visual features emerge in a completely unsupervised manner by fitting a hierarchical generative model to the sensory data. Crucially, high-level internal representations emerging from unsupervised deep learning can be easily read out by a linear classifier, achieving state-of-the-art recognition accuracy. Furthermore, we tested the hypothesis that handwritten digits and letters share many common visual features: A generative model that captures the statistical structure of the letters distribution should therefore also support the recognition of written digits. To this aim, deep networks trained on Persian letters were used to build high-level representations of Persian digits, which were indeed read out with high accuracy. Our simulations show that complex visual features, such as those mediating the identification of Persian symbols, can emerge from unsupervised learning in multilayered neural networks and can support knowledge transfer across related domains.

Penalized unsupervised learning with outliers

PubMed Central

Witten, Daniela M.

2013-01-01

We consider the problem of performing unsupervised learning in the presence of outliers – that is, observations that do not come from the same distribution as the rest of the data. It is known that in this setting, standard approaches for unsupervised learning can yield unsatisfactory results. For instance, in the presence of severe outliers, K-means clustering will often assign each outlier to its own cluster, or alternatively may yield distorted clusters in order to accommodate the outliers. In this paper, we take a new approach to extending existing unsupervised learning techniques to accommodate outliers. Our approach is an extension of a recent proposal for outlier detection in the regression setting. We allow each observation to take on an “error” term, and we penalize the errors using a group lasso penalty in order to encourage most of the observations’ errors to exactly equal zero. We show that this approach can be used in order to develop extensions of K-means clustering and principal components analysis that result in accurate outlier detection, as well as improved performance in the presence of outliers. These methods are illustrated in a simulation study and on two gene expression data sets, and connections with M-estimation are explored. PMID:23875057

A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data.

PubMed

Goldstein, Markus; Uchida, Seiichi

2016-01-01

Anomaly detection is the process of identifying unexpected items or events in datasets, which differ from the norm. In contrast to standard classification tasks, anomaly detection is often applied on unlabeled data, taking only the internal structure of the dataset into account. This challenge is known as unsupervised anomaly detection and is addressed in many practical applications, for example in network intrusion detection, fraud detection as well as in the life science and medical domain. Dozens of algorithms have been proposed in this area, but unfortunately the research community still lacks a comparative universal evaluation as well as common publicly available datasets. These shortcomings are addressed in this study, where 19 different unsupervised anomaly detection algorithms are evaluated on 10 different datasets from multiple application domains. By publishing the source code and the datasets, this paper aims to be a new well-funded basis for unsupervised anomaly detection research. Additionally, this evaluation reveals the strengths and weaknesses of the different approaches for the first time. Besides the anomaly detection performance, computational effort, the impact of parameter settings as well as the global/local anomaly detection behavior is outlined. As a conclusion, we give an advise on algorithm selection for typical real-world tasks.

Unsupervised categorization with individuals diagnosed as having moderate traumatic brain injury: Over-selective responding.

PubMed

Edwards, Darren J; Wood, Rodger

2016-01-01

This study explored over-selectivity (executive dysfunction) using a standard unsupervised categorization task. Over-selectivity has been demonstrated using supervised categorization procedures (where training is given); however, little has been done in the way of unsupervised categorization (without training). A standard unsupervised categorization task was used to assess levels of over-selectivity in a traumatic brain injury (TBI) population. Individuals with TBI were selected from the Tertiary Traumatic Brain Injury Clinic at Swansea University and were asked to categorize two-dimensional items (pictures on cards), into groups that they felt were most intuitive, and without any learning (feedback from experimenter). This was compared against categories made by a control group for the same task. The findings of this study demonstrate that individuals with TBI had deficits for both easy and difficult categorization sets, as indicated by a larger amount of one-dimensional sorting compared to control participants. Deficits were significantly greater for the easy condition. The implications of these findings are discussed in the context of over-selectivity, and the processes that underlie this deficit. Also, the implications for using this procedure as a screening measure for over-selectivity in TBI are discussed.

Accuracy of latent-variable estimation in Bayesian semi-supervised learning.

PubMed

Yamazaki, Keisuke

2015-09-01

Hierarchical probabilistic models, such as Gaussian mixture models, are widely used for unsupervised learning tasks. These models consist of observable and latent variables, which represent the observable data and the underlying data-generation process, respectively. Unsupervised learning tasks, such as cluster analysis, are regarded as estimations of latent variables based on the observable ones. The estimation of latent variables in semi-supervised learning, where some labels are observed, will be more precise than that in unsupervised, and one of the concerns is to clarify the effect of the labeled data. However, there has not been sufficient theoretical analysis of the accuracy of the estimation of latent variables. In a previous study, a distribution-based error function was formulated, and its asymptotic form was calculated for unsupervised learning with generative models. It has been shown that, for the estimation of latent variables, the Bayes method is more accurate than the maximum-likelihood method. The present paper reveals the asymptotic forms of the error function in Bayesian semi-supervised learning for both discriminative and generative models. The results show that the generative model, which uses all of the given data, performs better when the model is well specified. Copyright © 2015 Elsevier Ltd. All rights reserved.

Segmentation of fluorescence microscopy cell images using unsupervised mining.

PubMed

Du, Xian; Dua, Sumeet

2010-05-28

The accurate measurement of cell and nuclei contours are critical for the sensitive and specific detection of changes in normal cells in several medical informatics disciplines. Within microscopy, this task is facilitated using fluorescence cell stains, and segmentation is often the first step in such approaches. Due to the complex nature of cell issues and problems inherent to microscopy, unsupervised mining approaches of clustering can be incorporated in the segmentation of cells. In this study, we have developed and evaluated the performance of multiple unsupervised data mining techniques in cell image segmentation. We adapt four distinctive, yet complementary, methods for unsupervised learning, including those based on k-means clustering, EM, Otsu's threshold, and GMAC. Validation measures are defined, and the performance of the techniques is evaluated both quantitatively and qualitatively using synthetic and recently published real data. Experimental results demonstrate that k-means, Otsu's threshold, and GMAC perform similarly, and have more precise segmentation results than EM. We report that EM has higher recall values and lower precision results from under-segmentation due to its Gaussian model assumption. We also demonstrate that these methods need spatial information to segment complex real cell images with a high degree of efficacy, as expected in many medical informatics applications.

Effects of Supervised vs. Unsupervised Training Programs on Balance and Muscle Strength in Older Adults: A Systematic Review and Meta-Analysis.

PubMed

Lacroix, André; Hortobágyi, Tibor; Beurskens, Rainer; Granacher, Urs

2017-11-01

Balance and resistance training can improve healthy older adults' balance and muscle strength. Delivering such exercise programs at home without supervision may facilitate participation for older adults because they do not have to leave their homes. To date, no systematic literature analysis has been conducted to determine if supervision affects the effectiveness of these programs to improve healthy older adults' balance and muscle strength/power. The objective of this systematic review and meta-analysis was to quantify the effectiveness of supervised vs. unsupervised balance and/or resistance training programs on measures of balance and muscle strength/power in healthy older adults. In addition, the impact of supervision on training-induced adaptive processes was evaluated in the form of dose-response relationships by analyzing randomized controlled trials that compared supervised with unsupervised trials. A computerized systematic literature search was performed in the electronic databases PubMed, Web of Science, and SportDiscus to detect articles examining the role of supervision in balance and/or resistance training in older adults. The initially identified 6041 articles were systematically screened. Studies were included if they examined balance and/or resistance training in adults aged ≥65 years with no relevant diseases and registered at least one behavioral balance (e.g., time during single leg stance) and/or muscle strength/power outcome (e.g., time for 5-Times-Chair-Rise-Test). Finally, 11 studies were eligible for inclusion in this meta-analysis. Weighted mean standardized mean differences between subjects (SMD bs ) of supervised vs. unsupervised balance/resistance training studies were calculated. The included studies were coded for the following variables: number of participants, sex, age, number and type of interventions, type of balance/strength tests, and change (%) from pre- to post-intervention values. Additionally, we coded training according to the following modalities: period, frequency, volume, modalities of supervision (i.e., number of supervised/unsupervised sessions within the supervised or unsupervised training groups, respectively). Heterogeneity was computed using I 2 and χ 2 statistics. The methodological quality of the included studies was evaluated using the Physiotherapy Evidence Database scale. Our analyses revealed that in older adults, supervised balance/resistance training was superior compared with unsupervised balance/resistance training in improving measures of static steady-state balance (mean SMD bs  = 0.28, p = 0.39), dynamic steady-state balance (mean SMD bs  = 0.35, p = 0.02), proactive balance (mean SMD bs  = 0.24, p = 0.05), balance test batteries (mean SMD bs  = 0.53, p = 0.02), and measures of muscle strength/power (mean SMD bs  = 0.51, p = 0.04). Regarding the examined dose-response relationships, our analyses showed that a number of 10-29 additional supervised sessions in the supervised training groups compared with the unsupervised training groups resulted in the largest effects for static steady-state balance (mean SMD bs  = 0.35), dynamic steady-state balance (mean SMD bs  = 0.37), and muscle strength/power (mean SMD bs  = 1.12). Further, ≥30 additional supervised sessions in the supervised training groups were needed to produce the largest effects on proactive balance (mean SMD bs  = 0.30) and balance test batteries (mean SMD bs  = 0.77). Effects in favor of supervised programs were larger for studies that did not include any supervised sessions in their unsupervised programs (mean SMD bs : 0.28-1.24) compared with studies that implemented a few supervised sessions in their unsupervised programs (e.g., three supervised sessions throughout the entire intervention program; SMD bs : -0.06 to 0.41). The present findings have to be interpreted with caution because of the low number of eligible studies and the moderate methodological quality of the included studies, which is indicated by a median Physiotherapy Evidence Database scale score of 5. Furthermore, we indirectly compared dose-response relationships across studies and not from single controlled studies. Our analyses suggest that supervised balance and/or resistance training improved measures of balance and muscle strength/power to a greater extent than unsupervised programs in older adults. Owing to the small number of available studies, we were unable to establish a clear dose-response relationship with regard to the impact of supervision. However, the positive effects of supervised training are particularly prominent when compared with completely unsupervised training programs. It is therefore recommended to include supervised sessions (i.e., two out of three sessions/week) in balance/resistance training programs to effectively improve balance and muscle strength/power in older adults.

An image analysis of TLC patterns for quality control of saffron based on soil salinity effect: A strategy for data (pre)-processing.

PubMed

Sereshti, Hassan; Poursorkh, Zahra; Aliakbarzadeh, Ghazaleh; Zarre, Shahin; Ataolahi, Sahar

2018-01-15

Quality of saffron, a valuable food additive, could considerably affect the consumers' health. In this work, a novel preprocessing strategy for image analysis of saffron thin layer chromatographic (TLC) patterns was introduced. This includes performing a series of image pre-processing techniques on TLC images such as compression, inversion, elimination of general baseline (using asymmetric least squares (AsLS)), removing spots shift and concavity (by correlation optimization warping (COW)), and finally conversion to RGB chromatograms. Subsequently, an unsupervised multivariate data analysis including principal component analysis (PCA) and k-means clustering was utilized to investigate the soil salinity effect, as a cultivation parameter, on saffron TLC patterns. This method was used as a rapid and simple technique to obtain the chemical fingerprints of saffron TLC images. Finally, the separated TLC spots were chemically identified using high-performance liquid chromatography-diode array detection (HPLC-DAD). Accordingly, the saffron quality from different areas of Iran was evaluated and classified. Copyright © 2017 Elsevier Ltd. All rights reserved.

A New MI-Based Visualization Aided Validation Index for Mining Big Longitudinal Web Trial Data

PubMed Central

Zhang, Zhaoyang; Fang, Hua; Wang, Honggang

2016-01-01

Web-delivered clinical trials generate big complex data. To help untangle the heterogeneity of treatment effects, unsupervised learning methods have been widely applied. However, identifying valid patterns is a priority but challenging issue for these methods. This paper, built upon our previous research on multiple imputation (MI)-based fuzzy clustering and validation, proposes a new MI-based Visualization-aided validation index (MIVOOS) to determine the optimal number of clusters for big incomplete longitudinal Web-trial data with inflated zeros. Different from a recently developed fuzzy clustering validation index, MIVOOS uses a more suitable overlap and separation measures for Web-trial data but does not depend on the choice of fuzzifiers as the widely used Xie and Beni (XB) index. Through optimizing the view angles of 3-D projections using Sammon mapping, the optimal 2-D projection-guided MIVOOS is obtained to better visualize and verify the patterns in conjunction with trajectory patterns. Compared with XB and VOS, our newly proposed MIVOOS shows its robustness in validating big Web-trial data under different missing data mechanisms using real and simulated Web-trial data. PMID:27482473

Heterogeneous patterns of brain atrophy in Alzheimer's disease.

PubMed

Poulakis, Konstantinos; Pereira, Joana B; Mecocci, Patrizia; Vellas, Bruno; Tsolaki, Magda; Kłoszewska, Iwona; Soininen, Hilkka; Lovestone, Simon; Simmons, Andrew; Wahlund, Lars-Olof; Westman, Eric

2018-05-01

There is increasing evidence showing that brain atrophy varies between patients with Alzheimer's disease (AD), suggesting that different anatomical patterns might exist within the same disorder. We investigated AD heterogeneity based on cortical and subcortical atrophy patterns in 299 AD subjects from 2 multicenter cohorts. Clusters of patients and important discriminative features were determined using random forest pairwise similarity, multidimensional scaling, and distance-based hierarchical clustering. We discovered 2 typical (72.2%) and 3 atypical (28.8%) subtypes with significantly different demographic, clinical, and cognitive characteristics, and different rates of cognitive decline. In contrast to previous studies, our unsupervised random forest approach based on cortical and subcortical volume measures and their linear and nonlinear interactions revealed more typical AD subtypes with important anatomically discriminative features, while the prevalence of atypical cases was lower. The hippocampal-sparing and typical AD subtypes exhibited worse clinical progression in visuospatial, memory, and executive cognitive functions. Our findings suggest there is substantial heterogeneity in AD that has an impact on how patients function and progress over time. Copyright © 2018 Elsevier Inc. All rights reserved.

Examining unsupervised time with peers and the role of association with delinquent peers on adolescent smoking.

PubMed

Greene, Kathryn; Banerjee, Smita C

2009-04-01

This study explored the association between unsupervised time with peers and adolescent smoking behavior both directly and indirectly through interaction with delinquent peers, social expectancies about cigarette smoking, and cigarette offers from peers. A cross-sectional survey was used for the study and included 248 male and female middle school students. Results of structural equation modeling revealed that unsupervised time with peers is associated indirectly with adolescent smoking behavior through the mediation of association with delinquent peers, social expectancies about cigarette smoking, and cigarette offers from peers. Interventions designed to motivate adolescents without adult supervision to associate more with friends who engage in prosocial activities may eventually reduce adolescent smoking. Further implications for structured supervised time for students outside of school time are discussed.

A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain

NASA Technical Reports Server (NTRS)

Hall, Lawrence O.; Bensaid, Amine M.; Clarke, Laurence P.; Velthuizen, Robert P.; Silbiger, Martin S.; Bezdek, James C.

1992-01-01

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms and a supervised computational neural network, a dynamic multilayered perception trained with the cascade correlation learning algorithm. Initial clinical results are presented on both normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. However, for a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed.

Pile mixing increases greenhouse gas emissions during composting of dairy manure

USDA-ARS?s Scientific Manuscript database

The effect of pile mixing on greenhouse gas (GHG) emissions from stored dairy manure was determined using large flux chambers designed to completely cover pilot-scale manure piles. GHG emissions from piles that were mixed four times during the 80 day trial were about 20% higher than unmixed piles. ...

SOURCE APPORTIONMENT OF PM2.5 AT AN URBAN IMPROVE SITE IN SEATTLE, WA

EPA Science Inventory

The multivariate receptor models Positive Matrix Factorization (PMF) and Unmix were used along with EPA's Chemical Mass Balance model to deduce the sources of PM2.5 at a centrally located urban site in Seattle, Washington. A total of 289 filter samples were obtained with an IM...

SOURCE APPORTIONMENT OF SEATTLE PM 2.5: A COMPARISON OF IMPROVE AND ENHANCED STN DATA SETS

EPA Science Inventory

Seattle, WA, STN and IMPROVE data sets with STN temperature resolved carbon peaks were analyzed with both the PMF and Unmix receptor models. In addition, the IMPROVE trace element data was combined with the major STN species to examine the role of IMPROVE metals. To compare the ...

Postfire soil burn severity mapping with hyperspectral image unmixing

Treesearch

Peter R. Robichaud; Sarah A. Lewis; Denise Y. M. Laes; Andrew T. Hudak; Raymond F. Kokaly; Joseph A. Zamudio

2007-01-01

Burn severity is mapped after wildfires to evaluate immediate and long-term fire effects on the landscape. Remotely sensed hyperspectral imagery has the potential to provide important information about fine-scale ground cover components that are indicative of burn severity after large wildland fires. Airborne hyperspectral imagery and ground data were collected after...

Estimating the formation age distribution of continental crust by unmixing zircon ages

NASA Astrophysics Data System (ADS)

Korenaga, Jun

2018-01-01

Continental crust provides first-order control on Earth's surface environment, enabling the presence of stable dry landmasses surrounded by deep oceans. The evolution of continental crust is important for atmospheric evolution, because continental crust is an essential component of deep carbon cycle and is likely to have played a critical role in the oxygenation of the atmosphere. Geochemical information stored in the mineral zircon, known for its resilience to diagenesis and metamorphism, has been central to ongoing debates on the genesis and evolution of continental crust. However, correction for crustal reworking, which is the most critical step when estimating original formation ages, has been incorrectly formulated, undermining the significance of previous estimates. Here I suggest a simple yet promising approach for reworking correction using the global compilation of zircon data. The present-day distribution of crustal formation age estimated by the new "unmixing" method serves as the lower bound to the true crustal growth, and large deviations from growth models based on mantle depletion imply the important role of crustal recycling through the Earth history.

Method for hyperspectral imagery exploitation and pixel spectral unmixing

NASA Technical Reports Server (NTRS)

Lin, Ching-Fang (Inventor)

2003-01-01

An efficiently hybrid approach to exploit hyperspectral imagery and unmix spectral pixels. This hybrid approach uses a genetic algorithm to solve the abundance vector for the first pixel of a hyperspectral image cube. This abundance vector is used as initial state in a robust filter to derive the abundance estimate for the next pixel. By using Kalman filter, the abundance estimate for a pixel can be obtained in one iteration procedure which is much fast than genetic algorithm. The output of the robust filter is fed to genetic algorithm again to derive accurate abundance estimate for the current pixel. The using of robust filter solution as starting point of the genetic algorithm speeds up the evolution of the genetic algorithm. After obtaining the accurate abundance estimate, the procedure goes to next pixel, and uses the output of genetic algorithm as the previous state estimate to derive abundance estimate for this pixel using robust filter. And again use the genetic algorithm to derive accurate abundance estimate efficiently based on the robust filter solution. This iteration continues until pixels in a hyperspectral image cube end.

Multispectral analysis tools can increase utility of RGB color images in histology

NASA Astrophysics Data System (ADS)

Fereidouni, Farzad; Griffin, Croix; Todd, Austin; Levenson, Richard

2018-04-01

Multispectral imaging (MSI) is increasingly finding application in the study and characterization of biological specimens. However, the methods typically used come with challenges on both the acquisition and the analysis front. MSI can be slow and photon-inefficient, leading to long imaging times and possible phototoxicity and photobleaching. The resulting datasets can be large and complex, prompting the development of a number of mathematical approaches for segmentation and signal unmixing. We show that under certain circumstances, just three spectral channels provided by standard color cameras, coupled with multispectral analysis tools, including a more recent spectral phasor approach, can efficiently provide useful insights. These findings are supported with a mathematical model relating spectral bandwidth and spectral channel number to achievable spectral accuracy. The utility of 3-band RGB and MSI analysis tools are demonstrated on images acquired using brightfield and fluorescence techniques, as well as a novel microscopy approach employing UV-surface excitation. Supervised linear unmixing, automated non-negative matrix factorization and phasor analysis tools all provide useful results, with phasors generating particularly helpful spectral display plots for sample exploration.

