Science.gov

Sample records for achieved classification accuracies

  1. Improving classification accuracy and causal knowledge for better credit decisions.

    PubMed

    Wu, Wei-Wen

    2011-08-01

    Numerous studies have contributed to efforts to boost the accuracy of the credit scoring model. Especially interesting are recent studies which have successfully developed the hybrid approach, which advances classification accuracy by combining different machine learning techniques. However, to achieve better credit decisions, it is not enough merely to increase the accuracy of the credit scoring model. It is necessary to conduct meaningful supplementary analyses in order to obtain knowledge of causal relations, particularly in terms of significant conceptual patterns or structures involving attributes used in the credit scoring model. This paper proposes a solution of integrating data preprocessing strategies and the Bayesian network classifier with the tree augmented Na"ıve Bayes search algorithm, in order to improve classification accuracy and to obtain improved knowledge of causal patterns, thus enhancing the validity of credit decisions.

  2. Estimating Consistency and Accuracy Indices for Multiple Classifications

    ERIC Educational Resources Information Center

    Lee, Won-Chan; Hanson, Bradley A.; Brennan, Robert L.

    2002-01-01

    This article describes procedures for estimating various indices of classification consistency and accuracy for multiple category classifications using data from a single test administration. The estimates of the classification consistency and accuracy indices are compared under three different psychometric models: the two-parameter beta binomial,…

  3. Classification accuracy of actuarial risk assessment instruments.

    PubMed

    Neller, Daniel J; Frederick, Richard I

    2013-01-01

    Users of commonly employed actuarial risk assessment instruments (ARAIs) hope to generate numerical probability statements about risk; however, ARAI manuals often do not explicitly report data that are essential for understanding the classification accuracy of the instruments. In addition, ARAI manuals often contain data that have the potential for misinterpretation. The authors of the present article address the accurate generation of probability statements. First, they illustrate how the reporting of numerical probability statements based on proportions rather than predictive values can mislead users of ARAIs. Next, they report essential test characteristics that, to date, have gone largely unreported in ARAI manuals. Then they discuss a graphing method that can enhance the practice of clinicians who communicate risk via numerical probability statements. After the authors review several strategies for selecting optimal cut-off scores, they show how the graphing method can be used to estimate positive predictive values for each cut-off score of commonly used ARAIs, across all possible base rates. They also show how the graphing method can be used to estimate base rates of violent recidivism in local samples.

  4. A Nonparametric Approach to Estimate Classification Accuracy and Consistency

    ERIC Educational Resources Information Center

    Lathrop, Quinn N.; Cheng, Ying

    2014-01-01

    When cut scores for classifications occur on the total score scale, popular methods for estimating classification accuracy (CA) and classification consistency (CC) require assumptions about a parametric form of the test scores or about a parametric response model, such as item response theory (IRT). This article develops an approach to estimate CA…

  5. Estimating Classification Consistency and Accuracy for Cognitive Diagnostic Assessment

    ERIC Educational Resources Information Center

    Cui, Ying; Gierl, Mark J.; Chang, Hua-Hua

    2012-01-01

    This article introduces procedures for the computation and asymptotic statistical inference for classification consistency and accuracy indices specifically designed for cognitive diagnostic assessments. The new classification indices can be used as important indicators of the reliability and validity of classification results produced by…

  6. Achieving Climate Change Absolute Accuracy in Orbit

    NASA Technical Reports Server (NTRS)

    Wielicki, Bruce A.; Young, D. F.; Mlynczak, M. G.; Thome, K. J; Leroy, S.; Corliss, J.; Anderson, J. G.; Ao, C. O.; Bantges, R.; Best, F.; Bowman, K.; Brindley, H.; Butler, J. J.; Collins, W.; Dykema, J. A.; Doelling, D. R.; Feldman, D. R.; Fox, N.; Huang, X.; Holz, R.; Huang, Y.; Jennings, D.; Jin, Z.; Johnson, D. G.; Jucks, K.; Kato, S.; Kratz, D. P.; Liu, X.; Lukashin, C.; Mannucci, A. J.; Phojanamongkolkij, N.; Roithmayr, C. M.; Sandford, S.; Taylor, P. C.; Xiong, X.

    2013-01-01

    The Climate Absolute Radiance and Refractivity Observatory (CLARREO) mission will provide a calibration laboratory in orbit for the purpose of accurately measuring and attributing climate change. CLARREO measurements establish new climate change benchmarks with high absolute radiometric accuracy and high statistical confidence across a wide range of essential climate variables. CLARREO's inherently high absolute accuracy will be verified and traceable on orbit to Système Internationale (SI) units. The benchmarks established by CLARREO will be critical for assessing changes in the Earth system and climate model predictive capabilities for decades into the future as society works to meet the challenge of optimizing strategies for mitigating and adapting to climate change. The CLARREO benchmarks are derived from measurements of the Earth's thermal infrared spectrum (5-50 micron), the spectrum of solar radiation reflected by the Earth and its atmosphere (320-2300 nm), and radio occultation refractivity from which accurate temperature profiles are derived. The mission has the ability to provide new spectral fingerprints of climate change, as well as to provide the first orbiting radiometer with accuracy sufficient to serve as the reference transfer standard for other space sensors, in essence serving as a "NIST [National Institute of Standards and Technology] in orbit." CLARREO will greatly improve the accuracy and relevance of a wide range of space-borne instruments for decadal climate change. Finally, CLARREO has developed new metrics and methods for determining the accuracy requirements of climate observations for a wide range of climate variables and uncertainty sources. These methods should be useful for improving our understanding of observing requirements for most climate change observations.

  7. Nationwide forestry applications program. Analysis of forest classification accuracy

    NASA Technical Reports Server (NTRS)

    Congalton, R. G.; Mead, R. A.; Oderwald, R. G.; Heinen, J. (Principal Investigator)

    1981-01-01

    The development of LANDSAT classification accuracy assessment techniques, and of a computerized system for assessing wildlife habitat from land cover maps are considered. A literature review on accuracy assessment techniques and an explanation for the techniques development under both projects are included along with listings of the computer programs. The presentations and discussions at the National Working Conference on LANDSAT Classification Accuracy are summarized. Two symposium papers which were published on the results of this project are appended.

  8. 100% Classification Accuracy Considered Harmful: The Normalized Information Transfer Factor Explains the Accuracy Paradox

    PubMed Central

    Valverde-Albacete, Francisco J.; Peláez-Moreno, Carmen

    2014-01-01

    The most widely spread measure of performance, accuracy, suffers from a paradox: predictive models with a given level of accuracy may have greater predictive power than models with higher accuracy. Despite optimizing classification error rate, high accuracy models may fail to capture crucial information transfer in the classification task. We present evidence of this behavior by means of a combinatorial analysis where every possible contingency matrix of 2, 3 and 4 classes classifiers are depicted on the entropy triangle, a more reliable information-theoretic tool for classification assessment. Motivated by this, we develop from first principles a measure of classification performance that takes into consideration the information learned by classifiers. We are then able to obtain the entropy-modulated accuracy (EMA), a pessimistic estimate of the expected accuracy with the influence of the input distribution factored out, and the normalized information transfer factor (NIT), a measure of how efficient is the transmission of information from the input to the output set of classes. The EMA is a more natural measure of classification performance than accuracy when the heuristic to maximize is the transfer of information through the classifier instead of classification error count. The NIT factor measures the effectiveness of the learning process in classifiers and also makes it harder for them to “cheat” using techniques like specialization, while also promoting the interpretability of results. Their use is demonstrated in a mind reading task competition that aims at decoding the identity of a video stimulus based on magnetoencephalography recordings. We show how the EMA and the NIT factor reject rankings based in accuracy, choosing more meaningful and interpretable classifiers. PMID:24427282

  9. 100% classification accuracy considered harmful: the normalized information transfer factor explains the accuracy paradox.

    PubMed

    Valverde-Albacete, Francisco J; Peláez-Moreno, Carmen

    2014-01-01

    The most widely spread measure of performance, accuracy, suffers from a paradox: predictive models with a given level of accuracy may have greater predictive power than models with higher accuracy. Despite optimizing classification error rate, high accuracy models may fail to capture crucial information transfer in the classification task. We present evidence of this behavior by means of a combinatorial analysis where every possible contingency matrix of 2, 3 and 4 classes classifiers are depicted on the entropy triangle, a more reliable information-theoretic tool for classification assessment. Motivated by this, we develop from first principles a measure of classification performance that takes into consideration the information learned by classifiers. We are then able to obtain the entropy-modulated accuracy (EMA), a pessimistic estimate of the expected accuracy with the influence of the input distribution factored out, and the normalized information transfer factor (NIT), a measure of how efficient is the transmission of information from the input to the output set of classes. The EMA is a more natural measure of classification performance than accuracy when the heuristic to maximize is the transfer of information through the classifier instead of classification error count. The NIT factor measures the effectiveness of the learning process in classifiers and also makes it harder for them to "cheat" using techniques like specialization, while also promoting the interpretability of results. Their use is demonstrated in a mind reading task competition that aims at decoding the identity of a video stimulus based on magnetoencephalography recordings. We show how the EMA and the NIT factor reject rankings based in accuracy, choosing more meaningful and interpretable classifiers.

  10. Use of collateral information to improve LANDSAT classification accuracies

    NASA Technical Reports Server (NTRS)

    Strahler, A. H. (Principal Investigator)

    1981-01-01

    Methods to improve LANDSAT classification accuracies were investigated including: (1) the use of prior probabilities in maximum likelihood classification as a methodology to integrate discrete collateral data with continuously measured image density variables; (2) the use of the logit classifier as an alternative to multivariate normal classification that permits mixing both continuous and categorical variables in a single model and fits empirical distributions of observations more closely than the multivariate normal density function; and (3) the use of collateral data in a geographic information system as exercised to model a desired output information layer as a function of input layers of raster format collateral and image data base layers.

  11. An Evaluation of Item Response Theory Classification Accuracy and Consistency Indices

    ERIC Educational Resources Information Center

    Wyse, Adam E.; Hao, Shiqi

    2012-01-01

    This article introduces two new classification consistency indices that can be used when item response theory (IRT) models have been applied. The new indices are shown to be related to Rudner's classification accuracy index and Guo's classification accuracy index. The Rudner- and Guo-based classification accuracy and consistency indices are…

  12. The effect of atmospheric and topographic correction methods on land cover classification accuracy

    NASA Astrophysics Data System (ADS)

    Vanonckelen, Steven; Lhermitte, Stefaan; Van Rompaey, Anton

    2013-10-01

    Mapping of vegetation in mountain areas based on remote sensing is obstructed by atmospheric and topographic distortions. A variety of atmospheric and topographic correction methods has been proposed to minimize atmospheric and topographic effects and should in principle lead to a better land cover classification. Only a limited number of atmospheric and topographic combinations has been tested and the effect on class accuracy and on different illumination conditions is not yet researched extensively. The purpose of this study was to evaluate the effect of coupled correction methods on land cover classification accuracy. Therefore, all combinations of three atmospheric (no atmospheric correction, dark object subtraction and correction based on transmittance functions) and five topographic corrections (no topographic correction, band ratioing, cosine correction, pixel-based Minnaert and pixel-based C-correction) were applied on two acquisitions (2009 and 2010) of a Landsat image in the Romanian Carpathian mountains. The accuracies of the fifteen resulting land cover maps were evaluated statistically based on two validation sets: a random validation set and a validation subset containing pixels present in the difference area between the uncorrected classification and one of the fourteen corrected classifications. New insights into the differences in classification accuracy were obtained. First, results showed that all corrected images resulted in higher overall classification accuracies than the uncorrected images. The highest accuracy for the full validation set was achieved after combination of an atmospheric correction based on transmittance functions and a pixel-based Minnaert topographic correction. Secondly, class accuracies of especially the coniferous and mixed forest classes were enhanced after correction. There was only a minor improvement for the other land cover classes (broadleaved forest, bare soil, grass and water). This was explained by the position

  13. Impact of spatial resolution on correlation between segmentation evaluation metrics and forest classification accuracy

    NASA Astrophysics Data System (ADS)

    Švab Lenarčič, Andreja; Ritlop, Klemen; Äńurić, Nataša.; Čotar, Klemen; Oštir, Krištof

    2015-10-01

    Slovenia is one of the most forested countries in Europe. Its forest management authorities need information about the forest extent and state, as their responsibility lies in forest observation and preservation. Together with appropriate geographic information system mapping methods the remotely sensed data represent essential tool for an effective and sustainable forest management. Despite the large data availability, suitable mapping methods still present big challenge in terms of their speed which is often affected by the huge amount of data. The speed of the classification method could be maximised, if each of the steps in object-based classification was automated. However, automation is hard to achieve, since segmentation requires choosing optimum parameter values for optimal classification results. This paper focuses on the analysis of segmentation and classification performance and their correlation in a range of segmentation parameter values applied in the segmentation step. In order to find out which spatial resolution is still suitable for forest classification, forest classification accuracies obtained by using four images with different spatial resolutions were compared. Results of this study indicate that all high or very high spatial resolutions are suitable for optimal forest segmentation and classification, as long as appropriate scale and merge parameters combinations are used in the object-based classification. If computation interval includes all segmentation parameter combinations, all segmentation-classification correlations are spatial resolution independent and are generally high. If computation interval includes over- or optimal-segmentation parameter combinations, most segmentation-classification correlations are spatial resolution dependent.

  14. Evaluating Landsat classification accuracy from forest cover-type maps

    NASA Technical Reports Server (NTRS)

    Hudson, W. D.

    1987-01-01

    The use of complete enumeration in the form of photointerpreted forest cover-type maps to evaluate the accuracy of Landsat classifications was compared with assessments made directly from the aerial photography. A computerized, geographic information system was utilized to compare the Landsat classifications with the cover-type maps on a pixel-by-pixel basis. Error maps of pixels which were similarly misclassified by a variety of algorithms contained a larger number of errors than were verified from the aerial photography. For the two test sites studied, only 67 and 52 percent of the pixels which were originally considered to be in error were substantiated as being in error. Discrepancies between the two results were primarily caused by definitional differences between the cover-type maps and the Landsat classifications, especially with regard to minimum-type size and crown closure estimates of forest land.

  15. Classification accuracy of the wrist-worn GENEA accelerometer

    PubMed Central

    Welch, Whitney A.; Bassett, David R.; Thompson, Dixie L.; Freedson, Patty S.; Staudenmayer, John W.; John, Dinesh; Steeves, Jeremy A.; Conger, Scott A.; Ceaser, Tyrone; Howe, Cheryl A.; Sasaki, Jeffer E.; Fitzhugh, Eugene C.

    2013-01-01

    Purpose The purpose of this study was to determine whether the published left-wrist cut-points for the triaxial GENEA accelerometer, are accurate for predicting intensity categories during structured activity bouts. Methods A convenience sample of 130 adults wore a GENEA accelerometer on their left wrist while performing 14 different lifestyle activities. During each activity, oxygen consumption was continuously measured using the Oxycon mobile. Statistical analysis used Spearman's rank correlations to determine the relationship between measured and estimated intensity classifications. Cross tabulation tables were constructed to show under- or over-estimation of misclassified intensities. One-way chi-square tests were used to determine whether the intensity classification accuracy for each activity differed from 80%. Results For all activities the GENEA accelerometer-based physical activity monitor explained 41.1% of the variance in energy expenditure. The intensity classification accuracy was 69.8% for sedentary activities, 44.9% for light activities, 46.2% for moderate activities, and 77.7% for vigorous activities. The GENEA correctly classified intensity for 52.9% of observations when all activities were examined; this increased to 61.5% with stationary cycling removed. Conclusion A wrist-worn triaxial accelerometer has modest intensity classification accuracy across a broad range of activities, when using the cut-points of Esliger et al. Although the sensitivity and specificity are less than those reported by Esliger et al., they are generally in the same range as those reported for waist-worn, uniaxial accelerometer cut-points. PMID:23584403

  16. [Accuracy of apposition achieved by mandibular osteosyntheses. Stereophotogrammetric study].

    PubMed

    Randzio, J; Ficker, E; Wintges, T; Laser, S

    1989-01-01

    The accuracy of apposition achieved by wire and plate osteosyntheses is measured with the aid of close range stereophotogrammetry in the mandibles of dead bodies. Both osteosynthesis methods are characterized by an increase in the intercondylar distance which, on the average, is about 3.3 mm greater after plate osteosynthesis and about 1.9 mm after wiring. Moreover, osteosyntheses of the base of the mandible may involve a tendency of the condyle to become caudally dislocated.

  17. 3D imaging: how to achieve highest accuracy

    NASA Astrophysics Data System (ADS)

    Luhmann, Thomas

    2011-07-01

    The generation of 3D information from images is a key technology in many different areas, e.g. in 3D modeling and representation of architectural or heritage objects, in human body motion tracking and scanning, in 3D scene analysis of traffic scenes, in industrial applications and many more. The basic concepts rely on mathematical representations of central perspective viewing as they are widely known from photogrammetry or computer vision approaches. The objectives of these methods differ, more or less, from high precision and well-structured measurements in (industrial) photogrammetry to fully-automated non-structured applications in computer vision. Accuracy and precision is a critical issue for the 3D measurement of industrial, engineering or medical objects. As state of the art, photogrammetric multi-view measurements achieve relative precisions in the order of 1:100000 to 1:200000, and relative accuracies with respect to retraceable lengths in the order of 1:50000 to 1:100000 of the largest object diameter. In order to obtain these figures a number of influencing parameters have to be optimized. These are, besides others: physical representation of object surface (targets, texture), illumination and light sources, imaging sensors, cameras and lenses, calibration strategies (camera model), orientation strategies (bundle adjustment), image processing of homologue features (target measurement, stereo and multi-image matching), representation of object or workpiece coordinate systems and object scale. The paper discusses the above mentioned parameters and offers strategies for obtaining highest accuracy in object space. Practical examples of high-quality stereo camera measurements and multi-image applications are used to prove the relevance of high accuracy in different applications, ranging from medical navigation to static and dynamic industrial measurements. In addition, standards for accuracy verifications are presented and demonstrated by practical examples

  18. Combining sparseness and smoothness improves classification accuracy and interpretability.

    PubMed

    de Brecht, Matthew; Yamagishi, Noriko

    2012-04-02

    Sparse logistic regression (SLR) has been shown to be a useful method for decoding high-dimensional fMRI and MEG data by automatically selecting relevant feature dimensions. However, when applied to signals with high spatio-temporal correlations, SLR often over-prunes the feature space, which can result in overfitting and weight vectors that are difficult to interpret. To overcome this problem, we investigate a modification of ℓ₁-normed sparse logistic regression, called smooth sparse logistic regression (SSLR), which has a spatio-temporal "smoothing" prior that encourages weights that are close in time and space to have similar values. This causes the classifier to select spatio-temporally continuous groups of features, whereas SLR classifiers often select a scattered collection of independent features. We applied the method to both simulation data and real MEG data. We found that SSLR consistently increases classification accuracy, and produces weight vectors that are more meaningful from a neuroscientific perspective.

  19. Attribute-Level and Pattern-Level Classification Consistency and Accuracy Indices for Cognitive Diagnostic Assessment

    ERIC Educational Resources Information Center

    Wang, Wenyi; Song, Lihong; Chen, Ping; Meng, Yaru; Ding, Shuliang

    2015-01-01

    Classification consistency and accuracy are viewed as important indicators for evaluating the reliability and validity of classification results in cognitive diagnostic assessment (CDA). Pattern-level classification consistency and accuracy indices were introduced by Cui, Gierl, and Chang. However, the indices at the attribute level have not yet…

  20. Demographic corrections appear to compromise classification accuracy for severely skewed cognitive tests.

    PubMed

    O'Connell, Megan E; Tuokko, Holly; Kadlec, Helena

    2011-04-01

    Demographic corrections for cognitive tests should improve classification accuracy by reducing age or education biases, but empirical support has been equivocal. Using a simulation procedure, we show that creating moderate or extreme skewness in cognitive tests compromises the classification accuracy of demographic corrections, findings that appear replicated within clinical data for the few neuropsychological test scores with an extreme degree of skew. For most neuropsychological tests, the dementia classification accuracy of raw and demographically corrected scores was equivalent. These findings suggest that the dementia classification accuracy of demographic corrections is robust to slight degrees of skew (i.e., skewness <1.5).

  1. IMPACTS OF PATCH SIZE AND LANDSCAPE HETEROGENEITY ON THEMATIC IMAGE CLASSIFICATION ACCURACY

    EPA Science Inventory

    Impacts of Patch Size and Landscape Heterogeneity on Thematic Image Classification Accuracy.
    Currently, most thematic accuracy assessments of classified remotely sensed images oily account for errors between the various classes employed, at particular pixels of interest, thu...

  2. Classification Accuracy of Sequentially Administered WAIS-IV Short Forms.

    PubMed

    Ryan, Joseph J; Kreiner, David S; Gontkovsky, Samuel T; Glass Umfleet, Laura

    2015-01-01

    A Wechsler Adult Intelligence Scale-Fourth Edition (WAIS-IV) short form (SF) may be effective for ruling out subnormal intelligence. To create a useful SF, subtest administration should follow the order prescribed in the manual and, depending upon individual performance, be terminated after completion of 2, 3, 4, or 5 subtests. One hundred and twenty-two patients completed the WAIS-IV. In two analyses, Full-Scale IQs (FSIQs) ≤69 and ≤79 were classified as impairment. Classification accuracy statistics indicated that all SFs using both cutoff scores exceeded the base rate (i.e., 14% and 34%) of subnormal intelligence, with hit rates ranging from 84% to 95%. The FSIQ cutoff of ≤69 had poor sensitivity for detecting impaired intellectual functioning with the 2-, 3-, 4-, and 5-subtest SFs; specificity, positive predictive value (PPV), and negative predictive value (NPV) were excellent for each SF. With the FSIQ cutoff of ≤79, sensitivity was strong to excellent for the 3-, 4-, and 5-subtest SFs as were specificity, PPV, and NPV.

  3. Concurrent validity and classification accuracy of curriculum-based measurement for written expression.

    PubMed

    Furey, William M; Marcotte, Amanda M; Hintze, John M; Shackett, Caroline M

    2016-09-01

    The study presents a critical analysis of written expression curriculum-based measurement (WE-CBM) metrics derived from 3- and 10-min test lengths. Criterion validity and classification accuracy were examined for Total Words Written (TWW), Correct Writing Sequences (CWS), Percent Correct Writing Sequences (%CWS), and Correct Minus Incorrect Writing Sequences (CMIWS). Fourth grade students (n = 109) from 6 schools participated in the study. To assess criterion validity of each metric, total scores from writing tasks were correlated with the state achievement test's composition subtest. Each index investigated was moderately correlated with the subtest. Correlations increased with the longer sampling period, however they were not statistically significant. The accuracy at distinguishing between proficient and not proficient writers on the state assessment was analyzed for each index using discriminant function analysis and Receiver Operating Characteristic (ROC) curves. CWS and CMIWS, indices encompassing production and accuracy, were most accurate for predicting proficiency. Improvements were observed in classification accuracy with an increased sampling time. Utilizing cut scores to hold sensitivity above .90, specificity for each metric increased with longer probes. Sensitivity and specificity increased for all metrics with longer probes when using a 25th percentile cut. Visual analyses of ROC curves reveal where classification improvements were made. The 10-min sample for CWS more accurately identified at-risk students in the center of the distribution. Without measurement guiding decisions, writers in the middle of the distribution are more difficult to classify than those who clearly write well or struggle. The findings have implications for screening using WE-CBM. (PsycINFO Database Record

  4. Sampling issues affecting accuracy of likelihood-based classification using genetical data

    USGS Publications Warehouse

    Guinand, B.; Scribner, K.T.; Topchy, A.; Page, K.S.; Punch, W.; Burnham-Curtis, M. K.

    2004-01-01

    We demonstrate the effectiveness of a genetic algorithm for discovering multi-locus combinations that provide accurate individual assignment decisions and estimates of mixture composition based on likelihood classification. Using simulated data representing different levels of inter-population differentiation (Fst ~ 0.01 and 0.10), genetic diversities (four or eight alleles per locus), and population sizes (20, 40, 100 individuals in baseline populations), we show that subsets of loci can be identified that provide comparable levels of accuracy in classification decisions relative to entire multi-locus data sets, where 5, 10, or 20 loci were considered. Microsatellite data sets from hatchery strains of lake trout, Salvelinus namaycush, representing a comparable range of inter-population levels of differentiation in allele frequencies confirmed simulation results. For both simulated and empirical data sets, assignment accuracy was achieved using fewer loci (e.g., three or four loci out of eight for empirical lake trout studies). Simulation results were used to investigate properties of the 'leave-one-out' (L1O) method for estimating assignment error rates. Accuracy of population assignments based on L1O methods should be viewed with caution under certain conditions, particularly when baseline population sample sizes are low (<50).

  5. The Effects of Various Item Selection Methods on the Classification Accuracy and Classification Consistency of Criterion-Referenced Instruments.

    ERIC Educational Resources Information Center

    Smith, Douglas U.

    This study examined the effects of certain item selection methods on the classification accuracy and classification consistency of criterion-referenced instruments. Three item response data sets, representing varying situations of instructional effectiveness, were simulated. Five methods of item selection were then applied to each data set for the…

  6. ASSESSMENT OF LANDSCAPE CHARACTERISTICS ON THEMATIC IMAGE CLASSIFICATION ACCURACY

    EPA Science Inventory

    Landscape characteristics such as small patch size and land cover heterogeneity have been hypothesized to increase the likelihood of misclassifying pixels during thematic image classification. However, there has been a lack of empirical evidence, to support these hypotheses. This...

  7. Can segmentation evaluation metric be used as an indicator of land cover classification accuracy?

    NASA Astrophysics Data System (ADS)

    Švab Lenarčič, Andreja; Đurić, Nataša; Čotar, Klemen; Ritlop, Klemen; Oštir, Krištof

    2016-10-01

    It is a broadly established belief that the segmentation result significantly affects subsequent image classification accuracy. However, the actual correlation between the two has never been evaluated. Such an evaluation would be of considerable importance for any attempts to automate the object-based classification process, as it would reduce the amount of user intervention required to fine-tune the segmentation parameters. We conducted an assessment of segmentation and classification by analyzing 100 different segmentation parameter combinations, 3 classifiers, 5 land cover classes, 20 segmentation evaluation metrics, and 7 classification accuracy measures. The reliability definition of segmentation evaluation metrics as indicators of land cover classification accuracy was based on the linear correlation between the two. All unsupervised metrics that are not based on number of segments have a very strong correlation with all classification measures and are therefore reliable as indicators of land cover classification accuracy. On the other hand, correlation at supervised metrics is dependent on so many factors that it cannot be trusted as a reliable classification quality indicator. Algorithms for land cover classification studied in this paper are widely used; therefore, presented results are applicable to a wider area.

  8. Do you really understand? Achieving accuracy in interracial relationships.

    PubMed

    Holoien, Deborah Son; Bergsieker, Hilary B; Shelton, J Nicole; Alegre, Jan Marie

    2015-01-01

    Accurately perceiving whether interaction partners feel understood is important for developing intimate relationships and maintaining smooth interpersonal exchanges. During interracial interactions, when are Whites and racial minorities likely to accurately perceive how understood cross-race partners feel? We propose that participant race, desire to affiliate, and racial salience moderate accuracy in interracial interactions. Examination of cross-race roommates (Study 1) and interracial interactions with strangers (Study 2) revealed that when race is salient, Whites higher in desire to affiliate with racial minorities failed to accurately perceive the extent to which racial minority partners felt understood. Thus, although the desire to affiliate may appear beneficial, it may interfere with Whites' ability to accurately perceive how understood racial minorities feel. By contrast, racial minorities higher in desire to affiliate with Whites accurately perceived how understood White partners felt. Furthermore, participants' overestimation of how well they understood partners correlated negatively with partners' reports of relationship quality. Collectively, these findings indicate that racial salience and desire to affiliate moderate accurate perceptions of cross-race partners-even in the context of sustained interracial relationships-yielding divergent outcomes for Whites and racial minorities. (PsycINFO Database Record (c) 2015 APA, all rights reserved).

  9. Feature Selection Has a Large Impact on One-Class Classification Accuracy for MicroRNAs in Plants

    PubMed Central

    Yousef, Malik; Saçar Demirci, Müşerref Duygu; Khalifa, Waleed; Allmer, Jens

    2016-01-01

    MicroRNAs (miRNAs) are short RNA sequences involved in posttranscriptional gene regulation. Their experimental analysis is complicated and, therefore, needs to be supplemented with computational miRNA detection. Currently computational miRNA detection is mainly performed using machine learning and in particular two-class classification. For machine learning, the miRNAs need to be parametrized and more than 700 features have been described. Positive training examples for machine learning are readily available, but negative data is hard to come by. Therefore, it seems prerogative to use one-class classification instead of two-class classification. Previously, we were able to almost reach two-class classification accuracy using one-class classifiers. In this work, we employ feature selection procedures in conjunction with one-class classification and show that there is up to 36% difference in accuracy among these feature selection methods. The best feature set allowed the training of a one-class classifier which achieved an average accuracy of ~95.6% thereby outperforming previous two-class-based plant miRNA detection approaches by about 0.5%. We believe that this can be improved upon in the future by rigorous filtering of the positive training examples and by improving current feature clustering algorithms to better target pre-miRNA feature selection. PMID:27190509

  10. Optimal two-phase sampling design for comparing accuracies of two binary classification rules.

    PubMed

    Xu, Huiping; Hui, Siu L; Grannis, Shaun

    2014-02-10

    In this paper, we consider the design for comparing the performance of two binary classification rules, for example, two record linkage algorithms or two screening tests. Statistical methods are well developed for comparing these accuracy measures when the gold standard is available for every unit in the sample, or in a two-phase study when the gold standard is ascertained only in the second phase in a subsample using a fixed sampling scheme. However, these methods do not attempt to optimize the sampling scheme to minimize the variance of the estimators of interest. In comparing the performance of two classification rules, the parameters of primary interest are the difference in sensitivities, specificities, and positive predictive values. We derived the analytic variance formulas for these parameter estimates and used them to obtain the optimal sampling design. The efficiency of the optimal sampling design is evaluated through an empirical investigation that compares the optimal sampling with simple random sampling and with proportional allocation. Results of the empirical study show that the optimal sampling design is similar for estimating the difference in sensitivities and in specificities, and both achieve a substantial amount of variance reduction with an over-sample of subjects with discordant results and under-sample of subjects with concordant results. A heuristic rule is recommended when there is no prior knowledge of individual sensitivities and specificities, or the prevalence of the true positive findings in the study population. The optimal sampling is applied to a real-world example in record linkage to evaluate the difference in classification accuracy of two matching algorithms.

  11. Comparison of wheat classification accuracy using different classifiers of the image-100 system

    NASA Technical Reports Server (NTRS)

    Dejesusparada, N. (Principal Investigator); Chen, S. C.; Moreira, M. A.; Delima, A. M.

    1981-01-01

    Classification results using single-cell and multi-cell signature acquisition options, a point-by-point Gaussian maximum-likelihood classifier, and K-means clustering of the Image-100 system are presented. Conclusions reached are that: a better indication of correct classification can be provided by using a test area which contains various cover types of the study area; classification accuracy should be evaluated considering both the percentages of correct classification and error of commission; supervised classification approaches are better than K-means clustering; Gaussian distribution maximum likelihood classifier is better than Single-cell and Multi-cell Signature Acquisition Options of the Image-100 system; and in order to obtain a high classification accuracy in a large and heterogeneous crop area, using Gaussian maximum-likelihood classifier, homogeneous spectral subclasses of the study crop should be created to derive training statistics.

  12. Practical Issues in Estimating Classification Accuracy and Consistency with R Package cacIRT

    ERIC Educational Resources Information Center

    Lathrop, Quinn N.

    2015-01-01

    There are two main lines of research in estimating classification accuracy (CA) and classification consistency (CC) under Item Response Theory (IRT). The R package cacIRT provides computer implementations of both approaches in an accessible and unified framework. Even with available implementations, there remains decisions a researcher faces when…

  13. Does Maximizing Information at the Cut Score Always Maximize Classification Accuracy and Consistency?

    ERIC Educational Resources Information Center

    Wyse, Adam E.; Babcock, Ben

    2016-01-01

    A common suggestion made in the psychometric literature for fixed-length classification tests is that one should design tests so that they have maximum information at the cut score. Designing tests in this way is believed to maximize the classification accuracy and consistency of the assessment. This article uses simulated examples to illustrate…

  14. Forest Classification Accuracy as Influenced by Multispectral Scanner Spatial Resolution. [Sam Houston National Forest, Texas

    NASA Technical Reports Server (NTRS)

    Nalepka, R. F. (Principal Investigator); Sadowski, F. E.; Sarno, J. E.

    1976-01-01

    The author has identified the following significant results. A supervised classification within two separate ground areas of the Sam Houston National Forest was carried out for two sq meters spatial resolution MSS data. Data were progressively coarsened to simulate five additional cases of spatial resolution ranging up to 64 sq meters. Similar processing and analysis of all spatial resolutions enabled evaluations of the effect of spatial resolution on classification accuracy for various levels of detail and the effects on area proportion estimation for very general forest features. For very coarse resolutions, a subset of spectral channels which simulated the proposed thematic mapper channels was used to study classification accuracy.

  15. Effect of Pansharpened Image on Some of Pixel Based and Object Based Classification Accuracy

    NASA Astrophysics Data System (ADS)

    Karakus, P.; Karabork, H.

    2016-06-01

    Classification is the most important method to determine type of crop contained in a region for agricultural planning. There are two types of the classification. First is pixel based and the other is object based classification method. While pixel based classification methods are based on the information in each pixel, object based classification method is based on objects or image objects that formed by the combination of information from a set of similar pixels. Multispectral image contains a higher degree of spectral resolution than a panchromatic image. Panchromatic image have a higher spatial resolution than a multispectral image. Pan sharpening is a process of merging high spatial resolution panchromatic and high spectral resolution multispectral imagery to create a single high resolution color image. The aim of the study was to compare the potential classification accuracy provided by pan sharpened image. In this study, SPOT 5 image was used dated April 2013. 5m panchromatic image and 10m multispectral image are pan sharpened. Four different classification methods were investigated: maximum likelihood, decision tree, support vector machine at the pixel level and object based classification methods. SPOT 5 pan sharpened image was used to classification sun flowers and corn in a study site located at Kadirli region on Osmaniye in Turkey. The effects of pan sharpened image on classification results were also examined. Accuracy assessment showed that the object based classification resulted in the better overall accuracy values than the others. The results that indicate that these classification methods can be used for identifying sun flower and corn and estimating crop areas.

  16. The effect of spatial, spectral and radiometric factors on classification accuracy using thematic mapper data

    NASA Technical Reports Server (NTRS)

    Wrigley, R. C.; Acevedo, W.; Alexander, D.; Buis, J.; Card, D.

    1984-01-01

    An experiment of a factorial design was conducted to test the effects on classification accuracy of land cover types due to the improved spatial, spectral and radiometric characteristics of the Thematic Mapper (TM) in comparison to the Multispectral Scanner (MSS). High altitude aircraft scanner data from the Airborne Thematic Mapper instrument was acquired over central California in August, 1983 and used to simulate Thematic Mapper data as well as all combinations of the three characteristics for eight data sets in all. Results for the training sites (field center pixels) showed better classification accuracies for MSS spatial resolution, TM spectral bands and TM radiometry in order of importance.

  17. Evaluation of the contribution of LiDAR data and postclassification procedures to object-based classification accuracy

    NASA Astrophysics Data System (ADS)

    Styers, Diane M.; Moskal, L. Monika; Richardson, Jeffrey J.; Halabisky, Meghan A.

    2014-01-01

    Object-based image analysis (OBIA) is becoming an increasingly common method for producing land use/land cover (LULC) classifications in urban areas. In order to produce the most accurate LULC map, LiDAR data and postclassification procedures are often employed, but their relative contributions to accuracy are unclear. We examined the contribution of LiDAR data and postclassification procedures to increase classification accuracies over using imagery alone and assessed sources of error along an ecologically complex urban-to-rural gradient in Olympia, Washington. Overall classification accuracy and user's and producer's accuracies for individual classes were evaluated. The addition of LiDAR data to the OBIA classification resulted in an 8.34% increase in overall accuracy, while manual postclassification to the imagery+LiDAR classification improved accuracy only an additional 1%. Sources of error in this classification were largely due to edge effects, from which multiple different types of errors result.

  18. Effects of sample survey design on the accuracy of classification tree models in species distribution models

    USGS Publications Warehouse

    Edwards, T.C.; Cutler, D.R.; Zimmermann, N.E.; Geiser, L.; Moisen, G.G.

    2006-01-01

    We evaluated the effects of probabilistic (hereafter DESIGN) and non-probabilistic (PURPOSIVE) sample surveys on resultant classification tree models for predicting the presence of four lichen species in the Pacific Northwest, USA. Models derived from both survey forms were assessed using an independent data set (EVALUATION). Measures of accuracy as gauged by resubstitution rates were similar for each lichen species irrespective of the underlying sample survey form. Cross-validation estimates of prediction accuracies were lower than resubstitution accuracies for all species and both design types, and in all cases were closer to the true prediction accuracies based on the EVALUATION data set. We argue that greater emphasis should be placed on calculating and reporting cross-validation accuracy rates rather than simple resubstitution accuracy rates. Evaluation of the DESIGN and PURPOSIVE tree models on the EVALUATION data set shows significantly lower prediction accuracy for the PURPOSIVE tree models relative to the DESIGN models, indicating that non-probabilistic sample surveys may generate models with limited predictive capability. These differences were consistent across all four lichen species, with 11 of the 12 possible species and sample survey type comparisons having significantly lower accuracy rates. Some differences in accuracy were as large as 50%. The classification tree structures also differed considerably both among and within the modelled species, depending on the sample survey form. Overlap in the predictor variables selected by the DESIGN and PURPOSIVE tree models ranged from only 20% to 38%, indicating the classification trees fit the two evaluated survey forms on different sets of predictor variables. The magnitude of these differences in predictor variables throws doubt on ecological interpretation derived from prediction models based on non-probabilistic sample surveys. ?? 2006 Elsevier B.V. All rights reserved.

  19. Classification Accuracy of Brief Parent Report Measures of Language Development in Spanish-Speaking Toddlers

    ERIC Educational Resources Information Center

    Guiberson, Mark; Rodriguez, Barbara L.; Dale, Philip S.

    2011-01-01

    Purpose: The purpose of the current study was to examine the concurrent validity and classification accuracy of 3 parent report measures of language development in Spanish-speaking toddlers. Method: Forty-five Spanish-speaking parents and their 2-year-old children participated. Twenty-three children had expressive language delays (ELDs) as…

  20. Estimating the Consistency and Accuracy of Classifications Based on Test Scores.

    ERIC Educational Resources Information Center

    Livingston, Samuel A.; Lewis, Charles

    This paper presents a method for estimating the accuracy and consistency of classifications based on test scores. The scores can be produced by any scoring method, including the formation of a weighted composite. The estimates use data from a single form. The reliability of the score is used to estimate its effective test length in terms of…

  1. Factors Affecting the Item Parameter Estimation and Classification Accuracy of the DINA Model

    ERIC Educational Resources Information Center

    de la Torre, Jimmy; Hong, Yuan; Deng, Weiling

    2010-01-01

    To better understand the statistical properties of the deterministic inputs, noisy "and" gate cognitive diagnosis (DINA) model, the impact of several factors on the quality of the item parameter estimates and classification accuracy was investigated. Results of the simulation study indicate that the fully Bayes approach is most accurate when the…

  2. The Potential Impact of Not Being Able to Create Parallel Tests on Expected Classification Accuracy

    ERIC Educational Resources Information Center

    Wyse, Adam E.

    2011-01-01

    In many practical testing situations, alternate test forms from the same testing program are not strictly parallel to each other and instead the test forms exhibit small psychometric differences. This article investigates the potential practical impact that these small psychometric differences can have on expected classification accuracy. Ten…

  3. Examining the Classification Accuracy of a Vocabulary Screening Measure with Preschool Children

    ERIC Educational Resources Information Center

    Marcotte, Amanda M.; Clemens, Nathan H.; Parker, Christopher; Whitcomb, Sara A.

    2016-01-01

    This study investigated the classification accuracy of the "Dynamic Indicators of Vocabulary Skills" (DIVS) as a preschool vocabulary screening measure. With a sample of 240 preschoolers, fall and winter DIVS scores were used to predict year-end vocabulary risk using the 25th percentile on the "Peabody Picture Vocabulary Test--Third…

  4. Concurrent Validity and Classification Accuracy of Curriculum-Based Measurement for Written Expression

    ERIC Educational Resources Information Center

    Furey, William M.; Marcotte, Amanda M.; Hintze, John M.; Shackett, Caroline M.

    2016-01-01

    The study presents a critical analysis of written expression curriculum-based measurement (WE-CBM) metrics derived from 3- and 10-min test lengths. Criterion validity and classification accuracy were examined for Total Words Written (TWW), Correct Writing Sequences (CWS), Percent Correct Writing Sequences (%CWS), and Correct Minus Incorrect…

  5. Systematic Review: Classification Accuracy of Behavioral Screening Measures for Use in Integrated Primary Care Settings.

    PubMed

    Lavigne, John V; Meyers, Kathryn Mendelsohn; Feldman, Marissa

    2016-11-01

    OBJECTIVE : To examine the classification accuracy of measures of overall psychopathology recommended for pediatric primary care screening.  METHOD : A systematic review identified relevant instruments described in the literature. Subsequent systematic reviews identified studies of sensitivity (SE) and specificity (SP) of each measure for various cutoffs and different criteria for disorder (e.g., caseness determined by structured interview, exceeding a cutoff score, referral for psychiatric evaluation).  RESULTS : Measures include the Child Behavior Checklist (CBCL), Pediatric Symptom Checklist (PSC), Strengths and Difficulties Questionnaire (SDQ), Brief Infant-Toddler Social Emotional Assessment (BITSEA), and the Ages and Stages Questionnaire: Social-Emotional scale (ASQ:SE). For three measures (CBCL, PSC, and SDQ) studied extensively, achieving relatively high SE and SP values (≥ .70) simultaneously occurred in only 30-55% of the studies reviewed. There are relatively few studies of the ASQ:SE and BITSEA, or of relatively new measures.  DISCUSSION : Documented utility of these measures as screening instruments is limited.

  6. Predictive Utility and Classification Accuracy of Oral Reading Fluency and the Measures of Academic Progress for the Wisconsin Knowledge and Concepts Exam

    ERIC Educational Resources Information Center

    Ball, Carrie R.; O'Connor, Edward

    2016-01-01

    This study examined the predictive validity and classification accuracy of two commonly used universal screening measures relative to a statewide achievement test. Results indicated that second-grade performance on oral reading fluency and the Measures of Academic Progress (MAP), together with special education status, explained 68% of the…

  7. Combining atlas based segmentation and intensity classification with nearest neighbor transform and accuracy weighted vote.

    PubMed

    Sdika, Michaël

    2010-04-01

    In this paper, different methods to improve atlas based segmentation are presented. The first technique is a new mapping of the labels of an atlas consistent with a given intensity classification segmentation. This new mapping combines the two segmentations using the nearest neighbor transform and is especially effective for complex and folded regions like the cortex where the registration is difficult. Then, in a multi atlas context, an original weighting is introduced to combine the segmentation of several atlases using a voting procedure. This weighting is derived from statistical classification theory and is computed offline using the atlases as a training dataset. Concretely, the accuracy map of each atlas is computed and the vote is weighted by the accuracy of the atlases. Numerical experiments have been performed on publicly available in vivo datasets and show that, when used together, the two techniques provide an important improvement of the segmentation accuracy.

  8. Effects of autocorrelation upon LANDSAT classification accuracy. [Richmond, Virginia and Denver, Colorado

    NASA Technical Reports Server (NTRS)

    Craig, R. G. (Principal Investigator)

    1983-01-01

    Richmond, Virginia and Denver, Colorado were study sites in an effort to determine the effect of autocorrelation on the accuracy of a parallelopiped classifier of LANDSAT digital data. The autocorrelation was assumed to decay to insignificant levels when sampled at distances of at least ten pixels. Spectral themes developed using blocks of adjacent pixels, and using groups of pixels spaced at least 10 pixels apart were used. Effects of geometric distortions were minimized by using only pixels from the interiors of land cover sections. Accuracy was evaluated for three classes; agriculture, residential and "all other"; both type 1 and type 2 errors were evaluated by means of overall classification accuracy. All classes give comparable results. Accuracy is approximately the same in both techniques; however, the variance in accuracy is significantly higher using the themes developed from autocorrelated data. The vectors of mean spectral response were nearly identical regardless of sampling method used. The estimated variances were much larger when using autocorrelated pixels.

  9. Study on Increasing the Accuracy of Classification Based on Ant Colony algorithm

    NASA Astrophysics Data System (ADS)

    Yu, M.; Chen, D.-W.; Dai, C.-Y.; Li, Z.-L.

    2013-05-01

    The application for GIS advances the ability of data analysis on remote sensing image. The classification and distill of remote sensing image is the primary information source for GIS in LUCC application. How to increase the accuracy of classification is an important content of remote sensing research. Adding features and researching new classification methods are the ways to improve accuracy of classification. Ant colony algorithm based on mode framework defined, agents of the algorithms in nature-inspired computation field can show a kind of uniform intelligent computation mode. It is applied in remote sensing image classification is a new method of preliminary swarm intelligence. Studying the applicability of ant colony algorithm based on more features and exploring the advantages and performance of ant colony algorithm are provided with very important significance. The study takes the outskirts of Fuzhou with complicated land use in Fujian Province as study area. The multi-source database which contains the integration of spectral information (TM1-5, TM7, NDVI, NDBI) and topography characters (DEM, Slope, Aspect) and textural information (Mean, Variance, Homogeneity, Contrast, Dissimilarity, Entropy, Second Moment, Correlation) were built. Classification rules based different characters are discovered from the samples through ant colony algorithm and the classification test is performed based on these rules. At the same time, we compare with traditional maximum likelihood method, C4.5 algorithm and rough sets classifications for checking over the accuracies. The study showed that the accuracy of classification based on the ant colony algorithm is higher than other methods. In addition, the land use and cover changes in Fuzhou for the near term is studied and display the figures by using remote sensing technology based on ant colony algorithm. In addition, the land use and cover changes in Fuzhou for the near term is studied and display the figures by using

  10. Additional studies of forest classification accuracy as influenced by multispectral scanner spatial resolution

    NASA Technical Reports Server (NTRS)

    Sadowski, F. E.; Sarno, J. E.

    1976-01-01

    First, an analysis of forest feature signatures was used to help explain the large variation in classification accuracy that can occur among individual forest features for any one case of spatial resolution and the inconsistent changes in classification accuracy that were demonstrated among features as spatial resolution was degraded. Second, the classification rejection threshold was varied in an effort to reduce the large proportion of unclassified resolution elements that previously appeared in the processing of coarse resolution data when a constant rejection threshold was used for all cases of spatial resolution. For the signature analysis, two-channel ellipse plots showing the feature signature distributions for several cases of spatial resolution indicated that the capability of signatures to correctly identify their respective features is dependent on the amount of statistical overlap among signatures. Reductions in signature variance that occur in data of degraded spatial resolution may not necessarily decrease the amount of statistical overlap among signatures having large variance and small mean separations. Features classified by such signatures may thus continue to have similar amounts of misclassified elements in coarser resolution data, and thus, not necessarily improve in classification accuracy.

  11. Assessment of Classification Accuracies of SENTINEL-2 and LANDSAT-8 Data for Land Cover / Use Mapping

    NASA Astrophysics Data System (ADS)

    Hale Topaloğlu, Raziye; Sertel, Elif; Musaoğlu, Nebiye

    2016-06-01

    This study aims to compare classification accuracies of land cover/use maps created from Sentinel-2 and Landsat-8 data. Istanbul metropolitan city of Turkey, with a population of around 14 million, having different landscape characteristics was selected as study area. Water, forest, agricultural areas, grasslands, transport network, urban, airport- industrial units and barren land- mine land cover/use classes adapted from CORINE nomenclature were used as main land cover/use classes to identify. To fulfil the aims of this research, recently acquired dated 08/02/2016 Sentinel-2 and dated 22/02/2016 Landsat-8 images of Istanbul were obtained and image pre-processing steps like atmospheric and geometric correction were employed. Both Sentinel-2 and Landsat-8 images were resampled to 30m pixel size after geometric correction and similar spectral bands for both satellites were selected to create a similar base for these multi-sensor data. Maximum Likelihood (MLC) and Support Vector Machine (SVM) supervised classification methods were applied to both data sets to accurately identify eight different land cover/ use classes. Error matrix was created using same reference points for Sentinel-2 and Landsat-8 classifications. After the classification accuracy, results were compared to find out the best approach to create current land cover/use map of the region. The results of MLC and SVM classification methods were compared for both images.

  12. Investigation of the trade-off between time window length, classifier update rate and classification accuracy for restorative brain-computer interfaces.

    PubMed

    Darvishi, Sam; Ridding, Michael C; Abbott, Derek; Baumert, Mathias

    2013-01-01

    Recently, the application of restorative brain-computer interfaces (BCIs) has received significant interest in many BCI labs. However, there are a number of challenges, that need to be tackled to achieve efficient performance of such systems. For instance, any restorative BCI needs an optimum trade-off between time window length, classification accuracy and classifier update rate. In this study, we have investigated possible solutions to these problems by using a dataset provided by the University of Graz, Austria. We have used a continuous wavelet transform and the Student t-test for feature extraction and a support vector machine (SVM) for classification. We find that improved results, for restorative BCIs for rehabilitation, may be achieved by using a 750 milliseconds time window with an average classification accuracy of 67% that updates every 32 milliseconds.

  13. Bounds on achievable accuracy in analog optical linear-algebra processors

    NASA Astrophysics Data System (ADS)

    Batsell, Stephen G.; Walkup, John F.; Krile, Thomas F.

    1990-07-01

    Upper arid lower bounds on the number of bits of accuracy achievable are determined by applying a seconth-ortler statistical model to the linear algebra processor. The use of bounds was found necessary due to the strong signal-dependence of the noise at the output of the optical linear algebra processor (OLAP). 1 1. ACCURACY BOUNDS One of the limiting factors in applying OLAPs to real world problems has been the poor achievable accuracy of these processors. Little previous research has been done on determining noise sources from a systems perspective which would include noise generated in the multiplication ard addition operations spatial variations across arrays and crosstalk. We have previously examined these noise sources and determined a general model for the output noise mean and variance. The model demonstrates a strony signaldependency in the noise at the output of the processor which has been confirmed by our experiments. 1 We define accuracy similar to its definition for an analog signal input to an analog-to-digital (ND) converter. The number of bits of accuracy achievable is related to the log (base 2) of the number of separable levels at the P/D converter output. The number of separable levels is fouri by dividing the dynamic range by m times the standard deviation of the signal a. 2 Here m determines the error rate in the P/D conversion. The dynamic range can be expressed as the

  14. Developing an efficient technique for satellite image denoising and resolution enhancement for improving classification accuracy

    NASA Astrophysics Data System (ADS)

    Thangaswamy, Sree Sharmila; Kadarkarai, Ramar; Thangaswamy, Sree Renga Raja

    2013-01-01

    Satellite images are corrupted by noise during image acquisition and transmission. The removal of noise from the image by attenuating the high-frequency image components removes important details as well. In order to retain the useful information, improve the visual appearance, and accurately classify an image, an effective denoising technique is required. We discuss three important steps such as image denoising, resolution enhancement, and classification for improving accuracy in a noisy image. An effective denoising technique, hybrid directional lifting, is proposed to retain the important details of the images and improve visual appearance. The discrete wavelet transform based interpolation is developed for enhancing the resolution of the denoised image. The image is then classified using a support vector machine, which is superior to other neural network classifiers. The quantitative performance measures such as peak signal to noise ratio and classification accuracy show the significance of the proposed techniques.

  15. Biased binomial assessment of cross-validated estimation of classification accuracies illustrated in diagnosis predictions.

    PubMed

    Noirhomme, Quentin; Lesenfants, Damien; Gomez, Francisco; Soddu, Andrea; Schrouff, Jessica; Garraux, Gaëtan; Luxen, André; Phillips, Christophe; Laureys, Steven

    2014-01-01

    Multivariate classification is used in neuroimaging studies to infer brain activation or in medical applications to infer diagnosis. Their results are often assessed through either a binomial or a permutation test. Here, we simulated classification results of generated random data to assess the influence of the cross-validation scheme on the significance of results. Distributions built from classification of random data with cross-validation did not follow the binomial distribution. The binomial test is therefore not adapted. On the contrary, the permutation test was unaffected by the cross-validation scheme. The influence of the cross-validation was further illustrated on real-data from a brain-computer interface experiment in patients with disorders of consciousness and from an fMRI study on patients with Parkinson disease. Three out of 16 patients with disorders of consciousness had significant accuracy on binomial testing, but only one showed significant accuracy using permutation testing. In the fMRI experiment, the mental imagery of gait could discriminate significantly between idiopathic Parkinson's disease patients and healthy subjects according to the permutation test but not according to the binomial test. Hence, binomial testing could lead to biased estimation of significance and false positive or negative results. In our view, permutation testing is thus recommended for clinical application of classification with cross-validation.

  16. Improved reticle requalification accuracy and efficiency via simulation-powered automated defect classification

    NASA Astrophysics Data System (ADS)

    Paracha, Shazad; Eynon, Benjamin; Noyes, Ben F.; Nhiev, Anthony; Vacca, Anthony; Fiekowsky, Peter; Fiekowsky, Dan; Ham, Young Mog; Uzzel, Doug; Green, Michael; MacDonald, Susan; Morgan, John

    2014-04-01

    Advanced IC fabs must inspect critical reticles on a frequent basis to ensure high wafer yields. These necessary requalification inspections have traditionally carried high risk and expense. Manually reviewing sometimes hundreds of potentially yield-limiting detections is a very high-risk activity due to the likelihood of human error; the worst of which is the accidental passing of a real, yield-limiting defect. Painfully high cost is incurred as a result, but high cost is also realized on a daily basis while reticles are being manually classified on inspection tools since these tools often remain in a non-productive state during classification. An automatic defect analysis system (ADAS) has been implemented at a 20nm node wafer fab to automate reticle defect classification by simulating each defect's printability under the intended illumination conditions. In this paper, we have studied and present results showing the positive impact that an automated reticle defect classification system has on the reticle requalification process; specifically to defect classification speed and accuracy. To verify accuracy, detected defects of interest were analyzed with lithographic simulation software and compared to the results of both AIMS™ optical simulation and to actual wafer prints.

  17. A retrospective study to validate an intraoperative robotic classification system for assessing the accuracy of kirschner wire (K-wire) placements with postoperative computed tomography classification system for assessing the accuracy of pedicle screw placements.

    PubMed

    Tsai, Tai-Hsin; Wu, Dong-Syuan; Su, Yu-Feng; Wu, Chieh-Hsin; Lin, Chih-Lung

    2016-09-01

    This purpose of this retrospective study is validation of an intraoperative robotic grading classification system for assessing the accuracy of Kirschner-wire (K-wire) placements with the postoperative computed tomography (CT)-base classification system for assessing the accuracy of pedicle screw placements.We conducted a retrospective review of prospectively collected data from 35 consecutive patients who underwent 176 robotic assisted pedicle screws instrumentation at Kaohsiung Medical University Hospital from September 2014 to November 2015. During the operation, we used a robotic grading classification system for verifying the intraoperative accuracy of K-wire placements. Three months after surgery, we used the common CT-base classification system to assess the postoperative accuracy of pedicle screw placements. The distributions of accuracy between the intraoperative robot-assisted and various postoperative CT-based classification systems were compared using kappa statistics of agreement.The intraoperative accuracies of K-wire placements before and after repositioning were classified as excellent (131/176, 74.4% and 133/176, 75.6%, respectively), satisfactory (36/176, 20.5% and 41/176, 23.3%, respectively), and malpositioned (9/176, 5.1% and 2/176, 1.1%, respectively)In postoperative CT-base classification systems were evaluated. No screw placements were evaluated as unacceptable under any of these systems. Kappa statistics revealed no significant differences between the proposed system and the aforementioned classification systems (P <0.001).Our results revealed no significant differences between the intraoperative robotic grading system and various postoperative CT-based grading systems. The robotic grading classification system is a feasible method for evaluating the accuracy of K-wire placements. Using the intraoperative robot grading system to classify the accuracy of K-wire placements enables predicting the postoperative accuracy of pedicle screw

  18. Hyperspectral image preprocessing with bilateral filter for improving the classification accuracy of support vector machines

    NASA Astrophysics Data System (ADS)

    Sahadevan, Anand S.; Routray, Aurobinda; Das, Bhabani S.; Ahmad, Saquib

    2016-04-01

    Bilateral filter (BF) theory is applied to integrate spatial contextual information into the spectral domain for improving the accuracy of the support vector machine (SVM) classifier. The proposed classification framework is a two-stage process. First, an edge-preserved smoothing is carried out on a hyperspectral image (HSI). Then, the SVM multiclass classifier is applied on the smoothed HSI. One of the advantages of the BF-based implementation is that it considers the spatial as well as spectral closeness for smoothing the HSI. Therefore, the proposed method provides better smoothing in the homogeneous region and preserves the image details, which in turn improves the separability between the classes. The performance of the proposed method is tested using benchmark HSIs obtained from the airborne-visible-infrared-imaging-spectrometer (AVIRIS) and the reflective-optics-system-imaging-spectrometer (ROSIS) sensors. Experimental results demonstrate the effectiveness of the edge-preserved filtering in the classification of the HSI. Average accuracies (with 10% training samples) of the proposed classification framework are 99.04%, 98.11%, and 96.42% for AVIRIS-Salinas, ROSIS-Pavia University, and AVIRIS-Indian Pines images, respectively. Since the proposed method follows a combination of BF and the SVM formulations, it will be quite simple and practical to implement in real applications.

  19. Accuracy of supervised classification of cropland in sub-Saharan Africa

    NASA Astrophysics Data System (ADS)

    Lewis-Gonzales, S. L.; Nagle, N. N.; Grace, K.

    2013-12-01

    Identifying cropland is key to assessing food security hazards. Methods of identifying cropland usually fuse together readily available, but unclassified imagery, with labeled ground truth data from small training areas. We conduct a supervised classification of Landsat TM surface reflectance products for sub-Saharan Mali. Training data are provided by visual interpretation of high resolution (sub-meter) imagery. Due to the expense of acquiring and manually classifiying such data, it is infeasible to acquire many training samples. Thus, a crucial concern is determining the classification accuracy in regions where training data are sparse. We characterize this classification accuracy across the study region, as a function of geographic distance from training samples and as a function of landcover fragmentation. In regards to research involving food security and environmental deterioration crises, this method not only increases the overall scale at which a study can cover but also allows these assessments to take place in hostile and/or dangerous areas where food security and environmental crises are common.

  20. The Accuracy of Body Mass Index and Gallagher’s Classification in Detecting Obesity among Iranians

    PubMed Central

    Jahanlou, Alireza Shahab; Kouzekanani, Kamiar

    2016-01-01

    Background: The study was conducted to examine the comparability of the BMI and Gallagher’s classification in diagnosing obesity based on the cutoff points of the gold standards and to estimate suitable cutoff points for detecting obesity among Iranians. Methods: The cross-sectional study was comparative in nature. The sample consisted of 20,163 adults. The bioelectrical impedance analysis (BIA) was used to measure the variables of interest. Sensitivity, specificity, positive predictive power (PPV), and negative predictive power (NPV) were used to evaluate the comparability of the two classification methods in detecting obesity. Results: The BMI wrongly classified 29% of the obese persons as overweight. In both classifications, as age increased, the accuracy of detecting obesity decreased. The Gallagher’s classification is better than MBI in detecting obesity in men with the exception of those older than 59 years. In females, the BMI was better in determining sensitivity. In both classifications, either female or male, an increase in age was associated with a decrease in sensitivity and NPV with the exception of the BMI for the 18 year olds. Gallagher can correctly classify males and females who are less than 40 and 19 years old, respectively. Conclusion: Gallagher’s classification is recommended for non-obese in both sexes and in obese males younger than 40 years old. The BMI is recommended for obese females. The suitable cutoff points for the BMI to detect obesity are 27.70 kg/m2 for females and males, 27.70 kg/m2 for females, and 27.30 kg/m2 for males. PMID:27365550

  1. Classification Accuracy of Mixed Format Tests: A Bi-Factor Item Response Theory Approach

    PubMed Central

    Wang, Wei; Drasgow, Fritz; Liu, Liwen

    2016-01-01

    Mixed format tests (e.g., a test consisting of multiple-choice [MC] items and constructed response [CR] items) have become increasingly popular. However, the latent structure of item pools consisting of the two formats is still equivocal. Moreover, the implications of this latent structure are unclear: For example, do constructed response items tap reasoning skills that cannot be assessed with multiple choice items? This study explored the dimensionality of mixed format tests by applying bi-factor models to 10 tests of various subjects from the College Board's Advanced Placement (AP) Program and compared the accuracy of scores based on the bi-factor analysis with scores derived from a unidimensional analysis. More importantly, this study focused on a practical and important question—classification accuracy of the overall grade on a mixed format test. Our findings revealed that the degree of multidimensionality resulting from the mixed item format varied from subject to subject, depending on the disattenuated correlation between scores from MC and CR subtests. Moreover, remarkably small decrements in classification accuracy were found for the unidimensional analysis when the disattenuated correlations exceeded 0.90. PMID:26973568

  2. Bloodstain pattern classification: Accuracy, effect of contextual information and the role of analyst characteristics.

    PubMed

    Osborne, Nikola K P; Taylor, Michael C; Healey, Matthew; Zajac, Rachel

    2016-03-01

    It is becoming increasingly apparent that contextual information can exert a considerable influence on decisions about forensic evidence. Here, we explored accuracy and contextual influence in bloodstain pattern classification, and how these variables might relate to analyst characteristics. Thirty-nine bloodstain pattern analysts with varying degrees of experience each completed measures of compliance, decision-making style, and need for closure. Analysts then examined a bloodstain pattern without any additional contextual information, and allocated votes to listed pattern types according to favoured and less favoured classifications. Next, if they believed it would assist with their classification, analysts could request items of contextual information - from commonly encountered sources of information in bloodstain pattern analysis - and update their vote allocation. We calculated a shift score for each item of contextual information based on vote reallocation. Almost all forms of contextual information influenced decision-making, with medical findings leading to the highest shift scores. Although there was a small positive association between shift scores and the degree to which analysts displayed an intuitive decision-making style, shift scores did not vary meaningfully as a function of experience or the other characteristics measured. Almost all of the erroneous classifications were made by novice analysts.

  3. Evaluation of the accuracy and consistency of the Swedish environmental classification and information system for pharmaceuticals.

    PubMed

    Agerstrand, Marlene; Rudén, Christina

    2010-05-01

    The Swedish environmental and classification system for pharmaceuticals is a voluntary, industry-owned system with the purpose to provide environmental information about active pharmaceutical ingredients in the Swedish market. In this paper we report the results from a detailed evaluation of the accuracy and consistency of the risk assessments conducted within this system. The evaluation focused on the following three aspects: 1) comparison of the companies' risk assessments with the classification system's own guidance document, 2) how the risk assessments are affected if additional effect data is used, and 3) the consistency of different risk assessments for the same pharmaceutical substance. The analyses show that the system's guidance gives no criteria for when to consider a study "long-term" or "short-term", and that this confusion affected the outcome of the risk assessments in some cases. Furthermore, when the system's guidance document is followed and the risk assessment was supplemented with effect data from the open scientific literature, then the risk classification for a substantial number of the evaluated substances was altered. Our analyses also revealed that in some cases risk assessors disagree on the outcome of the assessment for the same active pharmaceutical ingredient. Finally we list some recommendations to improve the classification system. The recommendations include clarifying concepts and instructions in the guidance document, introduction of a standardized way of reporting data to the website, and promotion of use of non-standard test data when considered the most relevant.

  4. Effects of temporal variability in ground data collection on classification accuracy

    USGS Publications Warehouse

    Hoch, G.A.; Cully, J.F.

    1999-01-01

    This research tested whether the timing of ground data collection can significantly impact the accuracy of land cover classification. Ft. Riley Military Reservation, Kansas, USA was used to test this hypothesis. The U.S. Army's Land Condition Trend Analysis (LCTA) data annually collected at military bases was used to ground truth disturbance patterns. Ground data collected over an entire growing season and data collected one year after the imagery had a kappa statistic of 0.33. When using ground data from only within two weeks of image acquisition the kappa statistic improved to 0.55. Potential sources of this discrepancy are identified. These data demonstrate that there can be significant amounts of land cover change within a narrow time window on military reservations. To accurately conduct land cover classification at military reservations, ground data need to be collected in as narrow a window of time as possible and be closely synchronized with the date of the satellite imagery.

  5. Classification accuracy of multiple visual spatial measures in the detection of suspect effort.

    PubMed

    Whiteside, Douglas; Wald, Danielle; Busse, Michelle

    2011-02-01

    A wide variety of cognitive measures, particularly memory measures, have been studied for their ability to detect suspect effort, or biased responding on neuropsychological assessment instruments. However, visual spatial measures have received less attention. The purpose of this study was to evaluate the classification accuracy of several commonly used visual spatial measures, including the Judgment of Line Orientation Test, the Benton Facial Recognition Test, the Hooper Visual Organization Test, and the Rey Complex Figure Test-Copy and Recognition trials. Participants included 491 consecutive referrals who participated in a comprehensive neuropsychological assessment and met study criteria. Participants were divided into two groups identified as either unbiased responding (UR, N = 415) or biased responding (BR, N = 30) based on their performance on two measures of effort. The remaining participants (N = 46) had discrepant performance on the symptom validity measures and were excluded from further analysis. The groups differed significantly on all measures. Additionally, receiver operating characteristic (ROC) analysis indicated all of the measures had acceptable classification accuracy, but a measure combining scores from all of the measures had excellent classification accuracy. Results indicated that various cut-off scores on the measures could be used depending on the context of the evaluation. Suggested cut-off scores for the measures had sensitivity levels of approximately 32-46%, when specificity was at least 87%. When combined, the measures suggested cut-off scores had sensitivity increase to 57% while maintaining the same level of specificity (87%). The results were discussed in the context of research advocating the use of multiple measures of effort.

