[Application of Kohonen Self-Organizing Feature Maps in QSAR of human ADMET and kinase data sets].

PubMed

Hegymegi-Barakonyi, Bálint; Orfi, László; Kéri, György; Kövesdi, István

2013-01-01

QSAR predictions have been proven very useful in a large number of studies for drug design, such as kinase inhibitor design as targets for cancer therapy, however the overall predictability often remains unsatisfactory. To improve predictability of ADMET features and kinase inhibitory data, we present a new method using Kohonen's Self-Organizing Feature Map (SOFM) to cluster molecules based on explanatory variables (X) and separate dissimilar ones. We calculated SOFM clusters for a large number of molecules with human ADMET and kinase inhibitory data, and we showed that chemically similar molecules were in the same SOFM cluster, and within such clusters the QSAR models had significantly better predictability. We used also target variables (Y, e.g. ADMET) jointly with X variables to create a novel type of clustering. With our method, cells of loosely coupled XY data could be identified and separated into different model building sets.

Lead spatio-temporal pattern identification in urban microenvironments using moss bags and the Kohonen self-organizing maps

NASA Astrophysics Data System (ADS)

Deljanin, Isidora; Antanasijević, Davor; Vuković, Gordana; Urošević, Mira Aničić; Tomašević, Milica; Perić-Grujić, Aleksandra; Ristić, Mirjana

2015-09-01

The first investigation of the use of the Kohonen self-organizing map (SOM) which includes lead concentration and its isotopic composition in moss bags to assess the spatial and temporal patterns of lead in the urban microenvironments is presented in this paper. The moss bags experiment was carried out during 2011 in the city tunnel in Belgrade, as well as in street canyons at different heights (4, 8 and 16 m) and in public garages. The moss bags were exposed for 5 and 10 weeks. The results revealed that the 10 weeks period represents suitable exposure time in screening Pb isotopic composition in active biomonitoring analysis. The obtained results showed that the SOM analysis, by recognizing slight differences among moss samples regarding exposure time, horizontal and vertical spatial distribution, with both, contribution of stable lead isotopes and Pb concentration, could be recommended in biomonitoring analysis of lead distribution in urban microenvironments.

Application of Kohonen neural network for evaluation of the contamination of Brazilian breast milk with polychlorinated biphenyls.

PubMed

Kowalski, Cláudia H; da Silva, Gilmare A; Godoy, Helena T; Poppi, Ronei J; Augusto, Fabio

2013-11-15

Due to the tendency of polychlorinated biphenyls (PCB) to accumulate in matrixes with high lipid content, the contamination of the breast milk with these compounds is a serious issue, mainly to the newborn. In this study, milk samples were collected from breastfeeding mothers belonging to 4 Brazilian regions (south, southeast, northeast and north). Twelve PCB were analyzed by HS-SPME-GC-ECD and the corresponding peak areas were correlated to the answers to a questionnaire of general habits, breastfeeding and characteristics of the living places. To realize this exploratory analyze, self-organizing maps generated applying Kohonen neural network were applied. It was possible to verify the occurrence of different PCB congeners in the breast milk relating to the region of the Brazil that the breastfeeding lives, the proximity to an industry, the proximity to a contaminated river or sea, the type of milk (colostrum, foremilk and hindmilk) and the number of past pregnancies. © 2013 Elsevier B.V. All rights reserved.

Direct Analysis in Real Time-Mass Spectrometry & Kohonen Artificial Neural Networks for the Rapid Species Identification of Larvae, Pupae and Adult Life Stages of Carrion Insects.

PubMed

Beyramysoltan, Samira; Giffen, Justine E; Rosati, Jennifer Y; Musah, Rabi Ann

2018-06-20

Species determination of the various life stages of flies (order: Diptera) is challenging, particularly for the immature forms, because analogous life stages of different species are difficult to differentiate morphologically. It is demonstrated here that DART high-resolution mass spectrometry (DART-HRMS) combined with supervised Kohonen Self-Organizing Maps (SOM) enables accomplishment of species-level identification of larvae, pupae and adult life stages of carrion flies. DART-HRMS data for each life stage were acquired from analysis of ethanol suspensions representing Calliphoridae, Phoridae and Sarcophagidae families, without additional sample preparation. After preprocessing, the data were subjected to a combination of minimum Redundancy Maximal Relevance (mRMR) and Sparse Discriminant Analysis (SDA) methods to select the most significant variables for creating accurate SOM models. The resulting data were divided into training and validation sets, and then analyzed by the SOM method to define the proper discrimination models. The 5-fold venetian blind cross-validation misclassification error was below 7% for all life stages, and the validation samples were correctly identified in all cases. The multiclass SOM model also revealed which chemical components were the most significant markers for each species, with several of these being amino acids. The results show that processing of DART-HRMS data using artificial neural networks (ANNs) based on the Kohonen SOM approach enables rapid discrimination and identification of fly species even for the immature life stages. The ANNs can be continuously expanded to include a larger number of species, and can be used to screen DART-HRMS data from unknowns to rapidly determine species identity.

The use of diagnostic ratios, biomarkers and 3-way Kohonen neural networks to monitor the temporal evolution of oil spills.

PubMed

Fernández-Varela, R; Gómez-Carracedo, M P; Ballabio, D; Andrade, J M

2015-07-15

Oil spill identification relies usually on a wealth of chromatographic data which requires advanced data treatment (chemometrics). A simple approach based on Kohonen neural networks to handle three-dimensional arrays is presented. A suite of 28 diagnostic ratios was considered to monitor six oils along four months. It was found that some traditional diagnostic ratios were not stable enough. In particular, alkylated PAHs (e.g. 1-methyldibenzothiophene, 4-methylpyrene, 27bbSTER and the TA21 and TA26 triaromatic steroids) seemed less resistant to medium-weathering than biomarkers. One (or two) ratios were found to differentiate each product: 30O, 28ab (and 25nor30ab), C3-dbt/C3-phe, 27Ts, TA26 and 29Ts characterized Ashtart, Brent, Maya, Sahara, IFO and Prestige oils, respectively. Copyright © 2015 Elsevier Ltd. All rights reserved.

Enhancing the applicability of Kohonen Self-Organizing Map (KSOM) estimator for gap-filling in hydrometeorological timeseries data

NASA Astrophysics Data System (ADS)

Nanda, Trushnamayee; Sahoo, Bhabagrahi; Chatterjee, Chandranath

2017-06-01

The Kohonen Self-Organizing Map (KSOM) estimator is prescribed as a useful tool for infilling the missing data in hydrometeorology. However, in this study, when the performance of the KSOM estimator is tested for gap-filling in the streamflow, rainfall, evapotranspiration (ET), and temperature timeseries data, collected from 30 gauging stations in India under missing data situations, it is felt that the KSOM modeling performance could be further improved. Consequently, this study tries to answer the research questions as to whether the length of record of the historical data and its variability has any effect on the performance of the KSOM? Whether inclusion of temporal distribution of timeseries data and the nature of outliers in the KSOM framework enhances its performance further? Subsequently, it is established that the KSOM framework should include the coefficient of variation of the datasets for determination of the number of map units, without considering it as a single value function of the sample data size. This could help to upscale and generalize the applicability of KSOM for varied hydrometeorological data types.

A large sample of Kohonen selected E+A (post-starburst) galaxies from the Sloan Digital Sky Survey

NASA Astrophysics Data System (ADS)

Meusinger, H.; Brünecke, J.; Schalldach, P.; in der Au, A.

2017-01-01

Context. The galaxy population in the contemporary Universe is characterised by a clear bimodality, blue galaxies with significant ongoing star formation and red galaxies with only a little. The migration between the blue and the red cloud of galaxies is an issue of active research. Post starburst (PSB) galaxies are thought to be observed in the short-lived transition phase. Aims: We aim to create a large sample of local PSB galaxies from the Sloan Digital Sky Survey (SDSS) to study their characteristic properties, particularly morphological features indicative of gravitational distortions and indications for active galactic nuclei (AGNs). Another aim is to present a tool set for an efficient search in a large database of SDSS spectra based on Kohonen self-organising maps (SOMs). Methods: We computed a huge Kohonen SOM for ∼106 spectra from SDSS data release 7. The SOM is made fully available, in combination with an interactive user interface, for the astronomical community. We selected a large sample of PSB galaxies taking advantage of the clustering behaviour of the SOM. The morphologies of both PSB galaxies and randomly selected galaxies from a comparison sample in SDSS Stripe 82 (S82) were inspected on deep co-added SDSS images to search for indications of gravitational distortions. We used the Portsmouth galaxy property computations to study the evolutionary stage of the PSB galaxies and archival multi-wavelength data to search for hidden AGNs. Results: We compiled a catalogue of 2665 PSB galaxies with redshifts z < 0.4, among them 74 galaxies in S82 with EW(Hδ) > 3 Å and z < 0.25. In the colour-mass diagram, the PSB sample is clearly concentrated towards the region between the red and the blue cloud, in agreement with the idea that PSB galaxies represent the transitioning phase between actively and passively evolving galaxies. The relative frequency of distorted PSB galaxies is at least 57% for EW(Hδ) > 5 Å, significantly higher than in the comparison

A Graphical, Self-Organizing Approach to Classifying Electronic Meeting Output.

ERIC Educational Resources Information Center

Orwig, Richard E.; Chen, Hsinchun; Nunamaker, Jay F., Jr.

1997-01-01

Describes research using an artificial intelligence approach in the application of a Kohonen Self-Organizing Map (SOM) to the problem of classification of electronic brainstorming output and an evaluation of the results. The graphical representation of textual data produced by the Kohonen SOM suggests many opportunities for improving information…

Discussions on Some Educational Issues VIII. Research Report 204.

ERIC Educational Resources Information Center

Kansanen, Pertti, Ed.

This book contains six papers: "Studying the Teachers Life and Work" (Ivor F. Goodson); "Mindful Orientation in Teachers' Pedagogical Thinking" (Jukka Husu); "The Way Thinking is Once Again" (Pertti Kansanen); "Preparing Prospective Elementary Teachers to Teach Mathematics: A Problem-Solving Approach" (Frank…

A large sample of Kohonen-selected SDSS quasars with weak emission lines: selection effects and statistical properties

NASA Astrophysics Data System (ADS)

Meusinger, H.; Balafkan, N.

2014-08-01

Aims: A tiny fraction of the quasar population shows remarkably weak emission lines. Several hypotheses have been developed, but the weak line quasar (WLQ) phenomenon still remains puzzling. The aim of this study was to create a sizeable sample of WLQs and WLQ-like objects and to evaluate various properties of this sample. Methods: We performed a search for WLQs in the spectroscopic data from the Sloan Digital Sky Survey Data Release 7 based on Kohonen self-organising maps for nearly 105 quasar spectra. The final sample consists of 365 quasars in the redshift range z = 0.6 - 4.2 (z¯ = 1.50 ± 0.45) and includes in particular a subsample of 46 WLQs with equivalent widths WMg ii< 11 Å and WC iv< 4.8 Å. We compared the luminosities, black hole masses, Eddington ratios, accretion rates, variability, spectral slopes, and radio properties of the WLQs with those of control samples of ordinary quasars. Particular attention was paid to selection effects. Results: The WLQs have, on average, significantly higher luminosities, Eddington ratios, and accretion rates. About half of the excess comes from a selection bias, but an intrinsic excess remains probably caused primarily by higher accretion rates. The spectral energy distribution shows a bluer continuum at rest-frame wavelengths ≳1500 Å. The variability in the optical and UV is relatively low, even taking the variability-luminosity anti-correlation into account. The percentage of radio detected quasars and of core-dominant radio sources is significantly higher than for the control sample, whereas the mean radio-loudness is lower. Conclusions: The properties of our WLQ sample can be consistently understood assuming that it consists of a mix of quasars at the beginning of a stage of increased accretion activity and of beamed radio-quiet quasars. The higher luminosities and Eddington ratios in combination with a bluer spectral energy distribution can be explained by hotter continua, i.e. higher accretion rates. If

Self-organization and clustering algorithms

NASA Technical Reports Server (NTRS)

Bezdek, James C.

1991-01-01

Kohonen's feature maps approach to clustering is often likened to the k or c-means clustering algorithms. Here, the author identifies some similarities and differences between the hard and fuzzy c-Means (HCM/FCM) or ISODATA algorithms and Kohonen's self-organizing approach. The author concludes that some differences are significant, but at the same time there may be some important unknown relationships between the two methodologies. Several avenues of research are proposed.

Sea level forecasts using neural networks

NASA Astrophysics Data System (ADS)

Röske, Frank

1997-03-01

In this paper, a new method for predicting the sea level employing a neural network approach is introduced. It was designed to improve the prediction of the sea level along the German North Sea Coast under standard conditions. The sea level at any given time depends upon the tides as well as meteorological and oceanographic factors, such as the winds and external surges induced by air pressure. Since tidal predictions are already sufficiently accurate, they have been subtracted from the observed sea levels. The differences will be predicted up to 18 hours in advance. In this paper, the differences are called anomalies. The prediction of the sea level each hour is distinguished from its predictions at the times of high and low tide. For this study, Cuxhaven was selected as a reference site. The predictions made using neural networks were compared for accuracy with the prognoses prepared using six models: two hydrodynamic models, a statistical model, a nearest neighbor model, which is based on analogies, the persistence model, and the verbal forecasts that are broadcast and kept on record by the Sea Level Forecast Service of the Federal Maritime and Hydrography Agency (BSH) in Hamburg. Predictions were calculated for the year 1993 and compared with the actual levels measured. Artificial neural networks are capable of learning. By applying them to the prediction of sea levels, learning from past events has been attempted. It was also attempted to make the experiences of expert forecasters objective. Instead of using the wide-spread back-propagation networks, the self-organizing feature map of Kohonen, or “Kohonen network”, was applied. The fundamental principle of this network is the transformation of the signal similarity into the neighborhood of the neurons while preserving the topology of the signal space. The self-organization procedure of Kohonen networks can be visualized. To make predictions, these networks have been subdivided into a part describing the

Detection of Anomalies in Hydrometric Data Using Artificial Intelligence Techniques

NASA Astrophysics Data System (ADS)

Lauzon, N.; Lence, B. J.

2002-12-01

This work focuses on the detection of anomalies in hydrometric data sequences, such as 1) outliers, which are individual data having statistical properties that differ from those of the overall population; 2) shifts, which are sudden changes over time in the statistical properties of the historical records of data; and 3) trends, which are systematic changes over time in the statistical properties. For the purpose of the design and management of water resources systems, it is important to be aware of these anomalies in hydrometric data, for they can induce a bias in the estimation of water quantity and quality parameters. These anomalies may be viewed as specific patterns affecting the data, and therefore pattern recognition techniques can be used for identifying them. However, the number of possible patterns is very large for each type of anomaly and consequently large computing capacities are required to account for all possibilities using the standard statistical techniques, such as cluster analysis. Artificial intelligence techniques, such as the Kohonen neural network and fuzzy c-means, are clustering techniques commonly used for pattern recognition in several areas of engineering and have recently begun to be used for the analysis of natural systems. They require much less computing capacity than the standard statistical techniques, and therefore are well suited for the identification of outliers, shifts and trends in hydrometric data. This work constitutes a preliminary study, using synthetic data representing hydrometric data that can be found in Canada. The analysis of the results obtained shows that the Kohonen neural network and fuzzy c-means are reasonably successful in identifying anomalies. This work also addresses the problem of uncertainties inherent to the calibration procedures that fit the clusters to the possible patterns for both the Kohonen neural network and fuzzy c-means. Indeed, for the same database, different sets of clusters can be

Static hand gesture recognition from a video

NASA Astrophysics Data System (ADS)

Rokade, Rajeshree S.; Doye, Dharmpal

2011-10-01

A sign language (also signed language) is a language which, instead of acoustically conveyed sound patterns, uses visually transmitted sign patterns to convey meaning- "simultaneously combining hand shapes, orientation and movement of the hands". Sign languages commonly develop in deaf communities, which can include interpreters, friends and families of deaf people as well as people who are deaf or hard of hearing themselves. In this paper, we proposed a novel system for recognition of static hand gestures from a video, based on Kohonen neural network. We proposed algorithm to separate out key frames, which include correct gestures from a video sequence. We segment, hand images from complex and non uniform background. Features are extracted by applying Kohonen on key frames and recognition is done.

Applying of the Artificial Neural Networks (ANN) to Identify and Characterize Sweet Spots in Shale Gas Formations

NASA Astrophysics Data System (ADS)

Puskarczyk, Edyta

2018-03-01

The main goal of the study was to enhance and improve information about the Ordovician and Silurian gas-saturated shale formations. Author focused on: firstly, identification of the shale gas formations, especially the sweet spots horizons, secondly, classification and thirdly, the accurate characterization of divisional intervals. Data set comprised of standard well logs from the selected well. Shale formations are represented mainly by claystones, siltstones, and mudstones. The formations are also partially rich in organic matter. During the calculations, information about lithology of stratigraphy weren't taken into account. In the analysis, selforganizing neural network - Kohonen Algorithm (ANN) was used for sweet spots identification. Different networks and different software were tested and the best network was used for application and interpretation. As a results of Kohonen networks, groups corresponding to the gas-bearing intervals were found. The analysis showed diversification between gas-bearing formations and surrounding beds. It is also shown that internal diversification in sweet spots is present. Kohonen algorithm was also used for geological interpretation of well log data and electrofacies prediction. Reliable characteristic into groups shows that Ja Mb and Sa Fm which are usually treated as potential sweet spots only partially have good reservoir conditions. It is concluded that ANN appears to be useful and quick tool for preliminary classification of members and sweet spots identification.

The new and computationally efficient MIL-SOM algorithm: potential benefits for visualization and analysis of a large-scale high-dimensional clinically acquired geographic data.

PubMed

Oyana, Tonny J; Achenie, Luke E K; Heo, Joon

2012-01-01

The objective of this paper is to introduce an efficient algorithm, namely, the mathematically improved learning-self organizing map (MIL-SOM) algorithm, which speeds up the self-organizing map (SOM) training process. In the proposed MIL-SOM algorithm, the weights of Kohonen's SOM are based on the proportional-integral-derivative (PID) controller. Thus, in a typical SOM learning setting, this improvement translates to faster convergence. The basic idea is primarily motivated by the urgent need to develop algorithms with the competence to converge faster and more efficiently than conventional techniques. The MIL-SOM algorithm is tested on four training geographic datasets representing biomedical and disease informatics application domains. Experimental results show that the MIL-SOM algorithm provides a competitive, better updating procedure and performance, good robustness, and it runs faster than Kohonen's SOM.

Communications and control for electric power systems: Power flow classification for static security assessment

NASA Technical Reports Server (NTRS)

Niebur, D.; Germond, A.

1993-01-01

This report investigates the classification of power system states using an artificial neural network model, Kohonen's self-organizing feature map. The ultimate goal of this classification is to assess power system static security in real-time. Kohonen's self-organizing feature map is an unsupervised neural network which maps N-dimensional input vectors to an array of M neurons. After learning, the synaptic weight vectors exhibit a topological organization which represents the relationship between the vectors of the training set. This learning is unsupervised, which means that the number and size of the classes are not specified beforehand. In the application developed in this report, the input vectors used as the training set are generated by off-line load-flow simulations. The learning algorithm and the results of the organization are discussed.

The New and Computationally Efficient MIL-SOM Algorithm: Potential Benefits for Visualization and Analysis of a Large-Scale High-Dimensional Clinically Acquired Geographic Data

PubMed Central

Oyana, Tonny J.; Achenie, Luke E. K.; Heo, Joon

2012-01-01

The objective of this paper is to introduce an efficient algorithm, namely, the mathematically improved learning-self organizing map (MIL-SOM) algorithm, which speeds up the self-organizing map (SOM) training process. In the proposed MIL-SOM algorithm, the weights of Kohonen's SOM are based on the proportional-integral-derivative (PID) controller. Thus, in a typical SOM learning setting, this improvement translates to faster convergence. The basic idea is primarily motivated by the urgent need to develop algorithms with the competence to converge faster and more efficiently than conventional techniques. The MIL-SOM algorithm is tested on four training geographic datasets representing biomedical and disease informatics application domains. Experimental results show that the MIL-SOM algorithm provides a competitive, better updating procedure and performance, good robustness, and it runs faster than Kohonen's SOM. PMID:22481977

A search for new glucophores by isosteric replacement of carboxylic function.

PubMed

Polański, J; Jarzembek, K; Łysiak, V

2000-11-01

We used arylsulfonylalkanoic acids as parent structures for designing new potential sweeteners. The Kohonen maps of the molecular electrostatic potential of the possible bioisosteric replacements of carboxylic function have been simulated and used for the selection of the potential synthetic targets which are now under synthesis.

Integration of QSAR and SAR methods for the mechanistic interpretation of predictive models for carcinogenicity

PubMed Central

Fjodorova, Natalja; Novič, Marjana

2012-01-01

The knowledge-based Toxtree expert system (SAR approach) was integrated with the statistically based counter propagation artificial neural network (CP ANN) model (QSAR approach) to contribute to a better mechanistic understanding of a carcinogenicity model for non-congeneric chemicals using Dragon descriptors and carcinogenic potency for rats as a response. The transparency of the CP ANN algorithm was demonstrated using intrinsic mapping technique specifically Kohonen maps. Chemical structures were represented by Dragon descriptors that express the structural and electronic features of molecules such as their shape and electronic surrounding related to reactivity of molecules. It was illustrated how the descriptors are correlated with particular structural alerts (SAs) for carcinogenicity with recognized mechanistic link to carcinogenic activity. Moreover, the Kohonen mapping technique enables one to examine the separation of carcinogens and non-carcinogens (for rats) within a family of chemicals with a particular SA for carcinogenicity. The mechanistic interpretation of models is important for the evaluation of safety of chemicals. PMID:24688639

Web Image Retrieval Using Self-Organizing Feature Map.

ERIC Educational Resources Information Center

Wu, Qishi; Iyengar, S. Sitharama; Zhu, Mengxia

2001-01-01

Provides an overview of current image retrieval systems. Describes the architecture of the SOFM (Self Organizing Feature Maps) based image retrieval system, discussing the system architecture and features. Introduces the Kohonen model, and describes the implementation details of SOFM computation and its learning algorithm. Presents a test example…

Dysphonia Detected by Pattern Recognition of Spectral Composition.

ERIC Educational Resources Information Center

Leinonen, Lea; And Others

1992-01-01

This study analyzed production of a long vowel sound within Finnish words by normal or dysphonic voices, using the Self-Organizing Map, the artificial neural network algorithm of T. Kohonen which produces two-dimensional representations of speech. The method was found to be both sensitive and specific in the detection of dysphonia. (Author/JDD)

Independent component analysis (ICA) and self-organizing map (SOM) approach to multidetection system for network intruders

NASA Astrophysics Data System (ADS)

Abdi, Abdi M.; Szu, Harold H.

2003-04-01

With the growing rate of interconnection among computer systems, network security is becoming a real challenge. Intrusion Detection System (IDS) is designed to protect the availability, confidentiality and integrity of critical network information systems. Today"s approach to network intrusion detection involves the use of rule-based expert systems to identify an indication of known attack or anomalies. However, these techniques are less successful in identifying today"s attacks. Hackers are perpetually inventing new and previously unanticipated techniques to compromise information infrastructure. This paper proposes a dynamic way of detecting network intruders on time serious data. The proposed approach consists of a two-step process. Firstly, obtaining an efficient multi-user detection method, employing the recently introduced complexity minimization approach as a generalization of a standard ICA. Secondly, we identified unsupervised learning neural network architecture based on Kohonen"s Self-Organizing Map for potential functional clustering. These two steps working together adaptively will provide a pseudo-real time novelty detection attribute to supplement the current intrusion detection statistical methodology.

Predictive models reduce talent development costs in female gymnastics.

PubMed

Pion, Johan; Hohmann, Andreas; Liu, Tianbiao; Lenoir, Matthieu; Segers, Veerle

2017-04-01

This retrospective study focuses on the comparison of different predictive models based on the results of a talent identification test battery for female gymnasts. We studied to what extent these models have the potential to optimise selection procedures, and at the same time reduce talent development costs in female artistic gymnastics. The dropout rate of 243 female elite gymnasts was investigated, 5 years past talent selection, using linear (discriminant analysis) and non-linear predictive models (Kohonen feature maps and multilayer perceptron). The coaches classified 51.9% of the participants correct. Discriminant analysis improved the correct classification to 71.6% while the non-linear technique of Kohonen feature maps reached 73.7% correctness. Application of the multilayer perceptron even classified 79.8% of the gymnasts correctly. The combination of different predictive models for talent selection can avoid deselection of high-potential female gymnasts. The selection procedure based upon the different statistical analyses results in decrease of 33.3% of cost because the pool of selected athletes can be reduced to 92 instead of 138 gymnasts (as selected by the coaches). Reduction of the costs allows the limited resources to be fully invested in the high-potential athletes.

Data Mining in Cyber Operations

DTIC Science & Technology

2014-07-01

information processing units intended to mimic the network of neurons in the human brain for performing pattern recognition  Self- organizing maps (SOM...patterns are mined from in order to influence the learning model . An exploratory attack does not alter the training process , but rather uses other...New Jersey: Prentice Hall. 21) Kohonen, T. (1982). Self- organized formation of topologically correct feature maps. Biological Cybernetics , 43, 59–69

An Intelligent System for Monitoring the Microgravity Environment Quality On-Board the International Space Station

NASA Technical Reports Server (NTRS)

Lin, Paul P.; Jules, Kenol

2002-01-01

An intelligent system for monitoring the microgravity environment quality on-board the International Space Station is presented. The monitoring system uses a new approach combining Kohonen's self-organizing feature map, learning vector quantization, and back propagation neural network to recognize and classify the known and unknown patterns. Finally, fuzzy logic is used to assess the level of confidence associated with each vibrating source activation detected by the system.

