SVM Approach Research Articles

Clustering Urban Roads Using Local Binary Patterns to Enhance the Accuracy of Traffic Flow Prediction

Many studies employ a dynamic statistical approach to model the relationship between roads for predicting traffic flow. Statistical relationships among roads pertain to the associations between road segments in nearby areas. Roads with similar traffic patterns usually define the relationship. Previous studies have shown that adjacent roads demonstrated a similar traffic pattern on the same day and time interval. Studying similar patterns between roads in surrounding areas provides information about the traffic state among roads in a cluster. Furthermore, the results of this finding may be considered to increase the performance of prediction of traffic conditions. In general, road segment roads are correlated with other road segments. They are connected upstream, downstream, or both; they are connected upstream, downstream, or both. To address this, we propose a Local Binary Pattern (LBP) to explore road connections by clustering congestion features between the target roads and their neighboring roads. The outcomes show that the roads with high connectivity obtained from the clustering process were utilized to predict traffic conditions using the SVM approach. The David-Bouldin Index of LBP with k-means shows the lowest compared with PCA k-means and k-means only. By evaluating the clustering result using the Davies-Bouldin Index and assessing the prediction results with SVM, we discovered that incorporating LBP with K-Means improved outcomes in identifying highly connected roads using K-Means.

Deep Anomaly Detection: A Linear One-Class SVM Approach for High-Dimensional and Large-Scale Data

Deep Anomaly Detection: A Linear One-Class SVM Approach for High-Dimensional and Large-Scale Data

Z-K-R: A Novel Framework in Intrusion Detection system through enhanced techniques

Abstract Intrusion detection systems (IDS) are an important tool for securing computer networks from various types of cyberattacks. The increasing complexity of network attacks demands more sophisticated approaches to intrusion detection. This paper presents an innovative method for IDS that involves combining Z-Score outlier detection, KMeans clustering, and Random Forest classification techniques. We tested our methodology using the CICIDS2017 dataset, which is a standardization dataset for intrusion detection that is frequently utilized. Our proposed approach first uses Z-Score outlier detection to identify abnormal traffic flows in the network. Next, KMeans clustering is used to group the traffic flows into different clusters based on their similarity. Finally, Random Forest classification is used to classify each traffic flow into normal or abnormal categories. Based on our experimental results, our approach for intrusion detection shows superior performance compared to several other state-of-the-art methods in terms of accuracy and precision. Our proposed method achieved an accuracy rate of 95.75% and a precision of 95.76%, surpassing the performance of KNN, SVM, and decision trees approaches. In conclusion, the proposed Z-K-R approach offers a promising solution for IDS by leveraging the strengths of Z-Score outlier detection, KMeans clustering, and Random Forest classification techniques. This strategy has the potential to increase the efficiency of IDS and boost network security in applications that take place in the real world.

Deep Feature Extraction with SVM Classifier for Brain Tumor Classification

Recently, methods for classifying brain tumors have used Deep Learning (DL), in particular, Convolutional Neural Networks (CNNs), to obtain promising results. Unlike conventional Machine Learning (ML) algorithms, CNNs can automatically extract features from images; they do not, however, need the extraction regarding hand-crafted features. Many obstacles reduce the accuracy of brain tumor classification systems; to address such obstacles, we propose a DL-based feature extraction method for brain tumor classification. A total of two pretrained CNNs, VggNet-16 and ResNet-18, are applied as deep feature extractors in the scheme to accomplish deep feature extraction. Contrast Limited Adaptive Histogram Equalization (CLAHE) technique has been first used for enhancing the images. Second, each separately pretrained CNN, VggNet-16 and ResNet-18, is used for extracting the deep features from Magnetic Resonance Imaging (MRI). Lastly, a Multiclass Support Vector Machines (Multiclass -SVM) classifier is used to complete a classification task. Tests conducted on the aforementioned datasets: the effectiveness of the suggested approach is demonstrated by the CE-MRI Figshare, the REMBRANDT, and the Brain Tumor Classification, where the pre-trained CNN models and SVM classifier enhance performance. Specifically, the pretrained CNN with SVM approach produces accuracy ranging from 95.28% to 98.62% across all data-sets.