  6. Natural language processing with dynamic classification improves P300 speller accuracy and bit rate

    NASA Astrophysics Data System (ADS)

    Speier, William; Arnold, Corey; Lu, Jessica; Taira, Ricky K.; Pouratian, Nader

    2012-02-01

    The P300 speller is an example of a brain-computer interface that can restore functionality to victims of neuromuscular disorders. Although the most common application of this system has been communicating language, the properties and constraints of the linguistic domain have not to date been exploited when decoding brain signals that pertain to language. We hypothesized that combining the standard stepwise linear discriminant analysis with a Naive Bayes classifier and a trigram language model would increase the speed and accuracy of typing with the P300 speller. With integration of natural language processing, we observed significant improvements in accuracy and 40-60% increases in bit rate for all six subjects in a pilot study. This study suggests that integrating information about the linguistic domain can significantly improve signal classification.

  7. Adjusting for covariate effects on classification accuracy using the covariate-adjusted receiver operating characteristic curve.

    PubMed

    Janes, Holly; Pepe, Margaret S

    2009-06-01

    Recent scientific and technological innovations have produced an abundance of potential markers that are being investigated for their use in disease screening and diagnosis. In evaluating these markers, it is often necessary to account for covariates associated with the marker of interest. Covariates may include subject characteristics, expertise of the test operator, test procedures or aspects of specimen handling. In this paper, we propose the covariate-adjusted receiver operating characteristic curve, a measure of covariate-adjusted classification accuracy. Nonparametric and semiparametric estimators are proposed, asymptotic distribution theory is provided and finite sample performance is investigated. For illustration we characterize the age-adjusted discriminatory accuracy of prostate-specific antigen as a biomarker for prostate cancer.

  8. Accuracy assessment, using stratified plurality sampling, of portions of a LANDSAT classification of the Arctic National Wildlife Refuge Coastal Plain

    NASA Technical Reports Server (NTRS)

    Card, Don H.; Strong, Laurence L.

    1989-01-01

    An application of a classification accuracy assessment procedure is described for a vegetation and land cover map prepared by digital image processing of LANDSAT multispectral scanner data. A statistical sampling procedure called Stratified Plurality Sampling was used to assess the accuracy of portions of a map of the Arctic National Wildlife Refuge coastal plain. Results are tabulated as percent correct classification overall as well as per category with associated confidence intervals. Although values of percent correct were disappointingly low for most categories, the study was useful in highlighting sources of classification error and demonstrating shortcomings of the plurality sampling method.

  9. An improved multivariate analytical method to assess the accuracy of acoustic sediment classification maps.

    NASA Astrophysics Data System (ADS)

    Biondo, M.; Bartholomä, A.

    2014-12-01

    High resolution hydro acoustic methods have been successfully employed for the detailed classification of sedimentary habitats. The fine-scale mapping of very heterogeneous, patchy sedimentary facies, and the compound effect of multiple non-linear physical processes on the acoustic signal, cause the classification of backscatter images to be subject to a great level of uncertainty. Standard procedures for assessing the accuracy of acoustic classification maps are not yet established. This study applies different statistical techniques to automated classified acoustic images with the aim of i) quantifying the ability of backscatter to resolve grain size distributions ii) understanding complex patterns influenced by factors other than grain size variations iii) designing innovative repeatable statistical procedures to spatially assess classification uncertainties. A high-frequency (450 kHz) sidescan sonar survey, carried out in the year 2012 in the shallow upper-mesotidal inlet the Jade Bay (German North Sea), allowed to map 100 km2 of surficial sediment with a resolution and coverage never acquired before in the area. The backscatter mosaic was ground-truthed using a large dataset of sediment grab sample information (2009-2011). Multivariate procedures were employed for modelling the relationship between acoustic descriptors and granulometric variables in order to evaluate the correctness of acoustic classes allocation and sediment group separation. Complex patterns in the acoustic signal appeared to be controlled by the combined effect of surface roughness, sorting and mean grain size variations. The area is dominated by silt and fine sand in very mixed compositions; in this fine grained matrix, percentages of gravel resulted to be the prevailing factor affecting backscatter variability. In the absence of coarse material, sorting mostly affected the ability to detect gradual but significant changes in seabed types. Misclassification due to temporal discrepancies

  10. Reliability, Validity, and Classification Accuracy of the DSM-5 Diagnostic Criteria for Gambling Disorder and Comparison to DSM-IV.

    PubMed

    Stinchfield, Randy; McCready, John; Turner, Nigel E; Jimenez-Murcia, Susana; Petry, Nancy M; Grant, Jon; Welte, John; Chapman, Heather; Winters, Ken C

    2016-09-01

    The DSM-5 was published in 2013 and it included two substantive revisions for gambling disorder (GD). These changes are the reduction in the threshold from five to four criteria and elimination of the illegal activities criterion. The purpose of this study was to twofold. First, to assess the reliability, validity and classification accuracy of the DSM-5 diagnostic criteria for GD. Second, to compare the DSM-5-DSM-IV on reliability, validity, and classification accuracy, including an examination of the effect of the elimination of the illegal acts criterion on diagnostic accuracy. To compare DSM-5 and DSM-IV, eight datasets from three different countries (Canada, USA, and Spain; total N = 3247) were used. All datasets were based on similar research methods. Participants were recruited from outpatient gambling treatment services to represent the group with a GD and from the community to represent the group without a GD. All participants were administered a standardized measure of diagnostic criteria. The DSM-5 yielded satisfactory reliability, validity and classification accuracy. In comparing the DSM-5 to the DSM-IV, most comparisons of reliability, validity and classification accuracy showed more similarities than differences. There was evidence of modest improvements in classification accuracy for DSM-5 over DSM-IV, particularly in reduction of false negative errors. This reduction in false negative errors was largely a function of lowering the cut score from five to four and this revision is an improvement over DSM-IV. From a statistical standpoint, eliminating the illegal acts criterion did not make a significant impact on diagnostic accuracy. From a clinical standpoint, illegal acts can still be addressed in the context of the DSM-5 criterion of lying to others.

  11. A Comparative Investigation of Several Methods of Aiding College Freshmen to Achieve Grammatical Accuracy in Written Composition.

    ERIC Educational Resources Information Center

    Essary, William Howard

    Two problems were investigated in this study: (1) Which (if any) method of teaching freshmen composition is most effective in helping college students achieve grammatical accuracy? (2) Is improvement in grammatical accuracy paralleled or contrasted with improvement in content? Relatively weak students (low C high-school average and a mean SAT…

  12. Comparation of Typical Wetlands Classification Accuracy in Yellow River Estuary Using Multi-Angle Proba CHRIS Hyperspectral Remote Sensing Images

    NASA Astrophysics Data System (ADS)

    Wang, Xiaopeng; Zhang, Jie; Ma, Yi; Ren, Guangbo

    2013-01-01

    In this paper, Multi-angle PROBA CHRIS hyperspectral remote sensing images were used to study on their imaging quality and the ability of classification of Typical Wetlands in Yellow River Estuary, by the cooperation of interpretation and automatic classification. Taking 5-angle (0°, ±36°, ±55°) CHRIS hyperspectral remote sensing images of mode 2 obtained in September 2006 as an example, this paper research results indicate that the 0° image has the best imaging quality, with the highest spatial resolution, the ±36° images come second, the ±55° images are last; 5 typical wetlands, such as reservoir, bulrush, watercourse, barren beach and swamp were selected as study objects, then a Support Vector Machine (SVM) algorithm is used to classify different-angle remote sensing images into these 5 typical wetlands using training samples in the same location, the results of classification were analyzed based on field survey data, which shows that (1) The classification accuracy differs along the viewing angle of images, the overall accuracy and Kappa factor of the 0° image is highest, and the -36° image is lowest. (2) The overall accuracy and Kappa factor of the positive-angle images is higher than which of minus-angle images. (3) The producer accuracy and user accuracy of swamp is the lowest among all 5 typical wetlands in all images. (4) The producer accuracy and user accuracy of reservoir, bulrush and barren beach are relatively stable in all 5-angle images, however, the accuracies of Watercourse and swamp are fluctuant in all 5-angle images, and highest in the 0° image.

  13. Phase noise in pulsed Doppler lidar and limitations on achievable single-shot velocity accuracy

    NASA Technical Reports Server (NTRS)

    Mcnicholl, P.; Alejandro, S.

    1992-01-01

    The smaller sampling volumes afforded by Doppler lidars compared to radars allows for spatial resolutions at and below some sheer and turbulence wind structure scale sizes. This has brought new emphasis on achieving the optimum product of wind velocity and range resolutions. Several recent studies have considered the effects of amplitude noise, reduction algorithms, and possible hardware related signal artifacts on obtainable velocity accuracy. We discuss here the limitation on this accuracy resulting from the incoherent nature and finite temporal extent of backscatter from aerosols. For a lidar return from a hard (or slab) target, the phase of the intermediate frequency (IF) signal is random and the total return energy fluctuates from shot to shot due to speckle; however, the offset from the transmitted frequency is determinable with an accuracy subject only to instrumental effects and the signal to noise ratio (SNR), the noise being determined by the LO power in the shot noise limited regime. This is not the case for a return from a media extending over a range on the order of or greater than the spatial extent of the transmitted pulse, such as from atmospheric aerosols. In this case, the phase of the IF signal will exhibit a temporal random walk like behavior. It will be uncorrelated over times greater than the pulse duration as the transmitted pulse samples non-overlapping volumes of scattering centers. Frequency analysis of the IF signal in a window similar to the transmitted pulse envelope will therefore show shot-to-shot frequency deviations on the order of the inverse pulse duration reflecting the random phase rate variations. Like speckle, these deviations arise from the incoherent nature of the scattering process and diminish if the IF signal is averaged over times greater than a single range resolution cell (here the pulse duration). Apart from limiting the high SNR performance of a Doppler lidar, this shot-to-shot variance in velocity estimates has a

  14. The Wechsler Adult Intelligence Scale-III and Malingering in Traumatic Brain Injury: Classification Accuracy in Known Groups

    ERIC Educational Resources Information Center

    Curtis, Kelly L.; Greve, Kevin W.; Bianchini, Kevin J.

    2009-01-01

    A known-groups design was used to determine the classification accuracy of Wechsler Adult Intelligence Scale-III (WAIS-III) variables in detecting malingered neurocognitive dysfunction (MND) in traumatic brain injury (TBI). TBI patients were classified into the following groups: (a) mild TBI not-MND (n = 26), (b) mild TBI MND (n = 31), and (c)…

  15. Measurement Properties and Classification Accuracy of Two Spanish Parent Surveys of Language Development for Preschool-Age Children

    ERIC Educational Resources Information Center

    Guiberson, Mark; Rodriguez, Barbara L.

    2010-01-01

    Purpose: To describe the concurrent validity and classification accuracy of 2 Spanish parent surveys of language development, the Spanish Ages and Stages Questionnaire (ASQ; Squires, Potter, & Bricker, 1999) and the Pilot Inventario-III (Pilot INV-III; Guiberson, 2008a). Method: Forty-eight Spanish-speaking parents of preschool-age children…

  16. Pre-Processing Effect on the Accuracy of Event-Based Activity Segmentation and Classification through Inertial Sensors.

    PubMed

    Fida, Benish; Bernabucci, Ivan; Bibbo, Daniele; Conforto, Silvia; Schmid, Maurizio

    2015-09-11

    Inertial sensors are increasingly being used to recognize and classify physical activities in a variety of applications. For monitoring and fitness applications, it is crucial to develop methods able to segment each activity cycle, e.g., a gait cycle, so that the successive classification step may be more accurate. To increase detection accuracy, pre-processing is often used, with a concurrent increase in computational cost. In this paper, the effect of pre-processing operations on the detection and classification of locomotion activities was investigated, to check whether the presence of pre-processing significantly contributes to an increase in accuracy. The pre-processing stages evaluated in this study were inclination correction and de-noising. Level walking, step ascending, descending and running were monitored by using a shank-mounted inertial sensor. Raw and filtered segments, obtained from a modified version of a rule-based gait detection algorithm optimized for sequential processing, were processed to extract time and frequency-based features for physical activity classification through a support vector machine classifier. The proposed method accurately detected >99% gait cycles from raw data and produced >98% accuracy on these segmented gait cycles. Pre-processing did not substantially increase classification accuracy, thus highlighting the possibility of reducing the amount of pre-processing for real-time applications.

  17. Classification Accuracy of Oral Reading Fluency and Maze in Predicting Performance on Large-Scale Reading Assessments

    ERIC Educational Resources Information Center

    Decker, Dawn M.; Hixson, Michael D.; Shaw, Amber; Johnson, Gloria

    2014-01-01

    The purpose of this study was to examine whether using a multiple-measure framework yielded better classification accuracy than oral reading fluency (ORF) or maze alone in predicting pass/fail rates for middle-school students on a large-scale reading assessment. Participants were 178 students in Grades 7 and 8 from a Midwestern school district.…

  18. Post-transcriptional knowledge in pathway analysis increases the accuracy of phenotypes classification

    PubMed Central

    Alaimo, Salvatore; Giugno, Rosalba; Acunzo, Mario; Veneziano, Dario; Ferro, Alfredo; Pulvirenti, Alfredo

    2016-01-01

    Motivation Prediction of phenotypes from high-dimensional data is a crucial task in precision biology and medicine. Many technologies employ genomic biomarkers to characterize phenotypes. However, such elements are not sufficient to explain the underlying biology. To improve this, pathway analysis techniques have been proposed. Nevertheless, such methods have shown lack of accuracy in phenotypes classification. Results Here we propose a novel methodology called MITHrIL (Mirna enrIched paTHway Impact anaLysis) for the analysis of signaling pathways, which extends the work of Tarca et al., 2009. MITHrIL augments pathways with missing regulatory elements, such as microRNAs, and their interactions with genes. The method takes as input the expression values of genes and/or microRNAs and returns a list of pathways sorted according to their degree of deregulation, together with the corresponding statistical significance (p-values). Our analysis shows that MITHrIL outperforms its competitors even in the worst case. In addition, our method is able to correctly classify sets of tumor samples drawn from TCGA. Availability MITHrIL is freely available at the following URL: http://alpha.dmi.unict.it/mithril/ PMID:27275538

  19. A Comparative Accuracy Analysis of Classification Methods in Determination of Cultivated Lands with Spot 5 Satellite Imagery

    NASA Astrophysics Data System (ADS)

    kaya, S.; Alganci, U.; Sertel, E.; Ustundag, B.

    2013-12-01

    A Comparative Accuracy Analysis of Classification Methods in Determination of Cultivated Lands with Spot 5 Satellite Imagery Ugur ALGANCI1, Sinasi KAYA1,2, Elif SERTEL1,2,Berk USTUNDAG3 1 ITU, Center for Satellite Communication and Remote Sensing, 34469, Maslak-Istanbul,Turkey 2 ITU, Department of Geomatics, 34469, Maslak-Istanbul, Turkey 3 ITU, Agricultural and Environmental Informatics Research Center,34469, Maslak-Istanbul,Turkey alganci@itu.edu.tr, kayasina@itu.edu.tr, sertele@itu.edu.tr, berk@berk.tc ABSTRACT Cultivated land determination and their area estimation are important tasks for agricultural management. Derived information is mostly used in agricultural policies and precision agriculture, in specifically; yield estimation, irrigation and fertilization management and farmers declaration verification etc. The use of satellite image in crop type identification and area estimate is common for two decades due to its capability of monitoring large areas, rapid data acquisition and spectral response to crop properties. With launch of high and very high spatial resolution optical satellites in the last decade, such kind of analysis have gained importance as they provide information at big scale. With increasing spatial resolution of satellite images, image classification methods to derive the information form them have become important with increase of the spectral heterogeneity within land objects. In this research, pixel based classification with maximum likelihood algorithm and object based classification with nearest neighbor algorithm were applied to 2012 dated 2.5 m resolution SPOT 5 satellite images in order to investigate the accuracy of these methods in determination of cotton and corn planted lands and their area estimation. Study area was selected in Sanliurfa Province located on Southeastern Turkey that contributes to Turkey's agricultural production in a major way. Classification results were compared in terms of crop type identification using

  20. An improvement in land cover classification achieved by merging microwave data with Landsat multispectral scanner data

    NASA Technical Reports Server (NTRS)

    Wu, S. T.

    1980-01-01

    The improvement in land cover classification achieved by merging microwave data with Landsat MSS data is examined. To produce a merged data set for analysis and comparison, a registration procedure by which a set of Seasat SAR digital data was merged with the MSS data is described. The Landsat MSS data and the merged Landsat/Seasat data sets were processed using conventional multichannel spectral pattern recognition techniques. An analysis of the classified data sets indicates that while Landsat data delineate different forest types (i.e., deciduous/coniferous) and allow some species separation, SAR data provide additional information related to plant canopy configuration and vegetation density as associated with varying water regimes, and therefore allow for further subdivision in the classification of forested wetlands of the coastal region of the southern United States.

  1. Comparing the Classification Accuracy among Nonparametric, Parametric Discriminant Analysis and Logistic Regression Methods.

    ERIC Educational Resources Information Center

    Ferrer, Alvaro J. Arce; Wang, Lin

    This study compared the classification performance among parametric discriminant analysis, nonparametric discriminant analysis, and logistic regression in a two-group classification application. Field data from an organizational survey were analyzed and bootstrapped for additional exploration. The data were observed to depart from multivariate…

  2. Classification algorithms to improve the accuracy of identifying patients hospitalized with community-acquired pneumonia using administrative data.

    PubMed

    Yu, O; Nelson, J C; Bounds, L; Jackson, L A

    2011-09-01

    In epidemiological studies of community-acquired pneumonia (CAP) that utilize administrative data, cases are typically defined by the presence of a pneumonia hospital discharge diagnosis code. However, not all such hospitalizations represent true CAP cases. We identified 3991 hospitalizations during 1997-2005 in a managed care organization, and validated them as CAP or not by reviewing medical records. To improve the accuracy of CAP identification, classification algorithms that incorporated additional administrative information associated with the hospitalization were developed using the classification and regression tree analysis. We found that a pneumonia code designated as the primary discharge diagnosis and duration of hospital stay improved the classification of CAP hospitalizations. Compared to the commonly used method that is based on the presence of a primary discharge diagnosis code of pneumonia alone, these algorithms had higher sensitivity (81-98%) and positive predictive values (82-84%) with only modest decreases in specificity (48-82%) and negative predictive values (75-90%).

  3. Methods for improving accuracy and extending results beyond periods covered by traditional ground-truth in remote sensing classification of a complex landscape

    NASA Astrophysics Data System (ADS)

    Mueller-Warrant, George W.; Whittaker, Gerald W.; Banowetz, Gary M.; Griffith, Stephen M.; Barnhart, Bradley L.

    2015-06-01

    Successful development of approaches to quantify impacts of diverse landuse and associated agricultural management practices on ecosystem services is frequently limited by lack of historical and contemporary landuse data. We hypothesized that ground truth data from one year could be used to extrapolate previous or future landuse in a complex landscape where cropping systems do not generally change greatly from year to year because the majority of crops are established perennials or the same annual crops grown on the same fields over multiple years. Prior to testing this hypothesis, it was first necessary to classify 57 major landuses in the Willamette Valley of western Oregon from 2005 to 2011 using normal same year ground-truth, elaborating on previously published work and traditional sources such as Cropland Data Layers (CDL) to more fully include minor crops grown in the region. Available remote sensing data included Landsat, MODIS 16-day composites, and National Aerial Imagery Program (NAIP) imagery, all of which were resampled to a common 30 m resolution. The frequent presence of clouds and Landsat7 scan line gaps forced us to conduct of series of separate classifications in each year, which were then merged by choosing whichever classification used the highest number of cloud- and gap-free bands at any given pixel. Procedures adopted to improve accuracy beyond that achieved by maximum likelihood pixel classification included majority-rule reclassification of pixels within 91,442 Common Land Unit (CLU) polygons, smoothing and aggregation of areas outside the CLU polygons, and majority-rule reclassification over time of forest and urban development areas. Final classifications in all seven years separated annually disturbed agriculture, established perennial crops, forest, and urban development from each other at 90 to 95% overall 4-class validation accuracy. In the most successful use of subsequent year ground-truth data to classify prior year landuse, an

  4. Systematic classification of unseeded batch crystallization systems for achievable shape and size analysis

    NASA Astrophysics Data System (ADS)

    Acevedo, David; Nagy, Zoltan K.

    2014-05-01

    The purpose of the current work is to develop a systematic classification scheme for crystallization systems considering simultaneous size and shape variations, and to study the effect of temperature profiles on the achievable final shape of crystals for various crystallization systems. A classification method is proposed based on the simultaneous consideration of the effect of temperature profiles on nucleation and growth rates of two different characteristic crystal dimensions. Hence the approach provides direct indication of the extent in which crystal shape may be controlled for a particular system class by manipulating the supersaturation. A multidimensional population balance model (PBM) was implemented for unseeded crystallization processes of four different compounds. The effect between the nucleation and growth mechanisms on the final aspect ratio (AR) was investigated and it was shown that for nucleation dominated systems the AR is independent of the supersaturation profile. The simulation results confirmed experimentally also show that most crystallization systems tend to achieve an equilibrium shape hence the variation in the aspect ratio that can be achieved by manipulating the supersaturation is limited, in particular when nucleation is also taken into account as a competing phenomenon.

  5. Classification accuracy analysis of selected land use and land cover products in a portion of West-Central Lower Michigan

    NASA Astrophysics Data System (ADS)

    Ma, Kin Man

    2007-12-01

    Remote sensing satellites have been utilized to characterize and map land cover and its changes since the 1970s. However, uncertainties exist in almost all land use and land cover maps classified from remotely sensed images. In particular, it has been recognized that the spatial mis-registration of land cover maps can affect the true estimates of land use/land cover (LULC) changes. This dissertation addressed the following questions: what are the spatial patterns, magnitudes, and cover-dependencies of classification uncertainty associated with West-Central Lower Michigan's LULC products and how can the adverse effects of spatial misregistration on accuracy assessment be reduced? Two Michigan LULC products were chosen for comparison: 1998 Muskegon River Watershed (MRW) Michigan Resource Information Systems LULC map and a 2001 Integrated Forest Monitoring and Assessment Prescription Project (IFMAP). The 1m resolution 1998 MRW LULC map was derived from U.S. Geological Survey Digital Orthophoto Quarter Quadrangle (USGS DOQQs) color infrared imagery and was used as the reference map, since it has a thematic accuracy of 95%. The IFMAP LULC map was co-registered to a series of selected 1998 USGS DOQQs. The total combined root mean square error (rmse) distance of the georectified 2001 IFMAP was +/-12.20m. A spatial uncertainty buffer of at least 1.5 times the rmse was set at 20m so that polygon core areas would be unaffected by spatial misregistration noise. A new spatial misregistration buffer protocol (SPATIALM_ BUFFER) was developed to limit the effect of spatial misregistration on classification accuracy assessment. Spatial uncertainty buffer zones of 20m were generated around LULC polygons of both datasets. Eight-hundred seventeen (817) stratified random accuracy assessment points (AAPs) were generated across the 1998 MRW map. Classification accuracy and kappa statistics were generated for both the 817 AAPs and 604 AAPs comparisons. For the 817 AAPs comparison, the

  6. The Effects of Individual or Group Guidelines on the Calibration Accuracy and Achievement of High School Biology Students

    ERIC Educational Resources Information Center

    Bol, Linda; Hacker, Douglas J.; Walck, Camilla C.; Nunnery, John A.

    2012-01-01

    A 2 x 2 factorial design was employed in a quasi-experiment to investigate the effects of guidelines in group or individual settings on the calibration accuracy and achievement of 82 high school biology students. Significant main effects indicated that calibration practice with guidelines and practice in group settings increased prediction and…

  7. Classification and Accuracy Assessment for Coarse Resolution Mapping within the Great Lakes Basin, USA

    EPA Science Inventory

    This study applied a phenology-based land-cover classification approach across the Laurentian Great Lakes Basin (GLB) using time-series data consisting of 23 Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) composite images (250 ...

  8. Accuracy of Teachers' Judgments of Students' Academic Achievement: A Meta-Analysis

    ERIC Educational Resources Information Center

    Sudkamp, Anna; Kaiser, Johanna; Moller, Jens

    2012-01-01

    This meta-analysis summarizes empirical results on the correspondence between teachers' judgments of students' academic achievement and students' actual academic achievement. The article further investigates theoretically and methodologically relevant moderators of the correlation between the two measures. Overall, 75 studies reporting…

  9. Dysregulation of innate and adaptive serum mediators precedes systemic lupus erythematosus classification and improves prognostic accuracy of autoantibodies.

    PubMed

    Lu, Rufei; Munroe, Melissa E; Guthridge, Joel M; Bean, Krista M; Fife, Dustin A; Chen, Hua; Slight-Webb, Samantha R; Keith, Michael P; Harley, John B; James, Judith A

    2016-11-01

    Systemic lupus erythematosus (SLE) is a complex autoimmune disease with a poorly understood preclinical stage of immune dysregulation and symptom accrual. Accumulation of antinuclear autoantibody (ANA) specificities is a hallmark of impending clinical disease. Yet, many ANA-positive individuals remain healthy, suggesting that additional immune dysregulation underlies SLE pathogenesis. Indeed, we have recently demonstrated that interferon (IFN) pathways are dysregulated in preclinical SLE. To determine if other forms of immune dysregulation contribute to preclinical SLE pathogenesis, we measured SLE-associated autoantibodies and soluble mediators in samples from 84 individuals collected prior to SLE classification (average timespan = 5.98 years), compared to unaffected, healthy control samples matched by race, gender, age (±5 years), and time of sample procurement. We found that multiple soluble mediators, including interleukin (IL)-5, IL-6, and IFN-γ, were significantly elevated in cases compared to controls more than 3.5 years pre-classification, prior to or concurrent with autoantibody positivity. Additional mediators, including innate cytokines, IFN-associated chemokines, and soluble tumor necrosis factor (TNF) superfamily mediators increased longitudinally in cases approaching SLE classification, but not in controls. In particular, levels of B lymphocyte stimulator (BLyS) and a proliferation-inducing ligand (APRIL) were comparable in cases and controls until less than 10 months pre-classification. Over the entire pre-classification period, random forest models incorporating ANA and anti-Ro/SSA positivity with levels of IL-5, IL-6, and the IFN-γ-induced chemokine, MIG, distinguished future SLE patients with 92% (±1.8%) accuracy, compared to 78% accuracy utilizing ANA positivity alone. These data suggest that immune dysregulation involving multiple pathways contributes to SLE pathogenesis. Importantly, distinct immunological profiles are predictive for

  10. Effect of radiance-to-reflectance transformation and atmosphere removal on maximum likelihood classification accuracy of high-dimensional remote sensing data

    NASA Technical Reports Server (NTRS)

    Hoffbeck, Joseph P.; Landgrebe, David A.

    1994-01-01

    Many analysis algorithms for high-dimensional remote sensing data require that the remotely sensed radiance spectra be transformed to approximate reflectance to allow comparison with a library of laboratory reflectance spectra. In maximum likelihood classification, however, the remotely sensed spectra are compared to training samples, thus a transformation to reflectance may or may not be helpful. The effect of several radiance-to-reflectance transformations on maximum likelihood classification accuracy is investigated in this paper. We show that the empirical line approach, LOWTRAN7, flat-field correction, single spectrum method, and internal average reflectance are all non-singular affine transformations, and that non-singular affine transformations have no effect on discriminant analysis feature extraction and maximum likelihood classification accuracy. (An affine transformation is a linear transformation with an optional offset.) Since the Atmosphere Removal Program (ATREM) and the log residue method are not affine transformations, experiments with Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data were conducted to determine the effect of these transformations on maximum likelihood classification accuracy. The average classification accuracy of the data transformed by ATREM and the log residue method was slightly less than the accuracy of the original radiance data. Since the radiance-to-reflectance transformations allow direct comparison of remotely sensed spectra with laboratory reflectance spectra, they can be quite useful in labeling the training samples required by maximum likelihood classification, but these transformations have only a slight effect or no effect at all on discriminant analysis and maximum likelihood classification accuracy.

  11. Accurate rotational constants for linear interstellar carbon chains: achieving experimental accuracy

    NASA Astrophysics Data System (ADS)

    Etim, Emmanuel E.; Arunan, Elangannan

    2017-01-01

    Linear carbon chain molecular species remain the dominant theme in interstellar chemistry. Their continuous astronomical observation depends on the availability of accurate spectroscopic parameters. Accurate rotational constants are reported for hundreds of molecular species of astrophysical, spectroscopy and chemical interests from the different linear carbon chains; C_{{n}}H, C_{{n}}H-, C_{{n}}N, C_{{n}}N-, C_{{n}}O, C_{{n}}S, HC_{{n}}S, C_{{n}}Si, CH3(CC)_{{n}}H, HC_{{n}}N, DC_{2{n}+1}N, HC_{2{n}}NC, and CH3(C≡C)_{{n}}CN using three to four moments of inertia calculated from the experimental rotational constants coupled with those obtained from the optimized geometries at the Hartree Fock level. The calculated rotational constants are obtained from the corrected moments of inertia at the Hartfree Fock geometries. The calculated rotational constants show accuracy of few kHz below irrespective of the chain length and terminating groups. The obtained accuracy of few kHz places these rotational constants as excellent tools for both astronomical and laboratory detection of these molecular species of astrophysical interest. From the numerous unidentified lines from different astronomical surveys, transitions corresponding to known and new linear carbon chains could be found using these rotational constants. The astrophysical, spectroscopic and chemical implications of these results are discussed.

  12. Improving supervised classification accuracy using non-rigid multimodal image registration: detecting prostate cancer

    NASA Astrophysics Data System (ADS)

    Chappelow, Jonathan; Viswanath, Satish; Monaco, James; Rosen, Mark; Tomaszewski, John; Feldman, Michael; Madabhushi, Anant

    2008-03-01

    Computer-aided diagnosis (CAD) systems for the detection of cancer in medical images require precise labeling of training data. For magnetic resonance (MR) imaging (MRI) of the prostate, training labels define the spatial extent of prostate cancer (CaP); the most common source for these labels is expert segmentations. When ancillary data such as whole mount histology (WMH) sections, which provide the gold standard for cancer ground truth, are available, the manual labeling of CaP can be improved by referencing WMH. However, manual segmentation is error prone, time consuming and not reproducible. Therefore, we present the use of multimodal image registration to automatically and accurately transcribe CaP from histology onto MRI following alignment of the two modalities, in order to improve the quality of training data and hence classifier performance. We quantitatively demonstrate the superiority of this registration-based methodology by comparing its results to the manual CaP annotation of expert radiologists. Five supervised CAD classifiers were trained using the labels for CaP extent on MRI obtained by the expert and 4 different registration techniques. Two of the registration methods were affi;ne schemes; one based on maximization of mutual information (MI) and the other method that we previously developed, Combined Feature Ensemble Mutual Information (COFEMI), which incorporates high-order statistical features for robust multimodal registration. Two non-rigid schemes were obtained by succeeding the two affine registration methods with an elastic deformation step using thin-plate splines (TPS). In the absence of definitive ground truth for CaP extent on MRI, classifier accuracy was evaluated against 7 ground truth surrogates obtained by different combinations of the expert and registration segmentations. For 26 multimodal MRI-WMH image pairs, all four registration methods produced a higher area under the receiver operating characteristic curve compared to that

  13. IMPACTS OF PATCH SIZE AND LAND COVER HETEROGENEITY ON THEMATIC IMAGE CLASSIFICATION ACCURACY

    EPA Science Inventory


    Landscape characteristics such as small patch size and land cover heterogeneity have been hypothesized to increase the likelihood of miss-classifying pixels during thematic image classification. However, there has been a lack of empirical evidence to support these hypotheses,...

  14. The impact of catchment source group classification on the accuracy of sediment fingerprinting outputs.

    PubMed

    Pulley, Simon; Foster, Ian; Collins, Adrian L

    2016-05-05

    The objective classification of sediment source groups is at present an under-investigated aspect of source tracing studies, which has the potential to statistically improve discrimination between sediment sources and reduce uncertainty. This paper investigates this potential using three different source group classification schemes. The first classification scheme was simple surface and subsurface groupings (Scheme 1). The tracer signatures were then used in a two-step cluster analysis to identify the sediment source groupings naturally defined by the tracer signatures (Scheme 2). The cluster source groups were then modified by splitting each one into a surface and subsurface component to suit catchment management goals (Scheme 3). The schemes were tested using artificial mixtures of sediment source samples. Controlled corruptions were made to some of the mixtures to mimic the potential causes of tracer non-conservatism present when using tracers in natural fluvial environments. It was determined how accurately the known proportions of sediment sources in the mixtures were identified after unmixing modelling using the three classification schemes. The cluster analysis derived source groups (2) significantly increased tracer variability ratios (inter-/intra-source group variability) (up to 2122%, median 194%) compared to the surface and subsurface groupings (1). As a result, the composition of the artificial mixtures was identified an average of 9.8% more accurately on the 0-100% contribution scale. It was found that the cluster groups could be reclassified into a surface and subsurface component (3) with no significant increase in composite uncertainty (a 0.1% increase over Scheme 2). The far smaller effects of simulated tracer non-conservatism for the cluster analysis based schemes (2 and 3) was primarily attributed to the increased inter-group variability producing a far larger sediment source signal that the non-conservatism noise (1). Modified cluster analysis

  15. Multispectral imaging burn wound tissue classification system: a comparison of test accuracies between several common machine learning algorithms

    NASA Astrophysics Data System (ADS)

    Squiers, John J.; Li, Weizhi; King, Darlene R.; Mo, Weirong; Zhang, Xu; Lu, Yang; Sellke, Eric W.; Fan, Wensheng; DiMaio, J. Michael; Thatcher, Jeffrey E.

    2016-03-01

    The clinical judgment of expert burn surgeons is currently the standard on which diagnostic and therapeutic decisionmaking regarding burn injuries is based. Multispectral imaging (MSI) has the potential to increase the accuracy of burn depth assessment and the intraoperative identification of viable wound bed during surgical debridement of burn injuries. A highly accurate classification model must be developed using machine-learning techniques in order to translate MSI data into clinically-relevant information. An animal burn model was developed to build an MSI training database and to study the burn tissue classification ability of several models trained via common machine-learning algorithms. The algorithms tested, from least to most complex, were: K-nearest neighbors (KNN), decision tree (DT), linear discriminant analysis (LDA), weighted linear discriminant analysis (W-LDA), quadratic discriminant analysis (QDA), ensemble linear discriminant analysis (EN-LDA), ensemble K-nearest neighbors (EN-KNN), and ensemble decision tree (EN-DT). After the ground-truth database of six tissue types (healthy skin, wound bed, blood, hyperemia, partial injury, full injury) was generated by histopathological analysis, we used 10-fold cross validation to compare the algorithms' performances based on their accuracies in classifying data against the ground truth, and each algorithm was tested 100 times. The mean test accuracy of the algorithms were KNN 68.3%, DT 61.5%, LDA 70.5%, W-LDA 68.1%, QDA 68.9%, EN-LDA 56.8%, EN-KNN 49.7%, and EN-DT 36.5%. LDA had the highest test accuracy, reflecting the bias-variance tradeoff over the range of complexities inherent to the algorithms tested. Several algorithms were able to match the current standard in burn tissue classification, the clinical judgment of expert burn surgeons. These results will guide further development of an MSI burn tissue classification system. Given that there are few surgeons and facilities specializing in burn care

  16. Effects of change in FreeSurfer version on classification accuracy of patients with Alzheimer's disease and mild cognitive impairment.

    PubMed

    Chepkoech, Joy-Loi; Walhovd, Kristine B; Grydeland, Håkon; Fjell, Anders M

    2016-05-01

    Studies have found non-negligible differences in cortical thickness estimates across versions of software that are used for processing and quantifying MRI-based cortical measurements, and issues have arisen regarding these differences, as obtained estimates could potentially affect the validity of the results. However, more critical for diagnostic classification than absolute thickness estimates across versions is the inter-subject stability. We aimed to investigate the effect of change in software version on classification of older persons in groups of healthy, mild cognitive impairment and Alzheimer's Disease. Using MRI samples of 100 older normal controls, 100 with mild cognitive impairment and 100 Alzheimer's Disease patients obtained from the Alzheimer's Disease Neuroimaging Initiative database, we performed a standard reconstruction processing using the FreeSurfer image analysis suite versions 4.1.0, 4.5.0 and 5.1.0. Pair-wise comparisons of cortical thickness between FreeSurfer versions revealed significant differences, ranging from 1.6% (4.1.0 vs. 4.5.0) to 5.8% (4.1.0 vs. 5.1.0) across the cortical mantle. However, change of version had very little effect on detectable differences in cortical thickness between diagnostic groups, and there were little differences in accuracy between versions when using entorhinal thickness for diagnostic classification. This lead us to conclude that differences in absolute thickness estimates across software versions in this case did not imply lacking validity, that classification results appeared reliable across software versions, and that classification results obtained in studies using different FreeSurfer versions can be reliably compared. Hum Brain Mapp 37:1831-1841, 2016. © 2016 Wiley Periodicals, Inc.

  17. Optimizing statistical classification accuracy of satellite remotely sensed imagery for supporting fast flood hydrological analysis

    NASA Astrophysics Data System (ADS)

    Alexakis, Dimitrios; Agapiou, Athos; Hadjimitsis, Diofantos; Retalis, Adrianos

    2012-06-01

    The aim of this study is to improve classification results of multispectral satellite imagery for supporting flood risk assessment analysis in a catchment area in Cyprus. For this purpose, precipitation and ground spectroradiometric data have been collected and analyzed with innovative statistical analysis methods. Samples of regolith and construction material were in situ collected and examined in the spectroscopy laboratory for their spectral response under consecutive different conditions of humidity. Moreover, reflectance values were extracted from the same targets using Landsat TM/ETM+ images, for drought and humid time periods, using archived meteorological data. The comparison of the results showed that spectral responses for all the specimens were less correlated in cases of substantial humidity, both in laboratory and satellite images. These results were validated with the application of different classification algorithms (ISODATA, maximum likelihood, object based, maximum entropy) to satellite images acquired during time period when precipitation phenomena had been recorded.

  18. Improving ECG Classification Accuracy Using an Ensemble of Neural Network Modules

    PubMed Central

    Javadi, Mehrdad; Ebrahimpour, Reza; Sajedin, Atena; Faridi, Soheil; Zakernejad, Shokoufeh

    2011-01-01

    This paper illustrates the use of a combined neural network model based on Stacked Generalization method for classification of electrocardiogram (ECG) beats. In conventional Stacked Generalization method, the combiner learns to map the base classifiers' outputs to the target data. We claim adding the input pattern to the base classifiers' outputs helps the combiner to obtain knowledge about the input space and as the result, performs better on the same task. Experimental results support our claim that the additional knowledge according to the input space, improves the performance of the proposed method which is called Modified Stacked Generalization. In particular, for classification of 14966 ECG beats that were not previously seen during training phase, the Modified Stacked Generalization method reduced the error rate for 12.41% in comparison with the best of ten popular classifier fusion methods including Max, Min, Average, Product, Majority Voting, Borda Count, Decision Templates, Weighted Averaging based on Particle Swarm Optimization and Stacked Generalization. PMID:22046232

  19. Absolute Radiometric Calibration of ALS Intensity Data: Effects on Accuracy and Target Classification

    PubMed Central

    Kaasalainen, Sanna; Pyysalo, Ulla; Krooks, Anssi; Vain, Ants; Kukko, Antero; Hyyppä, Juha; Kaasalainen, Mikko

    2011-01-01

    Radiometric calibration of airborne laser scanning (ALS) intensity data aims at retrieving a value related to the target scattering properties, which is independent on the instrument or flight parameters. The aim of a calibration procedure is also to be able to compare results from different flights and instruments, but practical applications are sparsely available, and the performance of calibration methods for this purpose needs to be further assessed. We have studied the radiometric calibration with data from three separate flights and two different instruments using external calibration targets. We find that the intensity data from different flights and instruments can be compared to each other only after a radiometric calibration process using separate calibration targets carefully selected for each flight. The calibration is also necessary for target classification purposes, such as separating vegetation from sand using intensity data from different flights. The classification results are meaningful only for calibrated intensity data. PMID:22346660

  20. Classification accuracy of algorithms for blood chemistry data for three aquaculture-affected marine fish species.

    PubMed

    Coz-Rakovac, R; Topic Popovic, N; Smuc, T; Strunjak-Perovic, I; Jadan, M

    2009-11-01

    The objective of this study was determination and discrimination of biochemical data among three aquaculture-affected marine fish species (sea bass, Dicentrarchus labrax; sea bream, Sparus aurata L., and mullet, Mugil spp.) based on machine-learning methods. The approach relying on machine-learning methods gives more usable classification solutions and provides better insight into the collected data. So far, these new methods have been applied to the problem of discrimination of blood chemistry data with respect to season and feed of a single species. This is the first time these classification algorithms have been used as a framework for rapid differentiation among three fish species. Among the machine-learning methods used, decision trees provided the clearest model, which correctly classified 210 samples or 85.71%, and incorrectly classified 35 samples or 14.29% and clearly identified three investigated species from their biochemical traits.

  1. Investigating the Effects of Higher Spatial Resolution on Benthic Classification Accuracy at Midway Atoll

    DTIC Science & Technology

    2008-09-01

    monospecific F. DEEP ESCARPMENT massive branching mixed G. LAGOON e. other invertebrates- sea urchins , sponges H. BACK REEF f. artificial- North South West...et al., 2004). When this technique is applied to describing the features of the sea bottom, it is called a benthic classification. Unfortunately...Stamnes, 1999). The effects of atmospheric attenuation and scattering, the air- sea interface, and elements in the water column must all be

  2. Achieving sub-pixel geolocation accuracy in support of MODIS land science

    USGS Publications Warehouse

    Wolfe, R.E.; Nishihama, M.; Fleig, A.J.; Kuyper, J.A.; Roy, D.P.; Storey, J.C.; Patt, F.S.

    2002-01-01

    The Moderate Resolution Imaging Spectroradiometer (MODIS) was launched in December 1999 on the polar orbiting Terra spacecraft and since February 2000 has been acquiring daily global data in 36 spectral bands—29 with 1 km, five with 500 m, and two with 250 m nadir pixel dimensions. The Terra satellite has on-board exterior orientation (position and attitude) measurement systems designed to enable geolocation of MODIS data to approximately 150 m (1σ) at nadir. A global network of ground control points is being used to determine biases and trends in the sensor orientation. Biases have been removed by updating models of the spacecraft and instrument orientation in the MODIS geolocation software several times since launch and have improved the MODIS geolocation to approximately 50 m (1σ) at nadir. This paper overviews the geolocation approach, summarizes the first year of geolocation analysis, and overviews future work. The approach allows an operational characterization of the MODIS geolocation errors and enables individual MODIS observations to be geolocated to the sub-pixel accuracies required for terrestrial global change applications.

  3. a Method to Achieve Large Volume, High Accuracy Photogrammetric Measurements Through the Use of AN Actively Deformable Sensor Mounting Platform

    NASA Astrophysics Data System (ADS)

    Sargeant, B.; Robson, S.; Szigeti, E.; Richardson, P.; El-Nounu, A.; Rafla, M.

    2016-06-01

    When using any optical measurement system one important factor to consider is the placement of the sensors in relation to the workpiece being measured. When making decisions on sensor placement compromises are necessary in selecting the best placement based on the shape and size of the object of interest and the desired resolution and accuracy. One such compromise is in the distance the sensors are placed from the measurement surface, where a smaller distance gives a higher spatial resolution and local accuracy and a greater distance reduces the number of measurements necessary to cover a large area reducing the build-up of errors between measurements and increasing global accuracy. This paper proposes a photogrammetric approach whereby a number of sensors on a continuously flexible mobile platform are used to obtain local measurements while the position of the sensors is determined by a 6DoF tracking solution and the results combined to give a single set of measurement data within a continuous global coordinate system. The ability of this approach to achieve both high accuracy measurement and give results over a large volume is then tested and areas of weakness to be improved upon are identified.

  4. Multinomial tree models for assessing the status of the reference in studies of the accuracy of tools for binary classification

    PubMed Central

    Botella, Juan; Huang, Huiling; Suero, Manuel

    2013-01-01

    Studies that evaluate the accuracy of binary classification tools are needed. Such studies provide 2 × 2 cross-classifications of test outcomes and the categories according to an unquestionable reference (or gold standard). However, sometimes a suboptimal reliability reference is employed. Several methods have been proposed to deal with studies where the observations are cross-classified with an imperfect reference. These methods require that the status of the reference, as a gold standard or as an imperfect reference, is known. In this paper a procedure for determining whether it is appropriate to maintain the assumption that the reference is a gold standard or an imperfect reference, is proposed. This procedure fits two nested multinomial tree models, and assesses and compares their absolute and incremental fit. Its implementation requires the availability of the results of several independent studies. These should be carried out using similar designs to provide frequencies of cross-classification between a test and the reference under investigation. The procedure is applied in two examples with real data. PMID:24106484

  5. Concurrent Classification Accuracy of the HIV Dementia Scale for HIV-associated Neurocognitive Disorders in the CHARTER Cohort

    PubMed Central

    Sakamoto, Maiko; Marcotte, Thomas D.; Umlauf, Anya; Franklin, Donald; Heaton, Robert K.; Ellis, Ronald J.; Letendre, Scott; Alexander, Terry; McCutchan, J. Allen; Morgan, Erin E.; Woods, Steven Paul; Collier, Ann C.; Marra, Christina M.; Clifford, David B.; Gelman, Benjamin B.; McArthur, Justin C.; Morgello, Susan; Simpson, David; Grant, Igor

    2012-01-01

    Background The HIV Dementia Scale (HDS) was developed to screen for HIV-associated Neurocognitive Disorders (HAND), but concerns have persisted regarding its substandard sensitivity. This study aimed to examine the classification accuracy of the HDS using raw and norm-based cutpoints, and to evaluate the contribution of the HDS subtests to predicting HAND. Methods 1,580 HIV-infected participants from 6 U.S. sites completed the HDS, and a gold standard neuropsychological battery, on which 51% of participants were impaired. Results: Sensitivity and specificity to HAND using the standard raw HDS cutpoint were 24% and 92%, respectively. The raw HDS subtests of attention, recall, and psychomotor speed significantly contributed to classification of HAND, while visuomotor construction contributed the least. A modified raw cutpoint of 14 yielded sensitivity of 66% and specificity of 61%, with cross-validation. Using norms also significantly improved sensitivity to 69% with a concomitant reduction of specificity to 56%, while the positive predictive value declined from 75% to 62% and negative predictive value improved from 54% to 64%. The HDS showed similarly modest rates of sensitivity and specificity among subpopulations of individuals with minimal comorbidity and successful viral suppression. Conclusions Findings indicate that while the HDS is a statistically significant predictor of HAND, particularly when adjusted for demographic factors, its relatively low diagnostic classification accuracy continues to hinder its clinical utility. A raw cutpoint of 14 greatly improved the sensitivity of the previously established raw cutscore, but may be subject to ceiling effects, particularly on repeat assessments. PMID:23111573

  6. Overview of existing algorithms for emotion classification. Uncertainties in evaluations of accuracies.

    NASA Astrophysics Data System (ADS)

    Avetisyan, H.; Bruna, O.; Holub, J.

    2016-11-01

    A numerous techniques and algorithms are dedicated to extract emotions from input data. In our investigation it was stated that emotion-detection approaches can be classified into 3 following types: Keyword based / lexical-based, learning based, and hybrid. The most commonly used techniques, such as keyword-spotting method, Support Vector Machines, Naïve Bayes Classifier, Hidden Markov Model and hybrid algorithms, have impressive results in this sphere and can reach more than 90% determining accuracy.

  7. Mechanized pivot shift test achieves greater accuracy than manual pivot shift test.

    PubMed

    Musahl, Volker; Voos, James; O'Loughlin, Padhraig F; Stueber, Volker; Kendoff, Daniel; Pearle, Andrew D

    2010-09-01

    The objective of this study was to design a navigated mechanized pivot shift test setup and evaluate its repeatability in the ACL-deficient knee. It was hypothesized that translations and rotations measured with the mechanized pivot shift would be more repeatable when compared to those obtained with a manual pivot shift. Twelve fresh frozen cadaveric hip-to-toe whole lower extremities were used for this study. A manual pivot shift test was performed in the intact knee and in the ACL-deficient knee and was repeated three times. A navigation system simultaneously recorded tibial translation and rotation. The mechanized pivot shift test consists of a modified continuous passive motion (CPM) machine and a custom-made foot holder to allow for the application of internal rotation moments at the knee. Valgus moments were achieved by a 45 degrees tilt of the CPM machine with respect to the supine position and a Velcro strap secured across the proximal tibia. The mechanized pivot shift was repeated three times. Repeated measures ANOVA was used to compare manual and mechanized pivot shift testing. An intra-class correlation coefficient (ICC) was used to determine variability within each knee at each testing condition. In the ACL-deficient knee, translation with manual pivot shift testing (11.7 +/- 2.6 mm) was significantly higher than with mechanized pivot shift testing (7.4 +/- 2.5 mm; p < 0.05). Rotation with the manual pivot shift testing (18.6 +/- 5.4 degrees) was also significantly higher than with mechanized pivot shift testing (11.0 +/- 2.3 degrees; p < 0.05). The intra-class ICC for translations was 0.76 for manual pivot shift and 0.92 for the mechanized pivot shift test. The intra-class ICC for rotations was 0.89 for manual pivot shift and 0.82 for the mechanized pivot shift test. This study introduced a modified CPM for mechanized pivot shift testing. Although recorded translations and rotations with the mechanized pivot shift test were lower than with manual

  8. Assessing the accuracy of the International Classification of Diseases codes to identify abusive head trauma: a feasibility study

    PubMed Central

    Berger, Rachel P; Parks, Sharyn; Fromkin, Janet; Rubin, Pamela; Pecora, Peter J

    2016-01-01

    Objective To assess the accuracy of an International Classification of Diseases (ICD) code-based operational case definition for abusive head trauma (AHT). Methods Subjects were children <5 years of age evaluated for AHT by a hospital-based Child Protection Team (CPT) at a tertiary care paediatric hospital with a completely electronic medical record (EMR) system. Subjects were designated as non-AHT traumatic brain injury (TBI) or AHT based on whether the CPT determined that the injuries were due to AHT. The sensitivity and specificity of the ICD-based definition were calculated. Results There were 223 children evaluated for AHT: 117 AHT and 106 non-AHT TBI. The sensitivity and specificity of the ICD-based operational case definition were 92% (95% CI 85.8 to 96.2) and 96% (95% CI 92.3 to 99.7), respectively. All errors in sensitivity and three of the four specificity errors were due to coder error; one specificity error was a physician error. Conclusions In a paediatric tertiary care hospital with an EMR system, the accuracy of an ICD-based case definition for AHT was high. Additional studies are needed to assess the accuracy of this definition in all types of hospitals in which children with AHT are cared for. PMID:24167034

  9. A classification of bioinformatics algorithms from the viewpoint of maximizing expected accuracy (MEA).

    PubMed

    Hamada, Michiaki; Asai, Kiyoshi

    2012-05-01

    Many estimation problems in bioinformatics are formulated as point estimation problems in a high-dimensional discrete space. In general, it is difficult to design reliable estimators for this type of problem, because the number of possible solutions is immense, which leads to an extremely low probability for every solution-even for the one with the highest probability. Therefore, maximum score and maximum likelihood estimators do not work well in this situation although they are widely employed in a number of applications. Maximizing expected accuracy (MEA) estimation, in which accuracy measures of the target problem and the entire distribution of solutions are considered, is a more successful approach. In this review, we provide an extensive discussion of algorithms and software based on MEA. We describe how a number of algorithms used in previous studies can be classified from the viewpoint of MEA. We believe that this review will be useful not only for users wishing to utilize software to solve the estimation problems appearing in this article, but also for developers wishing to design algorithms on the basis of MEA.

  10. A promising tool to achieve chemical accuracy for density functional theory calculations on Y-NO homolysis bond dissociation energies.

    PubMed

    Li, Hong Zhi; Hu, Li Hong; Tao, Wei; Gao, Ting; Li, Hui; Lu, Ying Hua; Su, Zhong Min

    2012-01-01

    A DFT-SOFM-RBFNN method is proposed to improve the accuracy of DFT calculations on Y-NO (Y = C, N, O, S) homolysis bond dissociation energies (BDE) by combining density functional theory (DFT) and artificial intelligence/machine learning methods, which consist of self-organizing feature mapping neural networks (SOFMNN) and radial basis function neural networks (RBFNN). A descriptor refinement step including SOFMNN clustering analysis and correlation analysis is implemented. The SOFMNN clustering analysis is applied to classify descriptors, and the representative descriptors in the groups are selected as neural network inputs according to their closeness to the experimental values through correlation analysis. Redundant descriptors and intuitively biased choices of descriptors can be avoided by this newly introduced step. Using RBFNN calculation with the selected descriptors, chemical accuracy (≤1 kcal·mol(-1)) is achieved for all 92 calculated organic Y-NO homolysis BDE calculated by DFT-B3LYP, and the mean absolute deviations (MADs) of the B3LYP/6-31G(d) and B3LYP/STO-3G methods are reduced from 4.45 and 10.53 kcal·mol(-1) to 0.15 and 0.18 kcal·mol(-1), respectively. The improved results for the minimal basis set STO-3G reach the same accuracy as those of 6-31G(d), and thus B3LYP calculation with the minimal basis set is recommended to be used for minimizing the computational cost and to expand the applications to large molecular systems. Further extrapolation tests are performed with six molecules (two containing Si-NO bonds and two containing fluorine), and the accuracy of the tests was within 1 kcal·mol(-1). This study shows that DFT-SOFM-RBFNN is an efficient and highly accurate method for Y-NO homolysis BDE. The method may be used as a tool to design new NO carrier molecules.

  11. IMPROVING THE ACCURACY OF HISTORIC SATELLITE IMAGE CLASSIFICATION BY COMBINING LOW-RESOLUTION MULTISPECTRAL DATA WITH HIGH-RESOLUTION PANCHROMATIC DATA

    SciTech Connect

    Getman, Daniel J

    2008-01-01

    Many attempts to observe changes in terrestrial systems over time would be significantly enhanced if it were possible to improve the accuracy of classifications of low-resolution historic satellite data. In an effort to examine improving the accuracy of historic satellite image classification by combining satellite and air photo data, two experiments were undertaken in which low-resolution multispectral data and high-resolution panchromatic data were combined and then classified using the ECHO spectral-spatial image classification algorithm and the Maximum Likelihood technique. The multispectral data consisted of 6 multispectral channels (30-meter pixel resolution) from Landsat 7. These data were augmented with panchromatic data (15m pixel resolution) from Landsat 7 in the first experiment, and with a mosaic of digital aerial photography (1m pixel resolution) in the second. The addition of the Landsat 7 panchromatic data provided a significant improvement in the accuracy of classifications made using the ECHO algorithm. Although the inclusion of aerial photography provided an improvement in accuracy, this improvement was only statistically significant at a 40-60% level. These results suggest that once error levels associated with combining aerial photography and multispectral satellite data are reduced, this approach has the potential to significantly enhance the precision and accuracy of classifications made using historic remotely sensed data, as a way to extend the time range of efforts to track temporal changes in terrestrial systems.

  12. On evaluating the accuracy of SAR sea-ice classification using multifrequency polarimetric AIRSAR data

    NASA Technical Reports Server (NTRS)

    Drinkwater, Mark R.; Rignot, Eric

    1993-01-01

    We investigate how multifrequency and polarimetric synthetic aperture radar (SAR) imagery enhances present capability to discriminate different ice conditions in single-frequency, single-polarization satellite SAR data. Frequencies considered are C- (lambda = 5.6cm), L- (lambda = 24cm) and P- (lambda = 68cm) band. Radar backscatter characteristics of six radiometrically and polarimetrically distinct ice types are selected from a cluster analysis of the multifrequency polarimetric SAR data and used to classify SAR images. Validation of these ice conditions is based on information provided by aerial photos, weather and ice surface measurements acquired at an ice camp, together with airborne passive microwave imagery, and visual analysis of the SAR data. The six identified sea-ice types are: (1) multiyear sea-ice; (2) compressed first year ice; (3) first year rubble and ridges; (4) first year rough ice; (5) first year smooth ice; and (6) thin ice. Open water is absent in all analyzed data. Classification of the SAR imagery into those six ice types is performed using a Bayesian Maximum A Posteriori classifier. Two complete scenes acquired at different dates in different locations are classified. The scenes were chosen such that they are representative of typical ice conditions in the Beaufort Sea in March 1988 and because ancillary information is available for validating the segmentation of various ice surface conditions.

  13. Malingering in toxic exposure: classification accuracy of reliable digit span and WAIS-III Digit Span scaled scores.

    PubMed

    Greve, Kevin W; Springer, Steven; Bianchini, Kevin J; Black, F William; Heinly, Matthew T; Love, Jeffrey M; Swift, Douglas A; Ciota, Megan A

    2007-03-01

    This study examined the sensitivity and false-positive error rate of reliable digit span (RDS) and the WAIS-III Digit Span (DS) scaled score in persons alleging toxic exposure and determined whether error rates differed from published rates in traumatic brain injury (TBI) and chronic pain (CP). Data were obtained from the files of 123 persons referred for neuropsychological evaluation related to alleged exposure to environmental and industrial substances. Malingering status was determined using the criteria of Slick, Sherman, and Iverson (1999). The sensitivity and specificity of RDS and DS in toxic exposure are consistent with those observed in TBI and CP. These findings support the use of these malingering indicators in cases of alleged toxic exposure and suggest that the classification accuracy data of indicators derived from studies of TBI patients may also be validly applied to cases of alleged toxic exposure.

  14. The Effect of Two Science Programs (ESS and Laidlaw) on Student Classification Skills, Science Achievement, and Attitudes

    ERIC Educational Resources Information Center

    Vanek, Eugenia Poporad; Montean, John J.

    1977-01-01

    No significant differences were found for grade level, sex, or instructional treatment (activity-based curriculum vs. textbook approach) for third and fourth grade science students as measured by Piagetian Classification Tasks, the Science Attitude Scale, and the Science Achievement Test. (MLH)

  15. Peaks, plateaus, numerical instabilities, and achievable accuracy in Galerkin and norm minimizing procedures for solving Ax=b

    SciTech Connect

    Cullum, J.

    1994-12-31

    Plots of the residual norms generated by Galerkin procedures for solving Ax = b often exhibit strings of irregular peaks. At seemingly erratic stages in the iterations, peaks appear in the residual norm plot, intervals of iterations over which the norms initially increase and then decrease. Plots of the residual norms generated by related norm minimizing procedures often exhibit long plateaus, sequences of iterations over which reductions in the size of the residual norm are unacceptably small. In an earlier paper the author discussed and derived relationships between such peaks and plateaus within corresponding Galerkin/Norm Minimizing pairs of such methods. In this paper, through a set of numerical experiments, the author examines connections between peaks, plateaus, numerical instabilities, and the achievable accuracy for such pairs of iterative methods. Three pairs of methods, GMRES/Arnoldi, QMR/BCG, and two bidiagonalization methods are studied.

  16. Proficiency testing linked to the national reference system for the clinical laboratory: a proposal for achieving accuracy.

    PubMed

    Lasky, F D

    1992-07-01

    I propose using proficiency testing (PT) to achieve one of the important goals of CLIA: accurate and reliable clinical testing. Routine methods for the clinical laboratory are traceable to Definitive (DM) or Reference Methods (RM) or to Methodological Principles (MP) through a modification of the National Reference System for the Clinical Laboratory. PT is the link used to monitor consistent field performance. Although PT has been effective as a relative measure of laboratory performance, the technical limitations of PT fluids and of routine methods currently in use make it unlikely that PT alone can be used as a reliable measure of laboratory accuracy. Instead, I recommend calibration of routine systems through correlation to DM, RM, or MP with use of patients' specimens. The manufacturer is in the best position to assume this responsibility because of also being responsible for consistent, reliable product. Analysis of different manufactured batches of reagent would be compared with predetermined goals for precision and accuracy, as illustrated with data from product testing of Kodak Ektachem clinical chemistry slides. Adoption of this proposal would give manufacturers of PT materials, manufacturers of analytical systems, PT providers, and government agencies time to understand and resolve sources of error that limit the utility of PT for the job required by law.

  17. Teaching Methods, Intelligence, and Gender Factors in Pupil Achievement on a Classification Task

    ERIC Educational Resources Information Center

    Ryman, Don

    1977-01-01

    Reports on twelve year-old students instructed in Nuffield Project and in "traditional" classrooms. A division of the subjects into two groups based on intelligence revealed significant differences on classification ability. Interaction effects were also observed. (CP)

  18. Classification

    ERIC Educational Resources Information Center

    Clary, Renee; Wandersee, James

    2013-01-01

    In this article, Renee Clary and James Wandersee describe the beginnings of "Classification," which lies at the very heart of science and depends upon pattern recognition. Clary and Wandersee approach patterns by first telling the story of the "Linnaean classification system," introduced by Carl Linnacus (1707-1778), who is…

  19. Cognitive Processing Profiles of School-Age Children Who Meet Low-Achievement, IQ-Discrepancy, or Dual Criteria for Underachievement in Oral Reading Accuracy

    ERIC Educational Resources Information Center

    Van Santen, Frank W.

    2012-01-01

    The purpose of this study was to compare the cognitive processing profiles of school-age children (ages 7 to 17) who met criteria for underachievement in oral reading accuracy based on three different methods: 1) use of a regression-based IQ-achievement discrepancy only (REGonly), 2) use of a low-achievement cutoff only (LAonly), and 3) use of a…

  20. Influence of multi-source and multi-temporal remotely sensed and ancillary data on the accuracy of random forest classification of wetlands in northern Minnesota

    USGS Publications Warehouse

    Corcoran, Jennifer M.; Knight, Joseph F.; Gallant, Alisa L.

    2013-01-01

    Wetland mapping at the landscape scale using remotely sensed data requires both affordable data and an efficient accurate classification method. Random forest classification offers several advantages over traditional land cover classification techniques, including a bootstrapping technique to generate robust estimations of outliers in the training data, as well as the capability of measuring classification confidence. Though the random forest classifier can generate complex decision trees with a multitude of input data and still not run a high risk of over fitting, there is a great need to reduce computational and operational costs by including only key input data sets without sacrificing a significant level of accuracy. Our main questions for this study site in Northern Minnesota were: (1) how does classification accuracy and confidence of mapping wetlands compare using different remote sensing platforms and sets of input data; (2) what are the key input variables for accurate differentiation of upland, water, and wetlands, including wetland type; and (3) which datasets and seasonal imagery yield the best accuracy for wetland classification. Our results show the key input variables include terrain (elevation and curvature) and soils descriptors (hydric), along with an assortment of remotely sensed data collected in the spring (satellite visible, near infrared, and thermal bands; satellite normalized vegetation index and Tasseled Cap greenness and wetness; and horizontal-horizontal (HH) and horizontal-vertical (HV) polarization using L-band satellite radar). We undertook this exploratory analysis to inform decisions by natural resource managers charged with monitoring wetland ecosystems and to aid in designing a system for consistent operational mapping of wetlands across landscapes similar to those found in Northern Minnesota.

  1. Improving the classification accuracy for IR spectroscopic diagnosis of stomach and colon malignancy using non-linear spectral feature extraction methods.

    PubMed

    Lee, Sanguk; Kim, Kyoungok; Lee, Hyeseon; Jun, Chi-Hyuck; Chung, Hoeil; Park, Jong-Jae

    2013-07-21

    Non-linear feature extraction methods, neighborhood preserving embedding (NPE) and supervised NPE (SNPE), were employed to effectively represent the IR spectral features of stomach and colon biopsy tissues for classification, and improve the classification accuracy for diagnosis of malignancy. The motivation was to utilize the NPE and SNPE's capability of capturing non-linear spectral behaviors by simultaneously preserving local relationships in order that minute spectral differences among classes would be effectively recognized. NPE and SNPE derive an optimal embedding feature such that the local neighborhood structure can be preserved in reduced spaces (variables). The IR spectra collected from stomach and colon tissues were represented by several new variables through NPE and SNPE, and also by using the principal component analysis (PCA). Then, the feature-extracted variables were subsequently classified into normal, adenoma and cancer tissues by using both k-nearest neighbor (k-NN) and support vector machine (SVM), and the resulting accuracies were compared with each other. In both cases, the combination of SNPE-SVM provided the best classification performance, and the accuracy was substantially improved compared to when PCA-SVM was used. Overall results demonstrate that NPE and SNPE could be potential feature-representation strategies useful in biomedical diagnosis based on vibrational spectroscopy where effective recognition of minute spectral differences is critical.

  2. Mapping Crop Patterns in Central US Agricultural Systems from 2000 to 2014 Based on Landsat Data: To What Degree Does Fusing MODIS Data Improve Classification Accuracies?

    NASA Astrophysics Data System (ADS)

    Zhu, L.; Radeloff, V.; Ives, A. R.; Barton, B.

    2015-12-01

    Deriving crop pattern with high accuracy is of great importance for characterizing landscape diversity, which affects the resilience of food webs in agricultural systems in the face of climatic and land cover changes. Landsat sensors were originally designed to monitor agricultural areas, and both radiometric and spatial resolution are optimized for monitoring large agricultural fields. Unfortunately, few clear Landsat images per year are available, which has limited the use of Landsat for making crop classification, and this situation is worse in cloudy areas of the Earth. Meanwhile, the MODerate Resolution Imaging Spectroradiometer (MODIS) data has better temporal resolution but cannot capture fine spatial heterogeneity of agricultural systems. Our question was to what extent fusing imagery from both sensors could improve crop classifications. We utilized the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) algorithm to simulate Landsat-like images at MODIS temporal resolution. Based on Random Forests (RF) classifier, we tested whether and by what degree crop maps from 2000 to 2014 of the Arlington Agricultural Research Station (Wisconsin, USA) were improved by integrating available clear Landsat images each year with synthetic images. We predicted that the degree to which classification accuracy can be improved by incorporating synthetic imagery depends on the number and acquisition time of clear Landsat images. Moreover, multi-season data are essential for mapping crop types by capturing their phenological dynamics, and STARFM-simulated images can be used to compensate for missing Landsat observations. Our study is helpful for eliminating the limits of the use of Landsat data in mapping crop patterns, and can provide a benchmark of accuracy when choosing STARFM-simulated images to make crop classification at broader scales.

  3. Comparative accuracies of two common screening instruments for the classification of Alzheimer’s disease, mild cognitive impairment and healthy aging

    PubMed Central

    Roalf, David R.; Moberg, Paul J.; Xie, Sharon X.; Wolk, David A.; Moelter, Stephen T.; Arnold, Steven E.

