Multiple SVM Research Articles

Anomaly-Based IDS (Intrusion Detection System) for Cyber-Physical Systems

Cyber-physical systems (CPS) are critical infrastructures that integrate physical processes with computational components. The security of CPS is paramount, as any breach can lead to severe consequences. Anomaly-based intrusion detection systems (IDS) have emerged as a promising approach to safeguard CPS against cyber threats. This paper presents an anomaly-based IDS designed specifically for CPS, leveraging machine learning techniques to establish a baseline of normal system behaviour and promptly detect deviations indicative of malicious activities. The proposed system incorporates multiple classification techniques, including KNeighbors, RandomForest, XGB, DecisionTree, SGD, SVM, LGBM, AdaBoost, Bagging, and MLP Classifier, to enhance detection accuracy and robustness. Key components of the IDS, such as data collection, feature extraction, anomaly detection, and alert generation, are thoroughly outlined. The system's performance is evaluated, highlighting its effectiveness in accurately identifying intrusions while maintaining low false positive rates. The proposed anomaly-based IDS aims to provide a robust and reliable solution for enhancing the security of CPS and protecting critical infrastructure from cyber threats.

Kruskal Wallis and mRMR Feature Selection based Online Signature Verification System using Multiple SVM and KNN

Signature verification is a very important research area. Signature has been widely accepted as a person authentication method for centuries. It is mostly used in financial transactions, document authentication and agreements. It is more susceptible to being forged than any other biometrics. Online signature verification is used in real-time applications like e-commerce, online resource access, online financial transactions, physical access into a restricted area and many more. In order to achieve high efficiency in online signature verification systems, feature extraction and feature selection play a significant role. A suitable signature verification system is needed to prevent forgery and accept the genuine signer. We have extracted 30 global features from all 40 signers for verification. Here, k fold cross-validation technique is used to enhance the model's performance on unseen data. User-specific feature selection and ranking are done using Kruskal Wallis and Minimum Redundancy Maximum Relevance (mRMR) algorithm to hunt which performs better in our case. Kruskal-Wallis method tests if two or more classes have an equal median and gives the value of P based on which discriminative features are selected, whereas the mRMR algorithm ranks the whole feature set according to its importance. It evaluates the relevance of a feature and penalizes redundancy. Finally, multiple SVM and KNN classifiers are trained and tested with various selected features using Kruskal Wallis and mRMR to determine which combination performs best for the online signature verification system. Our model is trained, validated and tested on the SVC 2004 Task 1 database, which consists of skill forgery signatures. Here, one to one verification is done using each user's genuine and skill forgery signatures, which is the hardest to detect. Best average testing accuracy achieved in our case is 90.25% using Weighted KNN and Kruskal Wallis selected 15 features.

Low SNR multimirror Fabry-Perot pressure sensor optic spectrum signal analysis and demodulation via SVM-KNN regressors.

We demonstrate an ensemble learning based method to solve the problem of low SNR Fabry-Perot sensor spectrum signal demodulation. Taking the eight-layer approximate coefficients of a multilevel discrete wavelet transform as input features, an ensemble model that combines multiple SVM and KNN learners is trained. Bootstrap and booting techniques are introduced for better modeling performance and stability. It is shown that the performance of the proposed ensemble model based on SVM-KNN regressors is excellent; an accuracy of 0.46%F.S. relative mean error is achieved. This method could provide insight into the construction of a large scale fiber based Fabry-Perot sensor network.

A teaching management system for physical education in colleges and universities using the theory of multiple intelligences and SVM

A teaching management system for physical education in colleges and universities using the theory of multiple intelligences and SVM

Comparing Different Chemometric Approaches to Detect Adulteration of Cold-Pressed Flaxseed Oil with Refined Rapeseed Oil Using Differential Scanning Calorimetry.

Flaxseed oil is one of the best sources of n-3 fatty acids, thus its adulteration with refined oils can lead to a reduction in its nutritional value and overall quality. The purpose of this study was to compare different chemometric models to detect adulteration of flaxseed oil with refined rapeseed oil (RP) using differential scanning calorimetry (DSC). Based on the melting phase transition curve, parameters such as peak temperature (T), peak height (h), and percentage of area (P) were determined for pure and adulterated flaxseed oils with an RP concentration of 5, 10, 20, 30, and 50% (w/w). Significant linear correlations (p ≤ 0.05) between the RP concentration and all DSC parameters were observed, except for parameter h1 for the first peak. In order to assess the usefulness of the DSC technique for detecting adulterations, three chemometric approaches were compared: (1) classification models (linear discriminant analysis-LDA, adaptive regression splines-MARS, support vector machine-SVM, and artificial neural networks-ANNs); (2) regression models (multiple linear regression-MLR, MARS, SVM, ANNs, and PLS); and (3) a combined model of orthogonal partial least squares discriminant analysis (OPLS-DA). With the LDA model, the highest accuracy of 99.5% in classifying the samples, followed by ANN > SVM > MARS, was achieved. Among the regression models, the ANN model showed the highest correlation between observed and predicted values (R = 0.996), while other models showed goodness of fit as following MARS > SVM > MLR. Comparing OPLS-DA and PLS methods, higher values of R2X(cum) = 0.986 and Q2 = 0.973 were observed with the PLS model than OPLS-DA. This study demonstrates the usefulness of the DSC technique and importance of an appropriate chemometric model for predicting the adulteration of cold-pressed flaxseed oil with refined rapeseed oil.

