Performance Of Support Vector Machine Research Articles

Sensitivity of support vector machine to features selection for land cover classification based on sentinel-2 data over Riyadh urban arid area, Saudia Arabia

This study aimed to investigate the effect of three different combinations of features on land cover (LC) classification accuracy with support vector machine (SVM) and Sentinel-2 data over Riyadh city as an urban arid area. The three combinations included the original spectral bands, the spectral indices with spectral bands, and the selected features after applying recursive feature elimination (RFE). The results showed that with constant sample size, adding the spectral indices had a negative influence on SVM performance accuracy metrics. On the other hand, applying RFE as a feature selection improved the accuracy of LC by nearly 2% in the overall accuracy index and by 6% in the f1-score index. In addition, the feature selection approach decreased the processing time and the number of features for accurate LC classification by removing irrelevant and redundant features. In conclusion, the study showed the importance of applying feature selection with SVM for producing optimal LC classification in the selected urban arid study area.

IMPROVING DIGITAL SIGNATURE VERIFICATION ACCURACY THROUGH SUPPORT VECTOR MACHINE LEARNING: A COMPARATIVE STUDY

Digital signatures are widely used in electronic documents, and their verification is crucial to ensure document authenticity and security. However, digital signature verification can be challenging, especially when dealing with large amounts of data. In this paper, we present a comparative study of three Support Vector Machine (SVM) based methods for improving digital signature verification accuracy. We used a dataset of 10,000 digital signatures and compared the performance of linear SVM, polynomial SVM, and radial basis function (RBF) SVM. Our results showed that all three SVM-based methods improved the accuracy of digital signature verification compared to traditional methods. The RBF SVM method was found to be the most effective method for improving accuracy, with an accuracy of 98%.

Breast cancer classification application based on QGA-SVM

Early diagnosis of breast cancer plays an important role in improving survival rate. Physiological changes of breast tissue can be observed and measured through medical electrical impedance, and the results can be used as a preliminary diagnosis by doctors before treatment. In this paper, quantum genetic algorithm (QGA) and support vector machine (SVM) were combined to classify breast tissues to help clinicians in diagnosis. The algorithm uses QGA to optimize the parameters of SVM and improve the classification performance of SVM. In this experiment, the electrical impedance data measured from breast tissue provided by UCI [58] was used as the data set. Objectively speaking, the data volume of the data set is small and the representativeness is not strong enough. However, the experimental results show that QGA-SVM shows better classification performance, and it is better than SVM.

Early fault diagnosis based on reinforcement learning optimized-SVM model with vibration-monitored signals

Effective fault diagnosis maximizes economic benefits by ensuring the stability of machinery systems. Detecting the faults of the key components in machinery, such as rolling bearings, at an early stage, helps to avoid accidents to optimize the maintenance efficiency. It is well known that faulty bearings always deliver a message through their abnormal vibration variation, which can be captured by vibration acceleration sensors in order to facilitate the deteriorating status assessment. However, a clue for an early fault is so ambiguous and sometimes masked by ambient noise, which makes the early fault diagnosis a challenging problem. To tackle the problem, we propose a vibration signal-based data-driven early fault diagnosis approach based on the reinforcement learning (RL) optimized support vector machine (SVM) model. The exploration of the hyperparameter optimization using RL to improve SVM performance motivates this research. Firstly, the corresponding features in the time domain, frequency domain and time-frequency domain are extracted from the obtained vibration signals of the key components under certain working conditions. Subsequently, to better recognize the pattern of an early fault, linear discriminant analysis (LDA) is employed in fuzing the multi-domain early fault features. Finally, the fused features are fed into the RL optimized-SVM model for fault diagnosis. Experimental validation was performed with a public dataset of rolling bearings, and the results confirmed the effectiveness and superiority of the approach compared with other methods.

