Multi-class Support Vector Machine Research Articles

Vibration nonstationary representation of the railway vehicle's gear system considering spalling failure under variable speed conditions: Numerical modeling and field testing

The nonstationary representation of spalling faults in the helical gear transmission system of railway vehicles remains unclear under variable speed conditions, and the selection of sensitive features in faults recognition has been confirmed as a problem to be addressed in this field. Thus, a vehicle-track coupled model with a helical gear transmission system was built in this study, which considered the spalling faults and employed field testing data to verify the model. The model was adopted to analyze the non-stationary representation of a helical gear system with spalling faults in the translational directions under variable speed conditions. Subsequently, the data originating from the simulation and field testing were adopted in this study, such that the ReliefF-MSVM (Multi-class SVM) algorithm was driven to sift the sensitive features in the translational directions and obtain the optimal sensitive features and diagnostic direction. The result achieved with the sensitive features selected suggested that the vertical statistical characterization of the helical gear transmission system of railway vehicles exhibited low dimensionality and high robustness, and the diagnostic results were optimal. This study can provide a theoretical reference for dynamics analysis, health monitoring, and fault diagnosis in the helical gear system of railway vehicles.

A Multiclass Support Vector Machine Based Direction-of-Arrival Estimation Technique using Spherical Antenna Array with Undefined Mutual Coupling

A Multiclass Support Vector Machine Based Direction-of-Arrival Estimation Technique using Spherical Antenna Array with Undefined Mutual Coupling

High dimensional mislabeled learning

High-dimensional mislabeled learning is essential in AI theory and applications but rarely investigated. In this study, we present a novel learning technique to detect and rectify high-dimensional mislabeled data using proposed Feature Self-Organizing Map (fSOM) along with relevant theoretical findings. When combined with the reproducible multi-class SVM learning approach, this method forms the backbone of our proposed psychiatric map (pMAP) diagnosis algorithm. This algorithm specifically addresses the real-world challenge in psychiatry of differentiating between Schizophrenia and Bipolar disorder using SNP data. The pMAP diagnosis not only offers a more precise and dependable mechanism for identifying misdiagnoses compared to state-of-the-art deep learning and machine learning models but also unveils previously unreported latent psychiatry subtypes. Furthermore, this research sheds new light on the pathology of psychiatric disorders. By mapping the evolution and internal transitions of psychiatric states and analyzing the relative entropies between various psychiatric maps, we unveil avenues to both augment and refine traditional psychiatric research. To our knowledge, this represents the inaugural study in high-dimensional mislabeled learning, poised to inspire further exploration in the domain.

AN INNOVATIVE TECHNIQUE FOR CLASSIFICATION AND DETECTION OF SKIN CANCER USING IMAGE PROCESSING AND SVM ALGORITHM

Skin cancer is a serious health issue that affects millions of people worldwide. One in every three cancers is a skin cancer and, most people fail to identify and get a diagnosis which is why early detection is essential for effective treatment and improving patient outcomes. In recent years, computer vision and machine learning have become important tools for the automatic detection of skin cancer. One of the commonly used machine learning algorithms for this task is Support Vector Machines (SVMs). SVMs are a type of supervised learning algorithm that is used for classification tasks. In skin cancer detection, the SVM classifier is trained on a dataset of dermatoscopic images of skin lesions. The first step in the process is feature extraction, where relevant information is extracted from the images to serve as input to the SVM classifier. This information can include color, texture, and shape features, among others.
 The training and testing of the SVM classifier is then performed using a portion of the dataset, with the remainder being used to evaluate its performance. During the testing phase, the SVM classifier is used to predict the class label of each image, which can be malignant or benign. The accuracy of the classifier is evaluated by comparing its predictions to the actual class labels of the images in the evaluation dataset.
 The results of using SVMs in skin cancer detection have been promising, with high accuracy rates being achieved. This highlights the potential of SVMs as a useful tool for skin cancer screening and early detection. In conclusion, the use of SVMs in skin cancer detection provides a fast, automatic, and reliable method for detecting skin cancer, which can help to improve patient outcomes. Currently it is really very important to watch and analyse the cancer disease automatically at intervals the first stages. Irregular streaks square measure one in every of the foremost very important features (included in most of dermoscopy algorithms) that show high association with carcinoma and basal cell malignant growth malady. The diagnostic test technique for the detection is most painful and harmful so we have a tendency to tend to square measure going for the machine-driven detection. Here we have a tendency to tend to square measure practice the GLCM choices for the detection the choices of skin lesions square measure extracted normalized symmetrical grey Level Co-occurrence Matrices GLCM. GLCM based texture choices square measure extracted from each of the four classes and given as input to the Multi-Class Support vector machine that's utilized for classification purpose.

