Adjusted bat algorithm for tuning of support vector machine parameters

Automatic recognition of skin symptom plays an importance role in the skin diagnosis and treatment. Feature selection is to increase the classification performance of skin symptom. In this paper, the effects of feature selection on the classification of 4-class skin symptoms (chloasma, blackhead, freckled and comedone) are analyzed. Support vector machine (SVM) is employed to construct classifier, the parameters setting is very crucial to the learning results and generalization ability of SVM, and many irrelevant and redundant features degrade the performance of classification, furthermore, the choice of SVM parameters is influenced by the feature subset taken into account and vice versa. So a joint optimization method for selecting features and SVM parameters is proposed. Genetic algorithms, which have a lot of improvements about fitness, crossover and mutation in comparison with simple genetic algorithms, is to achieve a balance between the classification accuracy and the size of the feature subsets selected and have a fast convergence rate. Furthermore, ‘one-against-one’ approach is used to solve multi-class classification problems and a comparison of the model performances is made among the results of the joint optimization and the single optimization of features or SVM parameters in the experiments. The simulation result shows that our approach can find subsets of features for 4-class skin symptoms classification with higher average cross validation accuracy and a higher rate of convergence compared with single optimization of features or SVM parameters.

Support Vector Machine (SVM) has become a popular method in machine learning in recent years. SVM is widely used as a tool in many classifiction areas. The selection optimum values of the parameters (model selection) for SVM is an important step in SVM design. This paper presents the results of research and testing method Particle Swarm Optimization (PSO) in selecting the parameters for SVM. Here we focus on the selection parameter γ of the RBF function and soft margin parameter C of SVM for classification problems. In this paper we propose a Particle Swarm Optimization variation model which combine the cognition-only model with the social-only model and use randomised low discrepancy sequences for initialising particle swarms. We then evaluate the suggested strategies with a series of experiments on 6 benchmark datasets. Experimental results demonstrate the model we proposed better than grid search and full PSO-SVM model.

This research work presents a method of smokestack emission predicting model based on Latin hypercube sampling (LHS) and support vector machines (SVM). To solve the problem of predicting the concentration of smokestack emission, the Latin hypercube sampling method is adopted in a circular area above the smokestack to choose sample points, while the support vector machines regression analysis is carried out on the small data set and is evaluated by the mean square error. At the same time, an efficient parameter optimization method is proposed to reduce the mean square error and improve the prediction precision. With LIBSVM toolbox of MATLAB achieving the SVM regression analysis, SVM regression analysis and parameter optimization method were verified by a mathematical way. It turns out that the optimal parameters C and σ is respectively 2.8482 and 16, and the mean square error is 0.023011 which is acceptable. This study provides a reference sampling method and prediction model with parameters optimization for the detection of smokestack emission concentration.

This paper proposes a hybrid Electroencephalogram (EEG) classification approach based on grey wolf optimizer (GWO) enhanced support vector machines (SVMs) called GWO-SVM approach for automatic seizure detection. In order to decompose EEG into five sub-band components, the discrete wavelet transform (DWT) was utilized to extracted features set. Then, this features are used to train the SVM with radial basis function (RBF) kernel function. Further, GWO was used for selecting the significant feature subset and the optimal parameters of SVM in order to obtain a successful EEG classification. The experimental results proved that the proposed GWO-SVM approach, able to detect epileptic and could thus further enhance the diagnosis of epilepsy with accuracy 100%. Furthermore, the proposed approach has been compared with genetic algorithm (GA) with support vector machines (GA-SVMs) and SVM using RBF kernel function. The computational results reveal that GWO-SVM approach achieved better classification accuracy outperforms both GA-SVM and typical SVMs.