The performance evaluation of a new neural network based traffic management scheme for a satellite communication network

NASA Technical Reports Server (NTRS)

Ansari, Nirwan; Liu, Dequan

1991-01-01

A neural-network-based traffic management scheme for a satellite communication network is described. The scheme consists of two levels of management. The front end of the scheme is a derivation of Kohonen's self-organization model to configure maps for the satellite communication network dynamically. The model consists of three stages. The first stage is the pattern recognition task, in which an exemplar map that best meets the current network requirements is selected. The second stage is the analysis of the discrepancy between the chosen exemplar map and the state of the network, and the adaptive modification of the chosen exemplar map to conform closely to the network requirement (input data pattern) by means of Kohonen's self-organization. On the basis of certain performance criteria, whether a new map is generated to replace the original chosen map is decided in the third stage. A state-dependent routing algorithm, which arranges the incoming call to some proper path, is used to make the network more efficient and to lower the call block rate. Simulation results demonstrate that the scheme, which combines self-organization and the state-dependent routing mechanism, provides better performance in terms of call block rate than schemes that only have either the self-organization mechanism or the routing mechanism.

[Cluster analysis in biomedical researches].

PubMed

Akopov, A S; Moskovtsev, A A; Dolenko, S A; Savina, G D

2013-01-01

Cluster analysis is one of the most popular methods for the analysis of multi-parameter data. The cluster analysis reveals the internal structure of the data, group the separate observations on the degree of their similarity. The review provides a definition of the basic concepts of cluster analysis, and discusses the most popular clustering algorithms: k-means, hierarchical algorithms, Kohonen networks algorithms. Examples are the use of these algorithms in biomedical research.

Modeling the human mental lexicon with self-organizing feature maps

NASA Astrophysics Data System (ADS)

Wittenburg, Peter; Frauenfelder, Uli H.

1992-10-01

Recent efforts to model the remarkable ability of humans to recognize speech and words are described. Different techniques including the use of neural nets for representing phonological similarity between words in the lexicon with self organizing algorithms are discussed. Simulations using the standard Kohonen algorithm are presented to illustrate some problems confronted with this technique in modeling similarity relations of form in the human mental lexicon. Alternative approaches that can potentially deal with some of these limitations are sketched.

Ultimate compression after impact load prediction in graphite/epoxy coupons using neural network and multivariate statistical analyses

NASA Astrophysics Data System (ADS)

Gregoire, Alexandre David

2011-07-01

The goal of this research was to accurately predict the ultimate compressive load of impact damaged graphite/epoxy coupons using a Kohonen self-organizing map (SOM) neural network and multivariate statistical regression analysis (MSRA). An optimized use of these data treatment tools allowed the generation of a simple, physically understandable equation that predicts the ultimate failure load of an impacted damaged coupon based uniquely on the acoustic emissions it emits at low proof loads. Acoustic emission (AE) data were collected using two 150 kHz resonant transducers which detected and recorded the AE activity given off during compression to failure of thirty-four impacted 24-ply bidirectional woven cloth laminate graphite/epoxy coupons. The AE quantification parameters duration, energy and amplitude for each AE hit were input to the Kohonen self-organizing map (SOM) neural network to accurately classify the material failure mechanisms present in the low proof load data. The number of failure mechanisms from the first 30% of the loading for twenty-four coupons were used to generate a linear prediction equation which yielded a worst case ultimate load prediction error of 16.17%, just outside of the +/-15% B-basis allowables, which was the goal for this research. Particular emphasis was placed upon the noise removal process which was largely responsible for the accuracy of the results.

Clustering Similarity Digest Bloom Filters in Self-Organizing Maps

DTIC Science & Technology

2012-12-01

www.sciencedirect.com/science/article/ pii/S1742287610000368 [4] M. Rogers, J . Goldman, R. Mislan, T. Wedge, and S. Debrota, “Computer forensics field triage...1990. [9] T. Kohonen, S. Kaski, K. Lagus, J . Salojarvi, J . Honkela, V. Paatero, and A. Saarela, “Self organization of a massive document collection...the IEEE-INNS-ENNS Interna- tional Joint Conference on, vol. 6, 2000, pp. 15 –19 vol.6. [12] G. Salton , A. Wong, and C. Yang, “A vector space model for

Artificial neural networks and the study of the psychoactivity of cannabinoid compounds.

PubMed

Honório, Káthia M; de Lima, Emmanuela F; Quiles, Marcos G; Romero, Roseli A F; Molfetta, Fábio A; da Silva, Albérico B F

2010-06-01

Cannabinoid compounds have widely been employed because of its medicinal and psychotropic properties. These compounds are isolated from Cannabis sativa (or marijuana) and are used in several medical treatments, such as glaucoma, nausea associated to chemotherapy, pain and many other situations. More recently, its use as appetite stimulant has been indicated in patients with cachexia or AIDS. In this work, the influence of several molecular descriptors on the psychoactivity of 50 cannabinoid compounds is analyzed aiming one obtain a model able to predict the psychoactivity of new cannabinoids. For this purpose, initially, the selection of descriptors was carried out using the Fisher's weight, the correlation matrix among the calculated variables and principal component analysis. From these analyses, the following descriptors have been considered more relevant: E(LUMO) (energy of the lowest unoccupied molecular orbital), Log P (logarithm of the partition coefficient), VC4 (volume of the substituent at the C4 position) and LP1 (Lovasz-Pelikan index, a molecular branching index). To follow, two neural network models were used to construct a more adequate model for classifying new cannabinoid compounds. The first model employed was multi-layer perceptrons, with algorithm back-propagation, and the second model used was the Kohonen network. The results obtained from both networks were compared and showed that both techniques presented a high percentage of correctness to discriminate psychoactive and psychoinactive compounds. However, the Kohonen network was superior to multi-layer perceptrons.

Artificial Intelligence in Sports Biomechanics: New Dawn or False Hope?

PubMed Central

Bartlett, Roger

2006-01-01

This article reviews developments in the use of Artificial Intelligence (AI) in sports biomechanics over the last decade. It outlines possible uses of Expert Systems as diagnostic tools for evaluating faults in sports movements (‘techniques’) and presents some example knowledge rules for such an expert system. It then compares the analysis of sports techniques, in which Expert Systems have found little place to date, with gait analysis, in which they are routinely used. Consideration is then given to the use of Artificial Neural Networks (ANNs) in sports biomechanics, focusing on Kohonen self-organizing maps, which have been the most widely used in technique analysis, and multi-layer networks, which have been far more widely used in biomechanics in general. Examples of the use of ANNs in sports biomechanics are presented for javelin and discus throwing, shot putting and football kicking. I also present an example of the use of Evolutionary Computation in movement optimization in the soccer throw in, which predicted an optimal technique close to that in the coaching literature. After briefly overviewing the use of AI in both sports science and biomechanics in general, the article concludes with some speculations about future uses of AI in sports biomechanics. Key Points Expert Systems remain almost unused in sports biomechanics, unlike in the similar discipline of gait analysis. Artificial Neural Networks, particularly Kohonen Maps, have been used, although their full value remains unclear. Other AI applications, including Evolutionary Computation, have received little attention. PMID:24357939

Artificial intelligence in sports biomechanics: new dawn or false hope?

PubMed

Bartlett, Roger

2006-12-15

This article reviews developments in the use of Artificial Intelligence (AI) in sports biomechanics over the last decade. It outlines possible uses of Expert Systems as diagnostic tools for evaluating faults in sports movements ('techniques') and presents some example knowledge rules for such an expert system. It then compares the analysis of sports techniques, in which Expert Systems have found little place to date, with gait analysis, in which they are routinely used. Consideration is then given to the use of Artificial Neural Networks (ANNs) in sports biomechanics, focusing on Kohonen self-organizing maps, which have been the most widely used in technique analysis, and multi-layer networks, which have been far more widely used in biomechanics in general. Examples of the use of ANNs in sports biomechanics are presented for javelin and discus throwing, shot putting and football kicking. I also present an example of the use of Evolutionary Computation in movement optimization in the soccer throw in, which predicted an optimal technique close to that in the coaching literature. After briefly overviewing the use of AI in both sports science and biomechanics in general, the article concludes with some speculations about future uses of AI in sports biomechanics. Key PointsExpert Systems remain almost unused in sports biomechanics, unlike in the similar discipline of gait analysis.Artificial Neural Networks, particularly Kohonen Maps, have been used, although their full value remains unclear.Other AI applications, including Evolutionary Computation, have received little attention.

The research of "blind" spot in the LVQ network

NASA Astrophysics Data System (ADS)

Guo, Zhanjie; Nan, Shupo; Wang, Xiaoli

2017-04-01

Nowadays competitive neural network has been widely used in the pattern recognition, classification and other aspects, and show the great advantages compared with the traditional clustering methods. But the competitive neural networks still has inadequate in many aspects, and it needs to be further improved. Based on the learning Vector Quantization Network proposed by Learning Kohonen [1], this paper resolve the issue of the large training error, when there are "blind" spots in a network through the introduction of threshold value learning rules and finally programs the realization with Matlab.

Image segmentation using fuzzy LVQ clustering networks

NASA Technical Reports Server (NTRS)

Tsao, Eric Chen-Kuo; Bezdek, James C.; Pal, Nikhil R.

1992-01-01

In this note we formulate image segmentation as a clustering problem. Feature vectors extracted from a raw image are clustered into subregions, thereby segmenting the image. A fuzzy generalization of a Kohonen learning vector quantization (LVQ) which integrates the Fuzzy c-Means (FCM) model with the learning rate and updating strategies of the LVQ is used for this task. This network, which segments images in an unsupervised manner, is thus related to the FCM optimization problem. Numerical examples on photographic and magnetic resonance images are given to illustrate this approach to image segmentation.

The assessment of corruption impact on the inflow of foreign direct investment

NASA Astrophysics Data System (ADS)

Gasanova, Ayshan; Medvedev, Alexander N.; Komotskiy, Evgeny I.

2017-06-01

The aim of this paper is to investigate the impact of corruption on the inflow of foreign direct investment (FDI). The data, taken from official sources, Transparency International and the Heritage Foundation, have been treated in a special program "Deductor Studio Academic" by the method of Machine Learning (cluster analysis using Kohonen Self-Organizing Maps). There was composed a Kohonen map, in which the countries were divided into 4 clusters: countries with low levels of corruption and high level of FDI inflow, countries with low level of corruption and FDI above average, countries with average level of corruption and the average level of FDI, and countries with high level of corruption and low level of FDI. The research has shown that corruption influences the investment attractiveness of the host country. This means that in countries where the level of corruption is low and economic environment is attractive, the level of foreign direct investment is high, and in those countries where the level of corruption is high and and economic attractiveness is low - the level of investment is low. However, the study identified countries which have high level of corruption and high FDI inflow - China, India, Brazil and Russia (BRIC countries). These countries are the exception from the rule due to the wide domestic market, cheap labour, the wealth of natural resources - all these factors increase the investment attractiveness of these countries. It was found that corruption in BRIC countries has similarity being a controlled and predictable phenomenon. This allows calculating the cost of corruption for accounting it in business projects.

Minimum energy information fusion in sensor networks

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

Chapline, G

1999-05-11

In this paper we consider how to organize the sharing of information in a distributed network of sensors and data processors so as to provide explanations for sensor readings with minimal expenditure of energy. We point out that the Minimum Description Length principle provides an approach to information fusion that is more naturally suited to energy minimization than traditional Bayesian approaches. In addition we show that for networks consisting of a large number of identical sensors Kohonen self-organization provides an exact solution to the problem of combing the sensor outputs into minimal description length explanations.

Classification of the LCVF AVIRIS test site with a Kohonen artificial neural network

NASA Technical Reports Server (NTRS)

Merenyi, Erzsebet; Singer, Robert B.; Farrand, William H.

1993-01-01

We present a classification of an AVIRIS spectral image of the Lunar Crater Volcanic Field (LCVF). Geologic mapping from such data is made possible by distinctive mineral signatures: absorption features and the shape of the spectral continuum. The subtle spectral shape differences between some of the geological units in this scene along with the high dimensionality of the spectral presents a challenging pattern recognition task. We found an artificial neural network powerful in separating 13 geological units based on the full spectral resolution. The LCVF, in northern Nye County, Nevada, was the primary focus of the NASA-sponsored Geologic Remote Sensing Field Experiment in the summer of 1989. It consists of over 100 square miles of Quaternary basaltic pyroclastic and flow deposits. These deposits lie atop ignimbrites and silicic lava flows of Tertiary age and in turn are overlain by Quaternary alluvial and playa deposits. This AVIRIS image was collected on September 29, 1989 at 11:44 at 11:44 PDT. The 256-by-256 pixel subsection in this study contains oxidized basaltic cinder deposits, the southern half of the Lunar Lake playa, and outcrops of the Rhyollite of Big Sand Spring Valley. Vegetation in LCVF is sparse, but locally abundant within washes and near springs.

Kohonen Self-Organizing Maps in Validity Maintenance for Automated Scoring of Constructed Response.

ERIC Educational Resources Information Center

Williamson, David M.; Bejar, Isaac I.

As the automated scoring of constructed responses reaches operational status, monitoring the scoring process becomes a primary concern, particularly if automated scoring is intended to operate completely unassisted by humans. Using actual candidate selections from the Architectural Registration Examination (n=326), this study uses Kohonen…

Feature detection in satellite images using neural network technology

NASA Technical Reports Server (NTRS)

Augusteijn, Marijke F.; Dimalanta, Arturo S.

1992-01-01

A feasibility study of automated classification of satellite images is described. Satellite images were characterized by the textures they contain. In particular, the detection of cloud textures was investigated. The method of second-order gray level statistics, using co-occurrence matrices, was applied to extract feature vectors from image segments. Neural network technology was employed to classify these feature vectors. The cascade-correlation architecture was successfully used as a classifier. The use of a Kohonen network was also investigated but this architecture could not reliably classify the feature vectors due to the complicated structure of the classification problem. The best results were obtained when data from different spectral bands were fused.

Classification of cardiac arrhythmias using competitive networks.

PubMed

Leite, Cicilia R M; Martin, Daniel L; Sizilio, Glaucia R A; Dos Santos, Keylly E A; de Araujo, Bruno G; Valentim, Ricardo A M; Neto, Adriao D D; de Melo, Jorge D; Guerreiro, Ana M G

2010-01-01

Information generated by sensors that collect a patient's vital signals are continuous and unlimited data sequences. Traditionally, this information requires special equipment and programs to monitor them. These programs process and react to the continuous entry of data from different origins. Thus, the purpose of this study is to analyze the data produced by these biomedical devices, in this case the electrocardiogram (ECG). Processing uses a neural classifier, Kohonen competitive neural networks, detecting if the ECG shows any cardiac arrhythmia. In fact, it is possible to classify an ECG signal and thereby detect if it is exhibiting or not any alteration, according to normality.

Evaluation of power system security and development of transmission pricing method

NASA Astrophysics Data System (ADS)

Kim, Hyungchul

The electric power utility industry is presently undergoing a change towards the deregulated environment. This has resulted in unbundling of generation, transmission and distribution services. The introduction of competition into unbundled electricity services may lead system operation closer to its security boundaries resulting in smaller operating safety margins. The competitive environment is expected to lead to lower price rates for customers and higher efficiency for power suppliers in the long run. Under this deregulated environment, security assessment and pricing of transmission services have become important issues in power systems. This dissertation provides new methods for power system security assessment and transmission pricing. In power system security assessment, the following issues are discussed (1) The description of probabilistic methods for power system security assessment; (2) The computation time of simulation methods; (3) on-line security assessment for operation. A probabilistic method using Monte-Carlo simulation is proposed for power system security assessment. This method takes into account dynamic and static effects corresponding to contingencies. Two different Kohonen networks, Self-Organizing Maps and Learning Vector Quantization, are employed to speed up the probabilistic method. The combination of Kohonen networks and Monte-Carlo simulation can reduce computation time in comparison with straight Monte-Carlo simulation. A technique for security assessment employing Bayes classifier is also proposed. This method can be useful for system operators to make security decisions during on-line power system operation. This dissertation also suggests an approach for allocating transmission transaction costs based on reliability benefits in transmission services. The proposed method shows the transmission transaction cost of reliability benefits when transmission line capacities are considered. The ratio between allocation by transmission line

Integrating vegetation index time series and meteorological data to understand the effect of the land use/land cover (LULC) in the climatic seasonality of the Brazilian Cerrado

NASA Astrophysics Data System (ADS)

Lins, D. B.; Zullo, J.; Friedel, M. J.

2013-12-01

The Cerrado (savanna ecosystem) of São Paulo state (Brazil) represent a complex mosaic of different typologies of uses, actors and biophysical and social restrictions. Originally, 14% of the state of São Paulo area was covered by the diversity of Cerrado phytophysiognomies. Currently, only 1% of this original composition remains fragmented into numerous relicts of biodiversity, mainly concentrated in the central-eastern of the state. A relevant part of the fragments are found in areas of intense coverage change by human activities, whereas the greatest pressure comes from sugar cane cultivation, either by direct replacement of Cerrado vegetation or occupying pasture areas in the fragments edges. As a result, new local level dynamics has been introduced, directly or indirectly, affecting the established of processes in climate systems. In this study, the main goal is analyzing the relationship between the Cerrado landscape changing and the climate dynamics in regional and local areas. The multi-temporal MODIS 250 m Vegetation Index (VI) datasets (period of 2000 to 2012) are integrated with precipitation data of the correspondent period (http://www.agritempo.gov.br/),one of the most important variable of the spatial phytophysiognomies distribution. The integration of meteorological data enable the development of an integrated approach to understand the relationship between climatic seasonality and the changes in the spatial patterns. A procedure to congregated diverse dynamics information is the Self Organizing Map (SOM, Kohonen, 2001), a technique that relies on unsupervised competitive learning (Kohonen and Somervuo 2002) to recognize patterns. In this approach, high-dimensional data are represented on two dimensions, making possible to obtain patterns that takes into account information from different natures. Observed advances will contribute to bring machine-learning techniques as a valid tool to provide improve in land use/land cover (LULC) analyzes at

Ants as biological indicators of Wayana Amerindian land use in French Guiana.

PubMed

Delabie, Jacques H C; Céréghino, Régis; Groc, Sarah; Dejean, Andrea; Gibernau, Marc; Corbara, Bruno; Dejean, Alain

2009-07-01

We examined the ecological impact of traditional land use by Wayana Amerindians in French Guiana using ants as bio-indicators. Ants were sampled through a rapid assessment method and the core results analyzed using Kohonen's self-organizing maps (SOM). Our sample sites included: (1) a Wayana village; (2) a cassava plantation; (3) an abandoned cassava plantation; (4) a forest fragment near the village; (5) a riparian forest; and (6) a primary terra firma forest. The ant diversity decreases according to the degree to which the habitat is disturbed. The SOM allowed us to compare the ecological succession between the six habitats. The protocol used is robust since the same conclusions were drawn using partial data.

Self-organizing neural networks--an alternative way of cluster analysis in clinical chemistry.

PubMed

Reibnegger, G; Wachter, H

1996-04-15

Supervised learning schemes have been employed by several workers for training neural networks designed to solve clinical problems. We demonstrate that unsupervised techniques can also produce interesting and meaningful results. Using a data set on the chemical composition of milk from 22 different mammals, we demonstrate that self-organizing feature maps (Kohonen networks) as well as a modified version of error backpropagation technique yield results mimicking conventional cluster analysis. Both techniques are able to project a potentially multi-dimensional input vector onto a two-dimensional space whereby neighborhood relationships remain conserved. Thus, these techniques can be used for reducing dimensionality of complicated data sets and for enhancing comprehensibility of features hidden in the data matrix.

Automatic Galaxy Classification via Machine Learning Techniques: Parallelized Rotation/Flipping INvariant Kohonen Maps (PINK)

NASA Astrophysics Data System (ADS)

Polsterer, K. L.; Gieseke, F.; Igel, C.

2015-09-01

In the last decades more and more all-sky surveys created an enormous amount of data which is publicly available on the Internet. Crowd-sourcing projects such as Galaxy-Zoo and Radio-Galaxy-Zoo used encouraged users from all over the world to manually conduct various classification tasks. The combination of the pattern-recognition capabilities of thousands of volunteers enabled scientists to finish the data analysis within acceptable time. For up-coming surveys with billions of sources, however, this approach is not feasible anymore. In this work, we present an unsupervised method that can automatically process large amounts of galaxy data and which generates a set of prototypes. This resulting model can be used to both visualize the given galaxy data as well as to classify so far unseen images.

Kohonen Self-Organizing Feature Maps as a Means to Benchmark College and University Websites

ERIC Educational Resources Information Center

Cooper, Cameron; Burns, Andrew

2007-01-01

Websites for colleges and universities have become the primary means for students to obtain information in the college search process. Consequently, institutions of higher education should target their websites toward prospective and current students' needs, interests, and tastes. Numerous parameters must be determined in creating a school website…

Viewpoint: Exorcizing Maxwell’s demon

DOE PAGES

Deffner, Sebastian

2015-12-01

Here, physicists have been haunted by the idea of Maxwell's demon for almost 150 years. The beast, conjured in a thought experiment by James Clerk Maxwell, sorts particles in a gas according to their speeds, thus transferring heat from the colder, evenly mixed gas to the region containing the hotter, high-speed particles. At first sight, the demon appears to violate the second law of thermodynamics. But the paradox can be resolved by realizing that work must be performed on the demon for it to do its job properly. This description isn’t entirely satisfying, however, as it introduces an external—not necessarilymore » physical—entity to do work on the demon. Jukka Pekola and colleagues of Aalto University in Finland [1] have now exorcised such nonphysical beings by realizing a nanodevice equivalent to a Maxwell's demon (Fig. 1), but one whose operation doesn’t depend on an external entity. This so-called autonomous device, also known as an information machine, is completely self-contained. So far, autonomous demons have been a purely theoretical concept; this new experimental system provides a way to test formulations of fundamental axioms of thermodynamics and descriptions of information processing.« less

Applications of self-organizing neural networks in virtual screening and diversity selection.

PubMed

Selzer, Paul; Ertl, Peter

2006-01-01

Artificial neural networks provide a powerful technique for the analysis and modeling of nonlinear relationships between molecular structures and pharmacological activity. Many network types, including Kohonen and counterpropagation, also provide an intuitive method for the visual assessment of correspondence between the input and output data. This work shows how a combination of neural networks and radial distribution function molecular descriptors can be applied in various areas of industrial pharmaceutical research. These applications include the prediction of biological activity, the selection of screening candidates (cherry picking), and the extraction of representative subsets from large compound collections such as combinatorial libraries. The methods described have also been implemented as an easy-to-use Web tool, allowing chemists to perform interactive neural network experiments on the Novartis intranet.

Identification of Shifts and Trends in Hydrometric Data in Canada Based on Several Detection Tests

NASA Astrophysics Data System (ADS)

Lauzon, N.; Lence, B. J.

2004-05-01

This work proposes new detection tests based on the Kohonen neural network and on fuzzy c-means for the identification of shifts and trends in data sequences. Annual mean and maximum flow sequences are considered as application case, for they have often been considered for the study of shifts and trends in hydrologic data. In recent years, several studies for the identification of trends have been accomplished with North American hydrometric data, often making use of only one detection test. The assumption here is that one cannot rely on only one test, and consequently several are employed in this work. A total of eight tests are considered, four for shifts and four for trends. Four of these tests, two for shifts and two for trends, are conventional statistical tests that are regularly employed, while the other four are developed based on the Kohonen neural network and on fuzzy c-means. Data from a group of 40 hydrometric stations across Canada are assessed for the detection of shifts and trends in time periods of 30, 40 and 50 years. While the results obtained confirm the conclusions of previous studies performed on similar groups of data, they also indicate that each test may behave differently from one another. For example, one test may detect a trend in a given sequence while the other tests do not, or vice-versa. Thus, the strategy of using several tests ensures not only that they may confirm each others diagnostics but also may complement each other in the case of divergent diagnostics, with the possibility of improving the final conclusion on the detection of shifts and trends. Using artificial intelligence techniques for the construction of detection tests constitutes also a departure from the use of statistics, and a discussion in this work on complementary studies (i.e. detection on multivariate cases) highlights the possibility of enhanced performance by the artificial intelligence-based tests compared with conventional detection tests.

Development of module for neural network identification of attacks on applications and services in multi-cloud platforms

NASA Astrophysics Data System (ADS)

Parfenov, D. I.; Bolodurina, I. P.

2018-05-01

The article presents the results of developing an approach to detecting and protecting against network attacks on the corporate infrastructure deployed on the multi-cloud platform. The proposed approach is based on the combination of two technologies: a softwareconfigurable network and virtualization of network functions. The approach for searching for anomalous traffic is to use a hybrid neural network consisting of a self-organizing Kohonen network and a multilayer perceptron. The study of the work of the prototype of the system for detecting attacks, the method of forming a learning sample, and the course of experiments are described. The study showed that using the proposed approach makes it possible to increase the effectiveness of the obfuscation of various types of attacks and at the same time does not reduce the performance of the network

PubMed

Petyx, Carlo; Costa, Giovanni; Manno, Maurizio; Valenti, Antonio; Iavicoli, Sergio

2016-12-13

The Working Group responsible for the Italian translation of the third edition of the International Code of Ethics, appointed by the President of the International Commission on Occupational Health (ICOH), Dr. Jukka Takala, completed last April the revision work. The final text, already available on the ICOH website, has been printed and distributed by the Italian National Institute for Insurance against Accidents at Work (INAIL) at the 79th National Congress of the Italian Society of Occupational Medicine and Industrial Hygiene (SIMLII), in Rome. The curators of this third Italian edition have accomplished the delicate task of adaptation in Italian, taking into account the specificities of the practice of medicine in the Italian work environment. It involves many professionals with diverse roles and responsibilities in the public and private sectors for safety, hygiene, health and environment in relation to work. More than twenty years after the first Italian edition, we trace the evolution of the ICOH International Code of Ethics, in order to focus its birth, national and international distribution, and continuous improvement as well as its ability to direct the stakeholders towards a participatory prevention model, in a legislative framework that has seen over the past two decades a radical change in the Italian world of work.

A Kohonen-like decomposition method for the Euclidean traveling salesman problem-KNIES/spl I.bar/DECOMPOSE.