Endmember extraction from hyperspectral image based on discrete firefly algorithm (EE-DFA)

NASA Astrophysics Data System (ADS)

Zhang, Chengye; Qin, Qiming; Zhang, Tianyuan; Sun, Yuanheng; Chen, Chao

2017-04-01

This study proposed a novel method to extract endmembers from hyperspectral image based on discrete firefly algorithm (EE-DFA). Endmembers are the input of many spectral unmixing algorithms. Hence, in this paper, endmember extraction from hyperspectral image is regarded as a combinational optimization problem to get best spectral unmixing results, which can be solved by the discrete firefly algorithm. Two series of experiments were conducted on the synthetic hyperspectral datasets with different SNR and the AVIRIS Cuprite dataset, respectively. The experimental results were compared with the endmembers extracted by four popular methods: the sequential maximum angle convex cone (SMACC), N-FINDR, Vertex Component Analysis (VCA), and Minimum Volume Constrained Nonnegative Matrix Factorization (MVC-NMF). What's more, the effect of the parameters in the proposed method was tested on both synthetic hyperspectral datasets and AVIRIS Cuprite dataset, and the recommended parameters setting was proposed. The results in this study demonstrated that the proposed EE-DFA method showed better performance than the existing popular methods. Moreover, EE-DFA is robust under different SNR conditions.

Aliasing Signal Separation of Superimposed Abrasive Debris Based on Degenerate Unmixing Estimation Technique

PubMed Central

Li, Tongyang; Wang, Shaoping; Zio, Enrico; Shi, Jian; Hong, Wei

2018-01-01

Leakage is the most important failure mode in aircraft hydraulic systems caused by wear and tear between friction pairs of components. The accurate detection of abrasive debris can reveal the wear condition and predict a system’s lifespan. The radial magnetic field (RMF)-based debris detection method provides an online solution for monitoring the wear condition intuitively, which potentially enables a more accurate diagnosis and prognosis on the aviation hydraulic system’s ongoing failures. To address the serious mixing of pipe abrasive debris, this paper focuses on the superimposed abrasive debris separation of an RMF abrasive sensor based on the degenerate unmixing estimation technique. Through accurately separating and calculating the morphology and amount of the abrasive debris, the RMF-based abrasive sensor can provide the system with wear trend and sizes estimation of the wear particles. A well-designed experiment was conducted and the result shows that the proposed method can effectively separate the mixed debris and give an accurate count of the debris based on RMF abrasive sensor detection. PMID:29543733

Shallow sea-floor reflectance and water depth derived by unmixing multispectral imagery

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bierwirth, P.N.; Lee, T.J.; Burne, R.V.

1993-03-01

A major problem for mapping shallow water zones by the analysis of remotely sensed data is that contrast effects due to water depth obscure and distort the special nature of the substrate. This paper outlines a new method which unmixes the exponential influence of depth in each pixel by employing a mathematical constraint. This leaves a multispectral residual which represents relative substrate reflectance. Input to the process are the raw multispectral data and water attenuation coefficients derived by the co-analysis of known bathymetry and remotely sensed data. Outputs are substrate-reflectance images corresponding to the input bands and a greyscale depthmore » image. The method has been applied in the analysis of Landsat TM data at Hamelin Pool in Shark Bay, Western Australia. Algorithm derived substrate reflectance images for Landsat TM bands 1, 2, and 3 combined in color represent the optimum enhancement for mapping or classifying substrate types. As a result, this color image successfully delineated features, which were obscured in the raw data, such as the distributions of sea-grasses, microbial mats, and sandy area. 19 refs.« less

CHAMP: a locally adaptive unmixing-based hyperspectral anomaly detection algorithm

NASA Astrophysics Data System (ADS)

Crist, Eric P.; Thelen, Brian J.; Carrara, David A.

1998-10-01

Anomaly detection offers a means by which to identify potentially important objects in a scene without prior knowledge of their spectral signatures. As such, this approach is less sensitive to variations in target class composition, atmospheric and illumination conditions, and sensor gain settings than would be a spectral matched filter or similar algorithm. The best existing anomaly detectors generally fall into one of two categories: those based on local Gaussian statistics, and those based on linear mixing moles. Unmixing-based approaches better represent the real distribution of data in a scene, but are typically derived and applied on a global or scene-wide basis. Locally adaptive approaches allow detection of more subtle anomalies by accommodating the spatial non-homogeneity of background classes in a typical scene, but provide a poorer representation of the true underlying background distribution. The CHAMP algorithm combines the best attributes of both approaches, applying a linear-mixing model approach in a spatially adaptive manner. The algorithm itself, and teste results on simulated and actual hyperspectral image data, are presented in this paper.

High efficiency organic photovoltaic cells employing hybridized mixed-planar heterojunctions

DOEpatents

Xue, Jiangeng; Uchida, Soichi; Rand, Barry P.; Forrest, Stephen

2015-08-18

A device is provided, having a first electrode, a second electrode, and a photoactive region disposed between the first electrode and the second electrode. The photoactive region includes a first photoactive organic layer that is a mixture of an organic acceptor material and an organic donor material, wherein the first photoactive organic layer has a thickness not greater than 0.8 characteristic charge transport lengths; a second photoactive organic layer in direct contact with the first organic layer, wherein the second photoactive organic layer is an unmixed layer of the organic acceptor material of the first photoactive organic layer, and the second photoactive organic layer has a thickness not less than about 0.1 optical absorption lengths; and a third photoactive organic layer disposed between the first electrode and the second electrode and in direct contact with the first photoactive organic layer. The third photoactive organic layer is an unmixed layer of the organic donor layer of the first photoactive organic layer and has a thickness not less than about 0.1 optical absorption lengths.

Extracting Vegetation Coverage in Dry-hot Valley Regions Based on Alternating Angle Minimum Algorithm

NASA Astrophysics Data System (ADS)

Y Yang, M.; Wang, J.; Zhang, Q.

2017-07-01

Vegetation coverage is one of the most important indicators for ecological environment change, and is also an effective index for the assessment of land degradation and desertification. The dry-hot valley regions have sparse surface vegetation, and the spectral information about the vegetation in such regions usually has a weak representation in remote sensing, so there are considerable limitations for applying the commonly-used vegetation index method to calculate the vegetation coverage in the dry-hot valley regions. Therefore, in this paper, Alternating Angle Minimum (AAM) algorithm of deterministic model is adopted for selective endmember for pixel unmixing of MODIS image in order to extract the vegetation coverage, and accuracy test is carried out by the use of the Landsat TM image over the same period. As shown by the results, in the dry-hot valley regions with sparse vegetation, AAM model has a high unmixing accuracy, and the extracted vegetation coverage is close to the actual situation, so it is promising to apply the AAM model to the extraction of vegetation coverage in the dry-hot valley regions.

Adaptive fuzzy leader clustering of complex data sets in pattern recognition

NASA Technical Reports Server (NTRS)

Newton, Scott C.; Pemmaraju, Surya; Mitra, Sunanda

1992-01-01

A modular, unsupervised neural network architecture for clustering and classification of complex data sets is presented. The adaptive fuzzy leader clustering (AFLC) architecture is a hybrid neural-fuzzy system that learns on-line in a stable and efficient manner. The initial classification is performed in two stages: a simple competitive stage and a distance metric comparison stage. The cluster prototypes are then incrementally updated by relocating the centroid positions from fuzzy C-means system equations for the centroids and the membership values. The AFLC algorithm is applied to the Anderson Iris data and laser-luminescent fingerprint image data. It is concluded that the AFLC algorithm successfully classifies features extracted from real data, discrete or continuous.

An Introduction to Topic Modeling as an Unsupervised Machine Learning Way to Organize Text Information

ERIC Educational Resources Information Center

Snyder, Robin M.

2015-01-01

The field of topic modeling has become increasingly important over the past few years. Topic modeling is an unsupervised machine learning way to organize text (or image or DNA, etc.) information such that related pieces of text can be identified. This paper/session will present/discuss the current state of topic modeling, why it is important, and…

Post-Graduate Student Performance in "Supervised In-Class" vs. "Unsupervised Online" Multiple Choice Tests: Implications for Cheating and Test Security

ERIC Educational Resources Information Center

Ladyshewsky, Richard K.

2015-01-01

This research explores differences in multiple choice test (MCT) scores in a cohort of post-graduate students enrolled in a management and leadership course. A total of 250 students completed the MCT in either a supervised in-class paper and pencil test or an unsupervised online test. The only statistically significant difference between the nine…

Exploiting Secondary Sources for Unsupervised Record Linkage

DTIC Science & Technology

2004-01-01

paper, we present an extension to Apollo’s active learning component to Report Documentation Page Form ApprovedOMB No. 0704-0188 Public reporting...Sources address the issue of user involvement. Using secondary sources, a system can autonomously answer questions posed by its active learning component...over, we present how Apollo utilizes the identified sec- ondary sources in an unsupervised active learning pro- cess. Apollo’s learning algorithm

Comparing supervised and unsupervised multiresolution segmentation approaches for extracting buildings from very high resolution imagery.

PubMed

Belgiu, Mariana; Dr Guţ, Lucian

2014-10-01

Although multiresolution segmentation (MRS) is a powerful technique for dealing with very high resolution imagery, some of the image objects that it generates do not match the geometries of the target objects, which reduces the classification accuracy. MRS can, however, be guided to produce results that approach the desired object geometry using either supervised or unsupervised approaches. Although some studies have suggested that a supervised approach is preferable, there has been no comparative evaluation of these two approaches. Therefore, in this study, we have compared supervised and unsupervised approaches to MRS. One supervised and two unsupervised segmentation methods were tested on three areas using QuickBird and WorldView-2 satellite imagery. The results were assessed using both segmentation evaluation methods and an accuracy assessment of the resulting building classifications. Thus, differences in the geometries of the image objects and in the potential to achieve satisfactory thematic accuracies were evaluated. The two approaches yielded remarkably similar classification results, with overall accuracies ranging from 82% to 86%. The performance of one of the unsupervised methods was unexpectedly similar to that of the supervised method; they identified almost identical scale parameters as being optimal for segmenting buildings, resulting in very similar geometries for the resulting image objects. The second unsupervised method produced very different image objects from the supervised method, but their classification accuracies were still very similar. The latter result was unexpected because, contrary to previously published findings, it suggests a high degree of independence between the segmentation results and classification accuracy. The results of this study have two important implications. The first is that object-based image analysis can be automated without sacrificing classification accuracy, and the second is that the previously accepted idea that classification is dependent on segmentation is challenged by our unexpected results, casting doubt on the value of pursuing 'optimal segmentation'. Our results rather suggest that as long as under-segmentation remains at acceptable levels, imperfections in segmentation can be ruled out, so that a high level of classification accuracy can still be achieved.

Development of a risk-screening tool for cancer survivors to participate in unsupervised moderate- to vigorous-intensity exercise: results from a survey study.

PubMed

Brown, Justin C; Ko, Emily M; Schmitz, Kathryn H

2015-02-01

The health benefits of exercise increase in dose-response fashion among cancer survivors. However, it is unclear how to identify cancer survivors who may require a pre-exercise evaluation before they progress from the common recommendation of walking to unsupervised moderate- to vigorous-intensity exercise. To clarify how to identify cancer survivors who should undergo a pre-exercise evaluation before they progress from the common recommendation of walking to unsupervised moderate- to vigorous-intensity exercise. Electronic survey. Forty-seven (n = 47) experts in the field of exercise physiology, rehabilitation medicine, and cancer survivorship. Not applicable. We synthesized peer-reviewed guidelines for exercise and cancer survivorship and identified 82 health factors that may warrant a pre-exercise evaluation before a survivor engages in unsupervised moderate- to vigorous-intensity exercise. The 82 health factors were classified into 3 domains: (1) clinical health factors; (2) comorbidity and device health factors; and (3) medications. We surveyed a sample of experts asking them to identify which of the 82 health factors among cancer survivors would indicate the need for a pre-exercise evaluation before they engaged in moderate- to vigorous-intensity exercise. The response rate to our survey was 75% (n = 47). Across the 3 domains of health factors, acute symptoms, comorbidities, and medications related to cardiovascular disease were agreed on to indicate a pre-exercise evaluation for survivors before they engaged in unsupervised moderate- to vigorous-intensity exercise. Other health factors in the survey included hematologic, musculoskeletal, systemic, gastrointestinal, pulmonary, and neurological symptoms and comorbidities. Eighteen experts (38%) said it was difficult to provide absolute answers because no 2 patients are alike, and their decisions are made on a case-by-case basis. The results from this expert survey will help to identify which cancer survivors should undergo a pre-exercise evaluation before they engage in unsupervised moderate- to vigorous-intensity exercise. Copyright © 2015 American Academy of Physical Medicine and Rehabilitation. Published by Elsevier Inc. All rights reserved.

Chemical compositions and source identification of PM₂.₅ aerosols for estimation of a diesel source surrogate.

PubMed

Sahu, Manoranjan; Hu, Shaohua; Ryan, Patrick H; Le Masters, Grace; Grinshpun, Sergey A; Chow, Judith C; Biswas, Pratim

2011-06-01

Exposure to traffic-related pollution during childhood has been associated with asthma exacerbation, and asthma incidence. The objective of the Cincinnati Childhood Allergy and Air Pollution Study (CCAAPS) is to determine if the development of allergic and respiratory disease is associated with exposure to diesel engine exhaust particles. A detailed receptor model analyses was undertaken by applying positive matrix factorization (PMF) and UNMIX receptor models to two PM₂.₅ data sets: one consisting of two carbon fractions and the other of eight temperature-resolved carbon fractions. Based on the source profiles resolved from the analyses, markers of traffic-related air pollution were estimated: the elemental carbon attributed to traffic (ECAT) and elemental carbon attributed to diesel vehicle emission (ECAD). Application of UNMIX to the two data sets generated four source factors: combustion related sulfate, traffic, metal processing and soil/crustal. The PMF application generated six source factors derived from analyzing two carbon fractions and seven factors from temperature-resolved eight carbon fractions. The source factors (with source contribution estimates by mass concentrations in parentheses) are: combustion sulfate (46.8%), vegetative burning (15.8%), secondary sulfate (12.9%), diesel vehicle emission (10.9%), metal processing (7.5%), gasoline vehicle emission (5.6%) and soil/crustal (0.7%). Diesel and gasoline vehicle emission sources were separated using eight temperature-resolved organic and elemental carbon fractions. Application of PMF to both datasets also differentiated the sulfate rich source from the vegetative burning source, which are combined in a single factor by UNMIX modeling. Calculated ECAT and ECAD values at different locations indicated that traffic source impacts depend on factors such as traffic volumes, meteorological parameters, and the mode of vehicle operation apart from the proximity of the sites to highways. The difference in ECAT and ECAD, however, was less than one standard deviation. Thus, a cost benefit consideration should be used when deciding on the benefits of an eight or two carbon approach. Published by Elsevier B.V.

Spectral Unmixing Modeling of the Aristarchus Pyroclastic Deposit: Assessing the Eruptive History of Glass-Rich Regional Lunar Pyroclastic Deposits

NASA Astrophysics Data System (ADS)

Jawin, E. R.; Head, J. W., III; Cannon, K.

2017-12-01

The Aristarchus pyroclastic deposit in central Oceanus Procellarum is understood to have formed in a gas-rich explosive volcanic eruption, and has been observed to contain abundant volcanic glass. However, the interpreted color (and therefore composition) of the glass has been debated. In addition, previous analyses of the pyroclastic deposit have been performed using lower resolution data than are currently available. In this work, a nonlinear spectral unmixing model was applied to Moon Mineralogy Mapper (M3) data of the Aristarchus plateau to investigate the detailed mineralogic and crystalline nature of the Aristarchus pyroclastic deposit by using spectra of laboratory endmembers including a suite of volcanic glasses returned from the Apollo 15 and 17 missions (green, orange, black beads), as well as synthetic lunar glasses (orange, green, red, yellow). Preliminary results of the M3 unmixing model suggest that spectra of the pyroclastic deposit can be modeled by a mixture composed predominantly of a featureless endmember approximating space weathering and a smaller component of glass. The modeled spectra were most accurate with a synthetic orange glass endmember, relative to the other glasses analyzed in this work. The results confirm that there is a detectable component of glass in the Aristarchus pyroclastic deposit which may be similar to the high-Ti orange glass seen in other regional pyroclastic deposits, with only minimal contributions of other crystalline minerals. The presence of volcanic glass in the pyroclastic deposit, with the low abundance of crystalline material, would support the model that the Aristarchus pyroclastic deposit formed in a long-duration, hawaiian-style fire fountain eruption. No significant detection of devitrified black beads in the spectral modeling results (as was observed at the Apollo 17 landing site in the Taurus-Littrow pyroclastic deposit), suggests the optical density of the eruptive plume remained low throughout the eruption.

PM2.5 Source Apportionment: Reconciling Receptor Models for U.S. Nonurban and Urban Long-Term Networks.

PubMed

Chen, L-W Antony; Watson, John G; Chow, Judith C; DuBois, Dave W; Herschberger, Lisa

2011-11-01

Chemical mass balance (CMB) and trajectory receptor models were applied to speciated particulate matter with aerodynamic diameter ≤2.5 μm (PM 2.5 ) measurements from Speciation Trends Network (STN; part of the Chemical Speciation Network [CSN]) and Interagency Monitoring of Protected Visual Environments (IMPROVE) monitoring network across the state of Minnesota as part of the Minnesota PM 2.5 Source Apportionment Study (MPSAS). CMB equations were solved by the Unmix, positive matrix factorization (PMF), and effective variance (EV) methods, giving collective source contribution and uncertainty estimates. Geological source profiles developed from local dust materials were either incorporated into the EV-CMB model or used to verify factors derived from Unmix and PMF. Common sources include soil dust, calcium (Ca)-rich dust, diesel and gasoline vehicle exhausts, biomass burning, secondary sulfate, and secondary nitrate. Secondary sulfate and nitrate aerosols dominate PM 2.5 mass (50-69%). Mobile sources outweigh area sources at urban sites, and vice versa at rural sites due to traffic emissions. Gasoline and diesel contributions can be separated using data from the STN, despite significant uncertainties. Major differences between MPSAS and earlier studies on similar environments appear to be the type and magnitude of stationary sources, but these sources are generally minor (<7%) in this and other studies. Ensemble back-trajectory analysis shows that the lower Midwestern states are the predominant source region for secondary ammoniated sulfate in Minnesota. It also suggests substantial contributions of biomass burning and soil dust from out-of-state on occasions, although a quantitative separation of local and regional contributions was not achieved in the current study. Supplemental materials are available for this article. Go to the publisher's online edition of the Journal of the Air & Waste Management Association for a summary of input data, Unmix and PMF factor profiles, and additional maps. [Box: see text].

Is There a Paradox of Aging: When the Negative Aging Stereotype Meets the Positivity Effect in Older Adults.

PubMed

Zhou, Liqing; Lu, Jia; Chen, Guopeng; Dong, Li; Yao, Yujia

2017-01-01

Background/Study Context: Socioemotional selectivity theory (SST) states that the positivity effect is a result of older adults' emotion regulation and that older adults derive more emotional satisfaction from prioritizing positive information processing. The authors explored whether the positivity effect appeared when the negative aging stereotype was activated in older adults and also whether the effect differed between mixed and unmixed valence conditions. Sixty younger (18-23 years of age) and 60 older (60-87 years of age) adults were randomly assigned to a control group and a priming group, in which the negative aging stereotype was activated. All the participants were asked to select 15 words that best described the elderly from a mixed-word list (positive and negative words were mixed together) and from an unmixed-word list (positive and negative words were separated). Older adults in the control group selected more positive words, whereas among younger adults, selection did not differ by valence in either the mixed- or unmixed-word list conditions. There were no differences between the positive and negative word choices of the younger and older adults in the priming group. We calculated the differences between the numbers of positive and negative words, and the differences in the older adults' word choices were larger than those among the younger adults; the differences were also larger in the control group than in the priming group. The positivity effect worked by choosing positive stimuli rather than avoiding negative stimuli. The role of emotion regulation in older adults was limited, and when the positivity effect faced the effect of the negative aging stereotype, the negative stereotype effect was dominant. Future research should explore the changes in the positivity effect in the face of a positive aging stereotype and what roles other factors (e.g., activation level of the stereotype, arousal level of affective words) might play.

Detrital illite crystals identified from crystallite thickness measurements in siliciclastic sediments

USGS Publications Warehouse

Aldega, L.; Eberl, D.D.

