Support Vector Machine-based Feature Research Articles

An automated hybrid approach via deep learning and radiomics focused on the midbrain and substantia nigra to detect early-stage Parkinson’s disease

ObjectivesThe altered neuromelanin in substantia nigra pars compacta (SNpc) is a valuable biomarker in the detection of early-stage Parkinson’s disease (EPD). Diagnosis via visual inspection or single radiomics based method is challenging. Thus, we proposed a novel hybrid model that integrates radiomics and deep learning methodologies to automatically detect EPD based on neuromelanin-sensitive MRI, namely short-echo-time Magnitude (setMag) reconstructed from quantitative susceptibility mapping (QSM).MethodsIn our study, we collected QSM images including 73 EPD patients and 65 healthy controls, which were stratified into training-validation and independent test sets with an 8:2 ratio. Twenty-four participants from another center were included as the external validation set. Our framework began with the detection of the brainstem utilizing YOLO-v5. Subsequently, a modified LeNet was applied to obtain deep learning features. Meanwhile, 1781 radiomics features were extracted, and 10 features were retained after filtering. Finally, the classified models based on radiomics features, deep learning features, and the hybrid of both were established through machine learning algorithms, respectively. The performance was mainly evaluated using accuracy, net reclassification improvement (NRI), and integrated discrimination improvement (IDI). The saliency map was used to visualize the model.ResultsThe hybrid feature-based support vector machine (SVM) model showed the best performance, achieving ACC of 96.3 and 95.8% in the independent test set and external validation set, respectively. The model established by hybrid features outperformed the one radiomics feature-based (NRI: 0.245, IDI: 0.112). Furthermore, the saliency map showed that the bilateral “swallow tail” sign region was significant for classification.ConclusionThe integration of deep learning and radiomic features presents a potent strategy for the computer-aided diagnosis of EPD. This study not only validates the accuracy of our proposed model but also underscores its interpretability, evidenced by differential significance across various anatomical sites.

Pellet image segmentation model of superpixel feature-based support vector machine in digital twin

A digital twin model based on superpixel features is established to solve the problem of noise and similar gray values between foreground and background of pellet images. With superpixel as the basic unit of segmentation, the influence of single pixel on segmentation results is reduced, and allows for higher segmentation accuracy. The gray-level co-occurrence matrix is used to represent the superpixel characteristic information, and the color moment and gray level distribution are combined to comprehensively characterize the superpixel. Through principal component analysis and correlation analysis, The feature compression of superpixel is realized, and the computational efficiency is improved. The superpixel binary classification data set is built, and the multi-dimensional feature information of superpixel is extracted as input vector to train the binary classification model of SVM, and the image segmentation problem is transformed into foreground and background classification problem. A multi-scale superpixel segmentation boundary optimization method is proposed to further refine the boundary region of foreground and background. A four-neighborhood search algorithm is proposed to reduce the missegmentation rate of edge superpixels. Experimental results show that the accuracy of the proposed method can reach 95.87%, the precision of image edge segmentation is high, and the foreground and background of granular image are accurately segmented. The digital twin model is established which can provide basis for the subsequent visual analysis and decision.

Autonomic Features in Prediction of Coronary Artery Disease and Myocardial Infarction

Atherosclerosis is one of the causes of the progression of cardiovascular diseases that lead to coronary artery diseases (CAD) and myocardial infarction (MI). The disease severity causes electrocardiogram (ECG) shape deformation leads to difficulty in R-wave detection required for heart rate variability (HRV) analysis. This limitation in the diagnosis of atherosclerotic events using ECG leads to computer-aided ECG-derived features in the prediction of CAD and MI. In this study, the lead-II ECG was recorded from CAD (N = 30), MI (N = 10), and control (N = 30) subjects. The ECG-derived heart rate variability (HRV) features were extracted. The HRV features-based support vector machine (SVM) and the artificial neural network (ANN) models have been optimized in the prediction of CAD and MI subjects. The present study revealed an efficacy of time-domain HRV parameters with the ANN model in the classification of CAD and MI subjects with an accuracy of 100% and 99.6%, respectively. While SVM presented an accuracy of 75.5% and 98.9%, respectively. The time-domain HRV parameter-based automated computer-aided diagnostic approach can be used in developing low-cost technology that may provide aid to clinicians in the screening of CAD and MI subjects.