Unveiling intrusions: explainable SVM approaches for addressing encrypted Wi-Fi traffic in UAV networks

AbstractUnmanned aerial vehicles (UAVs), also known as drones, have become instrumental in various domains, including agriculture, geographic information systems, media, logistics, security, and defense. These UAVs often rely on wireless communication networks for data transmission, making them vulnerable to cyberattacks. To address these challenges, it is necessary to detect potential threats by analyzing the encrypted Wi-Fi traffic data generated by UAVs. This study aimed to develop a linear SVM model that is enhanced with explainable artificial intelligence (XAI) techniques and fine-tuned using Bayesian optimization for intrusion detection systems (IDSs); the model is specifically designed to identify malware threats targeting UAVs. This research utilized encrypted Wi-Fi traffic data derived from three different UAV networks, namely, Parrot Bebop 1, DBPower UDI, and DJI Spark, while considering unidirectional and bidirectional communication flow modes. SVM-based intrusion detection models have been modeled on these datasets, identified their key features using the local interpretable model-agnostic explanations (LIME) technique, and conducted a cost analysis of the proposed modeling approach. The incorporation of the LIME method enabled to highlight the features that are highly indicative of cyberattacks and provided valuable insights into the importance of each feature in the context of intrusion detection. In conclusion, this interpretable IDS model, fine-tuned with Bayesian optimization, demonstrated its superiority over the state-of-the-art methods, proving its efficacy in detecting and mitigating threats to UAVs while offering a cost-effective solution.

Unveiling High-Performance Ester-Based Lubricants for Minimized Surface Friction: An Ensemble Decision Tree-Weighted SVM Approach

Unveiling High-Performance Ester-Based Lubricants for Minimized Surface Friction: An Ensemble Decision Tree-Weighted SVM Approach

ADRC and IFOC Control of a Sensorless Induction Motor Driven by a Multilevel Converter Using SVM Approach and PV Generators

This paper offers a system for an electric vehicle. It consists of digitally controlling an induction motor without using a speed sensor. The machine is powered by a five-level cascading H-bridge inverter. The SVM control principle is used to manage the status of the five-level inverter; this removes harmonics. The H-bridge inverter converter is powered by photovoltaic sources via a serial converter, using the maximum power point tracker control principle. This structure can also reduce shading losses. In the absence of a mechanical sensor, a dynamic model of the asynchronous machine is utilized with the state variables defined in the stator reference frame. The state vector consists of the components of the rotor flux and stator current. The article provides a comparison of two methods widely used on an induction motor drive. The adaptive model-reference system method and Luenberger observer are evaluated using an active control strategy to reject disturbances to minimize the impact of disturbances. The operating principles of each method are described, and the mathematical models of training systems are developed. Both methods provide a promise for high-speed estimate applications in simulation environments. The simulation results obtained show the correct operation of both observers. Perfect decoupling between the velocity and flow control loops is observed, taking into account any disturbances that may affect the system.

Development and optimization of a prediction system model for mechanical properties in rotary friction-welded polyamide joints using the SVM approach and GA optimization

Development and optimization of a prediction system model for mechanical properties in rotary friction-welded polyamide joints using the SVM approach and GA optimization

Adaptive directed support vector machine method for the reliability evaluation of aeroengine structure

