Swarm Optimization-based Support Vector Research Articles

Modeling magnetic refrigeration capacity of doped EuTiO3 magnetocaloric compounds using swarm based intelligent computational method

This work models the magnetic refrigeration capacity (MRC) of doped europium titanate (EuTiO3) at different applied magnetic field using hybrid particle swarm optimization based support vector regression (SW-SVR) algorithm with ionic radii dopant descriptors. The developed model with Gaussian function (SW-SVR-Gas) shows better performance as compared with polynomial based model (SW-SVR-Pol) with improvement of 35.76 %, 0.13 % and 45.76 % using mean absolute error (MAE), correlation coefficient (CC) and root mean square error (RMSE) performance yardsticks, respectively. The developed SW-SVR-Gas model investigates the behavior of Eu1-xBaxTiO3 and EuTi1-xNixO3 doped europium titanate at different dopants concentration as well as applied field. Novelties of the developed model include circumvention of experimental difficulties associated with magnetic refrigeration capacity determination, implementation of simple molecular descriptors with high precision and accuracy. The demonstrated uniqueness of the developed model would strengthen exploration of refrigeration capacity of europium titanate based compounds for addressing global refrigeration crisis.

Tracing the geographic origin of CTC black tea based on colorimetric sensor array response to taste substances combined with chemometrics

The quality of crush–tear–curl black tea (CTC-BT) varies greatly by geographic origin. Origin traceability is crucial for consumer interest protection, market order regulation, and food safety monitoring. This paper proposes a fast and accurate method for qualitative discrimination of CTC-BT origins and quantitative detection of its key taste-presenting substances. The method involves a simple colorimetric sensor array and ultraviolet–visible spectroscopy. The effects of various variable screening methods on modeling results were compared. A particle swarm optimization–based support vector machine achieved the highest performance in qualitative discrimination, with a correct classification rate of 99.48%. Based on their origin-distinguishing contributions and dose-over-thresholds, seven key taste-presenting substances were screened, namely, theaflavin, caffine, vitexin-2-O-rhamnoside, rutin, epigallocatechin gallate, epicatechin gallate, gallic acid. A least squares-support vector regression model achieved accurate quantification of the seven aforementioned compounds (square root of determination coefficient of prediction >0.9698, residual prediction deviation >2).

Modeling magnetocaloric effect of doped EuTiO3 perovskite for cooling technology using swarm intelligent based support vector regression computational method

This work develops particle swarm optimization based support vector regression (PSVR) algorithm for predicting maximum magnetic entropy change using ionic radii of the constituting elements as well as the applied magnetic field as descriptors. The developed PSVR-G using Gaussian kernel function performs better than PSVR-P which employs polynomial data-mapping function with performance improvement of 0.04%, 9.93% and 5.25% on the basis of correlation coefficient (CC), mean absolute error (MAE) and root mean square error (RMSE), respectively on testing data samples. The influence of magnetic field ranging between 1 T and 5 T on doped perovskite EuTiO3 was investigated for different samples using the developed PSVR-G model. The significance of various dopants on perovskite EuTiO3 was further examined using the developed PSVR-G model. The accuracy and precision associated with the developed models would facilitate comprehensive exploration of perovskite EuTiO3 material for magnetic cooling application without experimental stress.

Dimensionality reduction of the attributes using fuzzy optimized independent component analysis for a Big Data Intrusion Detection System

Big data cybersecurity has garnered more attraction in recent years with the development of advanced machine learning and deep learning classifiers. These new classifier algorithms have significantly improved Intrusion Detection Systems (IDS). In these classifiers, the performance is positively influenced by high relevant features while less relevant features negatively influence the performance. However, considering all the attributes, especially the high dimensional attributes, increases computational complications. Hence it is essential to diminish the dimensionality of the attributes to improve the classifier performance. To achieve this objective, an efficient dimensionality reduction approach is presented through the development of the Fuzzy Optimized Independent Component Analysis (FOICA) technique. The standard Independent Component Analysis (ICA) is coupled with the fuzzy entropy to transform the high dimension attributes into low dimension attributes and helps in selecting high informative low-dimensional attributes. These selected features are fed to efficient hybrid classifiers namely Hyper-heuristic Support Vector Machines (HH-SVM), Hyper-Heuristic Improved Particle Swarm Optimization based Support Vector Machines (HHIPSO-SVM) and Hyper-Heuristic Firefly Algorithm based Convolutional Neural Networks (HHFA-CNN) to classify the cybersecurity data to identify the intrusions. Experiments are conducted over two cybersecurity datasets and real-time laboratory data whose outcomes specify the supremacy of the suggested IDS model based on FOICA dimensionality reduction.