Heart Disease Prediction Using Glowworm Swarm Optimization and Support Vector Machine Classifier

At present, health disorder is growing day by way of the day due to existence lifestyle, hereditary. Particularly, heart disease has ended up greater frequent these days. Heart disorder prognosis technique is very quintessential and integral trouble for the patient's health. Besides, it will help out to limit disorder to a larger distinctive level. The role of using strategy like machine learning and algorithm such as heart disease diagnosis using Data Mining(DM) techniques is very significant. In the previous system, the Fuzzy Extreme Learning Machine (FELM) was proposed to predict heart disease, ensuring an accurate and timely diagnosis. However, it only achieves 87.14 % of accuracy. To improve the classification accuracy, the proposed system designed an Improved Step Adjustment based Glowworm Swarm Optimization Algorithm with Weighted Feature based Support Vector Machine (ISAGSO-WFSVM) for Heart disease diagnosis. This proposed venture utilizes the dataset of heart disease for input. Using the Improved Step Adjustment based Glowworm Swarm Optimization Algorithm (ISAGSO) to enhance the true positive rate, optimal features are then selected. Finally, with the aid of the Weighted Feature based Support Vector Machine (WFSVM) classifier, classification is carried out relying selected features. In the proposed method, better performance obtained and that is validated through the experimental results in terms of precision, accuracy, recall and f-measures

Modeling fragmentation probability of land-use and land-cover using the bagging, random forest and random subspace in the Teesta River Basin, Bangladesh

Land-use and land-cover (LULC) changes have become a crucial issue that urgently needs to be addressed due to global environmental change. Many studies have employed remote sensing data for assessing LULC changes, however, the investigation of fragmentation probability modeling is still scarce in the existing literature. Thus, the coupling of bagging, random forest (RF), random subspace (RSS), and their ensemble model with multi-temporal datasets within the GIS environment makes it possible to model the fragmentation probability of LULC in the Teesta River Basin (TRB), Bangladesh. The number of patch (NP), edge density (ED), largest patch index (LPI), contagion index (%) (CONTAG), aggregation index (AI), perimeter area ratio (P/A ratio), the class area (CA), percentage of landscape (PLAND), patch density (PD), total edge (TE), largest shape index (LSI) and total core area (TCA) were the landscape and class matrices, which were derived from the LULC maps using FRAGSTATS software. The machine learning-based sensitivity models, such as decision tree and support vector machine-based feature selection techniques were implemented to explore the influence of the parameters for fragmentation probability modeling. The results showed that water bodies and barren land were substantially decreased by (6.21%), and (14.59%) respectively while the built-up areas increased by 1.45% from 2010 to 2019. Results revealed that the dominance of the agricultural area has been increased as human interference has been elevated in the TRB. However, twelve class-level and landscape matrices were used to delineate the fragmentation probability zone with the aid of bagging, RF, and RSS algorithms. LULC images and fragmentation probability models were validated using the kappa coefficient and the area under curve (AUC) of the receiver operating characteristics (ROC). The validation outcomes depicted that the three models such as bagging (AUC = 0.864), RF (AUC = 0.819), RSS (AUC = 0.859), and ensemble model (AUC = 0.912) have a good capability to appraise the fragmentation probability, and ensemble model has the highest precision level among three models. Nearly 49% (1789 km2) of the LULC was under a high to very high fragmentation potential zone that requires to be protected with direct measures. The results of sensitivity analysis showed that the number of patches significantly influenced the fragmentation probability model, while the largest patch index was the least sensitive parameter for modeling.

Identifying Parkinson's disease with mild cognitive impairment by using combined MR imaging and electroencephalogram.

To analyse the changes of quantitative electroencephalogram (qEEG) and cortex structural magnetic resonance (MR) imaging in Parkinson's disease with mild cognitive impairment (PD-MCI) and to explore the "composite marker"-based machine learning model in identifying PD-MCI. Retrospective analysis of patients with PD identified 36 PD-MCI and 35 PD with normal cognition (PD-NC). QEEG features of power spectrum and structural MR features of cortex based on surface-based morphometry (SBM) were extracted. Support vector machine (SVM) was established using combined features of structural MR and qEEG to identify PD-MCI. Feature importance evaluation algorithm of mean impact value (MIV) was established to sort the vital characteristics of qEEG and structural MR. Compared with PD-NC, PD-MCI showed a statistically significant difference in 5 leads and waves of qEEG and 7 cortical region features of structural MR. The SVM model based on these qEEG and structural MR features yielded an accuracy of 0.80 in the training set and had a high prediction accuracy of 0.80 in the test set (sensitivity was 0.78, specificity was 0.83, area under the receiver operating characteristic curve was 0.77), which was higher than the model built by the feature separately. QEEG features of theta wave in C3 had a marked impact on the model for classification according to the MIV algorithm. PD-MCI is characterized by widespread structural and EEG abnormality. "Composite markers" could be valuable for the individualized diagnosis of PD-MCI by machine learning. • Explore the brain abnormalities in Parkinson's disease with mild cognitive impairment by using the quantitative electroencephalogram and cortex structural MR simultaneously. • Multimodal features based support vector machine for identifying Parkinson's disease with mild cognitive impairment has an acceptable performance. • Theta wave in C3 is the most influential feature of qEEG and cortex structure MR imaging in identifying Parkinson's disease with mild cognitive impairment using support vector machine.

