Support Vector Machine Method Research Articles

Evaluation of Aeolian Sand Collapsibility Based on Physical Indicators in the Mu Us Desert, China

The collapsibility of aeolian sand has hindered the development of oil and gas resources and the construction of oil and gas stations in the Mu Us Desert. This study considered aeolian sand on the southern edge of the Mu Us Desert as the research object. Based on a water immersion load test, standard penetration test, and indoor geotechnical test, four evaluation indicators were selected, the water content, dry density, void ratio, and saturation. Combined with the support vector machine method, we established a method for evaluating the collapsibility of aeolian sand based on basic physical indicators. The results showed the following: (1) The degree of collapsibility was slight, with a small portion showing no collapsibility. And the load-settlement curve (P-s) was divided into three stages: the linear elastic deformation stage, the elastic–plastic deformation stage, and the collapsible deformation stage. (2) There was a strong relationship between the collapsibility coefficient and the four evaluation indicators for aeolian sand. Based on these indicators, we could accurately predict and evaluate the collapsibility coefficient. (3) Machine learning methods, such as the support vector machine, can effectively solve prediction and evaluation problems between variables when there is no clear mathematical relationship between multiple independent variables and a single dependent variable.

Enhancing ultrasound-guided brachial plexus nerve localization with ResNet50 and support vector machine

<p>Medical image segmentation and classification plays a vital role in nerve block/region identification, particularly for anesthesiologists relying on instinctual judgments. However, due to patient-specific anatomical variations, these methods sometimes lack precision. This research focuses on addressing the problem, by incorporating novel ensembling method of ResNet-50 and support vector machine (SVM) to achieve segmentation of dataset images and classification of nerve blocks respectively. The said novel ensemble model is trained on a publicly available dataset consisting of more than 16,800 images. The sole purpose of this work is to address the problem of peripheral nerve blocking (PNB) with the usage of ensemble modelling, while achieving the highest possible accuracy. This research will help practitioners in accurately identifying the location of brachial plexus and distinguishing the type of nerve block to be injected – interscalene and supraclavicular. The model, which integrates ResNet50 and SVM classifier, achieved a commendable 99.27% accuracy in identifying and classifying the brachial plexus region.</p>

Enhancing breast cancer diagnosis: a comparative analysis of feature selection techniques

Breast cancer is a significant contributor to female mortality, emphasizing the importance of early detection. Predicting breast cancer accurately remains a complex challenge within medical data analysis. Machine learning (ML) algorithms offer valuable assistance in decision-making and diagnosis using medical data. Numerous research studies highlight the effectiveness of ML techniques in improving breast cancer prediction. Feature selection plays a pivotal role in data preprocessing, eliminating irrelevant and redundant features to minimize feature count and improve classification accuracy. This study focuses on optimizing breast cancer diagnostics through feature selection methods, specifically genetic algorithms (GA) and particle swarm optimization (PSO). The research involves a comparative analysis of these methods and the application of a diverse set of ML classification techniques, including logistic regression (LR), support vector machine (SVM), decision tree (DT), and ensemble methods like random forest (RF), AdaBoost, and gradient boosting (GB), using a breast cancer dataset. The models' performance is subsequently evaluated using various performance metrics. The experimental findings illustrate that PSO achieved the highest average accuracy, reaching 99.6% when applied to AdaBoost, while GA attained an accuracy rate of 99.5% when employed with both AdaBoost and RF.

Cloud radon data for earthquake magnitude prediction using machine learning

<span>The study investigates the potential of integrating radon gas concentration telemonitoring systems with machine learning techniques to enhance earthquake magnitude prediction. Conducted in Pacitan, East Java, Indonesia, where the stations are near the active Grundulu fault, the research employs Random Forest (RF), Extreme Gradient Boosting (XGB), Neural Network (NN), AdaBoost (AB), and Support Vector Machine (SVM) methods. Utilizing real-time radon gas concentration measurements, the study aims to refine earthquake magnitude prediction, crucial for disaster preparedness. The evaluation involves multiple metrics like Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Mean Squared Error (MSE), Symmetric Mean Absolute Percentage Error (SMAPE), and cnSMAPE. XGB and SVM emerge as top performers, showcasing superior predictive accuracy with minimal errors across various metrics. XGB achieved MAE (0.33), MAPE (6.03%), RMSE (0.51), MSE (0.26), SMAPE (0.06), and cnMAPE (0.97), while SVM recorded MAE (0.34), MAPE (6.20%), RMSE (0.51), MSE (0.26), SMAPE (0.06), and cnMAPE (0.97). The analysis reveals XGB as the most effective method, boasting the lowest error values. The study underscores the importance of expanding data availability to enhance predictive models, ultimately contributing to more precise earthquake magnitude predictions and effective mitigation strategies.</span>

