Classification Accuracy Of Support Vector Machine Research Articles

Resting state fMRI feature-based cerebral glioma grading by support vector machine.

PURPOSE: Tumor grading plays an essential role in the optimal selection of solid tumor treatment. Noninvasive methods are needed for clinical grading of tumors. This study aimed to extract parameters of resting state blood oxygenation level-dependent functional magnetic resonance imaging (RS-fMRI) in the region of glioma and use the extracted features for tumor grading. METHODS: Tumor segmentation was performed with both conventional MRI and RS-fMRI. Four typical parameters, signal intensity difference ratio, signal intensity correlation (SIC), fractional amplitude of low-frequency fluctuation (fALFF) and regional homogeneity (ReHo), were defined to analyze tumor regions. Mann-Whitney [Formula: see text] test was employed to identify statistical difference of these four parameters between low-grade glioma (LGG) and high-grade glioma (HGG), respectively. Support vector machine (SVM) was employed to assess the diagnostic contributions of these parameters. RESULTS: Compared with LGG, HGG had more complex anatomical morphology and BOLD-fMRI features in the tumor region. SIC [Formula: see text], fALFF ([Formula: see text]) and ReHo ([Formula: see text]) were selected as features for classification according to the test [Formula: see text] value. The accuracy, sensitivity and specificity of SVM classification were better than 80, where SIC had the best classification accuracy (89). CONCLUSION: Parameters of RS-fMRI are effective to classify the tumor grade in glioma cases. The results indicate that this technique has clinical potential to serve as a complementary diagnostic tool.

Gender and age-related differences in bilateral lower extremity mechanics during treadmill running.

Female runners have a two-fold risk of sustaining certain running-related injuries as compared to their male counterparts. Thus, a comprehensive understanding of the sex-related differences in running kinematics is necessary. However, previous studies have either used discrete time point variables and inferential statistics and/or relatively small subject numbers. Therefore, the first purpose of this study was to use a principal component analysis (PCA) method along with a support vector machine (SVM) classifier to examine the differences in running gait kinematics between female and male runners across a large sample of the running population as well as between two age-specific sub-groups. Bilateral 3-dimensional lower extremity gait kinematic data were collected during treadmill running. Data were analysed on the complete sample (n = 483: female 263, male 220), a younger subject group (n = 56), and an older subject group (n = 51). The PC scores were first sorted by the percentage of variance explained and we also employed a novel approach wherein PCs were sorted based on between-gender statistical effect sizes. An SVM was used to determine if the sex and age conditions were separable and classifiable based on the PCA. Forty PCs explained 84.74% of the variance in the data and an SVM classification accuracy of 86.34% was found between female and male runners. Classification accuracies between genders for younger subjects were higher than a subgroup of older runners. The observed interactions between age and gender suggest these factors must be considered together when trying to create homogenous sub-groups for research purposes.

Dropout Training for Support Vector Machines

Dropout and other feature noising schemes have shown promising results in controlling over-fitting by artificially corrupting the training data. Though extensive theoretical and empirical studies have been performed for generalized linear models, little work has been done for support vector machines (SVMs), one of the most successful approaches for supervised learning. This paper presents dropout training for linear SVMs. To deal with the intractable expectation of the non-smooth hinge loss under corrupting distributions, we develop an iteratively re-weighted least square (IRLS) algorithm by exploring data augmentation techniques. Our algorithm iteratively minimizes the expectation of a re-weighted least square problem, where the re-weights have closed-form solutions. The similar ideas are applied to develop a new IRLS algorithm for the expected logistic loss under corrupting distributions. Our algorithms offer insights on the connection and difference between the hinge loss and logistic loss in dropout training. Empirical results on several real datasets demonstrate the effectiveness of dropout training on significantly boosting the classification accuracy of linear SVMs.