NOVEL HYBRID ALGORITHM USING CONVOLUTIONAL AUTOENCODER WITH SVM FOR ELECTRICAL IMPEDANCE TOMOGRAPHY AND ULTRASOUND COMPUTED TOMOGRAPHY

This paper presents a new hybrid algorithm using multiple Support Vector Machines models with convolutional autoencoder to Electrical Impedance Tomography, and Ultrasound Computed Tomography image reconstruction. The ultimate hybrid solution uses multiple SVM models to convert input measurements to individual autoencoder codes representing a given scene then the decoder part of the autoencoder can reconstruct the scene

Machine Learning-Driven Ubiquitous Mobile Edge Computing as a Solution to Network Challenges in Next-Generation IoT

Ubiquitous mobile edge computing (MEC) using the internet of things (IoT) is a promising technology for providing low-latency and high-throughput services to end-users. Resource allocation and quality of service (QoS) optimization are critical challenges in MEC systems due to the large number of devices and applications involved. This results in poor latency with minimum throughput and energy consumption as well as a high delay rate. Therefore, this paper proposes a novel approach for resource allocation and QoS optimization in MEC using IoT by combining the hybrid kernel random Forest (HKRF) and ensemble support vector machine (ESVM) algorithms with crossover-based hunter–prey optimization (CHPO). The HKRF algorithm uses decision trees and kernel functions to capture the complex relationships between input features and output labels. The ESVM algorithm combines multiple SVM classifiers to improve the classification accuracy and robustness. The CHPO algorithm is a metaheuristic optimization algorithm that mimics the hunting behavior of predators and prey in nature. The proposed approach aims to optimize the parameters of the HKRF and ESVM algorithms and allocate resources to different applications running on the MEC network to improve the QoS metrics such as latency, throughput, and energy efficiency. The experimental results show that the proposed approach outperforms other algorithms in terms of QoS metrics and resource allocation efficiency. The throughput and the energy consumption attained by our proposed approach are 595 mbit/s and 9.4 mJ, respectively.

Probability-weighted ensemble support vector machine for intelligent recognition of moving wear debris from joint implant

Friction-induced wear debris from joint implants are effective resources in investigating artificial joint wear and cellular immune response mechanisms. To improve the accuracy of wear debris analysis, an intelligent recognition method is developed for wear debris measurement under motion conditions. In this method, the multi-view image sequence of moving wear debris is captured to acquire the variations of aspect ratio, area, and roundness features. Then multiple SVM models are integrated to identify wear debris types based on weighted probability to improve the accuracy. The proposed method can achieve a classification accuracy of 90.51%, which is better than HIVE-COTE2.0, MultiRocket, and other time series classification algorithms. This method can be applied to monitor wear status of artificial joint articulating surfaces.

Some results on statistics and functional data analysis

This paper presents some recent results on regression and classification in Functional Data Analysis setting. The first work decated to Multiple kernel SVM for classifying functional data in Sobolev spaces focus on optimization of the information from each derivatives of the original functions, the second work devoted to An input/output-based aggregation rule for functional data classification when the last is interested with the problem of regression if the functional data lives in a finite dimensionnal submanifold.

Transmission Line Fault Diagnosis Method Based on Improved Multiple SVM Model

Transmission Line Fault Diagnosis Method Based on Improved Multiple SVM Model

A New Feature Extraction Method for EMG Signals

Surface Electromyography (sEMG) is an important tool for gesture recognition. Features and classification methods have to be carefully selected to be successful in the recognition of electromyografic signals. In most of the sEMG studies, time and frequency domain features have been extracted and classified with a single classifier. But neither one feature nor one classifier alone has achieved high classification accuracies. Using a feature and classifier combination would be a solution for this problem, and increase the accuracies. As a contribution to this field, a new time domain EMG feature is suggested and its classification performance is examined for feature and classifier combinations in this study. According to the results of this study, the new feature has high classification accuracy, and when it is used with AR and ST features, the average of the classification accuracy reaches 99.57% for multiple SVM classifier. Besides, the new feature+AR+ ST feature combination shows high classification accuracy for single classifier, and this eliminates the need for multiple classifiers.