Speech Signal Analysis in Patients with Parkinson’s Disease, Taking into Account Phonation, Articulation, and Prosody of Speech

This study involved performing tests to detect Parkinson’s disease (PD) based on voice changes, including speech phonation, articulation, and prosody, in patients with PD using different types of speech signal. For this purpose, during the first stage of the investigation, three separately modeled PD diagnosis systems using different types of speech signal characteristics were defined. The classification results were obtained when the SVM method was applied compared to the k-nearest neighbors method applying 1-nn in general. The tests were carried out within the database of patient voice recordings collected in the Department of Neurology at the Medical University of Warsaw. The second stage of the research was the selection of descriptors. The SFFS (sequential floating forward) method was applied together with the k-nn and SVM classifier. These subsets were used to create a new system based on a descriptor loose integration. Within the experiments conducted, general diagnosis results lead to improved classifier performance only in certain cases. This prompted the authors to conduct the last experimental research stage—selection at the feature fusion stage. Feature evaluation ranking methods (Relief, Fisher Score, F-tests, Chi-square) were applied for this purpose. With 10-fold validation, the k-nn method achieved an recognition rate of 92.2% with 91.1% sensitivity and 93.3% specificity.

Classification of plants based on time-series SAR coherence and intensity data in Yancheng coastal wetland

ABSTRACT Investigating coastal wetland plant communities is of great significance for wetland monitoring due to the important functions of coastal wetlands, such as maintaining biodiversity and mitigating global climate change. Current studies on wetland plants mostly rely on optical data, with few utilizing synthetic aperture radar (SAR) data. Moreover, these studies often analysed single temporal SAR data, which limited the exploration of the valuable information present in time-series SAR data. Therefore, in this paper, we proposed a technique for mapping coastal wetland plant types based on time-series SAR coherence and intensity data to fully utilize the information from these data. We utilized Sentinel-1 Single Look Complex (SLC) images covering the Yancheng coastal wetland for the entire year of 2021 to investigate the effectiveness of using dual-polarization interferometric coherence and intensity-derived information from time-series Sentinel-1 data as features for classification. Plant classification was conducted using support vector machine (SVM) and random forest (RF) methods. Our results demonstrated that integrating time-series dual-polarization coherence and intensity-derived information resulted the best classification accuracy, with an overall accuracy (OA) of 89.79% and a Kappa coefficient of 0.858. This highlights the effectiveness of combining coherence and intensity data from time-series Sentinel-1 for monitoring plant cover in coastal wetlands.

Resting-state functional magnetic resonance imaging and support vector machines for the diagnosis of major depressive disorder in adolescents

BACKGROUND Research has found that the amygdala plays a significant role in underlying pathology of major depressive disorder (MDD). However, few studies have explored machine learning-assisted diagnostic biomarkers based on amygdala functional connectivity (FC). AIM To investigate the analysis of neuroimaging biomarkers as a streamlined approach for the diagnosis of MDD in adolescents. METHODS Forty-four adolescents diagnosed with MDD and 43 healthy controls were enrolled in the study. Using resting-state functional magnetic resonance imaging, the FC was compared between the adolescents with MDD and the healthy controls, with the bilateral amygdala serving as the seed point, followed by statistical analysis of the results. The support vector machine (SVM) method was then applied to classify functional connections in various brain regions and to evaluate the neurophysiological characteristics associated with MDD. RESULTS Compared to the controls and using the bilateral amygdala as the region of interest, patients with MDD showed significantly lower FC values in the left inferior temporal gyrus, bilateral calcarine, right lingual gyrus, and left superior occipital gyrus. However, there was an increase in the FC value in Vermis-10. The SVM analysis revealed that the reduction in the FC value in the right lingual gyrus could effectively differentiate patients with MDD from healthy controls, achieving a diagnostic accuracy of 83.91%, sensitivity of 79.55%, specificity of 88.37%, and an area under the curve of 67.65%. CONCLUSION The results showed that an abnormal FC value in the right lingual gyrus was effective as a neuroimaging biomarker to distinguish patients with MDD from healthy controls.