Incorporation of texture information in a SVM method for classifying salt cedar in western China

Salt cedar is prominent plant species for wind-erosion resistance and saline–alkaline tolerance in arid desert and saline–alkali soil in China. Although some studies have been published for documenting salt cedar dynamics in its invasive habitat in the United States, the study of salt cedar in its native habitat, e.g. China, is relative scarce. Recently, the reduction of salt cedar is remarkable in western China that effective methods for monitoring salt cedar dynamics are essential for ecological environment preservation. As such, this study aims to develop a support vector machine (SVM) to better mapping salt cedar with high spatial resolution remote sensing image. Specifically, our objectives are twofold: (1) to examine the role that textures play in the SVM classification and further derive the optimal window size for extracting textures and (2) to determine optimal values for two vital parameters γ and C in the SVM method. To test the effectiveness of the developed SVM method, we compared the classification performance of SVM with three different combinations of input features, i.e. spectra only; spectra and textures; and spectra, textures, and Normalized Differential Vegetation Index (NDVI). In addition, for comparison purposes, a maximum likelihood classification method based on spectra, textures, and NDVI was adopted. Results indicate that (1) incorporation of textures and NDVI, especially textures, refines the SVM classification accuracy to 84.26%; (2) the optimal window size for texture calculation is 31 × 31 pixels; and (3) the optimal parameters of SVM model are C = 32 and γ = 8. Overall, the SVM method incorporating spectra, texture, and NDVI can accurately map salt cedar in our study site.

Rapid identification of Coix seed varieties by near infrared spectroscopy

Unsupervised learning algorithm-principal component analysis (PCA), and supervised learning algorithm-learning vector quantization (LVQ) neural network and support vector machine (SVM) were used to carry out qualitative discriminant analysis of different varieties of coix seed from different regions. Since nutrient compositions of different varieties coix seed samples from different origins were complex and the contents were similar, characteristic variables of two kinds of coix seed were alike, the scores plot of their principal components seriously overlapped and the categories of coix seed were difficult to distinguish While satisfactory results were obtained by LVQ neural network and SVM. The accuracy of LVQ neural network prediction is 90. 91%, while the classification accuracy of SVM, whose penalty parameter and kernel function parameter were optimized, can be up to 100%. The results show that NIRS combined with chemometrics can be used as a rapid, nondestructive and reliable method to identify coix seed varieties and provide technical reference for market regulation.

Classifying cropping area of middle Heihe River Basin in China using multitemporal Normalized Difference Vegetation Index data

Accurate information regarding the structure of crops is critical for the improvement and optimization of land surface models. Multitemporal remote sensing imagery is more effective to determine the crop structure than the single-temporal images because they contain phenological information. Crop structure was extracted based on time series of moderate-resolution imaging spectroradiometer (MODIS) data in the middle Heihe River Basin. A time series of Normalized Difference Vegetation Index (NDVI) data with a 3-day temporal resolution was composed based on daily MODIS reflectance products (MOD 09) from January to December 2011. A total of 120 scenes of composited imagery were integrated into an image data cube of NDVI time series, which was used to extract crop structure for the study area. The spectral curves of corn, wheat, rape, vegetables, and other crops are based on both in situ measurements and visual interpretation. The major crop types were classified by using the adaptive boosting (Adaboost) and support vector machine (SVM) algorithms. The results show that the classification accuracy of Adaboost and SVM was 86.01% and 70.28%, respectively, with Kappa coefficients of 0.8351 and 0.6438, respectively. Summarizing the classification methods used in this study effectively characterize the spatial distribution of the main crops.

Application of support vector machines to metabolomics experiments with limited replicates

Identifying biomarkers that are indicative of a phenotypic state is difficult because of the amount of natural variability which exists in any population. While there are many different algorithms to select biomarkers, previous investigation shows the sensitivity and flexibility of support vector machines (SVM) make them an attractive candidate. Here we evaluate the ability of support vector machine recursive feature elimination (SVM-RFE) to identify potential metabolic biomarkers in liquid chromatography mass spectrometry untargeted metabolite datasets. Two separate experiments are considered, a low variance (low biological noise) prokaryotic stress experiment, and a high variance (high biological noise) mammalian stress experiment. For each experiment, the phenotypic response to stress is metabolically characterized. SVM-based classification and metabolite ranking is undertaken using a systematically reduced number of biological replicates to evaluate the impact of sample size on biomarker reproducibility and robustness. Our results indicate the highest ranked 1 % of metabolites, the most predictive of the physiological state, were identified by SVM-RFE even when the number of training examples was small (≥3) and the coefficient of variation was high (>0.5). An accuracy analysis shows filtering with recursive feature elimination measurably improves SVM classification accuracy, an effect that is pronounced when the number of training examples is small. These results indicate that SVM-RFE can be successful at biomarker identification even in challenging scenarios where the training examples are noisy and the number of biological replicates is low.

