Arabic literal amount sub-word recognition using multiple features and classifiers

Diabetic retinopathy (DR) affects the vision of the person and may eventually lead to blindness. In the initial stage of the disease, patients are treated with a laser to restrict its progression. Such laser treatment leaves behind scars on the retina and patients are advised to undergo screening regularly to track further complications. This paper presents a novel retinal background characterization approach that explores the potential of discrete wavelet transform and rotational-invariant variance features for texture classification of retinal images with and without laser marks. For this experiment, different classifiers, namely, support vector machine, naive Bayes, neural network, and random forest classifiers are tested. We used two publicly available datasets, namely, LMD-DRS and LMD-BAPT. In all cases, the proposed approach obtained the sensitivity, specificity, and accuracy values higher than 68.9%, 70.2%, and 69.4%, respectively. It was found that all performance measures achieve over 87.5, 89.4, and 86.7% for the classification task using random forest classifier. These promising results suggest that the proposed technique can discriminate retinal images having laser marks and without laser marks, and has the potential to be an important constituent in computerized screening solution for retinal images.

Heart disease is one of the leading cause deaths of worldwide. Prediction of cardiovascular infection is a critical challenge in the area of clinical data analysis. Data mining techniques are providing an effective decision and significant results on data that are used widely for predicting. The purpose of this paper is to propose a novel approach with aims to find a noteworthy method to diagnose heart disease prediction. In this research, a unique dataset was created by combining the Cleveland dataset and Stalog heart disease datasets collected from the UCI ML repository. The new dataset contains 14 medical parameters such as age, sex, blood pressure, and 568 instances for training and prediction heart disease. This paper offers a novel methodology of NNDT (Neural Network and Decision Tree) that uses Neural Network for training model and Decision Tree to test classification for better heart disease prediction. The performance of the proposed approach have been compared with Naive Bayes, Support Vector Machine, Neural Network, Voted Perceptron, and Decision Tree algorithms. The results showed that the accuracy and performance improved as compared to other techniques and methods. This study enables the researchers to analyze the heart disease data with a new approach to predict heart diseases to maintain human health.

The increasing need of a handwritten character recognition system in the Indian offices such as banks, post offices and so forth, has made it an imperative field of research. In present paper, Authors have presented a novel hierarchical technique for isolated offline handwritten Gurmukhi character recognition. A robust feature set of 105 feature elements is proposed under this work for recognition of offline handwritten Gurmukhi characters using four types of topological features, namely, horizontally peak extent features, vertically peak extent features, diagonal features, and centroid features. For classification Support Vector Machines (SVMs) classifier has been used in this work. SVMs classifier has been considered with four different kernels, namely, linear kernel, polynomial kernel, RBF kernel and sigmoid kernel. For training and testing of a classifier, we have used 3,500 samples of isolated offline handwritten Gurmukhi characters written by one hundred different writers. Maximum recognition accuracy of 91.80 % have been achieved with proposed technique, while using PCA feature set and SVM with a linear kernel classifier.

Aiming at the problem that the detection accuracy of effluent COD (chemical oxygen demand) in sewage treatment needs to be further improved, a combined model based on support vector machine and neural network is proposed to predict effluent COD. It can reduce the influence of local optimum on the global scope so as to improve the accuracy of prediction. Firstly, the sample data are divided into two categories by support vector machine. Then the BP neural network model and the Echo State Network (ESN) model are established on two sub-samples respectively. Compared with single neural network model, the mean absolute error and root mean square error of combined model are both reduced. Besides, the proposed model has better comprehensive prediction performance and can meet the actual demand of effluent COD prediction in sewage treatment.