Comparison of Performance of Machine Learning Models for Predicting Compression Index Based on Clay Properties

As the construction of large structures increases primarily on the soft ground along coasts, prevention of damage to the structures due to subsidence should be prioritized. Ground subsidence has been investigated actively. Because the amount of settlement can be calculated based on the compression index of clay, the latter must be calculated accurately. In this study, data pertaining to the natural water content, liquid limit, plasticity index, initial void ratio, and compression index of clay are acquired from Busan, Gwangyang, and Mokpo to construct a dataset for predicting the compression index. Correlation analysis between factors is performed using the dataset, and compression index prediction models are developed using machine learning algorithms, random forest, multiple linear regression, ridge, Lasso, SVM, XGBoost, LightGBM, and DNN. Subsequently, the results of each model are compared in terms of the RMSE and R2. The results show that the natural water content, liquid limit, plasticity index, initial void ratio, and compression index are correlated significantly. Among the machine learning models, LightGBM demonstrates the best performance.

Hyperspectral image classification using multiple weighted local kernel matrix descriptors

ABSTRACT Local covariance matrix descriptor is a new spatial-spectral feature generation method. It has been successfully applied for remote sensing image classification. Meanwhile, there are some critiques of it because it neglects nonlinear relationships between features, which are serious when applied to hyperspectral images (HSIs). So, the present paper aims to develop weighted local kernel matrix (WLKM) descriptors for the spatial-spectral classification of HSI. The developed weighted local kernel matrix features, including spectral-textural-geometrical aspects, have been used in two classification schemes proposed. In the first approach, called ‘early fusion’, the weighted sum of WLKM descriptors derived from spectral and spatial features is classified using the log-Euclidean kernel SVM. In the second approach, called ‘late fusion’, a multiple log-Euclidean kernel SVM strategy based on the WLKM descriptors of spatial and spectral features is developed for HSI classification. Experiments on three widely used HSI datasets have proved the superiority of the proposed approaches over some recent spatial-spectral HSI classification techniques.

An Analog Circuit Fault Diagnosis Approach Based on Wavelet-based Fractal Analysis and Multiple Kernel SVM

Objective: In order to diagnose the analog circuit fault correctly, an analog circuit fault diagnosis approach on basis of wavelet-based fractal analysis and multiple kernel support vector machine (MKSVM) is presented in the paper. Methods: Time responses of the circuit under different faults are measured, and then wavelet-based fractal analysis is used to process the collected time responses for the purpose of generating features for the signals. Kernel principal component analysis (KPCA) is applied to reduce the features’ dimensionality. Afterwards, features are divided into training data and testing data. MKSVM with its multiple parameters optimized by chaos particle swarm optimization (CPSO) algorithm is utilized to construct an analog circuit fault diagnosis model based on the testing data. Results: The proposed analog diagnosis approach is revealed by a four opamp biquad high-pass filter fault diagnosis simulation. Conclusion: The approach outperforms other commonly used methods in the comparisons.

Hybrid fuzzy multiple SVM classifier through feature fusion based on convolution neural networks and its practical applications

Lately, Convolutional Neural Networks (CNNs) have been introduced to extract features and further enhance the classification performance in different application areas. In this study, a hybrid fuzzy multiple (HFM)-SVM design with the convolution-base (which consists of a series of pooling and convolutional layers) and composite kernel function is proposed. The objective of the proposed classifier is to enhance the nonlinear fitting ability of the classifier and improve the classification performance in high-dimensional applications. The key points of the proposed HFM SVM are enumerated as follows: 1) The convolution-base of the proposed classifier extracts features. The extracted features exhibit flexibility and applicability in high-dimensional applications. 2) The proposed HFM SVM designed with the composite kernel could adjust the nonlinear fitting ability for improving classification performance. The procedure of the proposed HFM SVM is described as follows: Convolution-base is considered as a preprocessing unit for extracting features. The features are not always linearly separable especially when being extracted from high dimensional data. A composite kernel function is constructed by considering the complicated (nonlinear) classification boundary into several local linear boundaries. The structure of the extracted features is captured by FCM clustering and integrated into the composite kernel function for enhancing the nonlinear fitting ability of the proposed classifier. The nonlinearity of the composite function can fill the gap between linear and nonlinear kernel functions by adjusting the number of clusters obtained by the FCM clustering algorithm. The proposed HFM SVM classifier based on composite kernel could improve the classification performance on high dimensional datasets. The performance of the proposed HFM SVM is experimented with and demonstrated by using three high-dimensional applications to show the effectiveness as well as performance improvement.