Three dimension finite element model (3D-FEM) of the spherical motor is presented in this paper. By analysis of one pair of stator-rotor poles, nonlinear regression model of one pair of stator-rotor poles based on the support vector machine (SVM) is introduced. Parameters optimization of one pair of stator-rotor poles for the maximal torque is also introduced which is based on chaos and uses the SVM regression model. Simulation results prove that using the SVM nonparametric modeling and parameter optimization based on chaos provide a novel way for finding the optimal structural parameters of the spherical motor.

Vehicle target recognition technology is an important technology in the auxiliary safe driving system, which greatly improves Vehicle safety assist driving. This paper proposes a method to identify vehicle target recognition with lidar point cloud data and machine learning; This method first establishes an ROI (region of interest), and uses voxel grid filter to downsample the lidar point cloud data in this area to reduce the amount of processed data, then use RANSAC (random sampling consensus) to remove ground points that are useless for the recognition process, and then use Euclidean clustering for clustering. A rough classifier is set to initially eliminate obstacles that cannot be vehicles, then the features of each cluster is extracted. SVM (Support Vector Machine) is used as an accurate classifier, the parameters of SVM is optimized through cross-validation and grid search to achieve the best classification effect. Finally, the optimized SVM is used to identify each cluster. Experiments show that this method can effectively detect the target vehicle in the ROI and has a good recognition accuracy.

Support Vector Machine (SVM) is an effective method for reservoir layer classification. However, its classification performance is influenced by many factors. In this paper, we study how the main factors affect classification accuracy of SVM on oil data. We collect two well-logging dataset, use k-Cross Validation and Grid Search to find the optimal SVM parameters, and compare the classification performance of different kernel function. The experiment results show that the type of kernel function affects classification rate most and Polynomial performs best.

In clinical field, the diagnosis of many diseases and their development stages depend on the detection of the corresponding bacteria. Raman spectroscopy and laser‐induced breakdown spectroscopy (LIBS) are two novel spectral diagnostic technologies for clinical bacteria identification. Both of them have been used in clinical detection combined with optimized support vector machine (SVM). In this paper, two feature‐level fusion methods (before feature selection fusion [BFSF] and after feature selection fusion [AFSF]) were proposed to improve the performance of SVM classifier and reduce the analyzing time (including the parameter tuning, model training, and testing time) simultaneously by combining data of LIBS and Raman spectroscopy. Using the most important 10 feature lines as the inputs of the optimized classifier, the analyzing time could be reduced to 1 to 2 min and the correct classification rate (CCR) achieved 95.67%. Without optimizing SVM parameters, the two proposed methods could achieve rapid and accurate classification of pathogenic bacteria further. The AFSF method showed better results with less fusion features while the BFSF method achieved higher CCR at 100% with more features. Both two methods costed around 0.2 s for analysis. These indicate that the proposed feature‐level fusion methods can improve the performance of SVM for bacteria detection. Maintaining the highest diagnostic accuracy, they can achieve the minimum analyzing time.