Machine learning methods have been widely applied to structural reliability analysis, due to the excellent performance in modeling precision and efficiency. In this paper, an adaptive directed support vector machine model (ADSVM) is proposed by integrating the adaptive sampling technology (AST) and the developed directed support vector machine (DSVM), to improve the efficiency and accuracy of turbine blade reliability analysis. In the developed method, the AST is adopted to extract high quality samples, in respect of distributed probability density and the distances between sample values and response values. The DSVM was developed by introducing the penalty coefficients for all the slack variables, to improve the modeling accuracy of SVM approach. One numerical example and the reliability analysis of aeroengine high-pressure turbine blade were performed to validate the developed methods. As illustrated in this numerical investigation, the modeling precision of DSVM is improved by alleviating the lag effect of support vector regression. From the comparison of methods, it is demonstrated that the ADSVM has higher accuracy, efficiency and stability in reliability simulations, which are improved by ∼20 % and ∼46.2 %, respectively. The main efforts of this study are to propose a promising approach, ADSVM, for the reliability analysis of complex structures besides turbine blades, which hold the academical significance in enriching and developing mechanical reliability theory.

Enhancing chronic kidney disease prediction performance through algorithm fusion: A combined KNN - SVM approach

Chronic Kidney Disease (CKD) is characterized by impaired kidney function and its ability to maintain overall health. It often progresses slowly over time and can lead to serious complications if left untreated. In order to prevent consequences such as hypertension, anemia, bone fragility, poor nutrition, and neurological dysfunction, early identification of chronic kidney disease (CKD) is imperative. Large-scale datasets are mined for insights in the healthcare industry that help with well-informed decision-making. Machine learning has applications in user authentication, fraud detection, and medical science, demonstrating its adaptability to a range of problems, including the management of chronic kidney disease. Numerous machine learning algorithms and data mining classification techniques are used in the context of forecasting chronic diseases like CKD. The purpose of this study is to create a novel decision-support system for forecasting chronic kidney disease. In this study, the execution times, accuracy, and precision of Random Forest and SVM-KNN fusion are compared. The results indicate that SVM-KNN performs better in prediction accuracy than Random Forest, providing important insights into machine learning methods for CKD prediction.

Proposed Framework for Semantic Segmentation of Aerial Hyperspectral Images Using Deep Learning and SVM Approach

The combination of deep neural networks and assistance vector machines for hyperspectral image recognition is presented in this work. A key issue in the real-world hyperspectral imaging system is hyperspectral picture recognition. Although deep learning can replicate highly dimensional feature vectors from source data, it comes at a high cost in terms of time and the Hugh phenomenon. The selection of the kernel feature and limit has a significant impact on the presentation of a kernel-based learning system. We introduce Support Vector Machine (SVM), a kernel learning method that is used to feature vectors obtained from deep learning on hyperspectral images. By modifying the data structure's parameters and kernel functions, the learning system's ability to solve challenging problems is enhanced. The suggested approaches' viability is confirmed by the outcomes of the experiments. At a particular rate, accuracy of testing for classification is around 90%. Moreover, to significantly make framework robust, validation is done using 5-flod verification.

Critical analysis of hybrid learning models to detect morphed images

Machine learning (ML) algorithms produce different results with the kind of input data set or parameters passed to the algorithm. As per input data set, the analysis generally depends on the data type and amount of data set being used to train and test. Other parameters which affect the machine learning analysis are the CNN parameters or the hybrid approach being used. As there is no similar result for ML analysis on various data set, it is hard to predict which model will work most efficiently on the given data set. In this paper an analytical analysis of machine learning algorithms has been done to examine the working of various algorithms individually or in Hybrid mode. This paper studies CNN, CNN + RF, CNN +SVM approach and the theoretical parameters affecting them which helps in deciding the best suited algorithm with the given data set.

Efficient lung cancer detection using computational intelligence and ensemble learning.