Modified Harris Hawks optimizer for feature selection and support vector machine kernels

<span lang="EN-US">The support vector machine (SVM), one of the most effective learning algorithms, has many real-world applications. The kernel type and its parameters have a significant impact on the SVM algorithm's effectiveness and performance. In machine learning, choosing the feature subset is a crucial step, especially when working with high-dimensional data sets. These crucial criteria were treated independently in the majority of earlier studies. In this research, we suggest a hybrid strategy based on the Harris Hawk optimization (HHO) algorithm. HHO is one of the lately suggested metaheuristic algorithms that has been demonstrated to be used more efficiently in facing some optimization problems. The suggested method optimizes the SVM model parameters while also locating the optimal features subset. </span><span lang="EN-AU">We ran the proposed approach </span><span lang="EN-US">HHO-SVM </span><span lang="EN-AU">on real biomedical datasets with 17 types of cancer for Iraqi patients in 2010-2012. </span><span lang="EN-US">The experimental results demonstrate the supremacy of the proposed HHO-SVM in terms of three performance metrics: feature selection accuracy, runtime, and number of selected features. The suggested method is contrasted with four well-known algorithms for verification: firefly (FF) algorithm, genetic algorithm (GA), grasshopper optimization algorithm (GOA), and particle swarm algorithm (PSO). The implementation of the proposed HHO-SVM approach reveals 99.967% average accuracy.</span>

Study on fault diagnosis algorithms of EHA based on CNN-SVM

Contrapose the highly integrated, complex working conditions and many kinds of faults of aircraft electro hydrostatic actuator(EHA), to diagnose the typical fault of EHA effectively, a fault diagnosis algorithm based on convolutional neural networks (CNN) and support vector machine(SVM) was proposed. Firstly, the fault date sets are entered on CNN for adaptive feature extraction, then the output of the fully connected layer of CNN are classified by using SVM. To improve the performance of SVM, dynamic inertia weight adaptive particle swarm optimization (IWAPSO) was used to optimize the SVM parameters. Finally, the sensitivity of SVM to noise was reduced by introducing ramp loss function. The results show that the accuracy of SVM after parameter optimization is 12.6% higher than that of standard SVM and 17.3% higher than CNN. The SVM based on the ramp loss function showed better robustness when using noisy test sets.

Analisis Sentimen Pengunjung Pulau Komodo dan Pulau Rinca di Website Tripadvisor Berbasis CRISP-DM

A sentiment analysis is needed to identify tourist preferences for products and services in a tourist destination. Therefore, this study uses the Cross-Industry Standard Procedure for Data Mining (CRISP-DM) method to classify visitor review data for Komodo Island and Rinca Island obtained from the Tripadvisor website based on negative and positive sentiments, then recommends the development of an information system that can optimize the products and services of tourist destinations on Komodo Island and Rinca Island. Meanwhile, the algorithms used are k-Nearest Neighbor (k-NN), Naïve Bayes Classifier (NBC), Support Vector Machine (SVM), and Decision Tree (DT). Based on the results of data classification using the word weighting method or Term Frequency Inverse Document Frequency (TF-IDF) through the sentiment extract operator, it can be known that the five words that most often appear in tourist reviews of Komodo Island are as follows: Komodo dragons (1894), dragons (1596), island (1492), tour (840), boat (774). Meanwhile, the five words that most often appear in tourist reviews of Rinca Island are as follows: komodo dragon (1042), dragons (962), island (882), rinca (606), and boat (372). In addition, the results of the classification of 564 Komodo Island tourist review data and 364 Rinca Island tourist review data using CRISP-DM-based k-NN, NBC, SVM, and DT algorithms, show that the Support Vector Machine (SVM) is the best-performing algorithm where the accuracy value is 99.69%, precision 100%, recall 99.39%, f-measure 99.69%, Area Under Curve (AUC) 100% and t-Test 0.958. Meanwhile, the results of processing tourist review data on Rinca Island products and services show that the Support Vector Machine (SVM) algorithm has the best performance with 100% accuracy, 100% precision, 100% recall, 100% f-measure, 100% Area Under Curve (AUC) and 0.964 t-Test. After comparing the performance of SVM before and after using the Synthetic Minority Oversampling Technique (SMOTE), it can be seen that the implementation of the algorithm becomes more optimal when using the SMOTE operator. Thus, SVM is a relevant algorithm used as a model for analyzing tourist sentiment on Komodo Island and Rinca Island based on CRISP-DM.