Drug–target interaction prediction by integrating heterogeneous information with mutual attention network

BackgroundIdentification of drug–target interactions is an indispensable part of drug discovery. While conventional shallow machine learning and recent deep learning methods based on chemogenomic properties of drugs and target proteins have pushed this prediction performance improvement to a new level, these methods are still difficult to adapt to novel structures. Alternatively, large-scale biological and pharmacological data provide new ways to accelerate drug–target interaction prediction.MethodsHere, we propose DrugMAN, a deep learning model for predicting drug–target interaction by integrating multiplex heterogeneous functional networks with a mutual attention network (MAN). DrugMAN uses a graph attention network-based integration algorithm to learn network-specific low-dimensional features for drugs and target proteins by integrating four drug networks and seven gene/protein networks collected by a certain screening conditions, respectively. DrugMAN then captures interaction information between drug and target representations by a mutual attention network to improve drug–target prediction.ResultsDrugMAN achieved the best performance compared with cheminformation-based methods SVM, RF, DeepPurpose and network-based deep learing methods DTINet and NeoDT in four different scenarios, especially in real-world scenarios. Compared with SVM, RF, deepurpose, DTINet, and NeoDT, DrugMAN showed the smallest decrease in AUROC, AUPRC, and F1-Score from warm-start to Both-cold scenarios. This result is attributed to DrugMAN’s learning from heterogeneous data and indicates that DrugMAN has a good generalization ability. Taking together, DrugMAN spotlights heterogeneous information to mine drug–target interactions and can be a powerful tool for drug discovery and drug repurposing.

Prediction of soil organic carbon and total nitrogen affected by mine using Vis–NIR spectroscopy coupled with machine learning algorithms in calcareous soils

The utilization of visible-near infrared (Vis–NIR) spectroscopy presents a nondestructive, fast, reliable and cost-effective approach to predicting total nitrogen (TN) and organic carbon (OC) levels. This study employed a combination of Vis–NIR spectroscopy, partial least-squares regression (PLSR), and support vector machine (SVM) models to investigate the effects of mining on TN and OC stocks in both the topsoil (0–10 cm) and subsoil (10–40 cm). 105 soil samples were collected from agricultural areas near an iron mine, polluted, moderately-polluted, and non-polluted sites. Results indicated that soils at the non-polluted site had the highest of soil OC stocks (7.5 kg m–2) and total nitrogen (2.5 kg m–2), followed by the moderately-polluted site. Furthermore, it was observed that soils from the polluted site displayed the highest spectral reflectance. The spectral bands in the range of 500–700 nm showed the strongest correlation with soil organic carbon content. Notably, the SVM method utilizing Vis–NIR spectroscopy provided superior predictions for both subsoil and topsoil organic carbon and total nitrogen compared to the PLSR methods. Additionally, SVM demonstrated better performance in predicting topsoil soil organic carbon (R2 = 0.87, RMSE = 0.13%, and RPD = 2.8) and total nitrogen (R2 = 0.91, RMSE = 0.13%, and RPD = 2.4) compared to the subsoil, owing to the larger OM content in the topsoils.

DANA App Sentiment Analysis: Comparison of XGBoost, SVM, and Extra Trees

This research aims to analyze sentiment on DANA application reviews to find out user perceptions by comparing Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Extra Trees Classifier classification methods. DANA application review data is obtained from the Kaggle site which consists of 50,000 Indonesian-language reviews labeled with positive and negative sentiments. The research stages include data preprocessing to clean and prepare the review text, applying word weighting using Word2Vec to give weight to words based on their context, balancing sentiment classes using SMOTE to address the imbalance of positive and negative review classes. It should be noted that the initial proportion of data before applying SMOTE may affect the results. The data is then divided into training and testing sets, then the models are trained and evaluated using Confusion Matrix and K-Fold Cross-Validation. The results of the three classification methods are measured by the accuracy matrix and F1-Score to assess model performance, the SVM and XGBoost methods obtained an accuracy of 93% and the ETC method achieved an F1-Score value of 96% at K=6, the three models proved to be very accurate in predicting the sentiment of DANA application reviews both positive and negative. The practical implications of this research can identify areas for application improvement, develop popular features, personalize services based on user preferences, and manage application reputation.