Lung cancer emerges as a major factor in cancer-related fatalities in the current generation, and it is predicted to continue having a long-term impact. Detecting symptoms early becomes crucial for effective treatment, underscoring innovative therapy's necessity. Many researchers have conducted extensive work in this area, yet challenges such as high false-positive rates and achieving high accuracy in detection continue to complicate accurate diagnosis. In this research, we aim to develop an ecologically considerate lung cancer therapy prototype model that maximizes resource utilization by leveraging recent advancements in computational intelligence. We also propose an Internet of Medical Things (IoMT)-based, consumer-focused integrated framework to implement the suggested approach, providing patients with appropriate care. Our proposed method employs Logistic Regression, MLP Classifier, Gaussian NB Classifier, and Intelligent Feature Selection using K-Means and Fuzzy Logic to enhance detection procedures in lung cancer dataset. Additionally, ensemble learning is incorporated through a voting classifier. The proposed model's effectiveness is improved through hyperparameter tuning via grid search. The proposed model's performance is demonstrated through comparative analysis with existing NB, J48, and SVM approaches, achieving a 98.50% accuracy rate. The efficiency gains from this approach have the potential to save a significant amount of time and cost. This study underscores the potential of computational intelligence and IoMT in developing effective, resource-efficient lung cancer therapies.

An Improved Internet of Thing-based Optimized SVM Approach for ECG-founded Cardiac Arrhythmia Classification

Cardiovascular diseases (CVD) stand as the leading cause of global mortality, claiming millions of lives annually. An electrocardiogram (ECG) records the heart's electrical activity based on the Internet of Things (IoT), crucial in detecting cardiac arrhythmias (CA), characterized by irregular heart rates and rhythms. Signals from the MIT-BIH Arrhythmia Physio net database are analyzed. This chapter aims to propose a hybrid approach merging Genetic Algorithm-Support Vector Machine (GSVM) and Particle Swarm Optimization-Support Vector Machine (PSVM) for CA classification. The study introduces an algorithm for categorizing ECG beats into six groups using Independent Component Analysis (ICA)-derived features. Optimal SVM settings are determined using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) on ICA features computed via non-parametric power spectral estimation. The research delves into the origins and methodologies of GA and PSO. Simulation results comparing GSVM and PSVM are presented, emphasizing PSVM's superior performance in accuracy, sensitivity, specificity, and positive predictivity. Detailed performance metrics, including Sensitivity, Specificity, Positive Predictivity, and Accuracy percentages, are scrutinized and compared against the top classifier. The findings endorse PSVM's superiority over GSVM, indicating enhanced performance across multiple evaluation criteria.

Piecewise Linear Approximation-Driven Primal SVM Approach for Improved Iris Classification Efficiency

Classification, a crucial aspect of machine learning, revolves around the meticulous analysis of data. However, the complexity of diverse life forms on Earth poses a challenge in distinguishing species that share similar attributes. The iris flower, with its subspecies exemplifies this challenge. The aim of the paper is to develop a methodology that not only enhances classification accuracy but also effectively addresses computational efficiency, facilitating faster and more practical categorization of iris patterns. This novel approach named Piecewise Linear Approximation based SVM (PLA-SVM) is applied to flower species classification and is benchmarked against alternative machine learning techniques. Implementation is carried out utilizing MATLAB – GUROBI interface of and GUROBI Solver. The performance metrics such as accuracy, precision, F1 score and ROC – AUC Curve are used to compare proposed algorithm performance. This comprehensive analysis enables a comparative study of diverse algorithms, ultimately validating the proposed PLA-SVM technique using the Iris dataset. The numerical implementation results shows that the PLASVM outperforms the existing standard classifiers in terms of different performance matrices.