    2013-01-01

    Objective To compare the utility and diagnostic accuracy of the MoCA and MMSE in the diagnosis of Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) in a clinical cohort. Method 321 AD, 126 MCI and 140 older adults with healthy cognition (HC) were evaluated using the the MMSE, MoCA, a standardized neuropsychological battery according to the Consortium to Establish a Registry of Alzheimer’s Disease (CERAD-NB) and an informant based measure of functional impairment, the Dementia Severity Rating Scale (DSRS). Diagnostic accuracy and optimal cut-off scores were calculated for each measure, and a method for converting MoCA to MMSE scores is presented also. Results The MMSE and MoCA offer reasonably good diagnostic and classification accuracy as compared to the more detailed CERAD-NB; however, as a brief cognitive screening measure the MoCA was more sensitive and had higher classification accuracy for differentiating MCI from HC. Complementing the MMSE or the MoCA with the DSRS significantly improved diagnostic accuracy. Conclusion The current results support recent data indicating that the MoCA is superior to the MMSE as a global assessment tool, particularly in discerning earlier stages of cognitive decline. In addition, we found that overall diagnostic accuracy improves when the MMSE or MoCA is combined with an informant-based functional measure. Finally, we provide a reliable and easy conversion of MoCA to MMSE scores. However, the need for MCI-specific measures is still needed to increase the diagnostic specificity between AD and MCI. PMID:23260866

  4. Evaluating IRT- and CTT-Based Methods of Estimating Classification Consistency and Accuracy Indices from Single Administrations

    ERIC Educational Resources Information Center

    Deng, Nina

    2011-01-01

    Three decision consistency and accuracy (DC/DA) methods, the Livingston and Lewis (LL) method, LEE method, and the Hambleton and Han (HH) method, were evaluated. The purposes of the study were: (1) to evaluate the accuracy and robustness of these methods, especially when their assumptions were not well satisfied, (2) to investigate the "true"…

  5. Classification.

    PubMed

    Tuxhorn, Ingrid; Kotagal, Prakash

    2008-07-01

    In this article, we review the practical approach and diagnostic relevance of current seizure and epilepsy classification concepts and principles as a basic framework for good management of patients with epileptic seizures and epilepsy. Inaccurate generalizations about terminology, diagnosis, and treatment may be the single most important factor, next to an inadequately obtained history, that determines the misdiagnosis and mismanagement of patients with epilepsy. A stepwise signs and symptoms approach for diagnosis, evaluation, and management along the guidelines of the International League Against Epilepsy and definitions of epileptic seizures and epilepsy syndromes offers a state-of-the-art clinical approach to managing patients with epilepsy.

  6. Accuracy of automatic syndromic classification of coded emergency department diagnoses in identifying mental health-related presentations for public health surveillance

    PubMed Central

    2014-01-01

    Background Syndromic surveillance in emergency departments (EDs) may be used to deliver early warnings of increases in disease activity, to provide situational awareness during events of public health significance, to supplement other information on trends in acute disease and injury, and to support the development and monitoring of prevention or response strategies. Changes in mental health related ED presentations may be relevant to these goals, provided they can be identified accurately and efficiently. This study aimed to measure the accuracy of using diagnostic codes in electronic ED presentation records to identify mental health-related visits. Methods We selected a random sample of 500 records from a total of 1,815,588 ED electronic presentation records from 59 NSW public hospitals during 2010. ED diagnoses were recorded using any of ICD-9, ICD-10 or SNOMED CT classifications. Three clinicians, blinded to the automatically generated syndromic grouping and each other’s classification, reviewed the triage notes and classified each of the 500 visits as mental health-related or not. A “mental health problem presentation” for the purposes of this study was defined as any ED presentation where either a mental disorder or a mental health problem was the reason for the ED visit. The combined clinicians’ assessment of the records was used as reference standard to measure the sensitivity, specificity, and positive and negative predictive values of the automatic classification of coded emergency department diagnoses. Agreement between the reference standard and the automated coded classification was estimated using the Kappa statistic. Results Agreement between clinician’s classification and automated coded classification was substantial (Kappa = 0.73. 95% CI: 0.58 - 0.87). The automatic syndromic grouping of coded ED diagnoses for mental health-related visits was found to be moderately sensitive (68% 95% CI: 46%-84%) and highly specific at 99% (95% CI: 98

  7. Classification

    NASA Technical Reports Server (NTRS)

    Oza, Nikunj C.

    2011-01-01

    A supervised learning task involves constructing a mapping from input data (normally described by several features) to the appropriate outputs. Within supervised learning, one type of task is a classification learning task, in which each output is one or more classes to which the input belongs. In supervised learning, a set of training examples---examples with known output values---is used by a learning algorithm to generate a model. This model is intended to approximate the mapping between the inputs and outputs. This model can be used to generate predicted outputs for inputs that have not been seen before. For example, we may have data consisting of observations of sunspots. In a classification learning task, our goal may be to learn to classify sunspots into one of several types. Each example may correspond to one candidate sunspot with various measurements or just an image. A learning algorithm would use the supplied examples to generate a model that approximates the mapping between each supplied set of measurements and the type of sunspot. This model can then be used to classify previously unseen sunspots based on the candidate's measurements. This chapter discusses methods to perform machine learning, with examples involving astronomy.

  8. Computerized assessment of pedophilic sexual interest through self-report and viewing time: reliability, validity, and classification accuracy of the affinity program.

    PubMed

    Mokros, Andreas; Gebhard, Michael; Heinz, Volker; Marschall, Roland W; Nitschke, Joachim; Glasgow, David V; Gress, Carmen L Z; Laws, D Richard

    2013-06-01

    Affinity is a computerized assessment tool that combines viewing time and self-report measures of sexual interest. The present study was designed to assess the diagnostic properties of Affinity with respect to sexual interest in prepubescent children. Reliability of both self-report and viewing time components was estimated to be high. The group profile of a sample of pedophilic adult male child molesters (n = 42, all of whom admitted their offenses) differed from the group profiles of male community controls (n = 95) and male nonsexual offenders (n = 27), respectively. More specifically, both ratings and viewing times for images showing small children or prejuvenile children were significantly higher within the child molester sample than in either of the other two groups, attesting to the validity of the measures. Overall classification accuracy, however, was mediocre: A multivariate classification routine yielded 50% sensitivity for child molester status at the cost of 13% false positives. The implications for forensic use of Affinity are discussed.

  9. The Effects of Q-Matrix Design on Classification Accuracy in the Log-Linear Cognitive Diagnosis Model

    ERIC Educational Resources Information Center

    Madison, Matthew J.; Bradshaw, Laine P.

    2015-01-01

    Diagnostic classification models are psychometric models that aim to classify examinees according to their mastery or non-mastery of specified latent characteristics. These models are well-suited for providing diagnostic feedback on educational assessments because of their practical efficiency and increased reliability when compared with other…

  10. The Effects of Q-Matrix Misspecification on Parameter Estimates and Classification Accuracy in the DINA Model

    ERIC Educational Resources Information Center

    Rupp, Andre A.; Templin, Jonathan

    2008-01-01

    This article reports a study that investigated the effects of Q-matrix misspecifications on parameter estimates and misclassification rates for the deterministic-input, noisy "and" gate (DINA) model, which is a restricted latent class model for multiple classifications of respondents that can be useful for cognitively motivated diagnostic…

  11. Classification Accuracy of MMPI-2 Validity Scales in the Detection of Pain-Related Malingering: A Known-Groups Study

    ERIC Educational Resources Information Center

    Bianchini, Kevin J.; Etherton, Joseph L.; Greve, Kevin W.; Heinly, Matthew T.; Meyers, John E.

    2008-01-01

    The purpose of this study was to determine the accuracy of "Minnesota Multiphasic Personality Inventory" 2nd edition (MMPI-2; Butcher, Dahlstrom, Graham, Tellegen, & Kaemmer, 1989) validity indicators in the detection of malingering in clinical patients with chronic pain using a hybrid clinical-known groups/simulator design. The…

  12. Comparison of Activity Type Classification Accuracy from Accelerometers Worn on the Hip, Wrists, and Thigh in Young, Apparently Healthy Adults

    ERIC Educational Resources Information Center

    Montoye, Alexander H. K.; Pivarnik, James M.; Mudd, Lanay M.; Biswas, Subir; Pfeiffer, Karin A.

    2016-01-01

    The purpose of this article is to compare accuracy of activity type prediction models for accelerometers worn on the hip, wrists, and thigh. Forty-four adults performed sedentary, ambulatory, lifestyle, and exercise activities (14 total, 10 categories) for 3-10 minutes each in a 90-minute semi-structured laboratory protocol. Artificial neural…

  13. Strategies for achieving high sequencing accuracy for low diversity samples and avoiding sample bleeding using illumina platform.

    PubMed

    Mitra, Abhishek; Skrzypczak, Magdalena; Ginalski, Krzysztof; Rowicka, Maga

    2015-01-01

    analysis can be repeated from saved sequencing images using the Long Template Protocol to increase accuracy.

  14. Strategies for Achieving High Sequencing Accuracy for Low Diversity Samples and Avoiding Sample Bleeding Using Illumina Platform

    PubMed Central

    Mitra, Abhishek; Skrzypczak, Magdalena; Ginalski, Krzysztof; Rowicka, Maga

    2015-01-01

    analysis can be repeated from saved sequencing images using the Long Template Protocol to increase accuracy. PMID:25860802

  15. Diagnostic efficiency of several methods of identifying socially rejected children and effect of participation rate on classification accuracy.

    PubMed

    McKown, Clark; Gumbiner, Laura M; Johnson, Jason

    2011-10-01

    Social rejection is associated with a wide variety of negative outcomes. Early identification of social rejection and intervention to minimize its negative impact is thus important. However, sociometric methods, which are considered high in validity for identifying socially rejected children, are frequently not used because of (a) procedural challenges, (b) community apprehension, and (c) sensitivity to missing data. In a sample of 316 students in grades K through 8, we used receiver operating characteristics (ROC) analyses to compare the diagnostic efficiency of several methods for identifying socially rejected children. When not using least-liked nominations, (a) most-liked nominations yielded the greatest diagnostic efficiency (AUC=.96), (b) peer ratings were more efficient (AUC=.84 to .99) than teacher ratings (AUC=.74 to .81), and (c) teacher report of social status was more efficient (AUC=.81) than scores from teacher behavior rating scales (AUC=.74 to .75). We also examined the effects of nominator non-participation on diagnostic efficiency. At participation as low as 50%, classification of sociometric rejection (i.e., being rejected or not rejected) was quite accurate (κ=.63 to .77). In contrast, at participation as high as 70%, classification of sociometric status (i.e., popular, average, unclassified, neglected, controversial, or rejected) was significantly less accurate (κ=.50 to .59).

  16. Supervised, Multivariate, Whole-Brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research

    PubMed Central

    Janousova, Eva; Montana, Giovanni; Kasparek, Tomas; Schwarz, Daniel

    2016-01-01

    We examined how penalized linear discriminant analysis with resampling, which is a supervised, multivariate, whole-brain reduction technique, can help schizophrenia diagnostics and research. In an experiment with magnetic resonance brain images of 52 first-episode schizophrenia patients and 52 healthy controls, this method allowed us to select brain areas relevant to schizophrenia, such as the left prefrontal cortex, the anterior cingulum, the right anterior insula, the thalamus, and the hippocampus. Nevertheless, the classification performance based on such reduced data was not significantly better than the classification of data reduced by mass univariate selection using a t-test or unsupervised multivariate reduction using principal component analysis. Moreover, we found no important influence of the type of imaging features, namely local deformations or gray matter volumes, and the classification method, specifically linear discriminant analysis or linear support vector machines, on the classification results. However, we ascertained significant effect of a cross-validation setting on classification performance as classification results were overestimated even though the resampling was performed during the selection of brain imaging features. Therefore, it is critically important to perform cross-validation in all steps of the analysis (not only during classification) in case there is no external validation set to avoid optimistically biasing the results of classification studies. PMID:27610072

  17. Radar target classification method with high accuracy and decision speed performance using MUSIC spectrum vectors and PCA projection

    NASA Astrophysics Data System (ADS)

    Secmen, Mustafa

    2011-10-01

    This paper introduces the performance of an electromagnetic target recognition method in resonance scattering region, which includes pseudo spectrum Multiple Signal Classification (MUSIC) algorithm and principal component analysis (PCA) technique. The aim of this method is to classify an "unknown" target as one of the "known" targets in an aspect-independent manner. The suggested method initially collects the late-time portion of noise-free time-scattered signals obtained from different reference aspect angles of known targets. Afterward, these signals are used to obtain MUSIC spectrums in real frequency domain having super-resolution ability and noise resistant feature. In the final step, PCA technique is applied to these spectrums in order to reduce dimensionality and obtain only one feature vector per known target. In the decision stage, noise-free or noisy scattered signal of an unknown (test) target from an unknown aspect angle is initially obtained. Subsequently, MUSIC algorithm is processed for this test signal and resulting test vector is compared with feature vectors of known targets one by one. Finally, the highest correlation gives the type of test target. The method is applied to wire models of airplane targets, and it is shown that it can tolerate considerable noise levels although it has a few different reference aspect angles. Besides, the runtime of the method for a test target is sufficiently low, which makes the method suitable for real-time applications.

  18. Improving classification accuracy using multi-date IRS/LISS data and development of thermal stress index for Asiatic lion habitat

    NASA Astrophysics Data System (ADS)

    Gupta, Rajendra Kumar

    The increase in lion and leopard population in the GIR wild life sanctuary and National Park (Gir Protected Area) demands periodic and precision monitoring of habitat at close intervals using space based remote sensing data. Besides characterizing the different forest classes, remote sensing needs to support for the assessment of thermal stress zones and identification of possible corridors for lion dispersion to new home ranges. The study focuses on assessing the thematic forest classification accuracies in percentage terms(CA) attainable using single date post-monsoon (CA=60, kappa = 0.514) as well as leaf shedding (CA=48.4, kappa = 0.372) season data in visible and Near-IR spectral bands of IRS/LISS-III at 23.5 m spatial resolution; and improvement of CA by using joint two date (multi-temporal) data sets (CA=87.2, kappa = 0.843) in the classification. The 188 m spatial resolution IRS/WiFS and 23.5 m spatial resolution LISS-III data were used to study the possible corridors for dispersion of Lions from GIR protected areas (PA). A relative thermal stress index (RTSI) for Gir PA has been developed using NOAA/ AVHRR data sets of post-monsoon, leaf shedded and summer seasons. The paper discusses the role of RTSI as a tool to work out forest management plans using leaf shedded season data to combat the thermal stress in the habitat, by identifying locations for artificial water holes during the ensuing summer season.

  19. Multimodality CAD: combination of computerized classification techniques based on mammograms and 3D ultrasound volumes for improved accuracy in breast mass characterization

    NASA Astrophysics Data System (ADS)

    Sahiner, Berkman; Chan, Heang-Ping; Hadjiiski, Lubomir M.; Roubidoux, Marilyn A.; Paramagul, Chintana; Helvie, Mark A.; Zhou, Chuan

    2004-05-01

    Mammography and ultrasound (US) are two low-cost modalities that are commonly used by radiologists for evaluating breast masses and making biopsy recommendations. The goal of this study was to investigate computerized methods for combining information from these two modalities for mass characterization. Our data set consisted of 3D US images and mammograms of biopsy-proven solid breast masses from 60 patients. Thirty of the masses were malignant and 30 were benign. The US volume was obtained by scanning with an experimental 3D US image acquisition system. After computerized feature extraction from the 3D US images and mammograms, we investigated three methods (A, B and C) for combining the image features or classifier scores from different mammographic views and the US volumes. The classifier scores were analyzed using the receiver operating characteristic (ROC) methodology. The area Az under the ROC curve of the classifier based on US alone was 0.88+/-0.04 for testing Two classifiers were designed using the mammograms alone, with test Az values of 0.85+/-0.05 and 0.87+/-0.05, respectively. The test accuracy of combination methods A, B, and C were 0.89+/-0.04, 0.92+/-0.03, and 0.93+/-0.03, respectively. Our results indicate that combining the image features or classifier scores from the US and mammographic classification methods can improve the accuracy of computerized mass characterization.

  20. Diagnostic Accuracy of the FIGO and the 5-Tier Fetal Heart Rate Classification Systems in the Detection of Neonatal Acidemia.

    PubMed

    Martí Gamboa, Sabina; Giménez, Olga Redrado; Mancho, Jara Pascual; Moros, María Lapresta; Sada, Julia Ruiz; Mateo, Sergio Castan

    2016-10-25

    Objective The objective of this study was to determine ability to detect neonatal acidemia and interobserver agreement with the FIGO 3-tier and 5-tier fetal heart rate (FHR) classification systems. Design This was a case-control study. Setting This study was set at the University Medical Center. Population A total of 202 FHR tracings of 102 women who delivered an acidemic fetus (umbilical arterial cord gas pH ≤ 7.10 and BE < - 8) and 100 who delivered a nonacidemic fetus (umbilical arterial cord gas pH > 7.10) were assessed. A subanalysis was performed for those fetuses who suffered severe metabolic acidemia (pH ≤ 7.0 and BE < - 12). Methods Two reviewers blind to clinical and outcome data classified tracings according to the new 3-tier system proposed by the FIGO and the 5-tier system proposed by Parer and Ikeda. Main Outcome Measures Sensitivity and specificity for detecting neonatal acidemia and interobserver agreement in classifying FHR tracings into categories of both systems were studied. Results The 3-tier system showed a greater sensitivity and lower specificity to detect neonatal acidemia (43.6% sensitivity, 82.5% specificity) and severe metabolic acidemia (71.4% sensitivity, 74.0% specificity) compared with the 5-tier system (36.3% sensitivity, 88% specificity and 61.9% sensitivity, 80.1% specificity, respectively). Both systems were compared by area under the receiver-operating characteristic curve, with comparable predictive ability for detecting neonatal acidemia (FIGO-area under the curve [AUC]: 0.63 [95% confidence interval [CI]: 0.57-0.68] and Parer-AUC: 0.62 [95% CI: 0.56-0.67]). Interobserver agreement was moderate for both systems, but performance at each specific category showed a better agreement for the 5-tier system identifying a pathological tracing (orange or red, κ: 0.625 vs. pathological category, κ: 0.538). Conclusion Both systems presented a comparable ability to predict neonatal acidemia, although the

  1. Achieving Accuracy Requirements for Forest Biomass Mapping: A Data Fusion Method for Estimating Forest Biomass and LiDAR Sampling Error with Spaceborne Data

    NASA Technical Reports Server (NTRS)

    Montesano, P. M.; Cook, B. D.; Sun, G.; Simard, M.; Zhang, Z.; Nelson, R. F.; Ranson, K. J.; Lutchke, S.; Blair, J. B.

    2012-01-01

    The synergistic use of active and passive remote sensing (i.e., data fusion) demonstrates the ability of spaceborne light detection and ranging (LiDAR), synthetic aperture radar (SAR) and multispectral imagery for achieving the accuracy requirements of a global forest biomass mapping mission. This data fusion approach also provides a means to extend 3D information from discrete spaceborne LiDAR measurements of forest structure across scales much larger than that of the LiDAR footprint. For estimating biomass, these measurements mix a number of errors including those associated with LiDAR footprint sampling over regional - global extents. A general framework for mapping above ground live forest biomass (AGB) with a data fusion approach is presented and verified using data from NASA field campaigns near Howland, ME, USA, to assess AGB and LiDAR sampling errors across a regionally representative landscape. We combined SAR and Landsat-derived optical (passive optical) image data to identify forest patches, and used image and simulated spaceborne LiDAR data to compute AGB and estimate LiDAR sampling error for forest patches and 100m, 250m, 500m, and 1km grid cells. Forest patches were delineated with Landsat-derived data and airborne SAR imagery, and simulated spaceborne LiDAR (SSL) data were derived from orbit and cloud cover simulations and airborne data from NASA's Laser Vegetation Imaging Sensor (L VIS). At both the patch and grid scales, we evaluated differences in AGB estimation and sampling error from the combined use of LiDAR with both SAR and passive optical and with either SAR or passive optical alone. This data fusion approach demonstrates that incorporating forest patches into the AGB mapping framework can provide sub-grid forest information for coarser grid-level AGB reporting, and that combining simulated spaceborne LiDAR with SAR and passive optical data are most useful for estimating AGB when measurements from LiDAR are limited because they minimized

  2. Utilizing artificial neural networks in MATLAB to achieve parts-per-billion mass measurement accuracy with a fourier transform ion cyclotron resonance mass spectrometer.

    PubMed

    Williams, D Keith; Kovach, Alexander L; Muddiman, David C; Hanck, Kenneth W

    2009-07-01

    Fourier transform ion cyclotron resonance mass spectrometry has the ability to realize exceptional mass measurement accuracy (MMA); MMA is one of the most significant attributes of mass spectrometric measurements as it affords extraordinary molecular specificity. However, due to space-charge effects, the achievable MMA significantly depends on the total number of ions trapped in the ICR cell for a particular measurement, as well as relative ion abundance of a given species. Artificial neural network calibration in conjunction with automatic gain control (AGC) is utilized in these experiments to formally account for the differences in total ion population in the ICR cell between the external calibration spectra and experimental spectra. In addition, artificial neural network calibration is used to account for both differences in total ion population in the ICR cell as well as relative ion abundance of a given species, which also affords mean MMA values at the parts-per-billion level.

  3. Practical Classification Guidelines for Diabetes in patients treated with insulin: a cross-sectional study of the accuracy of diabetes diagnosis

    PubMed Central

    Hope, Suzy V; Wienand-Barnett, Sophie; Shepherd, Maggie; King, Sophie M; Fox, Charles; Khunti, Kamlesh; Oram, Richard A; Knight, Bea A; Hattersley, Andrew T; Jones, Angus G; Shields, Beverley M

    2016-01-01

    Background Differentiating between type 1 and type 2 diabetes is fundamental to ensuring appropriate management of patients, but can be challenging, especially when treating with insulin. The 2010 UK Practical Classification Guidelines for Diabetes were developed to help make the differentiation. Aim To assess diagnostic accuracy of the UK guidelines against ‘gold standard’ definitions of type 1 and type 2 diabetes based on measured C-peptide levels. Design and setting In total, 601 adults with insulin-treated diabetes and diabetes duration ≥5 years were recruited in Devon, Northamptonshire, and Leicestershire. Method Baseline information and home urine sample were collected. Urinary C-peptide creatinine ratio (UCPCR) measures endogenous insulin production. Gold standard type 1 diabetes was defined as continuous insulin treatment within 3 years of diagnosis and absolute insulin deficiency (UCPCR<0.2 nmol/mmol ≥5 years post-diagnosis); all others classed as having type 2 diabetes. Diagnostic performance of the clinical criteria was assessed and other criteria explored using receiver operating characteristic (ROC) curves. Results UK guidelines correctly classified 86% of participants. Most misclassifications occurred in patients classed as having type 1 diabetes who had significant endogenous insulin levels (57 out of 601; 9%); most in those diagnosed ≥35 years and treated with insulin from diagnosis, where 37 out of 66 (56%) were misclassified. Time to insulin and age at diagnosis performed best in predicting long-term endogenous insulin production (ROC AUC = 0.904 and 0.871); BMI was a less strong predictor of diabetes type (AUC = 0.824). Conclusion Current UK guidelines provide a pragmatic clinical approach to classification reflecting long-term endogenous insulin production; caution is needed in older patients commencing insulin from diagnosis, where misclassification rates are increased. PMID:27080317

  4. Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests

    PubMed Central

    2011-01-01

    Background Dementia and cognitive impairment associated with aging are a major medical and social concern. Neuropsychological testing is a key element in the diagnostic procedures of Mild Cognitive Impairment (MCI), but has presently a limited value in the prediction of progression to dementia. We advance the hypothesis that newer statistical classification methods derived from data mining and machine learning methods like Neural Networks, Support Vector Machines and Random Forests can improve accuracy, sensitivity and specificity of predictions obtained from neuropsychological testing. Seven non parametric classifiers derived from data mining methods (Multilayer Perceptrons Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, CART, CHAID and QUEST Classification Trees and Random Forests) were compared to three traditional classifiers (Linear Discriminant Analysis, Quadratic Discriminant Analysis and Logistic Regression) in terms of overall classification accuracy, specificity, sensitivity, Area under the ROC curve and Press'Q. Model predictors were 10 neuropsychological tests currently used in the diagnosis of dementia. Statistical distributions of classification parameters obtained from a 5-fold cross-validation were compared using the Friedman's nonparametric test. Results Press' Q test showed that all classifiers performed better than chance alone (p < 0.05). Support Vector Machines showed the larger overall classification accuracy (Median (Me) = 0.76) an area under the ROC (Me = 0.90). However this method showed high specificity (Me = 1.0) but low sensitivity (Me = 0.3). Random Forest ranked second in overall accuracy (Me = 0.73) with high area under the ROC (Me = 0.73) specificity (Me = 0.73) and sensitivity (Me = 0.64). Linear Discriminant Analysis also showed acceptable overall accuracy (Me = 0.66), with acceptable area under the ROC (Me = 0.72) specificity (Me = 0.66) and sensitivity (Me = 0.64). The remaining classifiers showed

  5. Relative significance of heat transfer processes to quantify tradeoffs between complexity and accuracy of energy simulations with a building energy use patterns classification

    NASA Astrophysics Data System (ADS)

    Heidarinejad, Mohammad

    This dissertation develops rapid and accurate building energy simulations based on a building classification that identifies and focuses modeling efforts on most significant heat transfer processes. The building classification identifies energy use patterns and their contributing parameters for a portfolio of buildings. The dissertation hypothesis is "Building classification can provide minimal required inputs for rapid and accurate energy simulations for a large number of buildings". The critical literature review indicated there is lack of studies to (1) Consider synoptic point of view rather than the case study approach, (2) Analyze influence of different granularities of energy use, (3) Identify key variables based on the heat transfer processes, and (4) Automate the procedure to quantify model complexity with accuracy. Therefore, three dissertation objectives are designed to test out the dissertation hypothesis: (1) Develop different classes of buildings based on their energy use patterns, (2) Develop different building energy simulation approaches for the identified classes of buildings to quantify tradeoffs between model accuracy and complexity, (3) Demonstrate building simulation approaches for case studies. Penn State's and Harvard's campus buildings as well as high performance LEED NC office buildings are test beds for this study to develop different classes of buildings. The campus buildings include detailed chilled water, electricity, and steam data, enabling to classify buildings into externally-load, internally-load, or mixed-load dominated. The energy use of the internally-load buildings is primarily a function of the internal loads and their schedules. Externally-load dominated buildings tend to have an energy use pattern that is a function of building construction materials and outdoor weather conditions. However, most of the commercial medium-sized office buildings have a mixed-load pattern, meaning the HVAC system and operation schedule dictate

  6. Landsat wildland mapping accuracy

    USGS Publications Warehouse

    Todd, William J.; Gehring, Dale G.; Haman, J. F.

    1980-01-01

    A Landsat-aided classification of ten wildland resource classes was developed for the Shivwits Plateau region of the Lake Mead National Recreation Area. Single stage cluster sampling (without replacement) was used to verify the accuracy of each class.

  7. Risk Assessment of Head Start Children with the Brigance K&1 Screen: Differential Performance by Sex, Age, and Predictive Accuracy for Early School Achievement and Special Education Placement.

    ERIC Educational Resources Information Center

    Mantzicopoulos, Panayota

    1999-01-01

    Examined differences in performance as well as reliability and validity indices for 256 Head Start children screened with Brigance K&1 screen. Found high overall test consistency, but considerable variability across subscales. Classification analyses established that the Brigance was not completely accurate in predicting early school…

  8. Hyperspectral image classification using functional data analysis.

    PubMed

    Li, Hong; Xiao, Guangrun; Xia, Tian; Tang, Y Y; Li, Luoqing

    2014-09-01

    The large number of spectral bands acquired by hyperspectral imaging sensors allows us to better distinguish many subtle objects and materials. Unlike other classical hyperspectral image classification methods in the multivariate analysis framework, in this paper, a novel method using functional data analysis (FDA) for accurate classification of hyperspectral images has been proposed. The central idea of FDA is to treat multivariate data as continuous functions. From this perspective, the spectral curve of each pixel in the hyperspectral images is naturally viewed as a function. This can be beneficial for making full use of the abundant spectral information. The relevance between adjacent pixel elements in the hyperspectral images can also be utilized reasonably. Functional principal component analysis is applied to solve the classification problem of these functions. Experimental results on three hyperspectral images show that the proposed method can achieve higher classification accuracies in comparison to some state-of-the-art hyperspectral image classification methods.

  9. Video genre classification using multimodal features

    NASA Astrophysics Data System (ADS)

    Jin, Sung Ho; Bae, Tae Meon; Choo, Jin Ho; Ro, Yong Man

    2003-12-01

    We propose a video genre classification method using multimodal features. The proposed method is applied for the preprocessing of automatic video summarization or the retrieval and classification of broadcasting video contents. Through a statistical analysis of low-level and middle-level audio-visual features in video, the proposed method can achieve good performance in classifying several broadcasting genres such as cartoon, drama, music video, news, and sports. In this paper, we adopt MPEG-7 audio-visual descriptors as multimodal features of video contents and evaluate the performance of the classification by feeding the features into a decision tree-based classifier which is trained by CART. The experimental results show that the proposed method can recognize several broadcasting video genres with a high accuracy and the classification performance with multimodal features is superior to the one with unimodal features in the genre classification.

  10. Assessment of the Thematic Accuracy of Land Cover Maps

    NASA Astrophysics Data System (ADS)

    Höhle, J.

    2015-08-01

    Several land cover maps are generated from aerial imagery and assessed by different approaches. The test site is an urban area in Europe for which six classes (`building', `hedge and bush', `grass', `road and parking lot', `tree', `wall and car port') had to be derived. Two classification methods were applied (`Decision Tree' and `Support Vector Machine') using only two attributes (height above ground and normalized difference vegetation index) which both are derived from the images. The assessment of the thematic accuracy applied a stratified design and was based on accuracy measures such as user's and producer's accuracy, and kappa coefficient. In addition, confidence intervals were computed for several accuracy measures. The achieved accuracies and confidence intervals are thoroughly analysed and recommendations are derived from the gained experiences. Reliable reference values are obtained using stereovision, false-colour image pairs, and positioning to the checkpoints with 3D coordinates. The influence of the training areas on the results is studied. Cross validation has been tested with a few reference points in order to derive approximate accuracy measures. The two classification methods perform equally for five classes. Trees are classified with a much better accuracy and a smaller confidence interval by means of the decision tree method. Buildings are classified by both methods with an accuracy of 99% (95% CI: 95%-100%) using independent 3D checkpoints. The average width of the confidence interval of six classes was 14% of the user's accuracy.

  11. Improving crop classification through attention to the timing of airborne radar acquisitions

    NASA Technical Reports Server (NTRS)

    Brisco, B.; Ulaby, F. T.; Protz, R.

    1984-01-01

    Radar remote sensors may provide valuable input to crop classification procedures because of (1) their independence of weather conditions and solar illumination, and (2) their ability to respond to differences in crop type. Manual classification of multidate synthetic aperture radar (SAR) imagery resulted in an overall accuracy of 83 percent for corn, forest, grain, and 'other' cover types. Forests and corn fields were identified with accuracies approaching or exceeding 90 percent. Grain fields and 'other' fields were often confused with each other, resulting in classification accuracies of 51 and 66 percent, respectively. The 83 percent correct classification represents a 10 percent improvement when compared to similar SAR data for the same area collected at alternate time periods in 1978. These results demonstrate that improvements in crop classification accuracy can be achieved with SAR data by synchronizing data collection times with crop growth stages in order to maximize differences in the geometric and dielectric properties of the cover types of interest.

  12. Identification of Children with Language Impairment: Investigating the Classification Accuracy of the MacArthur-Bates Communicative Development Inventories, Level III

    ERIC Educational Resources Information Center

    Skarakis-Doyle, Elizabeth; Campbell, Wenonah; Dempsey, Lynn

    2009-01-01

    Purpose: This study tested the accuracy with which the MacArthur-Bates Communicative Development Inventories, Level III (CDI-III), a parent report measure of language ability, discriminated children with language impairment from those developing language typically. Method: Parents of 58 children, 49 with typically developing language (age 30 to 42…

  13. Wavelet-based asphalt concrete texture grading and classification

    NASA Astrophysics Data System (ADS)

    Almuntashri, Ali; Agaian, Sos

    2011-03-01

    In this Paper, we introduce a new method for evaluation, quality control, and automatic grading of texture images representing different textural classes of Asphalt Concrete (AC). Also, we present a new asphalt concrete texture grading, wavelet transform, fractal, and Support Vector Machine (SVM) based automatic classification and recognition system. Experimental results were simulated using different cross-validation techniques and achieved an average classification accuracy of 91.4.0 % in a set of 150 images belonging to five different texture grades.

  14. Compensatory neurofuzzy model for discrete data classification in biomedical

    NASA Astrophysics Data System (ADS)

    Ceylan, Rahime

    2015-03-01

    Biomedical data is separated to two main sections: signals and discrete data. So, studies in this area are about biomedical signal classification or biomedical discrete data classification. There are artificial intelligence models which are relevant to classification of ECG, EMG or EEG signals. In same way, in literature, many models exist for classification of discrete data taken as value of samples which can be results of blood analysis or biopsy in medical process. Each algorithm could not achieve high accuracy rate on classification of signal and discrete data. In this study, compensatory neurofuzzy network model is presented for classification of discrete data in biomedical pattern recognition area. The compensatory neurofuzzy network has a hybrid and binary classifier. In this system, the parameters of fuzzy systems are updated by backpropagation algorithm. The realized classifier model is conducted to two benchmark datasets (Wisconsin Breast Cancer dataset and Pima Indian Diabetes dataset). Experimental studies show that compensatory neurofuzzy network model achieved 96.11% accuracy rate in classification of breast cancer dataset and 69.08% accuracy rate was obtained in experiments made on diabetes dataset with only 10 iterations.

  15. Effect of various binning methods and ROI sizes on the accuracy of the automatic classification system for differentiation between diffuse infiltrative lung diseases on the basis of texture features at HRCT

    NASA Astrophysics Data System (ADS)

    Kim, Namkug; Seo, Joon Beom; Sung, Yu Sub; Park, Bum-Woo; Lee, Youngjoo; Park, Seong Hoon; Lee, Young Kyung; Kang, Suk-Ho

    2008-03-01

    To find optimal binning, variable binning size linear binning (LB) and non-linear binning (NLB) methods were tested. In case of small binning size (Q <= 10), NLB shows significant better accuracy than the LB. K-means NLB (Q = 26) is statistically significant better than every LB. To find optimal binning method and ROI size of the automatic classification system for differentiation between diffuse infiltrative lung diseases on the basis of textural analysis at HRCT Six-hundred circular regions of interest (ROI) with 10, 20, and 30 pixel diameter, comprising of each 100 ROIs representing six regional disease patterns (normal, NL; ground-glass opacity, GGO; reticular opacity, RO; honeycombing, HC; emphysema, EMPH; and consolidation, CONS) were marked by an experienced radiologist from HRCT images. Histogram (mean) and co-occurrence matrix (mean and SD of angular second moment, contrast, correlation, entropy, and inverse difference momentum) features were employed to test binning and ROI effects. To find optimal binning, variable binning size LB (bin size Q: 4~30, 32, 64, 128, 144, 196, 256, 384) and NLB (Q: 4~30) methods (K-means, and Fuzzy C-means clustering) were tested. For automated classification, a SVM classifier was implemented. To assess cross-validation of the system, a five-folding method was used. Each test was repeatedly performed twenty times. Overall accuracies with every combination of variable ROIs, and binning sizes were statistically compared. In case of small binning size (Q <= 10), NLB shows significant better accuracy than the LB. K-means NLB (Q = 26) is statistically significant better than every LB. In case of 30x30 ROI size and most of binning size, the K-means method showed better than other NLB and LB methods. When optimal binning and other parameters were set, overall sensitivity of the classifier was 92.85%. The sensitivity and specificity of the system for each class were as follows: NL, 95%, 97.9%; GGO, 80%, 98.9%; RO 85%, 96.9%; HC, 94

  16. Regional manifold learning for disease classification.

    PubMed

    Ye, Dong Hye; Desjardins, Benoit; Hamm, Jihun; Litt, Harold; Pohl, Kilian M

    2014-06-01

    While manifold learning from images itself has become widely used in medical image analysis, the accuracy of existing implementations suffers from viewing each image as a single data point. To address this issue, we parcellate images into regions and then separately learn the manifold for each region. We use the regional manifolds as low-dimensional descriptors of high-dimensional morphological image features, which are then fed into a classifier to identify regions affected by disease. We produce a single ensemble decision for each scan by the weighted combination of these regional classification results. Each weight is determined by the regional accuracy of detecting the disease. When applied to cardiac magnetic resonance imaging of 50 normal controls and 50 patients with reconstructive surgery of Tetralogy of Fallot, our method achieves significantly better classification accuracy than approaches learning a single manifold across the entire image domain.

  17. Classification of ASKAP Vast Radio Light Curves

    NASA Technical Reports Server (NTRS)

    Rebbapragada, Umaa; Lo, Kitty; Wagstaff, Kiri L.; Reed, Colorado; Murphy, Tara; Thompson, David R.

    2012-01-01

    The VAST survey is a wide-field survey that observes with unprecedented instrument sensitivity (0.5 mJy or lower) and repeat cadence (a goal of 5 seconds) that will enable novel scientific discoveries related to known and unknown classes of radio transients and variables. Given the unprecedented observing characteristics of VAST, it is important to estimate source classification performance, and determine best practices prior to the launch of ASKAP's BETA in 2012. The goal of this study is to identify light curve characterization and classification algorithms that are best suited for archival VAST light curve classification. We perform our experiments on light curve simulations of eight source types and achieve best case performance of approximately 90% accuracy. We note that classification performance is most influenced by light curve characterization rather than classifier algorithm.

  18. Classification of ASKAP VAST Radio Light Curves†

    NASA Astrophysics Data System (ADS)

    Rebbapragada, Umaa; Lo, Kitty; Wagstaff, Kiri L.; Reed, Colorado; Murphy, Tara; Thompson, David R.

    2012-04-01

    The VAST survey is a wide-field survey that observes with unprecedented instrument sensitivity (0.5 mJy or lower) and repeat cadence (a goal of 5 seconds) that will enable novel scientific discoveries related to known and unknown classes of radio transients and variables. Given the unprecedented observing characteristics of VAST, it is important to estimate source classification performance, and determine best practices prior to the launch of ASKAP's BETA in 2012. The goal of this study is to identify light-curve characterization and classification algorithms that are best suited for archival VAST light-curve classification. We perform our experiments on light-curve simulations of eight source types and achieve best-case performance of approximately 90% accuracy. We note that classification performance is most influenced by light-curve characterization rather than classifier algorithm.

  19. Injury narrative text classification using factorization model

    PubMed Central

    2015-01-01

    Narrative text is a useful way of identifying injury circumstances from the routine emergency department data collections. Automatically classifying narratives based on machine learning techniques is a promising technique, which can consequently reduce the tedious manual classification process. Existing works focus on using Naive Bayes which does not always offer the best performance. This paper proposes the Matrix Factorization approaches along with a learning enhancement process for this task. The results are compared with the performance of various other classification approaches. The impact on the classification results from the parameters setting during the classification of a medical text dataset is discussed. With the selection of right dimension k, Non Negative Matrix Factorization-model method achieves 10 CV accuracy of 0.93. PMID:26043671

  20. Multi-source remotely sensed data fusion for improving land cover classification

    NASA Astrophysics Data System (ADS)

    Chen, Bin; Huang, Bo; Xu, Bing

    2017-02-01

    Although many advances have been made in past decades, land cover classification of fine-resolution remotely sensed (RS) data integrating multiple temporal, angular, and spectral features remains limited, and the contribution of different RS features to land cover classification accuracy remains uncertain. We proposed to improve land cover classification accuracy by integrating multi-source RS features through data fusion. We further investigated the effect of different RS features on classification performance. The results of fusing Landsat-8 Operational Land Imager (OLI) data with Moderate Resolution Imaging Spectroradiometer (MODIS), China Environment 1A series (HJ-1A), and Advanced Spaceborne Thermal Emission and Reflection (ASTER) digital elevation model (DEM) data, showed that the fused data integrating temporal, spectral, angular, and topographic features achieved better land cover classification accuracy than the original RS data. Compared with the topographic feature, the temporal and angular features extracted from the fused data played more important roles in classification performance, especially those temporal features containing abundant vegetation growth information, which markedly increased the overall classification accuracy. In addition, the multispectral and hyperspectral fusion successfully discriminated detailed forest types. Our study provides a straightforward strategy for hierarchical land cover classification by making full use of available RS data. All of these methods and findings could be useful for land cover classification at both regional and global scales.

  1. Exploring the impact of wavelet-based denoising in the classification of remote sensing hyperspectral images

    NASA Astrophysics Data System (ADS)

    Quesada-Barriuso, Pablo; Heras, Dora B.; Argüello, Francisco

    2016-10-01

    The classification of remote sensing hyperspectral images for land cover applications is a very intensive topic. In the case of supervised classification, Support Vector Machines (SVMs) play a dominant role. Recently, the Extreme Learning Machine algorithm (ELM) has been extensively used. The classification scheme previously published by the authors, and called WT-EMP, introduces spatial information in the classification process by means of an Extended Morphological Profile (EMP) that is created from features extracted by wavelets. In addition, the hyperspectral image is denoised in the 2-D spatial domain, also using wavelets and it is joined to the EMP via a stacked vector. In this paper, the scheme is improved achieving two goals. The first one is to reduce the classification time while preserving the accuracy of the classification by using ELM instead of SVM. The second one is to improve the accuracy results by performing not only a 2-D denoising for every spectral band, but also a previous additional 1-D spectral signature denoising applied to each pixel vector of the image. For each denoising the image is transformed by applying a 1-D or 2-D wavelet transform, and then a NeighShrink thresholding is applied. Improvements in terms of classification accuracy are obtained, especially for images with close regions in the classification reference map, because in these cases the accuracy of the classification in the edges between classes is more relevant.

  2. Agricultural Land Use classification from Envisat MERIS

    NASA Astrophysics Data System (ADS)

    Brodsky, L.; Kodesova, R.

    2009-04-01

    This study focuses on evaluation of a crop classification from middle-resolution images (Envisat MERIS) at national level. The main goal of such Land Use product is to provid spatial data for optimisation of monitoring of surface and groundwater pollution in the Czech Republic caused by pesticides use in agriculture. As there is a lack of spatial data on the pesticide use and their distribution, the localisation can be done according to the crop cover on arable land derived from the remote sensing images. Often high resolution data are used for agricultural Land Use classification but only at regional or local level. Envisat MERIS data, due to the wide satellite swath, can be used also at national level. The high temporal and also spectral resolution of MERIS data has indisputable advantage for crop classification. Methodology of a pixel-based MERIS classification applying an artificial neural-network (ANN) technique was proposed and performed at a national level, the Czech Republic. Five crop groups were finally selected - winter crops, spring crops, summer crops and other crops to be classified. Classification models included a linear, radial basis function (RBF) and a multi-layer percepton (MLP) ANN with 50 networks tested in training. The training data set consisted of about 200 samples per class, on which bootstrap resampling was applied. Selection of a subset of independent variables (Meris spectral channels) was used in the procedure. The best selected ANN model (MLP: 3 in, 13 hidden, 3 out) resulted in very good performance (correct classification rate 0.974, error 0.103) applying three crop types data set. In the next step data set with five crop types was evaluated. The ANN model (MLP: 5 in, 12 hidden, 5 out) performance was also very good (correct classification rate 0.930, error 0.370). The study showed, that while accuracy of about 80 % was achieved at pixel level when classifying only three crops, accuracy of about 70 % was achieved for five crop

  3. Temporal context in floristic classification

    NASA Astrophysics Data System (ADS)

    Fitzgerald, R. W.; Lees, B. G.

    1996-11-01

    Multi-temporal remote sensing data present a number of significant problems for the statistical and spatial competence of a classifier. Ideally, a classifier of multi-temporal data should be temporally invariant. It must have the capacity to account for the variations in season, growth cycle, radiometric, and atmospheric conditions at any point in time when classifying the land cover. This paper tests two methods of creating a temporally invariant classifier based on the pattern recognition capabilities of a neural network. A suite of twelve multi-temporal datasets spread over 5 yr along with a comprehensive mix of environmental variables are fused into floristic classification images by the neural network. Uncertainties in the classifications are addressed explicitly with a confidence mask generated from the fuzzy membership value's output by the neural network. These confidence masks are used to produce constrained classification images. The overall accuracy percentage achieved from a study site containing highly disturbed undulating terrain averages 60%. The first method of training, sequential learning of temporal context, is tested by an examination of the step-by-step evolution of the sequential training process. This reveals that the sequential classifier may not have learned about time, because time was constant during each network training session. It also suggests that there are optimal times during the annual cycle to train the classifier for particular floristic classes. The second method of training the classifier is randomised exposure to the entire temporal training suite. Time was now a fluctuating input variable during the network training process. This method produced the best spatially accurate results. The performance of this classifier as a temporally invariant classifier is tested amongst four multi-temporal datasets with encouraging results. The classifier consistently achieved an overall accuracy percentage of 60%. The pairwise predicted

  4. High-accuracy user identification using EEG biometrics.

    PubMed

    Koike-Akino, Toshiaki; Mahajan, Ruhi; Marks, Tim K; Ye Wang; Watanabe, Shinji; Tuzel, Oncel; Orlik, Philip

    2016-08-01

    We analyze brain waves acquired through a consumer-grade EEG device to investigate its capabilities for user identification and authentication. First, we show the statistical significance of the P300 component in event-related potential (ERP) data from 14-channel EEGs across 25 subjects. We then apply a variety of machine learning techniques, comparing the user identification performance of various different combinations of a dimensionality reduction technique followed by a classification algorithm. Experimental results show that an identification accuracy of 72% can be achieved using only a single 800 ms ERP epoch. In addition, we demonstrate that the user identification accuracy can be significantly improved to more than 96.7% by joint classification of multiple epochs.

  5. Geographic stacking: Decision fusion to increase global land cover map accuracy

    NASA Astrophysics Data System (ADS)

    Clinton, Nicholas; Yu, Le; Gong, Peng

    2015-05-01

    Techniques to combine multiple classifier outputs is an established sub-discipline in data mining, referred to as "stacking," "ensemble classification," or "meta-learning." Here we describe how stacking of geographically allocated classifications can create a map composite of higher accuracy than any of the individual classifiers. We used both voting algorithms and trainable classifiers with a set of validation data to combine individual land cover maps. We describe the generality of this setup in terms of existing algorithms and accuracy assessment procedures. This method has the advantage of not requiring posterior probabilities or level of support for predicted class labels. We demonstrate the technique using Landsat based, 30-meter land cover maps, the highest resolution, globally available product of this kind. We used globally distributed validation samples to composite the maps and compute accuracy. We show that geographic stacking can improve individual map accuracy by up to 6.6%. The voting methods can also achieve higher accuracy than the best of the input classifications. Accuracies from different classifiers, input data, and output type are compared. The results are illustrated on a Landsat scene in California, USA. The compositing technique described here has broad applicability in remote sensing based map production and geographic classification.

  6. Ground Truth Sampling and LANDSAT Accuracy Assessment

    NASA Technical Reports Server (NTRS)

    Robinson, J. W.; Gunther, F. J.; Campbell, W. J.

    1982-01-01

    It is noted that the key factor in any accuracy assessment of remote sensing data is the method used for determining the ground truth, independent of the remote sensing data itself. The sampling and accuracy procedures developed for nuclear power plant siting study are described. The purpose of the sampling procedure was to provide data for developing supervised classifications for two study sites and for assessing the accuracy of that and the other procedures used. The purpose of the accuracy assessment was to allow the comparison of the cost and accuracy of various classification procedures as applied to various data types.

  7. An Epidemiological Study of Learning Disabled Adolescents in Secondary Schools: Classification and Discrimination of Learning Disabled and Low-Achieving Adolescents.

    ERIC Educational Resources Information Center

    Warner, Michael M.; And Others

    The paper, part of a research series on learning disabled (LD) adolescents, reports findings of a study on the variables which added significantly to group discrimination after ability and achievement had been controlled. Ss were 56 LD and 51 low achieving (LA) students in grades 7 through 12, their parents, and their regular classroom teachers.…

  8. LDA boost classification: boosting by topics

    NASA Astrophysics Data System (ADS)

    Lei, La; Qiao, Guo; Qimin, Cao; Qitao, Li

    2012-12-01

    AdaBoost is an efficacious classification algorithm especially in text categorization (TC) tasks. The methodology of setting up a classifier committee and voting on the documents for classification can achieve high categorization precision. However, traditional Vector Space Model can easily lead to the curse of dimensionality and feature sparsity problems; so it affects classification performance seriously. This article proposed a novel classification algorithm called LDABoost based on boosting ideology which uses Latent Dirichlet Allocation (LDA) to modeling the feature space. Instead of using words or phrase, LDABoost use latent topics as the features. In this way, the feature dimension is significantly reduced. Improved Naïve Bayes (NB) is designed as the weaker classifier which keeps the efficiency advantage of classic NB algorithm and has higher precision. Moreover, a two-stage iterative weighted method called Cute Integration in this article is proposed for improving the accuracy by integrating weak classifiers into strong classifier in a more rational way. Mutual Information is used as metrics of weights allocation. The voting information and the categorization decision made by basis classifiers are fully utilized for generating the strong classifier. Experimental results reveals LDABoost making categorization in a low-dimensional space, it has higher accuracy than traditional AdaBoost algorithms and many other classic classification algorithms. Moreover, its runtime consumption is lower than different versions of AdaBoost, TC algorithms based on support vector machine and Neural Networks.

  9. Automated protein classification using consensus decision.

    PubMed

    Can, Tolga; Camoğlu, Orhan; Singh, Ambuj K; Wang, Yuan-Fang

    2004-01-01

    We propose a novel technique for automatically generating the SCOP classification of a protein structure with high accuracy. High accuracy is achieved by combining the decisions of multiple methods using the consensus of a committee (or an ensemble) classifier. Our technique is rooted in machine learning which shows that by judicially employing component classifiers, an ensemble classifier can be constructed to outperform its components. We use two sequence- and three structure-comparison tools as component classifiers. Given a protein structure, using the joint hypothesis, we first determine if the protein belongs to an existing category (family, superfamily, fold) in the SCOP hierarchy. For the proteins that are predicted as members of the existing categories, we compute their family-, superfamily-, and fold-level classifications using the consensus classifier. We show that we can significantly improve the classification accuracy compared to the individual component classifiers. In particular, we achieve error rates that are 3-12 times less than the individual classifiers' error rates at the family level, 1.5-4.5 times less at the superfamily level, and 1.1-2.4 times less at the fold level.

  10. Enhancing the Classification Accuracy of IP Geolocation

    DTIC Science & Technology

    2013-10-01

    in cloud infrastructure services. For example, a Dropbox user may require their data to be hosted on servers in San Francisco, but the data’s true...location may actually be in Tennessee (see Fig. 1). Users of cloud computing deploy Virtual Machines (VM) on a cloud providers infrastructure without...datacenters, as specified by a Service Level Agreement (SLA). Cloud users can use IP geolocation to independently verify data confidentiality by

  11. Discoveries, Achievements, and Personalities of the Women Who Evolved the Harvard Classification of Stellar Spectra: Williamina Fleming, Antonia Maury, and Annie Jump Cannon.

    NASA Astrophysics Data System (ADS)

    Welther, Barbara L.

    2010-01-01

    In 1915, the year in which Cannon (1863-1941) completed her work of classifying stars for The Henry Draper Catalogue, she published a popular article entitled, "Pioneering in the Classification of Stellar Spectra.” In it she gave a historical overview of the field in nineteenth-century Europe. She also detailed the context for the structured and routine work she and her colleagues had been engaged in for several years in America. The motivators that kept Cannon and the other women working diligently were the exciting prospect of making new discoveries, the reward of publicity, and their own personal pride. Usually, the discoveries consisted of finding a peculiar type of spectrum and identifying the star as a nova or variable. Such a discovery often resulted in a newspaper headline about the star and a story about the discoverer. This paper will outline the contributions each woman made to the classification system, her style of working, the papers she wrote and published, and the rewards she reaped for her dedication to the field.

  12. Visual traffic surveillance framework: classification to event detection

    NASA Astrophysics Data System (ADS)

    Ambardekar, Amol; Nicolescu, Mircea; Bebis, George; Nicolescu, Monica

    2013-10-01

    Visual traffic surveillance using computer vision techniques can be noninvasive, automated, and cost effective. Traffic surveillance systems with the ability to detect, count, and classify vehicles can be employed in gathering traffic statistics and achieving better traffic control in intelligent transportation systems. However, vehicle classification poses a difficult problem as vehicles have high intraclass variation and relatively low interclass variation. Five different object recognition techniques are investigated: principal component analysis (PCA)+difference from vehicle space, PCA+difference in vehicle space, PCA+support vector machine, linear discriminant analysis, and constellation-based modeling applied to the problem of vehicle classification. Three of the techniques that performed well were incorporated into a unified traffic surveillance system for online classification of vehicles, which uses tracking results to improve the classification accuracy. To evaluate the accuracy of the system, 31 min of traffic video containing multilane traffic intersection was processed. It was possible to achieve classification accuracy as high as 90.49% while classifying correctly tracked vehicles into four classes: cars, SUVs/vans, pickup trucks, and buses/semis. While processing a video, our system also recorded important traffic parameters such as the appearance, speed, trajectory of a vehicle, etc. This information was later used in a search assistant tool to find interesting traffic events.

  13. Classification of urban features using airborne hyperspectral data

    NASA Astrophysics Data System (ADS)

    Ganesh Babu, Bharath

    Accurate mapping and modeling of urban environments are critical for their efficient and successful management. Superior understanding of complex urban environments is made possible by using modern geospatial technologies. This research focuses on thematic classification of urban land use and land cover (LULC) using 248 bands of 2.0 meter resolution hyperspectral data acquired from an airborne imaging spectrometer (AISA+) on 24th July 2006 in and near Terre Haute, Indiana. Three distinct study areas including two commercial classes, two residential classes, and two urban parks/recreational classes were selected for classification and analysis. Four commonly used classification methods -- maximum likelihood (ML), extraction and classification of homogeneous objects (ECHO), spectral angle mapper (SAM), and iterative self organizing data analysis (ISODATA) - were applied to each data set. Accuracy assessment was conducted and overall accuracies were compared between the twenty four resulting thematic maps. With the exception of SAM and ISODATA in a complex commercial area, all methods employed classified the designated urban features with more than 80% accuracy. The thematic classification from ECHO showed the best agreement with ground reference samples. The residential area with relatively homogeneous composition was classified consistently with highest accuracy by all four of the classification methods used. The average accuracy amongst the classifiers was 93.60% for this area. When individually observed, the complex recreational area (Deming Park) was classified with the highest accuracy by ECHO, with an accuracy of 96.80% and 96.10% Kappa. The average accuracy amongst all the classifiers was 92.07%. The commercial area with relatively high complexity was classified with the least accuracy by all classifiers. The lowest accuracy was achieved by SAM at 63.90% with 59.20% Kappa. This was also the lowest accuracy in the entire analysis. This study demonstrates the

  14. D Land Cover Classification Based on Multispectral LIDAR Point Clouds

    NASA Astrophysics Data System (ADS)

    Zou, Xiaoliang; Zhao, Guihua; Li, Jonathan; Yang, Yuanxi; Fang, Yong

    2016-06-01

    Multispectral Lidar System can emit simultaneous laser pulses at the different wavelengths. The reflected multispectral energy is captured through a receiver of the sensor, and the return signal together with the position and orientation information of sensor is recorded. These recorded data are solved with GNSS/IMU data for further post-processing, forming high density multispectral 3D point clouds. As the first commercial multispectral airborne Lidar sensor, Optech Titan system is capable of collecting point clouds data from all three channels at 532nm visible (Green), at 1064 nm near infrared (NIR) and at 1550nm intermediate infrared (IR). It has become a new source of data for 3D land cover classification. The paper presents an Object Based Image Analysis (OBIA) approach to only use multispectral Lidar point clouds datasets for 3D land cover classification. The approach consists of three steps. Firstly, multispectral intensity images are segmented into image objects on the basis of multi-resolution segmentation integrating different scale parameters. Secondly, intensity objects are classified into nine categories by using the customized features of classification indexes and a combination the multispectral reflectance with the vertical distribution of object features. Finally, accuracy assessment is conducted via comparing random reference samples points from google imagery tiles with the classification results. The classification results show higher overall accuracy for most of the land cover types. Over 90% of overall accuracy is achieved via using multispectral Lidar point clouds for 3D land cover classification.

  15. Decision forests for machine learning classification of large, noisy seafloor feature sets

    NASA Astrophysics Data System (ADS)

    Lawson, Ed; Smith, Denson; Sofge, Donald; Elmore, Paul; Petry, Frederick

    2017-02-01

    Extremely randomized trees (ET) classifiers, an extension of random forests (RF) are applied to classification of features such as seamounts derived from bathymetry data. This data is characterized by sparse training data from by large noisy features sets such as often found in other geospatial data. A variety of feature metrics may be useful for this task and we use a large number of metrics relevant to the task of finding seamounts. The major significant results to be described include: an outstanding seamount classification accuracy of 97%; an automated process to produce the most useful classification features that are relevant to geophysical scientists (as represented by the feature metrics); demonstration that topography provides the most important data representation for classification. As well as achieving good accuracy in classification, the human-understandable set of metrics generated by the classifier that are most relevant for the results are discussed.

  16. Urban Tree Classification Using Full-Waveform Airborne Laser Scanning

    NASA Astrophysics Data System (ADS)

    Koma, Zs.; Koenig, K.; Höfle, B.

    2016-06-01

    Vegetation mapping in urban environments plays an important role in biological research and urban management. Airborne laser scanning provides detailed 3D geodata, which allows to classify single trees into different taxa. Until now, research dealing with tree classification focused on forest environments. This study investigates the object-based classification of urban trees at taxonomic family level, using full-waveform airborne laser scanning data captured in the city centre of Vienna (Austria). The data set is characterised by a variety of taxa, including deciduous trees (beeches, mallows, plane trees and soapberries) and the coniferous pine species. A workflow for tree object classification is presented using geometric and radiometric features. The derived features are related to point density, crown shape and radiometric characteristics. For the derivation of crown features, a prior detection of the crown base is performed. The effects of interfering objects (e.g. fences and cars which are typical in urban areas) on the feature characteristics and the subsequent classification accuracy are investigated. The applicability of the features is evaluated by Random Forest classification and exploratory analysis. The most reliable classification is achieved by using the combination of geometric and radiometric features, resulting in 87.5% overall accuracy. By using radiometric features only, a reliable classification with accuracy of 86.3% can be achieved. The influence of interfering objects on feature characteristics is identified, in particular for the radiometric features. The results indicate the potential of using radiometric features in urban tree classification and show its limitations due to anthropogenic influences at the same time.

  17. Classification of Physical Activity

    PubMed Central

    Turksoy, Kamuran; Paulino, Thiago Marques Luz; Zaharieva, Dessi P.; Yavelberg, Loren; Jamnik, Veronica; Riddell, Michael C.; Cinar, Ali

    2015-01-01

    Physical activity has a wide range of effects on glucose concentrations in type 1 diabetes (T1D) depending on the type (ie, aerobic, anaerobic, mixed) and duration of activity performed. This variability in glucose responses to physical activity makes the development of artificial pancreas (AP) systems challenging. Automatic detection of exercise type and intensity, and its classification as aerobic or anaerobic would provide valuable information to AP control algorithms. This can be achieved by using a multivariable AP approach where biometric variables are measured and reported to the AP at high frequency. We developed a classification system that identifies, in real time, the exercise intensity and its reliance on aerobic or anaerobic metabolism and tested this approach using clinical data collected from 5 persons with T1D and 3 individuals without T1D in a controlled laboratory setting using a variety of common types of physical activity. The classifier had an average sensitivity of 98.7% for physiological data collected over a range of exercise modalities and intensities in these subjects. The classifier will be added as a new module to the integrated multivariable adaptive AP system to enable the detection of aerobic and anaerobic exercise for enhancing the accuracy of insulin infusion strategies during and after exercise. PMID:26443291

  18. Evaluation of space SAR as a land-cover classification

    NASA Technical Reports Server (NTRS)

    Brisco, B.; Ulaby, F. T.; Williams, T. H. L.

    1985-01-01

    The multidimensional approach to the mapping of land cover, crops, and forests is reported. Dimensionality is achieved by using data from sensors such as LANDSAT to augment Seasat and Shuttle Image Radar (SIR) data, using different image features such as tone and texture, and acquiring multidate data. Seasat, Shuttle Imaging Radar (SIR-A), and LANDSAT data are used both individually and in combination to map land cover in Oklahoma. The results indicates that radar is the best single sensor (72% accuracy) and produces the best sensor combination (97.5% accuracy) for discriminating among five land cover categories. Multidate Seasat data and a single data of LANDSAT coverage are then used in a crop classification study of western Kansas. The highest accuracy for a single channel is achieved using a Seasat scene, which produces a classification accuracy of 67%. Classification accuracy increases to approximately 75% when either a multidate Seasat combination or LANDSAT data in a multisensor combination is used. The tonal and textural elements of SIR-A data are then used both alone and in combination to classify forests into five categories.

  19. A Longitudinal Analysis of Torque and its Relationship to Achievement and Educational Classification among Normal, Disturbed, and Learning-Disabled Children.

    ERIC Educational Resources Information Center

    Alberts, Fred L.; Edwards, Ron P.

    1983-01-01

    Examined the effect of the presence of torque (clockwise circlings with either hand on a visual-motor task) on academic achievement variables among normal, disturbed, and learning-disabled children (N=948). Results indicated no clear relationship between torque and the various academic variables. (LLL)

  20. Structure and context in prostatic gland segmentation and classification.

    PubMed

    Nguyen, Kien; Sarkar, Anindya; Jain, Anil K

    2012-01-01

    A novel gland segmentation and classification scheme applied to an H&E histology image of the prostate tissue is proposed. For gland segmentation, we associate appropriate nuclei objects with each lumen object to create a gland segment. We further extract 22 features to describe the structural information and contextual information for each segment. These features are used to classify a gland segment into one of the three classes: artifact, normal gland and cancer gland. On a dataset of 48 images at 5x magnification (which includes 525 artifacts, 931 normal glands and 1,375 cancer glands), we achieved the following classification accuracies: 93% for artifacts v. true glands; 79% for normal v. cancer glands, and 77% for discriminating all three classes. The proposed method outperforms state of the art methods in terms of segmentation and classification accuracies and computational efficiency.

  1. EEG Channel Selection Using Particle Swarm Optimization for the Classification of Auditory Event-Related Potentials

    PubMed Central

    Hokari, Haruhide

    2014-01-01

    Brain-machine interfaces (BMI) rely on the accurate classification of event-related potentials (ERPs) and their performance greatly depends on the appropriate selection of classifier parameters and features from dense-array electroencephalography (EEG) signals. Moreover, in order to achieve a portable and more compact BMI for practical applications, it is also desirable to use a system capable of accurate classification using information from as few EEG channels as possible. In the present work, we propose a method for classifying P300 ERPs using a combination of Fisher Discriminant Analysis (FDA) and a multiobjective hybrid real-binary Particle Swarm Optimization (MHPSO) algorithm. Specifically, the algorithm searches for the set of EEG channels and classifier parameters that simultaneously maximize the classification accuracy and minimize the number of used channels. The performance of the method is assessed through offline analyses on datasets of auditory ERPs from sound discrimination experiments. The proposed method achieved a higher classification accuracy than that achieved by traditional methods while also using fewer channels. It was also found that the number of channels used for classification can be significantly reduced without greatly compromising the classification accuracy. PMID:24982944

  2. EEG Classification of Different Imaginary Movements within the Same Limb

    PubMed Central

    Yong, Xinyi; Menon, Carlo

    2015-01-01

    The task of discriminating the motor imagery of different movements within the same limb using electroencephalography (EEG) signals is challenging because these imaginary movements have close spatial representations on the motor cortex area. There is, however, a pressing need to succeed in this task. The reason is that the ability to classify different same-limb imaginary movements could increase the number of control dimensions of a brain-computer interface (BCI). In this paper, we propose a 3-class BCI system that discriminates EEG signals corresponding to rest, imaginary grasp movements, and imaginary elbow movements. Besides, the differences between simple motor imagery and goal-oriented motor imagery in terms of their topographical distributions and classification accuracies are also being investigated. To the best of our knowledge, both problems have not been explored in the literature. Based on the EEG data recorded from 12 able-bodied individuals, we have demonstrated that same-limb motor imagery classification is possible. For the binary classification of imaginary grasp and elbow (goal-oriented) movements, the average accuracy achieved is 66.9%. For the 3-class problem of discriminating rest against imaginary grasp and elbow movements, the average classification accuracy achieved is 60.7%, which is greater than the random classification accuracy of 33.3%. Our results also show that goal-oriented imaginary elbow movements lead to a better classification performance compared to simple imaginary elbow movements. This proposed BCI system could potentially be used in controlling a robotic rehabilitation system, which can assist stroke patients in performing task-specific exercises. PMID:25830611

  3. Comparisons of different methods for debris covered glacier classification

    NASA Astrophysics Data System (ADS)

    Tiwari, R. K.; Garg, P. K.; Saini, V.; Shukla, A.

    2016-05-01

    The paper outlines comparisons between different methods for the mapping of debris covered glaciers. The supervised classification method like Maximum Likelihood Classifier (MLC) has been tested using different data set for deriving the glacier area. Along with MLC the semi-automated method like Hierarchical Knowledge Based Classifier (HKBC) has also been used here. All the results were tested for accuracy, processing time and complexities. The results were also tested against the manually digitized boundary. The results suggests that the MLC when used with other ancillary data like geo-morphometric parameters and temperature image takes slightly more time than HKBC due to some to higher amount of post processing time but the output is satisfactory (89 % overall accuracy). Results show that the time taken in different classifications is significantly different which ranges from 1-2 hours in MLC to 5-10 hours in manual digitization. Depending on the classification method, some to large amount of post processing is always required to achieve the crisp glacial boundary. Classical classifier like maximum likelihood classification is less time consuming but the time taken in post-processing is higher than HKBC. Another factor which is important for a better accuracy is the prior knowledge of glacier terrain. In knowledge based classification method, it is required initially to establish crisp rules which are later used during classification, without this per-classification exercise the accuracy may significantly decrease. This is a time consuming procedure (2-3 hours in this case) but a minimal amount of post-processing is required. Thermal and geo-morphometric data when used synergistically, classified glacier boundaries are more crisp and accurate.