2005-01-01

Illite crystals in siliciclastic sediments are heterogeneous assemblages of detrital material coming from various source rocks and, at paleotemperatures >70 ??C, of superimposed diagenetic modification in the parent sediment. We distinguished the relative proportions of 2M1 detrital illite and possible diagenetic 1Md + 1M illite by a combined analysis of crystal-size distribution and illite polytype quantification. We found that the proportions of 1Md + 1M and 2M1 illite could be determined from crystallite thickness measurements (BWA method, using the MudMaster program) by unmixing measured crystallite thickness distributions using theoretical and calculated log-normal and/or asymptotic distributions. The end-member components that we used to unmix the measured distributions were three asymptotic-shaped distributions (assumed to be the diagenetic component of the mixture, the 1Md + 1M polytypes) calculated using the Galoper program (Phase A was simulated using 500 crystals per cycle of nucleation and growth, Phase B = 333/cycle, and Phase C = 250/ cycle), and one theoretical log-normal distribution (Phase D, assumed to approximate the detrital 2M1 component of the mixture). In addition, quantitative polytype analysis was carried out using the RockJock software for comparison. The two techniques gave comparable results (r2 = 0.93), which indicates that the unmixing method permits one to calculate the proportion of illite polytypes and, therefore, the proportion of 2M1 detrital illite, from crystallite thickness measurements. The overall illite crystallite thicknesses in the samples were found to be a function of the relative proportions of thick 2M1 and thin 1Md + 1M illite. The percentage of illite layers in I-S mixed layers correlates with the mean crystallite thickness of the 1Md + 1M polytypes, indicating that these polytypes, rather than the 2M1 polytype, participate in I-S mixed layering.

Physical-biopolymer characterization of polyhydroxybutyrate-co-hydroxyvalerate (PHBV) blended with natural rubber latex

DOE Office of Scientific and Technical Information (OSTI.GOV)

Kuntanoo, K., E-mail: thip-kk@hotmail.com; Promkotra, S., E-mail: sarunya@kku.ac.th; Kaewkannetra, P., E-mail: paknar@kku.ac.th

A biopolymer of polyhydroxybutyrate-co-hydroxyvalerate (PHBV) is blended with bio-based materials, natural rubber latex, to improve their microstructures. The various ratios between PHBV and natural rubber latex are examined to develop their mechanical properties. In general, physical properties of PHBV are hard, brittle and low flexible while natural rubber (NR) is presented itself as high elastic materials. Concentrations of the PHBV solution are constituted at 1%, 2% and 3% (w/v). The mixtures of their PHBV solutions to natural rubber latex are produced the blended films in three different ratios of 4:6, 5:5 and 6:4, respectively. They are characterized by appearance analysesmore » which are the scanning electron microscope (SEM), universal testing machine (UTM) and differential scanning calorimetry (DSC). The SEM photomicrographs of the blended films and the controlled PHBV can provide the void distribution in the range of 12-14% and 19-21%, respectively. For mechanical properties of the blended films, the various elastic moduli of 1%, 2% and 3% (w/v) PHBV are the average of 773, 956 and 1,007 kPa, respectively. The tensile strengths of the blends increase with the increased concentrations of PHBV, similarly trend to the elastic modulus. The crystallization and melting behavior of unmixed PHBV and the blends are determined by DSC. Melting transition temperatures (T{sub m}) of the unmixed PHBV are stated two melting peak at 154°C and 173°C. Besides, the melting peaks of the blends alter in the range of 152-156°C and 168-171°C, respectively. According to morphology of the blends, the void distribution decreases twice compared to the unmixed PHBV. The results of mechanical properties and thermal analysis indicate that the blended PHBV can be developed their properties by more resilient and wide range of temperature than usual.« less

Arctic Tundra Vegetation Functional Types Based on Photosynthetic Physiology and Optical Properties

NASA Technical Reports Server (NTRS)

Huemmrich, Karl Fred; Gamon, John A.; Tweedie, Craig E.; Campbell, Petya K. Entcheva; Landis, David R.; Middleton, Elizabeth M.

2013-01-01

Non-vascular plants (lichens and mosses) are significant components of tundra landscapes and may respond to climate change differently from vascular plants affecting ecosystem carbon balance. Remote sensing provides critical tools for monitoring plant cover types, as optical signals provide a way to scale from plot measurements to regional estimates of biophysical properties, for which spatial-temporal patterns may be analyzed. Gas exchange measurements were collected for pure patches of key vegetation functional types (lichens, mosses, and vascular plants) in sedge tundra at Barrow, AK. These functional types were found to have three significantly different values of light use efficiency (LUE) with values of 0.013 plus or minus 0.0002, 0.0018 plus or minus 0.0002, and 0.0012 plus or minus 0.0001 mol C mol (exp -1) absorbed quanta for vascular plants, mosses and lichens, respectively. Discriminant analysis of the spectra reflectance of these patches identified five spectral bands that separated each of these vegetation functional types as well as nongreen material (bare soil, standing water, and dead leaves). These results were tested along a 100 m transect where midsummer spectral reflectance and vegetation coverage were measured at one meter intervals. Along the transect, area-averaged canopy LUE estimated from coverage fractions of the three functional types varied widely, even over short distances. The patch-level statistical discriminant functions applied to in situ hyperspectral reflectance data collected along the transect successfully unmixed cover fractions of the vegetation functional types. The unmixing functions, developed from the transect data, were applied to 30 m spatial resolution Earth Observing-1 Hyperion imaging spectrometer data to examine variability in distribution of the vegetation functional types for an area near Barrow, AK. Spatial variability of LUE was derived from the observed functional type distributions. Across this landscape, a fivefold variation in tundra LUE was observed. LUE calculated from the functional type cover fractions was also correlated to a spectral vegetation index developed to detect vegetation chlorophyll content. The concurrence of these alternate methods suggest that hyperspectral remote sensing can distinguish functionally distinct vegetation types and can be used to develop regional estimates of photosynthetic LUE in tundra landscapes.

Phonological Concept Learning.

PubMed

Moreton, Elliott; Pater, Joe; Pertsova, Katya

2017-01-01

Linguistic and non-linguistic pattern learning have been studied separately, but we argue for a comparative approach. Analogous inductive problems arise in phonological and visual pattern learning. Evidence from three experiments shows that human learners can solve them in analogous ways, and that human performance in both cases can be captured by the same models. We test GMECCS (Gradual Maximum Entropy with a Conjunctive Constraint Schema), an implementation of the Configural Cue Model (Gluck & Bower, ) in a Maximum Entropy phonotactic-learning framework (Goldwater & Johnson, ; Hayes & Wilson, ) with a single free parameter, against the alternative hypothesis that learners seek featurally simple algebraic rules ("rule-seeking"). We study the full typology of patterns introduced by Shepard, Hovland, and Jenkins () ("SHJ"), instantiated as both phonotactic patterns and visual analogs, using unsupervised training. Unlike SHJ, Experiments 1 and 2 found that both phonotactic and visual patterns that depended on fewer features could be more difficult than those that depended on more features, as predicted by GMECCS but not by rule-seeking. GMECCS also correctly predicted performance differences between stimulus subclasses within each pattern. A third experiment tried supervised training (which can facilitate rule-seeking in visual learning) to elicit simple rule-seeking phonotactic learning, but cue-based behavior persisted. We conclude that similar cue-based cognitive processes are available for phonological and visual concept learning, and hence that studying either kind of learning can lead to significant insights about the other. Copyright © 2015 Cognitive Science Society, Inc.

A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detection.

PubMed

Li, Jia; Xia, Changqun; Chen, Xiaowu

2017-10-12

Image-based salient object detection (SOD) has been extensively studied in past decades. However, video-based SOD is much less explored due to the lack of large-scale video datasets within which salient objects are unambiguously defined and annotated. Toward this end, this paper proposes a video-based SOD dataset that consists of 200 videos. In constructing the dataset, we manually annotate all objects and regions over 7,650 uniformly sampled keyframes and collect the eye-tracking data of 23 subjects who free-view all videos. From the user data, we find that salient objects in a video can be defined as objects that consistently pop-out throughout the video, and objects with such attributes can be unambiguously annotated by combining manually annotated object/region masks with eye-tracking data of multiple subjects. To the best of our knowledge, it is currently the largest dataset for videobased salient object detection. Based on this dataset, this paper proposes an unsupervised baseline approach for video-based SOD by using saliencyguided stacked autoencoders. In the proposed approach, multiple spatiotemporal saliency cues are first extracted at the pixel, superpixel and object levels. With these saliency cues, stacked autoencoders are constructed in an unsupervised manner that automatically infers a saliency score for each pixel by progressively encoding the high-dimensional saliency cues gathered from the pixel and its spatiotemporal neighbors. In experiments, the proposed unsupervised approach is compared with 31 state-of-the-art models on the proposed dataset and outperforms 30 of them, including 19 imagebased classic (unsupervised or non-deep learning) models, six image-based deep learning models, and five video-based unsupervised models. Moreover, benchmarking results show that the proposed dataset is very challenging and has the potential to boost the development of video-based SOD.

Automated Glioblastoma Segmentation Based on a Multiparametric Structured Unsupervised Classification

PubMed Central

Juan-Albarracín, Javier; Fuster-Garcia, Elies; Manjón, José V.; Robles, Montserrat; Aparici, F.; Martí-Bonmatí, L.; García-Gómez, Juan M.

2015-01-01

Automatic brain tumour segmentation has become a key component for the future of brain tumour treatment. Currently, most of brain tumour segmentation approaches arise from the supervised learning standpoint, which requires a labelled training dataset from which to infer the models of the classes. The performance of these models is directly determined by the size and quality of the training corpus, whose retrieval becomes a tedious and time-consuming task. On the other hand, unsupervised approaches avoid these limitations but often do not reach comparable results than the supervised methods. In this sense, we propose an automated unsupervised method for brain tumour segmentation based on anatomical Magnetic Resonance (MR) images. Four unsupervised classification algorithms, grouped by their structured or non-structured condition, were evaluated within our pipeline. Considering the non-structured algorithms, we evaluated K-means, Fuzzy K-means and Gaussian Mixture Model (GMM), whereas as structured classification algorithms we evaluated Gaussian Hidden Markov Random Field (GHMRF). An automated postprocess based on a statistical approach supported by tissue probability maps is proposed to automatically identify the tumour classes after the segmentations. We evaluated our brain tumour segmentation method with the public BRAin Tumor Segmentation (BRATS) 2013 Test and Leaderboard datasets. Our approach based on the GMM model improves the results obtained by most of the supervised methods evaluated with the Leaderboard set and reaches the second position in the ranking. Our variant based on the GHMRF achieves the first position in the Test ranking of the unsupervised approaches and the seventh position in the general Test ranking, which confirms the method as a viable alternative for brain tumour segmentation. PMID:25978453

Unsupervised frequency-recognition method of SSVEPs using a filter bank implementation of binary subband CCA.

PubMed

Rabiul Islam, Md; Khademul Islam Molla, Md; Nakanishi, Masaki; Tanaka, Toshihisa

2017-04-01

Recently developed effective methods for detection commands of steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) that need calibration for visual stimuli, which cause more time and fatigue prior to the use, as the number of commands increases. This paper develops a novel unsupervised method based on canonical correlation analysis (CCA) for accurate detection of stimulus frequency. A novel unsupervised technique termed as binary subband CCA (BsCCA) is implemented in a multiband approach to enhance the frequency recognition performance of SSVEP. In BsCCA, two subbands are used and a CCA-based correlation coefficient is computed for the individual subbands. In addition, a reduced set of artificial reference signals is used to calculate CCA for the second subband. The analyzing SSVEP is decomposed into multiple subband and the BsCCA is implemented for each one. Then, the overall recognition score is determined by a weighted sum of the canonical correlation coefficients obtained from each band. A 12-class SSVEP dataset (frequency range: 9.25-14.75 Hz with an interval of 0.5 Hz) for ten healthy subjects are used to evaluate the performance of the proposed method. The results suggest that BsCCA significantly improves the performance of SSVEP-based BCI compared to the state-of-the-art methods. The proposed method is an unsupervised approach with averaged information transfer rate (ITR) of 77.04 bits min -1 across 10 subjects. The maximum individual ITR is 107.55 bits min -1 for 12-class SSVEP dataset, whereas, the ITR of 69.29 and 69.44 bits min -1 are achieved with CCA and NCCA respectively. The statistical test shows that the proposed unsupervised method significantly improves the performance of the SSVEP-based BCI. It can be usable in real world applications.

Evaluating unsupervised methods to size and classify suspended particles using digital in-line holography

USGS Publications Warehouse

Davies, Emlyn J.; Buscombe, Daniel D.; Graham, George W.; Nimmo-Smith, W. Alex M.

2015-01-01

Substantial information can be gained from digital in-line holography of marine particles, eliminating depth-of-field and focusing errors associated with standard lens-based imaging methods. However, for the technique to reach its full potential in oceanographic research, fully unsupervised (automated) methods are required for focusing, segmentation, sizing and classification of particles. These computational challenges are the subject of this paper, in which we draw upon data collected using a variety of holographic systems developed at Plymouth University, UK, from a significant range of particle types, sizes and shapes. A new method for noise reduction in reconstructed planes is found to be successful in aiding particle segmentation and sizing. The performance of an automated routine for deriving particle characteristics (and subsequent size distributions) is evaluated against equivalent size metrics obtained by a trained operative measuring grain axes on screen. The unsupervised method is found to be reliable, despite some errors resulting from over-segmentation of particles. A simple unsupervised particle classification system is developed, and is capable of successfully differentiating sand grains, bubbles and diatoms from within the surf-zone. Avoiding miscounting bubbles and biological particles as sand grains enables more accurate estimates of sand concentrations, and is especially important in deployments of particle monitoring instrumentation in aerated water. Perhaps the greatest potential for further development in the computational aspects of particle holography is in the area of unsupervised particle classification. The simple method proposed here provides a foundation upon which further development could lead to reliable identification of more complex particle populations, such as those containing phytoplankton, zooplankton, flocculated cohesive sediments and oil droplets.

Towards an unsupervised device for the diagnosis of childhood pneumonia in low resource settings: automatic segmentation of respiratory sounds.

PubMed

Sola, J; Braun, F; Muntane, E; Verjus, C; Bertschi, M; Hugon, F; Manzano, S; Benissa, M; Gervaix, A

2016-08-01

Pneumonia remains the worldwide leading cause of children mortality under the age of five, with every year 1.4 million deaths. Unfortunately, in low resource settings, very limited diagnostic support aids are provided to point-of-care practitioners. Current UNICEF/WHO case management algorithm relies on the use of a chronometer to manually count breath rates on pediatric patients: there is thus a major need for more sophisticated tools to diagnose pneumonia that increase sensitivity and specificity of breath-rate-based algorithms. These tools should be low cost, and adapted to practitioners with limited training. In this work, a novel concept of unsupervised tool for the diagnosis of childhood pneumonia is presented. The concept relies on the automated analysis of respiratory sounds as recorded by a point-of-care electronic stethoscope. By identifying the presence of auscultation sounds at different chest locations, this diagnostic tool is intended to estimate a pneumonia likelihood score. After presenting the overall architecture of an algorithm to estimate pneumonia scores, the importance of a robust unsupervised method to identify inspiratory and expiratory phases of a respiratory cycle is highlighted. Based on data from an on-going study involving pediatric pneumonia patients, a first algorithm to segment respiratory sounds is suggested. The unsupervised algorithm relies on a Mel-frequency filter bank, a two-step Gaussian Mixture Model (GMM) description of data, and a final Hidden Markov Model (HMM) interpretation of inspiratory-expiratory sequences. Finally, illustrative results on first recruited patients are provided. The presented algorithm opens the doors to a new family of unsupervised respiratory sound analyzers that could improve future versions of case management algorithms for the diagnosis of pneumonia in low-resources settings.

Training strategy for convolutional neural networks in pedestrian gender classification

NASA Astrophysics Data System (ADS)

Ng, Choon-Boon; Tay, Yong-Haur; Goi, Bok-Min

2017-06-01

In this work, we studied a strategy for training a convolutional neural network in pedestrian gender classification with limited amount of labeled training data. Unsupervised learning by k-means clustering on pedestrian images was used to learn the filters to initialize the first layer of the network. As a form of pre-training, supervised learning for the related task of pedestrian classification was performed. Finally, the network was fine-tuned for gender classification. We found that this strategy improved the network's generalization ability in gender classification, achieving better test results when compared to random weights initialization and slightly more beneficial than merely initializing the first layer filters by unsupervised learning. This shows that unsupervised learning followed by pre-training with pedestrian images is an effective strategy to learn useful features for pedestrian gender classification.

Simultaneously Discovering and Localizing Common Objects in Wild Images.

PubMed

Wang, Zhenzhen; Yuan, Junsong

2018-09-01

Motivated by the recent success of supervised and weakly supervised common object discovery, in this paper, we move forward one step further to tackle common object discovery in a fully unsupervised way. Generally, object co-localization aims at simultaneously localizing objects of the same class across a group of images. Traditional object localization/detection usually trains specific object detectors which require bounding box annotations of object instances, or at least image-level labels to indicate the presence/absence of objects in an image. Given a collection of images without any annotations, our proposed fully unsupervised method is to simultaneously discover images that contain common objects and also localize common objects in corresponding images. Without requiring to know the total number of common objects, we formulate this unsupervised object discovery as a sub-graph mining problem from a weighted graph of object proposals, where nodes correspond to object proposals, and edges represent the similarities between neighbouring proposals. The positive images and common objects are jointly discovered by finding sub-graphs of strongly connected nodes, with each sub-graph capturing one object pattern. The optimization problem can be efficiently solved by our proposed maximal-flow-based algorithm. Instead of assuming that each image contains only one common object, our proposed solution can better address wild images where each image may contain multiple common objects or even no common object. Moreover, our proposed method can be easily tailored to the task of image retrieval in which the nodes correspond to the similarity between query and reference images. Extensive experiments on PASCAL VOC 2007 and Object Discovery data sets demonstrate that even without any supervision, our approach can discover/localize common objects of various classes in the presence of scale, view point, appearance variation, and partial occlusions. We also conduct broad experiments on image retrieval benchmarks, Holidays and Oxford5k data sets, to show that our proposed method, which considers both the similarity between query and reference images and also similarities among reference images, can help to improve the retrieval results significantly.

Neural networks for learning and prediction with applications to remote sensing and speech perception

NASA Astrophysics Data System (ADS)

Gjaja, Marin N.

1997-11-01

Neural networks for supervised and unsupervised learning are developed and applied to problems in remote sensing, continuous map learning, and speech perception. Adaptive Resonance Theory (ART) models are real-time neural networks for category learning, pattern recognition, and prediction. Unsupervised fuzzy ART networks synthesize fuzzy logic and neural networks, and supervised ARTMAP networks incorporate ART modules for prediction and classification. New ART and ARTMAP methods resulting from analyses of data structure, parameter specification, and category selection are developed. Architectural modifications providing flexibility for a variety of applications are also introduced and explored. A new methodology for automatic mapping from Landsat Thematic Mapper (TM) and terrain data, based on fuzzy ARTMAP, is developed. System capabilities are tested on a challenging remote sensing problem, prediction of vegetation classes in the Cleveland National Forest from spectral and terrain features. After training at the pixel level, performance is tested at the stand level, using sites not seen during training. Results are compared to those of maximum likelihood classifiers, back propagation neural networks, and K-nearest neighbor algorithms. Best performance is obtained using a hybrid system based on a convex combination of fuzzy ARTMAP and maximum likelihood predictions. This work forms the foundation for additional studies exploring fuzzy ARTMAP's capability to estimate class mixture composition for non-homogeneous sites. Exploratory simulations apply ARTMAP to the problem of learning continuous multidimensional mappings. A novel system architecture retains basic ARTMAP properties of incremental and fast learning in an on-line setting while adding components to solve this class of problems. The perceptual magnet effect is a language-specific phenomenon arising early in infant speech development that is characterized by a warping of speech sound perception. An unsupervised neural network model is proposed that embodies two principal hypotheses supported by experimental data--that sensory experience guides language-specific development of an auditory neural map and that a population vector can predict psychological phenomena based on map cell activities. Model simulations show how a nonuniform distribution of map cell firing preferences can develop from language-specific input and give rise to the magnet effect.