Deriving Operating Rules of Hydropower Reservoirs Using Multi-Strategy Ensemble Henry Gas Solubility Optimization-Driven Support Vector Machine

Hydropower is an important clean renewable energy that plays a key role in coping with issues such as global energy security, environmental protection, and climate change. In order to improve the optimal operation ability of hydropower reservoirs in the context of forecast runoff with limited accuracy and prediction period, there has been a growing interest in deriving operating rules of hydropower reservoirs. Reasonable operation decision is very important for safe operation of reservoirs and efficient utilization of water resources. Therefore, a novel method of operation rules derivation is proposed in this study. Optimal operation model of hydropower reservoir is established and support vector machine (SVM) is used to derive operation rules based on the optimal operation results. In order to improve the performance of SVM, the Henry gas solubility optimization (HGSO) is used to optimize its hyperparameters for the first time. Meanwhile, multiple strategies are applied to overcome the drawbacks of HGSO. The multi-verse optimizer (MVO) is used to enhance the exploration capability of basic HGSO. Quadratic interpolation (QI) is used to improve the exploitation ability of HGSO. In this study, the Xiluodu and Xiangjiaba hydropower reservoirs in the upper Yangtze River of China were selected as a case study. First, the improved HGSO called MVQIHGSO was tested on 23 classical benchmark functions. Then, it was employed to optimize hyperparameters of SVM model for deriving operation rules. The results and statistical studies indicate that the improved HGSO outperforms the comparison algorithms in exploration and exploitation. The obtained results imply that the novel method named MVQIHGSO-SVM can provide a new practical tool to deriving operation rules for hydropower reservoirs, which is conducive to the safe and efficient utilization of water resources.

Prediction of Flood Discharge Using Hybrid PSO-SVM Algorithm in Barak River Basin

A crucial necessity in integrated water resource management is flood forecasting. Climate forecasts, specifically flood prediction, comprise multifaceted tasks as they are dependant on several parameters for predicting the dependant variable, which varies from time to time. Calculation of these parameters also changes with geographical location. From the time when Artificial Intelligence was first introduced to the field of hydrological modelling and prediction, it has produced enormous attention in research aspects for additional developments to hydrology. This study investigates the usability of support vector machine (SVM), back propagation neural network (BPNN), and integration of SVM with particle swarm optimization (PSO-SVM) models for flood forecasting. Performance of SVM solely depends on correct assortment of parameters. So, PSO method is employed in selecting SVM parameters. Monthly river flow discharge for a period of 1969 - 2018 of BP ghat and Fulertal gauging sites from Barak River flowing through Barak valley in Assam, India were used. For obtaining optimum results, different input combinations of Precipitation (Pt), temperature (Tt), solar radiation (Sr), humidity (Ht), evapotranspiration loss (El) were assessed. The model results were compared utilizing coefficient of determination (R2) root mean squared error (RMSE), and Nash–Sutcliffe coefficient (NSE). The most important results are highlighted below.•First, the inclusion of five meteorological parameters improved the forecasting accuracy of the hybrid model.•Second, model comparison specifies that hybrid PSO-SVM model executed superior performance with RMSE- 0.04962 and NSE- 0.99334 compared to BPNN and SVM models for monthly flood discharge forecasting.•Third, applied optimization algorithm has easy implementation, simple theory, and high computational efficacy.Results revealed that PSO-SVM could be utilised as an improved alternate method for flood forecasting as it provided a higher degree of reliability and accurateness.

Performance Analysis of the Distributed Support Vector Machine Algorithm Using Spark for Predicting Flight Delays

In big data analysis requires powerful machine learning frameworks, strategies, and environments to analyze data at scale. Therefore, Apache Spark is used as a cluster computing framework to process big data in parallel and can run on multiple clusters. In this study, the Support Vector Machine (SVM) algorithm is used as a classification method to predict whether a flight will experience a delayed arrival. This study also aims to analyze the performance of the distributed SVM algorithm using the Apache Spark framework in classifying delayed flight arrivals. Running time evaluation is important in proving how fast the data processing is done using Apache Spark. In addition, there is a test to prove the effect of using the SVM algorithm with a distributed system on the results of the classification accuracy of delayed flight arrivals. Distributed SVM performance testing is carried out using variations in data size and the number of worker nodes in the built cluster. From the test results, it was found that the most effective number of worker nodes used in the flight delay classification process was 4 worker nodes with the lowest running time results from the experiment of 4 variations in the number of worker nodes. In terms of accuracy, adding the number of worker nodes does not affect the accuracy of the program. The difference in the accuracy of results is caused by the random oversampling process on the data performed on each system test. Using the SVM algorithm with Spark is sufficient to provide good performance in the classification process with the highest accuracy result in the test being 93.98 %.