  4. An improved methodology for land-cover classification using artificial neural networks and a decision tree classifier

    NASA Astrophysics Data System (ADS)

    Arellano-Neri, Olimpia

    Mapping is essential for the analysis of the land and land-cover dynamics, which influence many environmental processes and properties. When creating land-cover maps it is important to minimize error, since error will propagate into later analyses based upon these land cover maps. The reliability of land cover maps derived from remotely sensed data depends upon an accurate classification. For decades, traditional statistical methods have been applied in land-cover classification with varying degrees of accuracy. One of the most significant developments in the field of land-cover classification using remotely sensed data has been the introduction of Artificial Neural Networks (ANN) procedures. In this research, Artificial Neural Networks were applied to remotely sensed data of the southwestern Ohio region for land-cover classification. Three variants on traditional ANN-based classifiers were explored here: (1) the use of a customized architecture of the neural network in terms of the input layer for each land-cover class, (2) the use of texture analysis to combine spectral information and spatial information which is essential for urban classes, and (3) the use of decision tree (DT) classification to refine the ANN classification and ultimately to achieve a more reliable land-cover thematic map. The objective of this research was to prove that a classification based on Artificial Neural Networks (ANN) and decision tree (DT) would outperform by far the National Land Cover Data (NLCD). The NLCD is a land-cover classification produced by a cooperative effort between the United States Geological Survey (USGS) and the United States Environmental Protection Agency (USEPA). In order to achieve this objective, an accuracy assessment was conducted for both NLCD classification and ANN/DT classification. Error matrices resulting from the accuracy assessments provided overall accuracy, accuracy of each class, omission errors, and commission errors for each classification. The

  5. Improving EEG-Based Driver Fatigue Classification Using Sparse-Deep Belief Networks

    PubMed Central

    Chai, Rifai; Ling, Sai Ho; San, Phyo Phyo; Naik, Ganesh R.; Nguyen, Tuan N.; Tran, Yvonne; Craig, Ashley; Nguyen, Hung T.

    2017-01-01

    This paper presents an improvement of classification performance for electroencephalography (EEG)-based driver fatigue classification between fatigue and alert states with the data collected from 43 participants. The system employs autoregressive (AR) modeling as the features extraction algorithm, and sparse-deep belief networks (sparse-DBN) as the classification algorithm. Compared to other classifiers, sparse-DBN is a semi supervised learning method which combines unsupervised learning for modeling features in the pre-training layer and supervised learning for classification in the following layer. The sparsity in sparse-DBN is achieved with a regularization term that penalizes a deviation of the expected activation of hidden units from a fixed low-level prevents the network from overfitting and is able to learn low-level structures as well as high-level structures. For comparison, the artificial neural networks (ANN), Bayesian neural networks (BNN), and original deep belief networks (DBN) classifiers are used. The classification results show that using AR feature extractor and DBN classifiers, the classification performance achieves an improved classification performance with a of sensitivity of 90.8%, a specificity of 90.4%, an accuracy of 90.6%, and an area under the receiver operating curve (AUROC) of 0.94 compared to ANN (sensitivity at 80.8%, specificity at 77.8%, accuracy at 79.3% with AUC-ROC of 0.83) and BNN classifiers (sensitivity at 84.3%, specificity at 83%, accuracy at 83.6% with AUROC of 0.87). Using the sparse-DBN classifier, the classification performance improved further with sensitivity of 93.9%, a specificity of 92.3%, and an accuracy of 93.1% with AUROC of 0.96. Overall, the sparse-DBN classifier improved accuracy by 13.8, 9.5, and 2.5% over ANN, BNN, and DBN classifiers, respectively. PMID:28326009

  6. Improving EEG-Based Driver Fatigue Classification Using Sparse-Deep Belief Networks.

    PubMed

    Chai, Rifai; Ling, Sai Ho; San, Phyo Phyo; Naik, Ganesh R; Nguyen, Tuan N; Tran, Yvonne; Craig, Ashley; Nguyen, Hung T

    2017-01-01

    This paper presents an improvement of classification performance for electroencephalography (EEG)-based driver fatigue classification between fatigue and alert states with the data collected from 43 participants. The system employs autoregressive (AR) modeling as the features extraction algorithm, and sparse-deep belief networks (sparse-DBN) as the classification algorithm. Compared to other classifiers, sparse-DBN is a semi supervised learning method which combines unsupervised learning for modeling features in the pre-training layer and supervised learning for classification in the following layer. The sparsity in sparse-DBN is achieved with a regularization term that penalizes a deviation of the expected activation of hidden units from a fixed low-level prevents the network from overfitting and is able to learn low-level structures as well as high-level structures. For comparison, the artificial neural networks (ANN), Bayesian neural networks (BNN), and original deep belief networks (DBN) classifiers are used. The classification results show that using AR feature extractor and DBN classifiers, the classification performance achieves an improved classification performance with a of sensitivity of 90.8%, a specificity of 90.4%, an accuracy of 90.6%, and an area under the receiver operating curve (AUROC) of 0.94 compared to ANN (sensitivity at 80.8%, specificity at 77.8%, accuracy at 79.3% with AUC-ROC of 0.83) and BNN classifiers (sensitivity at 84.3%, specificity at 83%, accuracy at 83.6% with AUROC of 0.87). Using the sparse-DBN classifier, the classification performance improved further with sensitivity of 93.9%, a specificity of 92.3%, and an accuracy of 93.1% with AUROC of 0.96. Overall, the sparse-DBN classifier improved accuracy by 13.8, 9.5, and 2.5% over ANN, BNN, and DBN classifiers, respectively.

  7. Deep Recurrent Neural Networks for Supernovae Classification

    NASA Astrophysics Data System (ADS)

    Charnock, Tom; Moss, Adam

    2017-03-01

    We apply deep recurrent neural networks, which are capable of learning complex sequential information, to classify supernovae (code available at https://github.com/adammoss/supernovae). The observational time and filter fluxes are used as inputs to the network, but since the inputs are agnostic, additional data such as host galaxy information can also be included. Using the Supernovae Photometric Classification Challenge (SPCC) data, we find that deep networks are capable of learning about light curves, however the performance of the network is highly sensitive to the amount of training data. For a training size of 50% of the representational SPCC data set (around 104 supernovae) we obtain a type-Ia versus non-type-Ia classification accuracy of 94.7%, an area under the Receiver Operating Characteristic curve AUC of 0.986 and an SPCC figure-of-merit F 1 = 0.64. When using only the data for the early-epoch challenge defined by the SPCC, we achieve a classification accuracy of 93.1%, AUC of 0.977, and F 1 = 0.58, results almost as good as with the whole light curve. By employing bidirectional neural networks, we can acquire impressive classification results between supernovae types I, II and III at an accuracy of 90.4% and AUC of 0.974. We also apply a pre-trained model to obtain classification probabilities as a function of time and show that it can give early indications of supernovae type. Our method is competitive with existing algorithms and has applications for future large-scale photometric surveys.

  8. Skimming Digits: Neuromorphic Classification of Spike-Encoded Images

    PubMed Central

    Cohen, Gregory K.; Orchard, Garrick; Leng, Sio-Hoi; Tapson, Jonathan; Benosman, Ryad B.; van Schaik, André

    2016-01-01

    The growing demands placed upon the field of computer vision have renewed the focus on alternative visual scene representations and processing paradigms. Silicon retinea provide an alternative means of imaging the visual environment, and produce frame-free spatio-temporal data. This paper presents an investigation into event-based digit classification using N-MNIST, a neuromorphic dataset created with a silicon retina, and the Synaptic Kernel Inverse Method (SKIM), a learning method based on principles of dendritic computation. As this work represents the first large-scale and multi-class classification task performed using the SKIM network, it explores different training patterns and output determination methods necessary to extend the original SKIM method to support multi-class problems. Making use of SKIM networks applied to real-world datasets, implementing the largest hidden layer sizes and simultaneously training the largest number of output neurons, the classification system achieved a best-case accuracy of 92.87% for a network containing 10,000 hidden layer neurons. These results represent the highest accuracies achieved against the dataset to date and serve to validate the application of the SKIM method to event-based visual classification tasks. Additionally, the study found that using a square pulse as the supervisory training signal produced the highest accuracy for most output determination methods, but the results also demonstrate that an exponential pattern is better suited to hardware implementations as it makes use of the simplest output determination method based on the maximum value. PMID:27199646

  9. Research On The Classification Of High Resolution Image Based On Object-oriented And Class Rule

    NASA Astrophysics Data System (ADS)

    Li, C. K.; Fang, W.; Dong, X. J.

    2015-06-01

    With the development of remote sensing technology, the spatial resolution, spectral resolution and time resolution of remote sensing data is greatly improved. How to efficiently process and interpret the massive high resolution remote sensing image data for ground objects, which with spatial geometry and texture information, has become the focus and difficulty in the field of remote sensing research. An object oriented and rule of the classification method of remote sensing data has presents in this paper. Through the discovery and mining the rich knowledge of spectrum and spatial characteristics of high-resolution remote sensing image, establish a multi-level network image object segmentation and classification structure of remote sensing image to achieve accurate and fast ground targets classification and accuracy assessment. Based on worldview-2 image data in the Zangnan area as a study object, using the object-oriented image classification method and rules to verify the experiment which is combination of the mean variance method, the maximum area method and the accuracy comparison to analysis, selected three kinds of optimal segmentation scale and established a multi-level image object network hierarchy for image classification experiments. The results show that the objectoriented rules classification method to classify the high resolution images, enabling the high resolution image classification results similar to the visual interpretation of the results and has higher classification accuracy. The overall accuracy and Kappa coefficient of the object-oriented rules classification method were 97.38%, 0.9673; compared with object-oriented SVM method, respectively higher than 6.23%, 0.078; compared with object-oriented KNN method, respectively more than 7.96%, 0.0996. The extraction precision and user accuracy of the building compared with object-oriented SVM method, respectively higher than 18.39%, 3.98%, respectively better than the object-oriented KNN method 21

  10. Dynamic time warping and sparse representation classification for birdsong phrase classification using limited training data.

    PubMed

    Tan, Lee N; Alwan, Abeer; Kossan, George; Cody, Martin L; Taylor, Charles E

    2015-03-01

    Annotation of phrases in birdsongs can be helpful to behavioral and population studies. To reduce the need for manual annotation, an automated birdsong phrase classification algorithm for limited data is developed. Limited data occur because of limited recordings or the existence of rare phrases. In this paper, classification of up to 81 phrase classes of Cassin's Vireo is performed using one to five training samples per class. The algorithm involves dynamic time warping (DTW) and two passes of sparse representation (SR) classification. DTW improves the similarity between training and test phrases from the same class in the presence of individual bird differences and phrase segmentation inconsistencies. The SR classifier works by finding a sparse linear combination of training feature vectors from all classes that best approximates the test feature vector. When the class decisions from DTW and the first pass SR classification are different, SR classification is repeated using training samples from these two conflicting classes. Compared to DTW, support vector machines, and an SR classifier without DTW, the proposed classifier achieves the highest classification accuracies of 94% and 89% on manually segmented and automatically segmented phrases, respectively, from unseen Cassin's Vireo individuals, using five training samples per class.

  11. Vehicle classification for road tunnel surveillance

    NASA Astrophysics Data System (ADS)

    Frías-Velázquez, Andrés.; Van Hese, Peter; Pižurica, Aleksandra; Philips, Wilfried

    2013-03-01

    Vehicle classification for tunnel surveillance aims to not only retrieve vehicle class statistics, but also prevent accidents by recognizing vehicles carrying dangerous goods. In this paper, we describe a method to classify vehicle images that experience different geometrical variations and challenging photometrical conditions such as those found in road tunnels. Unlike previous approaches, we propose a classification method that does not rely on the length and height estimation of the vehicles. Alternatively, we propose a novel descriptor based on trace transform signatures to extract salient and non-correlated information of the vehicle images. Also, we propose a metric that measures the complexity of the vehicles' shape based on corner point detection. As a result, these features describe the vehicle's appearance and shape complexity independently of the scale, pose, and illumination conditions. Experiments with vehicles captured from three different cameras confirm the saliency and robustness of the features proposed, achieving an overall accuracy of 97.5% for the classification of four different vehicle classes. For vehicles transporting dangerous goods, our classification scheme achieves an average recall of 97.6% at a precision of 98.6% for the combination of lorries and tankers, which is a very good result considering the scene conditions.

  12. Classification of skin cancer images using local binary pattern and SVM classifier

    NASA Astrophysics Data System (ADS)

    Adjed, Faouzi; Faye, Ibrahima; Ababsa, Fakhreddine; Gardezi, Syed Jamal; Dass, Sarat Chandra

    2016-11-01

    In this paper, a classification method for melanoma and non-melanoma skin cancer images has been presented using the local binary patterns (LBP). The LBP computes the local texture information from the skin cancer images, which is later used to compute some statistical features that have capability to discriminate the melanoma and non-melanoma skin tissues. Support vector machine (SVM) is applied on the feature matrix for classification into two skin image classes (malignant and benign). The method achieves good classification accuracy of 76.1% with sensitivity of 75.6% and specificity of 76.7%.

  13. A novel approach to malignant-benign classification of pulmonary nodules by using ensemble learning classifiers.

    PubMed

    Tartar, A; Akan, A; Kilic, N

    2014-01-01

    Computer-aided detection systems can help radiologists to detect pulmonary nodules at an early stage. In this paper, a novel Computer-Aided Diagnosis system (CAD) is proposed for the classification of pulmonary nodules as malignant and benign. The proposed CAD system using ensemble learning classifiers, provides an important support to radiologists at the diagnosis process of the disease, achieves high classification performance. The proposed approach with bagging classifier results in 94.7 %, 90.0 % and 77.8 % classification sensitivities for benign, malignant and undetermined classes (89.5 % accuracy), respectively.

  14. Crop classification using HJ satellite multispectral data in the North China Plain

    NASA Astrophysics Data System (ADS)

    Jia, Kun; Wu, Bingfang; Li, Qiangzi

    2013-01-01

    The HJ satellite constellation is designed for environment and disaster monitoring by the Chinese government. This paper investigates the performance of multitemporal multispectral charge-coupled device (CCD) data on board HJ-1-A and HJ-1-B for crop classification in the North China Plain. Support vector machine classifier is selected for the classification using different combinations of multitemporal HJ multispectral data. The results indicate that multitemporal HJ CCD data could effectively identify wheat fields with an overall classification accuracy of 91.7%. Considering only single temporal data, 88.2% is the best classification accuracy achieved using the data acquired at the flowering time of wheat. The performance of the combination of two temporal data acquired at the jointing and flowering times of wheat is almost as well as using all three temporal data, indicating that two appropriate temporal data are enough for wheat classification, and much more data have little effect on improving the classification accuracy. Moreover, two temporal data acquired over a larger time interval achieves better results than that over a smaller interval. However, the field borders and smaller cotton fields cannot be identified effectively by HJ multispectral data, and misclassification phenomenon exists because of the relatively coarse spatial resolution.

  15. Fusion of HJ1B and ALOS PALSAR data for land cover classification using machine learning methods

    NASA Astrophysics Data System (ADS)

    Wang, X. Y.; Guo, Y. G.; He, J.; Du, L. T.

    2016-10-01

    Image classification from remote sensing is becoming increasingly urgent for monitoring environmental changes. Exploring effective algorithms to increase classification accuracy is critical. This paper explores the use of multispectral HJ1B and ALOS (Advanced Land Observing Satellite) PALSAR L-band (Phased Array type L-band Synthetic Aperture Radar) for land cover classification using learning-based algorithms. Pixel-based and object-based image analysis approaches for classifying HJ1B data and the HJ1B and ALOS/PALSAR fused-images were compared using two machine learning algorithms, support vector machine (SVM) and random forest (RF), to test which algorithm can achieve the best classification accuracy in arid and semiarid regions. The overall accuracies of the pixel-based (Fused data: 79.0%; HJ1B data: 81.46%) and object-based classifications (Fused data: 80.0%; HJ1B data: 76.9%) were relatively close when using the SVM classifier. The pixel-based classification achieved a high overall accuracy (85.5%) using the RF algorithm for classifying the fused data, whereas the RF classifier using the object-based image analysis produced a lower overall accuracy (70.2%). The study demonstrates that the pixel-based classification utilized fewer variables and performed relatively better than the object-based classification using HJ1B imagery and the fused data. Generally, the integration of the HJ1B and ALOS/PALSAR imagery can improve the overall accuracy of 5.7% using the pixel-based image analysis and RF classifier.

  16. Landsat classification of coastal wetlands in Texas

    NASA Technical Reports Server (NTRS)

    Finley, R. J.; Mcculloch, S.; Harwood, P.

    1981-01-01

    Through a multiagency study of Landsat imagery applications, an analysis of Texas coastal wetlands shows that five Level III categories of wetlands can be delineated using image interpretation: topographically low marshes, topographically high marshes, tidal flats, sea grass and algal flats, and vegetated dredged material. Image interpretation involves optical enlargement of 1:1,000,000 scale, Landsat transparencies to a scale of 1:125,000 and mapping on a stable film base. Digital classification procedures, resulting in 1:24,000 scale line printer maps as output, require several iterations to display welands effectively. Accuracies of 65% were achieved for all wetland categories combined.

  17. Learning ECOC Code Matrix for Multiclass Classification with Application to Glaucoma Diagnosis.

    PubMed

    Bai, Xiaolong; Niwas, Swamidoss Issac; Lin, Weisi; Ju, Bing-Feng; Kwoh, Chee Keong; Wang, Lipo; Sng, Chelvin C; Aquino, Maria C; Chew, Paul T K

    2016-04-01

    Classification of different mechanisms of angle closure glaucoma (ACG) is important for medical diagnosis. Error-correcting output code (ECOC) is an effective approach for multiclass classification. In this study, we propose a new ensemble learning method based on ECOC with application to classification of four ACG mechanisms. The dichotomizers in ECOC are first optimized individually to increase their accuracy and diversity (or interdependence) which is beneficial to the ECOC framework. Specifically, the best feature set is determined for each possible dichotomizer and a wrapper approach is applied to evaluate the classification accuracy of each dichotomizer on the training dataset using cross-validation. The separability of the ECOC codes is maximized by selecting a set of competitive dichotomizers according to a new criterion, in which a regularization term is introduced in consideration of the binary classification performance of each selected dichotomizer. The proposed method is experimentally applied for classifying four ACG mechanisms. The eye images of 152 glaucoma patients are collected by using anterior segment optical coherence tomography (AS-OCT) and then segmented, from which 84 features are extracted. The weighted average classification accuracy of the proposed method is 87.65 % based on the results of leave-one-out cross-validation (LOOCV), which is much better than that of the other existing ECOC methods. The proposed method achieves accurate classification of four ACG mechanisms which is promising to be applied in diagnosis of glaucoma.

  18. Resource Classification for Medical Questions

    PubMed Central

    Roberts, Kirk; Rodriguez, Laritza; Shooshan, Sonya E.; Demner-Fushman, Dina

    2016-01-01

    We present an approach for manually and automatically classifying the resource type of medical questions. Three types of resources are considered: patient-specific, general knowledge, and research. Using this approach, an automatic question answering system could select the best type of resource from which to consider answers. We first describe our methodology for manually annotating resource type on four different question corpora totaling over 5,000 questions. We then describe our approach for automatically identifying the appropriate type of resource. A supervised machine learning approach is used with lexical, syntactic, semantic, and topic-based feature types. This approach is able to achieve accuracies in the range of 80.9% to 92.8% across four datasets. Finally, we discuss the difficulties encountered in both manual and automatic classification of this challenging task. PMID:28269901

  19. Resource Classification for Medical Questions.

    PubMed

    Roberts, Kirk; Rodriguez, Laritza; Shooshan, Sonya E; Demner-Fushman, Dina

    2016-01-01

    We present an approach for manually and automatically classifying the resource type of medical questions. Three types of resources are considered: patient-specific, general knowledge, and research. Using this approach, an automatic question answering system could select the best type of resource from which to consider answers. We first describe our methodology for manually annotating resource type on four different question corpora totaling over 5,000 questions. We then describe our approach for automatically identifying the appropriate type of resource. A supervised machine learning approach is used with lexical, syntactic, semantic, and topic-based feature types. This approach is able to achieve accuracies in the range of 80.9% to 92.8% across four datasets. Finally, we discuss the difficulties encountered in both manual and automatic classification of this challenging task.

  20. Bayesian neural networks for internet traffic classification.

    PubMed

    Auld, Tom; Moore, Andrew W; Gull, Stephen F

    2007-01-01

    Internet traffic identification is an important tool for network management. It allows operators to better predict future traffic matrices and demands, security personnel to detect anomalous behavior, and researchers to develop more realistic traffic models. We present here a traffic classifier that can achieve a high accuracy across a range of application types without any source or destination host-address or port information. We use supervised machine learning based on a Bayesian trained neural network. Though our technique uses training data with categories derived from packet content, training and testing were done using features derived from packet streams consisting of one or more packet headers. By providing classification without access to the contents of packets, our technique offers wider application than methods that require full packet/payloads for classification. This is a powerful advantage, using samples of classified traffic to permit the categorization of traffic based only upon commonly available information.

  1. SQL based cardiovascular ultrasound image classification.

    PubMed

    Nandagopalan, S; Suryanarayana, Adiga B; Sudarshan, T S B; Chandrashekar, Dhanalakshmi; Manjunath, C N

    2013-01-01

    This paper proposes a novel method to analyze and classify the cardiovascular ultrasound echocardiographic images using Naïve-Bayesian model via database OLAP-SQL. Efficient data mining algorithms based on tightly-coupled model is used to extract features. Three algorithms are proposed for classification namely Naïve-Bayesian Classifier for Discrete variables (NBCD) with SQL, NBCD with OLAP-SQL, and Naïve-Bayesian Classifier for Continuous variables (NBCC) using OLAP-SQL. The proposed model is trained with 207 patient images containing normal and abnormal categories. Out of the three proposed algorithms, a high classification accuracy of 96.59% was achieved from NBCC which is better than the earlier methods.

  2. Land use/cover classification in the Brazilian Amazon using satellite images.

    PubMed

    Lu, Dengsheng; Batistella, Mateus; Li, Guiying; Moran, Emilio; Hetrick, Scott; Freitas, Corina da Costa; Dutra, Luciano Vieira; Sant'anna, Sidnei João Siqueira

    2012-09-01

    Land use/cover classification is one of the most important applications in remote sensing. However, mapping accurate land use/cover spatial distribution is a challenge, particularly in moist tropical regions, due to the complex biophysical environment and limitations of remote sensing data per se. This paper reviews experiments related to land use/cover classification in the Brazilian Amazon for a decade. Through comprehensive analysis of the classification results, it is concluded that spatial information inherent in remote sensing data plays an essential role in improving land use/cover classification. Incorporation of suitable textural images into multispectral bands and use of segmentation-based method are valuable ways to improve land use/cover classification, especially for high spatial resolution images. Data fusion of multi-resolution images within optical sensor data is vital for visual interpretation, but may not improve classification performance. In contrast, integration of optical and radar data did improve classification performance when the proper data fusion method was used. Of the classification algorithms available, the maximum likelihood classifier is still an important method for providing reasonably good accuracy, but nonparametric algorithms, such as classification tree analysis, has the potential to provide better results. However, they often require more time to achieve parametric optimization. Proper use of hierarchical-based methods is fundamental for developing accurate land use/cover classification, mainly from historical remotely sensed data.

  3. Land use/cover classification in the Brazilian Amazon using satellite images

    PubMed Central

    Lu, Dengsheng; Batistella, Mateus; Li, Guiying; Moran, Emilio; Hetrick, Scott; Freitas, Corina da Costa; Dutra, Luciano Vieira; Sant’Anna, Sidnei João Siqueira

    2013-01-01

    Land use/cover classification is one of the most important applications in remote sensing. However, mapping accurate land use/cover spatial distribution is a challenge, particularly in moist tropical regions, due to the complex biophysical environment and limitations of remote sensing data per se. This paper reviews experiments related to land use/cover classification in the Brazilian Amazon for a decade. Through comprehensive analysis of the classification results, it is concluded that spatial information inherent in remote sensing data plays an essential role in improving land use/cover classification. Incorporation of suitable textural images into multispectral bands and use of segmentation-based method are valuable ways to improve land use/cover classification, especially for high spatial resolution images. Data fusion of multi-resolution images within optical sensor data is vital for visual interpretation, but may not improve classification performance. In contrast, integration of optical and radar data did improve classification performance when the proper data fusion method was used. Of the classification algorithms available, the maximum likelihood classifier is still an important method for providing reasonably good accuracy, but nonparametric algorithms, such as classification tree analysis, has the potential to provide better results. However, they often require more time to achieve parametric optimization. Proper use of hierarchical-based methods is fundamental for developing accurate land use/cover classification, mainly from historical remotely sensed data. PMID:24353353

  4. An adaptive method with integration of multi-wavelet based features for unsupervised classification of SAR images

    NASA Astrophysics Data System (ADS)

    Chamundeeswari, V. V.; Singh, D.; Singh, K.

    2007-12-01

    In single band and single polarized synthetic aperture radar (SAR) images, the information is limited to intensity and texture only and it is very difficult to interpret such SAR images without any a priori information. For unsupervised classification of SAR images, M-band wavelet decomposition is performed on the SAR image and sub-band selection on the basis of energy levels is applied to improve the classification results since sparse representation of sub-bands degrades the performance of classification. Then, textural features are obtained from selected sub-bands and integrated with intensity features. An adaptive neuro-fuzzy algorithm is used to improve computational efficiency by extracting significant features. K-means classification is performed on the extracted features and land features are labeled. This classification algorithm involves user defined parameters. To remove the user dependency and to obtain maximum achievable classification accuracy, an algorithm is developed in this paper for classification accuracy in terms of the parameters involved in the segmentation process. This is very helpful to develop the automated land-cover monitoring system with SAR, where optimized parameters are to be identified only once and these parameters can be applied to SAR imagery of the same scene obtained year after year. A single band, single polarized SAR image is classified into water, urban and vegetation areas using this method and overall classification accuracy is obtained in the range of 85.92%-93.70% by comparing with ground truth data.

  5. Analyzing thematic maps and mapping for accuracy

    USGS Publications Warehouse

    Rosenfield, G.H.

    1982-01-01

    Two problems which exist while attempting to test the accuracy of thematic maps and mapping are: (1) evaluating the accuracy of thematic content, and (2) evaluating the effects of the variables on thematic mapping. Statistical analysis techniques are applicable to both these problems and include techniques for sampling the data and determining their accuracy. In addition, techniques for hypothesis testing, or inferential statistics, are used when comparing the effects of variables. A comprehensive and valid accuracy test of a classification project, such as thematic mapping from remotely sensed data, includes the following components of statistical analysis: (1) sample design, including the sample distribution, sample size, size of the sample unit, and sampling procedure; and (2) accuracy estimation, including estimation of the variance and confidence limits. Careful consideration must be given to the minimum sample size necessary to validate the accuracy of a given. classification category. The results of an accuracy test are presented in a contingency table sometimes called a classification error matrix. Usually the rows represent the interpretation, and the columns represent the verification. The diagonal elements represent the correct classifications. The remaining elements of the rows represent errors by commission, and the remaining elements of the columns represent the errors of omission. For tests of hypothesis that compare variables, the general practice has been to use only the diagonal elements from several related classification error matrices. These data are arranged in the form of another contingency table. The columns of the table represent the different variables being compared, such as different scales of mapping. The rows represent the blocking characteristics, such as the various categories of classification. The values in the cells of the tables might be the counts of correct classification or the binomial proportions of these counts divided by

  6. Dissimilarity representations in lung parenchyma classification

    NASA Astrophysics Data System (ADS)

    Sørensen, Lauge; de Bruijne, Marleen

    2009-02-01

    A good problem representation is important for a pattern recognition system to be successful. The traditional approach to statistical pattern recognition is feature representation. More specifically, objects are represented by a number of features in a feature vector space, and classifiers are built in this representation. This is also the general trend in lung parenchyma classification in computed tomography (CT) images, where the features often are measures on feature histograms. Instead, we propose to build normal density based classifiers in dissimilarity representations for lung parenchyma classification. This allows for the classifiers to work on dissimilarities between objects, which might be a more natural way of representing lung parenchyma. In this context, dissimilarity is defined between CT regions of interest (ROI)s. ROIs are represented by their CT attenuation histogram and ROI dissimilarity is defined as a histogram dissimilarity measure between the attenuation histograms. In this setting, the full histograms are utilized according to the chosen histogram dissimilarity measure. We apply this idea to classification of different emphysema patterns as well as normal, healthy tissue. Two dissimilarity representation approaches as well as different histogram dissimilarity measures are considered. The approaches are evaluated on a set of 168 CT ROIs using normal density based classifiers all showing good performance. Compared to using histogram dissimilarity directly as distance in a emph{k} nearest neighbor classifier, which achieves a classification accuracy of 92.9%, the best dissimilarity representation based classifier is significantly better with a classification accuracy of 97.0% (text{emph{p" border="0" class="imgtopleft"> = 0.046).

  7. Improving Human-Machine Cooperative Classification Via Cognitive Theories of Similarity.

    PubMed

    Roads, Brett D; Mozer, Michael C

    2016-07-22

    Acquiring perceptual expertise is slow and effortful. However, untrained novices can accurately make difficult classification decisions (e.g., skin-lesion diagnosis) by reformulating the task as similarity judgment. Given a query image and a set of reference images, individuals are asked to select the best matching reference. When references are suitably chosen, the procedure yields an implicit classification of the query image. To optimize reference selection, we develop and evaluate a predictive model of similarity-based choice. The model builds on existing psychological literature and accommodates stochastic, dynamic shifts of attention among visual feature dimensions. We perform a series of human experiments with two stimulus types (rectangles, faces) and nine classification tasks to validate the model and to demonstrate the model's potential to boost performance. Our system achieves high accuracy for participants who are naive as to the classification task, even when the classification task switches from trial to trial.

  8. Radar micro-Doppler based human activity classification for indoor and outdoor environments

    NASA Astrophysics Data System (ADS)

    Zenaldin, Matthew; Narayanan, Ram M.

    2016-05-01

    This paper presents the results of our experimental investigation into how different environments impact the classification of human motion using radar micro-Doppler (MD) signatures. The environments studied include free space, through-thewall, leaf tree foliage, and needle tree foliage. Results on presented on classification of the following three motions: crawling, walking, and jogging. The classification task was designed how to best separate these movements. The human motion data were acquired using a monostatic coherent Doppler radar operating in the C-band at 6.5 GHz from a total of six human subjects. The received signals were analyzed in the time-frequency domain using the Short-time Fourier Transform (STFT) which was used for feature extraction. Classification was performed using a Support Vector Machine (SVM) using a Radial Basis Function (RBF). Classification accuracies in the range 80-90% were achieved to separate the three movements mentioned.

  9. The method of narrow-band audio classification based on universal noise background model

    NASA Astrophysics Data System (ADS)

    Rui, Rui; Bao, Chang-chun

    2013-03-01

    Audio classification is the basis of content-based audio analysis and retrieval. The conventional classification methods mainly depend on feature extraction of audio clip, which certainly increase the time requirement for classification. An approach for classifying the narrow-band audio stream based on feature extraction of audio frame-level is presented in this paper. The audio signals are divided into speech, instrumental music, song with accompaniment and noise using the Gaussian mixture model (GMM). In order to satisfy the demand of actual environment changing, a universal noise background model (UNBM) for white noise, street noise, factory noise and car interior noise is built. In addition, three feature schemes are considered to optimize feature selection. The experimental results show that the proposed algorithm achieves a high accuracy for audio classification, especially under each noise background we used and keep the classification time less than one second.

  10. Multiparameter classifications of optical tomographic images.

    PubMed

    Klose, Christian D; Klose, Alexander D; Netz, Uwe; Beuthan, Juergen; Hielscher, Andreas H

    2008-01-01

    This research study explores the combined use of more than one parameter derived from optical tomographic images to increase diagnostic accuracy which is measured in terms of sensitivity and specificity. Parameters considered include, for example, smallest or largest absorption or scattering coefficients or the ratios thereof in an image region of interest. These parameters have been used individually in a previous study to determine if a finger joint is affected or not affected by rheumatoid arthritis. To combine these parameters in the analysis we employ here a vector quantization based classification method called Self-Organizing Mapping (SOM). This method allows producing multivariate ROC-curves from which sensitivity and specificities can be determined. We found that some parameter combinations can lead to higher sensitivities whereas others to higher specificities when compared to singleparameter classifications employed in previous studies. The best diagnostic accuracy, in terms of highest Youden index, was achieved by combining three absorption parameters [maximum(micro a), minimum(micro a), and the ratio of minimum(micro a) and maximum(micro a)], which result in a sensitivity of 0.78, a specificity of 0.76, a Youden index of 0.54, and an area under the curve (AUC) of 0.72. These values are higher than for previously reported single parameter classifications with a best sensitivity and specificity of 0.71, a Youden index of 0.41, and an AUC of 0.66.

  11. Wishart Deep Stacking Network for Fast POLSAR Image Classification.

    PubMed

    Jiao, Licheng; Liu, Fang

    2016-05-11

    Inspired by the popular deep learning architecture - Deep Stacking Network (DSN), a specific deep model for polarimetric synthetic aperture radar (POLSAR) image classification is proposed in this paper, which is named as Wishart Deep Stacking Network (W-DSN). First of all, a fast implementation of Wishart distance is achieved by a special linear transformation, which speeds up the classification of POLSAR image and makes it possible to use this polarimetric information in the following Neural Network (NN). Then a single-hidden-layer neural network based on the fast Wishart distance is defined for POLSAR image classification, which is named as Wishart Network (WN) and improves the classification accuracy. Finally, a multi-layer neural network is formed by stacking WNs, which is in fact the proposed deep learning architecture W-DSN for POLSAR image classification and improves the classification accuracy further. In addition, the structure of WN can be expanded in a straightforward way by adding hidden units if necessary, as well as the structure of the W-DSN. As a preliminary exploration on formulating specific deep learning architecture for POLSAR image classification, the proposed methods may establish a simple but clever connection between POLSAR image interpretation and deep learning. The experiment results tested on real POLSAR image show that the fast implementation of Wishart distance is very efficient (a POLSAR image with 768000 pixels can be classified in 0.53s), and both the single-hidden-layer architecture WN and the deep learning architecture W-DSN for POLSAR image classification perform well and work efficiently.

  12. Minimum distance classification in remote sensing

    NASA Technical Reports Server (NTRS)

    Wacker, A. G.; Landgrebe, D. A.

    1972-01-01

    The utilization of minimum distance classification methods in remote sensing problems, such as crop species identification, is considered. Literature concerning both minimum distance classification problems and distance measures is reviewed. Experimental results are presented for several examples. The objective of these examples is to: (a) compare the sample classification accuracy of a minimum distance classifier, with the vector classification accuracy of a maximum likelihood classifier, and (b) compare the accuracy of a parametric minimum distance classifier with that of a nonparametric one. Results show the minimum distance classifier performance is 5% to 10% better than that of the maximum likelihood classifier. The nonparametric classifier is only slightly better than the parametric version.

  13. Galaxy Image Processing and Morphological Classification Using Machine Learning

    NASA Astrophysics Data System (ADS)

    Kates-Harbeck, Julian

    2012-03-01

    This work uses data from the Sloan Digital Sky Survey (SDSS) and the Galaxy Zoo Project for classification of galaxy morphologies via machine learning. SDSS imaging data together with reliable human classifications from Galaxy Zoo provide the training set and test set for the machine learning architectures. Classification is performed with hand-picked, pre-computed features from SDSS as well as with the raw imaging data from SDSS that was available to humans in the Galaxy Zoo project. With the hand-picked features and a logistic regression classifier, 95.21% classification accuracy and an area under the ROC curve of 0.986 are attained. In the case of the raw imaging data, the images are first processed to remove background noise, image artifacts, and celestial objects other than the galaxy of interest. They are then rotated onto their principle axis of variance to guarantee rotational invariance. The processed images are used to compute color information, up to 4^th order central normalized moments, and radial intensity profiles. These features are used to train a support vector machine with a 3^rd degree polynomial kernel, which achieves a classification accuracy of 95.89% with an ROC area of 0.943.

  14. Optimizing Classification in Intelligence Processing

    DTIC Science & Technology

    2010-12-01

    ACC Classification Accuracy AUC Area Under the ROC Curve CI Competitive Intelligence COMINT Communications Intelligence DoD Department of...indispensible tool to support a national leader’s decision making process, competitive intelligence (CI) has emerged in recent decades as an environment meant...effectiveness for the intelligence product in competitive intelligence environment: accuracy, objectivity, usability, relevance, readiness, and timeliness

  15. DOE LLW classification rationale

    SciTech Connect

    Flores, A.Y.

    1991-09-16

    This report was about the rationale which the US Department of Energy had with low-level radioactive waste (LLW) classification. It is based on the Nuclear Regulatory Commission`s classification system. DOE site operators met to review the qualifications and characteristics of the classification systems. They evaluated performance objectives, developed waste classification tables, and compiled dose limits on the waste. A goal of the LLW classification system was to allow each disposal site the freedom to develop limits to radionuclide inventories and concentrations according to its own site-specific characteristics. This goal was achieved with the adoption of a performance objectives system based on a performance assessment, with site-specific environmental conditions and engineered disposal systems.

  16. DOE LLW classification rationale

    SciTech Connect

    Flores, A.Y.

    1991-09-16

    This report was about the rationale which the US Department of Energy had with low-level radioactive waste (LLW) classification. It is based on the Nuclear Regulatory Commission's classification system. DOE site operators met to review the qualifications and characteristics of the classification systems. They evaluated performance objectives, developed waste classification tables, and compiled dose limits on the waste. A goal of the LLW classification system was to allow each disposal site the freedom to develop limits to radionuclide inventories and concentrations according to its own site-specific characteristics. This goal was achieved with the adoption of a performance objectives system based on a performance assessment, with site-specific environmental conditions and engineered disposal systems.

  17. Flotation classification of ultrafine particles -- A novel classification approach

    SciTech Connect

    Qiu Guanzhou; Luo Lin; Hu Yuehua; Xu Jin; Wang Dianzuo

    1995-12-31

    This paper introduces a novel classification approach named the flotation classification approach which works by controlling interactions between particles. It differs considerably from the conventional classification processes operating on mechanical forces. In the present test, the micro-bubble flotation technology is grafted onto hydro-classification. Selective aggregation and dispersion of ultrafine particles are achieved through governing the interactions in the classification process. A series of laboratory classification tests for {minus}44 gm kaolin have been conducted on a classification column. As a result, about 92% recovery for minus 2 {micro}m size fraction Kaolin in the final product is obtained. In addition, two criteria for the classification are set up. Finally, a principle of classifying and controlling the interactions between particles is discussed in terms of surface thermodynamics and hydrodynamics.

  18. Efficient HIK SVM learning for image classification.

    PubMed

    Wu, Jianxin

    2012-10-01

    Histograms are used in almost every aspect of image processing and computer vision, from visual descriptors to image representations. Histogram intersection kernel (HIK) and support vector machine (SVM) classifiers are shown to be very effective in dealing with histograms. This paper presents contributions concerning HIK SVM for image classification. First, we propose intersection coordinate descent (ICD), a deterministic and scalable HIK SVM solver. ICD is much faster than, and has similar accuracies to, general purpose SVM solvers and other fast HIK SVM training methods. We also extend ICD to the efficient training of a broader family of kernels. Second, we show an important empirical observation that ICD is not sensitive to the C parameter in SVM, and we provide some theoretical analyses to explain this observation. ICD achieves high accuracies in many problems, using its default parameters. This is an attractive property for practitioners, because many image processing tasks are too large to choose SVM parameters using cross-validation.

  19. Schizophrenia classification using functional network features

    NASA Astrophysics Data System (ADS)

    Rish, Irina; Cecchi, Guillermo A.; Heuton, Kyle

    2012-03-01

    This paper focuses on discovering statistical biomarkers (features) that are predictive of schizophrenia, with a particular focus on topological properties of fMRI functional networks. We consider several network properties, such as node (voxel) strength, clustering coefficients, local efficiency, as well as just a subset of pairwise correlations. While all types of features demonstrate highly significant statistical differences in several brain areas, and close to 80% classification accuracy, the most remarkable results of 93% accuracy are achieved by using a small subset of only a dozen of most-informative (lowest p-value) correlation features. Our results suggest that voxel-level correlations and functional network features derived from them are highly informative about schizophrenia and can be used as statistical biomarkers for the disease.

  20. Classification of Sporting Activities Using Smartphone Accelerometers

    PubMed Central

    Mitchell, Edmond; Monaghan, David; O'Connor, Noel E.

    2013-01-01

    In this paper we present a framework that allows for the automatic identification of sporting activities using commonly available smartphones. We extract discriminative informational features from smartphone accelerometers using the Discrete Wavelet Transform (DWT). Despite the poor quality of their accelerometers, smartphones were used as capture devices due to their prevalence in today's society. Successful classification on this basis potentially makes the technology accessible to both elite and non-elite athletes. Extracted features are used to train different categories of classifiers. No one classifier family has a reportable direct advantage in activity classification problems to date; thus we examine classifiers from each of the most widely used classifier families. We investigate three classification approaches; a commonly used SVM-based approach, an optimized classification model and a fusion of classifiers. We also investigate the effect of changing several of the DWT input parameters, including mother wavelets, window lengths and DWT decomposition levels. During the course of this work we created a challenging sports activity analysis dataset, comprised of soccer and field-hockey activities. The average maximum F-measure accuracy of 87% was achieved using a fusion of classifiers, which was 6% better than a single classifier model and 23% better than a standard SVM approach. PMID:23604031

  1. Semantic Shot Classification in Sports Video

    NASA Astrophysics Data System (ADS)

    Duan, Ling-Yu; Xu, Min; Tian, Qi

    2003-01-01

    In this paper, we present a unified framework for semantic shot classification in sports videos. Unlike previous approaches, which focus on clustering by aggregating shots with similar low-level features, the proposed scheme makes use of domain knowledge of a specific sport to perform a top-down video shot classification, including identification of video shot classes for each sport, and supervised learning and classification of the given sports video with low-level and middle-level features extracted from the sports video. It is observed that for each sport we can predefine a small number of semantic shot classes, about 5~10, which covers 90~95% of sports broadcasting video. With the supervised learning method, we can map the low-level features to middle-level semantic video shot attributes such as dominant object motion (a player), camera motion patterns, and court shape, etc. On the basis of the appropriate fusion of those middle-level shot classes, we classify video shots into the predefined video shot classes, each of which has a clear semantic meaning. The proposed method has been tested over 4 types of sports videos: tennis, basketball, volleyball and soccer. Good classification accuracy of 85~95% has been achieved. With correctly classified sports video shots, further structural and temporal analysis, such as event detection, video skimming, table of content, etc, will be greatly facilitated.

  2. Classification of posture and activities by using decision trees.

    PubMed

    Zhang, Ting; Tang, Wenlong; Sazonov, Edward S

    2012-01-01

    Obesity prevention and treatment as well as healthy life style recommendation requires the estimation of everyday physical activity. Monitoring posture allocations and activities with sensor systems is an effective method to achieve the goal. However, at present, most devices available rely on multiple sensors distributed on the body, which might be too obtrusive for everyday use. In this study, data was collected from a wearable shoe sensor system (SmartShoe) and a decision tree algorithm was applied for classification with high computational accuracy. The dataset was collected from 9 individual subjects performing 6 different activities--sitting, standing, walking, cycling, and stairs ascent/descent. Statistical features were calculated and the classification with decision tree classifier was performed, after which, advanced boosting algorithm was applied. The computational accuracy is as high as 98.85% without boosting, and 98.90% after boosting. Additionally, the simple tree structure provides a direct approach to simplify the feature set.

  3. Integrating Clonal Selection and Deterministic Sampling for Efficient Associative Classification

    PubMed Central

    Elsayed, Samir A. Mohamed; Rajasekaran, Sanguthevar; Ammar, Reda A.

    2013-01-01

    Traditional Associative Classification (AC) algorithms typically search for all possible association rules to find a representative subset of those rules. Since the search space of such rules may grow exponentially as the support threshold decreases, the rules discovery process can be computationally expensive. One effective way to tackle this problem is to directly find a set of high-stakes association rules that potentially builds a highly accurate classifier. This paper introduces AC-CS, an AC algorithm that integrates the clonal selection of the immune system along with deterministic data sampling. Upon picking a representative sample of the original data, it proceeds in an evolutionary fashion to populate only rules that are likely to yield good classification accuracy. Empirical results on several real datasets show that the approach generates dramatically less rules than traditional AC algorithms. In addition, the proposed approach is significantly more efficient than traditional AC algorithms while achieving a competitive accuracy. PMID:24500504

  4. Data resolution versus forestry classification and modeling

    NASA Technical Reports Server (NTRS)

    Kan, E. P.; Ball, D. L.; Basu, J. P.; Smelser, R. L.

    1975-01-01

    This paper examines the effects on timber stand computer classification accuracies caused by changes in the resolution of remotely sensed multispectral data. This investigation is valuable, especially for determining optimal sensor and platform designs. Theoretical justification and experimental verification support the finding that classification accuracies for low resolution data could be better than the accuracies for data with higher resolution. The increase in accuracy is constructed as due to the reduction of scene inhomogeneity at lower resolution. The computer classification scheme was a maximum likelihood classifier.

  5. Object Based Land Use and Land Cover Classification Using Sumbandilasat Imagery in Pretoria, South Africa

    NASA Astrophysics Data System (ADS)

    Mhangara, P.; Odindi, J.

    2012-04-01

    The launch of SumbandilaSat satellite on 17 September 2009 has ushered in new possibilities in land use/cover classification. SumbandilaSat has a ground sampling resolution of 6.25 m and possesses the red, red-edge and NIR spectral bands. The objective of this study was to demonstrate the feasibility of using SumbandilaSat imagery to classify land use/cover using an object-based classification ruleset that uses spectral indices, Haralick texture and the original spectral bands to classify urban land use and land cover in Pretoria, South Africa. High classification accuracies were achieved for water, forest, urban built up areas, irrigated-riparian vegetation and grass and sparse vegetation as shown by the very high KIAs higher than 0.85. Bare soil achieved a relatively low classification accuracy of 0.65. This study also showcases the value of SumbandilaSat imagery and the efficacy of object-oriented techniques in land use/cover classification as revealed by the overall accuracy of 0.93 and KIA of 0.91.

  6. Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders.

    PubMed

    Subasi, Abdulhamit

    2013-06-01

    Support vector machine (SVM) is an extensively used machine learning method with many biomedical signal classification applications. In this study, a novel PSO-SVM model has been proposed that hybridized the particle swarm optimization (PSO) and SVM to improve the EMG signal classification accuracy. This optimization mechanism involves kernel parameter setting in the SVM training procedure, which significantly influences the classification accuracy. The experiments were conducted on the basis of EMG signal to classify into normal, neurogenic or myopathic. In the proposed method the EMG signals were decomposed into the frequency sub-bands using discrete wavelet transform (DWT) and a set of statistical features were extracted from these sub-bands to represent the distribution of wavelet coefficients. The obtained results obviously validate the superiority of the SVM method compared to conventional machine learning methods, and suggest that further significant enhancements in terms of classification accuracy can be achieved by the proposed PSO-SVM classification system. The PSO-SVM yielded an overall accuracy of 97.41% on 1200 EMG signals selected from 27 subject records against 96.75%, 95.17% and 94.08% for the SVM, the k-NN and the RBF classifiers, respectively. PSO-SVM is developed as an efficient tool so that various SVMs can be used conveniently as the core of PSO-SVM for diagnosis of neuromuscular disorders.

  7. Oral lesion classification using true-color images

    NASA Astrophysics Data System (ADS)

    Chodorowski, Artur; Mattsson, Ulf; Gustavsson, Tomas

    1999-05-01

    The aim of the study was to investigate effective image analysis methods for the discrimination of two oral lesions, oral lichenoid reactions and oral leukoplakia, using only color information. Five different color representations (RGB, Irg, HSI, I1I2I3 and La*b*) were studied and their use for color analysis of mucosal images evaluated. Four common classifiers (Fisher's linear discriminant, Gaussian quadratic, kNN-Nearest Neighbor and Multilayer Perceptron) were chosen for the evaluation of classification performance. The feature vector consisted of the mean color difference between abnormal and normal regions extracted from digital color images. Classification accuracy was estimated using resubstitution and 5-fold crossvalidation methods. The best classification results were achieved in HSI color system and using linear discriminant function. In total, 70 out of 74 (94.6%) lichenoid reactions and 14 out of 20 (70.0%) of leukoplakia were correctly classified using only color information.

  8. The Classification of HEp-2 Cell Patterns Using Fractal Descriptor.

    PubMed

    Xu, Rudan; Sun, Yuanyuan; Yang, Zhihao; Song, Bo; Hu, Xiaopeng

    2015-07-01

    Indirect immunofluorescence (IIF) with HEp-2 cells is considered as a powerful, sensitive and comprehensive technique for analyzing antinuclear autoantibodies (ANAs). The automatic classification of the HEp-2 cell images from IIF has played an important role in diagnosis. Fractal dimension can be used on the analysis of image representing and also on the property quantification like texture complexity and spatial occupation. In this study, we apply the fractal theory in the application of HEp-2 cell staining pattern classification, utilizing fractal descriptor firstly in the HEp-2 cell pattern classification with the help of morphological descriptor and pixel difference descriptor. The method is applied to the data set of MIVIA and uses the support vector machine (SVM) classifier. Experimental results show that the fractal descriptor combining with morphological descriptor and pixel difference descriptor makes the precisions of six patterns more stable, all above 50%, achieving 67.17% overall accuracy at best with relatively simple feature vectors.

  9. Gaussian maximum likelihood and contextual classification algorithms for multicrop classification experiments using thematic mapper and multispectral scanner sensor data

    NASA Technical Reports Server (NTRS)

    Di Zenzo, Silvano; Degloria, Stephen D.; Bernstein, R.; Kolsky, Harwood G.

    1987-01-01

    The paper presents the results of a four-factor two-level analysis of a variance experiment designed to evaluate the combined effect of the improved quality of remote-sensor data and the use of context by the classifier on classification accuracy. The improvement achievable by using the context via relaxation techniques is significantly smaller than that provided by an increase of the radiometric resolution of the sensor from 6 to 8 bits per sample (the relative increase in radiometric resolution of TM relative to MSS). It is almost equal to that achievable by an increase in the spectral coverage as provided by TM relative to MSS.

  10. Linear distance coding for image classification.

    PubMed

    Wang, Zilei; Feng, Jiashi; Yan, Shuicheng; Xi, Hongsheng

    2013-02-01

    The feature coding-pooling framework is shown to perform well in image classification tasks, because it can generate discriminative and robust image representations. The unavoidable information loss incurred by feature quantization in the coding process and the undesired dependence of pooling on the image spatial layout, however, may severely limit the classification. In this paper, we propose a linear distance coding (LDC) method to capture the discriminative information lost in traditional coding methods while simultaneously alleviating the dependence of pooling on the image spatial layout. The core of the LDC lies in transforming local features of an image into more discriminative distance vectors, where the robust image-to-class distance is employed. These distance vectors are further encoded into sparse codes to capture the salient features of the image. The LDC is theoretically and experimentally shown to be complementary to the traditional coding methods, and thus their combination can achieve higher classification accuracy. We demonstrate the effectiveness of LDC on six data sets, two of each of three types (specific object, scene, and general object), i.e., Flower 102 and PFID 61, Scene 15 and Indoor 67, Caltech 101 and Caltech 256. The results show that our method generally outperforms the traditional coding methods, and achieves or is comparable to the state-of-the-art performance on these data sets.

  11. Hybrid fNIRS-EEG based classification of auditory and visual perception processes

    PubMed Central

    Putze, Felix; Hesslinger, Sebastian; Tse, Chun-Yu; Huang, YunYing; Herff, Christian; Guan, Cuntai; Schultz, Tanja

    2014-01-01

    For multimodal Human-Computer Interaction (HCI), it is very useful to identify the modalities on which the user is currently processing information. This would enable a system to select complementary output modalities to reduce the user's workload. In this paper, we develop a hybrid Brain-Computer Interface (BCI) which uses Electroencephalography (EEG) and functional Near Infrared Spectroscopy (fNIRS) to discriminate and detect visual and auditory stimulus processing. We describe the experimental setup we used for collection of our data corpus with 12 subjects. On this data, we performed cross-validation evaluation, of which we report accuracy for different classification conditions. The results show that the subject-dependent systems achieved a classification accuracy of 97.8% for discriminating visual and auditory perception processes from each other and a classification accuracy of up to 94.8% for detecting modality-specific processes independently of other cognitive activity. The same classification conditions could also be discriminated in a subject-independent fashion with accuracy of up to 94.6 and 86.7%, respectively. We also look at the contributions of the two signal types and show that the fusion of classifiers using different features significantly increases accuracy. PMID:25477777

  12. Hybrid fNIRS-EEG based classification of auditory and visual perception processes.

    PubMed

    Putze, Felix; Hesslinger, Sebastian; Tse, Chun-Yu; Huang, YunYing; Herff, Christian; Guan, Cuntai; Schultz, Tanja

    2014-01-01

    For multimodal Human-Computer Interaction (HCI), it is very useful to identify the modalities on which the user is currently processing information. This would enable a system to select complementary output modalities to reduce the user's workload. In this paper, we develop a hybrid Brain-Computer Interface (BCI) which uses Electroencephalography (EEG) and functional Near Infrared Spectroscopy (fNIRS) to discriminate and detect visual and auditory stimulus processing. We describe the experimental setup we used for collection of our data corpus with 12 subjects. On this data, we performed cross-validation evaluation, of which we report accuracy for different classification conditions. The results show that the subject-dependent systems achieved a classification accuracy of 97.8% for discriminating visual and auditory perception processes from each other and a classification accuracy of up to 94.8% for detecting modality-specific processes independently of other cognitive activity. The same classification conditions could also be discriminated in a subject-independent fashion with accuracy of up to 94.6 and 86.7%, respectively. We also look at the contributions of the two signal types and show that the fusion of classifiers using different features significantly increases accuracy.

  13. Classification of LiDAR Data with Point Based Classification Methods

    NASA Astrophysics Data System (ADS)

    Yastikli, N.; Cetin, Z.

    2016-06-01

    LiDAR is one of the most effective systems for 3 dimensional (3D) data collection in wide areas. Nowadays, airborne LiDAR data is used frequently in various applications such as object extraction, 3D modelling, change detection and revision of maps with increasing point density and accuracy. The classification of the LiDAR points is the first step of LiDAR data processing chain and should be handled in proper way since the 3D city modelling, building extraction, DEM generation, etc. applications directly use the classified point clouds. The different classification methods can be seen in recent researches and most of researches work with the gridded LiDAR point cloud. In grid based data processing of the LiDAR data, the characteristic point loss in the LiDAR point cloud especially vegetation and buildings or losing height accuracy during the interpolation stage are inevitable. In this case, the possible solution is the use of the raw point cloud data for classification to avoid data and accuracy loss in gridding process. In this study, the point based classification possibilities of the LiDAR point cloud is investigated to obtain more accurate classes. The automatic point based approaches, which are based on hierarchical rules, have been proposed to achieve ground, building and vegetation classes using the raw LiDAR point cloud data. In proposed approaches, every single LiDAR point is analyzed according to their features such as height, multi-return, etc. then automatically assigned to the class which they belong to. The use of un-gridded point cloud in proposed point based classification process helped the determination of more realistic rule sets. The detailed parameter analyses have been performed to obtain the most appropriate parameters in the rule sets to achieve accurate classes. The hierarchical rule sets were created for proposed Approach 1 (using selected spatial-based and echo-based features) and Approach 2 (using only selected spatial-based features

  14. A Comparison of Accelerometer Accuracy in Older Adults.

    PubMed

    Phillips, Lorraine J; Petroski, Gregory F; Markis, Natalie E

    2015-01-01

    Older adults' gait disorders present challenges for accurate activity monitoring. The current study compared the accuracy of accelerometer-detected to hand-tallied steps in 50 residential care/assisted living residents. Participants completed two walking trials wearing a Fitbit® Tracker and waist-, wrist-, and ankle-mounted Actigraph GT1M. Agreement between accelerometer and observed counts was calculated using concordance correlation coefficients (CCC), accelerometer to observed count ratios, accelerometer and observed count differences, and Bland-Altman plots. Classification and Regression Tree analysis identified minimum gait speed thresholds to achieve accelerometer accuracy ≥0.80. Participants' mean age was 84.2 and gait speed was 0.64 m/s. All accelerometers underestimated true steps. Only the ankle-mounted GT1M demonstrated positive agreement with observed counts (CCC = 0.205). Thresholds for 0.80 accuracy were gait speeds ≥0.56 m/s for the Fitbit and gait speeds ≥0.71 m/s for the ankle-mounted GT1M. Gait speed and accelerometer placement affected activity monitor accuracy in older adults.

  15. Classification of octet AB-type binary compounds using dynamical charges: A materials informatics perspective

    NASA Astrophysics Data System (ADS)

    Pilania, G.; Gubernatis, J. E.; Lookman, T.

    2015-12-01

    The role of dynamical (or Born effective) charges in classification of octet AB-type binary compounds between four-fold (zincblende/wurtzite crystal structures) and six-fold (rocksalt crystal structure) coordinated systems is discussed. We show that the difference in the dynamical charges of the fourfold and sixfold coordinated structures, in combination with Harrison’s polarity, serves as an excellent feature to classify the coordination of 82 sp-bonded binary octet compounds. We use a support vector machine classifier to estimate the average classification accuracy and the associated variance in our model where a decision boundary is learned in a supervised manner. Finally, we compare the out-of-sample classification accuracy achieved by our feature pair with those reported previously.

  16. Classification of octet AB-type binary compounds using dynamical charges: A materials informatics perspective

    PubMed Central

    Pilania, G.; Gubernatis, J. E.; Lookman, T.

    2015-01-01

    The role of dynamical (or Born effective) charges in classification of octet AB-type binary compounds between four-fold (zincblende/wurtzite crystal structures) and six-fold (rocksalt crystal structure) coordinated systems is discussed. We show that the difference in the dynamical charges of the fourfold and sixfold coordinated structures, in combination with Harrison’s polarity, serves as an excellent feature to classify the coordination of 82 sp–bonded binary octet compounds. We use a support vector machine classifier to estimate the average classification accuracy and the associated variance in our model where a decision boundary is learned in a supervised manner. Finally, we compare the out-of-sample classification accuracy achieved by our feature pair with those reported previously. PMID:26631979

  17. Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals

    PubMed Central

    Ayrulu-Erdem, Birsel; Barshan, Billur

    2011-01-01

    We extract the informative features of gyroscope signals using the discrete wavelet transform (DWT) decomposition and provide them as input to multi-layer feed-forward artificial neural networks (ANNs) for leg motion classification. Since the DWT is based on correlating the analyzed signal with a prototype wavelet function, selection of the wavelet type can influence the performance of wavelet-based applications significantly. We also investigate the effect of selecting different wavelet families on classification accuracy and ANN complexity and provide a comparison between them. The maximum classification accuracy of 97.7% is achieved with the Daubechies wavelet of order 16 and the reverse bi-orthogonal (RBO) wavelet of order 3.1, both with similar ANN complexity. However, the RBO 3.1 wavelet is preferable because of its lower computational complexity in the DWT decomposition and reconstruction. PMID:22319378

  18. Leg motion classification with artificial neural networks using wavelet-based features of gyroscope signals.

    PubMed

    Ayrulu-Erdem, Birsel; Barshan, Billur

    2011-01-01

    We extract the informative features of gyroscope signals using the discrete wavelet transform (DWT) decomposition and provide them as input to multi-layer feed-forward artificial neural networks (ANNs) for leg motion classification. Since the DWT is based on correlating the analyzed signal with a prototype wavelet function, selection of the wavelet type can influence the performance of wavelet-based applications significantly. We also investigate the effect of selecting different wavelet families on classification accuracy and ANN complexity and provide a comparison between them. The maximum classification accuracy of 97.7% is achieved with the Daubechies wavelet of order 16 and the reverse bi-orthogonal (RBO) wavelet of order 3.1, both with similar ANN complexity. However, the RBO 3.1 wavelet is preferable because of its lower computational complexity in the DWT decomposition and reconstruction.

  19. Classification of octet AB-type binary compounds using dynamical charges: A materials informatics perspective

    DOE PAGES

    Pilania, G.; Gubernatis, J. E.; Lookman, T.

    2015-12-03

    The role of dynamical (or Born effective) charges in classification of octet AB-type binary compounds between four-fold (zincblende/wurtzite crystal structures) and six-fold (rocksalt crystal structure) coordinated systems is discussed. We show that the difference in the dynamical charges of the fourfold and sixfold coordinated structures, in combination with Harrison’s polarity, serves as an excellent feature to classify the coordination of 82 sp–bonded binary octet compounds. We use a support vector machine classifier to estimate the average classification accuracy and the associated variance in our model where a decision boundary is learned in a supervised manner. Lastly, we compare the out-of-samplemore » classification accuracy achieved by our feature pair with those reported previously.« less

  20. Classification of octet AB-type binary compounds using dynamical charges: A materials informatics perspective

    SciTech Connect

    Pilania, G.; Gubernatis, J. E.; Lookman, T.

    2015-12-03

    The role of dynamical (or Born effective) charges in classification of octet AB-type binary compounds between four-fold (zincblende/wurtzite crystal structures) and six-fold (rocksalt crystal structure) coordinated systems is discussed. We show that the difference in the dynamical charges of the fourfold and sixfold coordinated structures, in combination with Harrison’s polarity, serves as an excellent feature to classify the coordination of 82 sp–bonded binary octet compounds. We use a support vector machine classifier to estimate the average classification accuracy and the associated variance in our model where a decision boundary is learned in a supervised manner. Lastly, we compare the out-of-sample classification accuracy achieved by our feature pair with those reported previously.

  1. Improving image classification in a complex wetland ecosystem through image fusion techniques

    NASA Astrophysics Data System (ADS)

    Kumar, Lalit; Sinha, Priyakant; Taylor, Subhashni

    2014-01-01

    The aim of this study was to evaluate the impact of image fusion techniques on vegetation classification accuracies in a complex wetland system. Fusion of panchromatic (PAN) and multispectral (MS) Quickbird satellite imagery was undertaken using four image fusion techniques: Brovey, hue-saturation-value (HSV), principal components (PC), and Gram-Schmidt (GS) spectral sharpening. These four fusion techniques were compared in terms of their mapping accuracy to a normal MS image using maximum-likelihood classification (MLC) and support vector machine (SVM) methods. Gram-Schmidt fusion technique yielded the highest overall accuracy and kappa value with both MLC (67.5% and 0.63, respectively) and SVM methods (73.3% and 0.68, respectively). This compared favorably with the accuracies achieved using the MS image. Overall, improvements of 4.1%, 3.6%, 5.8%, 5.4%, and 7.2% in overall accuracies were obtained in case of SVM over MLC for Brovey, HSV, GS, PC, and MS images, respectively. Visual and statistical analyses of the fused images showed that the Gram-Schmidt spectral sharpening technique preserved spectral quality much better than the principal component, Brovey, and HSV fused images. Other factors, such as the growth stage of species and the presence of extensive background water in many parts of the study area, had an impact on classification accuracies.

  2. The Accuracy and Reliability of Crowdsource Annotations of Digital Retinal Images

    PubMed Central

    Mitry, Danny; Zutis, Kris; Dhillon, Baljean; Peto, Tunde; Hayat, Shabina; Khaw, Kay-Tee; Morgan, James E.; Moncur, Wendy; Trucco, Emanuele; Foster, Paul J.

    2016-01-01

    Purpose Crowdsourcing is based on outsourcing computationally intensive tasks to numerous individuals in the online community who have no formal training. Our aim was to develop a novel online tool designed to facilitate large-scale annotation of digital retinal images, and to assess the accuracy of crowdsource grading using this tool, comparing it to expert classification. Methods We used 100 retinal fundus photograph images with predetermined disease criteria selected by two experts from a large cohort study. The Amazon Mechanical Turk Web platform was used to drive traffic to our site so anonymous workers could perform a classification and annotation task of the fundus photographs in our dataset after a short training exercise. Three groups were assessed: masters only, nonmasters only and nonmasters with compulsory training. We calculated the sensitivity, specificity, and area under the curve (AUC) of receiver operating characteristic (ROC) plots for all classifications compared to expert grading, and used the Dice coefficient and consensus threshold to assess annotation accuracy. Results In total, we received 5389 annotations for 84 images (excluding 16 training images) in 2 weeks. A specificity and sensitivity of 71% (95% confidence interval [CI], 69%–74%) and 87% (95% CI, 86%–88%) was achieved for all classifications. The AUC in this study for all classifications combined was 0.93 (95% CI, 0.91–0.96). For image annotation, a maximal Dice coefficient (∼0.6) was achieved with a consensus threshold of 0.25. Conclusions This study supports the hypothesis that annotation of abnormalities in retinal images by ophthalmologically naive individuals is comparable to expert annotation. The highest AUC and agreement with expert annotation was achieved in the nonmasters with compulsory training group. Translational Relevance The use of crowdsourcing as a technique for retinal image analysis may be comparable to expert graders and has the potential to deliver

  3. Improving Speaking Accuracy through Awareness

    ERIC Educational Resources Information Center

    Dormer, Jan Edwards

    2013-01-01

    Increased English learner accuracy can be achieved by leading students through six stages of awareness. The first three awareness stages build up students' motivation to improve, and the second three provide learners with crucial input for change. The final result is "sustained language awareness," resulting in ongoing…

  4. Supervised Protein Family Classification and New Family Construction

    PubMed Central

    Yi, Gangman; Thon, Michael R.