PubMed

Aras, N; Altinel, I K; Oommen, J

2003-01-01

In addition to the classical heuristic algorithms of operations research, there have also been several approaches based on artificial neural networks for solving the traveling salesman problem. Their efficiency, however, decreases as the problem size (number of cities) increases. A technique to reduce the complexity of a large-scale traveling salesman problem (TSP) instance is to decompose or partition it into smaller subproblems. We introduce an all-neural decomposition heuristic that is based on a recent self-organizing map called KNIES, which has been successfully implemented for solving both the Euclidean traveling salesman problem and the Euclidean Hamiltonian path problem. Our solution for the Euclidean TSP proceeds by solving the Euclidean HPP for the subproblems, and then patching these solutions together. No such all-neural solution has ever been reported.

Wains: a pattern-seeking artificial life species.

PubMed

de Buitléir, Amy; Russell, Michael; Daly, Mark

2012-01-01

We describe the initial phase of a research project to develop an artificial life framework designed to extract knowledge from large data sets with minimal preparation or ramp-up time. In this phase, we evolved an artificial life population with a new brain architecture. The agents have sufficient intelligence to discover patterns in data and to make survival decisions based on those patterns. The species uses diploid reproduction, Hebbian learning, and Kohonen self-organizing maps, in combination with novel techniques such as using pattern-rich data as the environment and framing the data analysis as a survival problem for artificial life. The first generation of agents mastered the pattern discovery task well enough to thrive. Evolution further adapted the agents to their environment by making them a little more pessimistic, and also by making their brains more efficient.

Dynamic gesture recognition using neural networks: a fundament for advanced interaction construction

NASA Astrophysics Data System (ADS)

Boehm, Klaus; Broll, Wolfgang; Sokolewicz, Michael A.

1994-04-01

Interaction in virtual reality environments is still a challenging task. Static hand posture recognition is currently the most common and widely used method for interaction using glove input devices. In order to improve the naturalness of interaction, and thereby decrease the user-interface learning time, there is a need to be able to recognize dynamic gestures. In this paper we describe our approach to overcoming the difficulties of dynamic gesture recognition (DGR) using neural networks. Backpropagation neural networks have already proven themselves to be appropriate and efficient for posture recognition. However, the extensive amount of data involved in DGR requires a different approach. Because of features such as topology preservation and automatic-learning, Kohonen Feature Maps are particularly suitable for the reduction of the high dimensional data space that is the result of a dynamic gesture, and are thus implemented for this task.

Prioritization of malaria endemic zones using self-organizing maps in the Manipur state of India.

PubMed

Murty, Upadhyayula Suryanarayana; Srinivasa Rao, Mutheneni; Misra, Sunil

2008-09-01

Due to the availability of a huge amount of epidemiological and public health data that require analysis and interpretation by using appropriate mathematical tools to support the existing method to control the mosquito and mosquito-borne diseases in a more effective way, data-mining tools are used to make sense from the chaos. Using data-mining tools, one can develop predictive models, patterns, association rules, and clusters of diseases, which can help the decision-makers in controlling the diseases. This paper mainly focuses on the applications of data-mining tools that have been used for the first time to prioritize the malaria endemic regions in Manipur state by using Self Organizing Maps (SOM). The SOM results (in two-dimensional images called Kohonen maps) clearly show the visual classification of malaria endemic zones into high, medium and low in the different districts of Manipur, and will be discussed in the paper.

Mapping Rock and Soil Units in the MPF IMP SuperPan Using a Kohonen Self Organizing Map

NASA Technical Reports Server (NTRS)

Farrand, W.; Merenyi, E.; Murchie, S.; Barnouin-Jha, O.; Johnson, J.

2004-01-01

The 1997 Mars Pathfinder mission provided information on a site in the Ares Vallis floodplain. Initial analysis of multispectral data from the Imager for Mars Pathfinder (IMP) indicated the presence of only a single rock type, the 'gray rock' spectral class and various coated variants thereof (e.g., 'maroon rock'). Continued analysis of the IMP 'SuperPan' mosaic has confirmed multiple examples of a second 'black rock' spectral class existing as small cobbles in the near field and as boulders in the far field. These results are consistent with recent analysis of MGS Thermal Emission Spectrometer (TES) data which indicates that there is likely a mix of both 'Surface Type 1' (ST1) and 'Surface Type 2' (ST2) spectral classes at the MPF landing site. Nominally, the black rock spectral class would correspond to ST1 (basalts) and 'gray rock' would correspond to ST2 (andesites). Orbital remote sensing has also revealed the pervasive presence of layering on Mars. Recently it was suggested that there are extensive outcrops of the black rock spectral class in the SuperPan far field on the flanks of the Twin Peaks and on the rim of Big Crater. These authors suggested that these exposures represented outcrops of black rock from beneath a surficial, flood deposited layer. In this work, we have reexamined the MPF IMP SuperPan mosaic using an artificial neural network self organizing map (SOM) processing architecture in order to classify the distribution of spectral classes within the SuperPan. In this paper, we present initial results from that work and draw specific attention to a subset of the identified spectral classes in order to address questions relating to whether there are extensive exposures of black rock in the IMP far field, what other materials might be exposed in the far field, and what evidence there is for subsurface layering at the MPF landing site.

Classification of dry-cured hams according to the maturation time using near infrared spectra and artificial neural networks.

PubMed

Prevolnik, M; Andronikov, D; Žlender, B; Font-i-Furnols, M; Novič, M; Škorjanc, D; Čandek-Potokar, M

2014-01-01

An attempt to classify dry-cured hams according to the maturation time on the basis of near infrared (NIR) spectra was studied. The study comprised 128 samples of biceps femoris (BF) muscle from dry-cured hams matured for 10 (n=32), 12 (n=32), 14 (n=32) or 16 months (n=32). Samples were minced and scanned in the wavelength range from 400 to 2500 nm using spectrometer NIR System model 6500 (Silver Spring, MD, USA). Spectral data were used for i) splitting of samples into the training and test set using 2D Kohonen artificial neural networks (ANN) and for ii) construction of classification models using counter-propagation ANN (CP-ANN). Different models were tested, and the one selected was based on the lowest percentage of misclassified test samples (external validation). Overall correctness of the classification was 79.7%, which demonstrates practical relevance of using NIR spectroscopy and ANN for dry-cured ham processing control. Copyright © 2013 Elsevier Ltd. All rights reserved.

Application of self-organizing maps for PCDD/F pattern recognition of environmental and biological samples to evaluate the impact of a hazardous waste incinerator.

PubMed

Mari, Montse; Nadal, Martí; Schuhmacher, Marta; Domingo, José L

2010-04-15

Kohonen's self-organizing maps (SOM) is one of the most popular artificial neural network models. In this study, SOM were used to assess the potential relationships between polychlorinated dibenzo-p-dioxins and dibenzofurans (PCDD/Fs) congener profiles in environmental (soil, herbage, and ambient air) and biological (plasma, adipose tissue, and breast milk) samples, and the emissions of a hazardous waste incinerator (HWI) in Spain. The visual examination of PCDD/F congener profiles of most environmental and biological samples did not allow finding out any differences between monitors. However, the global SOM analysis of environmental and biological samples showed that the weight of the PCDD/F stack emissions of the HWI on the environmental burden and on the exposure of the individuals living in the surroundings was not significant in relation to the background levels. The results confirmed the small influence of the HWI emissions of PCDD/Fs on the environment and the population living in the neighborhood.

Seismic event classification system

DOEpatents

Dowla, Farid U.; Jarpe, Stephen P.; Maurer, William

1994-01-01

In the computer interpretation of seismic data, the critical first step is to identify the general class of an unknown event. For example, the classification might be: teleseismic, regional, local, vehicular, or noise. Self-organizing neural networks (SONNs) can be used for classifying such events. Both Kohonen and Adaptive Resonance Theory (ART) SONNs are useful for this purpose. Given the detection of a seismic event and the corresponding signal, computation is made of: the time-frequency distribution, its binary representation, and finally a shift-invariant representation, which is the magnitude of the two-dimensional Fourier transform (2-D FFT) of the binary time-frequency distribution. This pre-processed input is fed into the SONNs. These neural networks are able to group events that look similar. The ART SONN has an advantage in classifying the event because the types of cluster groups do not need to be pre-defined. The results from the SONNs together with an expert seismologist's classification are then used to derive event classification probabilities.

Visualized analysis of mixed numeric and categorical data via extended self-organizing map.

PubMed

Hsu, Chung-Chian; Lin, Shu-Han

2012-01-01

Many real-world datasets are of mixed types, having numeric and categorical attributes. Even though difficult, analyzing mixed-type datasets is important. In this paper, we propose an extended self-organizing map (SOM), called MixSOM, which utilizes a data structure distance hierarchy to facilitate the handling of numeric and categorical values in a direct, unified manner. Moreover, the extended model regularizes the prototype distance between neighboring neurons in proportion to their map distance so that structures of the clusters can be portrayed better on the map. Extensive experiments on several synthetic and real-world datasets are conducted to demonstrate the capability of the model and to compare MixSOM with several existing models including Kohonen's SOM, the generalized SOM and visualization-induced SOM. The results show that MixSOM is superior to the other models in reflecting the structure of the mixed-type data and facilitates further analysis of the data such as exploration at various levels of granularity.

Neural network analysis of crosshole tomographic images: The seismic signature of gas hydrate bearing sediments in the Mackenzie Delta (NW Canada)

NASA Astrophysics Data System (ADS)

Bauer, K.; Pratt, R. G.; Haberland, C.; Weber, M.

2008-10-01

Crosshole seismic experiments were conducted to study the in-situ properties of gas hydrate bearing sediments (GHBS) in the Mackenzie Delta (NW Canada). Seismic tomography provided images of P velocity, anisotropy, and attenuation. Self-organizing maps (SOM) are powerful neural network techniques to classify and interpret multi-attribute data sets. The coincident tomographic images are translated to a set of data vectors in order to train a Kohonen layer. The total gradient of the model vectors is determined for the trained SOM and a watershed segmentation algorithm is used to visualize and map the lithological clusters with well-defined seismic signatures. Application to the Mallik data reveals four major litho-types: (1) GHBS, (2) sands, (3) shale/coal interlayering, and (4) silt. The signature of seismic P wave characteristics distinguished for the GHBS (high velocities, strong anisotropy and attenuation) is new and can be used for new exploration strategies to map and quantify gas hydrates.

Learning vector quantization neural networks improve accuracy of transcranial color-coded duplex sonography in detection of middle cerebral artery spasm--preliminary report.

PubMed

Swiercz, Miroslaw; Kochanowicz, Jan; Weigele, John; Hurst, Robert; Liebeskind, David S; Mariak, Zenon; Melhem, Elias R; Krejza, Jaroslaw

2008-01-01

To determine the performance of an artificial neural network in transcranial color-coded duplex sonography (TCCS) diagnosis of middle cerebral artery (MCA) spasm. TCCS was prospectively acquired within 2 h prior to routine cerebral angiography in 100 consecutive patients (54M:46F, median age 50 years). Angiographic MCA vasospasm was classified as mild (<25% of vessel caliber reduction), moderate (25-50%), or severe (>50%). A Learning Vector Quantization neural network classified MCA spasm based on TCCS peak-systolic, mean, and end-diastolic velocity data. During a four-class discrimination task, accurate classification by the network ranged from 64.9% to 72.3%, depending on the number of neurons in the Kohonen layer. Accurate classification of vasospasm ranged from 79.6% to 87.6%, with an accuracy of 84.7% to 92.1% for the detection of moderate-to-severe vasospasm. An artificial neural network may increase the accuracy of TCCS in diagnosis of MCA spasm.

Cluster analysis of word frequency dynamics

NASA Astrophysics Data System (ADS)

Maslennikova, Yu S.; Bochkarev, V. V.; Belashova, I. A.

2015-01-01

This paper describes the analysis and modelling of word usage frequency time series. During one of previous studies, an assumption was put forward that all word usage frequencies have uniform dynamics approaching the shape of a Gaussian function. This assumption can be checked using the frequency dictionaries of the Google Books Ngram database. This database includes 5.2 million books published between 1500 and 2008. The corpus contains over 500 billion words in American English, British English, French, German, Spanish, Russian, Hebrew, and Chinese. We clustered time series of word usage frequencies using a Kohonen neural network. The similarity between input vectors was estimated using several algorithms. As a result of the neural network training procedure, more than ten different forms of time series were found. They describe the dynamics of word usage frequencies from birth to death of individual words. Different groups of word forms were found to have different dynamics of word usage frequency variations.

Identification of petroleum hydrocarbons using a reduced number of PAHs selected by Procrustes rotation.

PubMed

Fernández-Varela, R; Andrade, J M; Muniategui, S; Prada, D; Ramírez-Villalobos, F

2010-04-01

Identifying petroleum-related products released into the environment is a complex and difficult task. To achieve this, polycyclic aromatic hydrocarbons (PAHs) are of outstanding importance nowadays. Despite traditional quantitative fingerprinting uses straightforward univariate statistical analyses to differentiate among oils and to assess their sources, a multivariate strategy based on Procrustes rotation (PR) was applied in this paper. The aim of PR is to select a reduced subset of PAHs still capable of performing a satisfactory identification of petroleum-related hydrocarbons. PR selected two subsets of three (C(2)-naphthalene, C(2)-dibenzothiophene and C(2)-phenanthrene) and five (C(1)-decahidronaphthalene, naphthalene, C(2)-phenanthrene, C(3)-phenanthrene and C(2)-fluoranthene) PAHs for each of the two datasets studied here. The classification abilities of each subset of PAHs were tested using principal components analysis, hierarchical cluster analysis and Kohonen neural networks and it was demonstrated that they unraveled the same patterns as the overall set of PAHs. (c) 2009 Elsevier Ltd. All rights reserved.

High-resolution Self-Organizing Maps for advanced visualization and dimension reduction.

PubMed

Saraswati, Ayu; Nguyen, Van Tuc; Hagenbuchner, Markus; Tsoi, Ah Chung

2018-05-04

Kohonen's Self Organizing feature Map (SOM) provides an effective way to project high dimensional input features onto a low dimensional display space while preserving the topological relationships among the input features. Recent advances in algorithms that take advantages of modern computing hardware introduced the concept of high resolution SOMs (HRSOMs). This paper investigates the capabilities and applicability of the HRSOM as a visualization tool for cluster analysis and its suitabilities to serve as a pre-processor in ensemble learning models. The evaluation is conducted on a number of established benchmarks and real-world learning problems, namely, the policeman benchmark, two web spam detection problems, a network intrusion detection problem, and a malware detection problem. It is found that the visualization resulted from an HRSOM provides new insights concerning these learning problems. It is furthermore shown empirically that broad benefits from the use of HRSOMs in both clustering and classification problems can be expected. Copyright © 2018 Elsevier Ltd. All rights reserved.

Pattern recognition and classification of vibrational spectra by artificial neural networks

NASA Astrophysics Data System (ADS)

Yang, Husheng

1999-10-01

A drawback of current open-path Fourier transform infrared (OP/FT-IR) systems is that they need a human expert to determine those compounds that may be quantified from a given spectrum. In this study, three types of artificial neural networks were used to alleviate this problem. Firstly, multi-layer feed-forward neural networks were used to automatically recognize compounds in an OP/FT-IR spectrum. Each neural network was trained to recognize one compound in the presence of up to ten interferents in an OP/FT-IR spectrum. The networks were successfully used to recognize five alcohols and two chlorinated compounds in field-measured controlled-release OP/FT-IR spectra of mixtures of these compounds. It has also been demonstrated that a neural network could correctly identify a spectrum in the presence of an interferent that was not included in the training set and could also reject interferents it has not seen before. Secondly, the possibility of using one- and two- dimensional Kohonen self-organizing maps (SOMs) to recognize similarities in low-resolution vapor-phase infrared spectra without any additional information has been investigated. Both full-range reference spectra and open-path window reference spectra were used to train the networks and the trained networks were then used to classify the reference spectra into several groups. The results showed that the SOMs obtained from the two different training sets were quite different, and it is more appropriate to use the second SOM in OP/FT-IR spectrometry. Thirdly, vapor-phase FT-IR reference spectra of five alcohols along with four baseline spectra were encoded as prototype vectors for a Hopfield network. Inclusion of the baseline spectra allowed the network to classify spectra as unknowns, when the reference spectra of these compounds were not stored as prototype vectors in the network. The network could identify each of the 5 alcohols correctly even in the presence of noise and interfering compounds. Finally

Seismic event classification system

DOEpatents

Dowla, F.U.; Jarpe, S.P.; Maurer, W.

1994-12-13

In the computer interpretation of seismic data, the critical first step is to identify the general class of an unknown event. For example, the classification might be: teleseismic, regional, local, vehicular, or noise. Self-organizing neural networks (SONNs) can be used for classifying such events. Both Kohonen and Adaptive Resonance Theory (ART) SONNs are useful for this purpose. Given the detection of a seismic event and the corresponding signal, computation is made of: the time-frequency distribution, its binary representation, and finally a shift-invariant representation, which is the magnitude of the two-dimensional Fourier transform (2-D FFT) of the binary time-frequency distribution. This pre-processed input is fed into the SONNs. These neural networks are able to group events that look similar. The ART SONN has an advantage in classifying the event because the types of cluster groups do not need to be pre-defined. The results from the SONNs together with an expert seismologist's classification are then used to derive event classification probabilities. 21 figures.

A new technique for solving puzzles.

PubMed

Makridis, Michael; Papamarkos, Nikos

2010-06-01

This paper proposes a new technique for solving jigsaw puzzles. The novelty of the proposed technique is that it provides an automatic jigsaw puzzle solution without any initial restriction about the shape of pieces, the number of neighbor pieces, etc. The proposed technique uses both curve- and color-matching similarity features. A recurrent procedure is applied, which compares and merges puzzle pieces in pairs, until the original puzzle image is reformed. Geometrical and color features are extracted on the characteristic points (CPs) of the puzzle pieces. CPs, which can be considered as high curvature points, are detected by a rotationally invariant corner detection algorithm. The features which are associated with color are provided by applying a color reduction technique using the Kohonen self-organized feature map. Finally, a postprocessing stage checks and corrects the relative position between puzzle pieces to improve the quality of the resulting image. Experimental results prove the efficiency of the proposed technique, which can be further extended to deal with even more complex jigsaw puzzle problems.

Variable selection based on clustering analysis for improvement of polyphenols prediction in green tea using synchronous fluorescence spectra

NASA Astrophysics Data System (ADS)

Shan, Jiajia; Wang, Xue; Zhou, Hao; Han, Shuqing; Riza, Dimas Firmanda Al; Kondo, Naoshi

2018-04-01

Synchronous fluorescence spectra, combined with multivariate analysis were used to predict flavonoids content in green tea rapidly and nondestructively. This paper presented a new and efficient spectral intervals selection method called clustering based partial least square (CL-PLS), which selected informative wavelengths by combining clustering concept and partial least square (PLS) methods to improve models’ performance by synchronous fluorescence spectra. The fluorescence spectra of tea samples were obtained and k-means and kohonen-self organizing map clustering algorithms were carried out to cluster full spectra into several clusters, and sub-PLS regression model was developed on each cluster. Finally, CL-PLS models consisting of gradually selected clusters were built. Correlation coefficient (R) was used to evaluate the effect on prediction performance of PLS models. In addition, variable influence on projection partial least square (VIP-PLS), selectivity ratio partial least square (SR-PLS), interval partial least square (iPLS) models and full spectra PLS model were investigated and the results were compared. The results showed that CL-PLS presented the best result for flavonoids prediction using synchronous fluorescence spectra.

Real-time camera-based face detection using a modified LAMSTAR neural network system

NASA Astrophysics Data System (ADS)

Girado, Javier I.; Sandin, Daniel J.; DeFanti, Thomas A.; Wolf, Laura K.

2003-03-01

This paper describes a cost-effective, real-time (640x480 at 30Hz) upright frontal face detector as part of an ongoing project to develop a video-based, tetherless 3D head position and orientation tracking system. The work is specifically targeted for auto-stereoscopic displays and projection-based virtual reality systems. The proposed face detector is based on a modified LAMSTAR neural network system. At the input stage, after achieving image normalization and equalization, a sub-window analyzes facial features using a neural network. The sub-window is segmented, and each part is fed to a neural network layer consisting of a Kohonen Self-Organizing Map (SOM). The output of the SOM neural networks are interconnected and related by correlation-links, and can hence determine the presence of a face with enough redundancy to provide a high detection rate. To avoid tracking multiple faces simultaneously, the system is initially trained to track only the face centered in a box superimposed on the display. The system is also rotationally and size invariant to a certain degree.

Variable selection based on clustering analysis for improvement of polyphenols prediction in green tea using synchronous fluorescence spectra.

PubMed

Shan, Jiajia; Wang, Xue; Zhou, Hao; Han, Shuqing; Riza, Dimas Firmanda Al; Kondo, Naoshi

2018-03-13

Synchronous fluorescence spectra, combined with multivariate analysis were used to predict flavonoids content in green tea rapidly and nondestructively. This paper presented a new and efficient spectral intervals selection method called clustering based partial least square (CL-PLS), which selected informative wavelengths by combining clustering concept and partial least square (PLS) methods to improve models' performance by synchronous fluorescence spectra. The fluorescence spectra of tea samples were obtained and k-means and kohonen-self organizing map clustering algorithms were carried out to cluster full spectra into several clusters, and sub-PLS regression model was developed on each cluster. Finally, CL-PLS models consisting of gradually selected clusters were built. Correlation coefficient (R) was used to evaluate the effect on prediction performance of PLS models. In addition, variable influence on projection partial least square (VIP-PLS), selectivity ratio partial least square (SR-PLS), interval partial least square (iPLS) models and full spectra PLS model were investigated and the results were compared. The results showed that CL-PLS presented the best result for flavonoids prediction using synchronous fluorescence spectra.

Classification of images acquired with colposcopy using artificial neural networks.

PubMed

Simões, Priscyla W; Izumi, Narjara B; Casagrande, Ramon S; Venson, Ramon; Veronezi, Carlos D; Moretti, Gustavo P; da Rocha, Edroaldo L; Cechinel, Cristian; Ceretta, Luciane B; Comunello, Eros; Martins, Paulo J; Casagrande, Rogério A; Snoeyer, Maria L; Manenti, Sandra A

2014-01-01

To explore the advantages of using artificial neural networks (ANNs) to recognize patterns in colposcopy to classify images in colposcopy. Transversal, descriptive, and analytical study of a quantitative approach with an emphasis on diagnosis. The training test e validation set was composed of images collected from patients who underwent colposcopy. These images were provided by a gynecology clinic located in the city of Criciúma (Brazil). The image database (n = 170) was divided; 48 images were used for the training process, 58 images were used for the tests, and 64 images were used for the validation. A hybrid neural network based on Kohonen self-organizing maps and multilayer perceptron (MLP) networks was used. After 126 cycles, the validation was performed. The best results reached an accuracy of 72.15%, a sensibility of 69.78%, and a specificity of 68%. Although the preliminary results still exhibit an average efficiency, the present approach is an innovative and promising technique that should be deeply explored in the context of the present study.

Extruded Bread Classification on the Basis of Acoustic Emission Signal With Application of Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Świetlicka, Izabela; Muszyński, Siemowit; Marzec, Agata

2015-04-01

The presented work covers the problem of developing a method of extruded bread classification with the application of artificial neural networks. Extruded flat graham, corn, and rye breads differening in water activity were used. The breads were subjected to the compression test with simultaneous registration of acoustic signal. The amplitude-time records were analyzed both in time and frequency domains. Acoustic emission signal parameters: single energy, counts, amplitude, and duration acoustic emission were determined for the breads in four water activities: initial (0.362 for rye, 0.377 for corn, and 0.371 for graham bread), 0.432, 0.529, and 0.648. For classification and the clustering process, radial basis function, and self-organizing maps (Kohonen network) were used. Artificial neural networks were examined with respect to their ability to classify or to cluster samples according to the bread type, water activity value, and both of them. The best examination results were achieved by the radial basis function network in classification according to water activity (88%), while the self-organizing maps network yielded 81% during bread type clustering.

Spike sorting based upon machine learning algorithms (SOMA).

PubMed

Horton, P M; Nicol, A U; Kendrick, K M; Feng, J F

2007-02-15

We have developed a spike sorting method, using a combination of various machine learning algorithms, to analyse electrophysiological data and automatically determine the number of sampled neurons from an individual electrode, and discriminate their activities. We discuss extensions to a standard unsupervised learning algorithm (Kohonen), as using a simple application of this technique would only identify a known number of clusters. Our extra techniques automatically identify the number of clusters within the dataset, and their sizes, thereby reducing the chance of misclassification. We also discuss a new pre-processing technique, which transforms the data into a higher dimensional feature space revealing separable clusters. Using principal component analysis (PCA) alone may not achieve this. Our new approach appends the features acquired using PCA with features describing the geometric shapes that constitute a spike waveform. To validate our new spike sorting approach, we have applied it to multi-electrode array datasets acquired from the rat olfactory bulb, and from the sheep infero-temporal cortex, and using simulated data. The SOMA sofware is available at http://www.sussex.ac.uk/Users/pmh20/spikes.