Classification of Cyclin Proteins Using Amino Acid Composition and an SVM Approach: An In-Depth Analysis

Classification of Cyclin Proteins Using Amino Acid Composition and an SVM Approach: An In-Depth Analysis

Enhancing diagnostic accuracy for unidentified primary tumors with remora-optimized novel machine learning approach

Unidentified originating Tumors (UPT) are a kind of cancer where the originating location of the disease is still unclear, despite cancer cells throughout the body. In other words, even when malignant cells are present, medical professionals are unable to pinpoint the precise organ or tissue where the disease first started. The medical industry offers a big opportunity for Machine Learning (ML) to contribute significantly to illness prediction. One of the primary health challenges that each country faces is the tumor or cancer. In this study, we create a Remora Optimized Gated Recurrent Neural Network (RO-GRNN) to predict UPTs. The proposed approach consists of three stages: pre-processing, classification, and optimization. At first, we classified the UPT using the datasets given in the UCI ML library. The acquired Magnetic Resonance Imaging (MRI)/ Computed Tomography (CT) images will therefore have noise, lowering the efficiency with which classification may be accomplished. Pre-processing techniques like filtering and contrast augmentation could be used to eliminate unwanted noise from the offered images. The Gated Recurrent Neural Network (GRNN) and the Remora Optimization Algorithm (ROA) were both used in the development of the suggested classifier. Multiple optimization procedures, including basic and parametric optimization, take advantage of the ROA inside the GRNN. The proposed approach is employed in Origin Pro, and F1-Measure, recall, precision, and accuracy are some of the performance matrices that are used to evaluate effectiveness. The suggested approach is contrasted with the current ANN, SVM, and LSTM approaches. This research revealed that the proposed method has a 98% accuracy rate for UPT prediction.

High Accuracy Classification of Populations with Breast Cancer: SVM Approach

High Accuracy Classification of Populations with Breast Cancer: SVM Approach

Fault Diagnosis of Electric Submersible Pumps Using a Three‐Stage Multiscale Feature Transformation Combined with CNN–SVM

A convolutional neural network support vector machine (CNN–SVM) method based on multichannel feature fusion is used for progressive fault diagnosis of offshore oil and gas wells. The excellent classification performance of CNN is attributed to its ability to extract feature representations from large amounts of easily distinguishable data. However, the capability of CNN is severely constrained by the noisy and small sample amount of the electric submersible pump fault data to be studied in this article. First, 12 representative statistical features are extracted from the raw data to reduce the noise. Then, the feature mapping model is designed based on CNN migration learning. Finally, SVM is used instead of softmax function to adopt representative features directly from the mapping model for fault classification. Comparative experimental results show that the accuracy of fault diagnosis using feature‐extracted samples is better than using the raw samples directly. The proposed CNN–SVM approach has the best classification results compared to SVM, BPNN, CNN, BPNN–SVM, CNN–Attention, CNN–LSTM, and CNN–LSTM–Attention, which implies that manual feature extraction is still an indispensable tool in the fault diagnosis process.

Collection of Partition Coefficients in Hexadecyltrimethylammonium Bromide, Sodium Cholate, and Lithium Perfluorooctanesulfonate Micellar Solutions: Experimental Determination and Computational Predictions.

This study focuses on determining the partition coefficients (logP) of a diverse set of 63 molecules in three distinct micellar systems: hexadecyltrimethylammonium bromide (HTAB), sodium cholate (SC), and lithium perfluorooctanesulfonate (LPFOS). The experimental log p values were obtained through micellar electrokinetic chromatography (MEKC) experiments, conducted under controlled pH conditions. Then, Quantum Mechanics (QM) and machine learning approaches are proposed for the prediction of the partition coefficients in these three micellar systems. In the applied QM approach, the experimentally obtained partition coefficients were correlated with the calculated values for the case of the 15 solvent mixtures. Using Density Function Theory (DFT) with the B3LYP functional, we calculated the solvation free energies of 63 molecules in these 16 solvents. The combined data from the experimental partition coefficients in the three micellar formulations showed that the 1-propanol/water combination demonstrated the best agreement with the experimental partition coefficients for the SC and HTAB micelles. Moreover, we employed the SVM approach and k-means clustering based on the generation of the chemical descriptor space. The analysis revealed distinct partitioning patterns associated with specific characteristic features within each identified class. These results indicate the utility of the combined techniques when we want an efficient and quicker model for predicting partition coefficients in diverse micelles.