    2012-01-01

    Abstract The goal of protein family classification is to group proteins into families so that proteins within the same family have common function or are related by ancestry. While supervised classification algorithms are available for this purpose, most of these approaches focus on assigning unclassified proteins to known families but do not allow for progressive construction of new families from proteins that cannot be assigned. Although unsupervised clustering algorithms are also available, they do not make use of information from known families. By computing similarities between proteins based on pairwise sequence comparisons, we develop supervised classification algorithms that achieve improved accuracy over previous approaches while allowing for construction of new families. We show that our algorithm has higher accuracy rate and lower mis-classification rate when compared to algorithms that are based on the use of multiple sequence alignments and hidden Markov models, and our algorithm performs well even on families with very few proteins and on families with low sequence similarity. A software program implementing the algorithm (SClassify) is available online (http://faculty.cse.tamu.edu/shsze/sclassify). PMID:22876787

  5. A new Mercer sigmoid kernel for clinical data classification.

    PubMed

    Carrington, André M; Fieguth, Paul W; Chen, Helen H

    2014-01-01

    In classification with Support Vector Machines, only Mercer kernels, i.e. valid kernels, such as the Gaussian RBF kernel, are widely accepted and thus suitable for clinical data. Practitioners would also like to use the sigmoid kernel, a non-Mercer kernel, but its range of validity is difficult to determine, and even within range its validity is in dispute. Despite these shortcomings the sigmoid kernel is used by some, and two kernels in the literature attempt to emulate and improve upon it. We propose the first Mercer sigmoid kernel, that is therefore trustworthy for the classification of clinical data. We show the similarity between the Mercer sigmoid kernel and the sigmoid kernel and, in the process, identify a normalization technique that improves the classification accuracy of the latter. The Mercer sigmoid kernel achieves the best mean accuracy on three clinical data sets, detecting melanoma in skin lesions better than the most popular kernels; while with non-clinical data sets it has no significant difference in median accuracy as compared with the Gaussian RBF kernel. It consistently classifies some points correctly that the Gaussian RBF kernel does not and vice versa.

  6. Evolving point-cloud features for gender classification

    NASA Astrophysics Data System (ADS)

    Keen, Brittany; Fouts, Aaron; Rizki, Mateen; Tamburino, Louis; Mendoza-Schrock, Olga L.

    2011-06-01

    In this paper we explore the use of histogram features extracted from 3D point clouds of human subjects for gender classification. Experiments are conducted using point clouds drawn from the CAESAR anthropometric database provided by the Air Force Research Laboratory (AFRL) Human Effectiveness Directorate and SAE International. This database contains approximately 4400 high resolution LIDAR whole body scans of carefully posed human subjects. Features are extracted from each point cloud by embedding the cloud in series of cylindrical shapes and computing a point count for each cylinder that characterizes a region of the subject. These measurements define rotationally invariant histogram features that are processed by a classifier to label the gender of each subject. Preliminary results using cylinder sizes defined by human experts demonstrate that gender can be predicted with 98% accuracy for the type of high density point cloud found in the CAESAR database. When point cloud densities are reduced to levels that might be obtained using stand-off sensors; gender classification accuracy degrades. We introduce an evolutionary algorithm to optimize the number and size of the cylinders used to define histogram features. The objective of this optimization process is to identify a set of cylindrical features that reduces the error rate when predicting gender from low density point clouds. A wrapper approach is used to interleave feature selection with classifier evaluation to train the evolutionary algorithm. Results of classification accuracy achieved using the evolved features are compared to the baseline feature set defined by human experts.

  7. Towards automatic classification of all WISE sources

    NASA Astrophysics Data System (ADS)

    Kurcz, A.; Bilicki, M.; Solarz, A.; Krupa, M.; Pollo, A.; Małek, K.

    2016-07-01

    Context. The Wide-field Infrared Survey Explorer (WISE) has detected hundreds of millions of sources over the entire sky. Classifying them reliably is, however, a challenging task owing to degeneracies in WISE multicolour space and low levels of detection in its two longest-wavelength bandpasses. Simple colour cuts are often not sufficient; for satisfactory levels of completeness and purity, more sophisticated classification methods are needed. Aims: Here we aim to obtain comprehensive and reliable star, galaxy, and quasar catalogues based on automatic source classification in full-sky WISE data. This means that the final classification will employ only parameters available from WISE itself, in particular those which are reliably measured for the majority of sources. Methods: For the automatic classification we applied a supervised machine learning algorithm, support vector machines (SVM). It requires a training sample with relevant classes already identified, and we chose to use the SDSS spectroscopic dataset (DR10) for that purpose. We tested the performance of two kernels used by the classifier, and determined the minimum number of sources in the training set required to achieve stable classification, as well as the minimum dimension of the parameter space. We also tested SVM classification accuracy as a function of extinction and apparent magnitude. Thus, the calibrated classifier was finally applied to all-sky WISE data, flux-limited to 16 mag (Vega) in the 3.4 μm channel. Results: By calibrating on the test data drawn from SDSS, we first established that a polynomial kernel is preferred over a radial one for this particular dataset. Next, using three classification parameters (W1 magnitude, W1-W2 colour, and a differential aperture magnitude) we obtained very good classification efficiency in all the tests. At the bright end, the completeness for stars and galaxies reaches ~95%, deteriorating to ~80% at W1 = 16 mag, while for quasars it stays at a level of

  8. A Hybrid Classification System for Heart Disease Diagnosis Based on the RFRS Method

    PubMed Central

    Su, Qiang; Zhang, Mo; Zhu, Yanhong; Wang, Qiugen; Wang, Qian

    2017-01-01

    Heart disease is one of the most common diseases in the world. The objective of this study is to aid the diagnosis of heart disease using a hybrid classification system based on the ReliefF and Rough Set (RFRS) method. The proposed system contains two subsystems: the RFRS feature selection system and a classification system with an ensemble classifier. The first system includes three stages: (i) data discretization, (ii) feature extraction using the ReliefF algorithm, and (iii) feature reduction using the heuristic Rough Set reduction algorithm that we developed. In the second system, an ensemble classifier is proposed based on the C4.5 classifier. The Statlog (Heart) dataset, obtained from the UCI database, was used for experiments. A maximum classification accuracy of 92.59% was achieved according to a jackknife cross-validation scheme. The results demonstrate that the performance of the proposed system is superior to the performances of previously reported classification techniques. PMID:28127385

  9. A Unified Framework for Dimensionality Reduction and Classification of Hyperspectral Data

    NASA Astrophysics Data System (ADS)

    Kolluru, P.; Pandey, K.; Padalia, H.

    2014-11-01

    The processing of hyperspectral remote sensing data, for information retrieval, is challenging due to its higher dimensionality. Machine learning based algorithms such as Support Vector Machine (SVM) is preferably applied to perform classification of high dimensionality data. A single-step unified framework is required which could decide the intrinsic dimensionality of data and achieve higher classification accuracy using SVM. This work present development of a SVM-based dimensionality reduction and classification (SVMDRC) framework for hyperspectral data. The proposed unified framework was tested at Los Tollos in Rodalquilar district of Spain, which have predominance of alunite, kaolinite, and illite minerals with sparse vegetation cover. Summer season image was utilized for implementing the proposed method. Modified broken stick rule (MBSR) was used to calculate the intrinsic dimensionality of HyMap data which automatically reduce the number of bands. Comparison of SVMDRC with SVM clearly suggests that SVM alone is inadequate in yielding better classification accuracies for minerals from hyperspectral data rather requires dimensionality reduction. Incorporation of modified broken stick method in SVMDRC framework positively influenced the feature separability and provided better classification accuracy. The mineral distribution map produced for the study area would be useful for refining the areas for mineral exploration.

  10. Comparative defect classifications and analysis of Lasertec's M1350 and M7360

    NASA Astrophysics Data System (ADS)

    Godwin, Milton; Balachandran, Dave; Tamura, Tomoya; Jia, Anwei

    2014-04-01

    Defect classification and characterization on mask substrates and blanks can be used to the identify defect sources within the tool and process. Defect reduction has been achieved in SEMATECH's EUV Mask Blank Development Center (MBDC), aided by successful classifications of defect populations. Failure analysis of EUV substrate and blank defects in the MBDC begins with automatic classification of defects detected by M1350 and M7360 Lasertec inspection tools. Two sets of defect images and classification emerge from the two detection tools. The M1350 provides a more variegated set of 13 defect class types, while the M7360 provides eight. During manual review of the classifications, the defect class sets for both tools are often collapsed to only two major classes of interests with respect to production and failure analysis: particles and pits. This leaves various other classes ignored before subsequent characterization steps like SEM classification and composition analysis. The usefulness of tracking and verifying more detailed classes of defect needs to be explored. SEM analysis can be used to validate the relative size comparison yielded from inspection data alone, beyond the calibrated comparison of inspection signals from well-understood polystyrene latex spheres. The accuracy of rule-based defect classification of inspection tool data must be quantified by statistical tracking and validation SEM analysis. Classification of false counts increases as sensitivity of detection tools are increased to ensure the capture of smallest defects. The validity of calling a defect "false" is usually a manual review of pixel images created on the detection tool.

  11. A new texture and shape based technique for improving meningioma classification.

    PubMed

    Fatima, Kiran; Arooj, Arshia; Majeed, Hammad

    2014-11-01

    Over the past decade, computer-aided diagnosis is rapidly growing due to the availability of patient data, sophisticated image acquisition tools and advancement in image processing and machine learning algorithms. Meningiomas are the tumors of brain and spinal cord. They account for 20% of all the brain tumors. Meningioma subtype classification involves the classification of benign meningioma into four major subtypes: meningothelial, fibroblastic, transitional, and psammomatous. Under the microscope, the histology images of these four subtypes show a variety of textural and structural characteristics. High intraclass and low interclass variabilities in meningioma subtypes make it an extremely complex classification problem. A number of techniques have been proposed for meningioma subtype classification with varying performances on different subtypes. Most of these techniques employed wavelet packet transforms for textural features extraction and analysis of meningioma histology images. In this article, a hybrid classification technique based on texture and shape characteristics is proposed for the classification of meningioma subtypes. Meningothelial and fibroblastic subtypes are classified on the basis of nuclei shapes while grey-level co-occurrence matrix textural features are used to train a multilayer perceptron for the classification of transitional and psammomatous subtypes. On the whole, average classification accuracy of 92.50% is achieved through the proposed hybrid classifier; which to the best of our knowledge is the highest.

  12. Classification of Clouds in Satellite Imagery Using Adaptive Fuzzy Sparse Representation.

    PubMed

    Jin, Wei; Gong, Fei; Zeng, Xingbin; Fu, Randi

    2016-12-16

    Automatic cloud detection and classification using satellite cloud imagery have various meteorological applications such as weather forecasting and climate monitoring. Cloud pattern analysis is one of the research hotspots recently. Since satellites sense the clouds remotely from space, and different cloud types often overlap and convert into each other, there must be some fuzziness and uncertainty in satellite cloud imagery. Satellite observation is susceptible to noises, while traditional cloud classification methods are sensitive to noises and outliers; it is hard for traditional cloud classification methods to achieve reliable results. To deal with these problems, a satellite cloud classification method using adaptive fuzzy sparse representation-based classification (AFSRC) is proposed. Firstly, by defining adaptive parameters related to attenuation rate and critical membership, an improved fuzzy membership is introduced to accommodate the fuzziness and uncertainty of satellite cloud imagery; secondly, by effective combination of the improved fuzzy membership function and sparse representation-based classification (SRC), atoms in training dictionary are optimized; finally, an adaptive fuzzy sparse representation classifier for cloud classification is proposed. Experiment results on FY-2G satellite cloud image show that, the proposed method not only improves the accuracy of cloud classification, but also has strong stability and adaptability with high computational efficiency.

  13. Classification of Clouds in Satellite Imagery Using Adaptive Fuzzy Sparse Representation

    PubMed Central

    Jin, Wei; Gong, Fei; Zeng, Xingbin; Fu, Randi

    2016-01-01

    Automatic cloud detection and classification using satellite cloud imagery have various meteorological applications such as weather forecasting and climate monitoring. Cloud pattern analysis is one of the research hotspots recently. Since satellites sense the clouds remotely from space, and different cloud types often overlap and convert into each other, there must be some fuzziness and uncertainty in satellite cloud imagery. Satellite observation is susceptible to noises, while traditional cloud classification methods are sensitive to noises and outliers; it is hard for traditional cloud classification methods to achieve reliable results. To deal with these problems, a satellite cloud classification method using adaptive fuzzy sparse representation-based classification (AFSRC) is proposed. Firstly, by defining adaptive parameters related to attenuation rate and critical membership, an improved fuzzy membership is introduced to accommodate the fuzziness and uncertainty of satellite cloud imagery; secondly, by effective combination of the improved fuzzy membership function and sparse representation-based classification (SRC), atoms in training dictionary are optimized; finally, an adaptive fuzzy sparse representation classifier for cloud classification is proposed. Experiment results on FY-2G satellite cloud image show that, the proposed method not only improves the accuracy of cloud classification, but also has strong stability and adaptability with high computational efficiency. PMID:27999261

  14. Segmentation, object-oriented applications for remote sensing land cover and land use classification

    NASA Astrophysics Data System (ADS)

    Magee, Kevin S.

    2011-12-01

    Multiscale segmentation, object-oriented methods in remote sensing have predominantly focused on urban applications using very fine resolution imagery. This dissertation explores three distinct but methodologically related remote sensing applications of multiscale segmentation, object-oriented classification using 30 m Landsat data. The first article reveals that object-oriented methods can achieve high classification accuracy for spectrally indistinct classes, even when forced to utilize non-ideal datasets such as hazy Landsat imagery and the "research grade" ASTER DEM. By incorporating spatial metrics, and exploiting elevational characteristics, seasonal wetlands can be differentiated from spectrally inseparable anthropogenically modified land use and from the upland, mixed tropical forest with high regional and local accuracies. The second article proposes and tests an object-oriented, target-constrained method for mangrove-specific change detection. By integrating pixel-based matched filter probability outputs with fuzzy object classification the proposed hybrid method bypass the need for exhaustive classification reducing classification time immensely. This method, then, has provided a means to globally assess mangrove stocks with the accuracy of object-based methods, but with the rapidity and repeatability found normally in less intensive methods. The third article demonstrates how both textural operators can be used at the object level for residential density classification with 30 m Landsat data. It was concluded that both mean GLCM and local Moran's I spatial statistics should be considered for the classification of residential density with the caveat that their utility is class-dependent. Object level usage of Moran's I was found to be able to be better differentiate high density land use classes while mean GLCM texture was indicated to be superior for separating low density land use and land cover. These applications demonstrate the utility of multiscale

  15. Combining multiple features for color texture classification

    NASA Astrophysics Data System (ADS)

    Cusano, Claudio; Napoletano, Paolo; Schettini, Raimondo

    2016-11-01

    The analysis of color and texture has a long history in image analysis and computer vision. These two properties are often considered as independent, even though they are strongly related in images of natural objects and materials. Correlation between color and texture information is especially relevant in the case of variable illumination, a condition that has a crucial impact on the effectiveness of most visual descriptors. We propose an ensemble of hand-crafted image descriptors designed to capture different aspects of color textures. We show that the use of these descriptors in a multiple classifiers framework makes it possible to achieve a very high classification accuracy in classifying texture images acquired under different lighting conditions. A powerful alternative to hand-crafted descriptors is represented by features obtained with deep learning methods. We also show how the proposed combining strategy hand-crafted and convolutional neural networks features can be used together to further improve the classification accuracy. Experimental results on a food database (raw food texture) demonstrate the effectiveness of the proposed strategy.

  16. Progressive Classification Using Support Vector Machines

    NASA Technical Reports Server (NTRS)

    Wagstaff, Kiri; Kocurek, Michael

    2009-01-01

    An algorithm for progressive classification of data, analogous to progressive rendering of images, makes it possible to compromise between speed and accuracy. This algorithm uses support vector machines (SVMs) to classify data. An SVM is a machine learning algorithm that builds a mathematical model of the desired classification concept by identifying the critical data points, called support vectors. Coarse approximations to the concept require only a few support vectors, while precise, highly accurate models require far more support vectors. Once the model has been constructed, the SVM can be applied to new observations. The cost of classifying a new observation is proportional to the number of support vectors in the model. When computational resources are limited, an SVM of the appropriate complexity can be produced. However, if the constraints are not known when the model is constructed, or if they can change over time, a method for adaptively responding to the current resource constraints is required. This capability is particularly relevant for spacecraft (or any other real-time systems) that perform onboard data analysis. The new algorithm enables the fast, interactive application of an SVM classifier to a new set of data. The classification process achieved by this algorithm is characterized as progressive because a coarse approximation to the true classification is generated rapidly and thereafter iteratively refined. The algorithm uses two SVMs: (1) a fast, approximate one and (2) slow, highly accurate one. New data are initially classified by the fast SVM, producing a baseline approximate classification. For each classified data point, the algorithm calculates a confidence index that indicates the likelihood that it was classified correctly in the first pass. Next, the data points are sorted by their confidence indices and progressively reclassified by the slower, more accurate SVM, starting with the items most likely to be incorrectly classified. The user

  17. Classification of amyloid status using machine learning with histograms of oriented 3D gradients.

    PubMed

    Cattell, Liam; Platsch, Günther; Pfeiffer, Richie; Declerck, Jérôme; Schnabel, Julia A; Hutton, Chloe

    2016-01-01

    Brain amyloid burden may be quantitatively assessed from positron emission tomography imaging using standardised uptake value ratios. Using these ratios as an adjunct to visual image assessment has been shown to improve inter-reader reliability, however, the amyloid positivity threshold is dependent on the tracer and specific image regions used to calculate the uptake ratio. To address this problem, we propose a machine learning approach to amyloid status classification, which is independent of tracer and does not require a specific set of regions of interest. Our method extracts feature vectors from amyloid images, which are based on histograms of oriented three-dimensional gradients. We optimised our method on 133 (18)F-florbetapir brain volumes, and applied it to a separate test set of 131 volumes. Using the same parameter settings, we then applied our method to 209 (11)C-PiB images and 128 (18)F-florbetaben images. We compared our method to classification results achieved using two other methods: standardised uptake value ratios and a machine learning method based on voxel intensities. Our method resulted in the largest mean distances between the subjects and the classification boundary, suggesting that it is less likely to make low-confidence classification decisions. Moreover, our method obtained the highest classification accuracy for all three tracers, and consistently achieved above 96% accuracy.

  18. Automated classification of periodic variable stars detected by the wide-field infrared survey explorer

    SciTech Connect

    Masci, Frank J.; Grillmair, Carl J.; Cutri, Roc M.; Hoffman, Douglas I.

    2014-07-01

    We describe a methodology to classify periodic variable stars identified using photometric time-series measurements constructed from the Wide-field Infrared Survey Explorer (WISE) full-mission single-exposure Source Databases. This will assist in the future construction of a WISE Variable Source Database that assigns variables to specific science classes as constrained by the WISE observing cadence with statistically meaningful classification probabilities. We have analyzed the WISE light curves of 8273 variable stars identified in previous optical variability surveys (MACHO, GCVS, and ASAS) and show that Fourier decomposition techniques can be extended into the mid-IR to assist with their classification. Combined with other periodic light-curve features, this sample is then used to train a machine-learned classifier based on the random forest (RF) method. Consistent with previous classification studies of variable stars in general, the RF machine-learned classifier is superior to other methods in terms of accuracy, robustness against outliers, and relative immunity to features that carry little or redundant class information. For the three most common classes identified by WISE: Algols, RR Lyrae, and W Ursae Majoris type variables, we obtain classification efficiencies of 80.7%, 82.7%, and 84.5% respectively using cross-validation analyses, with 95% confidence intervals of approximately ±2%. These accuracies are achieved at purity (or reliability) levels of 88.5%, 96.2%, and 87.8% respectively, similar to that achieved in previous automated classification studies of periodic variable stars.

  19. Behavioral state classification in epileptic brain using intracranial electrophysiology

    NASA Astrophysics Data System (ADS)

    Kremen, Vaclav; Duque, Juliano J.; Brinkmann, Benjamin H.; Berry, Brent M.; Kucewicz, Michal T.; Khadjevand, Fatemeh; Van Gompel, Jamie; Stead, Matt; St. Louis, Erik K.; Worrell, Gregory A.

    2017-04-01

    Objective. Automated behavioral state classification can benefit next generation implantable epilepsy devices. In this study we explored the feasibility of automated awake (AW) and slow wave sleep (SWS) classification using wide bandwidth intracranial EEG (iEEG) in patients undergoing evaluation for epilepsy surgery. Approach. Data from seven patients (age 34+/- 12 , 4 women) who underwent intracranial depth electrode implantation for iEEG monitoring were included. Spectral power features (0.1–600 Hz) spanning several frequency bands from a single electrode were used to train and test a support vector machine classifier. Main results. Classification accuracy of 97.8  ±  0.3% (normal tissue) and 89.4  ±  0.8% (epileptic tissue) across seven subjects using multiple spectral power features from a single electrode was achieved. Spectral power features from electrodes placed in normal temporal neocortex were found to be more useful (accuracy 90.8  ±  0.8%) for sleep-wake state classification than electrodes located in normal hippocampus (87.1  ±  1.6%). Spectral power in high frequency band features (Ripple (80–250 Hz), Fast Ripple (250–600 Hz)) showed comparable performance for AW and SWS classification as the best performing Berger bands (Alpha, Beta, low Gamma) with accuracy  ⩾90% using a single electrode contact and single spectral feature. Significance. Automated classification of wake and SWS should prove useful for future implantable epilepsy devices with limited computational power, memory, and number of electrodes. Applications include quantifying patient sleep patterns and behavioral state dependent detection, prediction, and electrical stimulation therapies.

  20. Wavelet Packet Entropy for Heart Murmurs Classification

    PubMed Central

    Safara, Fatemeh; Doraisamy, Shyamala; Azman, Azreen; Jantan, Azrul; Ranga, Sri

    2012-01-01

    Heart murmurs are the first signs of cardiac valve disorders. Several studies have been conducted in recent years to automatically differentiate normal heart sounds, from heart sounds with murmurs using various types of audio features. Entropy was successfully used as a feature to distinguish different heart sounds. In this paper, new entropy was introduced to analyze heart sounds and the feasibility of using this entropy in classification of five types of heart sounds and murmurs was shown. The entropy was previously introduced to analyze mammograms. Four common murmurs were considered including aortic regurgitation, mitral regurgitation, aortic stenosis, and mitral stenosis. Wavelet packet transform was employed for heart sound analysis, and the entropy was calculated for deriving feature vectors. Five types of classification were performed to evaluate the discriminatory power of the generated features. The best results were achieved by BayesNet with 96.94% accuracy. The promising results substantiate the effectiveness of the proposed wavelet packet entropy for heart sounds classification. PMID:23227043

  1. Classification of EEG with structural feature dictionaries in a brain computer interface.

    PubMed

    Göksu, Fikri; Ince, Nuri Firat; Tadipatri, Vijay Aditya; Tewfik, Ahmed H

    2008-01-01

    We present a new method for the classification of EEG in a brain computer interface by adapting subject specific features in spectral, temporal and spatial domain. For this particular purpose we extend our previous work on ECoG classification based on structural feature dictionary and apply it to extract the spectro-temporal patterns of multichannel EEG recordings related to a motor imagery task. The construction of the feature dictionary based on undecimated wavelet packet transform is extended to block FFT. We evaluate several subset selection algorithms to select a small number of features for final classification. We tested our proposed approach on five subjects of BCI Competition 2005 dataset- IVa. By adapting the wavelet filter for each subject, the algorithm achieved an average classification accuracy of 91.4% The classification results and characteristic of selected features indicate that the proposed algorithm can jointly adapt to EEG patterns in spectro-spatio-temporal domain and provide classification accuracies as good as existing methods used in the literature.

  2. Topological graph kernel on multiple thresholded functional connectivity networks for mild cognitive impairment classification.

    PubMed

    Jie, Biao; Zhang, Daoqiang; Wee, Chong-Yaw; Shen, Dinggang

    2014-07-01

    Recently, brain connectivity networks have been used for classification of Alzheimer's disease and mild cognitive impairment (MCI) from normal controls (NC). In typical connectivity-networks-based classification approaches, local measures of connectivity networks are first extracted from each region-of-interest as network features, which are then concatenated into a vector for subsequent feature selection and classification. However, some useful structural information of network, especially global topological information, may be lost in this type of approaches. To address this issue, in this article, we propose a connectivity-networks-based classification framework to identify accurately the MCI patients from NC. The core of the proposed method involves the use of a new graph-kernel-based approach to measure directly the topological similarity between connectivity networks. We evaluate our method on functional connectivity networks of 12 MCI and 25 NC subjects. The experimental results show that our proposed method achieves a classification accuracy of 91.9%, a sensitivity of 100.0%, a balanced accuracy of 94.0%, and an area under receiver operating characteristic curve of 0.94, demonstrating a great potential in MCI classification, based on connectivity networks. Further connectivity analysis indicates that the connectivity of the selected brain regions is different between MCI patients and NC, that is, MCI patients show reduced functional connectivity compared with NC, in line with the findings reported in the existing studies.

  3. Effective Dimension Reduction Using Sequential Projection Pursuit On Gene Expression Data for Cancer Classification

    SciTech Connect

    Webb-Robertson, Bobbie-Jo M.; Havre, Susan L.

    2004-06-23

    Motiviation: Classification is a powerful tool for uncovering interesting phenomena, for example classes of cancer, in microarray data. Due to the small number of observations (n) in comparison to the number of variables (p), genes, classification on microarray data is challenging. Thus, multivariate dimension reduction techniques are commonly used as a precursor to classification of microarray data; typically this is principal component analysis (PCA) or singular value decomposition (SVD). Since PCA and SVD are concerned with explaining the variance-covariance structure of the data, they may not be the best choice when the between-cluster variance is smaller than the within-cluster variance. Recently an attractive alternative to PCA, sequential projection pursuit (SPP), has been introduced which is designed to elicit clustering tendencies in the data. Thus, in some cases SPP may be more appropriate when performing clustering or classification analysis. Results: We compare the performance of SPP to PCA on two cancer gene expression datasets related to leukemia and colon cancer. Using PCA and SPP to reduce the dimensionality of the data to m<classification accuracy of each method at various levels of . For both datasets SPP achieves higher classification accuracy at low values of m. For example, given m=1 on the two-class case for the leukemia dataset SPP correctly classifies 77% of the observations in comparison to 50% for PCA.

  4. Robust neural-network-based classification of premature ventricular contractions using wavelet transform and timing interval features.

    PubMed

    Inan, Omer T; Giovangrandi, Laurent; Kovacs, Gregory T A

    2006-12-01

    Automatic electrocardiogram (ECG) beat classification is essential to timely diagnosis of dangerous heart conditions. Specifically, accurate detection of premature ventricular contractions (PVCs) is imperative to prepare for the possible onset of life-threatening arrhythmias. Although many groups have developed highly accurate algorithms for detecting PVC beats, results have generally been limited to relatively small data sets. Additionally, many of the highest classification accuracies (> 90%) have been achieved in experiments where training and testing sets overlapped significantly. Expanding the overall data set greatly reduces overall accuracy due to significant variation in ECG morphology among different patients. As a result, we believe that morphological information must be coupled with timing information, which is more constant among patients, in order to achieve high classification accuracy for larger data sets. With this approach, we combined wavelet-transformed ECG waves with timing information as our feature set for classification. We used select waveforms of 18 files of the MIT/BIH arrhythmia database, which provides an annotated collection of normal and arrhythmic beats, for training our neural-network classifier. We then tested the classifier on these 18 training files as well as 22 other files from the database. The accuracy was 95.16% over 93,281 beats from all 40 files, and 96.82% over the 22 files outside the training set in differentiating normal, PVC, and other beats.

  5. Weapon identification using hierarchical classification of acoustic signatures

    NASA Astrophysics Data System (ADS)

    Khan, Saad; Divakaran, Ajay; Sawhney, Harpreet S.

    2009-05-01

    We apply a unique hierarchical audio classification technique to weapon identification using gunshot analysis. The Audio Classification classifies each audio segment as one of ten weapon classes (e.g., 9mm, 22, shotgun etc.) using lowcomplexity Gaussian Mixture Models (GMM). The first level of hierarchy consists of classification into broad weapons categories such as Rifle, Hand-Gun etc. and the second consists of classification into specific weapons such as 9mm, 357 etc. Our experiments have yielded over 90% classification accuracy at the coarse (rifle-handgun) level of the classification hierarchy and over 85% accuracy at the finer level (weapon category such as 9mm).

  6. Semi-supervised classification via local spline regression.

    PubMed

    Xiang, Shiming; Nie, Feiping; Zhang, Changshui

    2010-11-01

    This paper presents local spline regression for semi-supervised classification. The core idea in our approach is to introduce splines developed in Sobolev space to map the data points directly to be class labels. The spline is composed of polynomials and Green's functions. It is smooth, nonlinear, and able to interpolate the scattered data points with high accuracy. Specifically, in each neighborhood, an optimal spline is estimated via regularized least squares regression. With this spline, each of the neighboring data points is mapped to be a class label. Then, the regularized loss is evaluated and further formulated in terms of class label vector. Finally, all of the losses evaluated in local neighborhoods are accumulated together to measure the global consistency on the labeled and unlabeled data. To achieve the goal of semi-supervised classification, an objective function is constructed by combining together the global loss of the local spline regressions and the squared errors of the class labels of the labeled data. In this way, a transductive classification algorithm is developed in which a globally optimal classification can be finally obtained. In the semi-supervised learning setting, the proposed algorithm is analyzed and addressed into the Laplacian regularization framework. Comparative classification experiments on many public data sets and applications to interactive image segmentation and image matting illustrate the validity of our method.

  7. Modeling neuron selectivity over simple midlevel features for image classification.

    PubMed

    Shu Kong; Zhuolin Jiang; Qiang Yang

    2015-08-01

    We now know that good mid-level features can greatly enhance the performance of image classification, but how to efficiently learn the image features is still an open question. In this paper, we present an efficient unsupervised midlevel feature learning approach (MidFea), which only involves simple operations, such as k-means clustering, convolution, pooling, vector quantization, and random projection. We show this simple feature can also achieve good performance in traditional classification task. To further boost the performance, we model the neuron selectivity (NS) principle by building an additional layer over the midlevel features prior to the classifier. The NS-layer learns category-specific neurons in a supervised manner with both bottom-up inference and top-down analysis, and thus supports fast inference for a query image. Through extensive experiments, we demonstrate that this higher level NS-layer notably improves the classification accuracy with our simple MidFea, achieving comparable performances for face recognition, gender classification, age estimation, and object categorization. In particular, our approach runs faster in inference by an order of magnitude than sparse coding-based feature learning methods. As a conclusion, we argue that not only do carefully learned features (MidFea) bring improved performance, but also a sophisticated mechanism (NS-layer) at higher level boosts the performance further.

  8. Automatic Fault Characterization via Abnormality-Enhanced Classification

    SciTech Connect

    Bronevetsky, G; Laguna, I; de Supinski, B R

    2010-12-20

    Enterprise and high-performance computing systems are growing extremely large and complex, employing hundreds to hundreds of thousands of processors and software/hardware stacks built by many people across many organizations. As the growing scale of these machines increases the frequency of faults, system complexity makes these faults difficult to detect and to diagnose. Current system management techniques, which focus primarily on efficient data access and query mechanisms, require system administrators to examine the behavior of various system services manually. Growing system complexity is making this manual process unmanageable: administrators require more effective management tools that can detect faults and help to identify their root causes. System administrators need timely notification when a fault is manifested that includes the type of fault, the time period in which it occurred and the processor on which it originated. Statistical modeling approaches can accurately characterize system behavior. However, the complex effects of system faults make these tools difficult to apply effectively. This paper investigates the application of classification and clustering algorithms to fault detection and characterization. We show experimentally that naively applying these methods achieves poor accuracy. Further, we design novel techniques that combine classification algorithms with information on the abnormality of application behavior to improve detection and characterization accuracy. Our experiments demonstrate that these techniques can detect and characterize faults with 65% accuracy, compared to just 5% accuracy for naive approaches.

  9. Superordinate Shape Classification Using Natural Shape Statistics

    ERIC Educational Resources Information Center

    Wilder, John; Feldman, Jacob; Singh, Manish

    2011-01-01

    This paper investigates the classification of shapes into broad natural categories such as "animal" or "leaf". We asked whether such coarse classifications can be achieved by a simple statistical classification of the shape skeleton. We surveyed databases of natural shapes, extracting shape skeletons and tabulating their…

  10. Diagnostic classification of intrinsic functional connectivity highlights somatosensory, default mode, and visual regions in autism.

    PubMed

    Chen, Colleen P; Keown, Christopher L; Jahedi, Afrooz; Nair, Aarti; Pflieger, Mark E; Bailey, Barbara A; Müller, Ralph-Axel

    2015-01-01

    Despite consensus on the neurological nature of autism spectrum disorders (ASD), brain biomarkers remain unknown and diagnosis continues to be based on behavioral criteria. Growing evidence suggests that brain abnormalities in ASD occur at the level of interconnected networks; however, previous attempts using functional connectivity data for diagnostic classification have reached only moderate accuracy. We selected 252 low-motion resting-state functional MRI (rs-fMRI) scans from the Autism Brain Imaging Data Exchange (ABIDE) including typically developing (TD) and ASD participants (n = 126 each), matched for age, non-verbal IQ, and head motion. A matrix of functional connectivities between 220 functionally defined regions of interest was used for diagnostic classification, implementing several machine learning tools. While support vector machines in combination with particle swarm optimization and recursive feature elimination performed modestly (with accuracies for validation datasets <70%), diagnostic classification reached a high accuracy of 91% with random forest (RF), a nonparametric ensemble learning method. Among the 100 most informative features (connectivities), for which this peak accuracy was achieved, participation of somatosensory, default mode, visual, and subcortical regions stood out. Whereas some of these findings were expected, given previous findings of default mode abnormalities and atypical visual functioning in ASD, the prominent role of somatosensory regions was remarkable. The finding of peak accuracy for 100 interregional functional connectivities further suggests that brain biomarkers of ASD may be regionally complex and distributed, rather than localized.

  11. MRI Brain Images Healthy and Pathological Tissues Classification with the Aid of Improved Particle Swarm Optimization and Neural Network

    PubMed Central

    Sheejakumari, V.; Sankara Gomathi, B.

    2015-01-01

    The advantages of magnetic resonance imaging (MRI) over other diagnostic imaging modalities are its higher spatial resolution and its better discrimination of soft tissue. In the previous tissues classification method, the healthy and pathological tissues are classified from the MRI brain images using HGANN. But the method lacks sensitivity and accuracy measures. The classification method is inadequate in its performance in terms of these two parameters. So, to avoid these drawbacks, a new classification method is proposed in this paper. Here, new tissues classification method is proposed with improved particle swarm optimization (IPSO) technique to classify the healthy and pathological tissues from the given MRI images. Our proposed classification method includes the same four stages, namely, tissue segmentation, feature extraction, heuristic feature selection, and tissue classification. The method is implemented and the results are analyzed in terms of various statistical performance measures. The results show the effectiveness of the proposed classification method in classifying the tissues and the achieved improvement in sensitivity and accuracy measures. Furthermore, the performance of the proposed technique is evaluated by comparing it with the other segmentation methods. PMID:25977706

  12. Convolutional neural networks for synthetic aperture radar classification

    NASA Astrophysics Data System (ADS)

    Profeta, Andrew; Rodriguez, Andres; Clouse, H. Scott

    2016-05-01

    For electro-optical object recognition, convolutional neural networks (CNNs) are the state-of-the-art. For large datasets, CNNs are able to learn meaningful features used for classification. However, their application to synthetic aperture radar (SAR) has been limited. In this work we experimented with various CNN architectures on the MSTAR SAR dataset. As the input to the CNN we used the magnitude and phase (2 channels) of the SAR imagery. We used the deep learning toolboxes CAFFE and Torch7. Our results show that we can achieve 93% accuracy on the MSTAR dataset using CNNs.

  13. Comparison of Hybrid Classifiers for Crop Classification Using Normalized Difference Vegetation Index Time Series: A Case Study for Major Crops in North Xinjiang, China.

    PubMed

    Hao, Pengyu; Wang, Li; Niu, Zheng

    2015-01-01

    A range of single classifiers have been proposed to classify crop types using time series vegetation indices, and hybrid classifiers are used to improve discriminatory power. Traditional fusion rules use the product of multi-single classifiers, but that strategy cannot integrate the classification output of machine learning classifiers. In this research, the performance of two hybrid strategies, multiple voting (M-voting) and probabilistic fusion (P-fusion), for crop classification using NDVI time series were tested with different training sample sizes at both pixel and object levels, and two representative counties in north Xinjiang were selected as study area. The single classifiers employed in this research included Random Forest (RF), Support Vector Machine (SVM), and See 5 (C 5.0). The results indicated that classification performance improved (increased the mean overall accuracy by 5%~10%, and reduced standard deviation of overall accuracy by around 1%) substantially with the training sample number, and when the training sample size was small (50 or 100 training samples), hybrid classifiers substantially outperformed single classifiers with higher mean overall accuracy (1%~2%). However, when abundant training samples (4,000) were employed, single classifiers could achieve good classification accuracy, and all classifiers obtained similar performances. Additionally, although object-based classification did not improve accuracy, it resulted in greater visual appeal, especially in study areas with a heterogeneous cropping pattern.

  14. Comparison of Hybrid Classifiers for Crop Classification Using Normalized Difference Vegetation Index Time Series: A Case Study for Major Crops in North Xinjiang, China

    PubMed Central

    Hao, Pengyu; Wang, Li; Niu, Zheng

    2015-01-01

    A range of single classifiers have been proposed to classify crop types using time series vegetation indices, and hybrid classifiers are used to improve discriminatory power. Traditional fusion rules use the product of multi-single classifiers, but that strategy cannot integrate the classification output of machine learning classifiers. In this research, the performance of two hybrid strategies, multiple voting (M-voting) and probabilistic fusion (P-fusion), for crop classification using NDVI time series were tested with different training sample sizes at both pixel and object levels, and two representative counties in north Xinjiang were selected as study area. The single classifiers employed in this research included Random Forest (RF), Support Vector Machine (SVM), and See 5 (C 5.0). The results indicated that classification performance improved (increased the mean overall accuracy by 5%~10%, and reduced standard deviation of overall accuracy by around 1%) substantially with the training sample number, and when the training sample size was small (50 or 100 training samples), hybrid classifiers substantially outperformed single classifiers with higher mean overall accuracy (1%~2%). However, when abundant training samples (4,000) were employed, single classifiers could achieve good classification accuracy, and all classifiers obtained similar performances. Additionally, although object-based classification did not improve accuracy, it resulted in greater visual appeal, especially in study areas with a heterogeneous cropping pattern. PMID:26360597

  15. Noise-Tolerant Hyperspectral Signature Classification in Unresolved Object Detection with Adaptive Tabular Nearest Neighbor Encoding

    NASA Astrophysics Data System (ADS)

    Schmalz, M.; Key, G.

    ) and rate of false detections (Rfa). Adaptive TNE can thus achieve accurate signature classification in the presence of time-varying noise, closely spaced or interleaved signatures, and imaging system optical distortions. We analyze classification accuracy of closely spaced spectral signatures adapted from a NASA database of space material signatures. Additional analysis pertains to computational complexity and noise sensitivity, which are superior to non-adaptive TNE or Bayesian techniques based on classical neural networks.

  16. Empirical Analysis and Automated Classification of Security Bug Reports

    NASA Technical Reports Server (NTRS)

    Tyo, Jacob P.

    2016-01-01

    With the ever expanding amount of sensitive data being placed into computer systems, the need for effective cybersecurity is of utmost importance. However, there is a shortage of detailed empirical studies of security vulnerabilities from which cybersecurity metrics and best practices could be determined. This thesis has two main research goals: (1) to explore the distribution and characteristics of security vulnerabilities based on the information provided in bug tracking systems and (2) to develop data analytics approaches for automatic classification of bug reports as security or non-security related. This work is based on using three NASA datasets as case studies. The empirical analysis showed that the majority of software vulnerabilities belong only to a small number of types. Addressing these types of vulnerabilities will consequently lead to cost efficient improvement of software security. Since this analysis requires labeling of each bug report in the bug tracking system, we explored using machine learning to automate the classification of each bug report as a security or non-security related (two-class classification), as well as each security related bug report as specific security type (multiclass classification). In addition to using supervised machine learning algorithms, a novel unsupervised machine learning approach is proposed. An ac- curacy of 92%, recall of 96%, precision of 92%, probability of false alarm of 4%, F-Score of 81% and G-Score of 90% were the best results achieved during two-class classification. Furthermore, an accuracy of 80%, recall of 80%, precision of 94%, and F-score of 85% were the best results achieved during multiclass classification.

  17. Single-trial EEG RSVP classification using convolutional neural networks

    NASA Astrophysics Data System (ADS)

    Shamwell, Jared; Lee, Hyungtae; Kwon, Heesung; Marathe, Amar R.; Lawhern, Vernon; Nothwang, William

    2016-05-01

    Traditionally, Brain-Computer Interfaces (BCI) have been explored as a means to return function to paralyzed or otherwise debilitated individuals. An emerging use for BCIs is in human-autonomy sensor fusion where physiological data from healthy subjects is combined with machine-generated information to enhance the capabilities of artificial systems. While human-autonomy fusion of physiological data and computer vision have been shown to improve classification during visual search tasks, to date these approaches have relied on separately trained classification models for each modality. We aim to improve human-autonomy classification performance by developing a single framework that builds codependent models of human electroencephalograph (EEG) and image data to generate fused target estimates. As a first step, we developed a novel convolutional neural network (CNN) architecture and applied it to EEG recordings of subjects classifying target and non-target image presentations during a rapid serial visual presentation (RSVP) image triage task. The low signal-to-noise ratio (SNR) of EEG inherently limits the accuracy of single-trial classification and when combined with the high dimensionality of EEG recordings, extremely large training sets are needed to prevent overfitting and achieve accurate classification from raw EEG data. This paper explores a new deep CNN architecture for generalized multi-class, single-trial EEG classification across subjects. We compare classification performance from the generalized CNN architecture trained across all subjects to the individualized XDAWN, HDCA, and CSP neural classifiers which are trained and tested on single subjects. Preliminary results show that our CNN meets and slightly exceeds the performance of the other classifiers despite being trained across subjects.

  18. Global Optimization Ensemble Model for Classification Methods

    PubMed Central

    Anwar, Hina; Qamar, Usman; Muzaffar Qureshi, Abdul Wahab

    2014-01-01

    Supervised learning is the process of data mining for deducing rules from training datasets. A broad array of supervised learning algorithms exists, every one of them with its own advantages and drawbacks. There are some basic issues that affect the accuracy of classifier while solving a supervised learning problem, like bias-variance tradeoff, dimensionality of input space, and noise in the input data space. All these problems affect the accuracy of classifier and are the reason that there is no global optimal method for classification. There is not any generalized improvement method that can increase the accuracy of any classifier while addressing all the problems stated above. This paper proposes a global optimization ensemble model for classification methods (GMC) that can improve the overall accuracy for supervised learning problems. The experimental results on various public datasets showed that the proposed model improved the accuracy of the classification models from 1% to 30% depending upon the algorithm complexity. PMID:24883382

  19. Feature analysis for indoor radar target classification

    NASA Astrophysics Data System (ADS)

    Bufler, Travis D.; Narayanan, Ram M.

    2016-05-01

    This paper analyzes the spectral features from human beings and indoor clutter for building and tuning Support Vector Machines (SVMs) classifiers for the purpose of classifying stationary human targets. The spectral characteristics were obtained through simulations using Finite Difference Time Domain (FDTD) techniques where the radar cross section (RCS) of humans and indoor clutter objects were captured over a wide range of frequencies, polarizations, aspect angles, and materials. Additionally, experimental data was obtained using a vector network analyzer. Two different feature sets for class discrimination are used from the acquired target and clutter RCS spectral data sets. The first feature vectors consist of the raw spectral characteristics, while the second set of feature vectors are statistical features extracted over a set frequency interval. Utilizing variables of frequency and polarization, a SVM classifier can be trained to classify unknown targets as a human or clutter. Classification accuracy over 80% can be effectively achieved given appropriate features.

  20. A new classification scheme of plastic wastes based upon recycling labels

    SciTech Connect

    Özkan, Kemal; Ergin, Semih; Işık, Şahin; Işıklı, İdil

    2015-01-15

    experimental setup with a camera and homogenous backlighting. Due to the giving global solution for a classification problem, Support Vector Machine (SVM) is selected to achieve the classification task and majority voting technique is used as the decision mechanism. This technique equally weights each classification result and assigns the given plastic object to the class that the most classification results agree on. The proposed classification scheme provides high accuracy rate, and also it is able to run in real-time applications. It can automatically classify the plastic bottle types with approximately 90% recognition accuracy. Besides this, the proposed methodology yields approximately 96% classification rate for the separation of PET or non-PET plastic types. It also gives 92% accuracy for the categorization of non-PET plastic types into HPDE or PP.

  1. Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images

    PubMed Central

    Fehr, Duc; Veeraraghavan, Harini; Wibmer, Andreas; Gondo, Tatsuo; Matsumoto, Kazuhiro; Vargas, Herbert Alberto; Sala, Evis; Hricak, Hedvig; Deasy, Joseph O.

    2015-01-01

    Noninvasive, radiological image-based detection and stratification of Gleason patterns can impact clinical outcomes, treatment selection, and the determination of disease status at diagnosis without subjecting patients to surgical biopsies. We present machine learning-based automatic classification of prostate cancer aggressiveness by combining apparent diffusion coefficient (ADC) and T2-weighted (T2-w) MRI-based texture features. Our approach achieved reasonably accurate classification of Gleason scores (GS) 6(3+3) vs. ≥7 and 7(3+4) vs. 7(4+3) despite the presence of highly unbalanced samples by using two different sample augmentation techniques followed by feature selection-based classification. Our method distinguished between GS 6(3+3) and ≥7 cancers with 93% accuracy for cancers occurring in both peripheral (PZ) and transition (TZ) zones and 92% for cancers occurring in the PZ alone. Our approach distinguished the GS 7(3+4) from GS 7(4+3) with 92% accuracy for cancers occurring in both the PZ and TZ and with 93% for cancers occurring in the PZ alone. In comparison, a classifier using only the ADC mean achieved a top accuracy of 58% for distinguishing GS 6(3+3) vs. GS ≥7 for cancers occurring in PZ and TZ and 63% for cancers occurring in PZ alone. The same classifier achieved an accuracy of 59% for distinguishing GS 7(3+4) from GS 7(4+3) occurring in the PZ and TZ and 60% for cancers occurring in PZ alone. Separate analysis of the cancers occurring in TZ alone was not performed owing to the limited number of samples. Our results suggest that texture features derived from ADC and T2-w MRI together with sample augmentation can help to obtain reasonably accurate classification of Gleason patterns. PMID:26578786

  2. Image features of spectral correlation function for arrhythmia classification.

    PubMed

    Khalaf, Aya F; Owis, Mohammed I; Yassine, Inas A

    2015-01-01

    Recently, computerized arrhythmia classification tools have been intensively used to aid physicians to recognize different irregular heartbeats. In this paper, we introduce arrhythmia CAD system exploiting cyclostationary signal analysis through estimation of the spectral correlation function for 5 different beat types. Two experiments were performed. Raw spectral correlation data were used as features in the first experiment while the other experiment which dealt with the spectral correlation coefficients as image included extraction of wavelet and shape features followed by fisher score for dimensionality reduction. As for the classification task, Support Vector Machine (SVM) with linear kernel was used for both experiments. The experimental results showed that both proposed approaches are superior compared to several state of the art methods. This approach achieved sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of 99.20%, 99.70%, 98.60%, 99.90% and 97.60% respectively.

  3. Collagen morphology and texture analysis: from statistics to classification

    PubMed Central

    Mostaço-Guidolin, Leila B.; Ko, Alex C.-T.; Wang, Fei; Xiang, Bo; Hewko, Mark; Tian, Ganghong; Major, Arkady; Shiomi, Masashi; Sowa, Michael G.

    2013-01-01

    In this study we present an image analysis methodology capable of quantifying morphological changes in tissue collagen fibril organization caused by pathological conditions. Texture analysis based on first-order statistics (FOS) and second-order statistics such as gray level co-occurrence matrix (GLCM) was explored to extract second-harmonic generation (SHG) image features that are associated with the structural and biochemical changes of tissue collagen networks. Based on these extracted quantitative parameters, multi-group classification of SHG images was performed. With combined FOS and GLCM texture values, we achieved reliable classification of SHG collagen images acquired from atherosclerosis arteries with >90% accuracy, sensitivity and specificity. The proposed methodology can be applied to a wide range of conditions involving collagen re-modeling, such as in skin disorders, different types of fibrosis and muscular-skeletal diseases affecting ligaments and cartilage. PMID:23846580

  4. Improved PCA + LDA Applies to Gastric Cancer Image Classification Process

    NASA Astrophysics Data System (ADS)

    Gan, Lan; Lv, Wenya; Zhang, Xu; Meng, Xiuming

    Principal component analysis (PCA) and linear discriminant analysis (LDA) are two most widely used pattern recognition methods in the field of feature extraction,while PCA + LDA is often used in image recognition.Here,we apply PCA + LDA to gastric cancer image feature classification, but the traditional PCA + LDA dimension reduction method has good effect on the training sample dimensionality and clustering, the effect on test samples dimension reduction and clustering is very poor, that is, the traditional PCA + LDA exists Generalization problem on the test samples. To solve this problem, this paper proposes an improved PCA + LDA method, which mainly considers from the LDA transform; improves the traditional PCA + LDA;increase the generalization performance of LDA on test samples and increases the classification accuracy on test samples. The experiment proves that the method can achieve good clustering.

  5. Collagen morphology and texture analysis: from statistics to classification.

    PubMed

    Mostaço-Guidolin, Leila B; Ko, Alex C-T; Wang, Fei; Xiang, Bo; Hewko, Mark; Tian, Ganghong; Major, Arkady; Shiomi, Masashi; Sowa, Michael G

    2013-01-01

    In this study we present an image analysis methodology capable of quantifying morphological changes in tissue collagen fibril organization caused by pathological conditions. Texture analysis based on first-order statistics (FOS) and second-order statistics such as gray level co-occurrence matrix (GLCM) was explored to extract second-harmonic generation (SHG) image features that are associated with the structural and biochemical changes of tissue collagen networks. Based on these extracted quantitative parameters, multi-group classification of SHG images was performed. With combined FOS and GLCM texture values, we achieved reliable classification of SHG collagen images acquired from atherosclerosis arteries with >90% accuracy, sensitivity and specificity. The proposed methodology can be applied to a wide range of conditions involving collagen re-modeling, such as in skin disorders, different types of fibrosis and muscular-skeletal diseases affecting ligaments and cartilage.

  6. Collagen morphology and texture analysis: from statistics to classification

    NASA Astrophysics Data System (ADS)

    Mostaço-Guidolin, Leila B.; Ko, Alex C.-T.; Wang, Fei; Xiang, Bo; Hewko, Mark; Tian, Ganghong; Major, Arkady; Shiomi, Masashi; Sowa, Michael G.

    2013-07-01

    In this study we present an image analysis methodology capable of quantifying morphological changes in tissue collagen fibril organization caused by pathological conditions. Texture analysis based on first-order statistics (FOS) and second-order statistics such as gray level co-occurrence matrix (GLCM) was explored to extract second-harmonic generation (SHG) image features that are associated with the structural and biochemical changes of tissue collagen networks. Based on these extracted quantitative parameters, multi-group classification of SHG images was performed. With combined FOS and GLCM texture values, we achieved reliable classification of SHG collagen images acquired from atherosclerosis arteries with >90% accuracy, sensitivity and specificity. The proposed methodology can be applied to a wide range of conditions involving collagen re-modeling, such as in skin disorders, different types of fibrosis and muscular-skeletal diseases affecting ligaments and cartilage.

  7. Multisensor classification of sedimentary rocks

    NASA Technical Reports Server (NTRS)

    Evans, Diane

    1988-01-01

    A comparison is made between linear discriminant analysis and supervised classification results based on signatures from the Landsat TM, the Thermal Infrared Multispectral Scanner (TIMS), and airborne SAR, alone and combined into extended spectral signatures for seven sedimentary rock units exposed on the margin of the Wind River Basin, Wyoming. Results from a linear discriminant analysis showed that training-area classification accuracies based on the multisensor data were improved an average of 15 percent over TM alone, 24 percent over TIMS alone, and 46 percent over SAR alone, with similar improvement resulting when supervised multisensor classification maps were compared to supervised, individual sensor classification maps. When training area signatures were used to map spectrally similar materials in an adjacent area, the average classification accuracy improved 19 percent using the multisensor data over TM alone, 2 percent over TIMS alone, and 11 percent over SAR alone. It is concluded that certain sedimentary lithologies may be accurately mapped using a single sensor, but classification of a variety of rock types can be improved using multisensor data sets that are sensitive to different characteristics such as mineralogy and surface roughness.

  8. EFFECTS OF LANDSCAPE CHARACTERISTICS ON LAND-COVER CLASS ACCURACY

    EPA Science Inventory



    Utilizing land-cover data gathered as part of the National Land-Cover Data (NLCD) set accuracy assessment, several logistic regression models were formulated to analyze the effects of patch size and land-cover heterogeneity on classification accuracy. Specific land-cover ...

  9. Assessment Of Accuracies Of Remote-Sensing Maps

    NASA Technical Reports Server (NTRS)

    Card, Don H.; Strong, Laurence L.

    1992-01-01

    Report describes study of accuracies of classifications of picture elements in map derived by digital processing of Landsat-multispectral-scanner imagery of coastal plain of Arctic National Wildlife Refuge. Accuracies of portions of map analyzed with help of statistical sampling procedure called "stratified plurality sampling", in which all picture elements in given cluster classified in stratum to which plurality of them belong.

  10. Student Metacognitive Monitoring: Predicting Test Achievement from Judgment Accuracy

    ERIC Educational Resources Information Center

    Valdez, Alfred

    2013-01-01

    Metacognitive monitoring processes have been shown to be critical determinants of human learning. Metacognitive monitoring consist of various knowledge estimates that enable learners to engage in self-regulatory processes important for both the acquisition of knowledge and the monitoring of one's knowledge when engaged in assessment. This study…

  11. A new adaptive GMRES algorithm for achieving high accuracy

    SciTech Connect

    Sosonkina, M.; Watson, L.T.; Kapania, R.K.; Walker, H.F.

    1996-12-31

    GMRES(k) is widely used for solving nonsymmetric linear systems. However, it is inadequate either when it converges only for k close to the problem size or when numerical error in the modified Gram-Schmidt process used in the GMRES orthogonalization phase dramatically affects the algorithm performance. An adaptive version of GMRES (k) which tunes the restart value k based on criteria estimating the GMRES convergence rate for the given problem is proposed here. The essence of the adaptive GMRES strategy is to adapt the parameter k to the problem, similar in spirit to how a variable order ODE algorithm tunes the order k. With FORTRAN 90, which provides pointers and dynamic memory management, dealing with the variable storage requirements implied by varying k is not too difficult. The parameter k can be both increased and decreased-an increase-only strategy is described next followed by pseudocode.

  12. Sleep stage classification with ECG and respiratory effort.

    PubMed

    Fonseca, Pedro; Long, Xi; Radha, Mustafa; Haakma, Reinder; Aarts, Ronald M; Rolink, Jérôme

    2015-10-01

    Automatic sleep stage classification with cardiorespiratory signals has attracted increasing attention. In contrast to the traditional manual scoring based on polysomnography, these signals can be measured using advanced unobtrusive techniques that are currently available, promising the application for personal and continuous home sleep monitoring. This paper describes a methodology for classifying wake, rapid-eye-movement (REM) sleep, and non-REM (NREM) light and deep sleep on a 30 s epoch basis. A total of 142 features were extracted from electrocardiogram and thoracic respiratory effort measured with respiratory inductance plethysmography. To improve the quality of these features, subject-specific Z-score normalization and spline smoothing were used to reduce between-subject and within-subject variability. A modified sequential forward selection feature selector procedure was applied, yielding 80 features while preventing the introduction of bias in the estimation of cross-validation performance. PSG data from 48 healthy adults were used to validate our methods. Using a linear discriminant classifier and a ten-fold cross-validation, we achieved a Cohen's kappa coefficient of 0.49 and an accuracy of 69% in the classification of wake, REM, light, and deep sleep. These values increased to kappa = 0.56 and accuracy = 80% when the classification problem was reduced to three classes, wake, REM sleep, and NREM sleep.

  13. Three-Class Mammogram Classification Based on Descriptive CNN Features

    PubMed Central

    Zhang, Qianni; Jadoon, Adeel

    2017-01-01

    In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques. PMID:28191461

  14. Better physical activity classification using smartphone acceleration sensor.

    PubMed

    Arif, Muhammad; Bilal, Mohsin; Kattan, Ahmed; Ahamed, S Iqbal

    2014-09-01

    Obesity is becoming one of the serious problems for the health of worldwide population. Social interactions on mobile phones and computers via internet through social e-networks are one of the major causes of lack of physical activities. For the health specialist, it is important to track the record of physical activities of the obese or overweight patients to supervise weight loss control. In this study, acceleration sensor present in the smartphone is used to monitor the physical activity of the user. Physical activities including Walking, Jogging, Sitting, Standing, Walking upstairs and Walking downstairs are classified. Time domain features are extracted from the acceleration data recorded by smartphone during different physical activities. Time and space complexity of the whole framework is done by optimal feature subset selection and pruning of instances. Classification results of six physical activities are reported in this paper. Using simple time domain features, 99 % classification accuracy is achieved. Furthermore, attributes subset selection is used to remove the redundant features and to minimize the time complexity of the algorithm. A subset of 30 features produced more than 98 % classification accuracy for the six physical activities.

  15. Energy-efficient context classification with dynamic sensor control.

    PubMed

    Au, Lawrence K; Bui, Alex A T; Batalin, Maxim A; Kaiser, William J

    2012-04-01

    Energy efficiency has been a longstanding design challenge for wearable sensor systems. It is especially crucial in continuous subject state monitoring due to the ongoing need for compact sizes and better sensors. This paper presents an energy-efficient classification algorithm, based on partially observable Markov decision process (POMDP). In every time step, POMDP dynamically selects sensors for classification via a sensor selection policy. The sensor selection problem is formalized as an optimization problem, where the objective is to minimize misclassification cost given some energy budget. State transitions are modeled as a hidden Markov model (HMM), and the corresponding sensor selection policy is represented using a finite-state controller (FSC). To evaluate this framework, sensor data were collected from multiple subjects in their free-living conditions. Relative accuracies and energy reductions from the proposed method are compared against naïve Bayes (always-on) and simple random strategies to validate the relative performance of the algorithm. When the objective is to maintain the same classification accuracy, significant energy reduction is achieved.

  16. Energy-Efficient Context Classification With Dynamic Sensor Control

    PubMed Central

    Au, Lawrence K.; Bui, Alex A. T.; Batalin, Maxim A.; Kaiser, William J.

    2016-01-01

    Energy efficiency has been a longstanding design challenge for wearable sensor systems. It is especially crucial in continuous subject state monitoring due to the ongoing need for compact sizes and better sensors. This paper presents an energy-efficient classification algorithm, based on partially observable Markov decision process (POMDP). In every time step, POMDP dynamically selects sensors for classification via a sensor selection policy. The sensor selection problem is formalized as an optimization problem, where the objective is to minimize misclassification cost given some energy budget. State transitions are modeled as a hidden Markov model (HMM), and the corresponding sensor selection policy is represented using a finite-state controller (FSC). To evaluate this framework, sensor data were collected from multiple subjects in their free-living conditions. Relative accuracies and energy reductions from the proposed method are compared against naïve Bayes (always-on) and simple random strategies to validate the relative performance of the algorithm. When the objective is to maintain the same classification accuracy, significant energy reduction is achieved. PMID:23852981

  17. Reduction of training costs using active classification in fused hyperspectral and LiDAR data

    NASA Astrophysics Data System (ADS)

    Wuttke, Sebastian; Schilling, Hendrik; Middelmann, Wolfgang

    2012-11-01

    This paper presents a novel approach for the reduction of training costs in classification with co-registered hyperspectral (HS) and Light Detection and Ranging (LiDAR) data using an active classification framework. Fully automatic classification can be achieved by unsupervised learning, which is not suited for adjustment to specific classes. On the other hand, supervised classification with predefined classes needs a lot of training examples, which need to be labeled with the ground truth, usually at a significant cost. The concept of active classification alleviates these problems by the use of a selection strategy: only selected samples are ground truth labeled and used as training data. One common selection strategy is to incorporate in a first step the current state of the classification algorithm and choose only the examples for which the expected information gain is maximized. In the second step a conventional classification algorithm is trained using this data. By alternating between these two steps the algorithm reaches high classification accuracy results with less training samples and therefore lower training costs. The approach presented in this paper involves the user in the active selection strategy and the k-NN algorithm is chosen for classification. The results further benefit from fusing the heterogeneous information of HS and LiDAR data within the classification algorithm. For this purpose, several HS features, such as vegetation indices, and LiDAR features, such as relative height and roughness, are extracted. This increases the separability between different classes and reduces the dimensionality of the HS data. The practicability and performance of this framework is shown for the detection and separation of different kinds of vegetation, e.g. trees and grass in an urban area of Berlin. The HS data was obtained by the SPECIM AISA Eagle 2 sensor, LiDAR data by Riegl LMS Q560.

  18. Comparison Between Spectral, Spatial and Polarimetric Classification of Urban and Periurban Landcover Using Temporal Sentinel - 1 Images

    NASA Astrophysics Data System (ADS)

    Roychowdhury, K.

    2016-06-01

    Landcover is the easiest detectable indicator of human interventions on land. Urban and peri-urban areas present a complex combination of landcover, which makes classification challenging. This paper assesses the different methods of classifying landcover using dual polarimetric Sentinel-1 data collected during monsoon (July) and winter (December) months of 2015. Four broad landcover classes such as built up areas, water bodies and wetlands, vegetation and open spaces of Kolkata and its surrounding regions were identified. Polarimetric analyses were conducted on Single Look Complex (SLC) data of the region while ground range detected (GRD) data were used for spectral and spatial classification. Unsupervised classification by means of K-Means clustering used backscatter values and was able to identify homogenous landcovers over the study area. The results produced an overall accuracy of less than 50% for both the seasons. Higher classification accuracy (around 70%) was achieved by adding texture variables as inputs along with the backscatter values. However, the accuracy of classification increased significantly with polarimetric analyses. The overall accuracy was around 80% in Wishart H-A-Alpha unsupervised classification. The method was useful in identifying urban areas due to their double-bounce scattering and vegetated areas, which have more random scattering. Normalized Difference Built-up index (NDBI) and Normalized Difference Vegetation Index (NDVI) obtained from Landsat 8 data over the study area were used to verify vegetation and urban classes. The study compares the accuracies of different methods of classifying landcover using medium resolution SAR data in a complex urban area and suggests that polarimetric analyses present the most accurate results for urban and suburban areas.

  19. Towards Arbitrary Accuracy Inviscid Surface Boundary Conditions

    NASA Technical Reports Server (NTRS)

    Dyson, Rodger W.; Hixon, Ray

    2002-01-01

    Inviscid nonlinear surface boundary conditions are currently limited to third order accuracy in time for non-moving surfaces and actually reduce to first order in time when the surfaces move. For steady-state calculations it may be possible to achieve higher accuracy in space, but high accuracy in time is required for efficient simulation of multiscale unsteady phenomena. A surprisingly simple technique is shown here that can be used to correct the normal pressure derivatives of the flow at a surface on a Cartesian grid so that arbitrarily high order time accuracy is achieved in idealized cases. This work demonstrates that nonlinear high order time accuracy at a solid surface is possible and desirable, but it also shows that the current practice of only correcting the pressure is inadequate.

  20. Multi-level discriminative dictionary learning with application to large scale image classification.

    PubMed

    Shen, Li; Sun, Gang; Huang, Qingming; Wang, Shuhui; Lin, Zhouchen; Wu, Enhua

    2015-10-01

    The sparse coding technique has shown flexibility and capability in image representation and analysis. It is a powerful tool in many visual applications. Some recent work has shown that incorporating the properties of task (such as discrimination for classification task) into dictionary learning is effective for improving the accuracy. However, the traditional supervised dictionary learning methods suffer from high computation complexity when dealing with large number of categories, making them less satisfactory in large scale applications. In this paper, we propose a novel multi-level discriminative dictionary learning method and apply it to large scale image classification. Our method takes advantage of hierarchical category correlation to encode multi-level discriminative information. Each internal node of the category hierarchy is associated with a discriminative dictionary and a classification model. The dictionaries at different layers are learnt to capture the information of different scales. Moreover, each node at lower layers also inherits the dictionary of its parent, so that the categories at lower layers can be described with multi-scale information. The learning of dictionaries and associated classification models is jointly conducted by minimizing an overall tree loss. The experimental results on challenging data sets demonstrate that our approach achieves excellent accuracy and competitive computation cost compared with other sparse coding methods for large scale image classification.

  1. Content-based medical image classification using a new hierarchical merging scheme.

    PubMed

    Pourghassem, Hossein; Ghassemian, Hassan

    2008-12-01

    Automatic medical image classification is a technique for assigning a medical image to a class among a number of image categories. Due to computational complexity, it is an important task in the content-based image retrieval (CBIR). In this paper, we propose a hierarchical medical image classification method including two levels using a perfect set of various shape and texture features. Furthermore, a tessellation-based spectral feature as well as a directional histogram has been proposed. In each level of the hierarchical classifier, using a new merging scheme and multilayer perceptron (MLP) classifiers (merging-based classification), homogenous (semantic) classes are created from overlapping classes in the database. The proposed merging scheme employs three measures to detect the overlapping classes: accuracy, miss-classified ratio, and dissimilarity. The first two measures realize a supervised classification method and the last one realizes an unsupervised clustering technique. In each level, the merging-based classification is applied to a merged class of the previous level and splits it to several classes. This procedure is progressive to achieve more classes. The proposed algorithm is evaluated on a database consisting of 9100 medical X-ray images of 40 classes. It provides accuracy rate of 90.83% on 25 merged classes in the first level. If the correct class is considered within the best three matches, this value will increase to 97.9%.