Application of Multidimensional Data Visualization by Means of Self-Organizing Kohonen Maps to Evaluate Classification Possibilities of Various Coal Types / Zastosowanie Wizualizacji Wielowymiarowych Danych Za Pomocą Sieci Kohonena Do Oceny Możliwości Klasyfikacji Różnych Typów Węgla

NASA Astrophysics Data System (ADS)

Jamróz, Dariusz; Niedoba, Tomasz

2015-03-01

Multidimensional data visualization methods are a modern tool allowing to classify some analysed objects. In the case of grained materials e.g. coal, many characteristics have an influence on the material quality. The paper presents the possibility of applying visualization techniques for coal type identification and determination of significant differences between various types of coal. To achieve this purpose, the method of Kohonen maps was applied by means of which three types of coal - 31, 34.2 and 35 (according to Polish classification of coal types) were investigated. It was stated that the applied methodology allows to identify certain coal types efficiently and can be used as a qualitative criterion for grained materials. Metody wizualizacji wielowymiarowych danych są nowoczesnym narzędziem umożliwającym klasyfikację analizowanych obiektów, którymi mogą być różnego typu dane opisujące wybrane zjawisko lub materiał. W przypadku materiałów uziarnionych, jakim jest np. węgiel, wiele cech ma wpływ na jakość materiału, tj. np. gęstość, wielkość ziaren, ciepło spalania, zawartość popiołu, zawartość siarki itp. Na potrzeby artykułu przeprowadzono rozdział węgli z trzech wybranych kopalni węgla kamiennego, zlokalizowanych w Górnośląskim Okręgu Przemysłowym. Każda z tych kopalni pracuje na innego typu węglu. W tym przypadku były to węgle o typach 31, 34.2 oraz 35 (według polskiej klasyfikacji typów węgla). Najpierw, materiał został podzielony na klasy ziarnowe a następnie za pomocą rozdziale w cieczy ciężkiej (roztwór chlorku cynku) na frakcje gęstościowe. Dla tak przygotowanego materiału przeprowadzono następnie analizy chemiczne mające na celu określenie takich parametrów, jak zawartość siarki, zawartość popiołu, zawartość części lotnych, ciepło spalania oraz wilgotność analityczną. W ten sposób, dla każdej klaso-frakcji uzyskano bogate charakterystyki badanego

Coupling Self-Organizing Maps with a Naïve Bayesian classifier: A case study for classifying Vermont streams using geomorphic, habitat and biological assessment data

NASA Astrophysics Data System (ADS)

Fytilis, N.; Rizzo, D. M.

2012-12-01

Environmental managers are increasingly required to forecast the long-term effects and the resilience or vulnerability of biophysical systems to human-generated stresses. Mitigation strategies for hydrological and environmental systems need to be assessed in the presence of uncertainty. An important aspect of such complex systems is the assessment of variable uncertainty on the model response outputs. We develop a new classification tool that couples a Naïve Bayesian Classifier with a modified Kohonen Self-Organizing Map to tackle this challenge. For proof-of-concept, we use rapid geomorphic and reach-scale habitat assessments data from over 2500 Vermont stream reaches (~1371 stream miles) assessed by the Vermont Agency of Natural Resources (VTANR). In addition, the Vermont Department of Environmental Conservation (VTDEC) estimates stream habitat biodiversity indices (macro-invertebrates and fish) and a variety of water quality data. Our approach fully utilizes the existing VTANR and VTDEC data sets to improve classification of stream-reach habitat and biological integrity. The combined SOM-Naïve Bayesian architecture is sufficiently flexible to allow for continual updates and increased accuracy associated with acquiring new data. The Kohonen Self-Organizing Map (SOM) is an unsupervised artificial neural network that autonomously analyzes properties inherent in a given a set of data. It is typically used to cluster data vectors into similar categories when a priori classes do not exist. The ability of the SOM to convert nonlinear, high dimensional data to some user-defined lower dimension and mine large amounts of data types (i.e., discrete or continuous, biological or geomorphic data) makes it ideal for characterizing the sensitivity of river networks in a variety of contexts. The procedure is data-driven, and therefore does not require the development of site-specific, process-based classification stream models, or sets of if-then-else rules associated with

Infrared differential-absorption Mueller matrix spectroscopy and neural network-based data fusion for biological aerosol standoff detection.

PubMed

Carrieri, Arthur H; Copper, Jack; Owens, David J; Roese, Erik S; Bottiger, Jerold R; Everly, Robert D; Hung, Kevin C

2010-01-20

An active spectrophotopolarimeter sensor and support system were developed for a military/civilian defense feasibility study concerning the identification and standoff detection of biological aerosols. Plumes of warfare agent surrogates gamma-irradiated Bacillus subtilis and chicken egg white albumen (analytes), Arizona road dust (terrestrial interferent), water mist (atmospheric interferent), and talcum powders (experiment controls) were dispersed inside windowless chambers and interrogated by multiple CO(2) laser beams spanning 9.1-12.0 microm wavelengths (lambda). Molecular vibration and vibration-rotation activities by the subject analyte are fundamentally strong within this "fingerprint" middle infrared spectral region. Distinct polarization-modulations of incident irradiance and backscatter radiance of tuned beams generate the Mueller matrix (M) of subject aerosol. Strings of all 15 normalized elements {M(ij)(lambda)/M(11)(lambda)}, which completely describe physical and geometric attributes of the aerosol particles, are input fields for training hybrid Kohonen self-organizing map feed-forward artificial neural networks (ANNs). The properly trained and validated ANN model performs pattern recognition and type-classification tasks via internal mappings. A typical ANN that mathematically clusters analyte, interferent, and control aerosols with nil overlap of species is illustrated, including sensitivity analysis of performance.

Benchmarking Ligand-Based Virtual High-Throughput Screening with the PubChem Database

PubMed Central

Butkiewicz, Mariusz; Lowe, Edward W.; Mueller, Ralf; Mendenhall, Jeffrey L.; Teixeira, Pedro L.; Weaver, C. David; Meiler, Jens

2013-01-01

With the rapidly increasing availability of High-Throughput Screening (HTS) data in the public domain, such as the PubChem database, methods for ligand-based computer-aided drug discovery (LB-CADD) have the potential to accelerate and reduce the cost of probe development and drug discovery efforts in academia. We assemble nine data sets from realistic HTS campaigns representing major families of drug target proteins for benchmarking LB-CADD methods. Each data set is public domain through PubChem and carefully collated through confirmation screens validating active compounds. These data sets provide the foundation for benchmarking a new cheminformatics framework BCL::ChemInfo, which is freely available for non-commercial use. Quantitative structure activity relationship (QSAR) models are built using Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Decision Trees (DTs), and Kohonen networks (KNs). Problem-specific descriptor optimization protocols are assessed including Sequential Feature Forward Selection (SFFS) and various information content measures. Measures of predictive power and confidence are evaluated through cross-validation, and a consensus prediction scheme is tested that combines orthogonal machine learning algorithms into a single predictor. Enrichments ranging from 15 to 101 for a TPR cutoff of 25% are observed. PMID:23299552

Monitoring the Microgravity Environment Quality On-Board the International Space Station Using Soft Computing Techniques

NASA Technical Reports Server (NTRS)

Jules, Kenol; Lin, Paul P.

2001-01-01

This paper presents an artificial intelligence monitoring system developed by the NASA Glenn Principal Investigator Microgravity Services project to help the principal investigator teams identify the primary vibratory disturbance sources that are active, at any moment in time, on-board the International Space Station, which might impact the microgravity environment their experiments are exposed to. From the Principal Investigator Microgravity Services' web site, the principal investigator teams can monitor via a graphical display, in near real time, which event(s) is/are on, such as crew activities, pumps, fans, centrifuges, compressor, crew exercise, platform structural modes, etc., and decide whether or not to run their experiments based on the acceleration environment associated with a specific event. This monitoring system is focused primarily on detecting the vibratory disturbance sources, but could be used as well to detect some of the transient disturbance sources, depending on the events duration. The system has built-in capability to detect both known and unknown vibratory disturbance sources. Several soft computing techniques such as Kohonen's Self-Organizing Feature Map, Learning Vector Quantization, Back-Propagation Neural Networks, and Fuzzy Logic were used to design the system.

MRI segmentation using dialectical optimization.

PubMed

dos Santos, Wellington P; de Assis, Francisco M; de Souza, Ricardo E

2009-01-01

Biology, Psychology and Social Sciences are intrinsically connected to the very roots of the development of algorithms and methods in Computational Intelligence, as it is easily seen in approaches like genetic algorithms, evolutionary programming and particle swarm optimization. In this work we propose a new optimization method based on dialectics using fuzzy membership functions to model the influence of interactions between integrating poles in the status of each pole. Poles are the basic units composing dialectical systems. In order to validate our proposal we designed a segmentation method based on the optimization of k-means using dialectics for the segmentation of MR images. As a case study we used 181 MR synthetic multispectral images composed by proton density, T(1)- and T(2)-weighted synthetic brain images of 181 slices with 1 mm, resolution of 1 mm(3), for a normal brain and a noiseless MR tomographic system without field inhomogeneities, amounting a total of 543 images, generated by the simulator BrainWeb [2]. Our principal target here is comparing our proposal to k-means, fuzzy c-means, and Kohonen's self-organized maps, concerning the quantization error, we proved that our method can improved results obtained using k-means.

DCS-Neural-Network Program for Aircraft Control and Testing

NASA Technical Reports Server (NTRS)

Jorgensen, Charles C.

2006-01-01

A computer program implements a dynamic-cell-structure (DCS) artificial neural network that can perform such tasks as learning selected aerodynamic characteristics of an airplane from wind-tunnel test data and computing real-time stability and control derivatives of the airplane for use in feedback linearized control. A DCS neural network is one of several types of neural networks that can incorporate additional nodes in order to rapidly learn increasingly complex relationships between inputs and outputs. In the DCS neural network implemented by the present program, the insertion of nodes is based on accumulated error. A competitive Hebbian learning rule (a supervised-learning rule in which connection weights are adjusted to minimize differences between actual and desired outputs for training examples) is used. A Kohonen-style learning rule (derived from a relatively simple training algorithm, implements a Delaunay triangulation layout of neurons) is used to adjust node positions during training. Neighborhood topology determines which nodes are used to estimate new values. The network learns, starting with two nodes, and adds new nodes sequentially in locations chosen to maximize reductions in global error. At any given time during learning, the error becomes homogeneously distributed over all nodes.

Sound quality indicators for urban places in Paris cross-validated by Milan data.

PubMed

Ricciardi, Paola; Delaitre, Pauline; Lavandier, Catherine; Torchia, Francesca; Aumond, Pierre

2015-10-01

A specific smartphone application was developed to collect perceptive and acoustic data in Paris. About 3400 questionnaires were analyzed, regarding the global sound environment characterization, the perceived loudness of some emergent sources and the presence time ratio of sources that do not emerge from the background. Sound pressure level was recorded each second from the mobile phone's microphone during a 10-min period. The aim of this study is to propose indicators of urban sound quality based on linear regressions with perceptive variables. A cross validation of the quality models extracted from Paris data was carried out by conducting the same survey in Milan. The proposed sound quality general model is correlated with the real perceived sound quality (72%). Another model without visual amenity and familiarity is 58% correlated with perceived sound quality. In order to improve the sound quality indicator, a site classification was performed by Kohonen's Artificial Neural Network algorithm, and seven specific class models were developed. These specific models attribute more importance on source events and are slightly closer to the individual data than the global model. In general, the Parisian models underestimate the sound quality of Milan environments assessed by Italian people.

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.

Estimation of dew point temperature using neuro-fuzzy and neural network techniques

NASA Astrophysics Data System (ADS)

Kisi, Ozgur; Kim, Sungwon; Shiri, Jalal

2013-11-01

This study investigates the ability of two different artificial neural network (ANN) models, generalized regression neural networks model (GRNNM) and Kohonen self-organizing feature maps neural networks model (KSOFM), and two different adaptive neural fuzzy inference system (ANFIS) models, ANFIS model with sub-clustering identification (ANFIS-SC) and ANFIS model with grid partitioning identification (ANFIS-GP), for estimating daily dew point temperature. The climatic data that consisted of 8 years of daily records of air temperature, sunshine hours, wind speed, saturation vapor pressure, relative humidity, and dew point temperature from three weather stations, Daego, Pohang, and Ulsan, in South Korea were used in the study. The estimates of ANN and ANFIS models were compared according to the three different statistics, root mean square errors, mean absolute errors, and determination coefficient. Comparison results revealed that the ANFIS-SC, ANFIS-GP, and GRNNM models showed almost the same accuracy and they performed better than the KSOFM model. Results also indicated that the sunshine hours, wind speed, and saturation vapor pressure have little effect on dew point temperature. It was found that the dew point temperature could be successfully estimated by using T mean and R H variables.

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.

Cascaded neural networks for sequenced propagation estimation, multiuser detection, and adaptive radio resource control of third-generation wireless networks for multimedia services

NASA Astrophysics Data System (ADS)

Hortos, William S.

1999-03-01

A hybrid neural network approach is presented to estimate radio propagation characteristics and multiuser interference and to evaluate their combined impact on throughput, latency and information loss in third-generation (3G) wireless networks. The latter three performance parameters influence the quality of service (QoS) for multimedia services under consideration for 3G networks. These networks, based on a hierarchical architecture of overlaying macrocells on top of micro- and picocells, are planned to operate in mobile urban and indoor environments with service demands emanating from circuit-switched, packet-switched and satellite-based traffic sources. Candidate radio interfaces for these networks employ a form of wideband CDMA in 5-MHz and wider-bandwidth channels, with possible asynchronous operation of the mobile subscribers. The proposed neural network (NN) architecture allocates network resources to optimize QoS metrics. Parameters of the radio propagation channel are estimated, followed by control of an adaptive antenna array at the base station to minimize interference, and then joint multiuser detection is performed at the base station receiver. These adaptive processing stages are implemented as a sequence of NN techniques that provide their estimates as inputs to a final- stage Kohonen self-organizing feature map (SOFM). The SOFM optimizes the allocation of available network resources to satisfy QoS requirements for variable-rate voice, data and video services. As the first stage of the sequence, a modified feed-forward multilayer perceptron NN is trained on the pilot signals of the mobile subscribers to estimate the parameters of shadowing, multipath fading and delays on the uplinks. A recurrent NN (RNN) forms the second stage to control base stations' adaptive antenna arrays to minimize intra-cell interference. The third stage is based on a Hopfield NN (HNN), modified to detect multiple users on the uplink radio channels to mitigate multiaccess

A multi-model fusion strategy for multivariate calibration using near and mid-infrared spectra of samples from brewing industry.

PubMed

Tan, Chao; Chen, Hui; Wang, Chao; Zhu, Wanping; Wu, Tong; Diao, Yuanbo

2013-03-15

Near and mid-infrared (NIR/MIR) spectroscopy techniques have gained great acceptance in the industry due to their multiple applications and versatility. However, a success of application often depends heavily on the construction of accurate and stable calibration models. For this purpose, a simple multi-model fusion strategy is proposed. It is actually the combination of Kohonen self-organizing map (KSOM), mutual information (MI) and partial least squares (PLSs) and therefore named as KMICPLS. It works as follows: First, the original training set is fed into a KSOM for unsupervised clustering of samples, on which a series of training subsets are constructed. Thereafter, on each of the training subsets, a MI spectrum is calculated and only the variables with higher MI values than the mean value are retained, based on which a candidate PLS model is constructed. Finally, a fixed number of PLS models are selected to produce a consensus model. Two NIR/MIR spectral datasets from brewing industry are used for experiments. The results confirms its superior performance to two reference algorithms, i.e., the conventional PLS and genetic algorithm-PLS (GAPLS). It can build more accurate and stable calibration models without increasing the complexity, and can be generalized to other NIR/MIR applications. Copyright © 2012 Elsevier B.V. All rights reserved.

Improving the segmentation of therapy-induced leukoencephalopathy using apriori information and a gradient magnitude threshold

NASA Astrophysics Data System (ADS)

Glass, John O.; Reddick, Wilburn E.; Reeves, Cara; Pui, Ching-Hon

2004-05-01

Reliably quantifying therapy-induced leukoencephalopathy in children treated for cancer is a challenging task due to its varying MR properties and similarity to normal tissues and imaging artifacts. T1, T2, PD, and FLAIR images were analyzed for a subset of 15 children from an institutional protocol for the treatment of acute lymphoblastic leukemia. Three different analysis techniques were compared to examine improvements in the segmentation accuracy of leukoencephalopathy versus manual tracings by two expert observers. The first technique utilized no apriori information and a white matter mask based on the segmentation of the first serial examination of each patient. MR images were then segmented with a Kohonen Self-Organizing Map. The other two techniques combine apriori maps from the ICBM atlas spatially normalized to each patient and resliced using SPM99 software. The apriori maps were included as input and a gradient magnitude threshold calculated on the FLAIR images was also utilized. The second technique used a 2-dimensional threshold, while the third algorithm utilized a 3-dimensional threshold. Kappa values were compared for the three techniques to each observer, and improvements were seen with each addition to the original algorithm (Observer 1: 0.651, 0.653, 0.744; Observer 2: 0.603, 0.615, 0.699).

Differentiating therapy-induced leukoencephalopathy from unmyelinated white matter in children treated for acute lymphoblastic leukemia (ALL)

NASA Astrophysics Data System (ADS)

Reddick, Wilburn E.; Glass, John O.; Pui, Ching-Hon

2003-05-01

Reliably detecting subtle therapy-induced leukoencephalopathy in children treated for cancer is a challenging task due to its nearly identical MR properties and location with unmyelinated white matter. T1, T2, PD, and FLAIR images were collected for 44 children aged 1.7-18.7 (median 5.9) years near the start of therapy for ALL. The ICBM atlas and corresponding apriori maps were spatially normalized to each patient and resliced using SPM99 software. A combined imaging set consisting of MR images and WM, GM and CSF apriori maps were then analyzed with a Kohonen Self-Organizing Map. Vectors from hyperintense regions were compared to normal appearing genu vectors from the same patient. Analysis of the distributions of the differences, calculated on T2 and FLAIR images, revealed two distinct groups. The first large group, assumed normal unmyelinated white matter, consisted of 37 patients with changes in FLAIR ranging from 80 to 147 (mean 117-/+17) and T2 ranging from 92 to 217 (mean 144-/+28). The second group, assumed leukoencephalopathy, consisted of seven patients with changes in FLAIR ranging from 154 to 196 (mean 171-/+19) and T2 ranging from 190 to 287 (mean 216-/+33). A threshold was established for both FLAIR (change > 150) and T2 (change > 180).

Atmospheric thorium pollution and inhalation exposure in the largest rare earth mining and smelting area in China.

PubMed

Wang, Lingqing; Zhong, Buqing; Liang, Tao; Xing, Baoshan; Zhu, Yifang

2016-12-01

Exposure to radionuclide thorium (Th) has generated widespread public concerns, mainly because of its radiological effects on human health. Activity levels of airborne 232 Th in total suspended particulate (TSP) were measured in the vicinity of the largest rare earth mine in China in August 2012 and March 2013. The mean activity concentrations of 232 Th in TSP ranged from 820μBqm -3 in a mining area in August 2012 to 39,720μBqm -3 in a smelting area in March 2013, much higher than the world reference of 0.5μBqm -3 . Multistatistical analysis and Kohonen's self-organizing maps suggested that 232 Th in TSP was mainly derived from rare earth mining and smelting practices. In addition, personal inhalation exposures to 232 Th associated with respirable particulate (PM 10 ) were also measured among local dwellers via personal monitoring. The mean dose values for different age groups in the smelting and mining areas ranged from 97.86 to 417μSvyear - 1 and from 101.03 to 430.83μSvyear -1 , respectively. These results indicate that people living in the study areas are exposed to high levels of widespread 232 Th. Copyright © 2016 Elsevier B.V. All rights reserved.

Comparison of antibiotic resistance patterns in collections of Escherichia coli and Proteus mirabilis uropathogenic strains.

PubMed

Adamus-Bialek, Wioletta; Zajac, Elzbieta; Parniewski, Pawel; Kaca, Wieslaw

2013-04-01

Escherichia coli and Proteus mirabilis are important urinary tract pathogens. The constant increase in the antibiotic resistance of clinical bacterial strains has become an important clinical problem. The aim of this study was to compare the antibiotic resistance of 141 clinical (Sweden and Poland) and 42 laboratory (Czech Republic) P. mirabilis strains and 129 clinical (Poland) uropathogenic E. coli strains. The proportion of unique versus diverse patterns in Swedish clinical and laboratory P. mirabilis strain collections was comparable. Notably, a similar proportion of unique versus diverse patterns was observed in Polish clinical P. mirabilis and E. coli strain collections. Mathematical models of the antibiotic resistance of E. coli and P. mirabilis strains based on Kohonen networks and association analysis are presented. In contrast to the three clinical strain collections, which revealed complex associations with the antibiotics tested, laboratory P. mirabilis strains provided simple antibiotic association diagrams. The monitoring of antibiotic resistance patterns of clinical E. coli and P. mirabilis strains plays an important role in the treatment procedures for urinary tract infections and is important in the context of the spreading drug resistance in uropathogenic strain populations. The adaptability and flexibility of the genomes of E. coli and P. mirabilis strains are discussed.

Metallic content of wines from the Canary Islands (Spain). Application of artificial neural networks to the data analysis.

PubMed

Frías, Sergio; Conde, José E; Rodríguez, Miguel A; Dohnal, Vlasta; Pérez-Trujillo, Juan P

2002-10-01

Eleven elements, K, Na, Ca, Mg, Fe, Cu, Zn, Mn, Sr, Li and Rb, were determined in dry and sweet wines bearing the denominations of origin of El Hierro, La Palma and Lanzarote islands (Canary Islands, Spain). Analyses were performed by flame atomic absorption spectrophotometry, with the exceptions of Li and Rb for which flame atomic emission spectrophotometry was used. The content in copper and iron did not present risks of cases. All samples presented a copper and zinc content below the maximum amount recommended by the Office International de la Vigne et du Vin (OIV) for these elements. Significant differences in the metallic content were found among the different islands. Thus, Lanzarote presented the highest mean content in sodium and lithium and the lowest mean content in rubidium, and La Palma presented the highest mean content in strontium and rubidium. Sweet wines from La Palma, elaborated as naturally sweet with over-ripe grapes, presented mean contents significantly higher with regard to dry wines from the same island in the majority of the analysed elements. Cluster analysis and Kohonen self-organising maps showed differences in wines according to the island of origin and the ripening state of the grapes. Back-propagation artificial neural networks showed better prediction ability than stepwise linear discriminant analysis.

Growing a hypercubical output space in a self-organizing feature map.

PubMed

Bauer, H U; Villmann, T

1997-01-01

Neural maps project data from an input space onto a neuron position in a (often lower dimensional) output space grid in a neighborhood preserving way, with neighboring neurons in the output space responding to neighboring data points in the input space. A map-learning algorithm can achieve an optimal neighborhood preservation only, if the output space topology roughly matches the effective structure of the data in the input space. We here present a growth algorithm, called the GSOM or growing self-organizing map, which enhances a widespread map self-organization process, Kohonen's self-organizing feature map (SOFM), by an adaptation of the output space grid during learning. The GSOM restricts the output space structure to the shape of a general hypercubical shape, with the overall dimensionality of the grid and its extensions along the different directions being subject of the adaptation. This constraint meets the demands of many larger information processing systems, of which the neural map can be a part. We apply our GSOM-algorithm to three examples, two of which involve real world data. Using recently developed methods for measuring the degree of neighborhood preservation in neural maps, we find the GSOM-algorithm to produce maps which preserve neighborhoods in a nearly optimal fashion.

Subtle volume differences in brain parenchyma of children surviving medulloblastoma

NASA Astrophysics Data System (ADS)

Reddick, Wilburn E.; Mulhern, Raymond K.; Elkin, T. David; Glass, John O.; Langston, James W.

1998-07-01

The overriding incentive for accurate quantification of the functional status of children treated for brain tumors emerges from the clinician's desire to balance the efficacy and chronic toxicity of therapies used for the developing child. A hybrid combination of the Kohonen self-organizing map (SOM) for segmentation and a multilayer backpropagation (MLBP) neural network for classification removes observer variances to yield a reproducible and accurate identification of tissues. A group of 17 volunteers and 77 patients from a larger ongoing study of pediatric patients with brain tumors were used to investigate the sensitivity of segmented volumes to determine atrophy as measured by two radiologists. The atrophy study revealed a significant relationship for brain parenchyma, CSF and white matter volumes with atrophy while gray matter had no significant relationship. Brain parenchyma and subsequently white matter were found to be inversely proportional to increasing grades of atrophy. An additional study compared fifteen age-matched patients treated with irradiation and surgery with patients treated with surgery alone. The age-matched study of patients demonstrated that brain volumes in the irradiated patients were significantly decreased compared to those treated with surgery alone. Further investigation of this difference revealed that white matter was significantly reduced while gray matter was relatively unchanged.

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.

Integration of Satellite Tracking Data and Satellite Images for Detailed Characteristics of Wildlife Habitats

NASA Astrophysics Data System (ADS)

Dobrynin, D. V.; Rozhnov, V. V.; Saveliev, A. A.; Sukhova, O. V.; Yachmennikova, A. A.

2017-12-01

Methods of analysis of the results got from satellite tracking of large terrestrial mammals differ in the level of their integration with additional geographic data. The reliable fine-scale cartographic basis for assessing specific wildlife habitats can be developed through the interpretation of multispectral remote sensing data and extrapolation of the results to the entire estimated species range. Topographic maps were ordinated according to classified features using self-organizing maps (Kohonen's SOM). The satellite image of the Ussuriiskyi Nature Reserve area was interpreted for the analysis of movement conditions for seven wild Amur tigers ( Panthera tigris altaica) equipped with GPS collars. 225 SOM classes for cartographic visualization are sufficient for the detailed mapping of all natural complexes that were identified as a result of interpretation. During snow-free periods, tigers preferred deciduous and shrub associations at lower elevations, as well as mixed forests in the valleys of streams that are adjacent to sparse forests and shrub watershed in the mountain ranges; during heavy snow periods, the animals preferred the entire range of plant communities in different relief types, except for open sites in meadows and abandoned fields at foothills. The border zones of different biotopes were typically used by the tigers during all seasons. Amur tigers preferred coniferous forests for long-term movements.

Application of counterpropagation artificial neural network for modelling properties of fish antibiotics.

PubMed

Maran, E; Novic, M; Barbieri, P; Zupan, J

2004-01-01

The present study focuses on fish antibiotics which are an important group of pharmaceuticals used in fish farming to treat infections and, until recently, most of them have been exposed to the environment with very little attention. Information about the environmental behaviour and the description of the environmental fate of medical substances are difficult or expensive to obtain. The experimental information in terms of properties is reported when available, in other cases, it is estimated by standard tools as those provided by the United States Environmental Protection Agency EPISuite software and by custom quantitative structure-activity relationship (QSAR) applications. In this study, a QSAR screening of 15 fish antibiotics and 132 xenobiotic molecules was performed with two aims: (i) to develop a model for the estimation of octanol--water partition coefficient (logP) and (ii) to estimate the relative binding affinity to oestrogen receptor (log RBA) using a model constructed on the activities of 132 xenobiotic compounds. The custom models are based on constitutional, topological, electrostatic and quantum chemical descriptors computed by the CODESSA software. Kohonen neural networks (self organising maps) were used to study similarity between the considered chemicals while counter-propagation artificial neural networks were used to estimate the properties.