These days, the Internet is developing at an exponential rate and can cover just about any data required. Nonetheless, the immense measure of web pages makes it more difficult to effectively discover the target data by a user. Therefore, an efficient method, for classifying this huge amount of data is essential if the web pages are to be exploited to its full potential. In the domain of automatic web page classifier many approaches have been tried to solve this problem using different Machine learning-based algorithms including Support Vector Machine (SVM), Naive Bayes, Decision Tree, K-Nearest Neighbor (K-NN) and Neural Networks. However, there is a lack of comparison between these algorithms to find a better framework for the classification and analysis of health related web pages. In this research study, we compare two commonly used supervised Machine Learning algorithms; Support Vector Machines (SVM) and Naive Bayes to classify web pages which provide drugs related information of patients for example side effects, patient action and follow-up information for patients. We use Unified Medical Language System (UMLS) to annotate the health related concepts in Web pages and train SVM and Naive Bayes classifiers in General Architecture for Text Engineering to classify health related and non-health related Web pages. The evaluation was performed using K-fold cross validation using four runs on a data set of fifty Web pages. Results found that SVM performed better to classify health and non-health related pages in terms of precision, recall and F-measure.

This study investigated the effect of a new approach, the support vector machine, as a classifier tool to identify the weeds in corn fields at early growth stage. Image segmentation was done by transforming original color images to gray level images according to the statistical values of red, green, blue components. The Gray Level Co-occurrence Matrix (GLCM) and statistical properties of the histogram from the gray level images were further used to obtain the texture features of the weeds and corn seedlings. These texture features were used in the classification procedure. Principle component analysis was used to select the texture features according to their better contributions to reduce space dimensions. A Support Vector Machine (SVM) classifier was employed to recognize the weeds and the corn seedlings. The results indicated that the SVM classifiers with different feature selections could identify successfully weed-corn with a higher accuracy ranged from 92.31 to 100%. A comparison study of the recognition capabilities of SVM and back-propagation (BP) neural-network classifier using the same data set was conducted. It was found that the SVM classifier provided the best recognition performance with an accuracy of 100%, which exceeded the accuracy of 80% given by the BP classifier. Key words: Corn seedling, weeds, texture, support vector machine, recognize.

BackgroundThis study aimed to screen the feature modules and characteristic genes related to ulcerative colitis (UC) and construct a support vector machine (SVM) classifier to distinguish UC patients.MethodsFour datasets that contained UC and control samples were obtained from the Gene Expression Omnibus database. Differentially expressed genes (DEGs) with consistency were screened via the MetaDE method. The weighted gene coexpression network (WGCNA) was used to distinguish significant modules based on the four datasets. The protein–protein interaction network was established based on intersection genes. Enrichment analysis of Gene Ontology (GO) biological processes (BPs) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment were established based on DAVID. An SVM combined with recursive feature elimination was also applied to construct a disease classifier for the disease diagnosis of UC patients. The efficacy of the SVM classifier was evaluated through receiver operating characteristic curves.ResultsTwelve highly preserved modules were obtained using the WGCNA, and 2009 DEGs with significant consistency were selected using the MetaDE method. Sixteen significantly related GO BPs and 12 KEGG pathways were obtained, such as cytokine-cytokine receptor interaction, cell adhesion molecules, and leukocyte transendothelial migration. Subsequently, 41 genes were used to construct an SVM classifier, such as CXCL1, CCR2, IL1B, and IL1A. The area under the curve (AUC) was 0.999 in the training dataset, whereas the AUC was 0.886, 0.790, and 0.819 in the validation set (GSE65114, GSE37283, and GSE36807, respectively).ConclusionsAn SVM classifier based on feature genes might correctly identify healthy people or UC patients.