  2. ProFold: Protein Fold Classification with Additional Structural Features and a Novel Ensemble Classifier

    PubMed Central

    2016-01-01

    Protein fold classification plays an important role in both protein functional analysis and drug design. The number of proteins in PDB is very large, but only a very small part is categorized and stored in the SCOPe database. Therefore, it is necessary to develop an efficient method for protein fold classification. In recent years, a variety of classification methods have been used in many protein fold classification studies. In this study, we propose a novel classification method called proFold. We import protein tertiary structure in the period of feature extraction and employ a novel ensemble strategy in the period of classifier training. Compared with existing similar ensemble classifiers using the same widely used dataset (DD-dataset), proFold achieves 76.2% overall accuracy. Another two commonly used datasets, EDD-dataset and TG-dataset, are also tested, of which the accuracies are 93.2% and 94.3%, higher than the existing methods. ProFold is available to the public as a web-server. PMID:27660761

  3. Automatic apical view classification of echocardiograms using a discriminative learning dictionary.

    PubMed

    Khamis, Hanan; Zurakhov, Grigoriy; Azar, Vered; Raz, Adi; Friedman, Zvi; Adam, Dan

    2017-02-01

    As part of striving towards fully automatic cardiac functional assessment of echocardiograms, automatic classification of their standard views is essential as a pre-processing stage. The similarity among three of the routinely acquired longitudinal scans: apical two-chamber (A2C), apical four-chamber (A4C) and apical long-axis (ALX), and the noise commonly inherent to these scans - make the classification a challenge. Here we introduce a multi-stage classification algorithm that employs spatio-temporal feature extraction (Cuboid Detector) and supervised dictionary learning (LC-KSVD) approaches to uniquely enhance the automatic recognition and classification accuracy of echocardiograms. The algorithm incorporates both discrimination and labelling information to allow a discriminative and sparse representation of each view. The advantage of the spatio-temporal feature extraction as compared to spatial processing is then validated. A set of 309 clinical clips (103 for each view), were labeled by 2 experts. A subset of 70 clips of each class was used as a training set and the rest as a test set. The recognition accuracies achieved were: 97%, 91% and 97% of A2C, A4C and ALX respectively, with average recognition rate of 95%. Thus, automatic classification of echocardiogram views seems promising, despite the inter-view similarity between the classes and intra-view variability among clips belonging to the same class.

  4. Classification of remote sensed images using random forests and deep learning framework

    NASA Astrophysics Data System (ADS)

    Piramanayagam, S.; Schwartzkopf, W.; Koehler, F. W.; Saber, E.

    2016-10-01

    In this paper, we explore the use of two machine learning algorithms: (a) random forest for structured labels and (b) fully convolutional neural network for the land cover classification of multi-sensor remote sensed images. In random forest algorithm, individual decision trees are trained on features obtained from image patches and corresponding patch labels. Structural information present in the image patches improves the classification performance when compared to just utilizing pixel features. Random forest method was trained and evaluated on the ISPRS Vaihingen dataset that consist of true ortho photo (TOP: near IR, R, G) and Digital Surface Model (DSM) data. The method achieves an overall accuracy of 86.3% on the test dataset. We also show qualitative results on a SAR image. In addition, we employ a fully convolutional neural network framework (FCN) to do pixel-wise classification of the above multi-sensor image. TOP and DSM data have individual convolutional layers with features fused before the fully convolutional layers. The network when evaluated on the Vaihingen dataset achieves an overall classification accuracy of 88%.

  5. Automatic classification of infant sleep based on instantaneous frequencies in a single-channel EEG signal.

    PubMed

    Čić, Maja; Šoda, Joško; Bonković, Mirjana

    2013-12-01

    This study presents a novel approach for the electroencephalogram (EEG) signal quantification in which the empirical mode decomposition method, a time-frequency method designated for nonlinear and non-stationary signals, decomposes the EEG signal into intrinsic mode functions (IMF) with corresponding frequency ranges that characterize the appropriate oscillatory modes embedded in the brain neural activity acquired using EEG. To calculate the instantaneous frequency of IMFs, an algorithm was developed using the Generalized Zero Crossing method. From the resulting frequencies, two different novel features were generated: the median instantaneous frequencies and the number of instantaneous frequency changes during a 30s segment for seven IMFs. The sleep stage classification for the daytime sleep of 20 healthy babies was determined using the Support Vector Machine classification algorithm. The results were evaluated using the cross-validation method to achieve an approximately 90% accuracy and with new examinee data to achieve 80% average accuracy of classification. The obtained results were higher than the human experts' agreement and were statistically significant, which positioned the method, based on the proposed features, as an efficient procedure for automatic sleep stage classification. The uniqueness of this study arises from newly proposed features of the time-frequency domain, which bind characteristics of the sleep signals to the oscillation modes of brain activity, reflecting the physical characteristics of sleep, and thus have the potential to highlight the congruency of twin pairs with potential implications for the genetic determination of sleep.

  6. Progressive Graph-Based Transductive Learning for Multi-modal Classification of Brain Disorder Disease

    PubMed Central

    Wang, Zhengxia; Zhu, Xiaofeng; Adeli, Ehsan; Zhu, Yingying; Zu, Chen; Nie, Feiping; Shen, Dinggang; Wu, Guorong

    2017-01-01

    Graph-based Transductive Learning (GTL) is a powerful tool in computer-assisted diagnosis, especially when the training data is not sufficient to build reliable classifiers. Conventional GTL approaches first construct a fixed subject-wise graph based on the similarities of observed features (i.e., extracted from imaging data) in the feature domain, and then follow the established graph to propagate the existing labels from training to testing data in the label domain. However, such a graph is exclusively learned in the feature domain and may not be necessarily optimal in the label domain. This may eventually undermine the classification accuracy. To address this issue, we propose a progressive GTL (pGTL) method to progressively find an intrinsic data representation. To achieve this, our pGTL method iteratively (1) refines the subject-wise relationships observed in the feature domain using the learned intrinsic data representation in the label domain, (2) updates the intrinsic data representation from the refined subject-wise relationships, and (3) verifies the intrinsic data representation on the training data, in order to guarantee an optimal classification on the new testing data. Furthermore, we extend our pGTL to incorporate multi-modal imaging data, to improve the classification accuracy and robustness as multi-modal imaging data can provide complementary information. Promising classification results in identifying Alzheimer’s disease (AD), Mild Cognitive Impairment (MCI), and Normal Control (NC) subjects are achieved using MRI and PET data.

  7. Classification based on pruning and double covered rule sets for the internet of things applications.

    PubMed

    Li, Shasha; Zhou, Zhongmei; Wang, Weiping

    2014-01-01

    The Internet of things (IOT) is a hot issue in recent years. It accumulates large amounts of data by IOT users, which is a great challenge to mining useful knowledge from IOT. Classification is an effective strategy which can predict the need of users in IOT. However, many traditional rule-based classifiers cannot guarantee that all instances can be covered by at least two classification rules. Thus, these algorithms cannot achieve high accuracy in some datasets. In this paper, we propose a new rule-based classification, CDCR-P (Classification based on the Pruning and Double Covered Rule sets). CDCR-P can induce two different rule sets A and B. Every instance in training set can be covered by at least one rule not only in rule set A, but also in rule set B. In order to improve the quality of rule set B, we take measure to prune the length of rules in rule set B. Our experimental results indicate that, CDCR-P not only is feasible, but also it can achieve high accuracy.

  8. Subspace ensembles for classification

    NASA Astrophysics Data System (ADS)

    Sun, Shiliang; Zhang, Changshui

    2007-11-01

    Ensemble learning constitutes one of the principal current directions in machine learning and data mining. In this paper, we explore subspace ensembles for classification by manipulating different feature subspaces. Commencing with the nature of ensemble efficacy, we probe into the microcosmic meaning of ensemble diversity, and propose to use region partitioning and region weighting to implement effective subspace ensembles. Individual classifiers possessing eminent performance on a partitioned region reflected by high neighborhood accuracies are deemed to contribute largely to this region, and are assigned large weights in determining the labels of instances in this area. A robust algorithm “Sena” that incarnates the mechanism is presented, which is insensitive to the number of nearest neighbors chosen to calculate neighborhood accuracies. The algorithm exhibits improved performance over the well-known ensembles of bagging, AdaBoost and random subspace. The difference of its effectivity with varying base classifiers is also investigated.

  9. Vietnamese Document Representation and Classification

    NASA Astrophysics Data System (ADS)

    Nguyen, Giang-Son; Gao, Xiaoying; Andreae, Peter

    Vietnamese is very different from English and little research has been done on Vietnamese document classification, or indeed, on any kind of Vietnamese language processing, and only a few small corpora are available for research. We created a large Vietnamese text corpus with about 18000 documents, and manually classified them based on different criteria such as topics and styles, giving several classification tasks of different difficulty levels. This paper introduces a new syllable-based document representation at the morphological level of the language for efficient classification. We tested the representation on our corpus with different classification tasks using six classification algorithms and two feature selection techniques. Our experiments show that the new representation is effective for Vietnamese categorization, and suggest that best performance can be achieved using syllable-pair document representation, an SVM with a polynomial kernel as the learning algorithm, and using Information gain and an external dictionary for feature selection.

  10. Efficient Fingercode Classification

    NASA Astrophysics Data System (ADS)

    Sun, Hong-Wei; Law, Kwok-Yan; Gollmann, Dieter; Chung, Siu-Leung; Li, Jian-Bin; Sun, Jia-Guang

    In this paper, we present an efficient fingerprint classification algorithm which is an essential component in many critical security application systems e. g. systems in the e-government and e-finance domains. Fingerprint identification is one of the most important security requirements in homeland security systems such as personnel screening and anti-money laundering. The problem of fingerprint identification involves searching (matching) the fingerprint of a person against each of the fingerprints of all registered persons. To enhance performance and reliability, a common approach is to reduce the search space by firstly classifying the fingerprints and then performing the search in the respective class. Jain et al. proposed a fingerprint classification algorithm based on a two-stage classifier, which uses a K-nearest neighbor classifier in its first stage. The fingerprint classification algorithm is based on the fingercode representation which is an encoding of fingerprints that has been demonstrated to be an effective fingerprint biometric scheme because of its ability to capture both local and global details in a fingerprint image. We enhance this approach by improving the efficiency of the K-nearest neighbor classifier for fingercode-based fingerprint classification. Our research firstly investigates the various fast search algorithms in vector quantization (VQ) and the potential application in fingerprint classification, and then proposes two efficient algorithms based on the pyramid-based search algorithms in VQ. Experimental results on DB1 of FVC 2004 demonstrate that our algorithms can outperform the full search algorithm and the original pyramid-based search algorithms in terms of computational efficiency without sacrificing accuracy.

  11. Automatic music genres classification as a pattern recognition problem

    NASA Astrophysics Data System (ADS)

    Ul Haq, Ihtisham; Khan, Fauzia; Sharif, Sana; Shaukat, Arsalan

    2013-12-01

    Music genres are the simplest and effect descriptors for searching music libraries stores or catalogues. The paper compares the results of two automatic music genres classification systems implemented by using two different yet simple classifiers (K-Nearest Neighbor and Naïve Bayes). First a 10-12 second sample is selected and features are extracted from it, and then based on those features results of both classifiers are represented in the form of accuracy table and confusion matrix. An experiment carried out on test 60 taken from middle of a song represents the true essence of its genre as compared to the samples taken from beginning and ending of a song. The novel techniques have achieved an accuracy of 91% and 78% by using Naïve Bayes and KNN classifiers respectively.

  12. Classification of protein crystallization imagery.

    PubMed

    Zhu, Xiaoqing; Sun, Shaohua; Bern, Marshall

    2004-01-01

    We investigate automatic classification of protein crystallization imagery, and evaluate the performance of several modern mathematical tools when applied to the problem. For feature extraction, we try a combination of geometric and texture features; for classification algorithms, the support vector machine (SVM) is compared with an automatic decision-tree classifier. Experimental results from 520 images are presented for the binary classification problem: separating successful trials from failed attempts. The best false positive and false negative rates are at 14.6% and 9.6% respectively, achieved by feeding both sets of features to the decision-tree classifier with boosting.

  13. On-board multispectral classification study

    NASA Technical Reports Server (NTRS)

    Ewalt, D.

    1979-01-01

    The factors relating to onboard multispectral classification were investigated. The functions implemented in ground-based processing systems for current Earth observation sensors were reviewed. The Multispectral Scanner, Thematic Mapper, Return Beam Vidicon, and Heat Capacity Mapper were studied. The concept of classification was reviewed and extended from the ground-based image processing functions to an onboard system capable of multispectral classification. Eight different onboard configurations, each with varying amounts of ground-spacecraft interaction, were evaluated. Each configuration was evaluated in terms of turnaround time, onboard processing and storage requirements, geometric and classification accuracy, onboard complexity, and ancillary data required from the ground.

  14. Algorithms for Hyperspectral Signature Classification in Non-resolved Object Characterization Using Tabular Nearest Neighbor Encoding

    NASA Astrophysics Data System (ADS)

    Schmalz, M.; Key, G.

    Accurate spectral signature classification is key to the nonimaging detection and recognition of spaceborne objects. In classical hyperspectral recognition applications, signature classification accuracy depends on accurate spectral endmember determination [1]. However, in selected target recognition (ATR) applications, it is possible to circumvent the endmember detection problem by employing a Bayesian classifier. Previous approaches to Bayesian classification of spectral signatures have been rule- based, or predicated on a priori parameterized information obtained from offline training, as in the case of neural networks [1,2]. Unfortunately, class separation and classifier refinement results in these methods tends to be suboptimal, and the number of signatures that can be accurately classified often depends linearly on the number of inputs. This can lead to potentially significant classification errors in the presence of noise or densely interleaved signatures. In this paper, we present an emerging technology for nonimaging spectral signature classfication based on a highly accurate but computationally efficient search engine called Tabular Nearest Neighbor Encoding (TNE) [3]. Based on prior results, TNE can optimize its classifier performance to track input nonergodicities, as well as yield measures of confidence or caution for evaluation of classification results. Unlike neural networks, TNE does not have a hidden intermediate data structure (e.g., the neural net weight matrix). Instead, TNE generates and exploits a user-accessible data structure called the agreement map (AM), which can be manipulated by Boolean logic operations to effect accurate classifier refinement algorithms. This allows the TNE programmer or user to determine parameters for classification accuracy, and to mathematically analyze the signatures for which TNE did not obtain classification matches. This dual approach to analysis (i.e., correct vs. incorrect classification) has been shown to

  15. Response conflict processes' classification in 7 and 9 year old children using EEG brain connectivity measures.

    PubMed

    Almabruk, T; Iyer, K; Girdler, S; Khan, M M; Tan, T

    2016-08-01

    Investigating cognitive development of children poses interesting challenges pertaining to emergence of children's' ability to think and understand. Psychological tasks that involve conflict, like the Flanker task, are widely used to understand development of response conflict processes. In this study, EEG signals were used to examine the coherence and imaginary part of coherency within the delta, theta, alpha and beta bands across different conditions of the Flanker task. Longitudinal data were collected from a group of typically developing children at ages of seven and nine. We found that the imaginary part of coherency was more helpful in distinguishing between stimuli - alpha and beta bands resulted in 90.90% classification rate in seven year old children. The beta and theta bands were found to be more effective for stimuli classification in nine year old children - more than 84.09% classification accuracy was achieved.

  16. Fuzzy-logic-based hybrid locomotion mode classification for an active pelvis orthosis: Preliminary results.

    PubMed

    Yuan, Kebin; Parri, Andrea; Yan, Tingfang; Wang, Long; Munih, Marko; Vitiello, Nicola; Wang, Qining

    2015-01-01

    In this paper, we present a fuzzy-logic-based hybrid locomotion mode classification method for an active pelvis orthosis. Locomotion information measured by the onboard hip joint angle sensors and the pressure insoles is used to classify five locomotion modes, including two static modes (sitting, standing still), and three dynamic modes (level-ground walking, ascending stairs, and descending stairs). The proposed method classifies these two kinds of modes first by monitoring the variation of the relative hip joint angle between the two legs within a specific period. Static states are then classified by the time-based absolute hip joint angle. As for dynamic modes, a fuzzy-logic based method is proposed for the classification. Preliminary experimental results with three able-bodied subjects achieve an off-line classification accuracy higher than 99.49%.

  17. Development of classification models to detect Salmonella Enteritidis and Salmonella Typhimurium found in poultry carcass rinses by visible-near infrared hyperspectral imaging

    NASA Astrophysics Data System (ADS)

    Seo, Young Wook; Yoon, Seung Chul; Park, Bosoon; Hinton, Arthur; Windham, William R.; Lawrence, Kurt C.

    2013-05-01

    accuracy of all 10 models on a validation set of chicken carcass rinses spiked with SE or ST and incubated on BGS agar plates was 94.45% and 83.73%, without and with PCA for classification, respectively. The best performing classification model on the validation set was QDA without PCA by achieving the classification accuracy of 98.65% (Kappa coefficient=0.98). The overall best performing classification model regardless of using PCA was MD with the classification accuracy of 94.84% (Kappa coefficient=0.88) on the validation set.

  18. A Novel Approach to Probabilistic Biomarker-Based Classification Using Functional Near-Infrared Spectroscopy

    PubMed Central

    Hahn, Tim; Marquand, Andre F; Plichta, Michael M; Ehlis, Ann-Christine; Schecklmann, Martin W; Dresler, Thomas; Jarczok, Tomasz A; Eirich, Elisa; Leonhard, Christine; Reif, Andreas; Lesch, Klaus-Peter; Brammer, Michael J; Mourao-Miranda, Janaina; Fallgatter, Andreas J

    2013-01-01

    Pattern recognition approaches to the analysis of neuroimaging data have brought new applications such as the classification of patients and healthy controls within reach. In our view, the reliance on expensive neuroimaging techniques which are not well tolerated by many patient groups and the inability of most current biomarker algorithms to accommodate information about prior class frequencies (such as a disorder's prevalence in the general population) are key factors limiting practical application. To overcome both limitations, we propose a probabilistic pattern recognition approach based on cheap and easy-to-use multi-channel near-infrared spectroscopy (fNIRS) measurements. We show the validity of our method by applying it to data from healthy controls (n = 14) enabling differentiation between the conditions of a visual checkerboard task. Second, we show that high-accuracy single subject classification of patients with schizophrenia (n = 40) and healthy controls (n = 40) is possible based on temporal patterns of fNIRS data measured during a working memory task. For classification, we integrate spatial and temporal information at each channel to estimate overall classification accuracy. This yields an overall accuracy of 76% which is comparable to the highest ever achieved in biomarker-based classification of patients with schizophrenia. In summary, the proposed algorithm in combination with fNIRS measurements enables the analysis of sub-second, multivariate temporal patterns of BOLD responses and high-accuracy predictions based on low-cost, easy-to-use fNIRS patterns. In addition, our approach can easily compensate for variable class priors, which is highly advantageous in making predictions in a wide range of clinical neuroimaging applications. Hum Brain Mapp, 2013. © 2012 Wiley Periodicals, Inc. PMID:22965654

  19. Classification Analysis.

    ERIC Educational Resources Information Center

    Ball, Geoffrey H.

    Sorting things into groups is a basic intellectual task that allows people to simplify with minimal reduction in information. Classification techniques, which include both clustering and discrimination, provide step-by-step computer-based procedures for sorting things based on notions of generalized similarity and on the "class description"…

  20. Large margin distribution machine for hyperspectral image classification

    NASA Astrophysics Data System (ADS)

    Zhan, Kun; Wang, Haibo; Huang, He; Xie, Yuange

    2016-11-01

    Support vector machine (SVM) classifiers are widely applied to hyperspectral image (HSI) classification and provide significant advantages in terms of accuracy, simplicity, and robustness. SVM is a well-known learning algorithm that maximizes the minimum margin. However, recent theoretical results pointed out that maximizing the minimum margin leads to a lower generalization performance than optimizing the margin distribution, and proved that the margin distribution is more important. In this paper, a large margin distribution machine (LDM) is applied to HSI classification, and optimizing the margin distribution achieves a better generalization performance than SVM. Since the raw HSI feature space is not the most effective space for representing HSI, we adopt factor analysis to learn an effective HSI feature and the learned features are further filtered by a structure-preserved filter to fully exploit the spatial structure information of HSI. The spatial structure information is integrated in the feature learning process to obtain a better HSI feature. Then we propose a multiclass LDM to classify the filtered HSI feature. Experimental results show that the proposed LDM with feature learning method achieves the classification performance of the state-of-the-art methods in terms of visual quality and three quantitative evaluations and indicates that LDM has a high generalization performance.

  1. Measuring Diagnoses: ICD Code Accuracy

    PubMed Central

    O'Malley, Kimberly J; Cook, Karon F; Price, Matt D; Wildes, Kimberly Raiford; Hurdle, John F; Ashton, Carol M

    2005-01-01

    Objective To examine potential sources of errors at each step of the described inpatient International Classification of Diseases (ICD) coding process. Data Sources/Study Setting The use of disease codes from the ICD has expanded from classifying morbidity and mortality information for statistical purposes to diverse sets of applications in research, health care policy, and health care finance. By describing a brief history of ICD coding, detailing the process for assigning codes, identifying where errors can be introduced into the process, and reviewing methods for examining code accuracy, we help code users more systematically evaluate code accuracy for their particular applications. Study Design/Methods We summarize the inpatient ICD diagnostic coding process from patient admission to diagnostic code assignment. We examine potential sources of errors at each step and offer code users a tool for systematically evaluating code accuracy. Principle Findings Main error sources along the “patient trajectory” include amount and quality of information at admission, communication among patients and providers, the clinician's knowledge and experience with the illness, and the clinician's attention to detail. Main error sources along the “paper trail” include variance in the electronic and written records, coder training and experience, facility quality-control efforts, and unintentional and intentional coder errors, such as misspecification, unbundling, and upcoding. Conclusions By clearly specifying the code assignment process and heightening their awareness of potential error sources, code users can better evaluate the applicability and limitations of codes for their particular situations. ICD codes can then be used in the most appropriate ways. PMID:16178999

  2. Micro-Doppler Based Classification of Human Aquatic Activities via Transfer Learning of Convolutional Neural Networks.

    PubMed

    Park, Jinhee; Javier, Rios Jesus; Moon, Taesup; Kim, Youngwook

    2016-11-24

    Accurate classification of human aquatic activities using radar has a variety of potential applications such as rescue operations and border patrols. Nevertheless, the classification of activities on water using radar has not been extensively studied, unlike the case on dry ground, due to its unique challenge. Namely, not only is the radar cross section of a human on water small, but the micro-Doppler signatures are much noisier due to water drops and waves. In this paper, we first investigate whether discriminative signatures could be obtained for activities on water through a simulation study. Then, we show how we can effectively achieve high classification accuracy by applying deep convolutional neural networks (DCNN) directly to the spectrogram of real measurement data. From the five-fold cross-validation on our dataset, which consists of five aquatic activities, we report that the conventional feature-based scheme only achieves an accuracy of 45.1%. In contrast, the DCNN trained using only the collected data attains 66.7%, and the transfer learned DCNN, which takes a DCNN pre-trained on a RGB image dataset and fine-tunes the parameters using the collected data, achieves a much higher 80.3%, which is a significant performance boost.

  3. Micro-Doppler Based Classification of Human Aquatic Activities via Transfer Learning of Convolutional Neural Networks

    PubMed Central

    Park, Jinhee; Javier, Rios Jesus; Moon, Taesup; Kim, Youngwook

    2016-01-01

    Accurate classification of human aquatic activities using radar has a variety of potential applications such as rescue operations and border patrols. Nevertheless, the classification of activities on water using radar has not been extensively studied, unlike the case on dry ground, due to its unique challenge. Namely, not only is the radar cross section of a human on water small, but the micro-Doppler signatures are much noisier due to water drops and waves. In this paper, we first investigate whether discriminative signatures could be obtained for activities on water through a simulation study. Then, we show how we can effectively achieve high classification accuracy by applying deep convolutional neural networks (DCNN) directly to the spectrogram of real measurement data. From the five-fold cross-validation on our dataset, which consists of five aquatic activities, we report that the conventional feature-based scheme only achieves an accuracy of 45.1%. In contrast, the DCNN trained using only the collected data attains 66.7%, and the transfer learned DCNN, which takes a DCNN pre-trained on a RGB image dataset and fine-tunes the parameters using the collected data, achieves a much higher 80.3%, which is a significant performance boost. PMID:27886151

  4. Generalized and Heuristic-Free Feature Construction for Improved Accuracy

    PubMed Central

    Fan, Wei; Zhong, Erheng; Peng, Jing; Verscheure, Olivier; Zhang, Kun; Ren, Jiangtao; Yan, Rong; Yang, Qiang

    2010-01-01

    State-of-the-art learning algorithms accept data in feature vector format as input. Examples belonging to different classes may not always be easy to separate in the original feature space. One may ask: can transformation of existing features into new space reveal significant discriminative information not obvious in the original space? Since there can be infinite number of ways to extend features, it is impractical to first enumerate and then perform feature selection. Second, evaluation of discriminative power on the complete dataset is not always optimal. This is because features highly discriminative on subset of examples may not necessarily be significant when evaluated on the entire dataset. Third, feature construction ought to be automated and general, such that, it doesn't require domain knowledge and its improved accuracy maintains over a large number of classification algorithms. In this paper, we propose a framework to address these problems through the following steps: (1) divide-conquer to avoid exhaustive enumeration; (2) local feature construction and evaluation within subspaces of examples where local error is still high and constructed features thus far still do not predict well; (3) weighting rules based search that is domain knowledge free and has provable performance guarantee. Empirical studies indicate that significant improvement (as much as 9% in accuracy and 28% in AUC) is achieved using the newly constructed features over a variety of inductive learners evaluated against a number of balanced, skewed and high-dimensional datasets. Software and datasets are available from the authors. PMID:21544257

  5. Empirical comparison of color normalization methods for epithelial-stromal classification in H and E images

    PubMed Central

    Sethi, Amit; Sha, Lingdao; Vahadane, Abhishek Ramnath; Deaton, Ryan J.; Kumar, Neeraj; Macias, Virgilia; Gann, Peter H.

    2016-01-01

    Context: Color normalization techniques for histology have not been empirically tested for their utility for computational pathology pipelines. Aims: We compared two contemporary techniques for achieving a common intermediate goal – epithelial-stromal classification. Settings and Design: Expert-annotated regions of epithelium and stroma were treated as ground truth for comparing classifiers on original and color-normalized images. Materials and Methods: Epithelial and stromal regions were annotated on thirty diverse-appearing H and E stained prostate cancer tissue microarray cores. Corresponding sets of thirty images each were generated using the two color normalization techniques. Color metrics were compared for original and color-normalized images. Separate epithelial-stromal classifiers were trained and compared on test images. Main analyses were conducted using a multiresolution segmentation (MRS) approach; comparative analyses using two other classification approaches (convolutional neural network [CNN], Wndchrm) were also performed. Statistical Analysis: For the main MRS method, which relied on classification of super-pixels, the number of variables used was reduced using backward elimination without compromising accuracy, and test - area under the curves (AUCs) were compared for original and normalized images. For CNN and Wndchrm, pixel classification test-AUCs were compared. Results: Khan method reduced color saturation while Vahadane reduced hue variance. Super-pixel-level test-AUC for MRS was 0.010–0.025 (95% confidence interval limits ± 0.004) higher for the two normalized image sets compared to the original in the 10–80 variable range. Improvement in pixel classification accuracy was also observed for CNN and Wndchrm for color-normalized images. Conclusions: Color normalization can give a small incremental benefit when a super-pixel-based classification method is used with features that perform implicit color normalization while the gain is

  6. Enhancements in localized classification for uterine cervical cancer digital histology image assessment

    PubMed Central

    Guo, Peng; Almubarak, Haidar; Banerjee, Koyel; Stanley, R. Joe; Long, Rodney; Antani, Sameer; Thoma, George; Zuna, Rosemary; Frazier, Shelliane R.; Moss, Randy H.; Stoecker, William V.

    2016-01-01

    Background: In previous research, we introduced an automated, localized, fusion-based approach for classifying uterine cervix squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN) based on digitized histology image analysis. As part of the CIN assessment process, acellular and atypical cell concentration features were computed from vertical segment partitions of the epithelium region to quantize the relative distribution of nuclei. Methods: Feature data was extracted from 610 individual segments from 61 images for epithelium classification into categories of Normal, CIN1, CIN2, and CIN3. The classification results were compared against CIN labels obtained from two pathologists who visually assessed abnormality in the digitized histology images. In this study, individual vertical segment CIN classification accuracy improvement is reported using the logistic regression classifier for an expanded data set of 118 histology images. Results: We analyzed the effects on classification using the same pathologist labels for training and testing versus using one pathologist labels for training and the other for testing. Based on a leave-one-out approach for classifier training and testing, exact grade CIN accuracies of 81.29% and 88.98% were achieved for individual vertical segment and epithelium whole-image classification, respectively. Conclusions: The Logistic and Random Tree classifiers outperformed the benchmark SVM and LDA classifiers from previous research. The Logistic Regression classifier yielded an improvement of 10.17% in CIN Exact grade classification results based on CIN labels for training-testing for the individual vertical segments and the whole image from the same single expert over the baseline approach using the reduced features. Overall, the CIN classification rates tended to be higher using the training-testing labels for the same expert than for training labels from one expert and testing labels from

  7. A multiple-point spatially weighted k-NN method for object-based classification

    NASA Astrophysics Data System (ADS)

    Tang, Yunwei; Jing, Linhai; Li, Hui; Atkinson, Peter M.

    2016-10-01

    Object-based classification, commonly referred to as object-based image analysis (OBIA), is now commonly regarded as able to produce more appealing classification maps, often of greater accuracy, than pixel-based classification and its application is now widespread. Therefore, improvement of OBIA using spatial techniques is of great interest. In this paper, multiple-point statistics (MPS) is proposed for object-based classification enhancement in the form of a new multiple-point k-nearest neighbour (k-NN) classification method (MPk-NN). The proposed method first utilises a training image derived from a pre-classified map to characterise the spatial correlation between multiple points of land cover classes. The MPS borrows spatial structures from other parts of the training image, and then incorporates this spatial information, in the form of multiple-point probabilities, into the k-NN classifier. Two satellite sensor images with a fine spatial resolution were selected to evaluate the new method. One is an IKONOS image of the Beijing urban area and the other is a WorldView-2 image of the Wolong mountainous area, in China. The images were object-based classified using the MPk-NN method and several alternatives, including the k-NN, the geostatistically weighted k-NN, the Bayesian method, the decision tree classifier (DTC), and the support vector machine classifier (SVM). It was demonstrated that the new spatial weighting based on MPS can achieve greater classification accuracy relative to the alternatives and it is, thus, recommended as appropriate for object-based classification.

  8. Class Extraction and Classification Accuracy in Latent Class Models

    ERIC Educational Resources Information Center

    Wu, Qiong

    2009-01-01

    Despite the increasing popularity of latent class models (LCM) in educational research, methodological studies have not yet accumulated much information on the appropriate application of this modeling technique, especially with regard to requirement on sample size and number of indicators. This dissertation study represented an initial attempt to…

  9. Exploration of Force Myography and surface Electromyography in hand gesture classification.

    PubMed

    Jiang, Xianta; Merhi, Lukas-Karim; Xiao, Zhen Gang; Menon, Carlo

    2017-03-01

    Whereas pressure sensors increasingly have received attention as a non-invasive interface for hand gesture recognition, their performance has not been comprehensively evaluated. This work examined the performance of hand gesture classification using Force Myography (FMG) and surface Electromyography (sEMG) technologies by performing 3 sets of 48 hand gestures using a prototyped FMG band and an array of commercial sEMG sensors worn both on the wrist and forearm simultaneously. The results show that the FMG band achieved classification accuracies as good as the high quality, commercially available, sEMG system on both wrist and forearm positions; specifically, by only using 8 Force Sensitive Resisters (FSRs), the FMG band achieved accuracies of 91.2% and 83.5% in classifying the 48 hand gestures in cross-validation and cross-trial evaluations, which were higher than those of sEMG (84.6% and 79.1%). By using all 16 FSRs on the band, our device achieved high accuracies of 96.7% and 89.4% in cross-validation and cross-trial evaluations.

  10. Accurate and interpretable classification of microspectroscopy pixels using artificial neural networks.

    PubMed

    Manescu, Petru; Jong Lee, Young; Camp, Charles; Cicerone, Marcus; Brady, Mary; Bajcsy, Peter

    2017-04-01

    This paper addresses the problem of classifying materials from microspectroscopy at a pixel level. The challenges lie in identifying discriminatory spectral features and obtaining accurate and interpretable models relating spectra and class labels. We approach the problem by designing a supervised classifier from a tandem of Artificial Neural Network (ANN) models that identify relevant features in raw spectra and achieve high classification accuracy. The tandem of ANN models is meshed with classification rule extraction methods to lower the model complexity and to achieve interpretability of the resulting model. The contribution of the work is in designing each ANN model based on the microspectroscopy hypothesis about a discriminatory feature of a certain target class being composed of a linear combination of spectra. The novelty lies in meshing ANN and decision rule models into a tandem configuration to achieve accurate and interpretable classification results. The proposed method was evaluated using a set of broadband coherent anti-Stokes Raman scattering (BCARS) microscopy cell images (600 000  pixel-level spectra) and a reference four-class rule-based model previously created by biochemical experts. The generated classification rule-based model was on average 85% accurate measured by the DICE pixel label similarity metric, and on average 96% similar to the reference rules measured by the vector cosine metric.

  11. Automatic lung nodule classification with radiomics approach

    NASA Astrophysics Data System (ADS)

    Ma, Jingchen; Wang, Qian; Ren, Yacheng; Hu, Haibo; Zhao, Jun

    2016-03-01

    Lung cancer is the first killer among the cancer deaths. Malignant lung nodules have extremely high mortality while some of the benign nodules don't need any treatment .Thus, the accuracy of diagnosis between benign or malignant nodules diagnosis is necessary. Notably, although currently additional invasive biopsy or second CT scan in 3 months later may help radiologists to make judgments, easier diagnosis approaches are imminently needed. In this paper, we propose a novel CAD method to distinguish the benign and malignant lung cancer from CT images directly, which can not only improve the efficiency of rumor diagnosis but also greatly decrease the pain and risk of patients in biopsy collecting process. Briefly, according to the state-of-the-art radiomics approach, 583 features were used at the first step for measurement of nodules' intensity, shape, heterogeneity and information in multi-frequencies. Further, with Random Forest method, we distinguish the benign nodules from malignant nodules by analyzing all these features. Notably, our proposed scheme was tested on all 79 CT scans with diagnosis data available in The Cancer Imaging Archive (TCIA) which contain 127 nodules and each nodule is annotated by at least one of four radiologists participating in the project. Satisfactorily, this method achieved 82.7% accuracy in classification of malignant primary lung nodules and benign nodules. We believe it would bring much value for routine lung cancer diagnosis in CT imaging and provide improvement in decision-support with much lower cost.

  12. Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands.

    PubMed

    Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

    2016-01-01

    Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.

  13. Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

    PubMed Central

    Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

    2016-01-01

    Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too. PMID:27656140

  14. GEOSPATIAL DATA ACCURACY ASSESSMENT

    EPA Science Inventory

    The development of robust accuracy assessment methods for the validation of spatial data represent's a difficult scientific challenge for the geospatial science community. The importance and timeliness of this issue is related directly to the dramatic escalation in the developmen...

  15. Multiple Sparse Representations Classification

    PubMed Central

    Plenge, Esben; Klein, Stefan S.; Niessen, Wiro J.; Meijering, Erik

    2015-01-01

    Sparse representations classification (SRC) is a powerful technique for pixelwise classification of images and it is increasingly being used for a wide variety of image analysis tasks. The method uses sparse representation and learned redundant dictionaries to classify image pixels. In this empirical study we propose to further leverage the redundancy of the learned dictionaries to achieve a more accurate classifier. In conventional SRC, each image pixel is associated with a small patch surrounding it. Using these patches, a dictionary is trained for each class in a supervised fashion. Commonly, redundant/overcomplete dictionaries are trained and image patches are sparsely represented by a linear combination of only a few of the dictionary elements. Given a set of trained dictionaries, a new patch is sparse coded using each of them, and subsequently assigned to the class whose dictionary yields the minimum residual energy. We propose a generalization of this scheme. The method, which we call multiple sparse representations classification (mSRC), is based on the observation that an overcomplete, class specific dictionary is capable of generating multiple accurate and independent estimates of a patch belonging to the class. So instead of finding a single sparse representation of a patch for each dictionary, we find multiple, and the corresponding residual energies provides an enhanced statistic which is used to improve classification. We demonstrate the efficacy of mSRC for three example applications: pixelwise classification of texture images, lumen segmentation in carotid artery magnetic resonance imaging (MRI), and bifurcation point detection in carotid artery MRI. We compare our method with conventional SRC, K-nearest neighbor, and support vector machine classifiers. The results show that mSRC outperforms SRC and the other reference methods. In addition, we present an extensive evaluation of the effect of the main mSRC parameters: patch size, dictionary size, and

  16. Predictive Discriminant Analysis Versus Logistic Regression in Two-Group Classification Problems.

    ERIC Educational Resources Information Center

    Meshbane, Alice; Morris, John D.

    A method for comparing the cross-validated classification accuracies of predictive discriminant analysis and logistic regression classification models is presented under varying data conditions for the two-group classification problem. With this method, separate-group, as well as total-sample proportions of the correct classifications, can be…

  17. A Method for Selecting between Linear and Quadratic Classification Models in Discriminant Analysis.

    ERIC Educational Resources Information Center

    Meshbane, Alice; Morris, John D.

    A method for comparing the cross validated classification accuracies of linear and quadratic classification rules is presented under varying data conditions for the k-group classification problem. With this method, separate-group as well as total-group proportions of correct classifications can be compared for the two rules. McNemar's test for…

  18. A support vector machine classifier reduces interscanner variation in the HRCT classification of regional disease pattern in diffuse lung disease: Comparison to a Bayesian classifier

    SciTech Connect

    Chang, Yongjun; Lim, Jonghyuck; Kim, Namkug; Seo, Joon Beom; Lynch, David A.

    2013-05-15

    Purpose: To investigate the effect of using different computed tomography (CT) scanners on the accuracy of high-resolution CT (HRCT) images in classifying regional disease patterns in patients with diffuse lung disease, support vector machine (SVM) and Bayesian classifiers were applied to multicenter data. Methods: Two experienced radiologists marked sets of 600 rectangular 20 Multiplication-Sign 20 pixel regions of interest (ROIs) on HRCT images obtained from two scanners (GE and Siemens), including 100 ROIs for each of local patterns of lungs-normal lung and five of regional pulmonary disease patterns (ground-glass opacity, reticular opacity, honeycombing, emphysema, and consolidation). Each ROI was assessed using 22 quantitative features belonging to one of the following descriptors: histogram, gradient, run-length, gray level co-occurrence matrix, low-attenuation area cluster, and top-hat transform. For automatic classification, a Bayesian classifier and a SVM classifier were compared under three different conditions. First, classification accuracies were estimated using data from each scanner. Next, data from the GE and Siemens scanners were used for training and testing, respectively, and vice versa. Finally, all ROI data were integrated regardless of the scanner type and were then trained and tested together. All experiments were performed based on forward feature selection and fivefold cross-validation with 20 repetitions. Results: For each scanner, better classification accuracies were achieved with the SVM classifier than the Bayesian classifier (92% and 82%, respectively, for the GE scanner; and 92% and 86%, respectively, for the Siemens scanner). The classification accuracies were 82%/72% for training with GE data and testing with Siemens data, and 79%/72% for the reverse. The use of training and test data obtained from the HRCT images of different scanners lowered the classification accuracy compared to the use of HRCT images from the same scanner. For

  19. Overlay accuracy fundamentals

    NASA Astrophysics Data System (ADS)

    Kandel, Daniel; Levinski, Vladimir; Sapiens, Noam; Cohen, Guy; Amit, Eran; Klein, Dana; Vakshtein, Irina

    2012-03-01

    Currently, the performance of overlay metrology is evaluated mainly based on random error contributions such as precision and TIS variability. With the expected shrinkage of the overlay metrology budget to < 0.5nm, it becomes crucial to include also systematic error contributions which affect the accuracy of the metrology. Here we discuss fundamental aspects of overlay accuracy and a methodology to improve accuracy significantly. We identify overlay mark imperfections and their interaction with the metrology technology, as the main source of overlay inaccuracy. The most important type of mark imperfection is mark asymmetry. Overlay mark asymmetry leads to a geometrical ambiguity in the definition of overlay, which can be ~1nm or less. It is shown theoretically and in simulations that the metrology may enhance the effect of overlay mark asymmetry significantly and lead to metrology inaccuracy ~10nm, much larger than the geometrical ambiguity. The analysis is carried out for two different overlay metrology technologies: Imaging overlay and DBO (1st order diffraction based overlay). It is demonstrated that the sensitivity of DBO to overlay mark asymmetry is larger than the sensitivity of imaging overlay. Finally, we show that a recently developed measurement quality metric serves as a valuable tool for improving overlay metrology accuracy. Simulation results demonstrate that the accuracy of imaging overlay can be improved significantly by recipe setup optimized using the quality metric. We conclude that imaging overlay metrology, complemented by appropriate use of measurement quality metric, results in optimal overlay accuracy.

  20. Context-driven, prescription-based personal activity classification: methodology, architecture, and end-to-end implementation.

    PubMed

    Xu, James Y; Chang, Hua-I; Chien, Chieh; Kaiser, William J; Pottie, Gregory J

    2014-05-01

    Enabling large-scale monitoring and classification of a range of motion activities is of primary importance due to the need by healthcare and fitness professionals to monitor exercises for quality and compliance. Past work has not fully addressed the unique challenges that arise from scaling. This paper presents a novel end-to-end system solution to some of these challenges. The system is built on the prescription-based context-driven activity classification methodology. First, we show that by refining the definition of context, and introducing the concept of scenarios, a prescription model can provide personalized activity monitoring. Second, through a flexible architecture constructed from interface models, we demonstrate the concept of a context-driven classifier. Context classification is achieved through a classification committee approach, and activity classification follows by means of context specific activity models. Then, the architecture is implemented in an end-to-end system featuring an Android application running on a mobile device, and a number of classifiers as core classification components. Finally, we use a series of experimental field evaluations to confirm the expected benefits of the proposed system in terms of classification accuracy, rate, and sensor operating life.

  1. Prognostic classification of mild cognitive impairment and Alzheimer's disease: MRI independent component analysis.

    PubMed

    Willette, Auriel A; Calhoun, Vince D; Egan, Josephine M; Kapogiannis, Dimitrios

    2014-11-30

    Identifying predictors of mild cognitive impairment (MCI) and Alzheimer's disease (AD) can lead to more accurate diagnosis and facilitate clinical trial participation. We identified 320 participants (93 cognitively normal or CN, 162 MCI, 65 AD) with baseline magnetic resonance imaging (MRI) data, cerebrospinal fluid biomarkers, and cognition data in the Alzheimer's Disease Neuroimaging Initiative database. We used independent component analysis (ICA) on structural MR images to derive 30 matter covariance patterns (ICs) across all participants. These ICs were used in iterative and stepwise discriminant classifier analyses to predict diagnostic classification at 24 months for CN vs. MCI, CN vs. AD, MCI vs. AD, and stable MCI (MCI-S) vs. MCI progression to AD (MCI-P). Models were cross-validated with a "leave-10-out" procedure. For CN vs. MCI, 84.7% accuracy was achieved based on cognitive performance measures, ICs, p-tau(181p), and ApoE ε4 status. For CN vs. AD, 94.8% accuracy was achieved based on cognitive performance measures, ICs, and p-tau(181p). For MCI vs. AD and MCI-S vs. MCI-P, models achieved 83.1% and 80.3% accuracy, respectively, based on cognitive performance measures, ICs, and p-tau(181p). ICA-derived MRI biomarkers achieve excellent diagnostic accuracy for MCI conversion, which is little improved by CSF biomarkers and ApoE ε4 status.

  2. Corpus Callosum MR Image Classification

    NASA Astrophysics Data System (ADS)

    Elsayed, A.; Coenen, F.; Jiang, C.; García-Fiñana, M.; Sluming, V.

    An approach to classifying Magnetic Resonance (MR) image data is described. The specific application is the classification of MRI scan data according to the nature of the corpus callosum, however the approach has more general applicability. A variation of the “spectral segmentation with multi-scale graph decomposition” mechanism is introduced. The result of the segmentation is stored in a quad-tree data structure to which a weighted variation (also developed by the authors) of the gSpan algorithm is applied to identify frequent sub-trees. As a result the images are expressed as a set frequent sub-trees. There may be a great many of these and thus a decision tree based feature reduction technique is applied before classification takes place. The results show that the proposed approach performs both efficiently and effectively, obtaining a classification accuracy of over 95% in the case of the given application.

  3. Harmonization of description and classification of fetal observations: achievements and problems still unresolved: report of the 7th Workshop on the Terminology in Developmental Toxicology Berlin, 4-6 May 2011.

    PubMed

    Solecki, Roland; Barbellion, Stephane; Bergmann, Brigitte; Bürgin, Heinrich; Buschmann, Jochen; Clark, Ruth; Comotto, Laura; Fuchs, Antje; Faqi, Ali Said; Gerspach, Ralph; Grote, Konstanze; Hakansson, Helen; Heinrich, Verena; Heinrich-Hirsch, Barbara; Hofmann, Thomas; Hübel, Ulrich; Inazaki, Thelma Helena; Khalil, Samia; Knudsen, Thomas B; Kudicke, Sabine; Lingk, Wolfgang; Makris, Susan; Müller, Simone; Paumgartten, Francisco; Pfeil, Rudolf; Rama, Elkiane Macedo; Schneider, Steffen; Shiota, Kohei; Tamborini, Eva; Tegelenbosch, Mariska; Ulbrich, Beate; van Duijnhoven, E A J; Wise, David; Chahoud, Ibrahim

    2013-01-01

    This article summarizes the 7th Workshop on the Terminology in Developmental Toxicology held in Berlin, May 4-6, 2011. The series of Berlin Workshops has been mainly concerned with the harmonization of terminology and classification of fetal anomalies in developmental toxicity studies. The main topics of the 7th Workshop were knowledge on the fate of anomalies after birth, use of Version 2 terminology for maternal-fetal observations and non-routinely used species, reclassification of "grey zone" anomalies and categorization of fetal observations for human health risk assessment. The paucity of data on health consequences of the postnatal permanence of fetal anomalies is relevant and further studies are needed. The Version 2 terminology is an important step forward and the terms listed in this glossary are considered also to be appropriate for most observations in non-routinely used species. Continuation of the Berlin Workshops was recommended. Topics suggested for the next Workshop were grouping of fetal observations for reporting and statistical analysis.

  4. Evaluation of supervised classification by class and classification characteristics

    NASA Astrophysics Data System (ADS)

    Masse, Antoine; Ducrot, Danielle; Marthon, Philippe

    2012-06-01

    As acquisition technology progresses, remote sensing data contains an ever increasing amount of information: optical and radar images, low, high and very high-resolution, multitemporal hyperspectral images, derived images, and physical or ancillary data (databases, Digital Elevation Model (D.E.M), Geographical Information System (G.I.S.)). Future projects in remote sensing will give high repeatability of acquisition like Venμs (CNES) which may provide data every 2 days with a resolution of 5.3 meters on 12 bands (420nm-900nm) and Sentinel-2 (ESA) 13 bands, 10-60m resolution and 5 days. With such data, supervised classification gives excellent results in term of accuracy indices (like Overall Accuracy, Kappa coefficient). In this paper, we present advantages and disadvantages of existing indices and propose a new index to evaluate supervised classification using all the information available from the confusion matrix. In addition to accuracy, a new feature is introduced in this index: fidelity. For example, a class could have a high accuracy (low omission error) but could be over-represented with other classes (high commission error). The new index reflects accuracy and correct representation of classes (fidelity) using commission and omission errors. Environment applications are in land cover and land use and the goal is to have the best classification for all classes, whether the biggest (corn, trees) or the lightest (rivers, hedges). The tests are performed on Formosat-2 images (every 2 days, 8 meters resolution on 4 bands) in the area of Toulouse, France). Tests used to validate the new index by demonstrating benefits of its use through various thematical studies.

  5. Classification of EEG signals using a multiple kernel learning support vector machine.

    PubMed

    Li, Xiaoou; Chen, Xun; Yan, Yuning; Wei, Wenshi; Wang, Z Jane

    2014-07-17

    In this study, a multiple kernel learning support vector machine algorithm is proposed for the identification of EEG signals including mental and cognitive tasks, which is a key component in EEG-based brain computer interface (BCI) systems. The presented BCI approach included three stages: (1) a pre-processing step was performed to improve the general signal quality of the EEG; (2) the features were chosen, including wavelet packet entropy and Granger causality, respectively; (3) a multiple kernel learning support vector machine (MKL-SVM) based on a gradient descent optimization algorithm was investigated to classify EEG signals, in which the kernel was defined as a linear combination of polynomial kernels and radial basis function kernels. Experimental results showed that the proposed method provided better classification performance compared with the SVM based on a single kernel. For mental tasks, the average accuracies for 2-class, 3-class, 4-class, and 5-class classifications were 99.20%, 81.25%, 76.76%, and 75.25% respectively. Comparing stroke patients with healthy controls using the proposed algorithm, we achieved the average classification accuracies of 89.24% and 80.33% for 0-back and 1-back tasks respectively. Our results indicate that the proposed approach is promising for implementing human-computer interaction (HCI), especially for mental task classification and identifying suitable brain impairment candidates.

  6. EEG Sleep Stages Classification Based on Time Domain Features and Structural Graph Similarity.

    PubMed

    Diykh, Mohammed; Li, Yan; Wen, Peng

    2016-11-01

    The electroencephalogram (EEG) signals are commonly used in diagnosing and treating sleep disorders. Many existing methods for sleep stages classification mainly depend on the analysis of EEG signals in time or frequency domain to obtain a high classification accuracy. In this paper, the statistical features in time domain, the structural graph similarity and the K-means (SGSKM) are combined to identify six sleep stages using single channel EEG signals. Firstly, each EEG segment is partitioned into sub-segments. The size of a sub-segment is determined empirically. Secondly, statistical features are extracted, sorted into different sets of features and forwarded to the SGSKM to classify EEG sleep stages. We have also investigated the relationships between sleep stages and the time domain features of the EEG data used in this paper. The experimental results show that the proposed method yields better classification results than other four existing methods and the support vector machine (SVM) classifier. A 95.93% average classification accuracy is achieved by using the proposed method.

  7. Classification of EEG Signals Using a Multiple Kernel Learning Support Vector Machine

    PubMed Central

    Li, Xiaoou; Chen, Xun; Yan, Yuning; Wei, Wenshi; Wang, Z. Jane

    2014-01-01

    In this study, a multiple kernel learning support vector machine algorithm is proposed for the identification of EEG signals including mental and cognitive tasks, which is a key component in EEG-based brain computer interface (BCI) systems. The presented BCI approach included three stages: (1) a pre-processing step was performed to improve the general signal quality of the EEG; (2) the features were chosen, including wavelet packet entropy and Granger causality, respectively; (3) a multiple kernel learning support vector machine (MKL-SVM) based on a gradient descent optimization algorithm was investigated to classify EEG signals, in which the kernel was defined as a linear combination of polynomial kernels and radial basis function kernels. Experimental results showed that the proposed method provided better classification performance compared with the SVM based on a single kernel. For mental tasks, the average accuracies for 2-class, 3-class, 4-class, and 5-class classifications were 99.20%, 81.25%, 76.76%, and 75.25% respectively. Comparing stroke patients with healthy controls using the proposed algorithm, we achieved the average classification accuracies of 89.24% and 80.33% for 0-back and 1-back tasks respectively. Our results indicate that the proposed approach is promising for implementing human-computer interaction (HCI), especially for mental task classification and identifying suitable brain impairment candidates. PMID:25036334

  8. Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System

    PubMed Central

    Li, Hongqiang; Yuan, Danyang; Wang, Youxi; Cui, Dianyin; Cao, Lu

    2016-01-01

    Automatic recognition of arrhythmias is particularly important in the diagnosis of heart diseases. This study presents an electrocardiogram (ECG) recognition system based on multi-domain feature extraction to classify ECG beats. An improved wavelet threshold method for ECG signal pre-processing is applied to remove noise interference. A novel multi-domain feature extraction method is proposed; this method employs kernel-independent component analysis in nonlinear feature extraction and uses discrete wavelet transform to extract frequency domain features. The proposed system utilises a support vector machine classifier optimized with a genetic algorithm to recognize different types of heartbeats. An ECG acquisition experimental platform, in which ECG beats are collected as ECG data for classification, is constructed to demonstrate the effectiveness of the system in ECG beat classification. The presented system, when applied to the MIT-BIH arrhythmia database, achieves a high classification accuracy of 98.8%. Experimental results based on the ECG acquisition experimental platform show that the system obtains a satisfactory classification accuracy of 97.3% and is able to classify ECG beats efficiently for the automatic identification of cardiac arrhythmias. PMID:27775596

  9. [LLE-SVM classification of apple mealiness based on hyperspectral scattering image].

    PubMed

    Zhao, Gui-lin; Zhu, Qi-bing; Huang, Min

    2010-10-01

    Apple mealiness degree is an important factor for its internal quality. hyperspectral scattering, as a promising technique, was investigated for noninvasive measurement of apple mealiness. In the present paper, a locally linear embedding (LLE) coupled with support vector machine (SVM) was proposed to achieve classification because of large number of image data. LLE is a nonlinear lowering dimension method, which reveals the structure of the global nonlinearity by the local linear joint. This method can effectively calculate high-dimensional input data embedded in a low-dimensional space manifold. The dimension reduction of hyperspectral data was classified by SVM. Comparing the LLE-SVM classification method with the traditional SVM classification, the results indicated that the training accuracy obtained with the LLE-SVM was higher than that just with SVM; and the testing accuracy of the classifier changed a little before and after dimensionality reduction, and the range of fluctuation was less than 5%. It is expected that LLE-SVM method would provide an effective classification method for apple mealiness nondestructive detection using hyperspectral scattering image technique.

  10. Keratin protein property based classification of mammals and non-mammals using machine learning techniques.

    PubMed

    Banerjee, Amit Kumar; Ravi, Vadlamani; Murty, U S N; Shanbhag, Anirudh P; Prasanna, V Lakshmi

    2013-08-01

    Keratin protein is ubiquitous in most vertebrates and invertebrates, and has several important cellular and extracellular functions that are related to survival and protection. Keratin function has played a significant role in the natural selection of an organism. Hence, it acts as a marker of evolution. Much information about an organism and its evolution can therefore be obtained by investigating this important protein. In the present study, Keratin sequences were extracted from public data repositories and various important sequential, structural and physicochemical properties were computed and used for preparing the dataset. The dataset containing two classes, namely mammals (Class-1) and non-mammals (Class-0), was prepared, and rigorous classification analysis was performed. To reduce the complexity of the dataset containing 56 parameters and to achieve improved accuracy, feature selection was done using the t-statistic. The 20 best features (parameters) were selected for further classification analysis using computational algorithms which included SVM, KNN, Neural Network, Logistic regression, Meta-modeling, Tree Induction, Rule Induction, Discriminant analysis and Bayesian Modeling. Statistical methods were used to evaluate the output. Logistic regression was found to be the most effective algorithm for classification, with greater than 96% accuracy using a 10-fold cross validation analysis. KNN, SVM and Rule Induction algorithms also were found to be efficacious for classification.

  11. Object categories specific brain activity classification with simultaneous EEG-fMRI.

    PubMed

    Ahmad, Rana Fayyaz; Malik, Aamir Saeed; Kamel, Nidal; Reza, Faruque

    2015-01-01

    Any kind of visual information is encoded in terms of patterns of neural activity occurring inside the brain. Decoding neural patterns or its classification is a challenging task. Functional magnetic resonance imaging (fMRI) and Electroencephalography (EEG) are non-invasive neuroimaging modalities to capture the brain activity pattern in term of images and electric potential respectively. To get higher spatiotemporal resolution of human brain from these two complementary neuroimaging modalities, simultaneous EEG-fMRI can be helpful. In this paper, we proposed a framework for classifying the brain activity patterns with simultaneous EEG-fMRI. We have acquired five human participants' data with simultaneous EEG-fMRI by showing different object categories. Further, combined analysis of EEG and fMRI data was carried out. Extracted information through combine analysis is passed to support vector machine (SVM) classifier for classification purpose. We have achieved better classification accuracy using simultaneous EEG-fMRI i.e., 81.8% as compared to fMRI data standalone. This shows that multimodal neuroimaging can improve the classification accuracy of brain activity patterns as compared to individual modalities reported in literature.

  12. The use of airborne hyperspectral data for tree species classification in a species-rich Central European forest area

    NASA Astrophysics Data System (ADS)

    Richter, Ronny; Reu, Björn; Wirth, Christian; Doktor, Daniel; Vohland, Michael

    2016-10-01

    The success of remote sensing approaches to assess tree species diversity in a heterogeneously mixed forest stand depends on the availability of both appropriate data and suitable classification algorithms. To separate the high number of in total ten broadleaf tree species in a small structured floodplain forest, the Leipzig Riverside Forest, we introduce a majority based classification approach for Discriminant Analysis based on Partial Least Squares (PLS-DA), which was tested against Random Forest (RF) and Support Vector Machines (SVM). The classifier performance was tested on different sets of airborne hyperspectral image data (AISA DUAL) that were acquired on single dates in August and September and also stacked to a composite product. Shadowed gaps and shadowed crown parts were eliminated via spectral mixture analysis (SMA) prior to the pixel-based classification. Training and validation sets were defined spectrally with the conditioned Latin hypercube method as a stratified random sampling procedure. In the validation, PLS-DA consistently outperformed the RF and SVM approaches on all datasets. The additional use of spectral variable selection (CARS, "competitive adaptive reweighted sampling") combined with PLS-DA further improved classification accuracies. Up to 78.4% overall accuracy was achieved for the stacked dataset. The image recorded in August provided slightly higher accuracies than the September image, regardless of the applied classifier.

  13. Classification of grass pollen through the quantitative analysis of surface ornamentation and texture.

    PubMed

    Mander, Luke; Li, Mao; Mio, Washington; Fowlkes, Charless C; Punyasena, Surangi W

    2013-11-07

    Taxonomic identification of pollen and spores uses inherently qualitative descriptions of morphology. Consequently, identifications are restricted to categories that can be reliably classified by multiple analysts, resulting in the coarse taxonomic resolution of the pollen and spore record. Grass pollen represents an archetypal example; it is not routinely identified below family level. To address this issue, we developed quantitative morphometric methods to characterize surface ornamentation and classify grass pollen grains. This produces a means of quantifying morphological features that are traditionally described qualitatively. We used scanning electron microscopy to image 240 specimens of pollen from 12 species within the grass family (Poaceae). We classified these species by developing algorithmic features that quantify the size and density of sculptural elements on the pollen surface, and measure the complexity of the ornamentation they form. These features yielded a classification accuracy of 77.5%. In comparison, a texture descriptor based on modelling the statistical distribution of brightness values in image patches yielded a classification accuracy of 85.8%, and seven human subjects achieved accuracies between 68.33 and 81.67%. The algorithmic features we developed directly relate to biologically meaningful features of grass pollen morphology, and could facilitate direct interpretation of unsupervised classification results from fossil material.

  14. Application of Linear Discriminant Analysis in Dimensionality Reduction for Hand Motion Classification

    NASA Astrophysics Data System (ADS)

    Phinyomark, A.; Hu, H.; Phukpattaranont, P.; Limsakul, C.

    2012-01-01

    The classification of upper-limb movements based on surface electromyography (EMG) signals is an important issue in the control of assistive devices and rehabilitation systems. Increasing the number of EMG channels and features in order to increase the number of control commands can yield a high dimensional feature vector. To cope with the accuracy and computation problems associated with high dimensionality, it is commonplace to apply a processing step that transforms the data to a space of significantly lower dimensions with only a limited loss of useful information. Linear discriminant analysis (LDA) has been successfully applied as an EMG feature projection method. Recently, a number of extended LDA-based algorithms have been proposed, which are more competitive in terms of both classification accuracy and computational costs/times with classical LDA. This paper presents the findings of a comparative study of classical LDA and five extended LDA methods. From a quantitative comparison based on seven multi-feature sets, three extended LDA-based algorithms, consisting of uncorrelated LDA, orthogonal LDA and orthogonal fuzzy neighborhood discriminant analysis, produce better class separability when compared with a baseline system (without feature projection), principle component analysis (PCA), and classical LDA. Based on a 7-dimension time domain and time-scale feature vectors, these methods achieved respectively 95.2% and 93.2% classification accuracy by using a linear discriminant classifier.

  15. Supervised Classification of Polarimetric SAR Imagery Using Temporal and Contextual Information

    NASA Astrophysics Data System (ADS)

    Dargahi, A.; Maghsoudi, Y.; Abkar, A. A.

    2013-09-01

    Using the context as a source of ancillary information in classification process provides a powerful tool to obtain better class discrimination. Modelling context using Markov Random Fields (MRFs) and combining with Bayesian approach, a context-based supervised classification method is proposed. In this framework, to have a full use of the statistical a priori knowledge of the data, the spatial relation of the neighbouring pixels was used. The proposed context-based algorithm combines a Gaussian-based wishart distribution of PolSAR images with temporal and contextual information. This combination was done through the Bayes decision theory: the class-conditional probability density function and the prior probability are modelled by the wishart distribution and the MRF model. Given the complexity and similarity of classes, in order to enhance the class separation, simultaneously two PolSAR images from two different seasons (leaf-on and leaf-off) were used. According to the achieved results, the maximum improvement in the overall accuracy of classification using WMRF (Combining Wishart and MRF) compared to the wishart classifier when the leaf-on image was used. The highest accuracy obtained was when using the combined datasets. In this case, the overall accuracy of the wishart and WMRF methods were 72.66% and 78.95% respectively.

  16. Application of spectral and spatial indices for specific class identification in Airborne Prism EXperiment (APEX) imaging spectrometer data for improved land cover classification

    NASA Astrophysics Data System (ADS)

    Kallepalli, Akhil; Kumar, Anil; Khoshelham, Kourosh; James, David B.

    2016-10-01

    Hyperspectral remote sensing's ability to capture spectral information of targets in very narrow bandwidths gives rise to many intrinsic applications. However, the major limiting disadvantage to its applicability is its dimensionality, known as the Hughes Phenomenon. Traditional classification and image processing approaches fail to process data along many contiguous bands due to inadequate training samples. Another challenge of successful classification is to deal with the real world scenario of mixed pixels i.e. presence of more than one class within a single pixel. An attempt has been made to deal with the problems of dimensionality and mixed pixels, with an objective to improve the accuracy of class identification. In this paper, we discuss the application of indices to cope with the disadvantage of the dimensionality of the Airborne Prism EXperiment (APEX) hyperspectral Open Science Dataset (OSD) and to improve the classification accuracy using the Possibilistic c-Means (PCM) algorithm. This was used for the formulation of spectral and spatial indices to describe the information in the dataset in a lesser dimensionality. This reduced dimensionality is used for classification, attempting to improve the accuracy of determination of specific classes. Spectral indices are compiled from the spectral signatures of the target and spatial indices have been defined using texture analysis over defined neighbourhoods. The classification of 20 classes of varying spatial distributions was considered in order to evaluate the applicability of spectral and spatial indices in the extraction of specific class information. The classification of the dataset was performed in two stages; spectral and a combination of spectral and spatial indices individually as input for the PCM classifier. In addition to the reduction of entropy, while considering a spectral-spatial indices approach, an overall classification accuracy of 80.50% was achieved, against 65% (spectral indices only) and

  17. Classification with spatio-temporal interpixel class dependency contexts

    NASA Technical Reports Server (NTRS)

    Jeon, Byeungwoo; Landgrebe, David A.

    1992-01-01

    A contextual classifier which can utilize both spatial and temporal interpixel dependency contexts is investigated. After spatial and temporal neighbors are defined, a general form of maximum a posterior spatiotemporal contextual classifier is derived. This contextual classifier is simplified under several assumptions. Joint prior probabilities of the classes of each pixel and its spatial neighbors are modeled by the Gibbs random field. The classification is performed in a recursive manner to allow a computationally efficient contextual classification. Experimental results with bitemporal TM data show significant improvement of classification accuracy over noncontextual pixelwise classifiers. This spatiotemporal contextual classifier should find use in many applications of remote sensing, especially when the classification accuracy is important.

  18. Unsupervised classification of operator workload from brain signals

    NASA Astrophysics Data System (ADS)

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

    2016-06-01

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

  19. Transportation Modes Classification Using Sensors on Smartphones

    PubMed Central

    Fang, Shih-Hau; Liao, Hao-Hsiang; Fei, Yu-Xiang; Chen, Kai-Hsiang; Huang, Jen-Wei; Lu, Yu-Ding; Tsao, Yu

    2016-01-01

    This paper investigates the transportation and vehicular modes classification by using big data from smartphone sensors. The three types of sensors used in this paper include the accelerometer, magnetometer, and gyroscope. This study proposes improved features and uses three machine learning algorithms including decision trees, K-nearest neighbor, and support vector machine to classify the user’s transportation and vehicular modes. In the experiments, we discussed and compared the performance from different perspectives including the accuracy for both modes, the executive time, and the model size. Results show that the proposed features enhance the accuracy, in which the support vector machine provides the best performance in classification accuracy whereas it consumes the largest prediction time. This paper also investigates the vehicle classification mode and compares the results with that of the transportation modes. PMID:27548182

  20. Automated patient-specific classification of long-term Electroencephalography.

    PubMed

    Kiranyaz, Serkan; Ince, Turker; Zabihi, Morteza; Ince, Dilek

    2014-06-01

    This paper presents a novel systematic approach for patient-specific classification of long-term Electroencephalography (EEG). The goal is to extract the seizure sections with a high accuracy to ease the Neurologist's burden of inspecting such long-term EEG data. We aim to achieve this using the minimum feedback from the Neurologist. To accomplish this, we use the majority of the state-of-the-art features proposed in this domain for evolving a collective network of binary classifiers (CNBC) using multi-dimensional particle swarm optimization (MD PSO). Multiple CNBCs are then used to form a CNBC ensemble (CNBC-E), which aggregates epileptic seizure frames from the classification map of each CNBC in order to maximize the sensitivity rate. Finally, a morphological filter forms the final epileptic segments while filtering out the outliers in the form of classification noise. The proposed system is fully generic, which does not require any a priori information about the patient such as the list of relevant EEG channels. The results of the classification experiments, which are performed over the benchmark CHB-MIT scalp long-term EEG database show that the proposed system can achieve all the aforementioned objectives and exhibits a significantly superior performance compared to several other state-of-the-art methods. Using a limited training dataset that is formed by less than 2 min of seizure and 24 min of non-seizure data on the average taken from the early 25% section of the EEG record of each patient, the proposed system establishes an average sensitivity rate above 89% along with an average specificity rate above 93% over the test set.

  1. Numerical accuracy assessment

    NASA Astrophysics Data System (ADS)

    Boerstoel, J. W.