Self-organized neural maps of human protein sequences.

PubMed Central

Ferrán, E. A.; Pflugfelder, B.; Ferrara, P.

1994-01-01

We have recently described a method based on artificial neural networks to cluster protein sequences into families. The network was trained with Kohonen's unsupervised learning algorithm using, as inputs, the matrix patterns derived from the dipeptide composition of the proteins. We present here a large-scale application of that method to classify the 1,758 human protein sequences stored in the SwissProt database (release 19.0), whose lengths are greater than 50 amino acids. In the final 2-dimensional topologically ordered map of 15 x 15 neurons, proteins belonging to known families were associated with the same neuron or with neighboring ones. Also, as an attempt to reduce the time-consuming learning procedure, we compared 2 learning protocols: one of 500 epochs (100 SUN CPU-hours [CPU-h]), and another one of 30 epochs (6.7 CPU-h). A further reduction of learning-computing time, by a factor of about 3.3, with similar protein clustering results, was achieved using a matrix of 11 x 11 components to represent the sequences. Although network training is time consuming, the classification of a new protein in the final ordered map is very fast (14.6 CPU-seconds). We also show a comparison between the artificial neural network approach and conventional methods of biosequence analysis. PMID:8019421

Self-organizing map analysis using multivariate data from theophylline powders predicted by a thin-plate spline interpolation.

PubMed

Yasuda, Akihito; Onuki, Yoshinori; Kikuchi, Shingo; Takayama, Kozo

2010-11-01

The quality by design concept in pharmaceutical formulation development requires establishment of a science-based rationale and a design space. We integrated thin-plate spline (TPS) interpolation and Kohonen's self-organizing map (SOM) to visualize the latent structure underlying causal factors and pharmaceutical responses. As a model pharmaceutical product, theophylline powders were prepared based on the standard formulation. The angle of repose, compressibility, cohesion, and dispersibility were measured as the response variables. These responses were predicted quantitatively on the basis of a nonlinear TPS. A large amount of data on these powders was generated and classified into several clusters using an SOM. The experimental values of the responses were predicted with high accuracy, and the data generated for the powders could be classified into several distinctive clusters. The SOM feature map allowed us to analyze the global and local correlations between causal factors and powder characteristics. For instance, the quantities of microcrystalline cellulose (MCC) and magnesium stearate (Mg-St) were classified distinctly into each cluster, indicating that the quantities of MCC and Mg-St were crucial for determining the powder characteristics. This technique provides a better understanding of the relationships between causal factors and pharmaceutical responses in theophylline powder formulations. © 2010 Wiley-Liss, Inc. and the American Pharmacists Association

A multi-model fusion strategy for multivariate calibration using near and mid-infrared spectra of samples from brewing industry

NASA Astrophysics Data System (ADS)

Tan, Chao; Chen, Hui; Wang, Chao; Zhu, Wanping; Wu, Tong; Diao, Yuanbo

2013-03-01

Near and mid-infrared (NIR/MIR) spectroscopy techniques have gained great acceptance in the industry due to their multiple applications and versatility. However, a success of application often depends heavily on the construction of accurate and stable calibration models. For this purpose, a simple multi-model fusion strategy is proposed. It is actually the combination of Kohonen self-organizing map (KSOM), mutual information (MI) and partial least squares (PLSs) and therefore named as KMICPLS. It works as follows: First, the original training set is fed into a KSOM for unsupervised clustering of samples, on which a series of training subsets are constructed. Thereafter, on each of the training subsets, a MI spectrum is calculated and only the variables with higher MI values than the mean value are retained, based on which a candidate PLS model is constructed. Finally, a fixed number of PLS models are selected to produce a consensus model. Two NIR/MIR spectral datasets from brewing industry are used for experiments. The results confirms its superior performance to two reference algorithms, i.e., the conventional PLS and genetic algorithm-PLS (GAPLS). It can build more accurate and stable calibration models without increasing the complexity, and can be generalized to other NIR/MIR applications.

Discrimination of Active and Weakly Active Human BACE1 Inhibitors Using Self-Organizing Map and Support Vector Machine.

PubMed

Li, Hang; Wang, Maolin; Gong, Ya-Nan; Yan, Aixia

2016-01-01

β-secretase (BACE1) is an aspartyl protease, which is considered as a novel vital target in Alzheimer`s disease therapy. We collected a data set of 294 BACE1 inhibitors, and built six classification models to discriminate active and weakly active inhibitors using Kohonen's Self-Organizing Map (SOM) method and Support Vector Machine (SVM) method. Each molecular descriptor was calculated using the program ADRIANA.Code. We adopted two different methods: random method and Self-Organizing Map method, for training/test set split. The descriptors were selected by F-score and stepwise linear regression analysis. The best SVM model Model2C has a good prediction performance on test set with prediction accuracy, sensitivity (SE), specificity (SP) and Matthews correlation coefficient (MCC) of 89.02%, 90%, 88%, 0.78, respectively. Model 1A is the best SOM model, whose accuracy and MCC of the test set were 94.57% and 0.98, respectively. The lone pair electronegativity and polarizability related descriptors importantly contributed to bioactivity of BACE1 inhibitor. The Extended-Connectivity Finger-Prints_4 (ECFP_4) analysis found some vitally key substructural features, which could be helpful for further drug design research. The SOM and SVM models built in this study can be obtained from the authors by email or other contacts.

Applications of neural networks in training science.

PubMed

Pfeiffer, Mark; Hohmann, Andreas

2012-04-01

Training science views itself as an integrated and applied science, developing practical measures founded on scientific method. Therefore, it demands consideration of a wide spectrum of approaches and methods. Especially in the field of competitive sports, research questions are usually located in complex environments, so that mainly field studies are drawn upon to obtain broad external validity. Here, the interrelations between different variables or variable sets are mostly of a nonlinear character. In these cases, methods like neural networks, e.g., the pattern recognizing methods of Self-Organizing Kohonen Feature Maps or similar instruments to identify interactions might be successfully applied to analyze data. Following on from a classification of data analysis methods in training-science research, the aim of the contribution is to give examples of varied sports in which network approaches can be effectually used in training science. First, two examples are given in which neural networks are employed for pattern recognition. While one investigation deals with the detection of sporting talent in swimming, the other is located in game sports research, identifying tactical patterns in team handball. The third and last example shows how an artificial neural network can be used to predict competitive performance in swimming. Copyright © 2011 Elsevier B.V. All rights reserved.

Self-organizing feature maps for dynamic control of radio resources in CDMA microcellular networks

NASA Astrophysics Data System (ADS)

Hortos, William S.

1998-03-01

The application of artificial neural networks to the channel assignment problem for cellular code-division multiple access (CDMA) cellular networks has previously been investigated. CDMA takes advantage of voice activity and spatial isolation because its capacity is only interference limited, unlike time-division multiple access (TDMA) and frequency-division multiple access (FDMA) where capacities are bandwidth-limited. Any reduction in interference in CDMA translates linearly into increased capacity. To satisfy the high demands for new services and improved connectivity for mobile communications, microcellular and picocellular systems are being introduced. For these systems, there is a need to develop robust and efficient management procedures for the allocation of power and spectrum to maximize radio capacity. Topology-conserving mappings play an important role in the biological processing of sensory inputs. The same principles underlying Kohonen's self-organizing feature maps (SOFMs) are applied to the adaptive control of radio resources to minimize interference, hence, maximize capacity in direct-sequence (DS) CDMA networks. The approach based on SOFMs is applied to some published examples of both theoretical and empirical models of DS/CDMA microcellular networks in metropolitan areas. The results of the approach for these examples are informally compared to the performance of algorithms, based on Hopfield- Tank neural networks and on genetic algorithms, for the channel assignment problem.

Hierarchical Kohonenen net for anomaly detection in network security.

PubMed

Sarasamma, Suseela T; Zhu, Qiuming A; Huff, Julie

2005-04-01

A novel multilevel hierarchical Kohonen Net (K-Map) for an intrusion detection system is presented. Each level of the hierarchical map is modeled as a simple winner-take-all K-Map. One significant advantage of this multilevel hierarchical K-Map is its computational efficiency. Unlike other statistical anomaly detection methods such as nearest neighbor approach, K-means clustering or probabilistic analysis that employ distance computation in the feature space to identify the outliers, our approach does not involve costly point-to-point computation in organizing the data into clusters. Another advantage is the reduced network size. We use the classification capability of the K-Map on selected dimensions of data set in detecting anomalies. Randomly selected subsets that contain both attacks and normal records from the KDD Cup 1999 benchmark data are used to train the hierarchical net. We use a confidence measure to label the clusters. Then we use the test set from the same KDD Cup 1999 benchmark to test the hierarchical net. We show that a hierarchical K-Map in which each layer operates on a small subset of the feature space is superior to a single-layer K-Map operating on the whole feature space in detecting a variety of attacks in terms of detection rate as well as false positive rate.

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.

The use of interactive graphical maps for browsing medical/health Internet information resources

PubMed Central

Boulos, Maged N Kamel

2003-01-01

As online information portals accumulate metadata descriptions of Web resources, it becomes necessary to develop effective ways for visualising and navigating the resultant huge metadata repositories as well as the different semantic relationships and attributes of described Web resources. Graphical maps provide a good method to visualise, understand and navigate a world that is too large and complex to be seen directly like the Web. Several examples of maps designed as a navigational aid for Web resources are presented in this review with an emphasis on maps of medical and health-related resources. The latter include HealthCyberMap maps , which can be classified as conceptual information space maps, and the very abstract and geometric Visual Net maps of PubMed (for demos). Information resources can be also organised and navigated based on their geographic attributes. Some of the maps presented in this review use a Kohonen Self-Organising Map algorithm, and only HealthCyberMap uses a Geographic Information System to classify Web resource data and render the maps. Maps based on familiar metaphors taken from users' everyday life are much easier to understand. Associative and pictorial map icons that enable instant recognition and comprehension are preferred to geometric ones and are key to successful maps for browsing medical/health Internet information resources. PMID:12556244

Analysis of a municipal wastewater treatment plant using a neural network-based pattern analysis

USGS Publications Warehouse

Hong, Y.-S.T.; Rosen, Michael R.; Bhamidimarri, R.

2003-01-01

This paper addresses the problem of how to capture the complex relationships that exist between process variables and to diagnose the dynamic behaviour of a municipal wastewater treatment plant (WTP). Due to the complex biological reaction mechanisms, the highly time-varying, and multivariable aspects of the real WTP, the diagnosis of the WTP are still difficult in practice. The application of intelligent techniques, which can analyse the multi-dimensional process data using a sophisticated visualisation technique, can be useful for analysing and diagnosing the activated-sludge WTP. In this paper, the Kohonen Self-Organising Feature Maps (KSOFM) neural network is applied to analyse the multi-dimensional process data, and to diagnose the inter-relationship of the process variables in a real activated-sludge WTP. By using component planes, some detailed local relationships between the process variables, e.g., responses of the process variables under different operating conditions, as well as the global information is discovered. The operating condition and the inter-relationship among the process variables in the WTP have been diagnosed and extracted by the information obtained from the clustering analysis of the maps. It is concluded that the KSOFM technique provides an effective analysing and diagnosing tool to understand the system behaviour and to extract knowledge contained in multi-dimensional data of a large-scale WTP. ?? 2003 Elsevier Science Ltd. All rights reserved.

Self-organizing map analysis using multivariate data from theophylline tablets predicted by a thin-plate spline interpolation.

PubMed

Yasuda, Akihito; Onuki, Yoshinori; Obata, Yasuko; Yamamoto, Rie; Takayama, Kozo

2013-01-01

The "quality by design" concept in pharmaceutical formulation development requires the establishment of a science-based rationale and a design space. We integrated thin-plate spline (TPS) interpolation and Kohonen's self-organizing map (SOM) to visualize the latent structure underlying causal factors and pharmaceutical responses. As a model pharmaceutical product, theophylline tablets were prepared based on a standard formulation. The tensile strength, disintegration time, and stability of these variables were measured as response variables. These responses were predicted quantitatively based on nonlinear TPS. A large amount of data on these tablets was generated and classified into several clusters using an SOM. The experimental values of the responses were predicted with high accuracy, and the data generated for the tablets were classified into several distinct clusters. The SOM feature map allowed us to analyze the global and local correlations between causal factors and tablet characteristics. The results of this study suggest that increasing the proportion of microcrystalline cellulose (MCC) improved the tensile strength and the stability of tensile strength of these theophylline tablets. In addition, the proportion of MCC has an optimum value for disintegration time and stability of disintegration. Increasing the proportion of magnesium stearate extended disintegration time. Increasing the compression force improved tensile strength, but degraded the stability of disintegration. This technique provides a better understanding of the relationships between causal factors and pharmaceutical responses in theophylline tablet formulations.

Mapping the Indonesian territory, based on pollution, social demography and geographical data, using self organizing feature map

NASA Astrophysics Data System (ADS)

Hernawati, Kuswari; Insani, Nur; Bambang S. H., M.; Nur Hadi, W.; Sahid

2017-08-01

This research aims to mapping the 33 (thirty-three) provinces in Indonesia, based on the data on air, water and soil pollution, as well as social demography and geography data, into a clustered model. The method used in this study was unsupervised method that combines the basic concept of Kohonen or Self-Organizing Feature Maps (SOFM). The method is done by providing the design parameters for the model based on data related directly/ indirectly to pollution, which are the demographic and social data, pollution levels of air, water and soil, as well as the geographical situation of each province. The parameters used consists of 19 features/characteristics, including the human development index, the number of vehicles, the availability of the plant's water absorption and flood prevention, as well as geographic and demographic situation. The data used were secondary data from the Central Statistics Agency (BPS), Indonesia. The data are mapped into SOFM from a high-dimensional vector space into two-dimensional vector space according to the closeness of location in term of Euclidean distance. The resulting outputs are represented in clustered grouping. Thirty-three provinces are grouped into five clusters, where each cluster has different features/characteristics and level of pollution. The result can used to help the efforts on prevention and resolution of pollution problems on each cluster in an effective and efficient way.

COMPUTATIONAL ANALYSIS BASED ON ARTIFICIAL NEURAL NETWORKS FOR AIDING IN DIAGNOSING OSTEOARTHRITIS OF THE LUMBAR SPINE.

PubMed

Veronezi, Carlos Cassiano Denipotti; de Azevedo Simões, Priscyla Waleska Targino; Dos Santos, Robson Luiz; da Rocha, Edroaldo Lummertz; Meláo, Suelen; de Mattos, Merisandra Côrtes; Cechinel, Cristian

2011-01-01

To ascertain the advantages of applying artificial neural networks to recognize patterns on lumbar spine radiographies in order to aid in the process of diagnosing primary osteoarthritis. This was a cross-sectional descriptive analytical study with a quantitative approach and an emphasis on diagnosis. The training set was composed of images collected between January and July 2009 from patients who had undergone lateral-view digital radiographies of the lumbar spine, which were provided by a radiology clinic located in the municipality of Criciúma (SC). Out of the total of 260 images gathered, those with distortions, those presenting pathological conditions that altered the architecture of the lumbar spine and those with patterns that were difficult to characterize were discarded, resulting in 206 images. The image data base (n = 206) was then subdivided, resulting in 68 radiographies for the training stage, 68 images for tests and 70 for validation. A hybrid neural network based on Kohonen self-organizing maps and on Multilayer Perceptron networks was used. After 90 cycles, the validation was carried out on the best results, achieving accuracy of 62.85%, sensitivity of 65.71% and specificity of 60%. Even though the effectiveness shown was moderate, this study is still innovative. The values show that the technique used has a promising future, pointing towards further studies on image and cycle processing methodology with a larger quantity of radiographies.

A Neural-Network Clustering-Based Algorithm for Privacy Preserving Data Mining

NASA Astrophysics Data System (ADS)

Tsiafoulis, S.; Zorkadis, V. C.; Karras, D. A.

The increasing use of fast and efficient data mining algorithms in huge collections of personal data, facilitated through the exponential growth of technology, in particular in the field of electronic data storage media and processing power, has raised serious ethical, philosophical and legal issues related to privacy protection. To cope with these concerns, several privacy preserving methodologies have been proposed, classified in two categories, methodologies that aim at protecting the sensitive data and those that aim at protecting the mining results. In our work, we focus on sensitive data protection and compare existing techniques according to their anonymity degree achieved, the information loss suffered and their performance characteristics. The ℓ-diversity principle is combined with k-anonymity concepts, so that background information can not be exploited to successfully attack the privacy of data subjects data refer to. Based on Kohonen Self Organizing Feature Maps (SOMs), we firstly organize data sets in subspaces according to their information theoretical distance to each other, then create the most relevant classes paying special attention to rare sensitive attribute values, and finally generalize attribute values to the minimum extend required so that both the data disclosure probability and the information loss are possibly kept negligible. Furthermore, we propose information theoretical measures for assessing the anonymity degree achieved and empirical tests to demonstrate it.

Organochlorine pesticides (OCPs) and polychlorinated biphenyls (PCBs) in Cyprinidae fish: Towards hints of their arrangements using advanced classification methods.

PubMed

Romanić, Snježana Herceg; Vuković, Gordana; Klinčić, Darija; Sarić, Marijana Matek; Župan, Ivan; Antanasijević, Davor; Popović, Aleksandar

2018-05-18

To tackle the ever-present global concern regarding human exposure to persistent organic pollutants (POPs) via food products, this study strived to indicate associations between organochlorine pesticides (OCPs) and polychlorinated biphenyls (PCBs) in lake-fish tissue depending on the species and sampling season. Apart from the monitoring initiatives recommended in the Global Monitoring Plan for POPs, the study discussed 7 OCPs and 18 PCB congeners determined in three Cyprinidae species (rudd, carp, and Prussian carp) from Vransko Lake (Croatia), which are widely domesticated and reared as food fish across Europe and Asia. We exploit advanced classification algorithms, the Kohonen self-organizing maps (SOM) and Decision Trees (DT), to search for POP patterns typical for the investigated species. As indicated by SOM, some of the dioxin-like and non-dioxin-like PCBs (PCB-28, PCB-74, PCB-52, PCB-101, PCB-105, PCB-114, PCB-118, PCB-156 and PCB-157), α-HCH and β-HCH caused dissimilarities among fish species, but regardless of their weight and length. To support these suggestions, DT analysis sequenced the fish species and seasons based on the concentration of heavier congeners. The presented assumptions indicated that the supplemental application of SOM and DT offers advantageous features over the usually rough interpretation of POPs pattern and over the single use of the methods. Copyright © 2018 Elsevier Inc. All rights reserved.

COMPUTATIONAL ANALYSIS BASED ON ARTIFICIAL NEURAL NETWORKS FOR AIDING IN DIAGNOSING OSTEOARTHRITIS OF THE LUMBAR SPINE

PubMed Central

Veronezi, Carlos Cassiano Denipotti; de Azevedo Simões, Priscyla Waleska Targino; dos Santos, Robson Luiz; da Rocha, Edroaldo Lummertz; Meláo, Suelen; de Mattos, Merisandra Côrtes; Cechinel, Cristian

2015-01-01

Objective: To ascertain the advantages of applying artificial neural networks to recognize patterns on lumbar spine radiographies in order to aid in the process of diagnosing primary osteoarthritis. Methods: This was a cross-sectional descriptive analytical study with a quantitative approach and an emphasis on diagnosis. The training set was composed of images collected between January and July 2009 from patients who had undergone lateral-view digital radiographies of the lumbar spine, which were provided by a radiology clinic located in the municipality of Criciúma (SC). Out of the total of 260 images gathered, those with distortions, those presenting pathological conditions that altered the architecture of the lumbar spine and those with patterns that were difficult to characterize were discarded, resulting in 206 images. The image data base (n = 206) was then subdivided, resulting in 68 radiographies for the training stage, 68 images for tests and 70 for validation. A hybrid neural network based on Kohonen self-organizing maps and on Multilayer Perceptron networks was used. Results: After 90 cycles, the validation was carried out on the best results, achieving accuracy of 62.85%, sensitivity of 65.71% and specificity of 60%. Conclusions: Even though the effectiveness shown was moderate, this study is still innovative. The values show that the technique used has a promising future, pointing towards further studies on image and cycle processing methodology with a larger quantity of radiographies. PMID:27027010

Neuronal networks and self-organizing maps: new computer techniques in the acoustic evaluation of the infant cry.

PubMed

Schönweiler, R; Kaese, S; Möller, S; Rinscheid, A; Ptok, M

1996-12-05

Neuronal networks are computer-based techniques for the evaluation and control of complex information systems and processes. So far, they have been used in engineering, telecommunications, artificial speech and speech recognition. A new approach in neuronal network is the self-organizing map (Kohonen map). In the phase of 'learning', the map adapts to the patterns of the primary signals. If, the phase of 'using the map', the input signal hits the field of the primary signals, it resembles them and is called a 'winner'. In our study, we recorded the cries of newborns and young infants using digital audio tape (DAT) and a high quality microphone. The cries were elicited by tactile stimuli wearing headphones. In 27 cases, delayed auditory feedback was presented to the children using a headphone and an additional three-head tape-recorder. Spectrographic characteristics of the cries were classified by 20-step bark spectra and then applied to the neuronal networks. It was possible to recognize similarities of different cries of the same children as well as interindividual differences, which are also audible to experienced listeners. Differences were obvious in profound hearing loss. We know much about the cries of both healthy and sick infants, but a reliable investigation regimen, which can be used for clinical routine purposes, has yet not been developed. If, in the future, it becomes possible to classify spectrographic characteristics automatically, even if they are not audible, neuronal networks may be helpful in the early diagnosis of infant diseases.

Neural network modelling and dynamical system theory: are they relevant to study the governing dynamics of association football players?

PubMed

Dutt-Mazumder, Aviroop; Button, Chris; Robins, Anthony; Bartlett, Roger

2011-12-01

Recent studies have explored the organization of player movements in team sports using a range of statistical tools. However, the factors that best explain the performance of association football teams remain elusive. Arguably, this is due to the high-dimensional behavioural outputs that illustrate the complex, evolving configurations typical of team games. According to dynamical system analysts, movement patterns in team sports exhibit nonlinear self-organizing features. Nonlinear processing tools (i.e. Artificial Neural Networks; ANNs) are becoming increasingly popular to investigate the coordination of participants in sports competitions. ANNs are well suited to describing high-dimensional data sets with nonlinear attributes, however, limited information concerning the processes required to apply ANNs exists. This review investigates the relative value of various ANN learning approaches used in sports performance analysis of team sports focusing on potential applications for association football. Sixty-two research sources were summarized and reviewed from electronic literature search engines such as SPORTDiscus, Google Scholar, IEEE Xplore, Scirus, ScienceDirect and Elsevier. Typical ANN learning algorithms can be adapted to perform pattern recognition and pattern classification. Particularly, dimensionality reduction by a Kohonen feature map (KFM) can compress chaotic high-dimensional datasets into low-dimensional relevant information. Such information would be useful for developing effective training drills that should enhance self-organizing coordination among players. We conclude that ANN-based qualitative analysis is a promising approach to understand the dynamical attributes of association football players.

Improving Scene Classifications with Combined Active/Passive Measurements

NASA Astrophysics Data System (ADS)

Hu, Y.; Rodier, S.; Vaughan, M.; McGill, M.

The uncertainties in cloud and aerosol physical properties derived from passive instruments such as MODIS are not insignificant And the uncertainty increases when the optical depths decrease Lidar observations do much better for the thin clouds and aerosols Unfortunately space-based lidar measurements such as the one onboard CALIPSO satellites are limited to nadir view only and thus have limited spatial coverage To produce climatologically meaningful thin cloud and aerosol data products it is necessary to combine the spatial coverage of MODIS with the highly sensitive CALIPSO lidar measurements Can we improving the quality of cloud and aerosol remote sensing data products by extending the knowledge about thin clouds and aerosols learned from CALIPSO-type of lidar measurements to a larger portion of the off-nadir MODIS-like multi-spectral pixels To answer the question we studied the collocated Cloud Physics Lidar CPL with Modis-Airborne-Simulation MAS observations and established an effective data fusion technique that will be applied in the combined CALIPSO MODIS cloud aerosol product algorithms This technique performs k-mean and Kohonen self-organized map cluster analysis on the entire swath of MAS data as well as on the combined CPL MAS data at the nadir track Interestingly the clusters generated from the two approaches are almost identical It indicates that the MAS multi-spectral data may have already captured most of the cloud and aerosol scene types such as cloud ice water phase multi-layer information aerosols

Latent structure modeling underlying theophylline tablet formulations using a Bayesian network based on a self-organizing map clustering.

PubMed

Yasuda, Akihito; Onuki, Yoshinori; Obata, Yasuko; Takayama, Kozo

2015-01-01

The "quality by design" concept in pharmaceutical formulation development requires the establishment of a science-based rationale and design space. In this article, we integrate thin-plate spline (TPS) interpolation, Kohonen's self-organizing map (SOM) and a Bayesian network (BN) to visualize the latent structure underlying causal factors and pharmaceutical responses. As a model pharmaceutical product, theophylline tablets were prepared using a standard formulation. We measured the tensile strength and disintegration time as response variables and the compressibility, cohesion and dispersibility of the pretableting blend as latent variables. We predicted these variables quantitatively using nonlinear TPS, generated a large amount of data on pretableting blends and tablets and clustered these data into several clusters using a SOM. Our results show that we are able to predict the experimental values of the latent and response variables with a high degree of accuracy and are able to classify the tablet data into several distinct clusters. In addition, to visualize the latent structure between the causal and latent factors and the response variables, we applied a BN method to the SOM clustering results. We found that despite having inserted latent variables between the causal factors and response variables, their relation is equivalent to the results for the SOM clustering, and thus we are able to explain the underlying latent structure. Consequently, this technique provides a better understanding of the relationships between causal factors and pharmaceutical responses in theophylline tablet formulation.