A machine learning framework to identify the hotspot in photovoltaic module using infrared thermography

In this paper, a hybrid features based support vector machine (SVM) model is proposed using infrared thermography technique for hotspots detection and classification of photovoltaic (PV) panels. A novel hybrid feature vector consisting of RGB, texture, the histogram of oriented gradient (HOG), and local binary pattern (LBP) as features is formed using a data fusion approach. A machine learning algorithm SVM is employed to classify the obtained thermal images of PV panels into three different classes (i.e., healthy, non-faulty hotspot, and faulty). The comparison of different machine learning algorithms and datasets is also carried out to validate the superiority of the proposed model and hybrid feature dataset. The experimental results reveal that the proposed hybrid features with SVM resulted in 96.8% training accuracy and 92% testing accuracy with lesser computational complexity and storage space than other machine learning algorithms. The proposed approach is easily implementable for efficient monitoring and fault diagnosis of PV panels.

Sentiment Analysis using Feature Based Support Vector Machine – A Proposed Method

Business decisions for any service or product depend on sentiments by the people. The mood of people towards any event, service and product are expressed in sentiments. The text sentiment contains different linguistic features of sentence. A sentiment sentence also contains other features which are playing a vital role in deciding the polarity of sentiments.The features like duplication of sentiment, unknown emotics may change the polarity of sentiment.If features selection is proper one can extract better sentiments for decision making. A directed preprocessing will feed filtered input to any machine learning approach. Support vector machine proved as a good tool of machine learning for better sentiment analysis.Better use of parts os speech (POS) folled by guided preprocessing and evaluation will provide less errorus polarity of sentiments

Simultaneous feature selection and heterogeneity control for SVM classification: An application to mental workload assessment

In this study, an expert system is presented for analyzing the mental workload of interacting with a mobile phone while facing common daily tasks. Psychophysiological signals were collected from various devices, each characterized by a different cost and obtrusiveness. To deal with user-level signal data, a support vector machine-based feature selection approach is proposed. Given the limited person-level information available, our goal was to construct robust models by pooling population-level information across users (as a heterogeneity control). A single optimization problem that combines four objectives is proposed: model, margin maximization, feature selection, and heterogeneity control. The costs of using the devices were estimated, leading to a decision tool that allowed experiment designers to evaluate the marginal benefit of using a given device in terms of performance and its cost.

In-field citrus detection and localisation based on RGB-D image analysis

In-field citrus detection and localisation are highly challenging tasks due to varying illumination conditions, partial occlusion of citrus, and the colour variation of citrus at different stages of maturity. A reliable algorithm based on red-green-blue-depth (RGB-D) images was developed to detect and locate citrus in real, outdoor orchard environments for robotic harvesting. A depth filter and a Bayes-classifier-based image segmentation method were first developed to exclude as many backgrounds as possible. A density clustering method was then used to group adjacent points in the filtered RGB-D images into clusters, where each cluster represents a possible citrus. A colour, gradient, and geometry feature-based support vector machine classifier was trained to remove false positives. To test the method, a dataset with 506 RGB-D images was acquired in a citrus orchard on sunny and cloudy days. Results showed that the proposed algorithm was robust with an F1 score of 0.9197; the positioning errors in the x, y and z directions were 7.0 ± 2.5 mm, −4.0 ± 3.0 mm and 13.0 ± 3.0 mm, respectively, and the sizing error was −1.0 ± 4.0 mm. These excellent performance values demonstrate that the proposed method could be used to guide a citrus-harvesting robot.

Serum N-Glycosylation in Parkinson's Disease: A Novel Approach for Potential Alterations.