Improving SVM performance for type II diabetes prediction with an improved non-linear kernel: Insights from the PIMA dataset

Type 2 diabetes is a chronic metabolic disease that affects a significant portion of the worldwide people. Prediction of this disease using different machine learning (ML) based algorithms has gained substantial attention due to its potential for early detection and effective intervention. One of the most powerful ML algorithm support vector machines (SVM) has proven to be effective in a variety of classification tasks, including diabetes prediction. However, the kernel function chosen has a substantial effect on the performance of SVM classifiers. This paper proposes an improved non-linear kernel for the SVM model to enhance Type 2 diabetes classification. The new kernel uses radial basis function (RBF) and RBF city block kernels that enable SVM to learn complex decision boundaries and adapt to the intricacies of the PIMA dataset. The PIMA dataset contains various clinical and demographic features of individuals. To address missing values and outliers, we impute them using the median, ensuring the integrity of the dataset. We tackle the class imbalance issue by leveraging a robust synthetic-based over-sampling approach.A comparative analysis is performed against several existing kernel functions to show that the proposed approach is superior in terms of various prediction evaluation matrices. Our recommended integrated kernel model also showed improved performance (ACC = 85.5, Recall = 87.0, Precision = 83.4, F1 score = 85.2, and AUC = 85.5) when compared to other approaches in the literature. The results of this study indicate that the proposed non-linear kernel in SVM outperforms existing kernel functions for predicting Type 2 diabetes using the PIMA dataset. Furthermore, a simulation study is carried out to robustify the proposed kernel in SVM and perform well. The improved accuracy and robustness of the model suggest its potential utility in clinical settings, aiding in the early identification and management of individuals at risk for developing diabetes.

Improving SVM Classification Performance on Unbalanced Student Graduation Time Data Using SMOTE

Student graduation accuracy is one of the indicators of the success of higher education institutions in carrying out the teaching and learning process and as a component of higher education accreditation. So it is not surprising that building a system that can predict or classify students graduating on time or not on time is necessary for universities to monitor the exact number of students graduating on time using educational technology. Unfortunately, educational technology or machine learning with data mining approaches is less accurate in classifying classes with unbalanced data. Therefore, this research purpose is to build a machine learning system that can improve classification performance on unbalanced class data between students who graduate on time and graduate late. This study applies the Synthetic Minority Oversampling Technique (SMOTE) method to improve the classifying performance of the Support Vector Machine (SVM) data mining method. The results of the study concluded that using the SMOTE method increased the accuracy, precision, and sensitivity of the SVM method in classifying class data of unbalanced student graduation times. The SVM performance score rises by 3% for classification accuracy, 8% for classification precision, and 25% for classification sensitivity.

IMPROVED SUPPORT VECTOR MACHINE PERFORMANCE USING PARTICLE SWARM OPTIMIZATION IN CREDIT RISK CLASSIFICATION

In Classification using Support Vector Machine (SVM), each kernel has parameters that affect the classification accuracy results. This study examines the improvement of SVM performance by selecting parameters using Particle Swarm Optimization (PSO) on credit risk classification, the results of which are compared with SVM with random parameter selection. The classification performance is evaluated by applying the SVM classification to the Credit German benchmark credit data set and the private credit data set which is a credit data set issued from a local bank in North Sumatra. Although it requires a longer execution time to achieve optimal accuracy values, the SVM+PSO combination is quite effective and more systematic than trial and error techniques in finding SVM parameter values, so as to produce better accuracy. In general, the test results show that the RBF kernel is able to produce higher accuracy and f1-scores than linear and polynomial kernels. SVM classification with optimization using PSO can produce better accuracy than classification using SVM without optimization, namely the determination of parameters randomly. Credit data classification accuracy increased to 92.31%.