Water Level Classification for Detect Flood Disaster Status Using KNN and SVM

Flooding occurs when the water's surface elevation exceeds the average level, overflowing river water and creating inundation in low-lying areas. Early warning for potential floods significantly reduces losses, such as human casualties and property damage. In this context, the flood disaster classification system uses water surface elevation data from the Water Resources Agency to predict the likelihood of floods using the K-Nearest Neighbors (KNN) Algorithm. This research aims to classify flood status based on water surface elevation using the K-Nearest Neighbors and Support Vector Machine(SVM) methods in the Ciliwung River. The study results indicate that the SVM algorithm outperforms the KNN algorithm. The SVM algorithm used parameter C ranging from 1 to 10 in the scenarios, and the RBF kernel achieved 100% accuracy. On the other hand, the KNN algorithm achieved 100% accuracy only for K values of 1, 2, 3, 4, and 5 in scenarios where K ranged from 1 to 10.

Machine learning for improved drought forecasting in Chhattisgarh India: a statistical evaluation

Meteorological drought is one of the major natural hazards that affects the ecosystem of the Central Indian state of Chhattisgarh. This study delves into the analysis, comparison, and prediction of drought trends spanning the period from 1993 to 2023 in the study area. Employing a comprehensive methodology, utilization of the Modified Mann–Kendall test to analyze drought trends, while assessing drought severity through the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI) has been done. Further research entails assessing the link between SPI and SPEI utilizing the Pearson correlation coefficient and simple linear regression techniques. Additionally, the Support Vector Machine (SVM) and Random Forest (RF) methods were used for predictive modelling feasibility. The findings helped to deepen our understanding of drought dynamics in the region, providing important insights for drought mitigation and adaptation efforts. This study emphasizes the importance of using a variety of statistical techniques and machine learning algorithms to thoroughly analyze, compare, and forecast drought patterns, thereby informing evidence-based decision-making for sustainable water resource management and agricultural planning in Chhattisgarh, India.

Analisis Sentimen Masyarakat terhadap Pelayanan e-KTP dengan Metode Support Vector Machine

The rapid development of information and communication technology allows society to access various information needed in daily life. The Law of the Republic of Indonesia Number 23 of 2006 concerning population administration serves as an important element in population management. Population documents are issued by official institutions and have legal legitimacy as valid evidence. The method used in this research regarding public sentiment towards e-ID card services is the survey method, which aims to collect data from a large population using a smaller sample. The steps or processes in this research using the SVM method consist of case folding, cleaning, tokenizing, normalization, stopword removal, and stemming. Based on the classification of 150 test data using SVM, the number of positive sentiments recorded is 110 opinions, while negative sentiments recorded are 40 opinions.

Prediction of Hydrogen Production from Solid Oxide Electrolytic Cells Based on ANN and SVM Machine Learning Methods

In recent years, the application of machine learning methods has become increasingly common in atmospheric science, particularly in modeling and predicting processes that impact air quality. This study focuses on predicting hydrogen production from solid oxide electrolytic cells (SOECs), a technology with significant potential for reducing greenhouse gas emissions and improving air quality. We developed two models using artificial neural networks (ANNs) and support vector machine (SVM) to predict hydrogen production. The input variables are current, voltage, communication delay time, and real-time measured hydrogen production, while the output variable is hydrogen production at the next sampling time. Both models address the critical issue of production hysteresis. Using 50 h of SOEC system data, we evaluated the effectiveness of the ANN and SVM methods, incorporating hydrogen production time as an input variable. The results show that the ANN model is superior to the SVM model in terms of hydrogen production prediction performance. Specifically, the ANN model shows strong predictive performance at a communication delay time ε = 0.01–0.02 h, with RMSE = 2.59 × 10−2, MAPE = 33.34 × 10−2%, MAE = 1.70 × 10−2 Nm3/h, and R2 = 99.76 × 10−2. At delay time ε = 0.03 h, the ANN model yields RMSE = 2.74 × 10−2 Nm3/h, MAPE = 34.43 × 10−2%, MAE = 1.73 × 10−2 Nm3/h, and R2 = 99.73 × 10−2. Using the SVM model, the prediction error values at delay time ε = 0.01–0.02 h are RMSE = 2.70 × 10−2 Nm3/h, MAPE = 44.01 × 10−2%, MAE = 2.24 × 10−2 Nm3/h, and R2 = 99.74 × 10−2, while at delay time ε = 0.03 h they become RMSE = 2.67 × 10−2 Nm3/h, MAPE = 43.44 × 10−2%, MAE = 2.11 × 10−2 Nm3/h, and R2 = 99.75 × 10−2. With this precision, the ANN model for SOEC hydrogen production prediction has positive implications for air pollution control strategies and the development of cleaner energy technologies, contributing to overall improvements in air quality and the reduction of atmospheric pollutants.