An improved crowd detection system using text and image filtration methods for precautions from COVID-19

The text feature is an important descriptive feature of many image analysis applications. Objectives of this study aim to determine the different texture characteristics of them estimation and calculation of population density. In this paper, we have various reviews of the texture and their own have been extensively reviewed, a different combination that is possible to test their effectiveness in crowds of pedestrians. Divide into two categories and retreat. A framework has been proposed to evaluate performance of all aspects of the density coefficient of human density as well to count. According to the framework, the input images are categorized into blocks and blocks into cells of different sizes, having various levels of overcrowding. Because of a distorted view of people, people's visibility near the camera contributes greatly to this feature vector than distant people. Therefore, the features released are usually using a standard visual map of the scene. In the first stage, picture blocks are classified using multiple classes SVM has been at a different level of congestion. In the second phase Gaussian Process Deactivation is used to restore undoing low-level features for calculation. Various texture features and their possible combinations checked on publicly available dataset.

Research on Face Recognition Algorithm Based on Multi-Class Support Vector Machine

Facial recognition is one of the main research directions in the field of artificial intelligence and image processing. It has been widely used in identity authentication, video surveillance and biological detection. Because it is non-contact, natural, convenient and reliable, facial recognition has become a popular choice for biometric systems. The accuracy of facial recognition still needs to be improved, the main goal of this paper is to improve the accuracy of face recognition. Based on the support vector machine method, the focus is on the feature extraction and feature matching of face images. In view of the particularity of face images, the pre-processing of face images is studied. In this paper, grayscale normalization and geometric normalization pre-processing methods are used. In order to reduce the interference factors of the image as much as possible, the features are high-lighted, and the non-featured parts are weakened, this paper adopts the Histogram of Oriented Gradient feature extraction method. Then we proposed a new method based on SVM, which uses a one-to-many method to construct multiple SVM classifiers, selects the optimal parameters through repeated experiments, and selects ORL face database for testing. The recognition rate can reach about 98.5%.

Advances in parallel and distributed computing and its applications

Advances in parallel and distributed computing and its applications

Application of particle mutation in drilling accidents diagnosis of Bohai shallow layers

Drilling accidents occur frequently in Bohai shallow layers. The existing drilling accidents analysis model lacks real-time performance and has poor operability. By introducing accidents mechanism, the data model based on SVM is established to improve the processing efficiency of drilling accidents, and the targeted measures for handling drilling accidents are recommended. In this study, to perform data optimization and parameter selection for SVM, we propose a quantum variation particle swarm algorithm (QVPSO), which combines K-mean classifier, quantum variation, and particle swarm algorithm. Using the problem of accidents mechanism identification, the proposed drilling accidents diagnosis, termed QVPSO-SVM, was compared with multiple competitive SVM models based on other optimization algorithms including the original algorithm, K-mean classifier, particle swarm optimization, grid method, and genetic algorithms. The experimental results demonstrate that, although the drilling accidents diagnosis needs more time than the original SVM model to solve the identification of accidents mechanism. Drilling accidents diagnosis can significantly improve the accuracy of model (96%). The targeted measures recommended by drilling accidents diagnosis can improve the processing efficiency of drilling accidents and reduce nonproductive time.

MK-FSVM-SVDD: A Multiple Kernel-based Fuzzy SVM Model for Predicting DNA-binding Proteins via Support Vector Data Description

Background: Detecting DNA-binding proteins (DBPs) based on biological and chemical methods is time-consuming and expensive. Objective: In recent years, the rise of computational biology methods based on Machine Learning (ML) has greatly improved the detection efficiency of DBPs. Method: In this study, the Multiple Kernel-based Fuzzy SVM Model with Support Vector Data Description (MK-FSVM-SVDD) is proposed to predict DBPs. Firstly, sex features are extracted from the protein sequence. Secondly, multiple kernels are constructed via these sequence features. Then, multiple kernels are integrated by Centered Kernel Alignment-based Multiple Kernel Learning (CKA-MKL). Next, fuzzy membership scores of training samples are calculated with Support Vector Data Description (SVDD). FSVM is trained and employed to detect new DBPs. Results: Our model is evaluated on several benchmark datasets. Compared with other methods, MKFSVM- SVDD achieves best Matthew's Correlation Coefficient (MCC) on PDB186 (0.7250) and PDB2272 (0.5476). Conclusion: We can conclude that MK-FSVM-SVDD is more suitable than common SVM, as the classifier for DNA-binding proteins identification.