Mapping of rock types using a joint approach by combining the multivariate statistics, self-organizing map and Bayesian neural networks: an example from IODP 323 site

NASA Astrophysics Data System (ADS)

Karmakar, Mampi; Maiti, Saumen; Singh, Amrita; Ojha, Maheswar; Maity, Bhabani Sankar

2017-07-01

Modeling and classification of the subsurface lithology is very important to understand the evolution of the earth system. However, precise classification and mapping of lithology using a single framework are difficult due to the complexity and the nonlinearity of the problem driven by limited core sample information. Here, we implement a joint approach by combining the unsupervised and the supervised methods in a single framework for better classification and mapping of rock types. In the unsupervised method, we use the principal component analysis (PCA), K-means cluster analysis (K-means), dendrogram analysis, Fuzzy C-means (FCM) cluster analysis and self-organizing map (SOM). In the supervised method, we use the Bayesian neural networks (BNN) optimized by the Hybrid Monte Carlo (HMC) (BNN-HMC) and the scaled conjugate gradient (SCG) (BNN-SCG) techniques. We use P-wave velocity, density, neutron porosity, resistivity and gamma ray logs of the well U1343E of the Integrated Ocean Drilling Program (IODP) Expedition 323 in the Bering Sea slope region. While the SOM algorithm allows us to visualize the clustering results in spatial domain, the combined classification schemes (supervised and unsupervised) uncover the different patterns of lithology such of as clayey-silt, diatom-silt and silty-clay from an un-cored section of the drilled hole. In addition, the BNN approach is capable of estimating uncertainty in the predictive modeling of three types of rocks over the entire lithology section at site U1343. Alternate succession of clayey-silt, diatom-silt and silty-clay may be representative of crustal inhomogeneity in general and thus could be a basis for detail study related to the productivity of methane gas in the oceans worldwide. Moreover, at the 530 m depth down below seafloor (DSF), the transition from Pliocene to Pleistocene could be linked to lithological alternation between the clayey-silt and the diatom-silt. The present results could provide the basis for the detailed study to get deeper insight into the Bering Sea' sediment deposition and sequence.

The Delicate Balance between Parental Protection, Unsupervised Wandering, and Adolescents' Autonomy and Its Relation with Antisocial Behavior: The TRAILS Study

ERIC Educational Resources Information Center

Sentse, Miranda; Dijkstra, Jan Kornelis; Lindenberg, Siegwart; Ormel, Johan; Veenstra, Rene

2010-01-01

In a large sample of early adolescents (T2: N = 1023; M age = 13.51; 55.5% girls), the impact of parental protection and unsupervised wandering on adolescents' antisocial behavior 2.5 years later was tested in this TRAILS study; gender and parental knowledge were controlled for. In addition, the level of biological maturation and having antisocial…

FRaC: a feature-modeling approach for semi-supervised and unsupervised anomaly detection.

PubMed

Noto, Keith; Brodley, Carla; Slonim, Donna

2012-01-01

Anomaly detection involves identifying rare data instances (anomalies) that come from a different class or distribution than the majority (which are simply called "normal" instances). Given a training set of only normal data, the semi-supervised anomaly detection task is to identify anomalies in the future. Good solutions to this task have applications in fraud and intrusion detection. The unsupervised anomaly detection task is different: Given unlabeled, mostly-normal data, identify the anomalies among them. Many real-world machine learning tasks, including many fraud and intrusion detection tasks, are unsupervised because it is impractical (or impossible) to verify all of the training data. We recently presented FRaC, a new approach for semi-supervised anomaly detection. FRaC is based on using normal instances to build an ensemble of feature models, and then identifying instances that disagree with those models as anomalous. In this paper, we investigate the behavior of FRaC experimentally and explain why FRaC is so successful. We also show that FRaC is a superior approach for the unsupervised as well as the semi-supervised anomaly detection task, compared to well-known state-of-the-art anomaly detection methods, LOF and one-class support vector machines, and to an existing feature-modeling approach.

A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data

PubMed Central

Goldstein, Markus; Uchida, Seiichi

2016-01-01

Anomaly detection is the process of identifying unexpected items or events in datasets, which differ from the norm. In contrast to standard classification tasks, anomaly detection is often applied on unlabeled data, taking only the internal structure of the dataset into account. This challenge is known as unsupervised anomaly detection and is addressed in many practical applications, for example in network intrusion detection, fraud detection as well as in the life science and medical domain. Dozens of algorithms have been proposed in this area, but unfortunately the research community still lacks a comparative universal evaluation as well as common publicly available datasets. These shortcomings are addressed in this study, where 19 different unsupervised anomaly detection algorithms are evaluated on 10 different datasets from multiple application domains. By publishing the source code and the datasets, this paper aims to be a new well-funded basis for unsupervised anomaly detection research. Additionally, this evaluation reveals the strengths and weaknesses of the different approaches for the first time. Besides the anomaly detection performance, computational effort, the impact of parameter settings as well as the global/local anomaly detection behavior is outlined. As a conclusion, we give an advise on algorithm selection for typical real-world tasks. PMID:27093601

FRaC: a feature-modeling approach for semi-supervised and unsupervised anomaly detection

PubMed Central

Brodley, Carla; Slonim, Donna

2011-01-01

Anomaly detection involves identifying rare data instances (anomalies) that come from a different class or distribution than the majority (which are simply called “normal” instances). Given a training set of only normal data, the semi-supervised anomaly detection task is to identify anomalies in the future. Good solutions to this task have applications in fraud and intrusion detection. The unsupervised anomaly detection task is different: Given unlabeled, mostly-normal data, identify the anomalies among them. Many real-world machine learning tasks, including many fraud and intrusion detection tasks, are unsupervised because it is impractical (or impossible) to verify all of the training data. We recently presented FRaC, a new approach for semi-supervised anomaly detection. FRaC is based on using normal instances to build an ensemble of feature models, and then identifying instances that disagree with those models as anomalous. In this paper, we investigate the behavior of FRaC experimentally and explain why FRaC is so successful. We also show that FRaC is a superior approach for the unsupervised as well as the semi-supervised anomaly detection task, compared to well-known state-of-the-art anomaly detection methods, LOF and one-class support vector machines, and to an existing feature-modeling approach. PMID:22639542

Detection of food intake from swallowing sequences by supervised and unsupervised methods.

PubMed

Lopez-Meyer, Paulo; Makeyev, Oleksandr; Schuckers, Stephanie; Melanson, Edward L; Neuman, Michael R; Sazonov, Edward

2010-08-01

Studies of food intake and ingestive behavior in free-living conditions most often rely on self-reporting-based methods that can be highly inaccurate. Methods of Monitoring of Ingestive Behavior (MIB) rely on objective measures derived from chewing and swallowing sequences and thus can be used for unbiased study of food intake with free-living conditions. Our previous study demonstrated accurate detection of food intake in simple models relying on observation of both chewing and swallowing. This article investigates methods that achieve comparable accuracy of food intake detection using only the time series of swallows and thus eliminating the need for the chewing sensor. The classification is performed for each individual swallow rather than for previously used time slices and thus will lead to higher accuracy in mass prediction models relying on counts of swallows. Performance of a group model based on a supervised method (SVM) is compared to performance of individual models based on an unsupervised method (K-means) with results indicating better performance of the unsupervised, self-adapting method. Overall, the results demonstrate that highly accurate detection of intake of foods with substantially different physical properties is possible by an unsupervised system that relies on the information provided by the swallowing alone.

Detection of Food Intake from Swallowing Sequences by Supervised and Unsupervised Methods

PubMed Central

Lopez-Meyer, Paulo; Makeyev, Oleksandr; Schuckers, Stephanie; Melanson, Edward L.; Neuman, Michael R.; Sazonov, Edward

2010-01-01

Studies of food intake and ingestive behavior in free-living conditions most often rely on self-reporting-based methods that can be highly inaccurate. Methods of Monitoring of Ingestive Behavior (MIB) rely on objective measures derived from chewing and swallowing sequences and thus can be used for unbiased study of food intake with free-living conditions. Our previous study demonstrated accurate detection of food intake in simple models relying on observation of both chewing and swallowing. This article investigates methods that achieve comparable accuracy of food intake detection using only the time series of swallows and thus eliminating the need for the chewing sensor. The classification is performed for each individual swallow rather than for previously used time slices and thus will lead to higher accuracy in mass prediction models relying on counts of swallows. Performance of a group model based on a supervised method (SVM) is compared to performance of individual models based on an unsupervised method (K-means) with results indicating better performance of the unsupervised, self-adapting method. Overall, the results demonstrate that highly accurate detection of intake of foods with substantially different physical properties is possible by an unsupervised system that relies on the information provided by the swallowing alone. PMID:20352335

Sleep in patients with disorders of consciousness characterized by means of machine learning

PubMed Central

Lechinger, Julia; Wislowska, Malgorzata; Blume, Christine; Ott, Peter; Wegenkittl, Stefan; del Giudice, Renata; Heib, Dominik P. J.; Mayer, Helmut A.; Laureys, Steven; Pichler, Gerald; Schabus, Manuel

2018-01-01

Sleep has been proposed to indicate preserved residual brain functioning in patients suffering from disorders of consciousness (DOC) after awakening from coma. However, a reliable characterization of sleep patterns in this clinical population continues to be challenging given severely altered brain oscillations, frequent and extended artifacts in clinical recordings and the absence of established staging criteria. In the present study, we try to address these issues and investigate the usefulness of a multivariate machine learning technique based on permutation entropy, a complexity measure. Specifically, we used long-term polysomnography (PSG), along with video recordings in day and night periods in a sample of 23 DOC; 12 patients were diagnosed as Unresponsive Wakefulness Syndrome (UWS) and 11 were diagnosed as Minimally Conscious State (MCS). Eight hour PSG recordings of healthy sleepers (N = 26) were additionally used for training and setting parameters of supervised and unsupervised model, respectively. In DOC, the supervised classification (wake, N1, N2, N3 or REM) was validated using simultaneous videos which identified periods with prolonged eye opening or eye closure.The supervised classification revealed that out of the 23 subjects, 11 patients (5 MCS and 6 UWS) yielded highly accurate classification with an average F1-score of 0.87 representing high overlap between the classifier predicting sleep (i.e. one of the 4 sleep stages) and closed eyes. Furthermore, the unsupervised approach revealed a more complex pattern of sleep-wake stages during the night period in the MCS group, as evidenced by the presence of several distinct clusters. In contrast, in UWS patients no such clustering was found. Altogether, we present a novel data-driven method, based on machine learning that can be used to gain new and unambiguous insights into sleep organization and residual brain functioning of patients with DOC. PMID:29293607

Gene expression profiles of breast biopsies from healthy women identify a group with claudin-low features

PubMed Central

2011-01-01

Background Increased understanding of the variability in normal breast biology will enable us to identify mechanisms of breast cancer initiation and the origin of different subtypes, and to better predict breast cancer risk. Methods Gene expression patterns in breast biopsies from 79 healthy women referred to breast diagnostic centers in Norway were explored by unsupervised hierarchical clustering and supervised analyses, such as gene set enrichment analysis and gene ontology analysis and comparison with previously published genelists and independent datasets. Results Unsupervised hierarchical clustering identified two separate clusters of normal breast tissue based on gene-expression profiling, regardless of clustering algorithm and gene filtering used. Comparison of the expression profile of the two clusters with several published gene lists describing breast cells revealed that the samples in cluster 1 share characteristics with stromal cells and stem cells, and to a certain degree with mesenchymal cells and myoepithelial cells. The samples in cluster 1 also share many features with the newly identified claudin-low breast cancer intrinsic subtype, which also shows characteristics of stromal and stem cells. More women belonging to cluster 1 have a family history of breast cancer and there is a slight overrepresentation of nulliparous women in cluster 1. Similar findings were seen in a separate dataset consisting of histologically normal tissue from both breasts harboring breast cancer and from mammoplasty reductions. Conclusion This is the first study to explore the variability of gene expression patterns in whole biopsies from normal breasts and identified distinct subtypes of normal breast tissue. Further studies are needed to determine the specific cell contribution to the variation in the biology of normal breasts, how the clusters identified relate to breast cancer risk and their possible link to the origin of the different molecular subtypes of breast cancer. PMID:22044755

Unmixing the Mixing Cost: Contributions from Dimensional Relevance and Stimulus-Response Suppression

ERIC Educational Resources Information Center

Mari-Beffa, Paloma; Cooper, Stephen; Houghton, George

2012-01-01

When participants repeat the same task in a context in which the task may also switch (a mixed block), performance deteriorates compared to when there is only one task repeating (a pure block). Three experiments were designed to assess how perceptual and motor transitions influenced this mixing cost. Experiment 1 provided three pure block…

A cross-comparison of field, spectral, and lidar estimates of forest canopy cover

Treesearch

Alistair M. S. Smith; Michael J. Falkowski; Andrew T. Hudak; Jeffrey S. Evans; Andrew P. Robinson; Caiti M. Steele

2010-01-01

A common challenge when comparing forest canopy cover and similar metrics across different ecosystems is that there are many field- and landscape-level measurement methods. This research conducts a cross-comparison and evaluation of forest canopy cover metrics produced using unmixing of reflective spectral satellite data, light detection and ranging (lidar) data, and...

Biomass and health based forest cover delineation using spectral un-mixing

Treesearch

Mohan Tiruveedhula; Joseph Fan; Ravi R. Sadasivuni; Surya S. Durbha; David L. Evans

2009-01-01

Remote sensing is a well-suited source of information on various forest characteristics such as forest cover type, leaf area, biomass, and health. The use of appropriate layers helps to quantify the variables of interest. For example, normalized difference vegetation index (NDVI) and greenness help explain variability in biomass as well as health of forests....

7 CFR 201.60 - Purity percentages.

Code of Federal Regulations, 2014 CFR

2014-01-01

... (2) mixtures in which the particle-weight ratio is 1:1 to 1.49:1, inclusive. Tolerances for... Component of a Purity Analysis for (1) Unmixed Seed or (2) Mixed Seed in Which the Particle Weight Ratio Is... particle-weight ratio is 1.5:1 to 20:1 and beyond: The symbols used in the formula are as follows: T...

7 CFR 201.60 - Purity percentages.

Code of Federal Regulations, 2011 CFR

2011-01-01

... (2) mixtures in which the particle-weight ratio is 1:1 to 1.49:1, inclusive. Tolerances for... Component of a Purity Analysis for (1) Unmixed Seed or (2) Mixed Seed in Which the Particle Weight Ratio Is... particle-weight ratio is 1.5:1 to 20:1 and beyond: The symbols used in the formula are as follows: T...

7 CFR 201.60 - Purity percentages.

Code of Federal Regulations, 2012 CFR

2012-01-01

... (2) mixtures in which the particle-weight ratio is 1:1 to 1.49:1, inclusive. Tolerances for... Component of a Purity Analysis for (1) Unmixed Seed or (2) Mixed Seed in Which the Particle Weight Ratio Is... particle-weight ratio is 1.5:1 to 20:1 and beyond: The symbols used in the formula are as follows: T...

7 CFR 201.60 - Purity percentages.

Code of Federal Regulations, 2013 CFR

2013-01-01

... (2) mixtures in which the particle-weight ratio is 1:1 to 1.49:1, inclusive. Tolerances for... Component of a Purity Analysis for (1) Unmixed Seed or (2) Mixed Seed in Which the Particle Weight Ratio Is... particle-weight ratio is 1.5:1 to 20:1 and beyond: The symbols used in the formula are as follows: T...

Learning complex temporal patterns with resource-dependent spike timing-dependent plasticity.

PubMed

Hunzinger, Jason F; Chan, Victor H; Froemke, Robert C

2012-07-01

Studies of spike timing-dependent plasticity (STDP) have revealed that long-term changes in the strength of a synapse may be modulated substantially by temporal relationships between multiple presynaptic and postsynaptic spikes. Whereas long-term potentiation (LTP) and long-term depression (LTD) of synaptic strength have been modeled as distinct or separate functional mechanisms, here, we propose a new shared resource model. A functional consequence of our model is fast, stable, and diverse unsupervised learning of temporal multispike patterns with a biologically consistent spiking neural network. Due to interdependencies between LTP and LTD, dendritic delays, and proactive homeostatic aspects of the model, neurons are equipped to learn to decode temporally coded information within spike bursts. Moreover, neurons learn spike timing with few exposures in substantial noise and jitter. Surprisingly, despite having only one parameter, the model also accurately predicts in vitro observations of STDP in more complex multispike trains, as well as rate-dependent effects. We discuss candidate commonalities in natural long-term plasticity mechanisms.

A Pattern Recognition Approach to Acoustic Emission Data Originating from Fatigue of Wind Turbine Blades

PubMed Central

Tang, Jialin; Soua, Slim; Mares, Cristinel; Gan, Tat-Hean

2017-01-01

The identification of particular types of damage in wind turbine blades using acoustic emission (AE) techniques is a significant emerging field. In this work, a 45.7-m turbine blade was subjected to flap-wise fatigue loading for 21 days, during which AE was measured by internally mounted piezoelectric sensors. This paper focuses on using unsupervised pattern recognition methods to characterize different AE activities corresponding to different fracture mechanisms. A sequential feature selection method based on a k-means clustering algorithm is used to achieve a fine classification accuracy. The visualization of clusters in peak frequency−frequency centroid features is used to correlate the clustering results with failure modes. The positions of these clusters in time domain features, average frequency−MARSE, and average frequency−peak amplitude are also presented in this paper (where MARSE represents the Measured Area under Rectified Signal Envelope). The results show that these parameters are representative for the classification of the failure modes. PMID:29104245

Clustering of tethered satellite system simulation data by an adaptive neuro-fuzzy algorithm

NASA Technical Reports Server (NTRS)

Mitra, Sunanda; Pemmaraju, Surya

1992-01-01

Recent developments in neuro-fuzzy systems indicate that the concepts of adaptive pattern recognition, when used to identify appropriate control actions corresponding to clusters of patterns representing system states in dynamic nonlinear control systems, may result in innovative designs. A modular, unsupervised neural network architecture, in which fuzzy learning rules have been embedded is used for on-line identification of similar states. The architecture and control rules involved in Adaptive Fuzzy Leader Clustering (AFLC) allow this system to be incorporated in control systems for identification of system states corresponding to specific control actions. We have used this algorithm to cluster the simulation data of Tethered Satellite System (TSS) to estimate the range of delta voltages necessary to maintain the desired length rate of the tether. The AFLC algorithm is capable of on-line estimation of the appropriate control voltages from the corresponding length error and length rate error without a priori knowledge of their membership functions and familarity with the behavior of the Tethered Satellite System.

Unsupervised texture image segmentation by improved neural network ART2

NASA Technical Reports Server (NTRS)

Wang, Zhiling; Labini, G. Sylos; Mugnuolo, R.; Desario, Marco

1994-01-01

We here propose a segmentation algorithm of texture image for a computer vision system on a space robot. An improved adaptive resonance theory (ART2) for analog input patterns is adapted to classify the image based on a set of texture image features extracted by a fast spatial gray level dependence method (SGLDM). The nonlinear thresholding functions in input layer of the neural network have been constructed by two parts: firstly, to reduce the effects of image noises on the features, a set of sigmoid functions is chosen depending on the types of the feature; secondly, to enhance the contrast of the features, we adopt fuzzy mapping functions. The cluster number in output layer can be increased by an autogrowing mechanism constantly when a new pattern happens. Experimental results and original or segmented pictures are shown, including the comparison between this approach and K-means algorithm. The system written in C language is performed on a SUN-4/330 sparc-station with an image board IT-150 and a CCD camera.

Quantifying Human Visible Color Variation from High Definition Digital Images of Orb Web Spiders.

PubMed

Tapia-McClung, Horacio; Ajuria Ibarra, Helena; Rao, Dinesh

2016-01-01

Digital processing and analysis of high resolution images of 30 individuals of the orb web spider Verrucosa arenata were performed to extract and quantify human visible colors present on the dorsal abdomen of this species. Color extraction was performed with minimal user intervention using an unsupervised algorithm to determine groups of colors on each individual spider, which was then analyzed in order to quantify and classify the colors obtained, both spatially and using energy and entropy measures of the digital images. Analysis shows that the colors cover a small region of the visible spectrum, are not spatially homogeneously distributed over the patterns and from an entropic point of view, colors that cover a smaller region on the whole pattern carry more information than colors covering a larger region. This study demonstrates the use of processing tools to create automatic systems to extract valuable information from digital images that are precise, efficient and helpful for the understanding of the underlying biology.

A Pattern Recognition Approach to Acoustic Emission Data Originating from Fatigue of Wind Turbine Blades.

PubMed

Tang, Jialin; Soua, Slim; Mares, Cristinel; Gan, Tat-Hean

2017-11-01

The identification of particular types of damage in wind turbine blades using acoustic emission (AE) techniques is a significant emerging field. In this work, a 45.7-m turbine blade was subjected to flap-wise fatigue loading for 21 days, during which AE was measured by internally mounted piezoelectric sensors. This paper focuses on using unsupervised pattern recognition methods to characterize different AE activities corresponding to different fracture mechanisms. A sequential feature selection method based on a k-means clustering algorithm is used to achieve a fine classification accuracy. The visualization of clusters in peak frequency-frequency centroid features is used to correlate the clustering results with failure modes. The positions of these clusters in time domain features, average frequency-MARSE, and average frequency-peak amplitude are also presented in this paper (where MARSE represents the Measured Area under Rectified Signal Envelope). The results show that these parameters are representative for the classification of the failure modes.