Tverberg's theorem and multi-class support vector machines

Tverberg's theorem and multi-class support vector machines

What artificial intelligence can bring us in the diagnosis and progression of glaucoma

Aims/Purpose: Our goal is to focus on the contribution of artificial intelligence in glaucoma from diagnosis to progression.Methods: By a literature review, we will review work using AI in the field of glaucoma, whether for screening, diagnosis or detection of progression.Results: For the diagnosis: Recently, two papers were published reporting results of DL algorithms to diagnose glaucoma from Visual Field data. Several authors have evaluated AI‐based fundus photograph analysis for its utility for detecting glaucoma such as the study of Liu et al which grouped 241 032 images of 68 013 patients with a sensitivity of 96.2% and specificity of 87.2% also for analysing OCT imaging data from peripapillary RNFL thickness maps and the macular ganglion cell complex for discriminating between glaucomatous and normal eyes with AROC values ranging from 0.69 to 0.99. Prediction of IOP trends from previous data and medications would be a useful and plausible use of AI. For the progression of glaucoma: Multiclass support vector machines (SVMs), have been used to simultaneously discriminate between normal, non progressing, and progressing eyes through the analysis of confocal scanning laser ophthalmoscopy (CSLO) images with a correct classification rate of 88% .Conclusions: Many AI strategies have shown promising results for glaucoma detection using fundus photography, optical coherence tomography, or automated perimetry. The combination of these imaging modalities increases the performance of AI algorithms, with results comparable to those of humans. Research in the coming years will need to address unavoidable questions regarding the clinical significance of such results and the explicability of the predictions.

SVM-RLF-DNN: A DNN with reliefF and SVM for automatic identification of COVID from chest X-ray and CT images.

To develop an advanced determination technology for detecting COVID-19 patterns from chest X-ray and CT-scan films with distinct applications of deep learning and machine learning methods. The newly enhanced proposed hybrid classification network (SVM-RLF-DNN) comprises of three phases: feature extraction, selection and classification. The in-depth features are extracted from a series of 3×3 convolution, 2×2 max polling operations followed by a flattened and fully connected layer of the deep neural network (DNN). ReLU activation function and Adam optimizer are used in the model. The ReliefF is an improved feature selection algorithm of Relief that uses Manhattan distance instead of Euclidean distance. Based on the significance of the feature, the ReliefF assigns weight to each extracted feature received from a fully connected layer. The weight to each feature is the average of k closest hits and misses in each class for a neighbouring instance pair in multiclass problems. The ReliefF eliminates lower-weight features by setting the node value to zero. The higher weights of the features are kept to obtain the feature selection. At the last layer of the neural network, the multiclass Support Vector Machine (SVM) is used to classify the patterns of COVID-19, viral pneumonia and healthy cases. The three classes with three binary SVM classifiers use linear kernel function for each binary SVM following a one-versus-all approach. The hinge loss function and L2-norm regularization are selected for more stable results. The proposed method is assessed on publicly available chest X-ray and CT-scan image databases from Kaggle and GitHub. The performance of the proposed classification model has comparable training, validation, and test accuracy, as well as sensitivity, specificity, and confusion matrix for quantitative evaluation on five-fold cross-validation. Our proposed network has achieved test accuracy of 98.48% and 95.34% on 2-class X-rays and CT. More importantly, the proposed model's test accuracy, sensitivity, and specificity are 87.9%, 86.32%, and 90.25% for 3-class classification (COVID-19, Pneumonia, Normal) on chest X-rays. The proposed model provides the test accuracy, sensitivity, and specificity of 95.34%, 94.12%, and 96.15% for 2-class classification (COVID-19, Non-COVID) on chest CT. Our proposed classification network experimental results indicate competitiveness with existing neural networks. The proposed neural network assists clinicians in determining and surveilling the disease.