Multiway real-time PCR gene expression profiling in yeast Saccharomyces cerevisiae reveals altered transcriptional response of ADH-genes to glucose stimuli.

PubMed

Ståhlberg, Anders; Elbing, Karin; Andrade-Garda, José Manuel; Sjögreen, Björn; Forootan, Amin; Kubista, Mikael

2008-04-16

The large sensitivity, high reproducibility and essentially unlimited dynamic range of real-time PCR to measure gene expression in complex samples provides the opportunity for powerful multivariate and multiway studies of biological phenomena. In multiway studies samples are characterized by their expression profiles to monitor changes over time, effect of treatment, drug dosage etc. Here we perform a multiway study of the temporal response of four yeast Saccharomyces cerevisiae strains with different glucose uptake rates upon altered metabolic conditions. We measured the expression of 18 genes as function of time after addition of glucose to four strains of yeast grown in ethanol. The data are analyzed by matrix-augmented PCA, which is a generalization of PCA for 3-way data, and the results are confirmed by hierarchical clustering and clustering by Kohonen self-organizing map. Our approach identifies gene groups that respond similarly to the change of nutrient, and genes that behave differently in mutant strains. Of particular interest is our finding that ADH4 and ADH6 show a behavior typical of glucose-induced genes, while ADH3 and ADH5 are repressed after glucose addition. Multiway real-time PCR gene expression profiling is a powerful technique which can be utilized to characterize functions of new genes by, for example, comparing their temporal response after perturbation in different genetic variants of the studied subject. The technique also identifies genes that show perturbed expression in specific strains.

Multiway real-time PCR gene expression profiling in yeast Saccharomyces cerevisiae reveals altered transcriptional response of ADH-genes to glucose stimuli

PubMed Central

Ståhlberg, Anders; Elbing, Karin; Andrade-Garda, José Manuel; Sjögreen, Björn; Forootan, Amin; Kubista, Mikael

2008-01-01

Background The large sensitivity, high reproducibility and essentially unlimited dynamic range of real-time PCR to measure gene expression in complex samples provides the opportunity for powerful multivariate and multiway studies of biological phenomena. In multiway studies samples are characterized by their expression profiles to monitor changes over time, effect of treatment, drug dosage etc. Here we perform a multiway study of the temporal response of four yeast Saccharomyces cerevisiae strains with different glucose uptake rates upon altered metabolic conditions. Results We measured the expression of 18 genes as function of time after addition of glucose to four strains of yeast grown in ethanol. The data are analyzed by matrix-augmented PCA, which is a generalization of PCA for 3-way data, and the results are confirmed by hierarchical clustering and clustering by Kohonen self-organizing map. Our approach identifies gene groups that respond similarly to the change of nutrient, and genes that behave differently in mutant strains. Of particular interest is our finding that ADH4 and ADH6 show a behavior typical of glucose-induced genes, while ADH3 and ADH5 are repressed after glucose addition. Conclusion Multiway real-time PCR gene expression profiling is a powerful technique which can be utilized to characterize functions of new genes by, for example, comparing their temporal response after perturbation in different genetic variants of the studied subject. The technique also identifies genes that show perturbed expression in specific strains. PMID:18412983

Microcrack Quantification in Composite Materials by a Neural Network Analysis of Ultrasound Spectral Data

NASA Technical Reports Server (NTRS)

Walker, James L.; Russell, Samuel S.; Suits, Michael W.

2003-01-01

Intra-ply microcracking in unlined composite pressure vessels can be very troublesome to detect and when linked through the thickness can provide leak paths that may hinder mission success. The leaks may lead to loss of pressure/propellant, increased risk of explosion and possible cryo-pumping into air pockets within the laminate. Ultrasonic techniques have been shown capable of detecting the presence of microcracking and in this work they are used to quantify the level of microcracking. Resonance ultrasound methods are utilized with artificial neural networks to build a microcrack prediction/measurement tool. Two networks are presented, one unsupervised to provide a qualitative measure of microcracking and one supervised which provides a quantitative assessment of the level of microcracking. The resonant ultrasound spectroscopic method is made sensitive to microcracking by tuning the input spectrum to the higher frequency (shorter wavelength) components allowing more significant interaction with the defects. This interaction causes the spectral characteristics to shift toward lower amplitudes at the higher frequencies. As the density of the defects increases more interactions occur and more drastic amplitude changes are observed. Preliminary experiments to quantify the level of microcracking induced in graphite/epoxy composite samples through a combination of tensile loading and cryogenic temperatures are presented. Both unsupervised (Kohonen) and supervised (radial basis function) artificial neural networks are presented to determine the measurable effect on the resonance spectrum of the ultrasonic data taken from the samples.

QSAR studies of the bioactivity of hepatitis C virus (HCV) NS3/4A protease inhibitors by multiple linear regression (MLR) and support vector machine (SVM).

PubMed

Qin, Zijian; Wang, Maolin; Yan, Aixia

2017-07-01

In this study, quantitative structure-activity relationship (QSAR) models using various descriptor sets and training/test set selection methods were explored to predict the bioactivity of hepatitis C virus (HCV) NS3/4A protease inhibitors by using a multiple linear regression (MLR) and a support vector machine (SVM) method. 512 HCV NS3/4A protease inhibitors and their IC 50 values which were determined by the same FRET assay were collected from the reported literature to build a dataset. All the inhibitors were represented with selected nine global and 12 2D property-weighted autocorrelation descriptors calculated from the program CORINA Symphony. The dataset was divided into a training set and a test set by a random and a Kohonen's self-organizing map (SOM) method. The correlation coefficients (r 2 ) of training sets and test sets were 0.75 and 0.72 for the best MLR model, 0.87 and 0.85 for the best SVM model, respectively. In addition, a series of sub-dataset models were also developed. The performances of all the best sub-dataset models were better than those of the whole dataset models. We believe that the combination of the best sub- and whole dataset SVM models can be used as reliable lead designing tools for new NS3/4A protease inhibitors scaffolds in a drug discovery pipeline. Copyright © 2017 Elsevier Ltd. All rights reserved.

Distorted Character Recognition Via An Associative Neural Network

NASA Astrophysics Data System (ADS)

Messner, Richard A.; Szu, Harold H.

1987-03-01

The purpose of this paper is two-fold. First, it is intended to provide some preliminary results of a character recognition scheme which has foundations in on-going neural network architecture modeling, and secondly, to apply some of the neural network results in a real application area where thirty years of effort has had little effect on providing the machine an ability to recognize distorted objects within the same object class. It is the author's belief that the time is ripe to start applying in ernest the results of over twenty years of effort in neural modeling to some of the more difficult problems which seem so hard to solve by conventional means. The character recognition scheme proposed utilizes a preprocessing stage which performs a 2-dimensional Walsh transform of an input cartesian image field, then sequency filters this spectrum into three feature bands. Various features are then extracted and organized into three sets of feature vectors. These vector patterns that are stored and recalled associatively. Two possible associative neural memory models are proposed for further investigation. The first being an outer-product linear matrix associative memory with a threshold function controlling the strength of the output pattern (similar to Kohonen's crosscorrelation approach [1]). The second approach is based upon a modified version of Grossberg's neural architecture [2] which provides better self-organizing properties due to its adaptive nature. Preliminary results of the sequency filtering and feature extraction preprocessing stage and discussion about the use of the proposed neural architectures is included.

Quantitative MRI assessments of white matter in children treated for acute lymphoblastic leukemia

NASA Astrophysics Data System (ADS)

Reddick, Wilburn E.; Glass, John O.; Helton, Kathleen J.; Li, Chin-Shang; Pui, Ching-Hon

2005-04-01

The purpose of this study was to use objective quantitative MR imaging methods to prospectively assess changes in the physiological structure of white matter during the temporal evolution of leukoencephalopathy (LE) in children treated for acute lymphoblastic leukemia. The longitudinal incidence, extent (proportion of white matter affect), and intensity (elevation of T1 and T2 relaxation rates) of LE was evaluated for 44 children. A combined imaging set consisting of T1, T2, PD, and FLAIR MR images and white matter, gray matter and CSF a priori maps from a spatially normalized atlas were analyzed with a neural network segmentation based on a Kohonen Self-Organizing Map (SOM). Quantitative T1 and T2 relaxation maps were generated using a nonlinear parametric optimization procedure to fit the corresponding multi-exponential models. A Cox proportional regression was performed to estimate the effect of intravenous methotrexate (IV-MTX) exposure on the development of LE followed by a generalized linear model to predict the probability of LE in new patients. Additional T-tests of independent samples were performed to assess differences in quantitative measures of extent and intensity at four different points in therapy. Higher doses and more courses of IV-MTX placed patients at a higher risk of developing LE and were associated with more intense changes affecting more of the white matter volume; many of the changes resolved after completion of therapy. The impact of these changes on neurocognitive functioning and quality of life in survivors remains to be determined.

Computer-aided diagnosis of leukoencephalopathy in children treated for acute lymphoblastic leukemia

NASA Astrophysics Data System (ADS)

Glass, John O.; Li, Chin-Shang; Helton, Kathleen J.; Reddick, Wilburn E.

2005-04-01

The purpose of this study was to use objective quantitative MR imaging methods to develop a computer-aided diagnosis tool to differentiate white matter (WM) hyperintensities as either leukoencephalopathy (LE) or normal maturational processes in children treated for acute lymphoblastic leukemia with intravenous high dose methotrexate. A combined imaging set consisting of T1, T2, PD, and FLAIR MR images and WM, gray matter, and cerebrospinal fluid a priori maps from a spatially normalized atlas were analyzed with a neural network segmentation based on a Kohonen Self-Organizing Map. Segmented regions were manually classified to identify the most hyperintense WM region and the normal appearing genu region. Signal intensity differences normalized to the genu within each examination were generated for two time points in 203 children. An unsupervised hierarchical clustering algorithm with the agglomeration method of McQuitty was used to divide data from the first examination into normal appearing or LE groups. A C-support vector machine (C-SVM) was then trained on the first examination data and used to classify the data from the second examination. The overall accuracy of the computer-aided detection tool was 83.5% (299/358) with sensitivity to normal WM of 86.9% (199/229) and specificity to LE of 77.5% (100/129) when compared to the readings of two expert observers. These results suggest that subtle therapy-induced leukoencephalopathy can be objectively and reproducibly detected in children treated for cancer using this computer-aided detection approach based on relative differences in quantitative signal intensity measures normalized within each examination.

Dioxin in the river Elbe.

PubMed

Götz, Rainer; Bergemann, Michael; Stachel, Burkhard; Umlauf, Gunther

2017-09-01

This paper provides a macro-analysis of the dioxin contamination in the river Elbe from the 1940s to the present. Based on different data sets, the historic dioxin concentration in the Elbe has been reconstructed. For the section between the tributary Mulde and Hamburg, during the 1940s, we find a concentration of about 1500 pg WHO-TEQ g -1 . We argue that this dioxin contamination was caused mainly by emissions from a magnesium plant in Bitterfeld-Wolfen, whose effluents were discharged into a tributary of the river Mulde which flows into the Elbe. Dioxin pattern recognition with neural networks (Kohonen) confirms this. A model simulation shows that a hypothetical dioxin concentration of 10,000 pg WHO-TEQ g -1 in the tributary Mulde could have caused the reconstructed dioxin concentration of 1500 pg WHO-TEQ g -1 in the Elbe. The recent dioxin concentration (about 25-100 pg WHO-TEQ g -1 ) in the river Elbe, downstream the tributary Mulde, originates, according to our hypothesis, from emissions of the banks and the highly contaminated flood plains (transport of the particle bound dioxin). As other possible dioxin sources, the following could be excluded: the dioxin concentration in the Mulde, groynes, small ports, sport boat harbours, and extreme floods. Our hypothesis is supported by the results of pattern recognition techniques and a model simulation. According to these findings, we argue that remediation efforts to reduce the dioxin concentration in the river Elbe are unlikely to be successful. Copyright © 2017 Elsevier Ltd. All rights reserved.

Statistical Downscaling of Gusts During Extreme European Winter Storms Using Radial-Basis-Function Networks

NASA Astrophysics Data System (ADS)

Voigt, M.; Lorenz, P.; Kruschke, T.; Osinski, R.; Ulbrich, U.; Leckebusch, G. C.

2012-04-01

Winterstorms and related gusts can cause extensive socio-economic damages. Knowledge about the occurrence and the small scale structure of such events may help to make regional estimations of storm losses. For a high spatial and temporal representation, the use of dynamical downscaling methods (RCM) is a cost-intensive and time-consuming option and therefore only applicable for a limited number of events. The current study explores a methodology to provide a statistical downscaling, which offers small scale structured gust fields from an extended large scale structured eventset. Radial-basis-function (RBF) networks in combination with bidirectional Kohonen (BDK) maps are used to generate the gustfields on a spatial resolution of 7 km from the 6-hourly mean sea level pressure field from ECMWF reanalysis data. BDK maps are a kind of neural network which handles supervised classification problems. In this study they are used to provide prototypes for the RBF network and give a first order approximation for the output data. A further interpolation is done by the RBF network. For the training process the 50 most extreme storm events over the North Atlantic area from 1957 to 2011 are used, which have been selected from ECMWF reanalysis datasets ERA40 and ERA-Interim by an objective wind based tracking algorithm. These events were downscaled dynamically by application of the DWD model chain GME → COSMO-EU. Different model parameters and their influence on the quality of the generated high-resolution gustfields are studied. It is shown that the statistical RBF network approach delivers reasonable results in modeling the regional gust fields for untrained events.

Adaptive training of cortical feature maps for a robot sensorimotor controller.

PubMed

Adams, Samantha V; Wennekers, Thomas; Denham, Sue; Culverhouse, Phil F

2013-08-01

This work investigates self-organising cortical feature maps (SOFMs) based upon the Kohonen Self-Organising Map (SOM) but implemented with spiking neural networks. In future work, the feature maps are intended as the basis for a sensorimotor controller for an autonomous humanoid robot. Traditional SOM methods require some modifications to be useful for autonomous robotic applications. Ideally the map training process should be self-regulating and not require predefined training files or the usual SOM parameter reduction schedules. It would also be desirable if the organised map had some flexibility to accommodate new information whilst preserving previous learnt patterns. Here methods are described which have been used to develop a cortical motor map training system which goes some way towards addressing these issues. The work is presented under the general term 'Adaptive Plasticity' and the main contribution is the development of a 'plasticity resource' (PR) which is modelled as a global parameter which expresses the rate of map development and is related directly to learning on the afferent (input) connections. The PR is used to control map training in place of a traditional learning rate parameter. In conjunction with the PR, random generation of inputs from a set of exemplar patterns is used rather than predefined datasets and enables maps to be trained without deciding in advance how much data is required. An added benefit of the PR is that, unlike a traditional learning rate, it can increase as well as decrease in response to the demands of the input and so allows the map to accommodate new information when the inputs are changed during training. Copyright © 2013 Elsevier Ltd. All rights reserved.

Motion planning with complete knowledge using a colored SOM.

PubMed

Vleugels, J; Kok, J N; Overmars, M

1997-01-01

The motion planning problem requires that a collision-free path be determined for a robot moving amidst a fixed set of obstacles. Most neural network approaches to this problem are for the situation in which only local knowledge about the configuration space is available. The main goal of the paper is to show that neural networks are also suitable tools in situations with complete knowledge of the configuration space. In this paper we present an approach that combines a neural network and deterministic techniques. We define a colored version of Kohonen's self-organizing map that consists of two different classes of nodes. The network is presented with random configurations of the robot and, from this information, it constructs a road map of possible motions in the work space. The map is a growing network, and different nodes are used to approximate boundaries of obstacles and the Voronoi diagram of the obstacles, respectively. In a second phase, the positions of the two kinds of nodes are combined to obtain the road map. In this way a number of typical problems with small obstacles and passages are avoided, and the required number of nodes for a given accuracy is within reasonable limits. This road map is searched to find a motion connecting the given source and goal configurations of the robot. The algorithm is simple and general; the only specific computation that is required is a check for intersection of two polygons. We implemented the algorithm for planar robots allowing both translation and rotation and experiments show that compared to conventional techniques it performs well, even for difficult motion planning scenes.

Automatic lithofacies segmentation from well-logs data. A comparative study between the Self-Organizing Map (SOM) and Walsh transform

NASA Astrophysics Data System (ADS)

Aliouane, Leila; Ouadfeul, Sid-Ali; Rabhi, Abdessalem; Rouina, Fouzi; Benaissa, Zahia; Boudella, Amar

2013-04-01

The main goal of this work is to realize a comparison between two lithofacies segmentation techniques of reservoir interval. The first one is based on the Kohonen's Self-Organizing Map neural network machine. The second technique is based on the Walsh transform decomposition. Application to real well-logs data of two boreholes located in the Algerian Sahara shows that the Self-organizing map is able to provide more lithological details that the obtained lithofacies model given by the Walsh decomposition. Keywords: Comparison, Lithofacies, SOM, Walsh References: 1)Aliouane, L., Ouadfeul, S., Boudella, A., 2011, Fractal analysis based on the continuous wavelet transform and lithofacies classification from well-logs data using the self-organizing map neural network, Arabian Journal of geosciences, doi: 10.1007/s12517-011-0459-4 2) Aliouane, L., Ouadfeul, S., Djarfour, N., Boudella, A., 2012, Petrophysical Parameters Estimation from Well-Logs Data Using Multilayer Perceptron and Radial Basis Function Neural Networks, Lecture Notes in Computer Science Volume 7667, 2012, pp 730-736, doi : 10.1007/978-3-642-34500-5_86 3)Ouadfeul, S. and Aliouane., L., 2011, Multifractal analysis revisited by the continuous wavelet transform applied in lithofacies segmentation from well-logs data, International journal of applied physics and mathematics, Vol01 N01. 4) Ouadfeul, S., Aliouane, L., 2012, Lithofacies Classification Using the Multilayer Perceptron and the Self-organizing Neural Networks, Lecture Notes in Computer Science Volume 7667, 2012, pp 737-744, doi : 10.1007/978-3-642-34500-5_87 5) Weisstein, Eric W. "Fast Walsh Transform." From MathWorld--A Wolfram Web Resource. http://mathworld.wolfram.com/FastWalshTransform.html

Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria

NASA Astrophysics Data System (ADS)

Prochazka, D.; Mazura, M.; Samek, O.; Rebrošová, K.; Pořízka, P.; Klus, J.; Prochazková, P.; Novotný, J.; Novotný, K.; Kaiser, J.

2018-01-01

In this work, we investigate the impact of data provided by complementary laser-based spectroscopic methods on multivariate classification accuracy. Discrimination and classification of five Staphylococcus bacterial strains and one strain of Escherichia coli is presented. The technique that we used for measurements is a combination of Raman spectroscopy and Laser-Induced Breakdown Spectroscopy (LIBS). Obtained spectroscopic data were then processed using Multivariate Data Analysis algorithms. Principal Components Analysis (PCA) was selected as the most suitable technique for visualization of bacterial strains data. To classify the bacterial strains, we used Neural Networks, namely a supervised version of Kohonen's self-organizing maps (SOM). We were processing results in three different ways - separately from LIBS measurements, from Raman measurements, and we also merged data from both mentioned methods. The three types of results were then compared. By applying the PCA to Raman spectroscopy data, we observed that two bacterial strains were fully distinguished from the rest of the data set. In the case of LIBS data, three bacterial strains were fully discriminated. Using a combination of data from both methods, we achieved the complete discrimination of all bacterial strains. All the data were classified with a high success rate using SOM algorithm. The most accurate classification was obtained using a combination of data from both techniques. The classification accuracy varied, depending on specific samples and techniques. As for LIBS, the classification accuracy ranged from 45% to 100%, as for Raman Spectroscopy from 50% to 100% and in case of merged data, all samples were classified correctly. Based on the results of the experiments presented in this work, we can assume that the combination of Raman spectroscopy and LIBS significantly enhances discrimination and classification accuracy of bacterial species and strains. The reason is the complementarity in

Water toxicity assessment and spatial pollution patterns identification in a Mediterranean River Basin District. Tools for water management and risk analysis.

PubMed

Carafa, Roberta; Faggiano, Leslie; Real, Montserrat; Munné, Antoni; Ginebreda, Antoni; Guasch, Helena; Flo, Monica; Tirapu, Luís; von der Ohe, Peter Carsten

2011-09-15

In compliance with the requirements of the EU Water Framework Directive, monitoring of the ecological and chemical status of Catalan river basins (NE Spain) is carried out by the Catalan Water Agency. The large amount of data collected and the complex relationships among the environmental variables monitored often mislead data interpretation in terms of toxic impact, especially considering that even pollutants at very low concentrations might contribute to the total toxicity. The total dataset of chemical monitoring carried out between 2007 and 2008 (232 sampling stations and 60 pollutants) has been analyzed using sequential advanced modeling techniques. Data on concentrations of contaminants in water were pre-treated in order to calculate the bioavailable fraction, depending on substance properties and local environmental conditions. The resulting values were used to predict the potential impact of toxic substances in complex mixtures on aquatic biota and to identify hot spots. Exposure assessment with Species Sensitivity Distribution (SSD) and mixture toxicity rules were used to compute the multi-substances Potentially Affected Fraction (msPAF). The combined toxicity of the pollutants analyzed in the Catalan surface waters might potentially impact more than 50% of the species in 10% of the sites. In order to understand and visualize the spatial distribution of the toxic risk, Self Organising Map (SOM), based on the Kohonen's Artificial Neural Network (ANN) algorithm, was applied on the output data of these models. Principal Component Analysis (PCA) was performed on top of Neural Network results in order to identify main influential variables which account for the pollution trends. Finally, predicted toxic impacts on biota have been linked and correlated to field data on biological quality indexes using macroinvertebrate and diatom communities (IBMWP and IPS). The methodology presented could represent a suitable tool for water managers in environmental risk

Time-resolved metabolomics reveals metabolic modulation in rice foliage

PubMed Central

Sato, Shigeru; Arita, Masanori; Soga, Tomoyoshi; Nishioka, Takaaki; Tomita, Masaru

2008-01-01

Background To elucidate the interaction of dynamics among modules that constitute biological systems, comprehensive datasets obtained from "omics" technologies have been used. In recent plant metabolomics approaches, the reconstruction of metabolic correlation networks has been attempted using statistical techniques. However, the results were unsatisfactory and effective data-mining techniques that apply appropriate comprehensive datasets are needed. Results Using capillary electrophoresis mass spectrometry (CE-MS) and capillary electrophoresis diode-array detection (CE-DAD), we analyzed the dynamic changes in the level of 56 basic metabolites in plant foliage (Oryza sativa L. ssp. japonica) at hourly intervals over a 24-hr period. Unsupervised clustering of comprehensive metabolic profiles using Kohonen's self-organizing map (SOM) allowed classification of the biochemical pathways activated by the light and dark cycle. The carbon and nitrogen (C/N) metabolism in both periods was also visualized as a phenotypic linkage map that connects network modules on the basis of traditional metabolic pathways rather than pairwise correlations among metabolites. The regulatory networks of C/N assimilation/dissimilation at each time point were consistent with previous works on plant metabolism. In response to environmental stress, glutathione and spermidine fluctuated synchronously with their regulatory targets. Adenine nucleosides and nicotinamide coenzymes were regulated by phosphorylation and dephosphorylation. We also demonstrated that SOM analysis was applicable to the estimation of unidentifiable metabolites in metabolome analysis. Hierarchical clustering of a correlation coefficient matrix could help identify the bottleneck enzymes that regulate metabolic networks. Conclusion Our results showed that our SOM analysis with appropriate metabolic time-courses effectively revealed the synchronous dynamics among metabolic modules and elucidated the underlying biochemical

Automated Classification of Thermal Infrared Spectra Using Self-organizing Maps

NASA Technical Reports Server (NTRS)

Roush, Ted L.; Hogan, Robert

2006-01-01

Existing and planned space missions to a variety of planetary and satellite surfaces produce an ever increasing volume of spectral data. Understanding the scientific informational content in this large data volume is a daunting task. Fortunately various statistical approaches are available to assess such data sets. Here we discuss an automated classification scheme based on Kohonen Self-organizing maps (SOM) we have developed. The SUM process produces an output layer were spectra having similar properties lie in close proximity to each other. One major effort is partitioning this output layer into appropriate regions. This is prefonned by defining dosed regions based upon the strength of the boundaries between adjacent cells in the SOM output layer. We use the Davies-Bouldin index as a measure of the inter-class similarities and intra-class dissimilarities that determines the optimum partition of the output layer, and hence number of SOM clusters. This allows us to identify the natural number of clusters formed from the spectral data. Mineral spectral libraries prepared at Arizona State University (ASU) and John Hopkins University (JHU) are used to test and evaluate the classification scheme. We label the library sample spectra in a hierarchical scheme with class, subclass, and mineral group names. We use a portion of the spectra to train the SOM, i.e. produce the output layer, while the remaining spectra are used to test the SOM. The test spectra are presented to the SOM output layer and assigned membership to the appropriate cluster. We then evaluate these assignments to assess the scientific meaning and accuracy of the derived SOM classes as they relate to the labels. We demonstrate that unsupervised classification by SOMs can be a useful component in autonomous systems designed to identify mineral species from reflectance and emissivity spectra in the therrnal IR.

Communications and control for electric power systems

NASA Technical Reports Server (NTRS)

Kirkham, H.; Goettsche, A.; Niebur, D.; Friend, H.; Johnston, A.

1991-01-01

The first section of the report describes the AbNET system, a hardware and software communications system designed for distribution automation (it can also find application in substation monitoring and control). The topology of the power system fixes the topology of the communications network, which can therefore be expected to include a larger number of branch points, tap points, and interconnections. These features make this communications network unlike any other. The network operating software has to solve the problem of communicating to all the nodes of a very complex network in as reliable a way as possible even if the network is damaged, and it has to do so with minimum transmission delays and at minimum cost. The design of the operating protocols is described within the framework of the seven-layer Open System Interconnection hierarchy of the International Standards Organization. Section 2 of the report describes the development and testing of a high voltage sensor based on an electro-optic polymer. The theory of operation is reviewed. Bulk fabrication of the polymer is discussed, as well as results of testing of the electro-optic coefficient of the material. Fabrication of a complete prototype sensor suitable for use in the range 1-20 kV is described. The electro-optic polymer is shown to be an important material for fiber optic sensing applications. Appendix A is theoretical support for this work. The third section of the report presents the application of an artificial neural network, Kohonen's self-organizing feature map, for the classification of power system states. This classifier maps vectors of an N-dimensional space to a 2-dimensional neural net in a nonlinear way preserving the topological order of the input vectors. These mappings are studied using a nonlinear power system model.