Quantifying Human Visible Color Variation from High Definition Digital Images of Orb Web Spiders

PubMed Central

Ajuria Ibarra, Helena; Rao, Dinesh

2016-01-01

Digital processing and analysis of high resolution images of 30 individuals of the orb web spider Verrucosa arenata were performed to extract and quantify human visible colors present on the dorsal abdomen of this species. Color extraction was performed with minimal user intervention using an unsupervised algorithm to determine groups of colors on each individual spider, which was then analyzed in order to quantify and classify the colors obtained, both spatially and using energy and entropy measures of the digital images. Analysis shows that the colors cover a small region of the visible spectrum, are not spatially homogeneously distributed over the patterns and from an entropic point of view, colors that cover a smaller region on the whole pattern carry more information than colors covering a larger region. This study demonstrates the use of processing tools to create automatic systems to extract valuable information from digital images that are precise, efficient and helpful for the understanding of the underlying biology. PMID:27902724

Down-Regulation of Olfactory Receptors in Response to Traumatic Brain Injury Promotes Risk for Alzheimers Disease

DTIC Science & Technology

2015-12-01

group assignment of samples in unsupervised hierarchical clustering by the Unweighted Pair-Group Method using Arithmetic averages ( UPGMA ) based on...log2 transformed MAS5.0 signal values; probe set clustering was performed by the UPGMA method using Cosine correlation as the similarity met- ric. For...differentially-regulated genes identified were subjected to unsupervised hierarchical clustering analysis using the UPGMA algorithm with cosine correlation as

Unsupervised classification of surface defects in wire rod production obtained by eddy current sensors.

PubMed

Saludes-Rodil, Sergio; Baeyens, Enrique; Rodríguez-Juan, Carlos P

2015-04-29

An unsupervised approach to classify surface defects in wire rod manufacturing is developed in this paper. The defects are extracted from an eddy current signal and classified using a clustering technique that uses the dynamic time warping distance as the dissimilarity measure. The new approach has been successfully tested using industrial data. It is shown that it outperforms other classification alternatives, such as the modified Fourier descriptors.

Nonequilibrium thermodynamics of restricted Boltzmann machines.

PubMed

Salazar, Domingos S P

2017-08-01

In this work, we analyze the nonequilibrium thermodynamics of a class of neural networks known as restricted Boltzmann machines (RBMs) in the context of unsupervised learning. We show how the network is described as a discrete Markov process and how the detailed balance condition and the Maxwell-Boltzmann equilibrium distribution are sufficient conditions for a complete thermodynamics description, including nonequilibrium fluctuation theorems. Numerical simulations in a fully trained RBM are performed and the heat exchange fluctuation theorem is verified with excellent agreement to the theory. We observe how the contrastive divergence functional, mostly used in unsupervised learning of RBMs, is closely related to nonequilibrium thermodynamic quantities. We also use the framework to interpret the estimation of the partition function of RBMs with the annealed importance sampling method from a thermodynamics standpoint. Finally, we argue that unsupervised learning of RBMs is equivalent to a work protocol in a system driven by the laws of thermodynamics in the absence of labeled data.

Unsupervised real-time speaker identification for daily movies

NASA Astrophysics Data System (ADS)

Li, Ying; Kuo, C.-C. Jay

2002-07-01

The problem of identifying speakers for movie content analysis is addressed in this paper. While most previous work on speaker identification was carried out in a supervised mode using pure audio data, more robust results can be obtained in real-time by integrating knowledge from multiple media sources in an unsupervised mode. In this work, both audio and visual cues will be employed and subsequently combined in a probabilistic framework to identify speakers. Particularly, audio information is used to identify speakers with a maximum likelihood (ML)-based approach while visual information is adopted to distinguish speakers by detecting and recognizing their talking faces based on face detection/recognition and mouth tracking techniques. Moreover, to accommodate for speakers' acoustic variations along time, we update their models on the fly by adapting to their newly contributed speech data. Encouraging results have been achieved through extensive experiments, which shows a promising future of the proposed audiovisual-based unsupervised speaker identification system.

An Unsupervised Anomalous Event Detection and Interactive Analysis Framework for Large-scale Satellite Data

NASA Astrophysics Data System (ADS)

LIU, Q.; Lv, Q.; Klucik, R.; Chen, C.; Gallaher, D. W.; Grant, G.; Shang, L.

2016-12-01

Due to the high volume and complexity of satellite data, computer-aided tools for fast quality assessments and scientific discovery are indispensable for scientists in the era of Big Data. In this work, we have developed a framework for automated anomalous event detection in massive satellite data. The framework consists of a clustering-based anomaly detection algorithm and a cloud-based tool for interactive analysis of detected anomalies. The algorithm is unsupervised and requires no prior knowledge of the data (e.g., expected normal pattern or known anomalies). As such, it works for diverse data sets, and performs well even in the presence of missing and noisy data. The cloud-based tool provides an intuitive mapping interface that allows users to interactively analyze anomalies using multiple features. As a whole, our framework can (1) identify outliers in a spatio-temporal context, (2) recognize and distinguish meaningful anomalous events from individual outliers, (3) rank those events based on "interestingness" (e.g., rareness or total number of outliers) defined by users, and (4) enable interactively query, exploration, and analysis of those anomalous events. In this presentation, we will demonstrate the effectiveness and efficiency of our framework in the application of detecting data quality issues and unusual natural events using two satellite datasets. The techniques and tools developed in this project are applicable for a diverse set of satellite data and will be made publicly available for scientists in early 2017.

When and where do youths have sex? The potential role of adult supervision.

PubMed

Cohen, Deborah A; Farley, Thomas A; Taylor, Stephanie N; Martin, David H; Schuster, Mark A

2002-12-01

Interventions to reduce high-risk behaviors such as sex and substance use among youths have focused mainly on promoting abstinence, refusal skills, and negotiation skills, yet the frequency of high-risk behaviors among youths may also be influenced by opportunity, particularly the amount of time during which they are not supervised by adults. In this study, we examined when and where youths have sex and whether there is a relationship between unsupervised time and sex, sexually transmitted diseases (STDs), and substance use. A cross-sectional survey was conducted in 6 public high schools in an urban school district. Participants were 1065 boys and 969 girls from a school-based STD screening program. Ninety-eight percent of students were black, and 79% were in the free or reduced lunch program. Most students reported living with 1 parent only, primarily the mother (52%); only 27% lived in 2-parent families. Sexual activity, substance use, and the prevalence of gonorrhea or chlamydia as determined by a ligase-chain reaction test on a urine sample were measured. Fifty-six percent reported being home without an adult present 4 or more hours per day after school. There was no difference in the number of unsupervised after-school hours between children in 1- and 2-parent families. Fifty-five percent of boys and 41% of girls were participating in or planned to participate in after-school activities during the school year. Boys were more likely than girls to report having had sex for the first time before age 14 (42% vs 9%) and had a greater number of lifetime sex partners (mean: 4.2 vs 2.4 partners). Among the respondents who had had intercourse, 91% said that the last time had been in a home setting, including their own home (37%), their partner's home (43%), and a friend's home (12%), usually after school. Boys were more likely than girls to report having had sex in their own homes (43% vs 28%) and less likely than girls to report having had sex in their partner's homes (30% vs 59%). Fifty-six percent of youths who had had intercourse reported that the last time was on a weekday: 18% before 3:00, 17% between 3:00 and 6:00, and 21% after 6:00. There were no gender differences in the day of the week or time of day during which students reported having had intercourse. Youths who were unsupervised for 30 or more hours per week were more likely to be sexually active compared with those who were unsupervised for 5 hours a week or less (80% vs 68%). In addition, for boys, the greater the amount of unsupervised time, the higher the number of lifetime sex partners. Among girls but not among boys, sexual activity was associated with nonparticipation in after-school programs; 71% of those who were not participating in an after-school activity were sexually active compared with 59% of those who were participating. Tobacco and alcohol use were associated with unsupervised time among boys but not among girls. Boys who were unsupervised >5 hours per week after school were twice as likely to have gonorrhea or chlamydial infection as boys who were unsupervised for 5 hours or less. We found that substantial numbers of youths currently spend long periods of time without adult supervision and have limited opportunities to participate in after-school activities. More than half of sexually active youths reported that they had sex at home after school, and, particularly for boys, sexual-and drug-related risks increased as the amount of unsupervised time increased. As youths come of age, parents probably believe that it is appropriate to leave them increasingly on their own, and, accordingly, prevention approaches have concentrated on providing information and motivation for abstinence or safer sex. However, given the independent association between the amount of unsupervised time and sexual behaviors (with STD rates suggestive of particularly risky sexual behaviors) and substance use behaviors, it is worth considering increasing youth supervision, if not by parents, then by programs organized at schools organized at school or other community settings. Parents and community members should consider increasing opportunities for supervised activities to determine whether this will reduce risk-taking among youths.

On the clustering of multidimensional pictorial data

NASA Technical Reports Server (NTRS)

Bryant, J. D. (Principal Investigator)

1979-01-01

Obvious approaches to reducing the cost (in computer resources) of applying current clustering techniques to the problem of remote sensing are discussed. The use of spatial information in finding fields and in classifying mixture pixels is examined, and the AMOEBA clustering program is described. Internally, a pattern recognition program, from without, AMOEBA appears to be an unsupervised clustering program. It is fast and automatic. No choices (such as arbitrary thresholds to set split/combine sequences) need be made. The problem of finding the number of clusters is solved automatically. At the conclusion of the program, all points in the scene are classified; however, a provision is included for a reject classification of some points which, within the theoretical framework, cannot rationally be assigned to any cluster.

Deciphering Neural Codes of Memory during Sleep

PubMed Central

Chen, Zhe; Wilson, Matthew A.

2017-01-01

Memories of experiences are stored in the cerebral cortex. Sleep is critical for consolidating hippocampal memory of wake experiences into the neocortex. Understanding representations of neural codes of hippocampal-neocortical networks during sleep would reveal important circuit mechanisms on memory consolidation, and provide novel insights into memory and dreams. Although sleep-associated ensemble spike activity has been investigated, identifying the content of memory in sleep remains challenging. Here, we revisit important experimental findings on sleep-associated memory (i.e., neural activity patterns in sleep that reflect memory processing) and review computational approaches for analyzing sleep-associated neural codes (SANC). We focus on two analysis paradigms for sleep-associated memory, and propose a new unsupervised learning framework (“memory first, meaning later”) for unbiased assessment of SANC. PMID:28390699

Damage identification in cement paste amended with carbon nanotubes

NASA Astrophysics Data System (ADS)

Soltangharaei, Vafa; Anay, Rafal; Assi, Lateef; Ziehl, Paul; Matta, Fabio

2018-04-01

Cement-based composites have been used as reliable materials in building and civil engineering infrastructure for many decades. Although there are several advantages, some drawbacks such as premature cracking may be problematic for sensitive applications such as those found in nuclear power plants or associated waste storage facilities. In this study, acoustic emission monitoring was employed to detect stress waves associated with damage progression during uniaxial compressive loading. Acoustic emission data resulting from loading of plain cement paste prisms and cement paste prisms amended with carbon nanotubes are compared. Unsupervised pattern recognition is employed to categorize the data. Results indicate that increased acoustic emission activity was recorded for the plain cement paste prisms when compared to prisms amended with carbon nanotubes.

Symmetric nonnegative matrix factorization: algorithms and applications to probabilistic clustering.

PubMed

He, Zhaoshui; Xie, Shengli; Zdunek, Rafal; Zhou, Guoxu; Cichocki, Andrzej

2011-12-01

Nonnegative matrix factorization (NMF) is an unsupervised learning method useful in various applications including image processing and semantic analysis of documents. This paper focuses on symmetric NMF (SNMF), which is a special case of NMF decomposition. Three parallel multiplicative update algorithms using level 3 basic linear algebra subprograms directly are developed for this problem. First, by minimizing the Euclidean distance, a multiplicative update algorithm is proposed, and its convergence under mild conditions is proved. Based on it, we further propose another two fast parallel methods: α-SNMF and β -SNMF algorithms. All of them are easy to implement. These algorithms are applied to probabilistic clustering. We demonstrate their effectiveness for facial image clustering, document categorization, and pattern clustering in gene expression.

Nonparametric weighted stochastic block models

NASA Astrophysics Data System (ADS)

Peixoto, Tiago P.

2018-01-01

We present a Bayesian formulation of weighted stochastic block models that can be used to infer the large-scale modular structure of weighted networks, including their hierarchical organization. Our method is nonparametric, and thus does not require the prior knowledge of the number of groups or other dimensions of the model, which are instead inferred from data. We give a comprehensive treatment of different kinds of edge weights (i.e., continuous or discrete, signed or unsigned, bounded or unbounded), as well as arbitrary weight transformations, and describe an unsupervised model selection approach to choose the best network description. We illustrate the application of our method to a variety of empirical weighted networks, such as global migrations, voting patterns in congress, and neural connections in the human brain.

Effects of a Supervised versus an Unsupervised Combined Balance and Strength Training Program on Balance and Muscle Power in Healthy Older Adults: A Randomized Controlled Trial.

PubMed

Lacroix, André; Kressig, Reto W; Muehlbauer, Thomas; Gschwind, Yves J; Pfenninger, Barbara; Bruegger, Othmar; Granacher, Urs

2016-01-01

Losses in lower extremity muscle strength/power, muscle mass and deficits in static and particularly dynamic balance due to aging are associated with impaired functional performance and an increased fall risk. It has been shown that the combination of balance and strength training (BST) mitigates these age-related deficits. However, it is unresolved whether supervised versus unsupervised BST is equally effective in improving muscle power and balance in older adults. This study examined the impact of a 12-week BST program followed by 12 weeks of detraining on measures of balance and muscle power in healthy older adults enrolled in supervised (SUP) or unsupervised (UNSUP) training. Sixty-six older adults (men: 25, women: 41; age 73 ± 4 years) were randomly assigned to a SUP group (2/week supervised training, 1/week unsupervised training; n = 22), an UNSUP group (3/week unsupervised training; n = 22) or a passive control group (CON; n = 22). Static (i.e., Romberg Test) and dynamic (i.e., 10-meter walk test) steady-state, proactive (i.e., Timed Up and Go Test, Functional Reach Test), and reactive balance (e.g., Push and Release Test), as well as lower extremity muscle power (i.e., Chair Stand Test; Stair Ascent and Descent Test) were tested before and after the active training phase as well as after detraining. Adherence rates to training were 92% for SUP and 97% for UNSUP. BST resulted in significant group × time interactions. Post hoc analyses showed, among others, significant training-related improvements for the Romberg Test, stride velocity, Timed Up and Go Test, and Chair Stand Test in favor of the SUP group. Following detraining, significantly enhanced performances (compared to baseline) were still present in 13 variables for the SUP group and in 10 variables for the UNSUP group. Twelve weeks of BST proved to be safe (no training-related injuries) and feasible (high attendance rates of >90%). Deficits of balance and lower extremity muscle power can be mitigated by BST in healthy older adults. Additionally, supervised as compared to unsupervised BST was more effective. Thus, it is recommended to counteract intrinsic fall risk factors by applying supervised BST programs for older adults. © 2015 The Author(s) Published by S. Karger AG, Basel.

Supervised and Unsupervised Self-Testing for HIV in High- and Low-Risk Populations: A Systematic Review

PubMed Central

Pant Pai, Nitika; Sharma, Jigyasa; Shivkumar, Sushmita; Pillay, Sabrina; Vadnais, Caroline; Joseph, Lawrence; Dheda, Keertan; Peeling, Rosanna W.

2013-01-01

Background Stigma, discrimination, lack of privacy, and long waiting times partly explain why six out of ten individuals living with HIV do not access facility-based testing. By circumventing these barriers, self-testing offers potential for more people to know their sero-status. Recent approval of an in-home HIV self test in the US has sparked self-testing initiatives, yet data on acceptability, feasibility, and linkages to care are limited. We systematically reviewed evidence on supervised (self-testing and counselling aided by a health care professional) and unsupervised (performed by self-tester with access to phone/internet counselling) self-testing strategies. Methods and Findings Seven databases (Medline [via PubMed], Biosis, PsycINFO, Cinahl, African Medicus, LILACS, and EMBASE) and conference abstracts of six major HIV/sexually transmitted infections conferences were searched from 1st January 2000–30th October 2012. 1,221 citations were identified and 21 studies included for review. Seven studies evaluated an unsupervised strategy and 14 evaluated a supervised strategy. For both strategies, data on acceptability (range: 74%–96%), preference (range: 61%–91%), and partner self-testing (range: 80%–97%) were high. A high specificity (range: 99.8%–100%) was observed for both strategies, while a lower sensitivity was reported in the unsupervised (range: 92.9%–100%; one study) versus supervised (range: 97.4%–97.9%; three studies) strategy. Regarding feasibility of linkage to counselling and care, 96% (n = 102/106) of individuals testing positive for HIV stated they would seek post-test counselling (unsupervised strategy, one study). No extreme adverse events were noted. The majority of data (n = 11,019/12,402 individuals, 89%) were from high-income settings and 71% (n = 15/21) of studies were cross-sectional in design, thus limiting our analysis. Conclusions Both supervised and unsupervised testing strategies were highly acceptable, preferred, and more likely to result in partner self-testing. However, no studies evaluated post-test linkage with counselling and treatment outcomes and reporting quality was poor. Thus, controlled trials of high quality from diverse settings are warranted to confirm and extend these findings. Please see later in the article for the Editors' Summary PMID:23565066

Medical tourism-A New Arena.

PubMed

Puri, S; Singh, A; Yashik

2010-01-01

Globalisation has given birth to medical tourism. Health and medical tourism are the fastest growing segments in not only developed nations but in developing countries too. India has become a hot destination, as the Indian medical standards match up to the highly prescribed international standards at a very low cost. However, it is an unmixed blessing; along with advantages, it has many unintended side effects also.

The effect of high intensity mixing on the enzymatic hydrolysis of concentrated cellulose fiber suspensions

Treesearch

Joseph R. Samaniuk; C. Tim Scott; Thatcher W. Root; Daniel J. Klingenberg

2011-01-01

Enzymatic hydrolysis of lignocellulosic biomass in a high shear environment was examined. The conversion of cellulose to glucose in samples mixed in a torque rheometer producing shear flows similar to those found in twin screw extruders was greater than that of unmixed samples. In addition, there is a synergistic effect of mixing and enzymatic hydrolysis; mixing...

High spatial resolution spectral unmixing for mapping ash species across a complex urban environment

Treesearch

Jennifer Pontius; Ryan P. Hanavan; Richard A. Hallett; Bruce D. Cook; Lawrence A. Corp

2017-01-01

Ash (Fraxinus L.) species are currently threatened by the emerald ash borer (EAB; Agrilus planipennis Fairmaire) across a growing area in the eastern US. Accurate mapping of ash species is required to monitor the host resource, predict EAB spread and better understand the short- and long-term effects of EAB on the ash resource...

Anion permselective membrane

NASA Technical Reports Server (NTRS)

Hodgdon, R. B.; Waite, W. A.; Alexander, S. S.