Laguerre Kernels –Based SVM for Image Classification

Support vector machines (SVMs) have been promising methods for classification and regression analysis because of their solid mathematical foundations which convey several salient properties that other methods hardly provide. However the performance of SVMs is very sensitive to how the kernel function is selected, the challenge is to choose the kernel function for accurate data classification. In this paper, we introduce a set of new kernel functions derived from the generalized Laguerre polynomials. The proposed kernels could improve the classification accuracy of SVMs for both linear and nonlinear data sets. The proposed kernel functions satisfy Mercer’s condition and orthogonally properties which are important and useful in some applications when the support vector number is needed as in feature selection. The performance of the generalized Laguerre kernels is evaluated in comparison with the existing kernels. It was found that the choice of the kernel function, and the values of the parameters for that kernel are critical for a given amount of data. The proposed kernels give good classification accuracy in nearly all the data sets, especially those of high dimensions.

Classification of speech intelligibility in Parkinson's disease

A problem in the clinical assessment of running speech in Parkinson's disease (PD) is to track underlying deficits in a number of speech components including respiration, phonation, articulation and prosody, each of which disturbs the speech intelligibility. A set of 13 features, including the cepstral separation difference and Mel-frequency cepstral coefficients were computed to represent deficits in each individual speech component. These features were then used in training a support vector machine (SVM) using n-fold cross validation. The dataset used for method development and evaluation consisted of 240 running speech samples recorded from 60 PD patients and 20 healthy controls. These speech samples were clinically rated using the Unified Parkinson's Disease Rating Scale Motor Examination of Speech (UPDRS-S). The classification accuracy of SVM was 85% in 3 levels of UPDRS-S scale and 92% in 2 levels with the average area under the ROC (receiver operating characteristic) curves of around 91%. The strong classification ability of selected features and the SVM model supports suitability of this scheme to monitor speech symptoms in PD.

Automatic Extraction of Place Entities and Sentences Containing the Date and Number of Victims of Tropical Disease Incidence from the Web

Many tropical disease incidences, such as leprosy, elephantiasis, malaria, dengue fever, are reported in online news portals. Online news portals are valuable data sources for creating a tropical disease repository if the information such as the location of the incidence, date of occurrence, and the number of victims can be automatically extracted from news articles. This paper describes approaches to extract that information from the Web. We introduce a rule-based algorithm to identify and extract the locations of the incidence and use Support Vector Machine (SVM) to determine the sentences containing the date of occurrence and the number of victims. Our experiments show that, the accuracy of the rule-based algorithm to identify the location entities is 99.8%, while the accuracy of the classifier to determine the sentences that contain one or more places of the incidence is 82%. The accuracy of SVM classifiers to classify the sentences that contain the date of occurrence and the number of victims are 96.41% and 93.38%, respectively.

An Effective Approach for Selection of Terrain Modeling Methods

This letter presents an effective approach for selection of appropriate terrain modeling methods in forming a digital elevation model (DEM). This approach achieves a balance between modeling accuracy and modeling speed. A terrain complexity index is defined to represent a terrain's complexity. A support vector machine (SVM) classifies terrain surfaces into either complex or moderate based on this index associated with the terrain elevation range. The classification result recommends a terrain modeling method for a given data set in accordance with its required modeling accuracy. Sample terrain data from the lunar surface are used in constructing an experimental data set. The results have shown that the terrain complexity index properly reflects the terrain complexity, and the SVM classifier derived from both the terrain complexity index and the terrain elevation range is more effective and generic than that designed from either the terrain complexity index or the terrain elevation range only. The statistical results have shown that the average classification accuracy of SVMs is about 84.3% ± 0.9% for terrain types (complex or moderate). For various ratios of complex and moderate terrain types in a selected data set, the DEM modeling speed increases up to 19.5% with given DEM accuracy.