Toward the Replacement of Animal Experiments through the Bioinformatics-driven Analysis of 'Omics' Data from Human Cell Cultures.

PubMed

Grafström, Roland C; Nymark, Penny; Hongisto, Vesa; Spjuth, Ola; Ceder, Rebecca; Willighagen, Egon; Hardy, Barry; Kaski, Samuel; Kohonen, Pekka

2015-11-01

This paper outlines the work for which Roland Grafström and Pekka Kohonen were awarded the 2014 Lush Science Prize. The research activities of the Grafström laboratory have, for many years, covered cancer biology studies, as well as the development and application of toxicity-predictive in vitro models to determine chemical safety. Through the integration of in silico analyses of diverse types of genomics data (transcriptomic and proteomic), their efforts have proved to fit well into the recently-developed Adverse Outcome Pathway paradigm. Genomics analysis within state-of-the-art cancer biology research and Toxicology in the 21st Century concepts share many technological tools. A key category within the Three Rs paradigm is the Replacement of animals in toxicity testing with alternative methods, such as bioinformatics-driven analyses of data obtained from human cell cultures exposed to diverse toxicants. This work was recently expanded within the pan-European SEURAT-1 project (Safety Evaluation Ultimately Replacing Animal Testing), to replace repeat-dose toxicity testing with data-rich analyses of sophisticated cell culture models. The aims and objectives of the SEURAT project have been to guide the application, analysis, interpretation and storage of 'omics' technology-derived data within the service-oriented sub-project, ToxBank. Particularly addressing the Lush Science Prize focus on the relevance of toxicity pathways, a 'data warehouse' that is under continuous expansion, coupled with the development of novel data storage and management methods for toxicology, serve to address data integration across multiple 'omics' technologies. The prize winners' guiding principles and concepts for modern knowledge management of toxicological data are summarised. The translation of basic discovery results ranged from chemical-testing and material-testing data, to information relevant to human health and environmental safety. 2015 FRAME.

ASPECT: A spectra clustering tool for exploration of large spectral surveys

NASA Astrophysics Data System (ADS)

in der Au, A.; Meusinger, H.; Schalldach, P. F.; Newholm, M.

2012-11-01

Context. Analysing the empirical output from large surveys is an important challenge in contemporary science. Difficulties arise, in particular, when the database is huge and the properties of the object types to be selected are poorly constrained a priori. Aims: We present the novel, semi-automated clustering tool ASPECT for analysing voluminous archives of spectra. Methods: The heart of the program is a neural network in the form of a Kohonen self-organizing map. The resulting map is designed as an icon map suitable for the inspection by eye. The visual analysis is supported by the option to blend in individual object properties such as redshift, apparent magnitude, or signal-to-noise ratio. In addition, the package provides several tools for the selection of special spectral types, e.g. local difference maps which reflect the deviations of all spectra from one given input spectrum (real or artificial). Results: ASPECT is able to produce a two-dimensional topological map of a huge number of spectra. The software package enables the user to browse and navigate through a huge data pool and helps them to gain an insight into underlying relationships between the spectra and other physical properties and to get the big picture of the entire data set. We demonstrate the capability of ASPECT by clustering the entire data pool of ~6 × 105 spectra from the Data Release 4 of the Sloan Digital Sky Survey (SDSS). To illustrate the results regarding quality and completeness we track objects from existing catalogues of quasars and carbon stars, respectively, and connect the SDSS spectra with morphological information from the GalaxyZoo project. Code is only available at the CDS via anonymous ftp to cdsarc.u-strasbg.fr (130.79.128.5) or via http://cdsarc.u-strasbg.fr/viz-bin/qcat?J/A+A/547/A115

A novel constructive-optimizer neural network for the traveling salesman problem.

PubMed

Saadatmand-Tarzjan, Mahdi; Khademi, Morteza; Akbarzadeh-T, Mohammad-R; Moghaddam, Hamid Abrishami

2007-08-01

In this paper, a novel constructive-optimizer neural network (CONN) is proposed for the traveling salesman problem (TSP). CONN uses a feedback structure similar to Hopfield-type neural networks and a competitive training algorithm similar to the Kohonen-type self-organizing maps (K-SOMs). Consequently, CONN is composed of a constructive part, which grows the tour and an optimizer part to optimize it. In the training algorithm, an initial tour is created first and introduced to CONN. Then, it is trained in the constructive phase for adding a number of cities to the tour. Next, the training algorithm switches to the optimizer phase for optimizing the current tour by displacing the tour cities. After convergence in this phase, the training algorithm switches to the constructive phase anew and is continued until all cities are added to the tour. Furthermore, we investigate a relationship between the number of TSP cities and the number of cities to be added in each constructive phase. CONN was tested on nine sets of benchmark TSPs from TSPLIB to demonstrate its performance and efficiency. It performed better than several typical Neural networks (NNs), including KNIES_TSP_Local, KNIES_TSP_Global, Budinich's SOM, Co-Adaptive Net, and multivalued Hopfield network as wall as computationally comparable variants of the simulated annealing algorithm, in terms of both CPU time and accuracy. Furthermore, CONN converged considerably faster than expanding SOM and evolved integrated SOM and generated shorter tours compared to KNIES_DECOMPOSE. Although CONN is not yet comparable in terms of accuracy with some sophisticated computationally intensive algorithms, it converges significantly faster than they do. Generally speaking, CONN provides the best compromise between CPU time and accuracy among currently reported NNs for TSP.

Variable selection in near-infrared spectroscopy: benchmarking of feature selection methods on biodiesel data.

PubMed

Balabin, Roman M; Smirnov, Sergey V

2011-04-29

During the past several years, near-infrared (near-IR/NIR) spectroscopy has increasingly been adopted as an analytical tool in various fields from petroleum to biomedical sectors. The NIR spectrum (above 4000 cm(-1)) of a sample is typically measured by modern instruments at a few hundred of wavelengths. Recently, considerable effort has been directed towards developing procedures to identify variables (wavelengths) that contribute useful information. Variable selection (VS) or feature selection, also called frequency selection or wavelength selection, is a critical step in data analysis for vibrational spectroscopy (infrared, Raman, or NIRS). In this paper, we compare the performance of 16 different feature selection methods for the prediction of properties of biodiesel fuel, including density, viscosity, methanol content, and water concentration. The feature selection algorithms tested include stepwise multiple linear regression (MLR-step), interval partial least squares regression (iPLS), backward iPLS (BiPLS), forward iPLS (FiPLS), moving window partial least squares regression (MWPLS), (modified) changeable size moving window partial least squares (CSMWPLS/MCSMWPLSR), searching combination moving window partial least squares (SCMWPLS), successive projections algorithm (SPA), uninformative variable elimination (UVE, including UVE-SPA), simulated annealing (SA), back-propagation artificial neural networks (BP-ANN), Kohonen artificial neural network (K-ANN), and genetic algorithms (GAs, including GA-iPLS). Two linear techniques for calibration model building, namely multiple linear regression (MLR) and partial least squares regression/projection to latent structures (PLS/PLSR), are used for the evaluation of biofuel properties. A comparison with a non-linear calibration model, artificial neural networks (ANN-MLP), is also provided. Discussion of gasoline, ethanol-gasoline (bioethanol), and diesel fuel data is presented. The results of other spectroscopic

Monitoring the Microgravity Environment Quality On-board the International Space Station Using Soft Computing Techniques. Part 2; Preliminary System Performance Results

NASA Technical Reports Server (NTRS)

Jules, Kenol; Lin, Paul P.; Weiss, Daniel S.

2002-01-01

and unknown vibratory disturbance sources. Several soft computing techniques such as Kohonen's Self-Organizing Feature Map, Learning Vector Quantization, Back-Propagation Neural Networks, and Fuzzy Logic were used to design the system.

Spatial analysis of agro-ecological data: Detection of spatial patterns combining three different methodical approaches

NASA Astrophysics Data System (ADS)

Heuer, A.; Casper, M. C.; Vohland, M.

2009-04-01

Processes in natural systems and the resulting patterns occur in ecological space and time. To study natural structures and to understand the functional processes it is necessary to identify the relevant spatial and temporal space at which these all occur; or with other words to isolate spatial and temporal patterns. In this contribution we will concentrate on the spatial aspects of agro-ecological data analysis. Data were derived from two agricultural plots, each of about 5 hectares, in the area of Newel, located in Western Palatinate, Germany. The plots had been conventionally cultivated with a crop rotation of winter rape, winter wheat and spring barley. Data about physical and chemical soil properties, vegetation and topography were i) collected by measurements in the field during three vegetation periods (2005-2008) and/or ii) derived from hyperspectral image data, acquired by a HyMap airborne imaging sensor (2005). To detect spatial variability within the plots, we applied three different approaches that examine and describe relationships among data. First, we used variography to get an overview of the data. A comparison of the experimental variograms facilitated to distinguish variables, which seemed to occur in related or dissimilar spatial space. Second, based on data available in raster-format basic cell statistics were conducted, using a geographic information system. Here we could make advantage of the powerful classification and visualization tool, which supported the spatial distribution of patterns. Third, we used an approach that is being used for visualization of complex highly dimensional environmental data, the Kohonen self-organizing map. The self-organizing map (SOM) uses multidimensional data that gets further reduced in dimensionality (2-D) to detect similarities in data sets and correlation between single variables. One of SOM's advantages is its powerful visualization capability. The combination of the three approaches leads to

Assessing Vermont's stream health and biological integrity using artificial neural networks and Bayesian methods

NASA Astrophysics Data System (ADS)

Rizzo, D. M.; Fytilis, N.; Stevens, L.

2012-12-01

Environmental managers are increasingly required to monitor and forecast long-term effects and vulnerability of biophysical systems to human-generated stresses. Ideally, a study involving both physical and biological assessments conducted concurrently (in space and time) could provide a better understanding of the mechanisms and complex relationships. However, costs and resources associated with monitoring the complex linkages between the physical, geomorphic and habitat conditions and the biological integrity of stream reaches are prohibitive. Researchers have used classification techniques to place individual streams and rivers into a broader spatial context (hydrologic or health condition). Such efforts require environmental managers to gather multiple forms of information - quantitative, qualitative and subjective. We research and develop a novel classification tool that combines self-organizing maps with a Naïve Bayesian classifier to direct resources to stream reaches most in need. The Vermont Agency of Natural Resources has developed and adopted protocols for physical stream geomorphic and habitat assessments throughout the state of Vermont. Separate from these assessments, the Vermont Department of Environmental Conservation monitors the biological communities and the water quality in streams. Our initial hypothesis is that the geomorphic reach assessments and water quality data may be leveraged to reduce error and uncertainty associated with predictions of biological integrity and stream health. We test our hypothesis using over 2500 Vermont stream reaches (~1371 stream miles) assessed by the two agencies. In the development of this work, we combine a Naïve Bayesian classifier with a modified Kohonen Self-Organizing Map (SOM). The SOM is an unsupervised artificial neural network that autonomously analyzes inherent dataset properties using input data only. It is typically used to cluster data into similar categories when a priori classes do not exist. The

21st Century Projections of High Streamflow Events in the UK and Germany

NASA Astrophysics Data System (ADS)

Cioffi, Francesco; Rosario Conticello, Federico; Lall, Upmanu; Merz, Bruno

2017-04-01

Radiative effects of anthropogenic changes in atmospheric composition are expected to enhance the hydrological cycle leading to more frequent and intense floods. To explore if there will be an increased risk of river flooding in the future, 21st century projections under global warming scenarios of High Streamflow Events (HSEs) for UK and German rivers are carried out, using a model that statistically relates large-scale atmospheric predictors - 850 hPa Geopotential Height (GPH850) and Integrated Water Vapor Transport (IVT) - to the occurrence of HSEs in one or simultaneously in several streamflow gauges. Here, HSE is defined as the streamflow exceeding the 99th percentile of daily flowrate time series measured at streamflow gauges. For the common period 1960-2012, historical data from 57 streamflow gauges in UK and 61 streamflow gauges in Germany, as well as, reanalysis data of GPH850 and IVT fields, bounded from 90W to 70E and from 20N to 80N are used. The link between GPH850 configurations and HSEs, and more precisely, identification of the GPH850 states potentially able to generate HSEs, is performed by a combined Kohonen Networks (Self Organized Map, SOM) and Event Syncronization approach. Complex network and modularity methods are used to cluster streamflow gauges that share common GPH850 configurations. Then a model based on a conditional Poisson distribution, in which the parameter of the Poisson distribution is assumed to be a nonlinear function of GPH850 and IVT, allows for the identification of GPH850 state and threshold of IVT beyond which there is the HSE highest probability. Using that model, projections of 21st century changes in frequency of HSEs occurrence in UK and Germany are estimated using the simulated fields of GPH850 and IVT from selected GCMs belonging to the Coupled Model Inter-comparison Project Phase 5 (CMIP5). Among the different GCMs, those are selected whose retrospective predictor fields have consistent statistics with the

Image Coding Based on Address Vector Quantization.

NASA Astrophysics Data System (ADS)

Feng, Yushu

Image coding is finding increased application in teleconferencing, archiving, and remote sensing. This thesis investigates the potential of Vector Quantization (VQ), a relatively new source coding technique, for compression of monochromatic and color images. Extensions of the Vector Quantization technique to the Address Vector Quantization method have been investigated. In Vector Quantization, the image data to be encoded are first processed to yield a set of vectors. A codeword from the codebook which best matches the input image vector is then selected. Compression is achieved by replacing the image vector with the index of the code-word which produced the best match, the index is sent to the channel. Reconstruction of the image is done by using a table lookup technique, where the label is simply used as an address for a table containing the representative vectors. A code-book of representative vectors (codewords) is generated using an iterative clustering algorithm such as K-means, or the generalized Lloyd algorithm. A review of different Vector Quantization techniques are given in chapter 1. Chapter 2 gives an overview of codebook design methods including the Kohonen neural network to design codebook. During the encoding process, the correlation of the address is considered and Address Vector Quantization is developed for color image and monochrome image coding. Address VQ which includes static and dynamic processes is introduced in chapter 3. In order to overcome the problems in Hierarchical VQ, Multi-layer Address Vector Quantization is proposed in chapter 4. This approach gives the same performance as that of the normal VQ scheme but the bit rate is about 1/2 to 1/3 as that of the normal VQ method. In chapter 5, a Dynamic Finite State VQ based on a probability transition matrix to select the best subcodebook to encode the image is developed. In chapter 6, a new adaptive vector quantization scheme, suitable for color video coding, called "A Self -Organizing

Analysis of ambient SO 2 concentrations and winds in the complex surroundings of a thermal power plant

NASA Astrophysics Data System (ADS)

Mlakar, P.

2004-11-01

SO2 pollution is still a significant problem in Slovenia, especially around large thermal power plants (TPPs), like the one at Šoštanj. The Šoštanj TPP is the exclusive source of SO2 in the area and is therefore a perfect example for air pollution studies. In order to understand air pollution around the Šoštanj TPP in detail, some analyses of emissions and ambient concentrations of SO2 at six automated monitoring stations in the surroundings of the TPP were made. The data base from 1991 to 1993 was used when there were no desulfurisation plants in operation. Statistical analyses of the influence of the emissions from the three TPP stacks at different measuring points were made. The analyses prove that the smallest stack (100 m) mainly pollutes villages and towns near the TPP within a radius of a few kilometres. The medium stack's (150 m) influence is noticed at shorter as well as at longer distances up to more than ten kilometres. The highest stack (230 m) pollutes mainly at longer distances, where the plume reaches the higher hills. Detailed analyses of ambient SO2 concentrations were made. They show the temporal and spatial distribution of different classes of SO2 concentrations from very low to alarming values. These analyses show that pollution patterns at a particular station remain the same if observed on a yearly basis, but can vary very much if observed on a monthly basis, mainly because of different weather patterns. Therefore the winds in the basin (as the most important feature influencing air pollution dispersion) were further analysed in detail to find clusters of similar patterns. For cluster analysis of ground-level winds patterns in the basin around the Šoštanj Thermal Power Plant, the Kohonen neural network and Leaders' method were used. Furthermore, the dependence of ambient SO2 concentrations on the clusters obtained was analysed. The results proved that effective cluster analysis can be a useful tool for compressing a huge wind data base

Large Scale Crop Classification in Ukraine using Multi-temporal Landsat-8 Images with Missing Data

NASA Astrophysics Data System (ADS)

Kussul, N.; Skakun, S.; Shelestov, A.; Lavreniuk, M. S.

2014-12-01

At present, there are no globally available Earth observation (EO) derived products on crop maps. This issue is being addressed within the Sentinel-2 for Agriculture initiative where a number of test sites (including from JECAM) participate to provide coherent protocols and best practices for various global agriculture systems, and subsequently crop maps from Sentinel-2. One of the problems in dealing with optical images for large territories (more than 10,000 sq. km) is the presence of clouds and shadows that result in having missing values in data sets. In this abstract, a new approach to classification of multi-temporal optical satellite imagery with missing data due to clouds and shadows is proposed. First, self-organizing Kohonen maps (SOMs) are used to restore missing pixel values in a time series of satellite imagery. SOMs are trained for each spectral band separately using non-missing values. Missing values are restored through a special procedure that substitutes input sample's missing components with neuron's weight coefficients. After missing data restoration, a supervised classification is performed for multi-temporal satellite images. For this, an ensemble of neural networks, in particular multilayer perceptrons (MLPs), is proposed. Ensembling of neural networks is done by the technique of average committee, i.e. to calculate the average class probability over classifiers and select the class with the highest average posterior probability for the given input sample. The proposed approach is applied for large scale crop classification using multi temporal Landsat-8 images for the JECAM test site in Ukraine [1-2]. It is shown that ensemble of MLPs provides better performance than a single neural network in terms of overall classification accuracy and kappa coefficient. The obtained classification map is also validated through estimated crop and forest areas and comparison to official statistics. 1. A.Yu. Shelestov et al., "Geospatial information system

Neural network analysis for geological interpretation of tomographic images beneath the Japan Islands

NASA Astrophysics Data System (ADS)

Kuwatani, T.; Toriumi, M.

2009-12-01

Recent advances in methodologies of geophysical observations, such as seismic tomography, seismic reflection method and geomagnetic method, provide us a large amount and a wide variety of data for physical properties of a crust and upper mantle (e.g. Matsubara et al. (2008)). However, it has still been difficult to specify a rock type and its physical conditions, mainly because (1) available data usually have a lot of error and uncertainty, and (2) physical properties of rocks are greatly affected by fluid and microstructures. The objective interpretation and quantitative evaluation for lithology and fluid-related structure require the statistical analyses of integrated geophysical and geological data. Self-Organizing Maps (SOMs) are unsupervised artificial neural networks that map the input space into clusters in a topological form whose organization is related to trends in the input data (Kohonen 2001). SOMs are powerful neural network techniques to classify and interpret multiattribute data sets. Results of SOM classifications can be represented as 2D images, called feature maps which illustrate the complexity and interrelationships among input data sets. Recently, some works have used SOM in order to interpret multidimensional, non-linear, and highly noised geophysical data for purposes of geological prediction (e.g. Klose 2006; Tselentis et al. 2007; Bauer et al. 2008). This paper describes the application of SOM to the 3D velocity structure beneath the whole Japan islands (e.g. Matsubara et al. 2008). From the obtained feature maps, we can specify the lithology and qualitatively evaluate the effect of fluid-related structures. Moreover, re-projection of feature maps onto the 3D velocity structures resulted in detailed images of the structures within the plates. The Pacific plate and the Philippine Sea plate subducting beneath the Eurasian plate can be imaged more clearly than the original P- and S-wave velocity structures. In order to understand more precise

Family influences on breakfast frequency and quality among primary school pupils in Warsaw and its surrounding areas.

PubMed

Zielińska, Monika; Hamułka, Jadwiga; Gajda, Karolina

2015-01-01

Regular consumption of a well balanced breakfast is a pre-requisite for normal growth and child development, along with the acquisition of proper eating habits. The family environment is crucial place where children learn such patterns of behaviour that form the basis for their development. To determine how family factors affect the regular eating of breakfast and types of foodstuffs consumed in primary school pupils, including food purchases made from vending machines and school tuck shops. Subjects were 836 pupils (435 girls and 401 boys, aged 6 - 13) from Warsaw and the surrounding areas. Appropriate socio-demographic data and relevant eating habits were obtained from direct interviewing of the subjects by means of a custom designed questionnaire. Statistical analyses were performed by the Kohonen type cluster analysis model and Chi-square test (Chi(2)); (p≤0.05). Three clusters of pupils were identified by their differing socio-demographics and eating habits (eg. rates of breakfast consumption, buying from vending machines or school tuck shops). The first and third clusters were mainly pupils from two-parent families with parents proportionally spending similar times at work, where respective breakfast (87% and 91%) and second breakfast (77% and 72%) consumption rates were also similar together with food shopping rates during school time (respectively 69% and 63%). Pupils with single-parents, multi-generation families or if both parents were profession- ally active, predominated in the second cluster. These ate breakfast (73%) and second breakfast (67%) more rarely, but more frequently shopped for food at school (84%). A small number of pupils had a packed second breakfast from home, rarely ate sandwiches, fruit and/or vegetables and dairy products but ate more sweets, sweet rolls and savoury snacks. However, a large number of subjects bought sandwiches, fresh fruit and/or vegetables and fast-food at school. Family factors were found to affect eating habits

Air Pollution Source/receptor Relationships in South Coast Air Basin, CA

NASA Astrophysics Data System (ADS)

Gao, Ning

This research project includes the application of some existing receptor models to study the air pollution source/receptor relationships in the South Coast Air Basin (SoCAB) of southern California, the development of a new receptor model and the testing and the modifications of some existing models. These existing receptor models used include principal component factor analysis (PCA), potential source contribution function (PSCF) analysis, Kohonen's neural network combined with Prim's minimal spanning tree (TREE-MAP), and direct trilinear decomposition followed by a matrix reconstruction. The ambient concentration measurements used in this study are a subset of the data collected during the 1987 field exercise of Southern California Air Quality Study (SCAQS). It consists of a number of gaseous and particulate pollutants analyzed from samples collected by SCAQS samplers at eight sampling sites, Anaheim, Azusa, Burbank, Claremont, Downtown Los Angeles, Hawthorne, Long Beach, and Rubidoux. Based on the information of emission inventories, meteorology and ambient concentrations, this receptor modeling study has revealed mechanisms that influence the air quality in SoCAB. Some of the mechanisms affecting the air quality in SoCAB that were revealed during this study include the following aspects. The SO_2 collected at sampling sites is mainly contributed by refineries in the coastal area and the ships equipped with oil-fired boilers off shore. Combustion of fossil fuel by automobiles dominates the emission of NO_{rm x} that is subsequently transformed and collected at sampling sites. Electric power plants also contribute HNO_3 to the sampling sites. A large feedlot in the eastern region of SoCAB has been identified as the major source of NH_3. Possible contributions from other industrial sources such as smelters and incinerators were also revealed. The results of this study also suggest the possibility of DMS (dimethylsulfide) and NH_3 emissions from off-shore sediments

Convolutional Neural Network for Multi-Source Deep Learning Crop Classification in Ukraine

NASA Astrophysics Data System (ADS)

Lavreniuk, M. S.

2016-12-01

Land cover and crop type maps are one of the most essential inputs when dealing with environmental and agriculture monitoring tasks [1]. During long time neural network (NN) approach was one of the most efficient and popular approach for most applications, including crop classification using remote sensing data, with high an overall accuracy (OA) [2]. In the last years the most popular and efficient method for multi-sensor and multi-temporal land cover classification is convolution neural networks (CNNs). Taking into account presence clouds in optical data, self-organizing Kohonen maps (SOMs) are used to restore missing pixel values in a time series of optical imagery from Landsat-8 satellite. After missing data restoration, optical data from Landsat-8 was merged with Sentinel-1A radar data for better crop types discrimination [3]. An ensemble of CNNs is proposed for multi-temporal satellite images supervised classification. Each CNN in the corresponding ensemble is a 1-d CNN with 4 layers implemented using the Google's library TensorFlow. The efficiency of the proposed approach was tested on a time-series of Landsat-8 and Sentinel-1A images over the JECAM test site (Kyiv region) in Ukraine in 2015. Overall classification accuracy for ensemble of CNNs was 93.5% that outperformed an ensemble of multi-layer perceptrons (MLPs) by +0.8% and allowed us to better discriminate summer crops, in particular maize and soybeans. For 2016 we would like to validate this method using Sentinel-1 and Sentinel-2 data for Ukraine territory within ESA project on country level demonstration Sen2Agri. 1. A. Kolotii et al., "Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine," The Int. Arch. of Photogram., Rem. Sens. and Spatial Inform. Scie., vol. 40, no. 7, pp. 39-44, 2015. 2. F. Waldner et al., "Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity," Int. Journal of Rem. Sens. vol. 37, no. 14, pp

Hybrid evolutionary computing model for mobile agents of wireless Internet multimedia

NASA Astrophysics Data System (ADS)

Hortos, William S.