MedOptNet: Meta-Learning Framework for Few-Shot Medical Image Classification.

In the medical research domain, limited data and high annotation costs have made efficient classification under few-shot conditions a popular research area. This paper proposes a meta-learning framework, termed MedOptNet, for few-shot medical image classification. The framework enables the use of various high-performance convex optimization models as classifiers, such as multi-class kernel support vector machines, ridge regression, and other models. End-to-end training is then implemented using dual problems and differentiation in the paper. Additionally, various regularization techniques are employed to enhance the model's generalization capabilities. Experiments on the BreakHis, ISIC2018, and Pap smear medical few-shot datasets demonstrate that the MedOptNet framework outperforms benchmark models. Moreover, the model training time is also compared to prove its effectiveness in the paper, and an ablation study is conducted to validate the effectiveness of each module.

Local Binary and Multiclass SVMs Trained on a Quantum Annealer

Local Binary and Multiclass SVMs Trained on a Quantum Annealer

An Efficient Spam Mail Classification Approach Using Improved Moth Flame Optimization and Multi-class Support Vector Machine

An Efficient Spam Mail Classification Approach Using Improved Moth Flame Optimization and Multi-class Support Vector Machine

Cucumber diseases diagnosis based on multi-class SVM and electronic medical record

Cucumber diseases diagnosis based on multi-class SVM and electronic medical record

Contactless wheat foreign material monitoring and localization with passive RFID tag arrays

In the early stage of harvesting, transportation, and storage, the grain could be mingled with clods from the field, metal pieces from aging machines, and other objects of foreign material, which will greatly influence the grain quality and food security. In this paper, we propose a novel radio frequency (RF) sensing system termed TagSee, which utilizes passive RFID tag arrays to sense the objects buried in wheat. The goal is to simultaneously sense the presence of foreign materials, locate their locations in the 3D space and sense their types, to automatically monitor the stored grain. Specifically, we use RFID received signal strength (RSS) and phase as features for foreign material detection. To design the TagSee system, we first introduce a sensing space division method. Then, an Euclidean Distance Ratio (EDR) algorithm and a heuristic method are proposed to achieve high localization success accuracy. A multi-class SVM method is used to sense different materials properties based on the impact of different foreign materials on signal features. Experimental results show that TagSee can effectively detect foreign materials in stored grain and achieve a centimeter-level localization success accuracy, and can recognize four types of objects in grain.

Blend of Deep Features and Binary Tree Growth Algorithm for Skin Lesion Classification

One of the most frequently identified cancers globally is skin cancer (SC). The computeraided categorization of numerous skin lesions via dermoscopic images is still a complicated problem. Early recognition is crucial since it considerably increases the survival chances. In this study, we introduce an approach for skin lesion categorization where, at first, a powerful hybrid deep-feature set is constructed, and then a binary tree growth (BTG)-based optimization procedure is implemented using a support vector machine (SVM) classifier with an intention to compute the categorizing error and build symmetry between categories, for selecting the most significant features which are finally fed to a multi-class SVM for classification. The hybrid deep-feature set is constructed by utilizing two pre-trained models, i.e., Densenet-201, and Inception-v3, that are fine-tuned on skin lesion data. These two deep-feature models have distinct architectures that characterize dissimilar feature abstraction strengths. This effective deep feature framework has been tested on two publicly available challenging datasets, i.e., ISIC2018 and ISIC2019. The proposed framework outperforms many existing approaches and achieves notable {accuracy, sensitivity, precision, specificity} values of {98.50%, 96.60%, 97.84%, 99.59%} and {96.60%, 94.21%, 96.38%, 99.39%} for the ISIC2018 and ISIC2019 datasets, respectively. The proposed implementation of the BTG-based optimization algorithm performs significantly better on the proposed feature blend for skin lesion classification.