1984-01-01

Two polymer ion exchange membranes were synthesized to fulfill the needs of both electrical resistivity and anolyte/catholyte separation for utility load leveling utilizing the DOE/NASA mixed electrolyte REDOX battery. Both membranes were shown to meet mixed electrolyte utility load leveling criteria. Several modifications of an anion exchange membrane failed to meet utility load leveling REDOX battery criteria using the unmixed electrolyte REDOX cell.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Altmann, Yoann; Maccarone, Aurora; McCarthy, Aongus

Here, this paper presents a new Bayesian spectral un-mixing algorithm to analyse remote scenes sensed via sparse multispectral Lidar measurements. To a first approximation, in the presence of a target, each Lidar waveform consists of a main peak, whose position depends on the target distance and whose amplitude depends on the wavelength of the laser source considered (i.e, on the target reflectivity). Besides, these temporal responses are usually assumed to be corrupted by Poisson noise in the low photon count regime. When considering multiple wavelengths, it becomes possible to use spectral information in order to identify and quantify the mainmore » materials in the scene, in addition to estimation of the Lidar-based range profiles. Due to its anomaly detection capability, the proposed hierarchical Bayesian model, coupled with an efficient Markov chain Monte Carlo algorithm, allows robust estimation of depth images together with abundance and outlier maps associated with the observed 3D scene. The proposed methodology is illustrated via experiments conducted with real multispectral Lidar data acquired in a controlled environment. The results demonstrate the possibility to unmix spectral responses constructed from extremely sparse photon counts (less than 10 photons per pixel and band).« less

Hyperspectral and multispectral data fusion based on linear-quadratic nonnegative matrix factorization

NASA Astrophysics Data System (ADS)

Benhalouche, Fatima Zohra; Karoui, Moussa Sofiane; Deville, Yannick; Ouamri, Abdelaziz

2017-04-01

This paper proposes three multisharpening approaches to enhance the spatial resolution of urban hyperspectral remote sensing images. These approaches, related to linear-quadratic spectral unmixing techniques, use a linear-quadratic nonnegative matrix factorization (NMF) multiplicative algorithm. These methods begin by unmixing the observable high-spectral/low-spatial resolution hyperspectral and high-spatial/low-spectral resolution multispectral images. The obtained high-spectral/high-spatial resolution features are then recombined, according to the linear-quadratic mixing model, to obtain an unobservable multisharpened high-spectral/high-spatial resolution hyperspectral image. In the first designed approach, hyperspectral and multispectral variables are independently optimized, once they have been coherently initialized. These variables are alternately updated in the second designed approach. In the third approach, the considered hyperspectral and multispectral variables are jointly updated. Experiments, using synthetic and real data, are conducted to assess the efficiency, in spatial and spectral domains, of the designed approaches and of linear NMF-based approaches from the literature. Experimental results show that the designed methods globally yield very satisfactory spectral and spatial fidelities for the multisharpened hyperspectral data. They also prove that these methods significantly outperform the used literature approaches.

Down-Regulation of Olfactory Receptors in Response to Traumatic Brain Injury Promotes Risk for Alzheimer’s Disease

DTIC Science & Technology

2013-10-01

correct group assignment of samples in unsupervised hierarchical clustering by the Unweighted Pair-Group Method using Arithmetic averages ( UPGMA ) based on...centering of log2 transformed MAS5.0 signal values; probe set clustering was performed by the UPGMA method using Cosine correlation as the similarity met...A) The 108 differentially-regulated genes identified were subjected to unsupervised hierarchical clustering analysis using the UPGMA algorithm with

Object-oriented feature-tracking algorithms for SAR images of the marginal ice zone

NASA Technical Reports Server (NTRS)

Daida, Jason; Samadani, Ramin; Vesecky, John F.

1990-01-01

An unsupervised method that chooses and applies the most appropriate tracking algorithm from among different sea-ice tracking algorithms is reported. In contrast to current unsupervised methods, this method chooses and applies an algorithm by partially examining a sequential image pair to draw inferences about what was examined. Based on these inferences the reported method subsequently chooses which algorithm to apply to specific areas of the image pair where that algorithm should work best.

An Example of Unsupervised Networks Kohonen's Self-Organizing Feature Map

NASA Technical Reports Server (NTRS)

Niebur, Dagmar

1995-01-01

Kohonen's self-organizing feature map belongs to a class of unsupervised artificial neural network commonly referred to as topographic maps. It serves two purposes, the quantization and dimensionality reduction of date. A short description of its history and its biological context is given. We show that the inherent classification properties of the feature map make it a suitable candidate for solving the classification task in power system areas like load forecasting, fault diagnosis and security assessment.

Precision assessment of some supervised and unsupervised algorithms for genotype discrimination in the genus Pisum using SSR molecular data.

PubMed

Nasiri, Jaber; Naghavi, Mohammad Reza; Kayvanjoo, Amir Hossein; Nasiri, Mojtaba; Ebrahimi, Mansour

2015-03-07

For the first time, prediction accuracies of some supervised and unsupervised algorithms were evaluated in an SSR-based DNA fingerprinting study of a pea collection containing 20 cultivars and 57 wild samples. In general, according to the 10 attribute weighting models, the SSR alleles of PEAPHTAP-2 and PSBLOX13.2-1 were the two most important attributes to generate discrimination among eight different species and subspecies of genus Pisum. In addition, K-Medoids unsupervised clustering run on Chi squared dataset exhibited the best prediction accuracy (83.12%), while the lowest accuracy (25.97%) gained as K-Means model ran on FCdb database. Irrespective of some fluctuations, the overall accuracies of tree induction models were significantly high for many algorithms, and the attributes PSBLOX13.2-3 and PEAPHTAP could successfully detach Pisum fulvum accessions and cultivars from the others when two selected decision trees were taken into account. Meanwhile, the other used supervised algorithms exhibited overall reliable accuracies, even though in some rare cases, they gave us low amounts of accuracies. Our results, altogether, demonstrate promising applications of both supervised and unsupervised algorithms to provide suitable data mining tools regarding accurate fingerprinting of different species and subspecies of genus Pisum, as a fundamental priority task in breeding programs of the crop. Copyright © 2015 Elsevier Ltd. All rights reserved.

Coupling human mobility and social ties.

PubMed

Toole, Jameson L; Herrera-Yaqüe, Carlos; Schneider, Christian M; González, Marta C

2015-04-06

Studies using massive, passively collected data from communication technologies have revealed many ubiquitous aspects of social networks, helping us understand and model social media, information diffusion and organizational dynamics. More recently, these data have come tagged with geographical information, enabling studies of human mobility patterns and the science of cities. We combine these two pursuits and uncover reproducible mobility patterns among social contacts. First, we introduce measures of mobility similarity and predictability and measure them for populations of users in three large urban areas. We find individuals' visitations patterns are far more similar to and predictable by social contacts than strangers and that these measures are positively correlated with tie strength. Unsupervised clustering of hourly variations in mobility similarity identifies three categories of social ties and suggests geography is an important feature to contextualize social relationships. We find that the composition of a user's ego network in terms of the type of contacts they keep is correlated with mobility behaviour. Finally, we extend a popular mobility model to include movement choices based on social contacts and compare its ability to reproduce empirical measurements with two additional models of mobility. © 2015 The Author(s) Published by the Royal Society. All rights reserved.

Class imbalance in unsupervised change detection - A diagnostic analysis from urban remote sensing

NASA Astrophysics Data System (ADS)

Leichtle, Tobias; Geiß, Christian; Lakes, Tobia; Taubenböck, Hannes

2017-08-01

Automatic monitoring of changes on the Earth's surface is an intrinsic capability and simultaneously a persistent methodological challenge in remote sensing, especially regarding imagery with very-high spatial resolution (VHR) and complex urban environments. In order to enable a high level of automatization, the change detection problem is solved in an unsupervised way to alleviate efforts associated with collection of properly encoded prior knowledge. In this context, this paper systematically investigates the nature and effects of class distribution and class imbalance in an unsupervised binary change detection application based on VHR imagery over urban areas. For this purpose, a diagnostic framework for sensitivity analysis of a large range of possible degrees of class imbalance is presented, which is of particular importance with respect to unsupervised approaches where the content of images and thus the occurrence and the distribution of classes are generally unknown a priori. Furthermore, this framework can serve as a general technique to evaluate model transferability in any two-class classification problem. The applied change detection approach is based on object-based difference features calculated from VHR imagery and subsequent unsupervised two-class clustering using k-means, genetic k-means and self-organizing map (SOM) clustering. The results from two test sites with different structural characteristics of the built environment demonstrated that classification performance is generally worse in imbalanced class distribution settings while best results were reached in balanced or close to balanced situations. Regarding suitable accuracy measures for evaluating model performance in imbalanced settings, this study revealed that the Kappa statistics show significant response to class distribution while the true skill statistic was widely insensitive to imbalanced classes. In general, the genetic k-means clustering algorithm achieved the most robust results with respect to class imbalance while the SOM clustering exhibited a distinct optimization towards a balanced distribution of classes.

Involvement of surgical trainees in surgery for colorectal cancer and their effect on outcome.

PubMed

Borowski, D W; Ratcliffe, A A; Bharathan, B; Gunn, A; Bradburn, D M; Mills, S J; Wilson, R G; Kelly, S B

2008-10-01

Surgical training in the UK is undergoing substantial changes. This study assessed: 1) the training opportunities available to trainees in operations for colorectal cancer, 2) the effect of colorectal specialization on training, and 3) the effect of consultant supervision on anastomotic complications, postoperative stay, operative mortality and 5-year survival. Unadjusted and adjusted comparisons of outcomes were made for unsupervised trainees, supervised trainees and consultants as the primary surgeon in 7411 operated patients included in the Northern Region Colorectal Cancer Audit between 1998 and 2002. Surgery was performed in 656 (8.8%) patients by unsupervised trainees and in 1578 (21.3%) patients by supervised trainees. Unsupervised operations reduced from 182 (12.4%) in 1998 to 82 (6.1%) in 2002 (P < 0.001). Consultants with a colorectal specialist interest were more likely than nonspecialists to be present at surgical resections (OR 1.35, 1.12-1.63, P = 0.001) and to provide supervised training (OR 1.34, 1.17-1.53, P < 0.001). Patients operated on by unsupervised trainees were more often high-risk patients, however, consultant presence was not significantly associated with operative mortality (OR 0.83, 0.63-1.09, P = 0.186) or survival (HR 1.02, 0.92-1.13, P = 0.735) in risk-adjusted analysis. Supervised trainees had a case-mix similar to consultants, with shorter length of hospital stay (11.4 vs 12.4 days, P < 0.001), but similar mortality (OR 0.90, 0.71-1.16, 0.418) and survival (HR 0.96, 0.89-1.05, P = 0.378). One third of patients were operated on by trainees, who were more likely to perform supervised resections in colorectal teams. There was no difference in anastomotic leaks rates, operative mortality or survival between unsupervised trainees, supervised trainees and consultants when case-mix adjustment was applied. This study would suggest that there is considerable underused training capacity available.

Unsupervised frequency-recognition method of SSVEPs using a filter bank implementation of binary subband CCA

NASA Astrophysics Data System (ADS)

Rabiul Islam, Md; Khademul Islam Molla, Md; Nakanishi, Masaki; Tanaka, Toshihisa

2017-04-01

Objective. Recently developed effective methods for detection commands of steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) that need calibration for visual stimuli, which cause more time and fatigue prior to the use, as the number of commands increases. This paper develops a novel unsupervised method based on canonical correlation analysis (CCA) for accurate detection of stimulus frequency. Approach. A novel unsupervised technique termed as binary subband CCA (BsCCA) is implemented in a multiband approach to enhance the frequency recognition performance of SSVEP. In BsCCA, two subbands are used and a CCA-based correlation coefficient is computed for the individual subbands. In addition, a reduced set of artificial reference signals is used to calculate CCA for the second subband. The analyzing SSVEP is decomposed into multiple subband and the BsCCA is implemented for each one. Then, the overall recognition score is determined by a weighted sum of the canonical correlation coefficients obtained from each band. Main results. A 12-class SSVEP dataset (frequency range: 9.25-14.75 Hz with an interval of 0.5 Hz) for ten healthy subjects are used to evaluate the performance of the proposed method. The results suggest that BsCCA significantly improves the performance of SSVEP-based BCI compared to the state-of-the-art methods. The proposed method is an unsupervised approach with averaged information transfer rate (ITR) of 77.04 bits min-1 across 10 subjects. The maximum individual ITR is 107.55 bits min-1 for 12-class SSVEP dataset, whereas, the ITR of 69.29 and 69.44 bits min-1 are achieved with CCA and NCCA respectively. Significance. The statistical test shows that the proposed unsupervised method significantly improves the performance of the SSVEP-based BCI. It can be usable in real world applications.

Unsupervised detection and removal of muscle artifacts from scalp EEG recordings using canonical correlation analysis, wavelets and random forests.

PubMed

Anastasiadou, Maria N; Christodoulakis, Manolis; Papathanasiou, Eleftherios S; Papacostas, Savvas S; Mitsis, Georgios D

2017-09-01

This paper proposes supervised and unsupervised algorithms for automatic muscle artifact detection and removal from long-term EEG recordings, which combine canonical correlation analysis (CCA) and wavelets with random forests (RF). The proposed algorithms first perform CCA and continuous wavelet transform of the canonical components to generate a number of features which include component autocorrelation values and wavelet coefficient magnitude values. A subset of the most important features is subsequently selected using RF and labelled observations (supervised case) or synthetic data constructed from the original observations (unsupervised case). The proposed algorithms are evaluated using realistic simulation data as well as 30min epochs of non-invasive EEG recordings obtained from ten patients with epilepsy. We assessed the performance of the proposed algorithms using classification performance and goodness-of-fit values for noisy and noise-free signal windows. In the simulation study, where the ground truth was known, the proposed algorithms yielded almost perfect performance. In the case of experimental data, where expert marking was performed, the results suggest that both the supervised and unsupervised algorithm versions were able to remove artifacts without affecting noise-free channels considerably, outperforming standard CCA, independent component analysis (ICA) and Lagged Auto-Mutual Information Clustering (LAMIC). The proposed algorithms achieved excellent performance for both simulation and experimental data. Importantly, for the first time to our knowledge, we were able to perform entirely unsupervised artifact removal, i.e. without using already marked noisy data segments, achieving performance that is comparable to the supervised case. Overall, the results suggest that the proposed algorithms yield significant future potential for improving EEG signal quality in research or clinical settings without the need for marking by expert neurophysiologists, EMG signal recording and user visual inspection. Copyright © 2017 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.

Disaggregating tree and grass phenology in tropical savannas

NASA Astrophysics Data System (ADS)

Zhou, Qiang

Savannas are mixed tree-grass systems and as one of the world's largest biomes represent an important component of the Earth system affecting water and energy balances, carbon sequestration and biodiversity as well as supporting large human populations. Savanna vegetation structure and its distribution, however, may change because of major anthropogenic disturbances from climate change, wildfire, agriculture, and livestock production. The overstory and understory may have different water use strategies, different nutrient requirements and have different responses to fire and climate variation. The accurate measurement of the spatial distribution and structure of the overstory and understory are essential for understanding the savanna ecosystem. This project developed a workflow for separating the dynamics of the overstory and understory fractional cover in savannas at the continental scale (Australia, South America, and Africa). Previous studies have successfully separated the phenology of Australian savanna vegetation into persistent and seasonal greenness using time series decomposition, and into fractions of photosynthetic vegetation (PV), non-photosynthetic vegetation (NPV) and bare soil (BS) using linear unmixing. This study combined these methods to separate the understory and overstory signal in both the green and senescent phenological stages using remotely sensed imagery from the MODIS (MODerate resolution Imaging Spectroradiometer) sensor. The methods and parameters were adjusted based on the vegetation variation. The workflow was first tested at the Australian site. Here the PV estimates for overstory and understory showed best performance, however NPV estimates exhibited spatial variation in validation relationships. At the South American site (Cerrado), an additional method based on frequency unmixing was developed to separate green vegetation components with similar phenology. When the decomposition and frequency methods were compared, the frequency method was better for extracting the green tree phenology, but the original decomposition method was better for retrieval of understory grass phenology. Both methods, however, were less accurate than in the Cerrado than in Australia due to intermingling and intergrading of grass and small woody components. Since African savanna trees are predominantly deciduous, the frequency method was combined with the linear unmixing of fractional cover to attempt to separate the relatively similar phenology of deciduous trees and seasonal grasses. The results for Africa revealed limitations associated with both methods. There was spatial and seasonal variation in the spectral indices used to unmix fractional cover resulting in poor validation for NPV in particular. The frequency analysis revealed significant phase variation indicative of different phenology, but these could not be clearly ascribed to separate grass and tree components. Overall findings indicate that site-specific variation and vegetation structure and composition, along with MODIS pixel resolution, and the simple vegetation index approach used was not robust across the different savanna biomes. The approach showed generally better performance for estimating PV fraction, and separating green phenology, but there were major inconsistencies, errors and biases in estimation of NPV and BS outside of the Australian savanna environment.

Medical tourism-A New Arena

PubMed Central

Puri, S; Singh, A; Yashik

2010-01-01

Globalisation has given birth to medical tourism. Health and medical tourism are the fastest growing segments in not only developed nations but in developing countries too. India has become a hot destination, as the Indian medical standards match up to the highly prescribed international standards at a very low cost. However, it is an unmixed blessing; along with advantages, it has many unintended side effects also. PMID:23113017

Evaluation of linear spectral unmixing and deltaNBR for predicting post-fire recovery in a North American ponderosa pine forest

Treesearch

A. M. S. Smith; L. B. Lenilte; A. T. Hudak; P. Morgan

2007-01-01

The Differenced Normalized Burn Ratio (deltaNBR) is widely used to map post-fire effects in North America from multispectral satellite imagery, but has not been rigorously validated across the great diversity in vegetation types. The importance of these maps to fire rehabilitation crews highlights the need for continued assessment of alternative remote sensing...

Unmixing the Materials and Mechanics Contributions in Non-resolved Object Signatures

DTIC Science & Technology

2008-09-01

abundances from hyperspectral or multi-spectral time - resolved signatures. A Fourier analysis of temporal variation of material abundance provides...factorization technique to extract the temporal variation of material abundances from hyperspectral or multi-spectral time - resolved signatures. A Fourier...approximately one hundred wavelengths in the visible spectrum. The frame rate for the instrument was not large enough to collect time resolved data. However

Evaluation of algorithm methods for fluorescence spectra of cancerous and normal human tissues

NASA Astrophysics Data System (ADS)

Pu, Yang; Wang, Wubao; Alfano, Robert R.

2016-03-01

The paper focus on the various algorithms on to unravel the fluorescence spectra by unmixing methods to identify cancerous and normal human tissues from the measured fluorescence spectroscopy. The biochemical or morphologic changes that cause fluorescence spectra variations would appear earlier than the histological approach; therefore, fluorescence spectroscopy holds a great promise as clinical tool for diagnosing early stage of carcinomas and other deceases for in vivo use. The method can further identify tissue biomarkers by decomposing the spectral contributions of different fluorescent molecules of interest. In this work, we investigate the performance of blind source un-mixing methods (backward model) and spectral fitting approaches (forward model) in decomposing the contributions of key fluorescent molecules from the tissue mixture background when certain selected excitation wavelength is applied. Pairs of adenocarcinoma as well as normal tissues confirmed by pathologist were excited by selective wavelength of 340 nm. The emission spectra of resected fresh tissue were used to evaluate the relative changes of collagen, reduced nicotinamide adenine dinucleotide (NADH), and Flavin by various spectral un-mixing methods. Two categories of algorithms: forward methods and Blind Source Separation [such as Principal Component Analysis (PCA) and Independent Component Analysis (ICA), and Nonnegative Matrix Factorization (NMF)] will be introduced and evaluated. The purpose of the spectral analysis is to discard the redundant information which conceals the difference between these two types of tissues, but keep their diagnostically significance. The facts predicted by different methods were compared to the gold standard of histopathology. The results indicate that these key fluorophores within tissue, e.g. tryptophan, collagen, and NADH, and flavin, show differences of relative contents of fluorophores among different types of human cancer and normal tissues. The sensitivity, specificity, and receiver operating characteristic (ROC) are finally employed as the criteria to evaluate the efficacy of these methods in cancer detection. The underlying physical and biological basis for these optical approaches will be discussed with examples. This ex vivo preliminary trial demonstrates that these different criteria from different methods can distinguish carcinoma from normal tissues with good sensitivity and specificity while among them, we found that ICA appears to be the superior method in predication accuracy.

Discrimination of Sedimentary Lithologies Through Unmixing of EO-1 Hyperion Data: Melville Island, Canadian High Arctic

NASA Astrophysics Data System (ADS)

Leverington, D. W.

2008-12-01

The use of remote-sensing techniques in the discrimination of rock and soil classes in northern regions can help support a diverse range of activities including environmental characterization, mineral exploration, and the study of Quaternary paleoenvironments. Images of low spectral resolution can commonly be used in the mapping of lithological classes possessing distinct spectral characteristics, but hyperspectral databases offer greater potential for discrimination of materials distinguished by more subtle reflectance properties. Orbiting sensors offer an especially flexible and cost-effective means for acquisition of data to workers unable to conduct airborne surveys. In an effort to better constrain the utility of hyperspectral datasets in northern research, this study undertook to investigate the effectiveness of EO-1 Hyperion data in the discrimination and mapping of surface classes at a study area on Melville Island, Nunavut. Bedrock units in the immediate study area consist of late-Paleozoic clastic and carbonate sequences of the Sverdrup Basin. Weathered and frost-shattered felsenmeer, predominantly taking the form of boulder- to pebble-sized clasts that have accumulated in place and that mantle parent bedrock units, is the most common surface material in the study area. Hyperion data were converted from at-sensor radiance to reflectance, and were then linearly unmixed on the basis of end-member spectra measured from field samples. Hyperion unmixing results effectively portray the general fractional cover of six end members, although the fraction images of several materials contain background values that in some areas overestimate surface exposure. The best separated end members include the snow, green vegetation, and red-weathering sandstone classes, whereas the classes most negatively affected by elevated fraction values include the mudstone, limestone, and 'other' sandstone classes. Local overestimates of fractional cover are likely related to the shared lithological and weathering characteristics of several clastic and carbonate units, and may also be related to the lower radiometric precision characteristic of Hyperion data. Despite these issues, the databases generated in this study successfully provide useful complementary information to that provided by maps of local bedrock geology.