2001-03-01

The ecosystem is used as an evolutionary paradigm of natural laws for the distributed information retrieval via mobile agents to allow the computational load to be added to server nodes of wireless networks, while reducing the traffic on communication links. Based on the Food Web model, a set of computational rules of natural balance form the outer stage to control the evolution of mobile agents providing multimedia services with a wireless Internet protocol WIP. The evolutionary model shows how mobile agents should behave with the WIP, in particular, how mobile agents can cooperate, compete and learn from each other, based on an underlying competition for radio network resources to establish the wireless connections to support the quality of service QoS of user requests. Mobile agents are also allowed to clone themselves, propagate and communicate with other agents. A two-layer model is proposed for agent evolution: the outer layer is based on the law of natural balancing, the inner layer is based on a discrete version of a Kohonen self-organizing feature map SOFM to distribute network resources to meet QoS requirements. The former is embedded in the higher OSI layers of the WIP, while the latter is used in the resource management procedures of Layer 2 and 3 of the protocol. Algorithms for the distributed computation of mobile agent evolutionary behavior are developed by adding a learning state to the agent evolution state diagram. When an agent is in an indeterminate state, it can communicate to other agents. Computing models can be replicated from other agents. Then the agents transitions to the mutating state to wait for a new information-retrieval goal. When a wireless terminal or station lacks a network resource, an agent in the suspending state can change its policy to submit to the environment before it transitions to the searching state. The agents learn the facts of agent state information entered into an external database. In the cloning process, two

Real Time On-line Space Research Laboratory Environment Monitoring with Off-line Trend and Prediction Analysis

NASA Technical Reports Server (NTRS)

Jules, Kenol; Lin, Paul P.

2006-01-01

their g-level contribution to the environment. The system can detect both known and unknown vibratory disturbance activities. It can also perform trend analysis and prediction by analyzing past data over many Increments of the space station for selected disturbance activities. This feature can be used to monitor the health of onboard mechanical systems to detect and prevent potential system failure as well as for use by research scientists during their science results analysis. Examples of both real time on-line vibratory disturbance detection and off-line trend analysis are presented in this paper. Several soft computing techniques such as Kohonen s Self-Organizing Feature Map, Learning Vector Quantization, Back-Propagation Neural Networks, and Fuzzy Logic were used to design the system.

Crustal block structure by GPS data using neural network in the Northern Tien Shan

NASA Astrophysics Data System (ADS)

Kostuk, A.; Carmenate, D.

2010-05-01

For over ten years regular GPS measurements have been carried out by Research Station RAS in the Central Asia. The results of these measurements have not only proved the conclusion that the Earth's crust meridional compression equals in total about 17 mm/year from the Tarim massif to the Kazakh shield, but have also allowed estimating deformation behavior in the region. As is known, deformation behavior of continental crust is an actively discussed issue. On the one hand, the Earth's crust is presented as a set of microplates (blocks) and deformation here is a result of shifting along the blocks boundaries, on the other hand, lithospheric deformation is distributed by volume and meets the rheological model of nonlinear viscous fluid. This work represents an attempt to detect the block structure of the surface of the Northern Tien Shan using GPS velocity fields. As a significant difference from analogous works, appears the vector field clustering with the help of neural network used as a classifier by many criteria that allows dividing input space into areas and using of all three components of GPS velocity. In this case, we use such a feature of neural networks as self-organization. Among the mechanisms of self-organization there are two main classes: self-organization based on the Hebb associative rule and the mechanism of neuronal competition based on the generalized Kohonen rule. In this case, we use an approach of self-organizing networks in which we take neuronal competition as an algorithm for their training. As a rule, these are single-layer networks where each neuron is connected to all components of m-dimensional input vector. GPS vectors of the Central Asian velocity field located within the territory of the Northern Tien Shan were used as input patterns. Measurements at GPS sites were fulfilled in 36 hour-long sessions by double-frequency receivers Trimble and Topcon. In so doing, measurement discreteness equaled 30 seconds; the data were processed by

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

Neural networks in chemistry

NASA Astrophysics Data System (ADS)

Zupan, Jure

1995-04-01

All problems that in some way are linked to handling of multi-variate experiments versus multi-variate responses can be approached by the group of methods that has recently became known as the artificial neural network (ANN) techniques. In this lecture, the types of the problems that can be solved by ANN techniques rather than the ANN techniques themselves will be addressed first. This issue is rather important due to the fact that the ANN techniques can be used for a very broad range of problems and choosing the wrong method can often result in either a failure to produce an effective solution or in a very time consuming and ineffective handling. Among the types of problems that can be solved by different ANN techniques the classification, mapping, look-up table, and modelling will be emphasized and discussed. Because all mentioned methods can be solved by different standard techniques, special emphasis will be paid to stress the advantages and drawbacks when employing different ANN techniques. Due to the fact that the range of possible use of ANN is so broad, even a very specific problem can be solved by many different ANN architectures or even using different learning strategies within ANN. In the second part the main learning strategies and corresponding choices of ANN architectures will be discussed. In this part the parameters and some guidelines how to select the method and the design of the ANNs will be shown on the examples of reported ANN applications in chemistry. The ANN learning strategies discussed will be back-propagation of errors, the Kohonen, and the counter propagation learning. The potential user of ANN should first, consider the problem, second, he must inspect the availability of data and the data themselves to decide for which ANN method they are best suited. In this respect, the amount of data, the dimensionality of the measurement space, the form of data (alphanumeric entries, binary, real, or even mixed forms of data) are crucial. After

Digital Gaming for Improving the Functioning of People With Traumatic Brain Injury: Randomized Clinical Feasibility Study.

PubMed

Välimäki, Maritta; Mishina, Kaisa; Kaakinen, Johanna K; Holm, Suvi K; Vahlo, Jukka; Kirjonen, Markus; Pekurinen, Virve; Tenovuo, Olli; Korkeila, Jyrki; Hämäläinen, Heikki; Sarajuuri, Jaana; Rantanen, Pekka; Orenius, Tage; Koponen, Aki

2018-03-19

. However, depression scores increased significantly between baseline and after 8 weeks and between baseline and after 3 months in the rehabilitative gaming group. No differences were found in patients' self-efficacy between the three measuring points in any of the groups. Participants did use the games (rehabilitation group: 93%, 27/29; entertainment group 100%, 29/29). Games were seen as a usable intervention (rehabilitation group: 70%, 14/29; entertainment group: 83%, 20/29). The rehabilitation group was less satisfied with the gaming intervention (68%, 13/29 vs 83%, 20/29), but they were more willing to use the game after the intervention period (76%, 16/29 vs 63%, 15/29). Total time spent on gaming during the intervention period was low (15.22 hour rehabilitation gaming group, 19.22 hour entertainment gaming group). We did not find differences between the groups in improvement in the outcome measures. The improvements in test performance by all three groups may reflect rehearsal effects. Entertainment gaming had elements that could be considered when rehabilitative games are designed for, implemented in, and assessed in larger clinical trials for persons with TBI. ClinicalTrials.gov NCT02425527; https://clinicaltrials.gov/ct2/show/NCT02425527 (Archived by WebCite at http://www.webcitation.org/6esKI1uDH). ©Maritta Välimäki, Kaisa Mishina, Johanna K Kaakinen, Suvi K Holm, Jukka Vahlo, Markus Kirjonen, Virve Pekurinen, Olli Tenovuo, Jyrki Korkeila, Heikki Hämäläinen, Jaana Sarajuuri, Pekka Rantanen, Tage Orenius, Aki Koponen. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 19.03.2018.

The European Science Foundation (ESF) Network SEDIFLUX — An introduction and overview

NASA Astrophysics Data System (ADS)

Beylich, Achim A.; Etienne, Samuel; Etzelmüller, Bernd; Gordeev, Vyacheslav V.; Käyhkö, Jukka; Rachold, Volker; Russell, Andrew J.; Schmidt, Karl-Heinz; Sæmundsson, Þorsteinn; Tweed, Fiona S.; Warburton, Jeff

2006-10-01

Climate change will cause major changes in the Earth surface systems, especially in high-latitude and high-altitude cold environments. Geomorphological processes operating at the Earth's surface, transferring sediments and changing landforms are dependent on climate and will be significantly affected by climate change. More reliable modelling of sediment transfer processes operating under present-day climatic settings is needed to determine the consequences of climate change. It is necessary to collect and to compare data and knowledge from a wide range of different high-latitude and high-altitude cold environments and to develop more standardized methods and approaches for future research on sediment fluxes and relationships between climate and sedimentary transfer processes. In Europe, the wide range of high-latitude and high-altitude cold environments provides great potential to investigate climate-process relationships and to model the effects of climate change by using space for time substitution. The European Science Foundation (ESF) Network (01.01.2004-31.12.2006) "Sedimentary Source-to-Sink-Fluxes in Cold Environments" ( SEDIFLUX) is bringing together leading scientists, young scientists and research teams from different fields. SEDIFLUX forms a framework for an integrated and multidisciplinary investigation of the addressed topic and is a major catalyst for strengthening and extending contacts, collaborative research activities and mobility of scientists in Europe. It also points to areas within Europe that would benefit from wider research collaboration (e.g. Russia, Poland). The SEDIFLUX Steering Committee consists of scientists from seven European countries: Achim A. Beylich, Co-ordinator of SEDIFLUX (Trondheim, Norway), Samuel Etienne (Clermont-Ferrand, France), Bernd Etzelmüller (Oslo, Norway), Vyacheslav V. Gordeev (Moscow, Russia), Jukka Käyhkö (Turku, Finland), Volker Rachold (Potsdam, Germany), Andrew J. Russell (Newcastle, England, UK), Karl

Influence of plant productivity over variability of soil respiration: a multi-scale approach

NASA Astrophysics Data System (ADS)

Curiel Yuste, J.

2009-04-01

general controlled by the seasonality of substrate supply by plants (via photosynthates translocation and/or litter) to soil. Although soil temperature and soil moisture exert a strong influence over the variation in SR, our results indicates that substrate supply by plant activity could exert a more important than previously expected role in the variability of soil respiration. 1. CREAF (Centre de Recerca Ecológica i Aplicacions Forestals), Unitat d'Ecofisiologia i Canvi Global CREAF-CEAB-CSIC, BELLATERRA (Barcelona), Spain (j.curiel@creaf.uab.es) 2. University of Antwerp (UA), Antwerp, Belgium (ivan.janssens@ua.ac.be) 3. Institute of Ecology, University of Innsbruck, Innsbruck, Austria (michael.bahn@uibk.ac.at) 4. UMR Ecologie et Ecophysiologie Forestières, Centre INRA de Nancy, France (longdoz@nancy.inra.fr) 5. ESPM, University of Calicornia at Berkeley, Berkeley, CA, US (baldocchi@nature.berkeley.edu) 6. The Woods Hole Research Center, Falmouth, USA (edavidson@whrc.org) 7. Max-Planck-Institute for Biogeochemistry, Jena, Germany (markus.reichstein@bgc-jena.mpg.de) 8. Institute of Systems Biology and Ecology, Academy of Sciences of the Czech Republic, Czech Republic (manuel@brno.cas.cz) 9. Università degli studi della Tuscia, Viterbo, Italy (arriga@unitus.it) 10. Laurence Berkeley lab, Berkeley, CA, USA (mstorn@lbl.gov) 11. Gembloux Agricultural University, Gembloux, Belgium (aubinet.m@fsagx.ac.be) 12. Fundacion CEAM(Centro de Estudios Ambientales del Mediterráneo), Valencia, Spain (arnaud@ceam.es) 13. Institute of Hydrology and Meteorology, Technische Universität Dresden, Pienner, Germany (gruenwald@forst.tu-dresden.de) 14. Department of Environmental Sciences, Second University of Naples, Caserta, Italy (ilaria.inglima@unina2.it) 15. CNRS-CEFE Montpellier, France (Laurent.MISSON@cefe.cnrs.fr) 16. Agenzia Provinciale per l'Ambiente, Bolzano, Italy (leonar@inwind.it) 17. University of Helsinki Department of Forest Ecology, Helsinki, Finland (jukka

A Combined Atmospheric Rivers and Geopotential Height Analysis for the Detection of High Streamflow Event Probability Occurrence in UK and Germany

NASA Astrophysics Data System (ADS)

Rosario Conticello, Federico; Cioffi, Francesco; Lall, Upmanu; Merz, Bruno

2017-04-01

in UK and 61 streamflow gauges in Germany, as well as reanalysis data of the 850 hPa geopotential fields bounded from 90W to 70E and from 20N to 80N are used. The common period is 1960 to 2012. The link between GPH850 and HSEs, and more precisely, the identification of the GPH850 states potentially able to generate HSEs is performed by a combined Kohonen Networks (Self Organized Map, SOM) and Event Syncronization approach. Complex network and modularity methods are used to cluster streamflow gauges that share common GPH850 configurations. Then a model based on a conditional Poisson distribution is carried out, in which the parameter of the Poisson distribution is assumed to be a nonlinear function of GPH850 state and IVT/ IWV. This model allows for the identification of the threshold of IVT/IWV beyond which there is the HSE highest probability.

Analysis of Induced Polarization effects in airborne TEM data - a case study from central East Greenland

NASA Astrophysics Data System (ADS)

Maack Rasmussen, Thorkild; Brethes, Anaïs; Pierpaolo Guarnieri, Pierpaolo; Bauer, Tobias

2017-04-01

Data from a high-resolution airborne SkyTEM time-domain electromagnetic survey conducted in central East Greenland were analysed. An analysis based on utilization of a Self Organizing Map procedure for response curve characterization and analyses based on data inversion and modelling are presented. The survey was flown in 2013 along the eastern margin of the Jameson Land basin with the purpose of base metal exploration and with sulphide mineralization as target. The survey area comprises crystalline basement to the East and layered Early Triassic to Jurassic sediments to the West. The layers are dipping a few degrees towards West. The Triassic sequence is 1 to 2 km thick and mostly of continental origin. The fluviatile Early Triassic arkoses and conglomerates, the Upper Triassic grey limestone and black shale beds and overlying gypsiferous sandstones and mudstones are known to host disseminated sulphides. E-W oriented lines were flown with an average terrain clearance of 30m and a separation of 300m. The data were initially processed and inverted by SkyTEM Aps. The conductivity models showed some conductive layers as well as induced polarization (IP) effects in the data. IP effects in TEM data reflect the relaxation of polarized charges in the ground which can be good indicators of the presence of metallic particles. Some of these locations were drilled during the following field season but unfortunately did not reveal the presence of mineralization. The aim of this study is therefore to understand the possible causes of these IP effects. Electrical charge accumulation in the ground can be related to the presence of sulphides, oxides or graphite or to the presence of clays or fibrous minerals. Permafrost may also cause IP effects and is then expected to be associated with a highly resistive subsurface. Several characteristics of the transient curves (IP indicators) of the SkyTEM survey were extracted and analysed by using the Kohonen Self-Organizing Map (SOM

Data driven model generation based on computational intelligence

NASA Astrophysics Data System (ADS)

Gemmar, Peter; Gronz, Oliver; Faust, Christophe; Casper, Markus

2010-05-01

parameters with respect to a defined rating function and experimental data. To find A, we use for example a linear equation solver and RMSE-function. In practical process models, the number of Fuzzy sets and the according number of rules is fairly low. Nevertheless, creating the optimal model requires some experience. Therefore, we improved this development step by methods for automatic generation of Fuzzy sets, rules, and conclusions. Basically, the model achievement depends to a great extend on the selection of the conclusion variables. It is the aim that variables having most influence on the system reaction being considered and superfluous ones being neglected. At first, we use Kohonen maps, a specialized ANN, to identify relevant input variables from the large set of available system variables. A greedy algorithm selects a comprehensive set of dominant and uncorrelated variables. Next, the premise variables are analyzed with clustering methods (e.g. Fuzzy-C-means) and Fuzzy sets are then derived from cluster centers and outlines. The rule base is automatically constructed by permutation of the Fuzzy sets of the premise variables. Finally, the conclusion parameters are calculated and the total coverage of the input space is iteratively tested with experimental data, rarely firing rules are combined and coarse coverage of sensitive process states results in refined Fuzzy sets and rules. Results The described methods were implemented and integrated in a development system for process models. A series of models has already been built e.g. for rainfall-runoff modeling or for flood prediction (up to 72 hours) in river catchments. The models required significantly less development effort and showed advanced simulation results compared to conventional models. The models can be used operationally and simulation takes only some minutes on a standard PC e.g. for a gauge forecast (up to 72 hours) for the whole Mosel (Germany) river catchment.

Analysis of short single rest/activation epoch fMRI by self-organizing map neural network

NASA Astrophysics Data System (ADS)

Erberich, Stephan G.; Dietrich, Thomas; Kemeny, Stefan; Krings, Timo; Willmes, Klaus; Thron, Armin; Oberschelp, Walter

2000-04-01

Functional magnet resonance imaging (fMRI) has become a standard non invasive brain imaging technique delivering high spatial resolution. Brain activation is determined by magnetic susceptibility of the blood oxygen level (BOLD effect) during an activation task, e.g. motor, auditory and visual tasks. Usually box-car paradigms have 2 - 4 rest/activation epochs with at least an overall of 50 volumes per scan in the time domain. Statistical test based analysis methods need a large amount of repetitively acquired brain volumes to gain statistical power, like Student's t-test. The introduced technique based on a self-organizing neural network (SOM) makes use of the intrinsic features of the condition change between rest and activation epoch and demonstrated to differentiate between the conditions with less time points having only one rest and one activation epoch. The method reduces scan and analysis time and the probability of possible motion artifacts from the relaxation of the patients head. Functional magnet resonance imaging (fMRI) of patients for pre-surgical evaluation and volunteers were acquired with motor (hand clenching and finger tapping), sensory (ice application), auditory (phonological and semantic word recognition task) and visual paradigms (mental rotation). For imaging we used different BOLD contrast sensitive Gradient Echo Planar Imaging (GE-EPI) single-shot pulse sequences (TR 2000 and 4000, 64 X 64 and 128 X 128, 15 - 40 slices) on a Philips Gyroscan NT 1.5 Tesla MR imager. All paradigms were RARARA (R equals rest, A equals activation) with an epoch width of 11 time points each. We used the self-organizing neural network implementation described by T. Kohonen with a 4 X 2 2D neuron map. The presented time course vectors were clustered by similar features in the 2D neuron map. Three neural networks were trained and used for labeling with the time course vectors of one, two and all three on/off epochs. The results were also compared by using a

EDITORIAL: 'Best article' prize for the 5th anniversary of Environmental Research Letters 'Best article' prize for the 5th anniversary of Environmental Research Letters

NASA Astrophysics Data System (ADS)

Kammen, Dan; Wright, Guillaume

2011-12-01

To celebrate the 5th anniversary of Environmental Research Letters (ERL) the publishers of the journal, IOP Publishing, have awarded a prize for the five best articles published in ERL since the journal began in 2006. The procedure for deciding the winning articles was as thorough as possible to ensure that the most outstanding articles would win the prize. A shortlist of 25 nominated research articles, five for each year since ERL was launched, which were chosen based on a range of criteria including novelty, scientific impact, readership, broad appeal and wider media coverage, was selected. The ERL Editorial Board then assessed and rated these 25 articles in order to choose a winning article for each year. We would like to announce that the following articles have been awarded ERL's 5th anniversary best article prize: 2006/7 The Bodélé depression: a single spot in the Sahara that provides most of the mineral dust to the Amazon forest Ilan Koren, Yoram J Kaufman, Richard Washington, Martin C Todd, Yinon Rudich, J Vanderlei Martins and Daniel Rosenfeld 2006 Environ. Res. Lett. 1 014005 2008 Causes and impacts of the 2005 Amazon drought Ning Zeng, Jin-Ho Yoon, Jose A Marengo, Ajit Subramaniam, Carlos A Nobre, Annarita Mariotti and J David Neelin 2008 Environ. Res. Lett. 3 014002 2009 How difficult is it to recover from dangerous levels of global warming? J A Lowe, C Huntingford, S C B Raper, C D Jones, S K Liddicoat and L K Gohar 2009 Environ. Res. Lett. 4 014012 2010 Is physical water scarcity a new phenomenon? Global assessment of water shortage over the last two millennia Matti Kummu, Philip J Ward, Hans de Moel and Olli Varis 2010 Environ. Res. Lett. 5 034006 2011 Implications of urban structure on carbon consumption in metropolitan areas Jukka Heinonen and Seppo Junnila 2011 Environ. Res. Lett. 6 014018 Our congratulations go to these authors. In recognition of their outstanding work, we are delighted to offer all of the authors of the winning articles free

Dealing with missing data in remote sensing images within land and crop classification

NASA Astrophysics Data System (ADS)

Skakun, Sergii; Kussul, Nataliia; Basarab, Ruslan

Optical remote sensing images from space provide valuable data for environmental monitoring, disaster management [1], agriculture mapping [2], so forth. In many cases, a time-series of satellite images is used to discriminate or estimate particular land parameters. One of the factors that influence the efficiency of satellite imagery is the presence of clouds. This leads to the occurrence of missing data that need to be addressed. Numerous approaches have been proposed to fill in missing data (or gaps) and can be categorized into inpainting-based, multispectral-based, and multitemporal-based. In [3], ancillary MODIS data are utilized for filling gaps and predicting Landsat data. In this paper we propose to use self-organizing Kohonen maps (SOMs) for missing data restoration in time-series of satellite imagery. Such approach was previously used for MODIS data [4], but applying this approach for finer spatial resolution data such as Sentinel-2 and Landsat-8 represents a challenge. Moreover, data for training the SOMs are selected manually in [4] that complicates the use of the method in an automatic mode. SOM is a type of artificial neural network that is trained using unsupervised learning to produce a discretised representation of the input space of the training samples, called a map. The map seeks to preserve the topological properties of the input space. The reconstruction of satellite images is performed for each spectral band separately, i.e. a separate SOM is trained for each spectral band. Pixels that have no missing values in the time-series are selected for training. Selecting the number of training pixels represent a trade-off, in particular increasing the number of training samples will lead to the increased time of SOM training while increasing the quality of restoration. Also, training data sets should be selected automatically. As such, we propose to select training samples on a regular grid of pixels. Therefore, the SOM seeks to project a large number

Adaptation response surfaces from an ensemble of wheat projections under climate change in Europe

NASA Astrophysics Data System (ADS)

Ruiz-Ramos, Margarita; Ferrise, Roberto

2016-04-01

preliminary ARSs show some adaptation options allow recover up to ca. 2000 kg/ha. Compared to the historical yields recorded at Lleida province (2550 kg/ha in 1981-2010) our results indicate that adaptation is feasible and may help to reduce detrimental effects of CC. Our analysis evaluates if the explored adaptations fulfill the biophysical requirements to become a practical adaptive solution. This study exemplifies how adaptation options and their impacts can be analyzed, evaluated and communicated in a context of high regional uncertainty for current and future conditions and for short to long-term perspective. This work was funded by MACSUR project within FACCE-JPI. References Abeledo, L.G., R. Savin and G.A. Slafer (2008). European Journal of Agronomy 28:541-550. Cartelle, J., A. Pedró, R. Savin, G.A. Slafer (2006) European Journal of Agronomy 25:365-371. Pirttioja, N., T. Carter, S. Fronzek, M. Bindi, H. Hoffmann, T. Palosuo, M. Ruiz-Ramos, F. Tao, M. Acutis, S. Asseng, P. Baranowski, B. Basso, P. Bodin, S. Buis, D. Cammarano, P. Deligios, M.-F. Destain, B. Dumont, R. Ewert, R. Ferrise, L. François, T. Gaiser, P. Hlavinka, I. Jacquemin, K.C. Kersebaum, C. Kollas, J. Krzyszczak, I.J. Lorite, J. Minet, M.I. Minguez, M. Montesino, M. Moriondo, C. Müller, C. Nendel, I. Öztürk, A. Perego, A. Rodríguez, A.C. Ruane, F. Ruget, M. Sanna, M.A. Semenov, C. Slawinski, P. Stratonovitch, I. Supit, K. Waha, E. Wang, L. Wu, Z. Zhao, and R.P. Rötter, 2015: A crop model ensemble analysis of temperature and precipitation effects on wheat yield across a European transect using impact response surfaces. Clim. Res., 65, 87-105, doi:10.3354/cr01322. IRS2 TEAM: Alfredo Rodríguez(1), Ignacio J. Lorite(3), Fulu Tao(4), Nina Pirttioja(5), Stefan Fronzek(5), Taru Palosuo(4), Timothy R. Carter(5), Marco Bindi(2), Jukka G Höhn(4), Kurt Christian Kersebaum(6), Miroslav Trnka(7,8), Holger Hoffmann(9), Piotr Baranowski(10), Samuel Buis(11), Davide Cammarano(12), Yi Chen(13,4), Paola Deligios

EDITORIAL The 17th Central European Workshop on Quantum Optics

NASA Astrophysics Data System (ADS)

Man'ko, Margarita A.

2011-02-01

), held at the University of Turku, are also available (2010 Phys. Scr. T140). The 18th Central European Workshop on Quantum Optics (CEWQO11) will be held in Madrid, Spain on 30 May--3 June 2011. It will be chaired by Professor Luis Lorenzo Sanchez Soto from the Complutense University of Madrid. List of Papers The 17th Central European Workshop on Quantum Optics in St Andrews, Scotland Ulf Leonhardt and Natalia Korolkova Double self-Kerr scheme for optical Schrödinger-cat state preparation P Adam, Z Darázs, T Kiss and M Mechler Relations between scaling transformed Husimi functions, Wigner functions and symplectic tomograms describing corresponding physical states V A Andreev, D M Davidović, L D Davidović and M D Davidović Entanglement dynamics of two independent cavity-embedded quantum dots B Bellomo, G Compagno, R Lo Franco, A Ridolfo and S Savasta Dynamical stabilization of spin systems in time-dependent magnetic fields Yu V Bezvershenko, P I Holod and A Messina Entanglement dynamics of a bipartite system in squeezed vacuum reservoirs Smail Bougouffa and Awatif Hindi On Wheeler's delayed-choice Gedankenexperiment and its laboratory realization M Božić, L Vušković, M Davidović and Á S Sanz A smooth, holographically generated ring trap for the investigation of superfluidity in ultracold atoms Graham D Bruce, James Mayoh, Giuseppe Smirne, Lara Torralbo-Campo and Donatella Cassettari Parametric amplification of the classical field in cavities with photoexcited semiconductors V V Dodonov Mutually unbiased bases: tomography of spin states and the star-product scheme S N Filippov and V I Man'ko Quantum trajectory model for photon detectors and optoelectronic devices Teppo Häyrynen, Jani Oksanen and Jukka Tulkki Entanglement in two-mode continuous variable open quantum systems Aurelian Isar A classical field comeback? The classical field viewpoint on triparticle entanglement Andrei Khrennikov Experimental investigation of the enhancement factor and the cross