Metabolic brain imaging with 2-[18F]fluoro-2-deoxy-D-glucose positron emission tomography (FDG PET) is a supportive diagnostic and differential diagnostic tool for neurodegenerative dementias. In the clinic, scans are usually visually interpreted. However, computer-aided approaches can improve diagnostic accuracy. We aimed to build two machine learning classifiers, based on two sets of FDG PET-derived features, for differential diagnosis of common dementia syndromes. We analyzed FDG PET scans from three dementia cohorts [63 dementia due to Alzheimer's disease (AD), 79 dementia with Lewy bodies (DLB) and 23 frontotemporal dementia (FTD)], and 41 normal controls (NCs). Patients' clinical diagnosis at follow-up (25 ± 20 months after scanning) or cerebrospinal fluid biomarkers for Alzheimer's disease was considered a gold standard. FDG PET scans were first visually evaluated. Scans were pre-processed, and two sets of features extracted: (1) the expressions of previously identified metabolic brain patterns, and (2) the mean uptake value in 95 regions of interest (ROIs). Two multi-class support vector machine (SVM) classifiers were tested and their diagnostic performance assessed and compared to visual reading. Class-specific regional feature importance was assessed with Shapley Additive Explanations. Pattern- and ROI-based classifier achieved higher overall accuracy than expert readers (78% and 80% respectively, vs. 71%). Both SVM classifiers performed similarly to one another and to expert readers in AD (F1 = 0.74, 0.78, and 0.78) and DLB (F1 = 0.81, 0.81, and 0.78). SVM classifiers outperformed expert readers in FTD (F1 = 0.87, 0.83, and 0.63), but not in NC (F1 = 0.71, 0.75, and 0.92). Visualization of the SVM model showed bilateral temporal cortices and cerebellum to be the most important features for AD; occipital cortices, hippocampi and parahippocampi, amygdala, and middle temporal lobes for DLB; bilateral frontal cortices, middle and anterior cingulum for FTD; and bilateral angular gyri, pons, and vermis for NC. Multi-class SVM classifiers based on the expression of characteristic metabolic brain patterns or ROI glucose uptake, performed better than experts in the differential diagnosis of common dementias using FDG PET scans. Experts performed better in the recognition of normal scans and a combined approach may yield optimal results in the clinical setting.

Surface electromyogram (sEMG) signals are widely used to control the myoelectric prosthetic arm for amputees. In this study, the authors investigated the usefulness of discrete wavelet transform (DWT) features from multiple levels of approximation and detail coefficients obtained from sEMG signals. DWT is used for de-noising as well as feature extraction in this study and further tested using Support Vector Machine (SVM) classifier and Artificial Neural Network (ANN) Classifier. The performance of SVM classifier is compared with ANN classifier. The classification accuracy of SVM classifiers was found better as compared to ANN in term of speed and robustness. In the first section of paper the authors presented the introduction related to the study. The experimental set-up for recording surface EMG signal is presented in section 2. In section 3 the experimental results are depicted and in section 4 the results are concluded.

<p>In this paper we present method of features extraction based on decomposition of the characters into several simple geometric shapes (segment, arc) by detecting the branch points and end points, as it explained follow a new methods are using to treated the obtained information in order to decide if the characters need to add more key points also in this step we extracte the type of the shapes (segment or arc) and the orientation. The next step of characters recognition different methods are used such as neural network (NN), K-mean and support vector machine (SVM) classifier. The results shown in this paper are obtained using the IRCAM database.</p>