An unsupervised method for quantifying the behavior of paired animals

NASA Astrophysics Data System (ADS)

Klibaite, Ugne; Berman, Gordon J.; Cande, Jessica; Stern, David L.; Shaevitz, Joshua W.

2017-02-01

Behaviors involving the interaction of multiple individuals are complex and frequently crucial for an animal’s survival. These interactions, ranging across sensory modalities, length scales, and time scales, are often subtle and difficult to characterize. Contextual effects on the frequency of behaviors become even more difficult to quantify when physical interaction between animals interferes with conventional data analysis, e.g. due to visual occlusion. We introduce a method for quantifying behavior in fruit fly interaction that combines high-throughput video acquisition and tracking of individuals with recent unsupervised methods for capturing an animal’s entire behavioral repertoire. We find behavioral differences between solitary flies and those paired with an individual of the opposite sex, identifying specific behaviors that are affected by social and spatial context. Our pipeline allows for a comprehensive description of the interaction between two individuals using unsupervised machine learning methods, and will be used to answer questions about the depth of complexity and variance in fruit fly courtship.

Modelling unsupervised online-learning of artificial grammars: linking implicit and statistical learning.

PubMed

Rohrmeier, Martin A; Cross, Ian

2014-07-01

Humans rapidly learn complex structures in various domains. Findings of above-chance performance of some untrained control groups in artificial grammar learning studies raise questions about the extent to which learning can occur in an untrained, unsupervised testing situation with both correct and incorrect structures. The plausibility of unsupervised online-learning effects was modelled with n-gram, chunking and simple recurrent network models. A novel evaluation framework was applied, which alternates forced binary grammaticality judgments and subsequent learning of the same stimulus. Our results indicate a strong online learning effect for n-gram and chunking models and a weaker effect for simple recurrent network models. Such findings suggest that online learning is a plausible effect of statistical chunk learning that is possible when ungrammatical sequences contain a large proportion of grammatical chunks. Such common effects of continuous statistical learning may underlie statistical and implicit learning paradigms and raise implications for study design and testing methodologies. Copyright © 2014 Elsevier Inc. All rights reserved.

Supervised and Unsupervised Aspect Category Detection for Sentiment Analysis with Co-occurrence Data.

PubMed

Schouten, Kim; van der Weijde, Onne; Frasincar, Flavius; Dekker, Rommert

2018-04-01

Using online consumer reviews as electronic word of mouth to assist purchase-decision making has become increasingly popular. The Web provides an extensive source of consumer reviews, but one can hardly read all reviews to obtain a fair evaluation of a product or service. A text processing framework that can summarize reviews, would therefore be desirable. A subtask to be performed by such a framework would be to find the general aspect categories addressed in review sentences, for which this paper presents two methods. In contrast to most existing approaches, the first method presented is an unsupervised method that applies association rule mining on co-occurrence frequency data obtained from a corpus to find these aspect categories. While not on par with state-of-the-art supervised methods, the proposed unsupervised method performs better than several simple baselines, a similar but supervised method, and a supervised baseline, with an -score of 67%. The second method is a supervised variant that outperforms existing methods with an -score of 84%.

Unsupervised self-testing as part public health screening for HIV in resource-poor environments: some ethical considerations.

PubMed

Scott, P Anne

2014-07-01

The use of unsupervised self-testing as part of a national screening program for HIV infection in resource-poor environments with high HIV prevalence may have a number of attractive aspects, such as increasing access to services for hard to reach and isolated populations. However, the presence of such technologies is at a relatively early stage in terms of use and impact in the field. In this paper, a principle-based approach, that recognizes the fundamentally utilitarian nature of public health combined with a focus on autonomy, is used as a lens to explore some of the ethical issues raised by HIV self-testing. The conclusion reached in this review is that at this point in time, on the basis of the principles of utility and respect for autonomy, it is not ethically appropriate to incorporate unsupervised HIV self-testing as part of a public health screening program in resource-poor environments.

A new simple /spl infin/OH neuron model as a biologically plausible principal component analyzer.

PubMed

Jankovic, M V

2003-01-01

A new approach to unsupervised learning in a single-layer neural network is discussed. An algorithm for unsupervised learning based upon the Hebbian learning rule is presented. A simple neuron model is analyzed. A dynamic neural model, which contains both feed-forward and feedback connections between the input and the output, has been adopted. The, proposed learning algorithm could be more correctly named self-supervised rather than unsupervised. The solution proposed here is a modified Hebbian rule, in which the modification of the synaptic strength is proportional not to pre- and postsynaptic activity, but instead to the presynaptic and averaged value of postsynaptic activity. It is shown that the model neuron tends to extract the principal component from a stationary input vector sequence. Usually accepted additional decaying terms for the stabilization of the original Hebbian rule are avoided. Implementation of the basic Hebbian scheme would not lead to unrealistic growth of the synaptic strengths, thanks to the adopted network structure.

Unsupervised learning of facial emotion decoding skills.

PubMed

Huelle, Jan O; Sack, Benjamin; Broer, Katja; Komlewa, Irina; Anders, Silke

2014-01-01

Research on the mechanisms underlying human facial emotion recognition has long focussed on genetically determined neural algorithms and often neglected the question of how these algorithms might be tuned by social learning. Here we show that facial emotion decoding skills can be significantly and sustainably improved by practice without an external teaching signal. Participants saw video clips of dynamic facial expressions of five different women and were asked to decide which of four possible emotions (anger, disgust, fear, and sadness) was shown in each clip. Although no external information about the correctness of the participant's response or the sender's true affective state was provided, participants showed a significant increase of facial emotion recognition accuracy both within and across two training sessions two days to several weeks apart. We discuss several similarities and differences between the unsupervised improvement of facial decoding skills observed in the current study, unsupervised perceptual learning of simple stimuli described in previous studies and practice effects often observed in cognitive tasks.

Unsupervised learning of facial emotion decoding skills

PubMed Central

Huelle, Jan O.; Sack, Benjamin; Broer, Katja; Komlewa, Irina; Anders, Silke

2013-01-01

Research on the mechanisms underlying human facial emotion recognition has long focussed on genetically determined neural algorithms and often neglected the question of how these algorithms might be tuned by social learning. Here we show that facial emotion decoding skills can be significantly and sustainably improved by practice without an external teaching signal. Participants saw video clips of dynamic facial expressions of five different women and were asked to decide which of four possible emotions (anger, disgust, fear, and sadness) was shown in each clip. Although no external information about the correctness of the participant’s response or the sender’s true affective state was provided, participants showed a significant increase of facial emotion recognition accuracy both within and across two training sessions two days to several weeks apart. We discuss several similarities and differences between the unsupervised improvement of facial decoding skills observed in the current study, unsupervised perceptual learning of simple visual stimuli described in previous studies and practice effects often observed in cognitive tasks. PMID:24578686

Infrared vehicle recognition using unsupervised feature learning based on K-feature

NASA Astrophysics Data System (ADS)

Lin, Jin; Tan, Yihua; Xia, Haijiao; Tian, Jinwen

2018-02-01

Subject to the complex battlefield environment, it is difficult to establish a complete knowledge base in practical application of vehicle recognition algorithms. The infrared vehicle recognition is always difficult and challenging, which plays an important role in remote sensing. In this paper we propose a new unsupervised feature learning method based on K-feature to recognize vehicle in infrared images. First, we use the target detection algorithm which is based on the saliency to detect the initial image. Then, the unsupervised feature learning based on K-feature, which is generated by Kmeans clustering algorithm that extracted features by learning a visual dictionary from a large number of samples without label, is calculated to suppress the false alarm and improve the accuracy. Finally, the vehicle target recognition image is finished by some post-processing. Large numbers of experiments demonstrate that the proposed method has satisfy recognition effectiveness and robustness for vehicle recognition in infrared images under complex backgrounds, and it also improve the reliability of it.

Analyzing Distributional Learning of Phonemic Categories in Unsupervised Deep Neural Networks

PubMed Central

Räsänen, Okko; Nagamine, Tasha; Mesgarani, Nima

2017-01-01

Infants’ speech perception adapts to the phonemic categories of their native language, a process assumed to be driven by the distributional properties of speech. This study investigates whether deep neural networks (DNNs), the current state-of-the-art in distributional feature learning, are capable of learning phoneme-like representations of speech in an unsupervised manner. We trained DNNs with unlabeled and labeled speech and analyzed the activations of each layer with respect to the phones in the input segments. The analyses reveal that the emergence of phonemic invariance in DNNs is dependent on the availability of phonemic labeling of the input during the training. No increased phonemic selectivity of the hidden layers was observed in the purely unsupervised networks despite successful learning of low-dimensional representations for speech. This suggests that additional learning constraints or more sophisticated models are needed to account for the emergence of phone-like categories in distributional learning operating on natural speech. PMID:29359204

Discovering motion primitives for unsupervised grouping and one-shot learning of human actions, gestures, and expressions.

PubMed

Yang, Yang; Saleemi, Imran; Shah, Mubarak

2013-07-01

This paper proposes a novel representation of articulated human actions and gestures and facial expressions. The main goals of the proposed approach are: 1) to enable recognition using very few examples, i.e., one or k-shot learning, and 2) meaningful organization of unlabeled datasets by unsupervised clustering. Our proposed representation is obtained by automatically discovering high-level subactions or motion primitives, by hierarchical clustering of observed optical flow in four-dimensional, spatial, and motion flow space. The completely unsupervised proposed method, in contrast to state-of-the-art representations like bag of video words, provides a meaningful representation conducive to visual interpretation and textual labeling. Each primitive action depicts an atomic subaction, like directional motion of limb or torso, and is represented by a mixture of four-dimensional Gaussian distributions. For one--shot and k-shot learning, the sequence of primitive labels discovered in a test video are labeled using KL divergence, and can then be represented as a string and matched against similar strings of training videos. The same sequence can also be collapsed into a histogram of primitives or be used to learn a Hidden Markov model to represent classes. We have performed extensive experiments on recognition by one and k-shot learning as well as unsupervised action clustering on six human actions and gesture datasets, a composite dataset, and a database of facial expressions. These experiments confirm the validity and discriminative nature of the proposed representation.

Coexistence of Reward and Unsupervised Learning During the Operant Conditioning of Neural Firing Rates

PubMed Central

Kerr, Robert R.; Grayden, David B.; Thomas, Doreen A.; Gilson, Matthieu; Burkitt, Anthony N.

2014-01-01

A fundamental goal of neuroscience is to understand how cognitive processes, such as operant conditioning, are performed by the brain. Typical and well studied examples of operant conditioning, in which the firing rates of individual cortical neurons in monkeys are increased using rewards, provide an opportunity for insight into this. Studies of reward-modulated spike-timing-dependent plasticity (RSTDP), and of other models such as R-max, have reproduced this learning behavior, but they have assumed that no unsupervised learning is present (i.e., no learning occurs without, or independent of, rewards). We show that these models cannot elicit firing rate reinforcement while exhibiting both reward learning and ongoing, stable unsupervised learning. To fix this issue, we propose a new RSTDP model of synaptic plasticity based upon the observed effects that dopamine has on long-term potentiation and depression (LTP and LTD). We show, both analytically and through simulations, that our new model can exhibit unsupervised learning and lead to firing rate reinforcement. This requires that the strengthening of LTP by the reward signal is greater than the strengthening of LTD and that the reinforced neuron exhibits irregular firing. We show the robustness of our findings to spike-timing correlations, to the synaptic weight dependence that is assumed, and to changes in the mean reward. We also consider our model in the differential reinforcement of two nearby neurons. Our model aligns more strongly with experimental studies than previous models and makes testable predictions for future experiments. PMID:24475240

Can Iberian red deer (Cervus elaphus hispanicus) discriminate among essential minerals in their diet?

PubMed

Ceacero, Francisco; Landete-Castillejos, Tomás; García, Andrés J; Estévez, José A; Gallego, Laureano

2010-02-01

Optimal foraging predicts that animals should be able to assess the content of important nutrients in food. Ungulates discriminate salt and P, but discrimination of other minerals is controversial even though they are also essential and often limiting. Animal scientists have explained this taste through palatability, which predicts the same pattern of discrimination for calves and hinds and greater consumption by the latter. Social learning may also be involved, predicting a correlation between mother and calf and less consumption by the latter. The present study examines the consumption behaviour of free-choice supplemented minerals by hinds and calves of Iberian red deer (Cervus elaphus hispanicus) to discern between these hypotheses. Behavioural indices of intake correlated with actual mineral consumption (P < 0.001). Mother and calf behavioural indices correlated only for salt-mixed minerals. Calves showed overall behavioural indices of consumption greater than hinds (P < 0.01 and P < 0.001), and also for all single supplements except NaCl, as expected from growth needs and in contrast to the palatability hypothesis. Calves showed a greater consumption of CuSO(4) and lower of Na(2)SeO(3) than pure salt. Hinds showed a different pattern, ingesting lower amounts of all minerals except CuSO(4) and salt. Additional analyses also showed discrimination between minerals unmixed with salt, such as CaHPO(4) and CaCO(3) (P = 0.012 and P = 0.020). The greater intake of growing calves and the different consumption patterns for hinds and calves suggest that deer can discriminate among minerals, and that they do not consume minerals for their palatability or driven by social learning. Therefore, deer may be selecting minerals according to nutritional requirements.

Unsupervised color normalisation for H and E stained histopathology image analysis

NASA Astrophysics Data System (ADS)

Celis, Raúl; Romero, Eduardo

2015-12-01

In histology, each dye component attempts to specifically characterise different microscopic structures. In the case of the Hematoxylin-Eosin (H&E) stain, universally used for routine examination, quantitative analysis may often require the inspection of different morphological signatures related mainly to nuclei patterns, but also to stroma distribution. Nevertheless, computer systems for automatic diagnosis are often fraught by color variations ranging from the capturing device to the laboratory specific staining protocol and stains. This paper presents a novel colour normalisation method for H&E stained histopathology images. This method is based upon the opponent process theory and blindly estimates the best color basis for the Hematoxylin and Eosin stains without relying on prior knowledge. Stain Normalisation and Color Separation are transversal to any Framework of Histopathology Image Analysis.

Applications of LANDSAT data to the integrated economic development of Mindoro, Phillipines

NASA Technical Reports Server (NTRS)

Wagner, T. W.; Fernandez, J. C.

1977-01-01

LANDSAT data is seen as providing essential up-to-date resource information for the planning process. LANDSAT data of Mindoro Island in the Philippines was processed to provide thematic maps showing patterns of agriculture, forest cover, terrain, wetlands and water turbidity. A hybrid approach using both supervised and unsupervised classification techniques resulted in 30 different scene classes which were subsequently color-coded and mapped at a scale of 1:250,000. In addition, intensive image analysis is being carried out in evaluating the images. The images, maps, and aerial statistics are being used to provide data to seven technical departments in planning the economic development of Mindoro. Multispectral aircraft imagery was collected to compliment the application of LANDSAT data and validate the classification results.

The relationship between unsupervised time after school and physical activity in adolescent girls.

PubMed

Rushovich, Berenice R; Voorhees, Carolyn C; Davis, C E; Neumark-Sztainer, Dianne; Pfeiffer, Karin A; Elder, John P; Going, Scott; Marino, Vivian G

2006-07-31

Rising obesity and declining physical activity levels are of great concern because of the associated health risks. Many children are left unsupervised after the school day ends, but little is known about the association between unsupervised time and physical activity levels. This paper seeks to determine whether adolescent girls who are without adult supervision after school are more or less active than their peers who have a caregiver at home. A random sample of girls from 36 middle schools at 6 field sites across the U.S. was selected during the fall of the 2002-2003 school year to participate in the baseline measurement activities of the Trial of Activity for Adolescent Girls (TAAG). Information was collected using six-day objectively measured physical activity, self-reported physical activity using a three-day recall, and socioeconomic and psychosocial measures. Complete information was available for 1422 out of a total of 1596 respondents.Categorical variables were analyzed using chi square and continuous variables were analyzed by t-tests. The four categories of time alone were compared using a mixed linear model controlling for clustering effects by study center. Girls who spent more time after school (> or = 2 hours per day, > or = 2 days per week) without adult supervision were more active than those with adult supervision (p = 0.01). Girls alone for > or = 2 hours after school, > or = 2 days a week, on average accrue 7.55 minutes more moderate to vigorous physical activity (MVPA) per day than do girls who are supervised (95% confidence interval ([C.I]). These results adjusted for ethnicity, parent's education, participation in the free/reduced lunch program, neighborhood resources, or available transportation. Unsupervised girls (n = 279) did less homework (53.1% vs. 63.3%), spent less time riding in a car or bus (48.0% vs. 56.6%), talked on the phone more (35.5% vs. 21.1%), and watched more television (59.9% vs. 52.6%) than supervised girls (n = 569). However, unsupervised girls also were more likely to be dancing (14.0% vs. 9.3%) and listening to music (20.8% vs. 12.0%) (p < .05). Girls in an unsupervised environment engaged in fewer structured activities and did not immediately do their homework, but they were more likely to be physically active than supervised girls. These results may have implications for parents, school, and community agencies as to how to structure activities in order to encourage teenage girls to be more physically active.

The relationship between unsupervised time after school and physical activity in adolescent girls

PubMed Central

Rushovich, Berenice R; Voorhees, Carolyn C; Davis, CE; Neumark-Sztainer, Dianne; Pfeiffer, Karin A; Elder, John P; Going, Scott; Marino, Vivian G

2006-01-01

Background Rising obesity and declining physical activity levels are of great concern because of the associated health risks. Many children are left unsupervised after the school day ends, but little is known about the association between unsupervised time and physical activity levels. This paper seeks to determine whether adolescent girls who are without adult supervision after school are more or less active than their peers who have a caregiver at home. Methods A random sample of girls from 36 middle schools at 6 field sites across the U.S. was selected during the fall of the 2002–2003 school year to participate in the baseline measurement activities of the Trial of Activity for Adolescent Girls (TAAG). Information was collected using six-day objectively measured physical activity, self-reported physical activity using a three-day recall, and socioeconomic and psychosocial measures. Complete information was available for 1422 out of a total of 1596 respondents. Categorical variables were analyzed using chi square and continuous variables were analyzed by t-tests. The four categories of time alone were compared using a mixed linear model controlling for clustering effects by study center. Results Girls who spent more time after school (≥2 hours per day, ≥2 days per week) without adult supervision were more active than those with adult supervision (p = 0.01). Girls alone for ≥2 hours after school, ≥2 days a week, on average accrue 7.55 minutes more moderate to vigorous physical activity (MVPA) per day than do girls who are supervised (95% confidence interval ([C.I]). These results adjusted for ethnicity, parent's education, participation in the free/reduced lunch program, neighborhood resources, or available transportation. Unsupervised girls (n = 279) did less homework (53.1% vs. 63.3%), spent less time riding in a car or bus (48.0% vs. 56.6%), talked on the phone more (35.5% vs. 21.1%), and watched more television (59.9% vs. 52.6%) than supervised girls (n = 569). However, unsupervised girls also were more likely to be dancing (14.0% vs. 9.3%) and listening to music (20.8% vs. 12.0%) (p < .05). Conclusion Girls in an unsupervised environment engaged in fewer structured activities and did not immediately do their homework, but they were more likely to be physically active than supervised girls. These results may have implications for parents, school, and community agencies as to how to structure activities in order to encourage teenage girls to be more physically active. PMID:16879750

Gene expression-based molecular diagnostic system for malignant gliomas is superior to histological diagnosis.