Seasonal Prediction Model for Airborne Pollen Content in Beijing Urban Area

Airborne pollen is considered to be one of the air pollutants that can cause allergic reactions in humans, leading to the occurrence or aggravation of a series of allergic diseases. The latest study showed that the positive rate of pollen allergens in allergic rhinitis patients in urban areas of Beijing exceeded 80%. Accurate prediction of pollen content could provide more effective assistance to susceptible populations. Based on the measured data from multiple stations in the urban area of Beijing during the pollen season from 2021 to 2022, the spatiotemporal distribution characteristics of pollen content were analyzed. The results showed that the main meteorological factors affecting spring pollen content in the urban area of Beijing were daily average wind speed, 3-day average temperature, water vapor pressure, daily average, temperature, and accumulated temperature. The main meteorological factors affecting autumn pollen content were 3-day average temperature, water vapor pressure, minimum surface temperature, and daily average temperature. In addition, it was found that there was a consistent spatial correlation between the current air pollen content and meteorological elements in the urban area of Beijing, but this correlation had significant seasonal differences. Furthermore, the Granger causality test method was applied to select the main meteorological factors that affected airborne pollen content in the urban area of Beijing, and two prediction models for air pollen content in the Beijing urban area for different seasons were established based on the support vector machine method （SVM） and multiple linear regression theory. The test of the prediction results for 2023 showed that both the SVM model considering seasonal differences and the multiple linear regression model could predict the daily distribution trend of pollen content well. The overall correlation coefficients between the predicted pollen content and the measured values were 0.693 and 0.636 （P <0.01）, respectively. Additionally, both models had good predictive ability for several severe content pollen pollution events within the year. In the spring of 2023, the prediction accuracy of the SVM model and linear model were 61.2% and 60.1%, respectively. During autumn, the prediction accuracy was 68.1% and 66.7%, respectively. The performance was better than that of existing business models, especially in the cross-level error improvement of heavy pollution event prediction. The research results provide reference value for further improving the prediction technology of airborne pollen content in the Beijing area.

Improved SVM Classification Using Particle Swarm Optimization for Student Completion Prediction System

Timely completion of a study program is crucial for evaluating the quality of universities. To achieve timely completion, student’s progress needs to be monitored early in order to ensure that they can complete the given task on time. This process is particularly important because universities often enroll thousands of students, thereby making individual supervision impractical. An effective solution to this problem is leveraging machine learning to develop a system that predicts whether student will complete the study without delay. Therefore, this study used Support Vector Machine (SVM) method for classification, with RBF kernel. Optimization of SVM classification was achieved by ensuring the values for Soft Margin C parameter and kernel parameter were correct. In addition, Particle Swarm Optimization (PSO) method was used to determine the optimal SVM parameter values. Consequently, the resulting model was evaluated using Cross Fold Validation. The optimized SVM parameter identified through PSO were gamma of 0.0085 and C of 0.4196. The average training accuracy recorded is 82.58%, with 81.22% validation, these results can be categorized into Good Classification. Finally, the application of PSO in optimization resulted in SVM models that avoided overfitting, as shown by the closeness of training and validation values.

Potential diagnostic markers and therapeutic targets for non-alcoholic fatty liver disease and ulcerative colitis based on bioinformatics analysis and machine learning.