MultiClass Text Classification Using Support Vector Machine

Support vector machine (SVM) was initially designed for binary classification .To solve multi-class problems of support vector machines (SVM) more efficiently, a novel framework, which we call class-incremental learning (CIL) CIL reuses the old models of the classifier and learns only one binary sub-classifier with an additional phase of feature selection when a new class comes. In text classification, where computers sort text documents into categories, keeping up with new information can be tricky. Traditional methods need lots of retraining to adapt. However, Incremental Learning for multi-class Support Vector Machines (SVMs) offers a solution. It lets us update the model with new data while remembering what it learned before .In this project, we'll explore how Incremental Learning makes multi-class SVMs better at handling changing data and even learning about new categories as they appear .There is a problem in addressing the challenge of integrating new classes while maintaining classification accuracy on existing and new classes .The main goal of this project is to create a method that effectively adapts the MC- SVM to evolving data distributions while minimizing the impact on previously learned classes and optimising resource utilization. Keywords— feature extraction, support vector machine, multi class incremental learning, Gaussian kernel.

Handwritten character recognition using optimization based skewed line segmentation method and multi-class support vector machine

Handwritten character recognition using optimization based skewed line segmentation method and multi-class support vector machine

User's learning capability aware E-content recommendation system for enhanced learning experience

E-learning is inevitable during these pandemic days and most of the learners find it comfortable to learn online. However, the main challenge is to locate the appropriate data in line with the learner's requirement. Considering the necessity of this issue, this article presents an e-content recommendation system that considers the user's learning capability. This work categorizes the documents into three categories such as basic, intermediate and advanced levels. Based on the users' learning capability, corresponding documents are recommended and this idea enhances the overall learning experience. This work is based on three phases such as data pre-processing, feature extraction and classification. The collected documents are pre-processed for preparing the documents suitable for further processes. Features such as Parts–OF–Speech (POS) tagging, Term Frequency - Inverse Document Frequency (TF-IDF) and semantic similarity based on WordNet are extracted and the multiclass Support Vector Machine (SVM) is employed for distinguishing between the classes. The performance of the work is tested and the results prove the efficacy of the work with 98 % accuracy rates, in contrast to the comparative techniques.

Adaptive Synthetic Support Vector Machine Multiclass untuk mengklasifikasikan Imbalance data pada Sentimen kenaikan Bahan Bakar Minyak

The phenomenon of increasing fuel oil (BBM) has become a trending topic for people in Indonesia in September 2022. Indonesian people from various provinces have chosen their opinions regarding this phenomenon on social media, one of which is Twitter. Sentiment analysis is used to describe a person's opinion on social media about a phenomenon. In this study, we will look at public sentiment regarding the increase in fuel prices which is labeled into three categories, namely positive, neutral and negative. This study applies adaptive synthetics to overcome data imbalances caused by negative sentiment. The data used in this research is public opinion related to the increase in fuel prices in every province in Indonesia. Each province is limited to 100 opinions. The classification method applied to this research is the multiclass Support Vector Machine (SVM). The results obtained are that people in all provinces in Indonesia have a negative opinion regarding the increase in fuel prices. The results of the multiclass SVM classification show an average accuracy of 87.94%, with the highest accuracy of 95%.

Self-healing FBG sensor network fault-detection based on a multi-class SVM algorithm

We propose a three-layer ring architecture with enhanced reconfigurable capabilities for fiber Bragg grating (FBG) sensor networks. The proposed network is capable of self-healing when three fiber links fail. In addition to self-healing, soft faults in the FBG sensors can be detected using a multi-classification support vector machine (multi-class SVM) algorithm. The detection accuracy reached 99%. Additionally, we used an artificial neural network (ANN) reliability estimation model to estimate the reliability of the FBG self-healing network. The results show that the ANN reliability analysis model can accurately estimate the reliability of the architecture at a reasonable cost.

QR code recognition based on HOG and multiclass SVM classifier

QR code recognition based on HOG and multiclass SVM classifier

Power Quality Disturbances Classification Through Optimal Feature Selective Mechanism

In the Detection and classification of Power Quality Disturbances, feature selection is very important because the more number of features causes more complexity and less number of feature impacts the accuracy. Hence, this paper proposed a new feature selection mechanism called as Flexible Mutual Information based Feature Selection (FMIFS) to represent the Power Quality Disturbances with an effective set of features. FMIFS computes the Mutual Redundancy between PQDs and removes redundant features between them. Once the optimal features are obtained for each PQD, then they are fed to Multi-class Support Vector Machine (MC-SVM) for classification. MC-SVM classifies each PQD based on the feature trained to the system. At experimental analysis, we applied our method on totally 11 types of PQDs for classification and the performance is measured through recall, precision, F1-score, and False Alarm Rate (FAR).