    1988-12-01

    A framework is provided for numerical accuracy assessment. The purpose of numerical flow simulations is formulated. This formulation concerns the classes of aeronautical configurations (boundaries), the desired flow physics (flow equations and their properties), the classes of flow conditions on flow boundaries (boundary conditions), and the initial flow conditions. Next, accuracy and economical performance requirements are defined; the final numerical flow simulation results of interest should have a guaranteed accuracy, and be produced for an acceptable FLOP-price. Within this context, the validation of numerical processes with respect to the well known topics of consistency, stability, and convergence when the mesh is refined must be done by numerical experimentation because theory gives only partial answers. This requires careful design of text cases for numerical experimentation. Finally, the results of a few recent evaluation exercises of numerical experiments with a large number of codes on a few test cases are summarized.

  2. Radar System Classification Using Neural Networks

    DTIC Science & Technology

    1991-12-01

    This study investigated methods of improving the accuracy of neural networks in the classification of large numbers of classes. A literature search...revealed that neural networks have been successful in the radar classification problem, and that many complex problems have been solved using systems...of multiple neural networks . The experiments conducted were based on 32 classes of radar system data. The neural networks were modelled using a program

  3. Computationally efficient target classification in multispectral image data with Deep Neural Networks

    NASA Astrophysics Data System (ADS)

    Cavigelli, Lukas; Bernath, Dominic; Magno, Michele; Benini, Luca

    2016-10-01

    Detecting and classifying targets in video streams from surveillance cameras is a cumbersome, error-prone and expensive task. Often, the incurred costs are prohibitive for real-time monitoring. This leads to data being stored locally or transmitted to a central storage site for post-incident examination. The required communication links and archiving of the video data are still expensive and this setup excludes preemptive actions to respond to imminent threats. An effective way to overcome these limitations is to build a smart camera that analyzes the data on-site, close to the sensor, and transmits alerts when relevant video sequences are detected. Deep neural networks (DNNs) have come to outperform humans in visual classifications tasks and are also performing exceptionally well on other computer vision tasks. The concept of DNNs and Convolutional Networks (ConvNets) can easily be extended to make use of higher-dimensional input data such as multispectral data. We explore this opportunity in terms of achievable accuracy and required computational effort. To analyze the precision of DNNs for scene labeling in an urban surveillance scenario we have created a dataset with 8 classes obtained in a field experiment. We combine an RGB camera with a 25-channel VIS-NIR snapshot sensor to assess the potential of multispectral image data for target classification. We evaluate several new DNNs, showing that the spectral information fused together with the RGB frames can be used to improve the accuracy of the system or to achieve similar accuracy with a 3x smaller computation effort. We achieve a very high per-pixel accuracy of 99.1%. Even for scarcely occurring, but particularly interesting classes, such as cars, 75% of the pixels are labeled correctly with errors occurring only around the border of the objects. This high accuracy was obtained with a training set of only 30 labeled images, paving the way for fast adaptation to various application scenarios.

  4. Genetic algorithm for the optimization of features and neural networks in ECG signals classification

    NASA Astrophysics Data System (ADS)

    Li, Hongqiang; Yuan, Danyang; Ma, Xiangdong; Cui, Dianyin; Cao, Lu

    2017-01-01

    Feature extraction and classification of electrocardiogram (ECG) signals are necessary for the automatic diagnosis of cardiac diseases. In this study, a novel method based on genetic algorithm-back propagation neural network (GA-BPNN) for classifying ECG signals with feature extraction using wavelet packet decomposition (WPD) is proposed. WPD combined with the statistical method is utilized to extract the effective features of ECG signals. The statistical features of the wavelet packet coefficients are calculated as the feature sets. GA is employed to decrease the dimensions of the feature sets and to optimize the weights and biases of the back propagation neural network (BPNN). Thereafter, the optimized BPNN classifier is applied to classify six types of ECG signals. In addition, an experimental platform is constructed for ECG signal acquisition to supply the ECG data for verifying the effectiveness of the proposed method. The GA-BPNN method with the MIT-BIH arrhythmia database achieved a dimension reduction of nearly 50% and produced good classification results with an accuracy of 97.78%. The experimental results based on the established acquisition platform indicated that the GA-BPNN method achieved a high classification accuracy of 99.33% and could be efficiently applied in the automatic identification of cardiac arrhythmias.

  5. Genetic algorithm for the optimization of features and neural networks in ECG signals classification

    PubMed Central

    Li, Hongqiang; Yuan, Danyang; Ma, Xiangdong; Cui, Dianyin; Cao, Lu

    2017-01-01

    Feature extraction and classification of electrocardiogram (ECG) signals are necessary for the automatic diagnosis of cardiac diseases. In this study, a novel method based on genetic algorithm-back propagation neural network (GA-BPNN) for classifying ECG signals with feature extraction using wavelet packet decomposition (WPD) is proposed. WPD combined with the statistical method is utilized to extract the effective features of ECG signals. The statistical features of the wavelet packet coefficients are calculated as the feature sets. GA is employed to decrease the dimensions of the feature sets and to optimize the weights and biases of the back propagation neural network (BPNN). Thereafter, the optimized BPNN classifier is applied to classify six types of ECG signals. In addition, an experimental platform is constructed for ECG signal acquisition to supply the ECG data for verifying the effectiveness of the proposed method. The GA-BPNN method with the MIT-BIH arrhythmia database achieved a dimension reduction of nearly 50% and produced good classification results with an accuracy of 97.78%. The experimental results based on the established acquisition platform indicated that the GA-BPNN method achieved a high classification accuracy of 99.33% and could be efficiently applied in the automatic identification of cardiac arrhythmias. PMID:28139677

  6. Computer-aided classification for remote sensing in agriculture and forestry in Northern Italy

    NASA Technical Reports Server (NTRS)

    Dejace, J.; Megier, J.; Mehl, W.

    1977-01-01

    A set of results concerning the processing and analysis of data from LANDSAT satellite and airborne scanner is presented. The possibility of performing inventories of irrigated crops-rice, planted groves-poplars, and natural forests in the mountians-beeches and chestnuts, is investigated in the Po valley and in an alphine site of Northern Italy. Accuracies around 95% or better, 70% and 60% respectively are achieved by using LANDSAT data and supervised classification. Discrimination of rice varieties is proved with 8 channels data from airborne scanner, processed after correction of the atmospheric effect due to the scanning angle, with and without linear feature selection of the data. The accuracies achieved range from 65% to more than 80%. The best results are obtained with the maximum likelihood classifier for normal parameters but rather close results are derived by using a modified version of the weighted euclidian distance between points, with consequent decrease in computing time around a factor 3.

  7. Functional connectivity classification of autism identifies highly predictive brain features but falls short of biomarker standards

    PubMed Central

    Plitt, Mark; Barnes, Kelly Anne; Martin, Alex

    2014-01-01

    Objectives Autism spectrum disorders (ASD) are diagnosed based on early-manifesting clinical symptoms, including markedly impaired social communication. We assessed the viability of resting-state functional MRI (rs-fMRI) connectivity measures as diagnostic biomarkers for ASD and investigated which connectivity features are predictive of a diagnosis. Methods Rs-fMRI scans from 59 high functioning males with ASD and 59 age- and IQ-matched typically developing (TD) males were used to build a series of machine learning classifiers. Classification features were obtained using 3 sets of brain regions. Another set of classifiers was built from participants' scores on behavioral metrics. An additional age and IQ-matched cohort of 178 individuals (89 ASD; 89 TD) from the Autism Brain Imaging Data Exchange (ABIDE) open-access dataset (http://fcon_1000.projects.nitrc.org/indi/abide/) were included for replication. Results High classification accuracy was achieved through several rs-fMRI methods (peak accuracy 76.67%). However, classification via behavioral measures consistently surpassed rs-fMRI classifiers (peak accuracy 95.19%). The class probability estimates, P(ASD|fMRI data), from brain-based classifiers significantly correlated with scores on a measure of social functioning, the Social Responsiveness Scale (SRS), as did the most informative features from 2 of the 3 sets of brain-based features. The most informative connections predominantly originated from regions strongly associated with social functioning. Conclusions While individuals can be classified as having ASD with statistically significant accuracy from their rs-fMRI scans alone, this method falls short of biomarker standards. Classification methods provided further evidence that ASD functional connectivity is characterized by dysfunction of large-scale functional networks, particularly those involved in social information processing. PMID:25685703

  8. Algorithm for reaction classification.

    PubMed

    Kraut, Hans; Eiblmaier, Josef; Grethe, Guenter; Löw, Peter; Matuszczyk, Heinz; Saller, Heinz

    2013-11-25

    Reaction classification has important applications, and many approaches to classification have been applied. Our own algorithm tests all maximum common substructures (MCS) between all reactant and product molecules in order to find an atom mapping containing the minimum chemical distance (MCD). Recent publications have concluded that new MCS algorithms need to be compared with existing methods in a reproducible environment, preferably on a generalized test set, yet the number of test sets available is small, and they are not truly representative of the range of reactions that occur in real reaction databases. We have designed a challenging test set of reactions and are making it publicly available and usable with InfoChem's software or other classification algorithms. We supply a representative set of example reactions, grouped into different levels of difficulty, from a large number of reaction databases that chemists actually encounter in practice, in order to demonstrate the basic requirements for a mapping algorithm to detect the reaction centers in a consistent way. We invite the scientific community to contribute to the future extension and improvement of this data set, to achieve the goal of a common standard.

  9. Clustering technique-based least square support vector machine for EEG signal classification.

    PubMed

    Siuly; Li, Yan; Wen, Peng Paul

    2011-12-01

    This paper presents a new approach called clustering technique-based least square support vector machine (CT-LS-SVM) for the classification of EEG signals. Decision making is performed in two stages. In the first stage, clustering technique (CT) has been used to extract representative features of EEG data. In the second stage, least square support vector machine (LS-SVM) is applied to the extracted features to classify two-class EEG signals. To demonstrate the effectiveness of the proposed method, several experiments have been conducted on three publicly available benchmark databases, one for epileptic EEG data, one for mental imagery tasks EEG data and another one for motor imagery EEG data. Our proposed approach achieves an average sensitivity, specificity and classification accuracy of 94.92%, 93.44% and 94.18%, respectively, for the epileptic EEG data; 83.98%, 84.37% and 84.17% respectively, for the motor imagery EEG data; and 64.61%, 58.77% and 61.69%, respectively, for the mental imagery tasks EEG data. The performance of the CT-LS-SVM algorithm is compared in terms of classification accuracy and execution (running) time with our previous study where simple random sampling with a least square support vector machine (SRS-LS-SVM) was employed for EEG signal classification. We also compare the proposed method with other existing methods in the literature for the three databases. The experimental results show that the proposed algorithm can produce a better classification rate than the previous reported methods and takes much less execution time compared to the SRS-LS-SVM technique. The research findings in this paper indicate that the proposed approach is very efficient for classification of two-class EEG signals.

  10. Testing of Land Cover Classification from Multispectral Airborne Laser Scanning Data

    NASA Astrophysics Data System (ADS)

    Bakuła, K.; Kupidura, P.; Jełowicki, Ł.

    2016-06-01

    Multispectral Airborne Laser Scanning provides a new opportunity for airborne data collection. It provides high-density topographic surveying and is also a useful tool for land cover mapping. Use of a minimum of three intensity images from a multiwavelength laser scanner and 3D information included in the digital surface model has the potential for land cover/use classification and a discussion about the application of this type of data in land cover/use mapping has recently begun. In the test study, three laser reflectance intensity images (orthogonalized point cloud) acquired in green, near-infrared and short-wave infrared bands, together with a digital surface model, were used in land cover/use classification where six classes were distinguished: water, sand and gravel, concrete and asphalt, low vegetation, trees and buildings. In the tested methods, different approaches for classification were applied: spectral (based only on laser reflectance intensity images), spectral with elevation data as additional input data, and spectro-textural, using morphological granulometry as a method of texture analysis of both types of data: spectral images and the digital surface model. The method of generating the intensity raster was also tested in the experiment. Reference data were created based on visual interpretation of ALS data and traditional optical aerial and satellite images. The results have shown that multispectral ALS data are unlike typical multispectral optical images, and they have a major potential for land cover/use classification. An overall accuracy of classification over 90% was achieved. The fusion of multi-wavelength laser intensity images and elevation data, with the additional use of textural information derived from granulometric analysis of images, helped to improve the accuracy of classification significantly. The method of interpolation for the intensity raster was not very helpful, and using intensity rasters with both first and last return

  11. Classification Algorithms for Big Data Analysis, a Map Reduce Approach

    NASA Astrophysics Data System (ADS)

    Ayma, V. A.; Ferreira, R. S.; Happ, P.; Oliveira, D.; Feitosa, R.; Costa, G.; Plaza, A.; Gamba, P.

    2015-03-01

    Since many years ago, the scientific community is concerned about how to increase the accuracy of different classification methods, and major achievements have been made so far. Besides this issue, the increasing amount of data that is being generated every day by remote sensors raises more challenges to be overcome. In this work, a tool within the scope of InterIMAGE Cloud Platform (ICP), which is an open-source, distributed framework for automatic image interpretation, is presented. The tool, named ICP: Data Mining Package, is able to perform supervised classification procedures on huge amounts of data, usually referred as big data, on a distributed infrastructure using Hadoop MapReduce. The tool has four classification algorithms implemented, taken from WEKA's machine learning library, namely: Decision Trees, Naïve Bayes, Random Forest and Support Vector Machines (SVM). The results of an experimental analysis using a SVM classifier on data sets of different sizes for different cluster configurations demonstrates the potential of the tool, as well as aspects that affect its performance.

  12. Instrument classification in polyphonic music based on timbre analysis

    NASA Astrophysics Data System (ADS)

    Zhang, Tong

    2001-07-01

    While most previous work on musical instrument recognition is focused on the classification of single notes in monophonic music, a scheme is proposed in this paper for the distinction of instruments in continuous music pieces which may contain one or more kinds of instruments. Highlights of the system include music segmentation into notes, harmonic partial estimation in polyphonic sound, note feature calculation and normalization, note classification using a set of neural networks, and music piece categorization with fuzzy logic principles. Example outputs of the system are `the music piece is 100% guitar (with 90% likelihood)' and `the music piece is 60% violin and 40% piano, thus a violin/piano duet'. The system has been tested with twelve kinds of musical instruments, and very promising experimental results have been obtained. An accuracy of about 80% is achieved, and the number can be raised to 90% if misindexings within the same instrument family are tolerated (e.g. cello, viola and violin). A demonstration system for musical instrument classification and music timbre retrieval is also presented.

  13. Deep Learning in Label-free Cell Classification

    DOE PAGES

    Chen, Claire Lifan; Mahjoubfar, Ata; Tai, Li-Chia; ...

    2016-03-15

    Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individualmore » cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. In conclusion, this system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells.« less

  14. Deep Learning in Label-free Cell Classification

    PubMed Central

    Chen, Claire Lifan; Mahjoubfar, Ata; Tai, Li-Chia; Blaby, Ian K.; Huang, Allen; Niazi, Kayvan Reza; Jalali, Bahram

    2016-01-01

    Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. This system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells. PMID:26975219

  15. Deep Learning in Label-free Cell Classification

    NASA Astrophysics Data System (ADS)

    Chen, Claire Lifan; Mahjoubfar, Ata; Tai, Li-Chia; Blaby, Ian K.; Huang, Allen; Niazi, Kayvan Reza; Jalali, Bahram

    2016-03-01

    Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. This system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells.

  16. Hyperspectral image classification for mapping agricultural tillage practices

    NASA Astrophysics Data System (ADS)

    Ran, Qiong; Li, Wei; Du, Qian; Yang, Chenghai

    2015-01-01

    An efficient classification framework for mapping agricultural tillage practice using hyperspectral remote sensing imagery is proposed, which has the potential to be implemented practically to provide rapid, accurate, and objective surveying data for precision agricultural management and appraisal from large-scale remote sensing images. It includes a local region filter [i.e., Gaussian low-pass filter (GLF)] to extract spatial-spectral features, a dimensionality reduction process [i.e., local fisher's discriminate analysis (LFDA)], and the traditional k-nearest neighbor (KNN) classifier, and is denoted as GLF-LFDA-KNN. Compared to our previously used local average filter and adaptive weighted filter, the GLF also considers spatial features in a small neighborhood, but it emphasizes the central pixel itself and is data-independent; therefore, it can achieve the balance between classification accuracy and computational complexity. The KNN classifier has a lower computational complexity compared to the traditional support vector machine (SVM). After classification separability is enhanced by the GLF and LFDA, the less powerful KNN can outperform SVM and the overall computational cost remains lower. The proposed framework can also outperform the SVM with composite kernel (SVM-CK) that uses spatial-spectral features.

  17. Deep Learning in Label-free Cell Classification

    SciTech Connect

    Chen, Claire Lifan; Mahjoubfar, Ata; Tai, Li-Chia; Blaby, Ian K.; Huang, Allen; Niazi, Kayvan Reza; Jalali, Bahram

    2016-03-15

    Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. In conclusion, this system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells.

  18. Deep Learning in Label-free Cell Classification.

    PubMed

    Chen, Claire Lifan; Mahjoubfar, Ata; Tai, Li-Chia; Blaby, Ian K; Huang, Allen; Niazi, Kayvan Reza; Jalali, Bahram

    2016-03-15

    Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. This system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells.

  19. Hyperspectral image classification based on NMF Features Selection Method

    NASA Astrophysics Data System (ADS)

    Abe, Bolanle T.; Jordaan, J. A.

    2013-12-01

    Hyperspectral instruments are capable of collecting hundreds of images corresponding to wavelength channels for the same area on the earth surface. Due to the huge number of features (bands) in hyperspectral imagery, land cover classification procedures are computationally expensive and pose a problem known as the curse of dimensionality. In addition, higher correlation among contiguous bands increases the redundancy within the bands. Hence, dimension reduction of hyperspectral data is very crucial so as to obtain good classification accuracy results. This paper presents a new feature selection technique. Non-negative Matrix Factorization (NMF) algorithm is proposed to obtain reduced relevant features in the input domain of each class label. This aimed to reduce classification error and dimensionality of classification challenges. Indiana pines of the Northwest Indiana dataset is used to evaluate the performance of the proposed method through experiments of features selection and classification. The Waikato Environment for Knowledge Analysis (WEKA) data mining framework is selected as a tool to implement the classification using Support Vector Machines and Neural Network. The selected features subsets are subjected to land cover classification to investigate the performance of the classifiers and how the features size affects classification accuracy. Results obtained shows that performances of the classifiers are significant. The study makes a positive contribution to the problems of hyperspectral imagery by exploring NMF, SVMs and NN to improve classification accuracy. The performances of the classifiers are valuable for decision maker to consider tradeoffs in method accuracy versus method complexity.

  20. Online clustering algorithms for radar emitter classification.

    PubMed

    Liu, Jun; Lee, Jim P Y; Senior; Li, Lingjie; Luo, Zhi-Quan; Wong, K Max

    2005-08-01

    Radar emitter classification is a special application of data clustering for classifying unknown radar emitters from received radar pulse samples. The main challenges of this task are the high dimensionality of radar pulse samples, small sample group size, and closely located radar pulse clusters. In this paper, two new online clustering algorithms are developed for radar emitter classification: One is model-based using the Minimum Description Length (MDL) criterion and the other is based on competitive learning. Computational complexity is analyzed for each algorithm and then compared. Simulation results show the superior performance of the model-based algorithm over competitive learning in terms of better classification accuracy, flexibility, and stability.

  1. The decision tree approach to classification

    NASA Technical Reports Server (NTRS)

    Wu, C.; Landgrebe, D. A.; Swain, P. H.

    1975-01-01

    A class of multistage decision tree classifiers is proposed and studied relative to the classification of multispectral remotely sensed data. The decision tree classifiers are shown to have the potential for improving both the classification accuracy and the computation efficiency. Dimensionality in pattern recognition is discussed and two theorems on the lower bound of logic computation for multiclass classification are derived. The automatic or optimization approach is emphasized. Experimental results on real data are reported, which clearly demonstrate the usefulness of decision tree classifiers.

  2. Unsupervised classification of earth resources data.

    NASA Technical Reports Server (NTRS)

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

    1972-01-01

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

  3. Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques.

    PubMed

    Amin, Hafeez Ullah; Malik, Aamir Saeed; Ahmad, Rana Fayyaz; Badruddin, Nasreen; Kamel, Nidal; Hussain, Muhammad; Chooi, Weng-Tink

    2015-03-01

    This paper describes a discrete wavelet transform-based feature extraction scheme for the classification of EEG signals. In this scheme, the discrete wavelet transform is applied on EEG signals and the relative wavelet energy is calculated in terms of detailed coefficients and the approximation coefficients of the last decomposition level. The extracted relative wavelet energy features are passed to classifiers for the classification purpose. The EEG dataset employed for the validation of the proposed method consisted of two classes: (1) the EEG signals recorded during the complex cognitive task--Raven's advance progressive metric test and (2) the EEG signals recorded in rest condition--eyes open. The performance of four different classifiers was evaluated with four performance measures, i.e., accuracy, sensitivity, specificity and precision values. The accuracy was achieved above 98 % by the support vector machine, multi-layer perceptron and the K-nearest neighbor classifiers with approximation (A4) and detailed coefficients (D4), which represent the frequency range of 0.53-3.06 and 3.06-6.12 Hz, respectively. The findings of this study demonstrated that the proposed feature extraction approach has the potential to classify the EEG signals recorded during a complex cognitive task by achieving a high accuracy rate.

  4. Study of wavelet packet energy entropy for emotion classification in speech and glottal signals

    NASA Astrophysics Data System (ADS)

    He, Ling; Lech, Margaret; Zhang, Jing; Ren, Xiaomei; Deng, Lihua

    2013-07-01

    The automatic speech emotion recognition has important applications in human-machine communication. Majority of current research in this area is focused on finding optimal feature parameters. In recent studies, several glottal features were examined as potential cues for emotion differentiation. In this study, a new type of feature parameter is proposed, which calculates energy entropy on values within selected Wavelet Packet frequency bands. The modeling and classification tasks are conducted using the classical GMM algorithm. The experiments use two data sets: the Speech Under Simulated Emotion (SUSE) data set annotated with three different emotions (angry, neutral and soft) and Berlin Emotional Speech (BES) database annotated with seven different emotions (angry, bored, disgust, fear, happy, sad and neutral). The average classification accuracy achieved for the SUSE data (74%-76%) is significantly higher than the accuracy achieved for the BES data (51%-54%). In both cases, the accuracy was significantly higher than the respective random guessing levels (33% for SUSE and 14.3% for BES).

  5. a Modified Stochastic Neighbor Embedding for Combining Multiple Features for Remote Sensing Image Classification

    NASA Astrophysics Data System (ADS)

    Zhang, L.; Zhang, L.; Tao, D.; Huang, X.

    2012-07-01

    In remote sensing image interpretation, it is important to combine multiple features of a certain pixel in both spatial and spectral domains to improve the classification accuracy, such as spectral signature, morphological property, and shape feature. Therefore, it is essential to consider the complementary property of different features and combine them in order to obtain an accurate classification rate. In this paper, we introduce a multi-feature dimension reduction algorithm under a probabilistic framework, modified stochastic neighbor embedding (MSNE). For each feature, a probability distribution is constructed based on SNE, and then we alternatively solve SNE and learn the optimal combination coefficients for different features in optimization. Compared with conventional dimension reduction strategies, the suggested algorithm can considers spectral, morphological and shape features of a pixel to achieve a physically meaningful low-dimensional feature representation by automatically learn a combination coefficient for each feature adapted to its contribution to subsequent classification. In experimental section, classification results using hyperspectral remote sensing image (HSI) show that this modified stochastic neighbor embedding can effectively improve classification performance.

  6. Interpretable exemplar-based shape classification using constrained sparse linear models

    NASA Astrophysics Data System (ADS)

    Sigurdsson, Gunnar A.; Yang, Zhen; Tran, Trac D.; Prince, Jerry L.

    2015-03-01

    Many types of diseases manifest themselves as observable changes in the shape of the affected organs. Using shape classification, we can look for signs of disease and discover relationships between diseases. We formulate the problem of shape classification in a holistic framework that utilizes a lossless scalar field representation and a non-parametric classification based on sparse recovery. This framework generalizes over certain classes of unseen shapes while using the full information of the shape, bypassing feature extraction. The output of the method is the class whose combination of exemplars most closely approximates the shape, and furthermore, the algorithm returns the most similar exemplars along with their similarity to the shape, which makes the result simple to interpret. Our results show that the method offers accurate classification between three cerebellar diseases and controls in a database of cerebellar ataxia patients. For reproducible comparison, promising results are presented on publicly available 2D datasets, including the ETH-80 dataset where the method achieves 88.4% classification accuracy.

  7. Critical thinking and accuracy of nurses' diagnoses.

    PubMed

    Lunney, Margaret

    2003-01-01

    Interpretations of patient data are complex and diverse, contributing to a risk of low accuracy nursing diagnoses. This risk is confirmed in research findings that accuracy of nurses' diagnoses varied widely from high to low. Highly accurate diagnoses are essential, however, to guide nursing interventions for the achievement of positive health outcomes. Development of critical thinking abilities is likely to improve accuracy of nurses' diagnoses. New views of critical thinking serve as a basis for critical thinking in nursing. Seven cognitive skills and ten habits of mind are identified as dimensions of critical thinking for use in the diagnostic process. Application of the cognitive skills of critical thinking illustrates the importance of using critical thinking for accuracy of nurses' diagnoses. Ten strategies are proposed for self-development of critical thinking abilities.

  8. Land cover classification of VHR airborne images for citrus grove identification

    NASA Astrophysics Data System (ADS)

    Amorós López, J.; Izquierdo Verdiguier, E.; Gómez Chova, L.; Muñoz Marí, J.; Rodríguez Barreiro, J. Z.; Camps Valls, G.; Calpe Maravilla, J.

    Managing land resources using remote sensing techniques is becoming a common practice. However, data analysis procedures should satisfy the high accuracy levels demanded by users (public or private companies and governments) in order to be extensively used. This paper presents a multi-stage classification scheme to update the citrus Geographical Information System (GIS) of the Comunidad Valenciana region (Spain). Spain is the first citrus fruit producer in Europe and the fourth in the world. In particular, citrus fruits represent 67% of the agricultural production in this region, with a total production of 4.24 million tons (campaign 2006-2007). The citrus GIS inventory, created in 2001, needs to be regularly updated in order to monitor changes quickly enough, and allow appropriate policy making and citrus production forecasting. Automatic methods are proposed in this work to facilitate this update, whose processing scheme is summarized as follows. First, an object-oriented feature extraction process is carried out for each cadastral parcel from very high spatial resolution aerial images (0.5 m). Next, several automatic classifiers (decision trees, artificial neural networks, and support vector machines) are trained and combined to improve the final classification accuracy. Finally, the citrus GIS is automatically updated if a high enough level of confidence, based on the agreement between classifiers, is achieved. This is the case for 85% of the parcels and accuracy results exceed 94%. The remaining parcels are classified by expert photo-interpreters in order to guarantee the high accuracy demanded by policy makers.

  9. RAPID COMMUNICATION: Asynchronous data-driven classification of weapon systems

    NASA Astrophysics Data System (ADS)

    Jin, Xin; Mukherjee, Kushal; Gupta, Shalabh; Ray, Asok; Phoha, Shashi; Damarla, Thyagaraju

    2009-12-01

    This communication addresses real-time weapon classification by analysis of asynchronous acoustic data, collected from microphones on a sensor network. The weapon classification algorithm consists of two parts: (i) feature extraction from time-series data using symbolic dynamic filtering (SDF), and (ii) pattern classification based on the extracted features using the language measure (LM) and support vector machine (SVM). The proposed algorithm has been tested on field data, generated by firing of two types of rifles. The results of analysis demonstrate high accuracy and fast execution of the pattern classification algorithm with low memory requirements. Potential applications include simultaneous shooter localization and weapon classification with soldier-wearable networked sensors.

  10. Soft Classification of Diffractive Interactions at the LHC

    SciTech Connect

    Kuusela, Mikael; Malmi, Eric; Orava, Risto; Vatanen, Tommi

    2011-07-15

    Multivariate machine learning techniques provide an alternative to the rapidity gap method for event-by-event identification and classification of diffraction in hadron-hadron collisions. Traditionally, such methods assign each event exclusively to a single class producing classification errors in overlap regions of data space. As an alternative to this so called hard classification approach, we propose estimating posterior probabilities of each diffractive class and using these estimates to weigh event contributions to physical observables. It is shown with a Monte Carlo study that such a soft classification scheme is able to reproduce observables such as multiplicity distributions and relative event rates with a much higher accuracy than hard classification.

  11. Remote Sensing Information Classification

    NASA Technical Reports Server (NTRS)

    Rickman, Douglas L.

    2008-01-01

    This viewgraph presentation reviews the classification of Remote Sensing data in relation to epidemiology. Classification is a way to reduce the dimensionality and precision to something a human can understand. Classification changes SCALAR data into NOMINAL data.

  12. Classification and knowledge

    NASA Technical Reports Server (NTRS)

    Kurtz, Michael J.

    1989-01-01

    Automated procedures to classify objects are discussed. The classification problem is reviewed, and the relation of epistemology and classification is considered. The classification of stellar spectra and of resolved images of galaxies is addressed.

  13. Accuracy of Pressure Sensitive Paint

    NASA Technical Reports Server (NTRS)

    Liu, Tianshu; Guille, M.; Sullivan, J. P.

    2001-01-01

    Uncertainty in pressure sensitive paint (PSP) measurement is investigated from a standpoint of system modeling. A functional relation between the imaging system output and luminescent emission from PSP is obtained based on studies of radiative energy transports in PSP and photodetector response to luminescence. This relation provides insights into physical origins of various elemental error sources and allows estimate of the total PSP measurement uncertainty contributed by the elemental errors. The elemental errors and their sensitivity coefficients in the error propagation equation are evaluated. Useful formulas are given for the minimum pressure uncertainty that PSP can possibly achieve and the upper bounds of the elemental errors to meet required pressure accuracy. An instructive example of a Joukowsky airfoil in subsonic flows is given to illustrate uncertainty estimates in PSP measurements.

  14. AVHRR channel selection for land cover classification

    USGS Publications Warehouse

    Maxwell, S.K.; Hoffer, R.M.; Chapman, P.L.

    2002-01-01

    Mapping land cover of large regions often requires processing of satellite images collected from several time periods at many spectral wavelength channels. However, manipulating and processing large amounts of image data increases the complexity and time, and hence the cost, that it takes to produce a land cover map. Very few studies have evaluated the importance of individual Advanced Very High Resolution Radiometer (AVHRR) channels for discriminating cover types, especially the thermal channels (channels 3, 4 and 5). Studies rarely perform a multi-year analysis to determine the impact of inter-annual variability on the classification results. We evaluated 5 years of AVHRR data using combinations of the original AVHRR spectral channels (1-5) to determine which channels are most important for cover type discrimination, yet stabilize inter-annual variability. Particular attention was placed on the channels in the thermal portion of the spectrum. Fourteen cover types over the entire state of Colorado were evaluated using a supervised classification approach on all two-, three-, four- and five-channel combinations for seven AVHRR biweekly composite datasets covering the entire growing season for each of 5 years. Results show that all three of the major portions of the electromagnetic spectrum represented by the AVHRR sensor are required to discriminate cover types effectively and stabilize inter-annual variability. Of the two-channel combinations, channels 1 (red visible) and 2 (near-infrared) had, by far, the highest average overall accuracy (72.2%), yet the inter-annual classification accuracies were highly variable. Including a thermal channel (channel 4) significantly increased the average overall classification accuracy by 5.5% and stabilized interannual variability. Each of the thermal channels gave similar classification accuracies; however, because of the problems in consistently interpreting channel 3 data, either channel 4 or 5 was found to be a more

  15. Arizona Vegetation Resource Inventory (AVRI) accuracy assessment

    USGS Publications Warehouse

    Szajgin, John; Pettinger, L.R.; Linden, D.S.; Ohlen, D.O.

    1982-01-01

    A quantitative accuracy assessment was performed for the vegetation classification map produced as part of the Arizona Vegetation Resource Inventory (AVRI) project. This project was a cooperative effort between the Bureau of Land Management (BLM) and the Earth Resources Observation Systems (EROS) Data Center. The objective of the accuracy assessment was to estimate (with a precision of ?10 percent at the 90 percent confidence level) the comission error in each of the eight level II hierarchical vegetation cover types. A stratified two-phase (double) cluster sample was used. Phase I consisted of 160 photointerpreted plots representing clusters of Landsat pixels, and phase II consisted of ground data collection at 80 of the phase I cluster sites. Ground data were used to refine the phase I error estimates by means of a linear regression model. The classified image was stratified by assigning each 15-pixel cluster to the stratum corresponding to the dominant cover type within each cluster. This method is known as stratified plurality sampling. Overall error was estimated to be 36 percent with a standard error of 2 percent. Estimated error for individual vegetation classes ranged from a low of 10 percent ?6 percent for evergreen woodland to 81 percent ?7 percent for cropland and pasture. Total cost of the accuracy assessment was $106,950 for the one-million-hectare study area. The combination of the stratified plurality sampling (SPS) method of sample allocation with double sampling provided the desired estimates within the required precision levels. The overall accuracy results confirmed that highly accurate digital classification of vegetation is difficult to perform in semiarid environments, due largely to the sparse vegetation cover. Nevertheless, these techniques show promise for providing more accurate information than is presently available for many BLM-administered lands.

  16. Classification effects of real and imaginary movement selective attention tasks on a P300-based brain-computer interface

    NASA Astrophysics Data System (ADS)

    Salvaris, Mathew; Sepulveda, Francisco

    2010-10-01

    Brain-computer interfaces (BCIs) rely on various electroencephalography methodologies that allow the user to convey their desired control to the machine. Common approaches include the use of event-related potentials (ERPs) such as the P300 and modulation of the beta and mu rhythms. All of these methods have their benefits and drawbacks. In this paper, three different selective attention tasks were tested in conjunction with a P300-based protocol (i.e. the standard counting of target stimuli as well as the conduction of real and imaginary movements in sync with the target stimuli). The three tasks were performed by a total of 10 participants, with the majority (7 out of 10) of the participants having never before participated in imaginary movement BCI experiments. Channels and methods used were optimized for the P300 ERP and no sensory-motor rhythms were explicitly used. The classifier used was a simple Fisher's linear discriminant. Results were encouraging, showing that on average the imaginary movement achieved a P300 versus No-P300 classification accuracy of 84.53%. In comparison, mental counting, the standard selective attention task used in previous studies, achieved 78.9% and real movement 90.3%. Furthermore, multiple trial classification results were recorded and compared, with real movement reaching 99.5% accuracy after four trials (12.8 s), imaginary movement reaching 99.5% accuracy after five trials (16 s) and counting reaching 98.2% accuracy after ten trials (32 s).

  17. Automatic approach to solve the morphological galaxy classification problem using the sparse representation technique and dictionary learning

    NASA Astrophysics Data System (ADS)

    Diaz-Hernandez, R.; Ortiz-Esquivel, A.; Peregrina-Barreto, H.; Altamirano-Robles, L.; Gonzalez-Bernal, J.

    2016-06-01

    The observation of celestial objects in the sky is a practice that helps astronomers to understand the way in which the Universe is structured. However, due to the large number of observed objects with modern telescopes, the analysis of these by hand is a difficult task. An important part in galaxy research is the morphological structure classification based on the Hubble sequence. In this research, we present an approach to solve the morphological galaxy classification problem in an automatic way by using the Sparse Representation technique and dictionary learning with K-SVD. For the tests in this work, we use a database of galaxies extracted from the Principal Galaxy Catalog (PGC) and the APM Equatorial Catalogue of Galaxies obtaining a total of 2403 useful galaxies. In order to represent each galaxy frame, we propose to calculate a set of 20 features such as Hu's invariant moments, galaxy nucleus eccentricity, gabor galaxy ratio and some other features commonly used in galaxy classification. A stage of feature relevance analysis was performed using Relief-f in order to determine which are the best parameters for the classification tests using 2, 3, 4, 5, 6 and 7 galaxy classes making signal vectors of different length values with the most important features. For the classification task, we use a 20-random cross-validation technique to evaluate classification accuracy with all signal sets achieving a score of 82.27 % for 2 galaxy classes and up to 44.27 % for 7 galaxy classes.

  18. Measures of Linguistic Accuracy in Second Language Writing Research.

    ERIC Educational Resources Information Center

    Polio, Charlene G.

    1997-01-01

    Investigates the reliability of measures of linguistic accuracy in second language writing. The study uses a holistic scale, error-free T-units, and an error classification system on the essays of English-as-a-Second-Language students and discusses why disagreements arise within a rater and between raters. (24 references) (Author/CK)

  19. Texture-Based Automated Lithological Classification Using Aeromagenetic Anomaly Images

    USGS Publications Warehouse

    Shankar, Vivek

    2009-01-01

    This report consists of a thesis submitted to the faculty of the Department of Electrical and Computer Engineering, in partial fulfillment of the requirements for the degree of Master of Science, Graduate College, The University of Arizona, 2004 Aeromagnetic anomaly images are geophysical prospecting tools frequently used in the exploration of metalliferous minerals and hydrocarbons. The amplitude and texture content of these images provide a wealth of information to geophysicists who attempt to delineate the nature of the Earth's upper crust. These images prove to be extremely useful in remote areas and locations where the minerals of interest are concealed by basin fill. Typically, geophysicists compile a suite of aeromagnetic anomaly images, derived from amplitude and texture measurement operations, in order to obtain a qualitative interpretation of the lithological (rock) structure. Texture measures have proven to be especially capable of capturing the magnetic anomaly signature of unique lithological units. We performed a quantitative study to explore the possibility of using texture measures as input to a machine vision system in order to achieve automated classification of lithological units. This work demonstrated a significant improvement in classification accuracy over random guessing based on a priori probabilities. Additionally, a quantitative comparison between the performances of five classes of texture measures in their ability to discriminate lithological units was achieved.

  20. Automatic classification of DMSA scans using an artificial neural network

    NASA Astrophysics Data System (ADS)

    Wright, J. W.; Duguid, R.; Mckiddie, F.; Staff, R. T.

    2014-04-01

    DMSA imaging is carried out in nuclear medicine to assess the level of functional renal tissue in patients. This study investigated the use of an artificial neural network to perform diagnostic classification of these scans. Using the radiological report as the gold standard, the network was trained to classify DMSA scans as positive or negative for defects using a representative sample of 257 previously reported images. The trained network was then independently tested using a further 193 scans and achieved a binary classification accuracy of 95.9%. The performance of the network was compared with three qualified expert observers who were asked to grade each scan in the 193 image testing set on a six point defect scale, from ‘definitely normal’ to ‘definitely abnormal’. A receiver operating characteristic analysis comparison between a consensus operator, generated from the scores of the three expert observers, and the network revealed a statistically significant increase (α < 0.05) in performance between the network and operators. A further result from this work was that when suitably optimized, a negative predictive value of 100% for renal defects was achieved by the network, while still managing to identify 93% of the negative cases in the dataset. These results are encouraging for application of such a network as a screening tool or quality assurance assistant in clinical practice.

  1. Automatic classification of DMSA scans using an artificial neural network.

    PubMed

    Wright, J W; Duguid, R; McKiddie, F; Staff, R T

    2014-04-07

    DMSA imaging is carried out in nuclear medicine to assess the level of functional renal tissue in patients. This study investigated the use of an artificial neural network to perform diagnostic classification of these scans. Using the radiological report as the gold standard, the network was trained to classify DMSA scans as positive or negative for defects using a representative sample of 257 previously reported images. The trained network was then independently tested using a further 193 scans and achieved a binary classification accuracy of 95.9%. The performance of the network was compared with three qualified expert observers who were asked to grade each scan in the 193 image testing set on a six point defect scale, from 'definitely normal' to 'definitely abnormal'. A receiver operating characteristic analysis comparison between a consensus operator, generated from the scores of the three expert observers, and the network revealed a statistically significant increase (α < 0.05) in performance between the network and operators. A further result from this work was that when suitably optimized, a negative predictive value of 100% for renal defects was achieved by the network, while still managing to identify 93% of the negative cases in the dataset. These results are encouraging for application of such a network as a screening tool or quality assurance assistant in clinical practice.

  2. Hierarchical classification of protein folds using a novel ensemble classifier.

    PubMed

    Lin, Chen; Zou, Ying; Qin, Ji; Liu, Xiangrong; Jiang, Yi; Ke, Caihuan; Zou, Quan

    2013-01-01

    The analysis of biological information from protein sequences is important for the study of cellular functions and interactions, and protein fold recognition plays a key role in the prediction of protein structures. Unfortunately, the prediction of protein fold patterns is challenging due to the existence of compound protein structures. Here, we processed the latest release of the Structural Classification of Proteins (SCOP, version 1.75) database and exploited novel techniques to impressively increase the accuracy of protein fold classification. The techniques proposed in this paper include ensemble classifying and a hierarchical framework, in the first layer of which similar or redundant sequences were deleted in two manners; a set of base classifiers, fused by various selection strategies, divides the input into seven classes; in the second layer of which, an analogous ensemble method is adopted to predict all protein folds. To our knowledge, it is the first time all protein folds can be intelligently detected hierarchically. Compared with prior studies, our experimental results demonstrated the efficiency and effectiveness of our proposed method, which achieved a success rate of 74.21%, which is much higher than results obtained with previous methods (ranging from 45.6% to 70.5%). When applied to the second layer of classification, the prediction accuracy was in the range between 23.13% and 46.05%. This value, which may not be remarkably high, is scientifically admirable and encouraging as compared to the relatively low counts of proteins from most fold recognition programs. The web server Hierarchical Protein Fold Prediction (HPFP) is available at http://datamining.xmu.edu.cn/software/hpfp.

  3. Hierarchical Classification of Protein Folds Using a Novel Ensemble Classifier

    PubMed Central

    Qin, Ji; Liu, Xiangrong; Jiang, Yi; Ke, Caihuan; Zou, Quan

    2013-01-01

    The analysis of biological information from protein sequences is important for the study of cellular functions and interactions, and protein fold recognition plays a key role in the prediction of protein structures. Unfortunately, the prediction of protein fold patterns is challenging due to the existence of compound protein structures. Here, we processed the latest release of the Structural Classification of Proteins (SCOP, version 1.75) database and exploited novel techniques to impressively increase the accuracy of protein fold classification. The techniques proposed in this paper include ensemble classifying and a hierarchical framework, in the first layer of which similar or redundant sequences were deleted in two manners; a set of base classifiers, fused by various selection strategies, divides the input into seven classes; in the second layer of which, an analogous ensemble method is adopted to predict all protein folds. To our knowledge, it is the first time all protein folds can be intelligently detected hierarchically. Compared with prior studies, our experimental results demonstrated the efficiency and effectiveness of our proposed method, which achieved a success rate of 74.21%, which is much higher than results obtained with previous methods (ranging from 45.6% to 70.5%). When applied to the second layer of classification, the prediction accuracy was in the range between 23.13% and 46.05%. This value, which may not be remarkably high, is scientifically admirable and encouraging as compared to the relatively low counts of proteins from most fold recognition programs. The web server Hierarchical Protein Fold Prediction (HPFP) is available at http://datamining.xmu.edu.cn/software/hpfp. PMID:23437146

  4. Classification of hyperspectral imagery for identifying fecal and ingesta contaminants

    NASA Astrophysics Data System (ADS)

    Park, Bosoon; Windham, William R.; Lawrence, Kurt C.; Smith, Douglas P.

    2004-03-01

    This paper presents the research results of the performance of classification methods for hyperspectral poultry imagery to identify fecal and ingesta contaminants on the surface of broiler carcasses. A pushbroom line-scan hyperspectral imager was used to acquire hyperspectral data with 512 narrow bands covered from 400 to 900 nm wavelengths. Three different feces from digestive tracts (duodenum, ceca, colon), and ingesta were used as contaminants. These contaminants were collected from the broiler carcasses fed by corn, milo, and wheat with soybean meals. For the selection of optimum classifier, various widely used supervised classification methods (parallelepiped, minimum distance, Mahalanobis distance, maximum likelihood, spectral angle mapper, and binary coding) were investigated. The classification accuracies ranged from 62.94% to 92.27%. The highest classification accuracy for identifying contaminants for corn fed carcasses was 92.27% with spectral angle mapper classifier. While, the classification accuracy was 82.02% with maximum likelihood method for milo fed carcasses and 91.16% accuracy was obtained for wheat fed carcasses when same classification method was used. The mean classification accuracy obtained in this study for classifying fecal and ingesta contaminants was 90.21%.

  5. Segmentation and Classification of Bone Marrow Cells Images Using Contextual Information for Medical Diagnosis of Acute Leukemias

    PubMed Central

    Reta, Carolina; Altamirano, Leopoldo; Gonzalez, Jesus A.; Diaz-Hernandez, Raquel; Peregrina, Hayde; Olmos, Ivan; Alonso, Jose E.; Lobato, Ruben

    2015-01-01

    Morphological identification of acute leukemia is a powerful tool used by hematologists to determine the family of such a disease. In some cases, experienced physicians are even able to determine the leukemia subtype of the sample. However, the identification process may have error rates up to 40% (when classifying acute leukemia subtypes) depending on the physician’s experience and the sample quality. This problem raises the need to create automatic tools that provide hematologists with a second opinion during the classification process. Our research presents a contextual analysis methodology for the detection of acute leukemia subtypes from bone marrow cells images. We propose a cells separation algorithm to break up overlapped regions. In this phase, we achieved an average accuracy of 95% in the evaluation of the segmentation process. In a second phase, we extract descriptive features to the nucleus and cytoplasm obtained in the segmentation phase in order to classify leukemia families and subtypes. We finally created a decision algorithm that provides an automatic diagnosis for a patient. In our experiments, we achieved an overall accuracy of 92% in the supervised classification of acute leukemia families, 84% for the lymphoblastic subtypes, and 92% for the myeloblastic subtypes. Finally, we achieved accuracies of 95% in the diagnosis of leukemia families and 90% in the diagnosis of leukemia subtypes. PMID:26107374

  6. Segmentation and Classification of Bone Marrow Cells Images Using Contextual Information for Medical Diagnosis of Acute Leukemias.

    PubMed

    Reta, Carolina; Altamirano, Leopoldo; Gonzalez, Jesus A; Diaz-Hernandez, Raquel; Peregrina, Hayde; Olmos, Ivan; Alonso, Jose E; Lobato, Ruben

    2015-01-01

    Morphological identification of acute leukemia is a powerful tool used by hematologists to determine the family of such a disease. In some cases, experienced physicians are even able to determine the leukemia subtype of the sample. However, the identification process may have error rates up to 40% (when classifying acute leukemia subtypes) depending on the physician's experience and the sample quality. This problem raises the need to create automatic tools that provide hematologists with a second opinion during the classification process. Our research presents a contextual analysis methodology for the detection of acute leukemia subtypes from bone marrow cells images. We propose a cells separation algorithm to break up overlapped regions. In this phase, we achieved an average accuracy of 95% in the evaluation of the segmentation process. In a second phase, we extract descriptive features to the nucleus and cytoplasm obtained in the segmentation phase in order to classify leukemia families and subtypes. We finally created a decision algorithm that provides an automatic diagnosis for a patient. In our experiments, we achieved an overall accuracy of 92% in the supervised classification of acute leukemia families, 84% for the lymphoblastic subtypes, and 92% for the myeloblastic subtypes. Finally, we achieved accuracies of 95% in the diagnosis of leukemia families and 90% in the diagnosis of leukemia subtypes.

  7. Automatic classification of small bowel mucosa alterations in celiac disease for confocal laser endomicroscopy

    NASA Astrophysics Data System (ADS)

    Boschetto, Davide; Di Claudio, Gianluca; Mirzaei, Hadis; Leong, Rupert; Grisan, Enrico

    2016-03-01

    Celiac disease (CD) is an immune-mediated enteropathy triggered by exposure to gluten and similar proteins, affecting genetically susceptible persons, increasing their risk of different complications. Small bowels mucosa damage due to CD involves various degrees of endoscopically relevant lesions, which are not easily recognized: their overall sensitivity and positive predictive values are poor even when zoom-endoscopy is used. Confocal Laser Endomicroscopy (CLE) allows skilled and trained experts to qualitative evaluate mucosa alteration such as a decrease in goblet cells density, presence of villous atrophy or crypt hypertrophy. We present a method for automatically classifying CLE images into three different classes: normal regions, villous atrophy and crypt hypertrophy. This classification is performed after a features selection process, in which four features are extracted from each image, through the application of homomorphic filtering and border identification through Canny and Sobel operators. Three different classifiers have been tested on a dataset of 67 different images labeled by experts in three classes (normal, VA and CH): linear approach, Naive-Bayes quadratic approach and a standard quadratic analysis, all validated with a ten-fold cross validation. Linear classification achieves 82.09% accuracy (class accuracies: 90.32% for normal villi, 82.35% for VA and 68.42% for CH, sensitivity: 0.68, specificity 1.00), Naive Bayes analysis returns 83.58% accuracy (90.32% for normal villi, 70.59% for VA and 84.21% for CH, sensitivity: 0.84 specificity: 0.92), while the quadratic analysis achieves a final accuracy of 94.03% (96.77% accuracy for normal villi, 94.12% for VA and 89.47% for CH, sensitivity: 0.89, specificity: 0.98).

  8. Item Selection Criteria with Practical Constraints for Computerized Classification Testing

    ERIC Educational Resources Information Center

    Lin, Chuan-Ju

    2011-01-01

    This study compares four item selection criteria for a two-category computerized classification testing: (1) Fisher information (FI), (2) Kullback-Leibler information (KLI), (3) weighted log-odds ratio (WLOR), and (4) mutual information (MI), with respect to the efficiency and accuracy of classification decision using the sequential probability…

  9. Preprocessing for classification of thermograms in breast cancer detection

    NASA Astrophysics Data System (ADS)

    Neumann, Łukasz; Nowak, Robert M.; Okuniewski, Rafał; Oleszkiewicz, Witold; Cichosz, Paweł; Jagodziński, Dariusz; Matysiewicz, Mateusz

    2016-09-01

    Performance of binary classification of breast cancer suffers from high imbalance between classes. In this article we present the preprocessing module designed to negate the discrepancy in training examples. Preprocessing module is based on standardization, Synthetic Minority Oversampling Technique and undersampling. We show how each algorithm influences classification accuracy. Results indicate that described module improves overall Area Under Curve up to 10% on the tested dataset. Furthermore we propose other methods of dealing with imbalanced datasets in breast cancer classification.

  10. On evaluating clustering procedures for use in classification

    NASA Technical Reports Server (NTRS)

    Pore, M. D.; Moritz, T. E.; Register, D. T.; Yao, S. S.; Eppler, W. G. (Principal Investigator)

    1979-01-01

    The problem of evaluating clustering algorithms and their respective computer programs for use in a preprocessing step for classification is addressed. In clustering for classification the probability of correct classification is suggested as the ultimate measure of accuracy on training data. A means of implementing this criterion and a measure of cluster purity are discussed. Examples are given. A procedure for cluster labeling that is based on cluster purity and sample size is presented.

  11. Analysis of the classification of US and Canadian intensive test sites using the Image 100 hybrid classification system

    NASA Technical Reports Server (NTRS)

    Hocutt, W. T. (Principal Investigator)

    1978-01-01

    The author has identified the following significant results. Labeling of wheat rather than total grains, particularly with only one acquisition, led to significant overestimates in some segments. The Image-100 software and procedures were written to facilitate classification of the LACIE segments but were not designed to record data for later accuracy assessment. A much better evaluation would have been possible if accuracy assessment data had been collected following each satisfactory classification.

  12. Random forests for classification in ecology.

    PubMed

    Cutler, D Richard; Edwards, Thomas C; Beard, Karen H; Cutler, Adele; Hess, Kyle T; Gibson, Jacob; Lawler, Joshua J

    2007-11-01

    Classification procedures are some of the most widely used statistical methods in ecology. Random forests (RF) is a new and powerful statistical classifier that is well established in other disciplines but is relatively unknown in ecology. Advantages of RF compared to other statistical classifiers include (1) very high classification accuracy; (2) a novel method of determining variable importance; (3) ability to model complex interactions among predictor variables; (4) flexibility to perform several types of statistical data analysis, including regression, classification, survival analysis, and unsupervised learning; and (5) an algorithm for imputing missing values. We compared the accuracies of RF and four other commonly used statistical classifiers using data on invasive plant species presence in Lava Beds National Monument, California, USA, rare lichen species presence in the Pacific Northwest, USA, and nest sites for cavity nesting birds in the Uinta Mountains, Utah, USA. We observed high classification accuracy in all applications as measured by cross-validation and, in the case of the lichen data, by independent test data, when comparing RF to other common classification methods. We also observed that the variables that RF identified as most important for classifying invasive plant species coincided with expectations based on the literature.

  13. Random forests for classification in ecology

    USGS Publications Warehouse

    Cutler, D.R.; Edwards, T.C.; Beard, K.H.; Cutler, A.; Hess, K.T.; Gibson, J.; Lawler, J.J.

    2007-01-01

    Classification procedures are some of the most widely used statistical methods in ecology. Random forests (RF) is a new and powerful statistical classifier that is well established in other disciplines but is relatively unknown in ecology. Advantages of RF compared to other statistical classifiers include (1) very high classification accuracy; (2) a novel method of determining variable importance; (3) ability to model complex interactions among predictor variables; (4) flexibility to perform several types of statistical data analysis, including regression, classification, survival analysis, and unsupervised learning; and (5) an algorithm for imputing missing values. We compared the accuracies of RF and four other commonly used statistical classifiers using data on invasive plant species presence in Lava Beds National Monument, California, USA, rare lichen species presence in the Pacific Northwest, USA, and nest sites for cavity nesting birds in the Uinta Mountains, Utah, USA. We observed high classification accuracy in all applications as measured by cross-validation and, in the case of the lichen data, by independent test data, when comparing RF to other common classification methods. We also observed that the variables that RF identified as most important for classifying invasive plant species coincided with expectations based on the literature. ?? 2007 by the Ecological Society of America.

  14. Retinal vasculature classification using novel multifractal features

    NASA Astrophysics Data System (ADS)

    Ding, Y.; Ward, W. O. C.; Duan, Jinming; Auer, D. P.; Gowland, Penny; Bai, L.

    2015-11-01

    Retinal blood vessels have been implicated in a large number of diseases including diabetic retinopathy and cardiovascular diseases, which cause damages to retinal blood vessels. The availability of retinal vessel imaging provides an excellent opportunity for monitoring and diagnosis of retinal diseases, and automatic analysis of retinal vessels will help with the processes. However, state of the art vascular analysis methods such as counting the number of branches or measuring the curvature and diameter of individual vessels are unsuitable for the microvasculature. There has been published research using fractal analysis to calculate fractal dimensions of retinal blood vessels, but so far there has been no systematic research extracting discriminant features from retinal vessels for classifications. This paper introduces new methods for feature extraction from multifractal spectra of retinal vessels for classification. Two publicly available retinal vascular image databases are used for the experiments, and the proposed methods have produced accuracies of 85.5% and 77% for classification of healthy and diabetic retinal vasculatures. Experiments show that classification with multiple fractal features produces better rates compared with methods using a single fractal dimension value. In addition to this, experiments also show that classification accuracy can be affected by the accuracy of vessel segmentation algorithms.

  15. Acne image analysis: lesion localization and classification

    NASA Astrophysics Data System (ADS)

    Abas, Fazly Salleh; Kaffenberger, Benjamin; Bikowski, Joseph; Gurcan, Metin N.

    2016-03-01

    Acne is a common skin condition present predominantly in the adolescent population, but may continue into adulthood. Scarring occurs commonly as a sequel to severe inflammatory acne. The presence of acne and resultant scars are more than cosmetic, with a significant potential to alter quality of life and even job prospects. The psychosocial effects of acne and scars can be disturbing and may be a risk factor for serious psychological concerns. Treatment efficacy is generally determined based on an invalidated gestalt by the physician and patient. However, the validated assessment of acne can be challenging and time consuming. Acne can be classified into several morphologies including closed comedones (whiteheads), open comedones (blackheads), papules, pustules, cysts (nodules) and scars. For a validated assessment, the different morphologies need to be counted independently, a method that is far too time consuming considering the limited time available for a consultation. However, it is practical to record and analyze images since dermatologists can validate the severity of acne within seconds after uploading an image. This paper covers the processes of region-ofinterest determination using entropy-based filtering and thresholding as well acne lesion feature extraction. Feature extraction methods using discrete wavelet frames and gray-level co-occurence matrix were presented and their effectiveness in separating the six major acne lesion classes were discussed. Several classifiers were used to test the extracted features. Correct classification accuracy as high as 85.5% was achieved using the binary classification tree with fourteen principle components used as descriptors. Further studies are underway to further improve the algorithm performance and validate it on a larger database.

  16. High accuracy OMEGA timekeeping

    NASA Technical Reports Server (NTRS)

    Imbier, E. A.

    1982-01-01

    The Smithsonian Astrophysical Observatory (SAO) operates a worldwide satellite tracking network which uses a combination of OMEGA as a frequency reference, dual timing channels, and portable clock comparisons to maintain accurate epoch time. Propagational charts from the U.S. Coast Guard OMEGA monitor program minimize diurnal and seasonal effects. Daily phase value publications of the U.S. Naval Observatory provide corrections to the field collected timing data to produce an averaged time line comprised of straight line segments called a time history file (station clock minus UTC). Depending upon clock location, reduced time data accuracies of between two and eight microseconds are typical.

  17. A Method for Selecting between Fisher's Linear Classification Functions and Least Absolute Deviation in Predictive Discriminant Analysis.

    ERIC Educational Resources Information Center

    Meshbane, Alice; Morris, John D.

    A method for comparing the cross-validated classification accuracy of Fisher's linear classification functions (FLCFs) and the least absolute deviation is presented under varying data conditions for the two-group classification problem. With this method, separate-group as well as total-sample proportions of current classifications can be compared…

  18. ECOD: new developments in the evolutionary classification of domains

    PubMed Central

    Schaeffer, R. Dustin; Liao, Yuxing; Cheng, Hua; Grishin, Nick V.

    2017-01-01

    Evolutionary Classification Of protein Domains (ECOD) (http://prodata.swmed.edu/ecod) comprehensively classifies protein with known spatial structures maintained by the Protein Data Bank (PDB) into evolutionary groups of protein domains. ECOD relies on a combination of automatic and manual weekly updates to achieve its high accuracy and coverage with a short update cycle. ECOD classifies the approximately 120 000 depositions of the PDB into more than 500 000 domains in ∼3400 homologous groups. We show the performance of the weekly update pipeline since the release of ECOD, describe improvements to the ECOD website and available search options, and discuss novel structures and homologous groups that have been classified in the recent updates. Finally, we discuss the future directions of ECOD and further improvements planned for the hierarchy and update process. PMID:27899594

  19. Kraken: ultrafast metagenomic sequence classification using exact alignments

    PubMed Central

    2014-01-01

    Kraken is an ultrafast and highly accurate program for assigning taxonomic labels to metagenomic DNA sequences. Previous programs designed for this task have been relatively slow and computationally expensive, forcing researchers to use faster abundance estimation programs, which only classify small subsets of metagenomic data. Using exact alignment of k-mers, Kraken achieves classification accuracy comparable to the fastest BLAST program. In its fastest mode, Kraken classifies 100 base pair reads at a rate of over 4.1 million reads per minute, 909 times faster than Megablast and 11 times faster than the abundance estimation program MetaPhlAn. Kraken is available at http://ccb.jhu.edu/software/kraken/. PMID:24580807

  20. Towards Experimental Accuracy from the First Principles

    NASA Astrophysics Data System (ADS)

    Polyansky, O. L.; Lodi, L.; Tennyson, J.; Zobov, N. F.

    2013-06-01

    Producing ab initio ro-vibrational energy levels of small, gas-phase molecules with an accuracy of 0.10 cm^{-1} would constitute a significant step forward in theoretical spectroscopy and would place calculated line positions considerably closer to typical experimental accuracy. Such an accuracy has been recently achieved for the H_3^+ molecular ion for line positions up to 17 000 cm ^{-1}. However, since H_3^+ is a two-electron system, the electronic structure methods used in this study are not applicable to larger molecules. A major breakthrough was reported in ref., where an accuracy of 0.10 cm^{-1} was achieved ab initio for seven water isotopologues. Calculated vibrational and rotational energy levels up to 15 000 cm^{-1} and J=25 resulted in a standard deviation of 0.08 cm^{-1} with respect to accurate reference data. As far as line intensities are concerned, we have already achieved for water a typical accuracy of 1% which supersedes average experimental accuracy. Our results are being actively extended along two major directions. First, there are clear indications that our results for water can be improved to an accuracy of the order of 0.01 cm^{-1} by further, detailed ab initio studies. Such level of accuracy would already be competitive with experimental results in some situations. A second, major, direction of study is the extension of such a 0.1 cm^{-1} accuracy to molecules containg more electrons or more than one non-hydrogen atom, or both. As examples of such developments we will present new results for CO, HCN and H_2S, as well as preliminary results for NH_3 and CH_4. O.L. Polyansky, A. Alijah, N.F. Zobov, I.I. Mizus, R. Ovsyannikov, J. Tennyson, L. Lodi, T. Szidarovszky and A.G. Csaszar, Phil. Trans. Royal Soc. London A, {370}, 5014-5027 (2012). O.L. Polyansky, R.I. Ovsyannikov, A.A. Kyuberis, L. Lodi, J. Tennyson and N.F. Zobov, J. Phys. Chem. A, (in press). L. Lodi, J. Tennyson and O.L. Polyansky, J. Chem. Phys. {135}, 034113 (2011).

  1. Classification of the botanical origin for Malaysian honey using UV-Vis spectroscopy

    NASA Astrophysics Data System (ADS)

    Almaleeh, Abd Alazeez; Adom, Abdul Hamid; Fathinul-Syahir, A. S.

    2017-03-01

    The aim of this study is to perform the classification of three brands of Malaysian honeys according to their botanical origin using UV-Vis Spectroscopy. The ability to classify honey according to their botanical origin is important to ensure the quality of the product. A total of nine samples from three commercial brands of honey produces were measured by a Lambda 35 UV-Vis Spectrometer. The wavelength range recorded was from 200 nm to 400 nm and used for model calibration. The (PCs) were extracted from principal components analysis (PCA), the first three (PCs) which accounted 98.03% of disparity of the spectra were combined separately with support vector machine (SVM) for the development of (PC-SVM) model, and achieved 100% discrimination accuracy. The results can be utilized in the development of device for the classification of honey accurately and rapid as well as safe guarantee to ordinary consumers.

  2. Machine Learning Approaches to Classification of Seafloor Features from High Resolution Sonar Data

    NASA Astrophysics Data System (ADS)

    Smith, D. G.; Ed, L.; Sofge, D.; Elmore, P. A.; Petry, F.

    2014-12-01

    Navigation charts provide topographic maps of the seafloor created from swaths of sonar data. Converting sonar data to a topographic map is a manual, labor-intensive process that can be greatly assisted by contextual information obtained from automated classification of geomorphological structures. Finding structures such as seamounts can be challenging, as there are no established rules that can be used for decision-making. Often times, it is a determination that is made by human expertise. A variety of feature metrics may be useful for this task and we use a large number of metrics relevant to the task of finding seamounts. We demonstrate this ability in locating seamounts by two related machine learning techniques. As well as achieving good accuracy in classification, the human-understandable set of metrics that are most important for the results are discussed.

  3. Motion data classification on the basis of dynamic time warping with a cloud point distance measure

    NASA Astrophysics Data System (ADS)

    Switonski, Adam; Josinski, Henryk; Zghidi, Hafedh; Wojciechowski, Konrad

    2016-06-01

    The paper deals with the problem of classification of model free motion data. The nearest neighbors classifier which is based on comparison performed by Dynamic Time Warping transform with cloud point distance measure is proposed. The classification utilizes both specific gait features reflected by a movements of subsequent skeleton joints and anthropometric data. To validate proposed approach human gait identification challenge problem is taken into consideration. The motion capture database containing data of 30 different humans collected in Human Motion Laboratory of Polish-Japanese Academy of Information Technology is used. The achieved results are satisfactory, the obtained accuracy of human recognition exceeds 90%. What is more, the applied cloud point distance measure does not depend on calibration process of motion capture system which results in reliable validation.

  4. Staining Pattern Classification of Antinuclear Autoantibodies Based on Block Segmentation in Indirect Immunofluorescence Images

    PubMed Central

    Li, Jiaqian; Tseng, Kuo-Kun; Hsieh, Zu Yi; Yang, Ching Wen; Huang, Huang-Nan

    2014-01-01

    Indirect immunofluorescence based on HEp-2 cell substrate is the most commonly used staining method for antinuclear autoantibodies associated with different types of autoimmune pathologies. The aim of this paper is to design an automatic system to identify the staining patterns based on block segmentation compared to the cell segmentation most used in previous research. Various feature descriptors and classifiers are tested and compared in the classification of the staining pattern of blocks and it is found that the technique of the combination of the local binary pattern and the k-nearest neighbor algorithm achieve the best performance. Relying on the results of block pattern classification, experiments on the whole images show that classifier fusion rules are able to identify the staining patterns of the whole well (specimen image) with a total accuracy of about 94.62%. PMID:25474260

  5. A novel classification method based on ICA and ELM: a case study in lie detection.

    PubMed

    Xiong, Yijun; Luo, Yu; Huang, Wentao; Zhang, Wenjia; Yang, Yong; Gao, Junfeng

    2014-01-01

    The classification of EEG tasks has drawn much attention in recent years. In this paper, a novel classification model based on independent component analysis (ICA) and Extreme learning machine (ELM) is proposed to detect lying. Firstly, ICA and its topography information were used to automatically identify the P300 ICs. Then, time and frequency-domain features were extracted from the reconstructed P3 waveforms. Finally, two classes of feature samples were used to train ELM, Back-propagation network (BPNN) and support vector machine (SVM) classifiers for comparison. The optimal number of P3 ICs and the values of classifier parameter were optimized by the cross-validation procedures. Experimental results show that the presented method (ICA_ELM) achieves the highest training accuracy of 95.40% with extremely less training and testing time on detecting P3 components for the guilty and the innocent subjects. The results indicate that the proposed method can be applied in lie detection.

  6. Study of USGS/NASA land use classification system. [computer analysis from LANDSAT data

    NASA Technical Reports Server (NTRS)

    Spann, G. W.

    1975-01-01

    The results of a computer mapping project using LANDSAT data and the USGS/NASA land use classification system are summarized. During the computer mapping portion of the project, accuracies of 67 percent to 79 percent were achieved using Level II of the classification system and a 4,000 acre test site centered on Douglasville, Georgia. Analysis of response to a questionaire circulated to actual and potential LANDSAT data users reveals several important findings: (1) there is a substantial desire for additional information related to LANDSAT capabilities; (2) a majority of the respondents feel computer mapping from LANDSAT data could aid present or future projects; and (3) the costs of computer mapping are substantially less than those of other methods.