Sustainable production using a hybrid IPSO optimized SVM-based technique: Fashion industry

The fashion industry is one of the most polluting industries in the world. Accordingly, it is crucial to gain a greater understanding of the products in this industry in order to prevent environmental degradation. Due to the rapid rate of transformation and the enormous volume of data, it is critical to develop an appropriate feature selection technique that improves managers' decision-making to predict the production of products with minimal environmental pollution. In this research, we proposed a new feature selection method based on Support Vector Machine (SVM) technique involving more than one environmental parameter, such as waste, pollution and energy. It served to predict the sustainable productions that achieve the highest number of customers and the lowest possible damage to the environment. Furthermore, we intended to optimize the SVM technique in feature selection by adopting the improved form of this technique through the Improved Particle Swarm Optimization (IPSO) algorithm and ultimately adjust the different kernel parameters involved in the SVM technique learning process. The overall objective of this study was to evaluate the performance of SVM in combination with IPSO algorithm and its impact on predicting high demand products and to enable smart decisions for managers to make sustainable production compared to other existing techniques. The results suggested that the accuracy of the test in the newly proposed hybrid method is higher than other similar methods owing to optimization of the parameters of SVM algorithm by IPSO as well as the adoption of kernels corresponding to the environmental parameter in SVM technique learning process.

XAI Framework for Cardiovascular Disease Prediction Using Classification Techniques

Machine intelligence models are robust in classifying the datasets for data analytics and for predicting the insights that would assist in making clinical decisions. The models would assist in the disease prognosis and preliminary disease investigation, which is crucial for effective treatment. There is a massive demand for the interpretability and explainability of decision models in the present day. The models’ trustworthiness can be attained through deploying the ensemble classification models in the eXplainable Artificial Intelligence (XAI) framework. In the current study, the role of ensemble classifiers over the XAI framework for predicting heart disease from the cardiovascular datasets is carried out. There are 303 instances and 14 attributes in the cardiovascular dataset taken for the proposed work. The attribute characteristics in the dataset are categorical, integer, and real type and the associated task related to the dataset is classification. The classification techniques, such as the support vector machine (SVM), AdaBoost, K-nearest neighbor (KNN), bagging, logistic regression (LR), and naive Bayes, are considered for classification purposes. The experimental outcome of each of those algorithms is compared to each other and with the conventional way of implementing the classification models. The efficiency of the XAI-based classification models is reasonably fair, compared to the other state-of-the-art models, which are assessed using the various evaluation metrics, such as area under curve (AUC), receiver operating characteristic (ROC), sensitivity, specificity, and the F1-score. The performances of the XAI-driven SVM, LR, and naive Bayes are robust, with an accuracy of 89%, which is assumed to be reasonably fair, compared to the existing models.

Recognition of EEG based on Improved Black Widow Algorithm optimized SVM

As a classifier suitable for nonlinear samples, support vector machines (SVM) is widely used in Electroencephalogram (EEG) signals pattern recognition. The performance of SVM depends mainly on the selection of model parameters. This paper modifies the reproductive formula of the Black Widow Optimization (BWO) algorithm to obtain an improved Black Widow Optimization (IBWO) algorithm, which solves the problem of the restricted search radius of the BWO algorithm. We construct an IBWO-SVM model in which IBWO is used to optimize the penalty parameter C and the kernel function parameter g of the SVM, and the optimized SVM model is applied to EEG signals classification. The effectiveness and superiority of IBWO-SVM is verified by using the BCI competition III dataset IVa EEG public dataset, and compared with the SVM optimized by the original BWO algorithm (BWO-SVM), the artificial fish swarm algorithm (AFSA-SVM) and the particle swarm optimization algorithm (PSO-SVM), The simulation results demonstrate that all indicators of the IBWO-SVM model are better than the three comparison models, in which the average classification accuracy on five subjects reaches 97.29%. In addition, the two-class motor imagery (left arm stretch and right fist clenched) EEG data collected from our experiment is also used to test the performance of the IBWO-SVM model. The average classification accuracy of the final twelve subjects is 5.21%, 4.16% and 1.47% higher than that of BWO-SVM, AFSA-SVM, and PSO-SVM, respectively. Therefore, the IBWO-SVM model can effectively improve the accuracy of EEG signals pattern recognition, which has a very important practical value.