흡수, 분포, 대사, 배설 특성 및 독성을 예측하기 위한 효과적인 툴을 개발하는 것은 신약개발의 초기단계에서 NCE(new chemical entity)에 대한 가장 중요한 업무 중의 하나이다. 최근에 이런 시도중의 하나로서 ADME/T(absorption, distribution, metabolism, excretion, toxicity)관련 성질들의 예측에 support vector machine(SVM)을 이용하고 있다. 그리고 SVM은 ADME/T 성질들을 정확하게 예측하는데 많이 사용 되고 있다. 그러나 SVM 모델링에 두 가지 문제가 있다. 특성 선택(feature selection) 과 매개변수 설정(parameter setting)은 여전히 해결해야 할 과제이다. 이 두 가지 문제들은 SVM 분류의 효율성과 정확도에 결정적인 영향을 끼친다. 특히 특성 선택과 최적화된 SVM 변수의 설정은 서로 영향을 주기 때문에 동시에 다루어져야 한다. 여기서 우리는 genetic algorithm(GA) – 특성 선택에 사용 – 과 grid search(GS) method– 변수최적화에 사용 – 두 가지를 통합하는 효과적인 해결책을 제시하였다. ADME/T관련 성질 중 하나인 심장부정맥을 야기시키는 hERG 이온채널 저해제 분류 모델이 여기서 제안된 GA-GS-SVM을 위해 할당되고 테스트 되었다. 1891개의 화합물을 가지는 트레이닝 셋으로 단일 모델 3개, 앙상블 모델 3개, 총 6개의 모델을 만들었고 175개의 외부 데이터를 테스트 셋으로 사용하여 검증하였다. 데이터의 불균형 문제를 해결하기 위하여 GA-GS-SVM 단일 모델에 의한 예측 정확도와 GA-GS-SVM 앙상블 모델 예측 정확도를 비교하였으며, 앙상블모델을 사용하여 예측의 정확도를 높일 수 있었다. Developing effective tools for predicting absorption, distribution, metabolism, excretion properties and toxicity (ADME/T) of new chemical entities in the early stage of drug design is one of the most important tasks in drug discovery and development today. As one of these attempts, support vector machines (SVM) has recently been exploited for the prediction of ADME/T related properties. However, two problems in SVM modeling, i.e. feature selection and parameters setting, are still far from solved. The two problems have been shown to be crucial to the efficiency and accuracy of SVM classification. In particular, the feature selection and optimal SVM parameters setting influence each other, which indicates that they should be dealt with simultaneously. In this account, we present an integrated practical solution, in which genetic-based algorithm (GA) is used for feature selection and grid search (GS) method for parameters optimization. hERG ion-channel inhibitor classification models of ADME/T related properties has been built for assessing and testing the proposed GA-GS-SVM. We generated 6 different models that are 3 different single models and 3 different ensemble models using training set - 1891 compounds and validated with external test set - 175 compounds. We compared single model with ensemble model to solve data imbalance problems. It was able to improve accuracy of prediction to use ensemble model.

Land use/cover (LU/LC) classification provides proxies of the natural and social processes related to urban development, providing stakeholders with crucial information. Remotely sensed images combined with supervised classification are common to define land use, but high-performance classifiers remain difficult to achieve, due to the presence of model hyperparameters. Conventional approaches rely on manual adjustment, which is time consuming and often unsatisfying. Therefore, the goal of this study has been to optimize the parameters of the support vector machine (SVM) algorithm for the generation of land use/cover maps from Sentinel-2 satellite imagery in selected humid and arid (three study sites each) climatic regions of Iran. For supervised SVM classification, we optimized two important parameters (gamma in kernel function and penalty parameter) of the LU/LC classification. Using the radial basis function (RBF) of the SVM classification method, we examined seven values for both parameters ranging from 0.001 to 1000. For both climate types, the penalty parameters (PP) showed a direct relationship with overall accuracy (OA). Statistical results confirmed that in humid study regions, LU/LC maps produced with a penalty parameter >100 were more accurate. However, for regions with arid climates, LU/LC maps with a penalty parameter >0.1 were more accurate. Mapping accuracy for both climate types was sensitive to the penalty parameter. In contrast, variations of the gamma values in the kernel function had no effect on the accuracy of the LU/LC maps in either of the climate zones. These new findings on SVM image classification are directly applicable to LU/LC for planning and environmental and natural resource management.

Support Vector Machine (SVM) is a relatively novel classification technology, which has shown higher performance than traditional learning methods in many applications. Therefore, some security researchers have proposed an intrusion detection method based on SVM. However, the SVM algorithm is very sensitive to the choice of kernel function and parameter adjustment. Once the parameter selection is unscientific, it will lead to poor classification accuracy. To solve this problem, this paper presents a Grey Wolf Optimizer Algorithm based on Particle Swarm Optimization (PSOGWO) algorithm to improve the Intrusion Detection System (IDS) based on SVM. This method uses PSOGWO algorithm to optimize the parameters of SVM to improve the overall performance of intrusion detection based on SVM. The "optimal detection model" of SVM classifier is determined by the fusion of PSOGWO algorithm and SVM. The comparison experiments based on NSL-KDD dataset show that the intrusion detection method based on PSOGWO-SVM achieves the optimization of the parameters of SVM, and has improved significantly in terms of detection rate, convergence speed and model balance. This shows that the method has better performance for network intrusion detection.