PubMed

Shirahata, Mitsuaki; Iwao-Koizumi, Kyoko; Saito, Sakae; Ueno, Noriko; Oda, Masashi; Hashimoto, Nobuo; Takahashi, Jun A; Kato, Kikuya

2007-12-15

Current morphology-based glioma classification methods do not adequately reflect the complex biology of gliomas, thus limiting their prognostic ability. In this study, we focused on anaplastic oligodendroglioma and glioblastoma, which typically follow distinct clinical courses. Our goal was to construct a clinically useful molecular diagnostic system based on gene expression profiling. The expression of 3,456 genes in 32 patients, 12 and 20 of whom had prognostically distinct anaplastic oligodendroglioma and glioblastoma, respectively, was measured by PCR array. Next to unsupervised methods, we did supervised analysis using a weighted voting algorithm to construct a diagnostic system discriminating anaplastic oligodendroglioma from glioblastoma. The diagnostic accuracy of this system was evaluated by leave-one-out cross-validation. The clinical utility was tested on a microarray-based data set of 50 malignant gliomas from a previous study. Unsupervised analysis showed divergent global gene expression patterns between the two tumor classes. A supervised binary classification model showed 100% (95% confidence interval, 89.4-100%) diagnostic accuracy by leave-one-out cross-validation using 168 diagnostic genes. Applied to a gene expression data set from a previous study, our model correlated better with outcome than histologic diagnosis, and also displayed 96.6% (28 of 29) consistency with the molecular classification scheme used for these histologically controversial gliomas in the original article. Furthermore, we observed that histologically diagnosed glioblastoma samples that shared anaplastic oligodendroglioma molecular characteristics tended to be associated with longer survival. Our molecular diagnostic system showed reproducible clinical utility and prognostic ability superior to traditional histopathologic diagnosis for malignant glioma.

Automated classification of dolphin echolocation click types from the Gulf of Mexico.

PubMed

Frasier, Kaitlin E; Roch, Marie A; Soldevilla, Melissa S; Wiggins, Sean M; Garrison, Lance P; Hildebrand, John A

2017-12-01

Delphinids produce large numbers of short duration, broadband echolocation clicks which may be useful for species classification in passive acoustic monitoring efforts. A challenge in echolocation click classification is to overcome the many sources of variability to recognize underlying patterns across many detections. An automated unsupervised network-based classification method was developed to simulate the approach a human analyst uses when categorizing click types: Clusters of similar clicks were identified by incorporating multiple click characteristics (spectral shape and inter-click interval distributions) to distinguish within-type from between-type variation, and identify distinct, persistent click types. Once click types were established, an algorithm for classifying novel detections using existing clusters was tested. The automated classification method was applied to a dataset of 52 million clicks detected across five monitoring sites over two years in the Gulf of Mexico (GOM). Seven distinct click types were identified, one of which is known to be associated with an acoustically identifiable delphinid (Risso's dolphin) and six of which are not yet identified. All types occurred at multiple monitoring locations, but the relative occurrence of types varied, particularly between continental shelf and slope locations. Automatically-identified click types from autonomous seafloor recorders without verifiable species identification were compared with clicks detected on sea-surface towed hydrophone arrays in the presence of visually identified delphinid species. These comparisons suggest potential species identities for the animals producing some echolocation click types. The network-based classification method presented here is effective for rapid, unsupervised delphinid click classification across large datasets in which the click types may not be known a priori.

Automated classification of dolphin echolocation click types from the Gulf of Mexico

PubMed Central

Roch, Marie A.; Soldevilla, Melissa S.; Wiggins, Sean M.; Garrison, Lance P.; Hildebrand, John A.

2017-01-01

Delphinids produce large numbers of short duration, broadband echolocation clicks which may be useful for species classification in passive acoustic monitoring efforts. A challenge in echolocation click classification is to overcome the many sources of variability to recognize underlying patterns across many detections. An automated unsupervised network-based classification method was developed to simulate the approach a human analyst uses when categorizing click types: Clusters of similar clicks were identified by incorporating multiple click characteristics (spectral shape and inter-click interval distributions) to distinguish within-type from between-type variation, and identify distinct, persistent click types. Once click types were established, an algorithm for classifying novel detections using existing clusters was tested. The automated classification method was applied to a dataset of 52 million clicks detected across five monitoring sites over two years in the Gulf of Mexico (GOM). Seven distinct click types were identified, one of which is known to be associated with an acoustically identifiable delphinid (Risso’s dolphin) and six of which are not yet identified. All types occurred at multiple monitoring locations, but the relative occurrence of types varied, particularly between continental shelf and slope locations. Automatically-identified click types from autonomous seafloor recorders without verifiable species identification were compared with clicks detected on sea-surface towed hydrophone arrays in the presence of visually identified delphinid species. These comparisons suggest potential species identities for the animals producing some echolocation click types. The network-based classification method presented here is effective for rapid, unsupervised delphinid click classification across large datasets in which the click types may not be known a priori. PMID:29216184

Scalable High Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning

PubMed Central

Wu, Guorong; Kim, Minjeong; Wang, Qian; Munsell, Brent C.

2015-01-01

Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data,, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked auto-encoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework image registration experiments were conducted on 7.0-tesla brain MR images. In all experiments, the results showed the new image registration framework consistently demonstrated more accurate registration results when compared to state-of-the-art. PMID:26552069

Heterogeneous activation of the TGFβ pathway in glioblastomas identified by gene expression-based classification using TGFβ-responsive genes

PubMed Central

Xu, Xie L; Kapoun, Ann M

2009-01-01

Background TGFβ has emerged as an attractive target for the therapeutic intervention of glioblastomas. Aberrant TGFβ overproduction in glioblastoma and other high-grade gliomas has been reported, however, to date, none of these reports has systematically examined the components of TGFβ signaling to gain a comprehensive view of TGFβ activation in large cohorts of human glioma patients. Methods TGFβ activation in mammalian cells leads to a transcriptional program that typically affects 5–10% of the genes in the genome. To systematically examine the status of TGFβ activation in high-grade glial tumors, we compiled a gene set of transcriptional response to TGFβ stimulation from tissue culture and in vivo animal studies. These genes were used to examine the status of TGFβ activation in high-grade gliomas including a large cohort of glioblastomas. Unsupervised and supervised classification analysis was performed in two independent, publicly available glioma microarray datasets. Results Unsupervised and supervised classification using the TGFβ-responsive gene list in two independent glial tumor gene expression data sets revealed various levels of TGFβ activation in these tumors. Among glioblastomas, one of the most devastating human cancers, two subgroups were identified that showed distinct TGFβ activation patterns as measured from transcriptional responses. Approximately 62% of glioblastoma samples analyzed showed strong TGFβ activation, while the rest showed a weak TGFβ transcriptional response. Conclusion Our findings suggest heterogeneous TGFβ activation in glioblastomas, which may cause potential differences in responses to anti-TGFβ therapies in these two distinct subgroups of glioblastomas patients. PMID:19192267

Individualized Functional Parcellation of the Human Amygdala Using a Semi-supervised Clustering Method: A 7T Resting State fMRI Study.

PubMed

Zhang, Xianchang; Cheng, Hewei; Zuo, Zhentao; Zhou, Ke; Cong, Fei; Wang, Bo; Zhuo, Yan; Chen, Lin; Xue, Rong; Fan, Yong

2018-01-01

The amygdala plays an important role in emotional functions and its dysfunction is considered to be associated with multiple psychiatric disorders in humans. Cytoarchitectonic mapping has demonstrated that the human amygdala complex comprises several subregions. However, it's difficult to delineate boundaries of these subregions in vivo even if using state of the art high resolution structural MRI. Previous attempts to parcellate this small structure using unsupervised clustering methods based on resting state fMRI data suffered from the low spatial resolution of typical fMRI data, and it remains challenging for the unsupervised methods to define subregions of the amygdala in vivo . In this study, we developed a novel brain parcellation method to segment the human amygdala into spatially contiguous subregions based on 7T high resolution fMRI data. The parcellation was implemented using a semi-supervised spectral clustering (SSC) algorithm at an individual subject level. Under guidance of prior information derived from the Julich cytoarchitectonic atlas, our method clustered voxels of the amygdala into subregions according to similarity measures of their functional signals. As a result, three distinct amygdala subregions can be obtained in each hemisphere for every individual subject. Compared with the cytoarchitectonic atlas, our method achieved better performance in terms of subregional functional homogeneity. Validation experiments have also demonstrated that the amygdala subregions obtained by our method have distinctive, lateralized functional connectivity (FC) patterns. Our study has demonstrated that the semi-supervised brain parcellation method is a powerful tool for exploring amygdala subregional functions.

Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning.

PubMed

Wu, Guorong; Kim, Minjeong; Wang, Qian; Munsell, Brent C; Shen, Dinggang

2016-07-01

Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked autoencoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework, image registration experiments were conducted on 7.0-T brain MR images. In all experiments, the results showed that the new image registration framework consistently demonstrated more accurate registration results when compared to state of the art.

Disentangling dynamic networks: Separated and joint expressions of functional connectivity patterns in time.

PubMed

Leonardi, Nora; Shirer, William R; Greicius, Michael D; Van De Ville, Dimitri

2014-12-01

Resting-state functional connectivity (FC) is highly variable across the duration of a scan. Groups of coevolving connections, or reproducible patterns of dynamic FC (dFC), have been revealed in fluctuating FC by applying unsupervised learning techniques. Based on results from k-means clustering and sliding-window correlations, it has recently been hypothesized that dFC may cycle through several discrete FC states. Alternatively, it has been proposed to represent dFC as a linear combination of multiple FC patterns using principal component analysis. As it is unclear whether sparse or nonsparse combinations of FC patterns are most appropriate, and as this affects their interpretation and use as markers of cognitive processing, the goal of our study was to evaluate the impact of sparsity by performing an empirical evaluation of simulated, task-based, and resting-state dFC. To this aim, we applied matrix factorizations subject to variable constraints in the temporal domain and studied both the reproducibility of ensuing representations of dFC and the expression of FC patterns over time. During subject-driven tasks, dFC was well described by alternating FC states in accordance with the nature of the data. The estimated FC patterns showed a rich structure with combinations of known functional networks enabling accurate identification of three different tasks. During rest, dFC was better described by multiple FC patterns that overlap. The executive control networks, which are critical for working memory, appeared grouped alternately with externally or internally oriented networks. These results suggest that combinations of FC patterns can provide a meaningful way to disentangle resting-state dFC. © 2014 The Authors. Human Brain Mapping published by Wiley Periodicals, Inc.

RS- and GIS-based study on landscape pattern change in the Poyang Lake wetland area, China

NASA Astrophysics Data System (ADS)

Chen, Xiaoling; Li, Hui; Bao, Shuming; Wu, Zhongyi; Fu, Weijuan; Cai, Xiaobin; Zhao, Hongmei; Guo, Peng

2006-10-01

As wetland has been recognized as an important component of ecosystem, it is received ever-increasing attention worldwide. Poyang Lake wetlands, the international wetlands and the largest bird habitat in Asia, play an important role in biodiversity and ecologic protection. However, with the rapid economic growth and urbanization, landscape patterns in the wetlands have dramatically changed in the past three decades. To better understand the wetland landscape dynamics, remote sensing, geographic information system technologies, and the FRAGSTATS landscape analysis program were used to measure landscape patterns. Statistical approach was employed to illustrate the driving forces. In this study, Landsat images (TM and ETM+) from 1989 and 2000 were acquired for the wetland area. The landscapes in the wetland area were classified as agricultural land, urban, wetland, forest, grassland, unused land, and water body using a combination of supervised and unsupervised classification techniques integrated with Digital Elevation Model (DEM). Landscape indices, which are popular for the quantitative analysis of landscape pattern, were then employed to analyze the landscape pattern changes between the two dates in a GIS. From this analysis an understanding of the spatial-temporal patterns of landscape evolution was generated. The results show that wetland area was reduced while fragmentation was increased over the study period. Further investigation was made to examine the relationship between landscape metrics and some other parameters such as urbanization to address the driving forces for those changes. The urban was chosen as center to conduct buffer analysis in a GIS to study the impact of human-induced activities on landscape pattern dynamics. It was found that the selected parameters were significantly correlated with the landscape metrics, which may well indicate the impact of human-induced activities on the wetland landscape pattern dynamics and account for the driving forces.

Effect of animal mixing as a stressor on biomarkers of autophagy and oxidative stress during pig muscle maturation.

PubMed

Rubio-González, A; Potes, Y; Illán-Rodríguez, D; Vega-Naredo, I; Sierra, V; Caballero, B; Fàbrega, E; Velarde, A; Dalmau, A; Oliván, M; Coto-Montes, A

2015-07-01

The objective of this work was to study the postmortem evolution of potential biomarkers of autophagy (Beclin 1, LC3-II/LC3-I ratio) and oxidative stress (total antioxidant activity, TAA; superoxide dismutase activity, SOD and catalase activity, CAT) in the Longissimus dorsi muscle of entire male ((Large White×Landrace)×Duroc) pigs subjected to different management treatments that may promote stress, such as mixing unfamiliar animals at the farm and/or during transport and lairage before slaughter. During the rearing period at the farm, five animals were never mixed after the initial formation of the experimental groups (unmixed group at the farm, UF), whereas 10 animals were subjected to a common routine of being mixed with unfamiliar animals (mixed group at the farm, MF). Furthermore, two different treatments were used during the transport and lairage before slaughter: 10 pigs were not mixed (unmixed group during transport and lairage, UTL), whereas five pigs were mixed with unfamiliar animals on the lorry and during lairage (mixed group during transport and lairage, MTL). These mixing treatments were then combined into three pre-slaughter treatments - namely, UF-UTL, MF-UTL and MF-MTL. The results show that MF-UTL and MF-MTL increased significantly the muscle antioxidant defense (TAA, SOD and CAT) at short postmortem times (4 and 8 h; P<0.001), followed by an earlier depletion of the antioxidant activity at 24 h postmortem (P<0.05). We also found that mixing unfamiliar animals, both at the farm and during transport and lairage, triggers postmortem muscle autophagy, which showed an earlier activation (higher expression of Beclin 1 and LC3-II/LC3-I ratio at 4 h postmortem followed by a decreasing pattern of this ratio along first 24 h postmortem) in the muscle tissues of animals from the MF-UTL and MF-MTL groups, as an adaptive strategy of the muscle cells for counteracting induced stress. From these results, we propose that monitoring the evolution of the main biomarkers of autophagy (Beclin 1, LC3-II/LC3-I ratio) and muscle antioxidant defense (TAA, SOD, CAT) in the muscle tissue within the first 24 h postmortem may help the detection of animal stress and its potential effect on the postmortem muscle metabolism.

Recognizing patterns of visual field loss using unsupervised machine learning

NASA Astrophysics Data System (ADS)

Yousefi, Siamak; Goldbaum, Michael H.; Zangwill, Linda M.; Medeiros, Felipe A.; Bowd, Christopher

2014-03-01

Glaucoma is a potentially blinding optic neuropathy that results in a decrease in visual sensitivity. Visual field abnormalities (decreased visual sensitivity on psychophysical tests) are the primary means of glaucoma diagnosis. One form of visual field testing is Frequency Doubling Technology (FDT) that tests sensitivity at 52 points within the visual field. Like other psychophysical tests used in clinical practice, FDT results yield specific patterns of defect indicative of the disease. We used Gaussian Mixture Model with Expectation Maximization (GEM), (EM is used to estimate the model parameters) to automatically separate FDT data into clusters of normal and abnormal eyes. Principal component analysis (PCA) was used to decompose each cluster into different axes (patterns). FDT measurements were obtained from 1,190 eyes with normal FDT results and 786 eyes with abnormal (i.e., glaucomatous) FDT results, recruited from a university-based, longitudinal, multi-center, clinical study on glaucoma. The GEM input was the 52-point FDT threshold sensitivities for all eyes. The optimal GEM model separated the FDT fields into 3 clusters. Cluster 1 contained 94% normal fields (94% specificity) and clusters 2 and 3 combined, contained 77% abnormal fields (77% sensitivity). For clusters 1, 2 and 3 the optimal number of PCA-identified axes were 2, 2 and 5, respectively. GEM with PCA successfully separated FDT fields from healthy and glaucoma eyes and identified familiar glaucomatous patterns of loss.

Comparative analysis of spectral unmixing and neural networks for estimating small diameter tree above-ground biomass in the State of Mississippi

Treesearch

Moham P. Tiruveedhula; Joseph Fan; Ravi R. Sadasivuni; Surya S. Durbha; David L. Evans

2010-01-01

The accumulation of small diameter trees (SDTs) is becoming a nationwide concern. Forest management practices such as fire suppression and selective cutting of high grade timber have contributed to an overabundance of SDTs in many areas. Alternative value-added utilization of SDTs (for composite wood products and biofuels) has prompted the need to estimate their...

Spectral Unmixing Applied to Desert Soils for the Detection of Sub-Pixel Disturbances

DTIC Science & Technology

2012-09-01

and Glazner, 1997). Rocks underlying Panum Crater consist of the granitic and metamorphic batholith associated with the Sierra Nevada. On top of this...of Management and Budget, Paperwork Reduction Project (0704-0188) Washington DC 20503. 1. AGENCY USE ONLY (Leave blank) 2. REPORT DATE September...technology can be used to detect and characterize surface disturbance both literally (visually) and non-literally (analytically). Non-literal approaches

Mineral and Lithology Mapping of Drill Core Pulps Using Visible and Infrared Spectrometry

DOE Office of Scientific and Technical Information (OSTI.GOV)

Taylor, G. R., E-mail: G.Taylor@unsw.edu.au

2000-12-15

A novel approach for using field spectrometry for determining both the mineralogy and the lithology of drill core pulps (powders) is developed and evaluated. The methodology is developed using material from a single drillhole through a mineralized sequence of rocks from central New South Wales. Mineral library spectra are used in linear unmixing routines to determine the mineral abundances in drill core pulps that represent between 1 m and 3 m of core. Comparison with X-Ray Diffraction (XRD) analyses shows that for most major constituents, spectrometry provides an estimate of quantitative mineralogy that is as reliable as that provided bymore » XRD. Confusion between the absorption features of calcite and those of chlorite causes the calcite contents determined by spectrometry to be unreliable. Convex geometry is used to recognize the spectra of those samples that are extreme and are representative of unique lithologies. Linear unmixing is used to determine the abundance of these lithologies in each drillhole sample and these abundances are used to interpret the geology of the drillhole. The interpreted geology agrees well with conventional drillhole logs of the visible geology and photographs of the split core. The methods developed provide a quick and cost-effective way of determining the lithology and alteration mineralogy of drill core pulps.« less

Application of a combined approach including contamination indexes, geographic information system and multivariate statistical models in levels, distribution and sources study of metals in soils in Northern China

PubMed Central

Huang, Kuixian; Luo, Xingzhang

2018-01-01

The purpose of this study is to recognize the contamination characteristics of trace metals in soils and apportion their potential sources in Northern China to provide a scientific basis for basic of soil environment management and pollution control. The data set of metals for 12 elements in surface soil samples was collected. The enrichment factor and geoaccumulation index were used to identify the general geochemical characteristics of trace metals in soils. The UNMIX and positive matrix factorizations (PMF) models were comparatively applied to apportion their potential sources. Furthermore, geostatistical tools were used to study the spatial distribution of pollution characteristics and to identify the affected regions of sources that were derived from apportionment models. The soils were contaminated by Cd, Hg, Pb and Zn to varying degree. Industrial activities, agricultural activities and natural sources were identified as the potential sources determining the contents of trace metals in soils with contributions of 24.8%–24.9%, 33.3%–37.2% and 38.0%–41.8%, respectively. The slightly different results obtained from UNMIX and PMF might be caused by the estimations of uncertainty and different algorithms within the models. PMID:29474412

The Yearly Variation in Fall-Winter Arctic Winter Vortex Descent

NASA Technical Reports Server (NTRS)

Schoeberl, Mark R.; Newman, Paul A.

1999-01-01

Using the change in HALOE methane profiles from early September to late March, we have estimated the minimum amount of diabatic descent within the polar which takes place during Arctic winter. The year to year variations are a result in the year to year variations in stratospheric wave activity which (1) modify the temperature of the vortex and thus the cooling rate; (2) reduce the apparent descent by mixing high amounts of methane into the vortex. The peak descent amounts from HALOE methane vary from l0km -14km near the arrival altitude of 25 km. Using a diabatic trajectory calculation, we compare forward and backward trajectories over the course of the winter using UKMO assimilated stratospheric data. The forward calculation agrees fairly well with the observed descent. The backward calculation appears to be unable to produce the observed amount of descent, but this is only an apparent effect due to the density decrease in parcels with altitude. Finally we show the results for unmixed descent experiments - where the parcels are fixed in latitude and longitude and allowed to descend based on the local cooling rate. Unmixed descent is found to always exceed mixed descent, because when normal parcel motion is included, the path average cooling is always less than the cooling at a fixed polar point.