In this study, we present the application of a novel capillary electrophoresis (CE) method in combination with label-free quantitation and support vector machine-based feature selection (support vector machine-estimated recursive feature elimination or SVM-RFE) to identify potential glycan alterations in Parkinson’s disease. Specific focus was placed on the use of neutral coated capillaries, by a dynamic capillary coating strategy, to ensure stable and repeatable separations without the need of non-mass spectrometry (MS) friendly additives within the separation electrolyte. The developed online dynamic coating strategy was applied to identify serum N-glycosylation by CE-MS/MS in combination with exoglycosidase sequencing. The annotated structures were quantified in 15 controls and 15 Parkinson’s disease patients by label-free quantitation. Lower sialylation and increased fucosylation were found in Parkinson’s disease patients on tri-antennary glycans with 2 and 3 terminal sialic acids. The set of potential glycan alterations was narrowed by a recursive feature elimination algorithm resulting in the efficient classification of male patients.

Mass Surveilance of C. elegans-Smartphone-Based DIY Microscope and Machine-Learning-Based Approach for Worm Detection.

The nematode Caenorhabditis elegans (C. elegans) is often used as an alternative animal model due to several advantages such as morphological changes that can be seen directly under a microscope. Limitations of the model include the usage of expensive and cumbersome microscopes, and restrictions of the comprehensive use of C. elegans for toxicological trials. With the general applicability of the detection of C. elegans from microscope images via machine learning, as well as of smartphone-based microscopes, this article investigates the suitability of smartphone-based microscopy to detect C. elegans in a complete Petri dish. Thereby, the article introduces a smartphone-based microscope (including optics, lighting, and housing) for monitoring C. elegans and the corresponding classification via a trained Histogram of Oriented Gradients (HOG) feature-based Support Vector Machine for the automatic detection of C. elegans. Evaluation showed classification sensitivity of 0.90 and specificity of 0.85, and thereby confirms the general practicability of the chosen approach.

Reprint of: Big data approach to batch process monitoring: Simultaneous fault detection and diagnosis using nonlinear support vector machine-based feature selection

This paper presents a novel data-driven framework for process monitoring in batch processes, a critical task in industry to attain a safe operability and minimize loss of productivity and profit. We exploit high dimensional process data with nonlinear Support Vector Machine-based feature selection algorithm, where we aim to retrieve the most informative process measurements for accurate and simultaneous fault detection and diagnosis. The proposed framework is applied to an extensive benchmark data set which includes process data describing 22,200 batches with 15 faults. We train fault and time-specific models on the pre-aligned batch data trajectories via three distinct time horizon approaches: one-step rolling, two-step rolling, and evolving which varies the amount of data incorporation during modeling. The results show that two-step rolling and evolving time horizon approaches perform superior to the other. Regardless of the approach, proposed framework provides a promising decision support tool for online simultaneous fault detection and diagnosis for batch processes.

Fast and Adaptive Detection of Pulmonary Nodules in Thoracic CT Images Using a Contextual Clustering Based Region Growing

For segmenting the Region of interest and for analyzing each area separately to locate whether pathologies present in it or not, we use segmentation process as the first step to diagnose lung image using ComputerAided Diagnosis. In this paper, ROI is segmented by using supervised Contextual Clustering in addition to the Region growing algorithm. Accurate segmentation of the lungs from the chest volume is obtained from the Contextual clustering which is better than all other thresholding approaches that are simple. Initial Nodule Candidates can be detected and segmented effectively by contextual clustering which is considered to be the most effective approach when compared to the remaining approaches present.We combine rule-based filtering and a feature based support vector machine using which we can reduce the False-positives (FP) ,custom CNN, Alex net, neuro-fuzzy classifier.

Big data approach to batch process monitoring: Simultaneous fault detection and diagnosis using nonlinear support vector machine-based feature selection

This paper presents a novel data-driven framework for process monitoring in batch processes, a critical task in industry to attain a safe operability and minimize loss of productivity and profit. We exploit high dimensional process data with nonlinear Support Vector Machine-based feature selection algorithm, where we aim to retrieve the most informative process measurements for accurate and simultaneous fault detection and diagnosis. The proposed framework is applied to an extensive benchmark data set which includes process data describing 22,200 batches with 15 faults. We train fault and time-specific models on the pre-aligned batch data trajectories via three distinct time horizon approaches: one-step rolling, two-step rolling, and evolving which varies the amount of data incorporation during modeling. The results show that two-step rolling and evolving time horizon approaches perform superior to the other. Regardless of the approach, proposed framework provides a promising decision support tool for online simultaneous fault detection and diagnosis for batch processes.