There are usually a small amount and short sequence of prototype monitoring data on structural behavior during dangerous dam reinforcement. According to above data characteristics, some methods, such as support vector machine, particle swarm optimization, genetic algorithm, rough set, are combined to build the real-time monitoring model of safety status during structural reinforcement of dangerous dam. Firstly, the construction principle on standard support vector machine-based monitoring model of safety status is demonstrated. To improve the modeling accuracy and efficiency, particle swarm optimization and genetic algorithm are introduced to implement the support vector machine parameters optimization. Secondly, the ability on data mining in rough set is developed to determine the input vector of support vector machine. An approach is presented to obtain the simplified non-linear mapping relationship between dam behavior (effect-quantity) and its cause (influence-quantity). An index and its calculating formula are proposed to measure the influence-quantity importance. A real-time monitoring model based on rough set-support vector machine is established to describe reasonably the working mechanism during dangerous dam reinforcement. Lastly, the fitting and prediction capability of above monitoring model is demonstrated with an actual case.

The changes in China’s stock market are inseparable from the country’s economic development and macroeconomic regulation and control and have far-reaching significance in promoting China’s national economic growth. Compared with the Western developed capital market, China’s current stock market’s main smart investment strategy still has certain defects. Based on the SVM model, this paper establishes a predictive model that combines kernel parameters and parameter optimization to model. The mesh search method, genetic algorithm, and particle swarm optimization algorithm are used to optimize the parameters of the SVM under various kernel functions such as radial basis kernel function. The algorithm and particle swarm optimization algorithm optimize the parameters of the SVM to strengthen the applicability of the model in practice. The empirical results show that under the three-parameter optimization algorithms, the prediction results are higher than the random prediction accuracy, which indicates that it is effective to optimize the model by adjusting the parameters of the SVM. Among them, the SVM using the genetic algorithm parameter optimization under the radial basis kernel function shows the better prediction effect, which is the closest to the real value in the stock market forecast. The particle swarm algorithm supports the vector machine to predict the effect is slightly lower than the grid. Search method. In addition, through comparison experiments, the guess accuracy of BP neural network is worse than that of the support vector machine model before the adjustment. Finally, this paper uses the well-trained model to plan the stock smart investment plan.

Coronary artery disease (CAD) is a category of cardiovascular disease that causes the highest mortality rate in the world. CAD occurs due to plaque build-up on the walls of the arteries that supply blood to the heart and other organs of the body. To control the mortality rate, a practical model that is capable of predicting CAD is needed. Machine learning approaches have been used in solving various problems in various domains, including biomedicine. However, real-world data often has an unbalanced class distribution that can interfere with classifier performance. In addition, data has many features to process. This study focuses on effective modeling capable of predicting CAD using feature selection to handle high dimensional data and feature resampling to handle unbalanced data. Feature selection is very effective by eliminating irrelevant features from the training data. Hyperparameter tuning is also done to find the best combination of parameters in support vector machines (SVM). Our results show that the SVM cross-validated ten times has a more accurate training result. Furthermore, the grid search on SVM cross-validated ten times had more accurate training model results and achieved 88% accuracy on the test data.

This paper presents a novel fault diagnosis model for oil-immersed power transformers based on dissolved gas analysis. The model is rooted on the theories of rough set and support vector machine. A fitness function based on attribute dependence is developed to identify fault features to improve classification accuracy of transformer fault samples by using Genetic Algorithm. To get improved classification performance, grid search, genetic algorithm and particle swarm optimization are applied to search parameters of support vector machine. Compared with modified Rogers and back propagation neural network, the superiority of the established model is verified.