  7. On the Automated Segmentation of Epicardial and Mediastinal Cardiac Adipose Tissues Using Classification Algorithms.

    PubMed

    Rodrigues, Érick Oliveira; Cordeiro de Morais, Felipe Fernandes; Conci, Aura

    2015-01-01

    The quantification of fat depots on the surroundings of the heart is an accurate procedure for evaluating health risk factors correlated with several diseases. However, this type of evaluation is not widely employed in clinical practice due to the required human workload. This work proposes a novel technique for the automatic segmentation of cardiac fat pads. The technique is based on applying classification algorithms to the segmentation of cardiac CT images. Furthermore, we extensively evaluate the performance of several algorithms on this task and discuss which provided better predictive models. Experimental results have shown that the mean accuracy for the classification of epicardial and mediastinal fats has been 98.4% with a mean true positive rate of 96.2%. On average, the Dice similarity index, regarding the segmented patients and the ground truth, was equal to 96.8%. Therfore, our technique has achieved the most accurate results for the automatic segmentation of cardiac fats, to date.

  8. Hierarchical image classification in the bioscience literature.

    PubMed

    Kim, Daehyun; Yu, Hong

    2009-11-14

    Our previous work has shown that images appearing in bioscience articles can be classified into five types: Gel-Image, Image-of-Thing, Graph, Model, and Mix. For this paper, we explored and analyzed features strongly associated with each image type and developed a hierarchical image classification approach for classifying an image into one of the five types. First, we applied texture features to separate images into two groups: 1) a texture group comprising Gel Image, Image-of-Thing, and Mix, and 2) a non-texture group comprising Graph and Model. We then applied entropy, skewness, and uniformity for the first group, and edge difference, uniformity, and smoothness for the second group to classify images into specific types. Our results show that hierarchical image classification accurately divided images into the two groups during the initial classification and that the overall accuracy of the image classification was higher than that of our previous approach. In particular, the recall of hierarchical image classification was greatly improved due to the high accuracy of the initial classification.

  9. Intelligent feature selection techniques for pattern classification of Lamb wave signals

    SciTech Connect

    Hinders, Mark K.; Miller, Corey A.

    2014-02-18

    Lamb wave interaction with flaws is a complex, three-dimensional phenomenon, which often frustrates signal interpretation schemes based on mode arrival time shifts predicted by dispersion curves. As the flaw severity increases, scattering and mode conversion effects will often dominate the time-domain signals, obscuring available information about flaws because multiple modes may arrive on top of each other. Even for idealized flaw geometries the scattering and mode conversion behavior of Lamb waves is very complex. Here, multi-mode Lamb waves in a metal plate are propagated across a rectangular flat-bottom hole in a sequence of pitch-catch measurements corresponding to the double crosshole tomography geometry. The flaw is sequentially deepened, with the Lamb wave measurements repeated at each flaw depth. Lamb wave tomography reconstructions are used to identify which waveforms have interacted with the flaw and thereby carry information about its depth. Multiple features are extracted from each of the Lamb wave signals using wavelets, which are then fed to statistical pattern classification algorithms that identify flaw severity. In order to achieve the highest classification accuracy, an optimal feature space is required but it’s never known a priori which features are going to be best. For structural health monitoring we make use of the fact that physical flaws, such as corrosion, will only increase over time. This allows us to identify feature vectors which are topologically well-behaved by requiring that sequential classes “line up” in feature vector space. An intelligent feature selection routine is illustrated that identifies favorable class distributions in multi-dimensional feature spaces using computational homology theory. Betti numbers and formal classification accuracies are calculated for each feature space subset to establish a correlation between the topology of the class distribution and the corresponding classification accuracy.

  10. Intelligent feature selection techniques for pattern classification of Lamb wave signals

    NASA Astrophysics Data System (ADS)

    Hinders, Mark K.; Miller, Corey A.

    2014-02-01

    Lamb wave interaction with flaws is a complex, three-dimensional phenomenon, which often frustrates signal interpretation schemes based on mode arrival time shifts predicted by dispersion curves. As the flaw severity increases, scattering and mode conversion effects will often dominate the time-domain signals, obscuring available information about flaws because multiple modes may arrive on top of each other. Even for idealized flaw geometries the scattering and mode conversion behavior of Lamb waves is very complex. Here, multi-mode Lamb waves in a metal plate are propagated across a rectangular flat-bottom hole in a sequence of pitch-catch measurements corresponding to the double crosshole tomography geometry. The flaw is sequentially deepened, with the Lamb wave measurements repeated at each flaw depth. Lamb wave tomography reconstructions are used to identify which waveforms have interacted with the flaw and thereby carry information about its depth. Multiple features are extracted from each of the Lamb wave signals using wavelets, which are then fed to statistical pattern classification algorithms that identify flaw severity. In order to achieve the highest classification accuracy, an optimal feature space is required but it's never known a priori which features are going to be best. For structural health monitoring we make use of the fact that physical flaws, such as corrosion, will only increase over time. This allows us to identify feature vectors which are topologically well-behaved by requiring that sequential classes "line up" in feature vector space. An intelligent feature selection routine is illustrated that identifies favorable class distributions in multi-dimensional feature spaces using computational homology theory. Betti numbers and formal classification accuracies are calculated for each feature space subset to establish a correlation between the topology of the class distribution and the corresponding classification accuracy.

  11. [A post-processing method of classification rule on stellar spectra].

    PubMed

    Cai, Jiang-Hui; Yang, Hai-Feng; Zhao, Xu-Jun; Zhang, Ji-Fu

    2013-01-01

    Automatic classification and analysis of observational data is of great significance along with the gradual implementation of LAMOST Survey, which will obtain a large number of spectra data. In classification rules extracted, there is often a great deal of redundancy which will reduce the classification efficiency and quality seriously. In the present paper, a post-processing method of star spectra classification rule based on predicate logic is presented by using predication to describe the classification rules and logical reasoning to eliminate redundant rules. In the end, some experimental results on LAMOST's stellar spectra data show that, with no classification accuracy reduction, the efficiency of auto classification is significantly improved.

  12. Computers vs. Humans in Galaxy Classification

    NASA Astrophysics Data System (ADS)

    Kohler, Susanna

    2016-04-01

    54% for spirals and 80% for ellipticals, the agreement is over 98%. [Kuminski et al. 2016]In addition, the classifier calculates a certainty level for each classification, with the certainties adding to 100%: a galaxy categorized as spiral at 85% certainty is categorized as elliptical at 15% certainty. This provides a quantity/quality tradeoff, allowing for the creation of subcatalogs by cutting at specific certainty levels. Selecting for a high level of certainty decreases the sample size, but increases the samples classification accuracy.Comparing the OutcomeTo evaluate the accuracy of the algorithms findings, the authors examined SDSS galaxies that had also been classified by Galaxy Zoo. In particular, they used a 45,000-galaxy subset that consists only of superclean Galaxy Zoo galaxies meaning the human volunteers who categorized them were in agreement at a level of 95% or higher.Number of spiral and elliptical galaxies classified above different certainty levels. Cutting at the 54% certainty level for spirals and 80% for ellipticals leaves ~900,000 and ~600,000 spiral and elliptical galaxies, respectively. [Kuminski et al. 2016]In this set, Kuminski and Shamir found that if they draw a cut-off at the 54% certainty level for spiral galaxies and the 80% certainty level for ellipticals, they find 98% agreement between the computer classification of the galaxies and the human classification via Galaxy Zoo. Applying these cuts to the entire sample resulted in the identification of ~900,000 spiral galaxies and ~600,000 ellipticals, representing the largest catalog of its kind.The authors acknowledge that completeness is a problem; half the data had to be cut to achieve this level of accuracy. Sacrificing some data can still result in very large catalogs, however and as surveys become more powerful and large databases become more prevalent, algorithms such as this one will likely become critical to the scientific process.CitationEvan Kuminski and Lior Shamir 2016 Ap

  13. A Cross-Culture Study in Classification Operation.

    ERIC Educational Resources Information Center

    Sintoovongse, Kingfa

    1978-01-01

    Investigates classification achievement in Thai and American children as well as children's classification achievement within cultures and across cultures at different age levels. One hundred and twenty American and Thai children from 6 to 11 years of age were randomly selected to participate in this study. (HM)

  14. A new classification scheme of plastic wastes based upon recycling labels.

    PubMed

    Özkan, Kemal; Ergin, Semih; Işık, Şahin; Işıklı, Idil

    2015-01-01

    Since recycling of materials is widely assumed to be environmentally and economically beneficial, reliable sorting and processing of waste packaging materials such as plastics is very important for recycling with high efficiency. An automated system that can quickly categorize these materials is certainly needed for obtaining maximum classification while maintaining high throughput. In this paper, first of all, the photographs of the plastic bottles have been taken and several preprocessing steps were carried out. The first preprocessing step is to extract the plastic area of a bottle from the background. Then, the morphological image operations are implemented. These operations are edge detection, noise removal, hole removing, image enhancement, and image segmentation. These morphological operations can be generally defined in terms of the combinations of erosion and dilation. The effect of bottle color as well as label are eliminated using these operations. Secondly, the pixel-wise intensity values of the plastic bottle images have been used together with the most popular subspace and statistical feature extraction methods to construct the feature vectors in this study. Only three types of plastics are considered due to higher existence ratio of them than the other plastic types in the world. The decision mechanism consists of five different feature extraction methods including as Principal Component Analysis (PCA), Kernel PCA (KPCA), Fisher's Linear Discriminant Analysis (FLDA), Singular Value Decomposition (SVD) and Laplacian Eigenmaps (LEMAP) and uses a simple experimental setup with a camera and homogenous backlighting. Due to the giving global solution for a classification problem, Support Vector Machine (SVM) is selected to achieve the classification task and majority voting technique is used as the decision mechanism. This technique equally weights each classification result and assigns the given plastic object to the class that the most classification

  15. Increasing Accuracy in Computed Inviscid Boundary Conditions

    NASA Technical Reports Server (NTRS)

    Dyson, Roger

    2004-01-01

    A technique has been devised to increase the accuracy of computational simulations of flows of inviscid fluids by increasing the accuracy with which surface boundary conditions are represented. This technique is expected to be especially beneficial for computational aeroacoustics, wherein it enables proper accounting, not only for acoustic waves, but also for vorticity and entropy waves, at surfaces. Heretofore, inviscid nonlinear surface boundary conditions have been limited to third-order accuracy in time for stationary surfaces and to first-order accuracy in time for moving surfaces. For steady-state calculations, it may be possible to achieve higher accuracy in space, but high accuracy in time is needed for efficient simulation of multiscale unsteady flow phenomena. The present technique is the first surface treatment that provides the needed high accuracy through proper accounting of higher-order time derivatives. The present technique is founded on a method known in art as the Hermitian modified solution approximation (MESA) scheme. This is because high time accuracy at a surface depends upon, among other things, correction of the spatial cross-derivatives of flow variables, and many of these cross-derivatives are included explicitly on the computational grid in the MESA scheme. (Alternatively, a related method other than the MESA scheme could be used, as long as the method involves consistent application of the effects of the cross-derivatives.) While the mathematical derivation of the present technique is too lengthy and complex to fit within the space available for this article, the technique itself can be characterized in relatively simple terms: The technique involves correction of surface-normal spatial pressure derivatives at a boundary surface to satisfy the governing equations and the boundary conditions and thereby achieve arbitrarily high orders of time accuracy in special cases. The boundary conditions can now include a potentially infinite number

  16. View-centralized multi-atlas classification for Alzheimer's disease diagnosis.

    PubMed

    Liu, Mingxia; Zhang, Daoqiang; Shen, Dinggang

    2015-05-01

    Multi-atlas based methods have been recently used for classification of Alzheimer's disease (AD) and its prodromal stage, that is, mild cognitive impairment (MCI). Compared with traditional single-atlas based methods, multiatlas based methods adopt multiple predefined atlases and thus are less biased by a certain atlas. However, most existing multiatlas based methods simply average or concatenate the features from multiple atlases, which may ignore the potentially important diagnosis information related to the anatomical differences among different atlases. In this paper, we propose a novel view (i.e., atlas) centralized multi-atlas classification method, which can better exploit useful information in multiple feature representations from different atlases. Specifically, all brain images are registered onto multiple atlases individually, to extract feature representations in each atlas space. Then, the proposed view-centralized multi-atlas feature selection method is used to select the most discriminative features from each atlas with extra guidance from other atlases. Next, we design a support vector machine (SVM) classifier using the selected features in each atlas space. Finally, we combine multiple SVM classifiers for multiple atlases through a classifier ensemble strategy for making a final decision. We have evaluated our method on 459 subjects [including 97 AD, 117 progressive MCI (p-MCI), 117 stable MCI (s-MCI), and 128 normal controls (NC)] from the Alzheimer's Disease Neuroimaging Initiative database, and achieved an accuracy of 92.51% for AD versus NC classification and an accuracy of 78.88% for p-MCI versus s-MCI classification. These results demonstrate that the proposed method can significantly outperform the previous multi-atlas based classification methods.

  17. Classification of Photogrammetric Point Clouds of Scaffolds for Construction Site Monitoring Using Subspace Clustering and PCA

    NASA Astrophysics Data System (ADS)

    Xu, Y.; Tuttas, S.; Heogner, L.; Stilla, U.

    2016-06-01

    This paper presents an approach for the classification of photogrammetric point clouds of scaffolding components in a construction site, aiming at making a preparation for the automatic monitoring of construction site by reconstructing an as-built Building Information Model (as-built BIM). The points belonging to tubes and toeboards of scaffolds will be distinguished via subspace clustering process and principal components analysis (PCA) algorithm. The overall workflow includes four essential processing steps. Initially, the spherical support region of each point is selected. In the second step, the normalized cut algorithm based on spectral clustering theory is introduced for the subspace clustering, so as to select suitable subspace clusters of points and avoid outliers. Then, in the third step, the feature of each point is calculated by measuring distances between points and the plane of local reference frame defined by PCA in cluster. Finally, the types of points are distinguished and labelled through a supervised classification method, with random forest algorithm used. The effectiveness and applicability of the proposed steps are investigated in both simulated test data and real scenario. The results obtained by the two experiments reveal that the proposed approaches are qualified to the classification of points belonging to linear shape objects having different shapes of sections. For the tests using synthetic point cloud, the classification accuracy can reach 80%, with the condition contaminated by noise and outliers. For the application in real scenario, our method can also achieve a classification accuracy of better than 63%, without using any information about the normal vector of local surface.

  18. Multiclass Classification by Adaptive Network of Dendritic Neurons with Binary Synapses Using Structural Plasticity

    PubMed Central

    Hussain, Shaista; Basu, Arindam

    2016-01-01

    The development of power-efficient neuromorphic devices presents the challenge of designing spike pattern classification algorithms which can be implemented on low-precision hardware and can also achieve state-of-the-art performance. In our pursuit of meeting this challenge, we present a pattern classification model which uses a sparse connection matrix and exploits the mechanism of nonlinear dendritic processing to achieve high classification accuracy. A rate-based structural learning rule for multiclass classification is proposed which modifies a connectivity matrix of binary synaptic connections by choosing the best “k” out of “d” inputs to make connections on every dendritic branch (k < < d). Because learning only modifies connectivity, the model is well suited for implementation in neuromorphic systems using address-event representation (AER). We develop an ensemble method which combines several dendritic classifiers to achieve enhanced generalization over individual classifiers. We have two major findings: (1) Our results demonstrate that an ensemble created with classifiers comprising moderate number of dendrites performs better than both ensembles of perceptrons and of complex dendritic trees. (2) In order to determine the moderate number of dendrites required for a specific classification problem, a two-step solution is proposed. First, an adaptive approach is proposed which scales the relative size of the dendritic trees of neurons for each class. It works by progressively adding dendrites with fixed number of synapses to the network, thereby allocating synaptic resources as per the complexity of the given problem. As a second step, theoretical capacity calculations are used to convert each neuronal dendritic tree to its optimal topology where dendrites of each class are assigned different number of synapses. The performance of the model is evaluated on classification of handwritten digits from the benchmark MNIST dataset and compared with other

  19. Multiclass Classification by Adaptive Network of Dendritic Neurons with Binary Synapses Using Structural Plasticity.

    PubMed

    Hussain, Shaista; Basu, Arindam

    2016-01-01

    The development of power-efficient neuromorphic devices presents the challenge of designing spike pattern classification algorithms which can be implemented on low-precision hardware and can also achieve state-of-the-art performance. In our pursuit of meeting this challenge, we present a pattern classification model which uses a sparse connection matrix and exploits the mechanism of nonlinear dendritic processing to achieve high classification accuracy. A rate-based structural learning rule for multiclass classification is proposed which modifies a connectivity matrix of binary synaptic connections by choosing the best "k" out of "d" inputs to make connections on every dendritic branch (k < < d). Because learning only modifies connectivity, the model is well suited for implementation in neuromorphic systems using address-event representation (AER). We develop an ensemble method which combines several dendritic classifiers to achieve enhanced generalization over individual classifiers. We have two major findings: (1) Our results demonstrate that an ensemble created with classifiers comprising moderate number of dendrites performs better than both ensembles of perceptrons and of complex dendritic trees. (2) In order to determine the moderate number of dendrites required for a specific classification problem, a two-step solution is proposed. First, an adaptive approach is proposed which scales the relative size of the dendritic trees of neurons for each class. It works by progressively adding dendrites with fixed number of synapses to the network, thereby allocating synaptic resources as per the complexity of the given problem. As a second step, theoretical capacity calculations are used to convert each neuronal dendritic tree to its optimal topology where dendrites of each class are assigned different number of synapses. The performance of the model is evaluated on classification of handwritten digits from the benchmark MNIST dataset and compared with other spike

  20. A Hybrid Machine Learning Method for Fusing fMRI and Genetic Data: Combining both Improves Classification of Schizophrenia

    PubMed Central

    Yang, Honghui; Liu, Jingyu; Sui, Jing; Pearlson, Godfrey; Calhoun, Vince D.

    2010-01-01

    We demonstrate a hybrid machine learning method to classify schizophrenia patients and healthy controls, using functional magnetic resonance imaging (fMRI) and single nucleotide polymorphism (SNP) data. The method consists of four stages: (1) SNPs with the most discriminating information between the healthy controls and schizophrenia patients are selected to construct a support vector machine ensemble (SNP-SVME). (2) Voxels in the fMRI map contributing to classification are selected to build another SVME (Voxel-SVME). (3) Components of fMRI activation obtained with independent component analysis (ICA) are used to construct a single SVM classifier (ICA-SVMC). (4) The above three models are combined into a single module using a majority voting approach to make a final decision (Combined SNP-fMRI). The method was evaluated by a fully validated leave-one-out method using 40 subjects (20 patients and 20 controls). The classification accuracy was: 0.74 for SNP-SVME, 0.82 for Voxel-SVME, 0.83 for ICA-SVMC, and 0.87 for Combined SNP-fMRI. Experimental results show that better classification accuracy was achieved by combining genetic and fMRI data than using either alone, indicating that genetic and brain function representing different, but partially complementary aspects, of schizophrenia etiopathology. This study suggests an effective way to reassess biological classification of individuals with schizophrenia, which is also potentially useful for identifying diagnostically important markers for the disorder. PMID:21119772

  1. Artificial Neural Network classification of operator workload with an assessment of time variation and noise-enhancement to increase performance.

    PubMed

    Casson, Alexander J

    2014-01-01

    Workload classification-the determination of whether a human operator is in a high or low workload state to allow their working environment to be optimized-is an emerging application of passive Brain-Computer Interface (BCI) systems. Practical systems must not only accurately detect the current workload state, but also have good temporal performance: requiring little time to set up and train the classifier, and ensuring that the reported performance level is consistent and predictable over time. This paper investigates the temporal performance of an Artificial Neural Network based classification system. For networks trained on little EEG data good classification accuracies (86%) are achieved over very short time frames, but substantial decreases in accuracy are found as the time gap between the network training and the actual use is increased. Noise-enhanced processing, where artificially generated noise is deliberately added to the testing signals, is investigated as a potential technique to mitigate this degradation without requiring the network to be re-trained using more data. Small stochastic resonance effects are demonstrated whereby the classification process gets better in the presence of more noise. The effect is small and does not eliminate the need for re-training, but it is consistent, and this is the first demonstration of such effects for non-evoked/free-running EEG signals suitable for passive BCI.

  2. Cross-correlation of EEG frequency bands and heart rate variability for sleep apnoea classification.

    PubMed

    Abdullah, Haslaile; Maddage, Namunu C; Cosic, Irena; Cvetkovic, Dean

    2010-12-01

    Sleep apnoea is a sleep breathing disorder which causes changes in cardiac and neuronal activity and discontinuities in sleep pattern when observed via electrocardiogram (ECG) and electroencephalogram (EEG). Using both statistical analysis and Gaussian discriminative modelling approaches, this paper presents a pilot study of assessing the cross-correlation between EEG frequency bands and heart rate variability (HRV) in normal and sleep apnoea clinical patients. For the study we used EEG (delta, theta, alpha, sigma and beta) and HRV (LF(nu), HF(nu) and LF/HF) features from the spectral analysis. The statistical analysis in different sleep stages highlighted that in sleep apnoea patients, the EEG delta, sigma and beta bands exhibited a strong correlation with HRV features. Then the correlation between EEG frequency bands and HRV features were examined for sleep apnoea classification using univariate and multivariate Gaussian models (UGs and MGs). The MG outperformed the UG in the classification. When EEG and HRV features were combined and modelled with MG, we achieved 64% correct classification accuracy, which is 2 or 8% improvement with respect to using only EEG or ECG features. When delta and acceleration coefficients of the EEG features were incorporated, then the overall accuracy improved to 71%.

  3. Military Vehicle Classification via Acoustic and Seismic Signals Using Statistical Learning Methods

    NASA Astrophysics Data System (ADS)

    Xiao, Hanguang; Cai, Congzhong; Chen, Yuzong

    It is a difficult and important task to classify the types of military vehicles using the acoustic and seismic signals generated by military vehicles. For improving the classification accuracy and reducing the computing time and memory size, we investigated different pre-processing technology, feature extraction and selection methods. Short Time Fourier Transform (STFT) was employed for feature extraction. Genetic Algorithms (GA) and Principal Component Analysis (PCA) were used for feature selection and extraction further. A new feature vector construction method was proposed by uniting PCA and another feature selection method. K-Nearest Neighbor Classifier (KNN) and Support Vector Machines (SVM) were used for classification. The experimental results showed the accuracies of KNN and SVM were affected obviously by the window size which was used to frame the time series of the acoustic and seismic signals. The classification results indicated the performance of SVM was superior to that of KNN. The comparison of the four feature selection and extraction methods showed the proposed method is a simple, none time-consuming, and reliable technique for feature selection and helps the classifier SVM to achieve more better results than solely using PCA, GA, or combination.

  4. Combined texture feature analysis of segmentation and classification of benign and malignant tumour CT slices.

    PubMed

    Padma, A; Sukanesh, R

    2013-01-01

    A computer software system is designed for the segmentation and classification of benign from malignant tumour slices in brain computed tomography (CT) images. This paper presents a method to find and select both the dominant run length and co-occurrence texture features of region of interest (ROI) of the tumour region of each slice to be segmented by Fuzzy c means clustering (FCM) and evaluate the performance of support vector machine (SVM)-based classifiers in classifying benign and malignant tumour slices. Two hundred and six tumour confirmed CT slices are considered in this study. A total of 17 texture features are extracted by a feature extraction procedure, and six features are selected using Principal Component Analysis (PCA). This study constructed the SVM-based classifier with the selected features and by comparing the segmentation results with the experienced radiologist labelled ground truth (target). Quantitative analysis between ground truth and segmented tumour is presented in terms of segmentation accuracy, segmentation error and overlap similarity measures such as the Jaccard index. The classification performance of the SVM-based classifier with the same selected features is also evaluated using a 10-fold cross-validation method. The proposed system provides some newly found texture features have an important contribution in classifying benign and malignant tumour slices efficiently and accurately with less computational time. The experimental results showed that the proposed system is able to achieve the highest segmentation and classification accuracy effectiveness as measured by jaccard index and sensitivity and specificity.

  5. A Transform-Based Feature Extraction Approach for Motor Imagery Tasks Classification.

    PubMed

    Baali, Hamza; Khorshidtalab, Aida; Mesbah, Mostefa; Salami, Momoh J E

    2015-01-01

    In this paper, we present a new motor imagery classification method in the context of electroencephalography (EEG)-based brain-computer interface (BCI). This method uses a signal-dependent orthogonal transform, referred to as linear prediction singular value decomposition (LP-SVD), for feature extraction. The transform defines the mapping as the left singular vectors of the LP coefficient filter impulse response matrix. Using a logistic tree-based model classifier; the extracted features are classified into one of four motor imagery movements. The proposed approach was first benchmarked against two related state-of-the-art feature extraction approaches, namely, discrete cosine transform (DCT) and adaptive autoregressive (AAR)-based methods. By achieving an accuracy of 67.35%, the LP-SVD approach outperformed the other approaches by large margins (25% compared with DCT and 6 % compared with AAR-based methods). To further improve the discriminatory capability of the extracted features and reduce the computational complexity, we enlarged the extracted feature subset by incorporating two extra features, namely, Q- and the Hotelling's [Formula: see text] statistics of the transformed EEG and introduced a new EEG channel selection method. The performance of the EEG classification based on the expanded feature set and channel selection method was compared with that of a number of the state-of-the-art classification methods previously reported with the BCI IIIa competition data set. Our method came second with an average accuracy of 81.38%.

  6. Automatic classification and pattern discovery in high-throughput protein crystallization trials.

    PubMed

    Cumbaa, Christian; Jurisica, Igor

    2005-01-01

    Conceptually, protein crystallization can be divided into two phases search and optimization. Robotic protein crystallization screening can speed up the search phase, and has a potential to increase process quality. Automated image classification helps to increase throughput and consistently generate objective results. Although the classification accuracy can always be improved, our image analysis system can classify images from 1,536-well plates with high classification accuracy (85%) and ROC score (0.87), as evaluated on 127 human-classified protein screens containing 5,600 crystal images and 189,472 non-crystal images. Data mining can integrate results from high-throughput screens with information about crystallizing conditions, intrinsic protein properties, and results from crystallization optimization. We apply association mining, a data mining approach that identifies frequently occurring patterns among variables and their values. This approach segregates proteins into groups based on how they react in a broad range of conditions, and clusters cocktails to reflect their potential to achieve crystallization. These results may lead to crystallization screen optimization, and reveal associations between protein properties and crystallization conditions. We also postulate that past experience may lead us to the identification of initial conditions favorable to crystallization for novel proteins.

  7. Robotic Rock Classification

    NASA Technical Reports Server (NTRS)

    Hebert, Martial

    1999-01-01

    This report describes a three-month research program undertook jointly by the Robotics Institute at Carnegie Mellon University and Ames Research Center as part of the Ames' Joint Research Initiative (JRI.) The work was conducted at the Ames Research Center by Mr. Liam Pedersen, a graduate student in the CMU Ph.D. program in Robotics under the supervision Dr. Ted Roush at the Space Science Division of the Ames Research Center from May 15 1999 to August 15, 1999. Dr. Martial Hebert is Mr. Pedersen's research adviser at CMU and is Principal Investigator of this Grant. The goal of this project is to investigate and implement methods suitable for a robotic rover to autonomously identify rocks and minerals in its vicinity, and to statistically characterize the local geological environment. Although primary sensors for these tasks are a reflection spectrometer and color camera, the goal is to create a framework under which data from multiple sensors, and multiple readings on the same object, can be combined in a principled manner. Furthermore, it is envisioned that knowledge of the local area, either a priori or gathered by the robot, will be used to improve classification accuracy. The key results obtained during this project are: The continuation of the development of a rock classifier; development of theoretical statistical methods; development of methods for evaluating and selecting sensors; and experimentation with data mining techniques on the Ames spectral library. The results of this work are being applied at CMU, in particular in the context of the Winter 99 Antarctica expedition in which the classification techniques will be used on the Nomad robot. Conversely, the software developed based on those techniques will continue to be made available to NASA Ames and the data collected from the Nomad experiments will also be made available.

  8. Accuracy assessment of NLCD 2006 land cover and impervious surface

    USGS Publications Warehouse

    Wickham, James D.; Stehman, Stephen V.; Gass, Leila; Dewitz, Jon; Fry, Joyce A.; Wade, Timothy G.

    2013-01-01

    Release of NLCD 2006 provides the first wall-to-wall land-cover change database for the conterminous United States from Landsat Thematic Mapper (TM) data. Accuracy assessment of NLCD 2006 focused on four primary products: 2001 land cover, 2006 land cover, land-cover change between 2001 and 2006, and impervious surface change between 2001 and 2006. The accuracy assessment was conducted by selecting a stratified random sample of pixels with the reference classification interpreted from multi-temporal high resolution digital imagery. The NLCD Level II (16 classes) overall accuracies for the 2001 and 2006 land cover were 79% and 78%, respectively, with Level II user's accuracies exceeding 80% for water, high density urban, all upland forest classes, shrubland, and cropland for both dates. Level I (8 classes) accuracies were 85% for NLCD 2001 and 84% for NLCD 2006. The high overall and user's accuracies for the individual dates translated into high user's accuracies for the 2001–2006 change reporting themes water gain and loss, forest loss, urban gain, and the no-change reporting themes for water, urban, forest, and agriculture. The main factor limiting higher accuracies for the change reporting themes appeared to be difficulty in distinguishing the context of grass. We discuss the need for more research on land-cover change accuracy assessment.

  9. Thematic Accuracy Assessment of the 2011 National Land ...

    EPA Pesticide Factsheets

    Accuracy assessment is a standard protocol of National Land Cover Database (NLCD) mapping. Here we report agreement statistics between map and reference labels for NLCD 2011, which includes land cover for ca. 2001, ca. 2006, and ca. 2011. The two main objectives were assessment of agreement between map and reference labels for the three, single-date NLCD land cover products at Level II and Level I of the classification hierarchy, and agreement for 17 land cover change reporting themes based on Level I classes (e.g., forest loss; forest gain; forest, no change) for three change periods (2001–2006, 2006–2011, and 2001–2011). The single-date overall accuracies were 82%, 83%, and 83% at Level II and 88%, 89%, and 89% at Level I for 2011, 2006, and 2001, respectively. Many class-specific user's accuracies met or exceeded a previously established nominal accuracy benchmark of 85%. Overall accuracies for 2006 and 2001 land cover components of NLCD 2011 were approximately 4% higher (at Level II and Level I) than the overall accuracies for the same components of NLCD 2006. The high Level I overall, user's, and producer's accuracies for the single-date eras in NLCD 2011 did not translate into high class-specific user's and producer's accuracies for many of the 17 change reporting themes. User's accuracies were high for the no change reporting themes, commonly exceeding 85%, but were typically much lower for the reporting themes that represented change. Only forest l

  10. Radiocarbon dating accuracy improved

    NASA Astrophysics Data System (ADS)

    Scientists have extended the accuracy of carbon-14 (14C) dating by correlating dates older than 8,000 years with uranium-thorium dates that span from 8,000 to 30,000 years before present (ybp, present = 1950). Edouard Bard, Bruno Hamelin, Richard Fairbanks and Alan Zindler, working at Columbia University's Lamont-Doherty Geological Observatory, dated corals from reefs off Barbados using both 14C and uranium-234/thorium-230 by thermal ionization mass spectrometry techniques. They found that the two age data sets deviated in a regular way, allowing the scientists to correlate the two sets of ages. The 14C dates were consistently younger than those determined by uranium-thorium, and the discrepancy increased to about 3,500 years at 20,000 ybp.

  11. Multiple Spectral-Spatial Classification Approach for Hyperspectral Data

    NASA Technical Reports Server (NTRS)

    Tarabalka, Yuliya; Benediktsson, Jon Atli; Chanussot, Jocelyn; Tilton, James C.

    2010-01-01

    A .new multiple classifier approach for spectral-spatial classification of hyperspectral images is proposed. Several classifiers are used independently to classify an image. For every pixel, if all the classifiers have assigned this pixel to the same class, the pixel is kept as a marker, i.e., a seed of the spatial region, with the corresponding class label. We propose to use spectral-spatial classifiers at the preliminary step of the marker selection procedure, each of them combining the results of a pixel-wise classification and a segmentation map. Different segmentation methods based on dissimilar principles lead to different classification results. Furthermore, a minimum spanning forest is built, where each tree is rooted on a classification -driven marker and forms a region in the spectral -spatial classification: map. Experimental results are presented for two hyperspectral airborne images. The proposed method significantly improves classification accuracies, when compared to previously proposed classification techniques.

  12. Sugarcane Land Classification with Satellite Imagery using Logistic Regression Model

    NASA Astrophysics Data System (ADS)

    Henry, F.; Herwindiati, D. E.; Mulyono, S.; Hendryli, J.

    2017-03-01

    This paper discusses the classification of sugarcane plantation area from Landsat-8 satellite imagery. The classification process uses binary logistic regression method with time series data of normalized difference vegetation index as input. The process is divided into two steps: training and classification. The purpose of training step is to identify the best parameter of the regression model using gradient descent algorithm. The best fit of the model can be utilized to classify sugarcane and non-sugarcane area. The experiment shows high accuracy and successfully maps the sugarcane plantation area which obtained best result of Cohen’s Kappa value 0.7833 (strong) with 89.167% accuracy.

  13. Automatic Spectral Classification of Unresolved Binary Stars

    NASA Astrophysics Data System (ADS)

    Weaver, W. B.

    2000-12-01

    An artificial neural network (ANN) technique has been developed to perform two-dimensional classification of the components of binary stars of any temperature or luminosity classifications. Using 15 Angstrom-resolution spectra, a single ANN can classify the unresolved components with an average accuracy of 2.5 subclasses in temperature and about 0.45 classes in luminostiy for up to 3 magnitudes difference in luminosity. The use of two ANNs, the first providing coarse classification while the second provides specialist classification, reduces the mean absolute errors to about 0.5 subclasses in temperature and 0.33 classes in luminosity. The system operates with no human intervention except initial wavelength registration and can classify about 20 binaries per second on a Pentium-class computer. This research was supported by the Friends of MIRA.

  14. Multiclass Classification for the Differential Diagnosis on the ADHD Subtypes Using Recursive Feature Elimination and Hierarchical Extreme Learning Machine: Structural MRI Study

    PubMed Central

    Qureshi, Muhammad Naveed Iqbal; Min, Beomjun; Jo, Hang Joon; Lee, Boreom

    2016-01-01

    The classification of neuroimaging data for the diagnosis of certain brain diseases is one of the main research goals of the neuroscience and clinical communities. In this study, we performed multiclass classification using a hierarchical extreme learning machine (H-ELM) classifier. We compared the performance of this classifier with that of a support vector machine (SVM) and basic extreme learning machine (ELM) for cortical MRI data from attention deficit/hyperactivity disorder (ADHD) patients. We used 159 structural MRI images of children from the publicly available ADHD-200 MRI dataset. The data consisted of three types, namely, typically developing (TDC), ADHD-inattentive (ADHD-I), and ADHD-combined (ADHD-C). We carried out feature selection by using standard SVM-based recursive feature elimination (RFE-SVM) that enabled us to achieve good classification accuracy (60.78%). In this study, we found the RFE-SVM feature selection approach in combination with H-ELM to effectively enable the acquisition of high multiclass classification accuracy rates for structural neuroimaging data. In addition, we found that the most important features for classification were the surface area of the superior frontal lobe, and the cortical thickness, volume, and mean surface area of the whole cortex. PMID:27500640

  15. Multiclass Classification for the Differential Diagnosis on the ADHD Subtypes Using Recursive Feature Elimination and Hierarchical Extreme Learning Machine: Structural MRI Study.

    PubMed

    Qureshi, Muhammad Naveed Iqbal; Min, Beomjun; Jo, Hang Joon; Lee, Boreom

    2016-01-01

    The classification of neuroimaging data for the diagnosis of certain brain diseases is one of the main research goals of the neuroscience and clinical communities. In this study, we performed multiclass classification using a hierarchical extreme learning machine (H-ELM) classifier. We compared the performance of this classifier with that of a support vector machine (SVM) and basic extreme learning machine (ELM) for cortical MRI data from attention deficit/hyperactivity disorder (ADHD) patients. We used 159 structural MRI images of children from the publicly available ADHD-200 MRI dataset. The data consisted of three types, namely, typically developing (TDC), ADHD-inattentive (ADHD-I), and ADHD-combined (ADHD-C). We carried out feature selection by using standard SVM-based recursive feature elimination (RFE-SVM) that enabled us to achieve good classification accuracy (60.78%). In this study, we found the RFE-SVM feature selection approach in combination with H-ELM to effectively enable the acquisition of high multiclass classification accuracy rates for structural neuroimaging data. In addition, we found that the most important features for classification were the surface area of the superior frontal lobe, and the cortical thickness, volume, and mean surface area of the whole cortex.

  16. Stratifying land use/land cover for spatial analysis of disease ecology and risk: an example using object-based classification techniques.

    PubMed

    Koch, David E; Mohler, Rhett L; Goodin, Douglas G

    2007-11-01

    Landscape epidemiology has made significant strides recently, driven in part by increasing availability of land cover data derived from remotely-sensed imagery. Using an example from a study of land cover effects on hantavirus dynamics at an Atlantic Forest site in eastern Paraguay, we demonstrate how automated classification methods can be used to stratify remotely-sensed land cover for studies of infectious disease dynamics. For this application, it was necessary to develop a scheme that could yield both land cover and land use data from the same classification. Hypothesizing that automated discrimination between classes would be more accurate using an object-based method compared to a per-pixel method, we used a single Landsat Enhanced Thematic Mapper+ (ETM+) image to classify land cover into eight classes using both per-pixel and object-based classification algorithms. Our results show that the object-based method achieves 84% overall accuracy, compared to only 43% using the per-pixel method. Producer's and user's accuracies for the object-based map were higher for every class compared to the per-pixel classification. The Kappa statistic was also significantly higher for the object-based classification. These results show the importance of using image information from domains beyond the spectral domain, and also illustrate the importance of object-based techniques for remote sensing applications in epidemiological studies.

  17. Epileptic seizure classifications of single-channel scalp EEG data using wavelet-based features and SVM.

    PubMed

    Janjarasjitt, Suparerk

    2017-02-13

    In this study, wavelet-based features of single-channel scalp EEGs recorded from subjects with intractable seizure are examined for epileptic seizure classification. The wavelet-based features extracted from scalp EEGs are simply based on detail and approximation coefficients obtained from the discrete wavelet transform. Support vector machine (SVM), one of the most commonly used classifiers, is applied to classify vectors of wavelet-based features of scalp EEGs into either seizure or non-seizure class. In patient-based epileptic seizure classification, a training data set used to train SVM classifiers is composed of wavelet-based features of scalp EEGs corresponding to the first epileptic seizure event. Overall, the excellent performance on patient-dependent epileptic seizure classification is obtained with the average accuracy, sensitivity, and specificity of, respectively, 0.9687, 0.7299, and 0.9813. The vector composed of two wavelet-based features of scalp EEGs provide the best performance on patient-dependent epileptic seizure classification in most cases, i.e., 19 cases out of 24. The wavelet-based features corresponding to the 32-64, 8-16, and 4-8 Hz subbands of scalp EEGs are the mostly used features providing the best performance on patient-dependent classification. Furthermore, the performance on both patient-dependent and patient-independent epileptic seizure classifications are also validated using tenfold cross-validation. From the patient-independent epileptic seizure classification validated using tenfold cross-validation, it is shown that the best classification performance is achieved using the wavelet-based features corresponding to the 64-128 and 4-8 Hz subbands of scalp EEGs.

  18. Algorithms for Hyperspectral Endmember Extraction and Signature Classification with Morphological Dendritic Networks

    NASA Astrophysics Data System (ADS)

    Schmalz, M.; Ritter, G.

    Accurate multispectral or hyperspectral signature classification is key to the nonimaging detection and recognition of space objects. Additionally, signature classification accuracy depends on accurate spectral endmember determination [1]. Previous approaches to endmember computation and signature classification were based on linear operators or neural networks (NNs) expressed in terms of the algebra (R, +, x) [1,2]. Unfortunately, class separation in these methods tends to be suboptimal, and the number of signatures that can be accurately classified often depends linearly on the number of NN inputs. This can lead to poor endmember distinction, as well as potentially significant classification errors in the presence of noise or densely interleaved signatures. In contrast to traditional CNNs, autoassociative morphological memories (AMM) are a construct similar to Hopfield autoassociatived memories defined on the (R, +, ?,?) lattice algebra [3]. Unlimited storage and perfect recall of noiseless real valued patterns has been proven for AMMs [4]. However, AMMs suffer from sensitivity to specific noise models, that can be characterized as erosive and dilative noise. On the other hand, the prior definition of a set of endmembers corresponds to material spectra lying on vertices of the minimum convex region covering the image data. These vertices can be characterized as morphologically independent patterns. It has further been shown that AMMs can be based on dendritic computation [3,6]. These techniques yield improved accuracy and class segmentation/separation ability in the presence of highly interleaved signature data. In this paper, we present a procedure for endmember determination based on AMM noise sensitivity, which employs morphological dendritic computation. We show that detected endmembers can be exploited by AMM based classification techniques, to achieve accurate signature classification in the presence of noise, closely spaced or interleaved signatures, and

  19. Spatial Classification of Orchards and Vineyards with High Spatial Resolution Panchromatic Imagery

    SciTech Connect

    Warner, Timothy; Steinmaus, Karen L.

    2005-02-01

    New high resolution single spectral band imagery offers the capability to conduct image classifications based on spatial patterns in imagery. A classification algorithm based on autocorrelation patterns was developed to automatically extract orchards and vineyards from satellite imagery. The algorithm was tested on IKONOS imagery over Granger, WA, which resulted in a classification accuracy of 95%.

  20. Toward automated classification of consumers' cancer-related questions with a new taxonomy of expected answer types.

    PubMed

    McRoy, Susan; Jones, Sean; Kurmally, Adam

    2016-09-01

    This article examines methods for automated question classification applied to cancer-related questions that people have asked on the web. This work is part of a broader effort to provide automated question answering for health education. We created a new corpus of consumer-health questions related to cancer and a new taxonomy for those questions. We then compared the effectiveness of different statistical methods for developing classifiers, including weighted classification and resampling. Basic methods for building classifiers were limited by the high variability in the natural distribution of questions and typical refinement approaches of feature selection and merging categories achieved only small improvements to classifier accuracy. Best performance was achieved using weighted classification and resampling methods, the latter yielding an accuracy of F1 = 0.963. Thus, it would appear that statistical classifiers can be trained on natural data, but only if natural distributions of classes are smoothed. Such classifiers would be useful for automated question answering, for enriching web-based content, or assisting clinical professionals to answer questions.

  1. Prediction of Rate Constants for Catalytic Reactions with Chemical Accuracy.

    PubMed

    Catlow, C Richard A

    2016-08-01

    Ex machina: A computational method for predicting rate constants for reactions within microporous zeolite catalysts with chemical accuracy has recently been reported. A key feature of this method is a stepwise QM/MM approach that allows accuracy to be achieved while using realistic models with accessible computer resources.

  2. Improved algorithms for the classification of rough rice using a bionic electronic nose based on PCA and the Wilks distribution.

    PubMed

    Xu, Sai; Zhou, Zhiyan; Lu, Huazhong; Luo, Xiwen; Lan, Yubin

    2014-03-19

    Principal Component Analysis (PCA) is one of the main methods used for electronic nose pattern recognition. However, poor classification performance is common in classification and recognition when using regular PCA. This paper aims to improve the classification performance of regular PCA based on the existing Wilks Λ-statistic (i.e., combined PCA with the Wilks distribution). The improved algorithms, which combine regular PCA with the Wilks Λ-statistic, were developed after analysing the functionality and defects of PCA. Verification tests were conducted using a PEN3 electronic nose. The collected samples consisted of the volatiles of six varieties of rough rice (Zhongxiang1, Xiangwan13, Yaopingxiang, WufengyouT025, Pin 36, and Youyou122), grown in same area and season. The first two principal components used as analysis vectors cannot perform the rough rice varieties classification task based on a regular PCA. Using the improved algorithms, which combine the regular PCA with the Wilks Λ-statistic, many different principal components were selected as analysis vectors. The set of data points of the Mahalanobis distance between each of the varieties of rough rice was selected to estimate the performance of the classification. The result illustrates that the rough rice varieties classification task is achieved well using the improved algorithm. A Probabilistic Neural Networks (PNN) was also established to test the effectiveness of the improved algorithms. The first two principal components (namely PC1 and PC2) and the first and fifth principal component (namely PC1 and PC5) were selected as the inputs of PNN for the classification of the six rough rice varieties. The results indicate that the classification accuracy based on the improved algorithm was improved by 6.67% compared to the results of the regular method. These results prove the effectiveness of using the Wilks Λ-statistic to improve the classification accuracy of the regular PCA approach. The results

  3. Classification of Urban Feature from Unmanned Aerial Vehicle Images Using Gasvm Integration and Multi-Scale Segmentation

    NASA Astrophysics Data System (ADS)

    Modiri, M.; Salehabadi, A.; Mohebbi, M.; Hashemi, A. M.; Masumi, M.

    2015-12-01

    The use of UAV in the application of photogrammetry to obtain cover images and achieve the main objectives of the photogrammetric mapping has been a boom in the region. The images taken from REGGIOLO region in the province of, Italy Reggio -Emilia by UAV with non-metric camera Canon Ixus and with an average height of 139.42 meters were used to classify urban feature. Using the software provided SURE and cover images of the study area, to produce dense point cloud, DSM and Artvqvtv spatial resolution of 10 cm was prepared. DTM area using Adaptive TIN filtering algorithm was developed. NDSM area was prepared with using the difference between DSM and DTM and a separate features in the image stack. In order to extract features, using simultaneous occurrence matrix features mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment, and correlation for each of the RGB band image was used Orthophoto area. Classes used to classify urban problems, including buildings, trees and tall vegetation, grass and vegetation short, paved road and is impervious surfaces. Class consists of impervious surfaces such as pavement conditions, the cement, the car, the roof is stored. In order to pixel-based classification and selection of optimal features of classification was GASVM pixel basis. In order to achieve the classification results with higher accuracy and spectral composition informations, texture, and shape conceptual image featureOrthophoto area was fencing. The segmentation of multi-scale segmentation method was used.it belonged class. Search results using the proposed classification of urban feature, suggests the suitability of this method of classification complications UAV is a city using images. The overall accuracy and kappa coefficient method proposed in this study, respectively, 47/93% and 84/91% was.

  4. Multiple Hypotheses Image Segmentation and Classification With Application to Dietary Assessment

    PubMed Central

    Zhu, Fengqing; Bosch, Marc; Khanna, Nitin; Boushey, Carol J.; Delp, Edward J.

    2016-01-01

    We propose a method for dietary assessment to automatically identify and locate food in a variety of images captured during controlled and natural eating events. Two concepts are combined to achieve this: a set of segmented objects can be partitioned into perceptually similar object classes based on global and local features; and perceptually similar object classes can be used to assess the accuracy of image segmentation. These ideas are implemented by generating multiple segmentations of an image to select stable segmentations based on the classifier’s confidence score assigned to each segmented image region. Automatic segmented regions are classified using a multichannel feature classification system. For each segmented region, multiple feature spaces are formed. Feature vectors in each of the feature spaces are individually classified. The final decision is obtained by combining class decisions from individual feature spaces using decision rules. We show improved accuracy of segmenting food images with classifier feedback. PMID:25561457

  5. Comparison of classification methods for P300 brain-computer interface on disabled subjects.

    PubMed

    Manyakov, Nikolay V; Chumerin, Nikolay; Combaz, Adrien; Van Hulle, Marc M

    2011-01-01

    We report on tests with a mind typing paradigm based on a P300 brain-computer interface (BCI) on a group of amyotrophic lateral sclerosis (ALS), middle cerebral artery (MCA) stroke, and subarachnoid hemorrhage (SAH) patients, suffering from motor and speech disabilities. We investigate the achieved typing accuracy given the individual patient's disorder, and how it correlates with the type of classifier used. We considered 7 types of classifiers, linear as well as nonlinear ones, and found that, overall, one type of linear classifier yielded a higher classification accuracy. In addition to the selection of the classifier, we also suggest and discuss a number of recommendations to be considered when building a P300-based typing system for disabled subjects.

  6. Land Cover Classification Using ALOS Imagery For Penang, Malaysia

    NASA Astrophysics Data System (ADS)

    Sim, C. K.; Abdullah, K.; MatJafri, M. Z.; Lim, H. S.

    2014-02-01

    This paper presents the potential of integrating optical and radar remote sensing data to improve automatic land cover mapping. The analysis involved standard image processing, and consists of spectral signature extraction and application of a statistical decision rule to identify land cover categories. A maximum likelihood classifier is utilized to determine different land cover categories. Ground reference data from sites throughout the study area are collected for training and validation. The land cover information was extracted from the digital data using PCI Geomatica 10.3.2 software package. The variations in classification accuracy due to a number of radar imaging processing techniques are studied. The relationship between the processing window and the land classification is also investigated. The classification accuracies from the optical and radar feature combinations are studied. Our research finds that fusion of radar and optical significantly improved classification accuracies. This study indicates that the land cover/use can be mapped accurately by using this approach.

  7. How Predictable are “Spontaneous Decisions” and “Hidden Intentions”? Comparing Classification Results Based on Previous Responses with Multivariate Pattern Analysis of fMRI BOLD Signals

    PubMed Central

    Lages, Martin; Jaworska, Katarzyna

    2012-01-01

    In two replication studies we examined response bias and dependencies in voluntary decisions. We trained a linear classifier to predict “spontaneous decisions” and in the second study “hidden intentions” from responses in preceding trials and achieved comparable prediction accuracies as reported for multivariate pattern classification based on voxel activities in frontopolar cortex. We discuss implications of our findings and suggest ways to improve classification analyses of fMRI BOLD signals that may help to reduce effects of response dependencies between trials. PMID:22408630

  8. EEG error potentials detection and classification using time-frequency features for robot reinforcement learning.

    PubMed

    Boubchir, Larbi; Touati, Youcef; Daachi, Boubaker; Chérif, Arab Ali

    2015-08-01

    In thought-based steering of robots, error potentials (ErrP) can appear when the action resulting from the brain-machine interface (BMI) classifier/controller does not correspond to the user's thought. Using the Steady State Visual Evoked Potentials (SSVEP) techniques, ErrP, which appear when a classification error occurs, are not easily recognizable by only examining the temporal or frequency characteristics of EEG signals. A supplementary classification process is therefore needed to identify them in order to stop the course of the action and back up to a recovery state. This paper presents a set of time-frequency (t-f) features for the detection and classification of EEG ErrP in extra-brain activities due to misclassification observed by a user exploiting non-invasive BMI and robot control in the task space. The proposed features are able to characterize and detect ErrP activities in the t-f domain. These features are derived from the information embedded in the t-f representation of EEG signals, and include the Instantaneous Frequency (IF), t-f information complexity, SVD information, energy concentration and sub-bands' energies. The experiment results on real EEG data show that the use of the proposed t-f features for detecting and classifying EEG ErrP achieved an overall classification accuracy up to 97% for 50 EEG segments using 2-class SVM classifier.

  9. Classification of Cancer Primary Sites Using Machine Learning and Somatic Mutations.

    PubMed

    Chen, Yukun; Sun, Jingchun; Huang, Liang-Chin; Xu, Hua; Zhao, Zhongming

    2015-01-01

    An accurate classification of human cancer, including its primary site, is important for better understanding of cancer and effective therapeutic strategies development. The available big data of somatic mutations provides us a great opportunity to investigate cancer classification using machine learning. Here, we explored the patterns of 1,760,846 somatic mutations identified from 230,255 cancer patients along with gene function information using support vector machine. Specifically, we performed a multiclass classification experiment over the 17 tumor sites using the gene symbol, somatic mutation, chromosome, and gene functional pathway as predictors for 6,751 subjects. The performance of the baseline using only gene features is 0.57 in accuracy. It was improved to 0.62 when adding the information of mutation and chromosome. Among the predictable primary tumor sites, the prediction of five primary sites (large intestine, liver, skin, pancreas, and lung) could achieve the performance with more than 0.70 in F-measure. The model of the large intestine ranked the first with 0.87 in F-measure. The results demonstrate that the somatic mutation information is useful for prediction of primary tumor sites with machine learning modeling. To our knowledge, this study is the first investigation of the primary sites classification using machine learning and somatic mutation data.

  10. 3D texture analysis for classification of second harmonic generation images of human ovarian cancer

    PubMed Central

    Wen, Bruce; Campbell, Kirby R.; Tilbury, Karissa; Nadiarnykh, Oleg; Brewer, Molly A.; Patankar, Manish; Singh, Vikas; Eliceiri, Kevin. W.; Campagnola, Paul J.

    2016-01-01

    Remodeling of the collagen architecture in the extracellular matrix (ECM) has been implicated in ovarian cancer. To quantify these alterations we implemented a form of 3D texture analysis to delineate the fibrillar morphology observed in 3D Second Harmonic Generation (SHG) microscopy image data of normal (1) and high risk (2) ovarian stroma, benign ovarian tumors (3), low grade (4) and high grade (5) serous tumors, and endometrioid tumors (6). We developed a tailored set of 3D filters which extract textural features in the 3D image sets to build (or learn) statistical models of each tissue class. By applying k-nearest neighbor classification using these learned models, we achieved 83–91% accuracies for the six classes. The 3D method outperformed the analogous 2D classification on the same tissues, where we suggest this is due the increased information content. This classification based on ECM structural changes will complement conventional classification based on genetic profiles and can serve as an additional biomarker. Moreover, the texture analysis algorithm is quite general, as it does not rely on single morphological metrics such as fiber alignment, length, and width but their combined convolution with a customizable basis set. PMID:27767180

  11. A contour-based shape descriptor for biomedical image classification and retrieval

    NASA Astrophysics Data System (ADS)

    You, Daekeun; Antani, Sameer; Demner-Fushman, Dina; Thoma, George R.

    2013-12-01

    Contours, object blobs, and specific feature points are utilized to represent object shapes and extract shape descriptors that can then be used for object detection or image classification. In this research we develop a shape descriptor for biomedical image type (or, modality) classification. We adapt a feature extraction method used in optical character recognition (OCR) for character shape representation, and apply various image preprocessing methods to successfully adapt the method to our application. The proposed shape descriptor is applied to radiology images (e.g., MRI, CT, ultrasound, X-ray, etc.) to assess its usefulness for modality classification. In our experiment we compare our method with other visual descriptors such as CEDD, CLD, Tamura, and PHOG that extract color, texture, or shape information from images. The proposed method achieved the highest classification accuracy of 74.1% among all other individual descriptors in the test, and when combined with CSD (color structure descriptor) showed better performance (78.9%) than using the shape descriptor alone.

  12. 3D texture analysis for classification of second harmonic generation images of human ovarian cancer

    NASA Astrophysics Data System (ADS)

    Wen, Bruce; Campbell, Kirby R.; Tilbury, Karissa; Nadiarnykh, Oleg; Brewer, Molly A.; Patankar, Manish; Singh, Vikas; Eliceiri, Kevin. W.; Campagnola, Paul J.

    2016-10-01

    Remodeling of the collagen architecture in the extracellular matrix (ECM) has been implicated in ovarian cancer. To quantify these alterations we implemented a form of 3D texture analysis to delineate the fibrillar morphology observed in 3D Second Harmonic Generation (SHG) microscopy image data of normal (1) and high risk (2) ovarian stroma, benign ovarian tumors (3), low grade (4) and high grade (5) serous tumors, and endometrioid tumors (6). We developed a tailored set of 3D filters which extract textural features in the 3D image sets to build (or learn) statistical models of each tissue class. By applying k-nearest neighbor classification using these learned models, we achieved 83–91% accuracies for the six classes. The 3D method outperformed the analogous 2D classification on the same tissues, where we suggest this is due the increased information content. This classification based on ECM structural changes will complement conventional classification based on genetic profiles and can serve as an additional biomarker. Moreover, the texture analysis algorithm is quite general, as it does not rely on single morphological metrics such as fiber alignment, length, and width but their combined convolution with a customizable basis set.

  13. Polarization imaging and classification of Jurkat T and Ramos B cells using a flow cytometer.

    PubMed

    Feng, Yuanming; Zhang, Ning; Jacobs, Kenneth M; Jiang, Wenhuan; Yang, Li V; Li, Zhigang; Zhang, Jun; Lu, Jun Q; Hu, Xin-Hua

    2014-09-01

    Label-free and rapid classification of cells can have awide range of applications in biology. We report a robust method of polarization diffraction imaging flow cytometry (p-DIFC) for achieving this goal. Coherently scattered light signals are acquired from single cells excited by a polarized laser beam in the form of two cross-polarized diffraction images. Image texture and intensity parameters are extracted with a gray level co-occurrence matrix (GLCM) algorithm to obtain an optimized set of feature parameters as the morphological "fingerprints" for automated cell classification. We selected the Jurkat T cells and Ramos B cells to test the p-DIFC method's capacity for cell classification. After detailed statistical analysis, we found that the optimized feature vectors yield accuracies of classification between the Jurkat and Ramos ranging from 97.8% to 100% among different cell data sets. Confocal imaging and three-dimensional reconstruction were applied to gain insights on the ability of p-DIFC method for classifying the two cell lines of highly similar morphology. Based on these results we conclude that the p-DIFC method has the capacity to discriminate cells of high similarity in their morphology with "fingerprints" features extracted from the diffraction images, which may be attributed to subtle but statistically significant differences in the nucleus-to-cell volume ratio in the case of Jurkat and Ramos cells.

  14. Automatic classification of schizophrenia using resting-state functional language network via an adaptive learning algorithm

    NASA Astrophysics Data System (ADS)

    Zhu, Maohu; Jie, Nanfeng; Jiang, Tianzi

    2014-03-01

    A reliable and precise classification of schizophrenia is significant for its diagnosis and treatment of schizophrenia. Functional magnetic resonance imaging (fMRI) is a novel tool increasingly used in schizophrenia research. Recent advances in statistical learning theory have led to applying pattern classification algorithms to access the diagnostic value of functional brain networks, discovered from resting state fMRI data. The aim of this study was to propose an adaptive learning algorithm to distinguish schizophrenia patients from normal controls using resting-state functional language network. Furthermore, here the classification of schizophrenia was regarded as a sample selection problem where a sparse subset of samples was chosen from the labeled training set. Using these selected samples, which we call informative vectors, a classifier for the clinic diagnosis of schizophrenia was established. We experimentally demonstrated that the proposed algorithm incorporating resting-state functional language network achieved 83.6% leaveone- out accuracy on resting-state fMRI data of 27 schizophrenia patients and 28 normal controls. In contrast with KNearest- Neighbor (KNN), Support Vector Machine (SVM) and l1-norm, our method yielded better classification performance. Moreover, our results suggested that a dysfunction of resting-state functional language network plays an important role in the clinic diagnosis of schizophrenia.

  15. Sparse coding based dense feature representation model for hyperspectral image classification

    NASA Astrophysics Data System (ADS)

    Oguslu, Ender; Zhou, Guoqing; Zheng, Zezhong; Iftekharuddin, Khan; Li, Jiang

    2015-11-01

    We present a sparse coding based dense feature representation model (a preliminary version of the paper was presented at the SPIE Remote Sensing Conference, Dresden, Germany, 2013) for hyperspectral image (HSI) classification. The proposed method learns a new representation for each pixel in HSI through the following four steps: sub-band construction, dictionary learning, encoding, and feature selection. The new representation usually has a very high dimensionality requiring a large amount of computational resources. We applied the l1/lq regularized multiclass logistic regression technique to reduce the size of the new representation. We integrated the method with a linear support vector machine (SVM) and a composite kernels SVM (CKSVM) to discriminate different types of land cover. We evaluated the proposed algorithm on three well-known HSI datasets and compared our method to four recently developed classification methods: SVM, CKSVM, simultaneous orthogonal matching pursuit, and image fusion and recursive filtering. Experimental results show that the proposed method can achieve better overall and average classification accuracies with a much more compact representation leading to more efficient sparse models for HSI classification.

  16. Spectral and Image Integrated Analysis of Hyperspectral Data for Waxy Corn Seed Variety Classification

    PubMed Central

    Yang, Xiaoling; Hong, Hanmei; You, Zhaohong; Cheng, Fang

    2015-01-01

    The purity of waxy corn seed is a very important index of seed quality. A novel procedure for the classification of corn seed varieties was developed based on the combined spectral, morphological, and texture features extracted from visible and near-infrared (VIS/NIR) hyperspectral images. For the purpose of exploration and comparison, images of both sides of corn kernels (150 kernels of each variety) were captured and analyzed. The raw spectra were preprocessed with Savitzky-Golay (SG) smoothing and derivation. To reduce the dimension of spectral data, the spectral feature vectors were constructed using the successive projections algorithm (SPA). Five morphological features (area, circularity, aspect ratio, roundness, and solidity) and eight texture features (energy, contrast, correlation, entropy, and their standard deviations) were extracted as appearance character from every corn kernel. Support vector machines (SVM) and a partial least squares–discriminant analysis (PLS-DA) model were employed to build the classification models for seed varieties classification based on different groups of features. The results demonstrate that combining spectral and appearance characteristic could obtain better classification results. The recognition accuracy achieved in the SVM model (98.2% and 96.3% for germ side and endosperm side, respectively) was more satisfactory than in the PLS-DA model. This procedure has the potential for use as a new method for seed purity testing. PMID:26140347

  17. Multimodal Classification of Mild Cognitive Impairment Based on Partial Least Squares.

    PubMed

    Wang, Pingyue; Chen, Kewei; Yao, Li; Hu, Bin; Wu, Xia; Zhang, Jiacai; Ye, Qing; Guo, Xiaojuan

    2016-08-10

    In recent years, increasing attention has been given to the identification of the conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD). Brain neuroimaging techniques have been widely used to support the classification or prediction of MCI. The present study combined magnetic resonance imaging (MRI), 18F-fluorodeoxyglucose PET (FDG-PET), and 18F-florbetapir PET (florbetapir-PET) to discriminate MCI converters (MCI-c, individuals with MCI who convert to AD) from MCI non-converters (MCI-nc, individuals with MCI who have not converted to AD in the follow-up period) based on the partial least squares (PLS) method. Two types of PLS models (informed PLS and agnostic PLS) were built based on 64 MCI-c and 65 MCI-nc from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The results showed that the three-modality informed PLS model achieved better classification accuracy of 81.40%, sensitivity of 79.69%, and specificity of 83.08% compared with the single-modality model, and the three-modality agnostic PLS model also achieved better classification compared with the two-modality model. Moreover, combining the three modalities with clinical test score (ADAS-cog), the agnostic PLS model (independent data: florbetapir-PET; dependent data: FDG-PET and MRI) achieved optimal accuracy of 86.05%, sensitivity of 81.25%, and specificity of 90.77%. In addition, the comparison of PLS, support vector machine (SVM), and random forest (RF) showed greater diagnostic power of PLS. These results suggested that our multimodal PLS model has the potential to discriminate MCI-c from the MCI-nc and may therefore be helpful in the early diagnosis of AD.

  18. Reticence, Accuracy and Efficacy

    NASA Astrophysics Data System (ADS)

    Oreskes, N.; Lewandowsky, S.

    2015-12-01

    James Hansen has cautioned the scientific community against "reticence," by which he means a reluctance to speak in public about the threat of climate change. This may contribute to social inaction, with the result that society fails to respond appropriately to threats that are well understood scientifically. Against this, others have warned against the dangers of "crying wolf," suggesting that reticence protects scientific credibility. We argue that both these positions are missing an important point: that reticence is not only a matter of style but also of substance. In previous work, Bysse et al. (2013) showed that scientific projections of key indicators of climate change have been skewed towards the low end of actual events, suggesting a bias in scientific work. More recently, we have shown that scientific efforts to be responsive to contrarian challenges have led scientists to adopt the terminology of a "pause" or "hiatus" in climate warming, despite the lack of evidence to support such a conclusion (Lewandowsky et al., 2015a. 2015b). In the former case, scientific conservatism has led to under-estimation of climate related changes. In the latter case, the use of misleading terminology has perpetuated scientific misunderstanding and hindered effective communication. Scientific communication should embody two equally important goals: 1) accuracy in communicating scientific information and 2) efficacy in expressing what that information means. Scientists should strive to be neither conservative nor adventurous but to be accurate, and to communicate that accurate information effectively.

  19. Groves model accuracy study

    NASA Astrophysics Data System (ADS)

    Peterson, Matthew C.

    1991-08-01

    The United States Air Force Environmental Technical Applications Center (USAFETAC) was tasked to review the scientific literature for studies of the Groves Neutral Density Climatology Model and compare the Groves Model with others in the 30-60 km range. The tasking included a request to investigate the merits of comparing accuracy of the Groves Model to rocketsonde data. USAFETAC analysts found the Groves Model to be state of the art for middle-atmospheric climatological models. In reviewing previous comparisons with other models and with space shuttle-derived atmospheric densities, good density vs altitude agreement was found in almost all cases. A simple technique involving comparison of the model with range reference atmospheres was found to be the most economical way to compare the Groves Model with rocketsonde data; an example of this type is provided. The Groves 85 Model is used routinely in USAFETAC's Improved Point Analysis Model (IPAM). To create this model, Dr. Gerald Vann Groves produced tabulations of atmospheric density based on data derived from satellite observations and modified by rocketsonde observations. Neutral Density as presented here refers to the monthly mean density in 10-degree latitude bands as a function of altitude. The Groves 85 Model zonal mean density tabulations are given in their entirety.

  20. Machine Learning Algorithms for Automatic Classification of Marmoset Vocalizations

    PubMed Central

    Ribeiro, Sidarta; Pereira, Danillo R.; Papa, João P.; de Albuquerque, Victor Hugo C.

    2016-01-01

    Automatic classification of vocalization type could potentially become a useful tool for acoustic the monitoring of captive colonies of highly vocal primates. However, for classification to be useful in practice, a reliable algorithm that can be successfully trained on small datasets is necessary. In this work, we consider seven different classification algorithms with the goal of finding a robust classifier that can be successfully trained on small datasets. We found good classification performance (accuracy > 0.83 and F1-score > 0.84) using the Optimum Path Forest classifier. Dataset and algorithm