A decision support system for diagnosis of neuromuscular disorders using DWT and evolutionary support vector machines

Support vector machines (SVMs) have been widely used in many pattern recognition problems. Generally, the performance of SVM classifiers is affected by the selection of the kernel parameters. However, SVM does not offer the mechanism for proper setting of their control parameters. The objective of this research is to optimize the parameters without degrading the SVM classification accuracy in diagnosis of neuromuscular disorders. An evolutionary approach for designing an SVM-based classifier (ESVM) by optimization of automatic parameter tuning using genetic algorithm is proposed. To illustrate and evaluate the efficiency of ESVM, a typical application to EMG signals classification using normal, myopathic, and neurogenic datasets is adopted. 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 was extracted from the sub-bands to represent the distribution of wavelet coefficients. It is shown that ESVM can obtain a high accuracy of 97 % using tenfold cross-validation for the EMG datasets. ESVM is developed as an efficient tool, so that various SVMs can be used conveniently as the core of ESVM for diagnosis of neuromuscular disorders.

Using Stratified Sample and Grid Search to Improve Disease Prediction Accuracy of SVM

SVM (Support Vector Machine) is a powerful data mining algorithm, and is mainly used to finish classification or regression tasks. In this literature, SVM is used to conduct disease prediction. We focus on integrating with stratified sample and grid search technology to improve the classification accuracy of SVM, thus, we propose an improved algorithm named SGSVM: Stratified sample and Grid search based SVM. To testify the performance of SGSVM, heart-disease data from UCI are used in our experiment, and the results show SGSVM has obvious improvement in classification accuracy, and this is very valuable especially in disease prediction.

A Classification Algorithm for Network Traffic based on Improved Support Vector Machine

An algorithm to classify the network traffic based on improved support vector machine (SVM) is presented in this paper. Each feature of the traditional support vector machine (SVM) algorithm has the same effect on classification rather than considering its practical effect. To improve the classification accuracy of SVM, the probabilistic distributing area of a feature in a kind of network traffic is obtained from the real network traffic. Then the overlapped degree of the feature’s probabilistic distributing area between two different kinds of network traffic is calculated to obtain the feature’s contribution degree, and the corresponding weight value of the feature is derived from its contribution degree. Thus each feature has different effect on the classification according to its weight value. Considering the feature’s probabilistic distributing area is affected by the outliers or noises intensively, the data space is mapped to high dimension feature space, and the Gustafson-Kessel clustering algorithm is employed to deal with the outliers or noises existing in the input samples. The experimental results show that the method presented in this paper has a higher classification accuracy.

Predictors of Medication Adherence in Elderly Patients with Chronic Diseases Using Support Vector Machine Models

ObjectivesThe aim of this study was to establish a prediction model of medication adherence in elderly patients with chronic diseases and to identify variables showing the highest classification accuracy of medication adherence in elderly patients with chronic diseases using support vector machine (SVM) and conventional statistical methods, such as logistic regression (LR).MethodsWe included 293 chronic disease patients older than 65 years treated at one tertiary hospital. For the medication adherence, Morisky's self-report was used. Data were collected through face-to-face interviews. The mean age of the patients was 73.8 years. The classification process was performed with LR (SPSS ver. 20.0) and SVM (MATLAB ver. 7.12) method.ResultsTaking into account 16 variables as predictors, the result of applying LR and SVM classification accuracy was 71.1% and 97.3%, respectively. We listed the top nine variables selected by SVM, and the accuracy using a single variable, self-efficacy, was 72.4%. The results suggest that self-efficacy is a key factor to medication adherence among a Korean elderly population both in LR and SVM.ConclusionsMedication non-adherence was strongly associated with self-efficacy. Also, modifiable factors such as depression, health literacy, and medication knowledge associated with medication non-adherence were identified. Since SVM builds an optimal classifier to minimize empirical classification errors in discriminating between patient samples, it could achieve a higher accuracy with the smaller number of variables than the number of variables used in LR. Further applications of our approach in areas of complex diseases, treatment will provide uncharted potentials to researchers in the domains.