Facial emotions recognition using local monotonic pattern and grey level co‐occurrence matrices images aided development

AbstractIn this article, local monotonic pattern (LMP) paired with grey level co‐occurrence matrix (GLCM) methods are suggested to identify facial emotions with a high identification rate even when the face pictures are rotated. The proposed method extracts image features using the properties of the LMP algorithm and features extracted from the GLCM, which are then fed into the Support Vector Machine (SVM) process that reduces the dimensionality of the features vector and classifies the output into different facial expressions or emotions. The SVM performance rate is then compared to the K‐nearest neighbour approach (KNN) to see which method produces the best facial emotion identification and categorization. The study identified facial emotions in the images using advanced algorithms of GLCM and LMP models to be compared. As a result, the accuracy of SVM and KNN was utilized to determine the method's usefulness in classification using the application of MATLAB. A result of more than 93% was achieved using the SVM method compared with 89.4% using the KNN for the recognition process. The study also demonstrated that this approach would lead to more classification outcomes if the LMP and GLCM are combined with an edge‐based technique yielding a new method that is more efficient and more effective.

Evaluation of Debris-Flow Vibration Signals Recorded at the Aiyuzi Stream in Shenmu Taiwan Using Machine Learning Methods

In recent years, due to the frequent occurrence of extreme weather due to climate change, the Taiwan region has often suffered from landslides and debris flows in the past 20 years. This study used the ground surface vibration signals collected by the geophone from seven debris flow events in the Shenmu area. Data were processed to represent the time series of velocity and accumulated energy per second. Datasets were established for model training and validation. In this study, Support Vector Machine (SVM) and Random Forest (RF) algorithms were used for comparison. After analyzing the data through balance processing (Synthetic Minority Oversampling Technique, SMOTE), a signal model of debris flow was established. The research results showed that the models using SVM and RF training had good accuracy, recall, and AUC values when choosing input data average of every 6 s and the 10-s time interval within which the data were marked as the occurrence of debris flow. The performance of SVM was better than that of RF after validation. Through the aforementioned research, the vibration signals of debris flow can be regarded as a reference factor, and the model established by the SVM method had acceptable performance and can be used for early-warning of debris flow.

Facial emotions recognition using local monotonic pattern and gray level co-occurrence matrices plant leaf images aided agriculture development

In this article, Local Monotonic Pattern (LMP) paired with Gray Level Co-occurrence Matrix (GLCM) methods are suggested in this study to identify facial emotions with a high identification rate even when the face pictures are rotated. The proposed method extracts image features using the properties of the LMP algorithm and features extracted from the GLCM, which are then fed into the Support Vector Machine (SVM) process that reduces the dimensionality of the features vector and classifies the output into different facial expressions or emotions. The SVM performance rate is then compared to the K-Nearest Neighbor approach (KNN) to see which method produces the best facial emotion identification and categorization. Consequently, the study identified facial emotions in the images using advanced algorithms of GLCM and LMP models to be compared with. As a result, the accuracy of SVM and KNN was utilized to determine the method's usefulness in classification using the application of MATLAB. A result of more than 93% has been achieved using SVM method compared with 89.4% using the KNN for the recognition process. The study also demonstrated that this approach will result in a more classification outcomes if the LMP and GLCM are combined with an edge-based technique which yield in a new method that is more efficient and more effective.

Radar signal recognition exploiting information geometry and support vector machine

Aiming at the recognition of low-probability-of-intercept (LPI) radar signals, a support vector machine (SVM)-based algorithm is proposed, where the information geometry theory is utilised to optimise the kernel function of the SVM. Since signals with different modulations have different characteristics in the time-frequency domain, the time-frequency transformation result of the LPI radar signal is considered as an image, referred to as the time-frequency image, and computer vision techniques are utilized to perform recognition. Specifically, the time-frequency images of different LPI radar signals are obtained via the Choi-Williams distribution (CWD) transform, and the AlexNet network, one improved convolutional neural network (CNN), is used to extract time-frequency features. Then, an SVM is adopted to recognise LPI radar signals due to its superiority in addressing the dimension disaster and non-linear inseparability issue. The extracted time-frequency features are fed into the SVM for classification and recognition. Note that the classification performance of SVM depends on the kernel function. Therefore, in the proposed algorithm, information geometry theory is exploited to improve the Gaussian kernel function, and the maximum margin between different categories of samples is further enlarged. As a consequence, the recognition accuracy for LPI radar signals with similar time-frequency images is effectively improved. In addition, the proposed algorithm has better robustness to small samples than other deep learning-based algorithms, since the SVM method minimises the structural risk instead of the empirical risk. Simulation results verify the effectiveness of the proposed algorithm.