Attention-Based Memory Network for Text Sentiment Classification

In order to explore the impact of different memory modules under the framework of memory network for aspect level sentiment classification, we use convolutional neural networks (CNN) and bidirectional long short term memory (BiLSTM) to design four kinds of memory network models in this paper. The first model uses CNN for building a memory module, which is capable of capturing local information in documents. The second uses BiLSTM for building another memory module, which captures sequence information in documents. At the same time, the following two models use CNN and BiLSTM for building memory module——one builds a hierarchical neural network by using CNN and BiLSTM for building memory module, which combines both local and sequence information together. The other, respectively, uses CNN and BiLSTM for building two memory modules, respectively, which captures local information and sequence information through different modules. And then, we combine the final representations, which are generated from the different memory networks, for further sentiment classification. Experiments on laptop and restaurant datasets demonstrate that our four methods achieving better results than MemNet. In particular, the latter two models achieve better performance than the first two models and feature-based support vector machine approach.

Human–vehicle classification using feature‐based SVM in 77‐GHz automotive FMCW radar

In this study, a human-vehicle classification using a feature-based support vector machine (SVM) in a 77-GHz automotive frequency modulated continuous wave (FMCW) radar system is proposed. As a classification criterion, the authors use a newly defined parameter called root radar cross section which reflects the reflection characteristics of targets. Based on this parameter, three distinctive signal features are extracted from frequency-domain received FMCW radar signals, and they become classification standards used for the SVM. Finally, through measurement results on the test field, the classification performance of the authors' proposed method is verified, and the average classification accuracy from a four-fold cross data validation is found to be higher than 90%. In addition, the authors' proposed classification method is applied to distinguish a pedestrian, a vehicle, and a cyclist in a more practical situation, and it also shows good classification performance.

Comparing 2D image features on viewpoint independence using 3D anthropometric dataset

We study the viewpoint-independence of image features in the classification of identities using multiple-view full-body images. A reliable vision system should be robust in classifying objects from images captured on novel viewpoints. To obtain a robust classifier, 3D models are collected for rendering training and testing images from various viewpoints. These images are then used for extracting features and building classifiers. In this work, we compute multiple view human-body images from a 3D anthropometry human body database. For each subject, a majority of the views are randomly selected to be included in the training dataset and the remaining views are used for testing. More specifically, we use histogram of oriented gradient (HOG) feature-based support vector machine (SVM) as the baseline to be compared with deep auto-encoders network and deep convolutional neural networks (CNN). Through experiments, we conclude that the deep CNN performs the best (deep auto-encoders network as the runner-up) in computing viewpointindependent image features for identity classifications based on 2D full-body images.

Comparing 2D image features on viewpoint independence using 3D anthropometric dataset

We study the viewpoint-independence of image features in the classification of identities using multiple-view full-body images. A reliable vision system should be robust in classifying objects from images captured on novel viewpoints. To obtain a robust classifier, 3D models are collected for rendering training and testing images from various viewpoints. These images are then used for extracting features and building classifiers. In this work, we compute multiple view human-body images from a 3D anthropometry human body database. For each subject, a majority of the views are randomly selected to be included in the training dataset and the remaining views are used for testing. More specifically, we use histogram of oriented gradient (HOG) feature-based support vector machine (SVM) as the baseline to be compared with deep auto-encoders network and deep convolutional neural networks (CNN). Through experiments, we conclude that the deep CNN performs the best (deep auto-encoders network as the runner-up) in computing viewpointindependent image features for identity classifications based on 2D full-body images.

Analysis of functionality of left ventricle

Detecting Left Ventricular (LV) structural changes from echo sequences can facilitate early Diagnosis and treatment of coronary artery disease. We develop a novel feature-based support vector machine (SVM) to detect the LV functionality as potential biomarkers. In the first phase, image pre-processing was carried out by using Shift 4 Algorithm. In the second phase, heart wall boundaries were detected by using Level set Algorithm. Then composite motion image creation was created using the heart wall boundaries, followed by feature extraction and statistical pattern recognition. In the third phase, dual LV contour region is segmented and segmented into LV individual segments. Volume, velocity of blood flow, and motion in between frames are calculated for each LV segment. The one against all SVM classifier was used to identify the LV segment abnormality. The performance of this approach was tested with 20 Abnormal and 20 Normal cases. We trained with 25 Normal & 25 Abnormal cases. During testing, we found that out of 24 cases are classified correctly. The results indicated that the SVM was an effective tool for automatically diagnosing LV functionality when compared to earlier works.