Recurrence quantification analysis on pulse morphological changes in patients with coronary heart disease

ObjectiveTo show that the pulse diagnosis used in Traditional Chinese Medicine, combined with nonlinear dynamic analysis, can help identify cardiovascular diseases. MethodsRecurrence quantification analysis (RQA) was used to study pulse morphological changes in 37 inpatients with coronary heart disease (CHD) and 37 normal subjects (controls). An independent sample t-test detected significant differences in RQA measures of their pulses. A support vector machine (SVM) classified the groups according to their RQA measures. Classic time-domain parameters were used for comparison. ResultsRQA measures can be divided into two groups. One group of measures [ecurrence rate (RR), determinism (DEL), average diagonal line length (L), maximum length of diagonal structures (Lmax), Shannon entropy of the frequency distribution of diagonal line lengths (ENTR), laminarity (LAM), average length of vertical structures (TT), maximum length of vertical structures (Vmax)] showed significantly higher values for patients with CHD than for normal subjects (P<0.05). The other measures (RR_std, L_std, Lmax_std, TT_std, Vmax_std) showed significantly lower values for the CHD group than for normal subjects (P<0.05). SVM classification accuracy was higher with RQA measures: With RQA (16 parameters) accuracy was at 88.21%, and with RQA (12 parameters) accuracy was at 84.11%. In contrast, with classic time-domain (15 parameters) accuracy was 75.73%, and with time-domain (7 parameters) accuracy was 74.70%. ConclusionNonlinear dynamic methods such as RQA can be used to study functional and structural changes in the pulse noninvasively. Pulse signals of individuals with CHD have greater regularity, determinism, and stability than normal subjects, and their pulse morphology displays less variability. RQA can distinguish the CHD pulse from the healthy pulse with an accuracy of 88.21%, thereby providing an early diagnosis of cardiovascular diseases such as CHD.

Dried jujube classification using support vector machine based on fractal parameters and red, green and blue intensity

SummaryA new method that combines fractal theory and red, green and blue (RGB) colour intensity was developed to sort dried jujube fruits by using support vector machine (SVM). Our result shows that the new method is fast and accurate in dried jujube fruits classification. The SVM models based on fractal parameters only achieved 85.18–92.73% total accuracy rate. The total classification accuracy of SVM based on RGB intensity values was 94.44%. However, the SVM models based on combining fractal parameters with RGB intensity values achieved 94.44–98.15% total accuracy rate. The best classification accuracy (98.15%) was found when using SVM model based on combining fractal measures (FM) with RGB intensity values (C = 512, γ = 0.0078125). Therefore, the SVM model based on combining FMs with RGB intensity is recommended in dried jujube fruits classification.

Research in SVM Sample Optimizes of ISODATA Algorithm

Support Vector Machine is widely used in data classification, but in the case of more training samples, the training time is longer. To solve this problem, use the ISODATA clustering algorithm to cluster samples to obtain the new cluster center, together with high similarity to the error for the sample to form a new cluster of training samples, training support vector machines. So that a solution of high similarity to repeat the training samples of similar problems, while focusing on the easily lead to wrong classification of the training samples. The support vector machine classification accuracy can be improved, and also reduces the training time, to make it more convenient for engineering application.

Particle Swarm Optimization-Based Hyperspectral Dimensionality Reduction for Urban Land Cover Classification

A particle swarm optimization (PSO)-based dimensionality reduction approach is proposed to use a simple searching criterion function, called minimum estimated abundance covariance (MEAC), requiring class signatures only. It has low computational cost, and the selected bands are independent of the detector or classifiers used in the following data analysis step. With such an efficient criterion, PSO can find a global optimal solution much more efficiently, compared with other frequently used searching strategies. Its performance is evaluated by support vector machine (SVM)-based classification for urban land cover mapping. In our experiments, SVM classification accuracy using PSO-selected bands is greatly higher than using all of the original bands or dimensionality-reduced data from principal component analysis (PCA) or linear discriminant analysis (LDA). In addition, the improvement on SVM accuracy can bring out even more significant improvement in classifier fusion.

A novel binary tree support vector machine for hyperspectral remote sensing image classification

According to the principle of support vector machine (SVM) and the inter-class separability rule of hyperspectral data, a novel binary tree SVM classifier based on separability measure among different classes is proposed for hyperspectral image classification. J–M distance is used to measure the separability in order to generate the binary tree automatically. By experiments using airborne operational modular imaging spectrometer II (OMIS II) data, satellite EO-1 Hyperion hyperspectral data and airborne AVIRIS data, the classification accuracy of different multi-class SVMs is obtained and compared. Experimental results indicate that the proposed adaptive binary tree classifier outperforms other existing multi-class SVM strategies. Use of the adaptive binary tree SVM classifier is a novel approach to improve the accuracy of hyperspectral image classification and expand the possibilities for interpretation and application of hyperspectral remote sensing image.