Non-alcoholic fatty liver disease (NAFLD) and ulcerative colitis (UC) are two common health issues that have gained significant global attention. Previous studies have suggested a possible connection between NAFLD and UC, but the underlying pathophysiology remains unclear. This study investigates common genes, underlying pathogenesis mechanisms, identification of diagnostic markers applicable to both conditions, and exploration of potential therapeutic targets shared by NAFLD and UC. We obtained datasets for NAFLD and UC from the GEO database. The DEGs in the GSE89632 dataset of the NAFLD and GSE87466 of the UC dataset were analyzed. WGCNA, a powerful tool for identifying modules of highly correlated genes, was employed for both datasets. The DEGs of NAFLD and UC and the modular genes were then intersected to obtain shared genes. Functional enrichment analysis was conducted on these shared genes. Next, we utilize the STRING database to establish a PPI network. To enhance visualization, we employ Cytoscape software. Subsequently, the Cytohubba algorithm within Cytoscape was used to identify central genes. Diagnostic biomarkers were initially screened using LASSO regression and SVM methods. The diagnostic value of ROC curve analysis was assessed to detect diagnostic genes in both training and validation sets for NAFLD and UC. A nomogram was also developed to evaluate diagnostic efficacy. Additionally, we used the CIBERSORT algorithm to explore immune infiltration patterns in both NAFLD and UC samples. Finally, we investigated the correlation between hub gene expression, diagnostic gene expression, and immune infiltration levels. We identified 34 shared genes that were found to be associated with both NAFLD and UC. These genes were subjected to enrichment analysis, which revealed significant enrichment in several pathways, including the IL-17 signaling pathway, Rheumatoid arthritis, and Chagas disease. One optimal candidate gene was selected through LASSO regression and SVM: CCL2. The ROC curve confirmed the presence of CCL2 in both the NAFLD and UC training sets and other validation sets. This finding was further validated using a nomogram in the validation set. Additionally, the expression levels of CCL2 for NAFLD and UC showed a significant correlation with immune cell infiltration. This study identified a gene (CCL2) as a biomarker for NAFLD and UC, which may actively participate in the progression of NAFLD and UC. This discovery holds significant implications for understanding the progression of these diseases and potentially developing more effective diagnostic and treatment strategies.

Mining interpretable fuzzy If-Then linguistic rules from energy and economic data to forecast CO[formula omitted] emissions of regions in China

Forecasting CO2 emission is the one of most important issues for the “30⋅60” CO2 emission target in China. Due to unbalanced socio-economic developments of regions in China, exactly forecasting CO2 emissions of provinces depend on their energy consumptions and economic developments. In the paper, a novel method based on K-means clustering method and computing with words is proposed to forecast CO2 emissions of 30 provinces, which is consisted by (1) K-means clustering method is used to respectively cluster energy consumption and economic datasets of provinces and the interpretable fuzzy If-Then linguistic rules of CO2 emissions are mined from the clusters; (2) computing with words method is utilized to transform fuzzy If-Then linguistic rules into fuzzy If-Then rules with membership functions on the universe of discourse; (3) a fuzzy inference method is adopted to forecast CO2 emissions of 30 provinces. To show the usefulness and effectiveness of the novel method, energy consumptions and economic datasets of 30 provinces from 1997 to 2021 are employed to forecast CO2 emissions, metrics of MAE, MAPE, RMSE and the out-of-sample Roos2 are utilized to evaluate CO2 emission forecasting of 30 provinces, means of them reach 13.304, 15.279, 0.081 and 0.965. By comparative analysis for forecasting CO2 emissions of 30 provinces, means of MAE, MAPE, RMSE and the out-of-sample Roos2 by the novel method are more than SVM, ANFIS and MLR methods. In addition, four kinds of mechanisms influencing CO2 are discovered and analyzed by the fuzzy If-Then linguistic rules of 30 provinces, which can help to improve energy consumption and sustainable development of 30 provinces in China.

Vehicle Lane Changing Game Model Based on Improved SVM Algorithm

In order to improve the autonomous lane-changing performance of unmanned vehicles, this paper aims to solve the problem of inaccurate decision classification in traditional support vector machine (SVM) algorithms applied to the lane-changing decision-making stage of intelligent driving vehicles. By using game theory-related theories and combining the improved support vector machine (SSA-SVM) method, a vehicle autonomous lane-changing strategy based on game theory is established. The optimized SVM method has certain advantages for vehicle lane-changing decision-making with a small sample size in actual production processes. The lane-changing decision judgment accuracy rate of the SSA-SVM algorithm model can reach 93.6% compared with the SVM algorithm model without algorithm optimization; the SSA-SVM algorithm model has obvious advantages in decision performance and running speed. Therefore, the proposed new algorithm can effectively solve the problem of the objective consideration of the payoff function in conventional decision game theory.

Splitting Method for Support Vector Machine in Reproducing Kernel Banach Space with a Lower Semi-continuous Loss Function

Splitting Method for Support Vector Machine in Reproducing Kernel Banach Space with a Lower Semi-continuous Loss Function