e14528 Background: Treatment monitoring in patients with High-Grade Glioma (HGG) and identification of disease progression, remains a major challenge in clinical neurooncology. We aimed to develop a support vector machine (SVM) classifier utilising combined longitudinal conventional and Dynamic Susceptibility Contrast (DSC) perfusion MRI to classify between Stable Disease (SD), Pseudoprogression (PsP) and Progressive Disease (PD) in glioma patients under surveillance. Methods: Conventional (269) and perfusion (62) MRI studies of HGG patients acquired between 2012 and 2018 were prospectively analysed. Study participants were separated into two groups: Group I with a single DSC time point (64 participants) and Group II with multiple DSC time points (19 participants). The SVM classifier was trained using all available MRI for each group. Classification accuracy was assessed for the use of features extracted from different feature dataset and time point combinations and compared to the experienced radiologists’ predictions. Results: The study included 64 participants (mean age: 48.5 ± 12.8 yrs [standard deviation], 24 female). SVM classification based on combined perfusion and structural features outperformed standalone datasets across all groups. For the clinically relevant classification step (SD/PSP vs PD), both feature combination as well as the addition of multiple DSC time points, improved classification performance (lowest median error rate: 0.016). The SVM algorithm outperformed radiologists in predicting lesion destiny in both groups. Optimal performance was observed in Group II, in which SVM sensitivity/specificity/accuracy was 100/91.67/94.7% for analysis based on the first time point and 85.71/100/ 94.7% based on multiple time points compared to 60/78/68% and 70/90/84.2% for the respective radiologist classifications. In Group I, the SVM also exceeded radiologist predictions, albeit by a smaller margin and resulted in sensitivity/specificity of 86.49/75.00/81.53% (SVM) compared to 75.7/68.9/73.84% (radiologists). Conclusions: Our results indicate that the addition of multiple longitudinal perfusion time points as well as the combination of structural and perfusion features significantly enhance classification outcome in treatment monitoring of HGGs and machine-learning-assisted diagnosis has potentially superior accuracy than the radiologist's visual evaluation and expertise.

Using information technology such as search engine for collecting and monitoring of network public opinion is a practical and effective method. This paper puts forward an improved algorithm of SVM classifier based on incremental learning online, and then implements a topic crawler system for network public opinion and to grab the public opinion.

Radio frequency fingerprinting (RFF) could provide an efficient solution to address the security issues in wireless networks. The data acquisition system constitutes an important part of RFF. In this context, this paper presents an implementation of a modular RF front end system to be used in data acquisition for RFF. Modularity of the system provides flexible implementation options to suit diverse frequency bands with different applications. Moreover, the system is able to collect data by means of any digitizer, and enable to record the data at lower frequencies. Therefore, proposed RF front end system becomes a low-cost alternative to existing devices used in data acquisition. In its implementation, Bluetooth (BT) signals were used. Initially, transients of BT signals were detected by utilizing a large number of BT devices (smartphones). From the detected transients, distinctive signal features were extracted. Then, support vector machine (SVM) and neural networks (NN) classifiers were implemented to the extracted features for evaluating the feasibility of proposed system in RFF. As a result, 96.9% and 96.5% classification accuracies on BT devices have been demonstrated for SVM and NN classifiers respectively.

Failure of power transformer is very complex, so that it is difficult to use the mathematical model to describe their faults. In this study, an intelligent diagnostic method based on ant colony-support vector machine (AC-SVM) approach is presented for fault diagnosis of power transformer. The AC-SVM selects kernel function parameter and soft margin constant C penalty parameter of support vector machine (SVM) classifier. The performance of the AC-SVM system proposed in this study is evaluated by cases in China. The test results show that this AC-SVM model is effective to detect failure of power transformer.

“Artificial neural networks (ANNs)” and support vector networks have been widely used for the purpose of analysis of spatial remote sensory images. Attributes selection plays a major role in reduction of computational time for model processing and improvement in performance accuracy. In this paper, we present rough set-based artificial neural network (RS-ANN) and support vector machine classification (RS-SVM) methods for the classification of hyperspectral images. In both of these techniques, rough set (RS) is used as a feature selection mathematical tool. Further, this diminished dimensionality data is carried to artificial neural network (ANN) and support vector machine (SVM) classifiers correspondingly. The proposed procedure uses spatial information and implements the strategy for efficient processing of the image, and with utilization of the “graphics processing units (GPUs)” successfully implemented with improved efficiency. The experimental analysis achieved efficient outcome that the proposed procedures perform with improved accuracy, improved efficiency with a good amount of reduction in the execution and computing time, and enhancing the accuracy in the categorizing of spatial images in comparison with other conventional strategies.