Classification of lower limb motor imagery based on iterative EEG source localization and feature fusion

Motor imagery (MI) brain–computer interface (BCI) systems have broad application prospects in rehabilitation and other fields. However, to achieve accurate and practical MI-BCI applications, there are still several critical issues, such as channel selection, electroencephalogram (EEG) feature extraction and EEG classification, needed to be better resolved. In this paper, these issues are studied for lower limb MI which is more difficult and less studied than upper limb MI. First, a novel iterative EEG source localization method is proposed for channel selection. Channels FC1, FC2, C1, C2 and Cz, instead of the commonly used traditional channel set (TCS) C3, C4 and Cz, are selected as the optimal channel set (OCS). Then, a multi-domain feature (MDF) extraction algorithm is presented to fuse single-domain features into multi-domain features. Finally, a particle swarm optimization based support vector machine (SVM) method is utilized to classify the EEG data collected by the lower limb MI experiment designed by us. The results show that the classification accuracy is 88.43%, 3.35–5.41% higher than those of using traditional SVM to classify single-domain features on the TCS, which proves that the combination of OCS and MDF can not only reduce the amount of data processing, but also retain more feature information to improve the accuracy of EEG classification.

Forecasting of the Prevalence of Dementia Using the LSTM Neural Network in Taiwan

The World Health Organization has urged countries to prioritize dementia in their public health policies. Dementia poses a tremendous socioeconomic burden, and the accurate prediction of the annual increase in prevalence is essential for establishing strategies to cope with its effects. The present study established a model based on the architecture of the long short-term memory (LSTM) neural network for predicting the number of dementia cases in Taiwan, which considers the effects of age and sex on the prevalence of dementia. The LSTM network is a variant of recurrent neural networks (RNNs), which possesses a special gate structure and avoids the problems in RNNs of gradient explosion, gradient vanishing, and long-term memory failure. A number of patients diagnosed as having dementia from 1997 to 2017 was collected in annual units from a data set extracted from the Health Insurance Database of the Ministry of Health and Welfare in Taiwan. To further verify the validity of the proposed model, the LSTM network was compared with three types of models: statistical models (exponential smoothing (ETS), autoregressive integrated moving average model (ARIMA), trigonometric seasonality, Box–Cox transformation, autoregressive moving average errors, and trend seasonal components model (TBATS)), hybrid models (support vector regression (SVR), particle swarm optimization–based support vector regression (PSOSVR)), and deep learning model (artificial neural networks (ANN)). The mean absolute percentage error (MAPE), root-mean-square error (RMSE), mean absolute error (MAE), and R-squared (R2) were used to evaluate the model performances. The results indicated that the LSTM network has higher prediction accuracy than the three types of models for forecasting the prevalence of dementia in Taiwan.

Comparison Of Classification Methods On Sentiment Analysis Of Political Figure Electability Based On Public Comments On Online News Media Sites

Elections are an important part of the political process so that not a few figures from political parties begin preparing to participate in the process. Electability is one of the issues of concern, various things are done to be able to increase the electability of political figures who participated in the general election. Media has become one of the important tools used to increase electability, one of which is online news media. News coverage in online news media with its real-time nature will very quickly get comments from readers and can be used as an assessment of political figures in the form of sentiment analysis. However, it is not easy to analyze sentiments from various comments on online news media, because comments that contain text have irregularities, especially in Indonesian texts. Text mining is one way that can be used to overcome this. Pre-processing of text in text mining is an important part of getting basic information contained in comments. This study uses the Indonesian text pre-processing using the Gata text-mining framework. Then proceed with extracting more in-depth information using the Naïve Bayes classification method and Support Vector Machine which is optimized using Particle Swarm Optimization. The tests carried out with both methods get the results that, the Particle Swarm Optimization based Support Vector Machine method is the best method in the process of classifying sentiments analysis of political figures with an accuracy of 78.40% and AUC 0.850. The results of this study get an effective algorithm in classifying positive and negative comments related to political figures from online news media.

Development of a particle swarm optimization based support vector regression model for titanium dioxide band gap characterization

Energy band gap of titanium dioxide (TiO2) semiconductor plays significant roles in many practical applications of the semiconductor and determines its appropriateness in technological and industrial applications such as UV absorption, pigment, photo-catalysis, pollution control systems and solar cells among others. Substitution of impurities into crystal lattice structure is the most commonly used method of tuning the band gap of TiO2 for specific application and eventually leads to lattice distortion. This work utilizes the distortion in the lattice structure to estimate the band gap of doped TiO2, for the first time, through hybridization of a particle swarm optimization algorithm (PSO) with a support vector regression (SVR) algorithm for developing a PSO-SVR model. The precision and accuracy of the developed PSO-SVR model was further justified by applying the model for estimating the effect of cobalt-sulfur co-doping, nickel-iodine co-doping, tungsten and indium doping on the band gap of TiO2 and excellent agreement with the experimentally reported values was achieved. Practical implementation of the proposed PSO-SVR model would further widen the applications of the semiconductor and reduce the experimental stress involved in band gap determination of TiO2.

Particle Swarm Optimization Based Support Vector Machine (P-SVM) for the Segmentation and Classification of Plants

With the rapid growth in urbanization and population, it has become an earnest task to nurture and grow plants that are both important in sustaining the nature and the living beings needs. In addition, there is a need for preserving the plants having global importance both economically and environmentally. Locating such species from the forest or shrubs having human involvement is a time consuming and costly task to perform. Therefore, in this paper, a novel method is presented for the segmentation and classification of the seven different plants, named Guava, Jamun, Mango, Grapes, Apple, Tomato, and Arjun, based on their leaf images. In the first phase, both real-time images and images from the crowdAI database are collected and preprocessed for noise removal, resizing, and contrast enhancement. Then, in the second phase, different features are extracted based on color and texture. The third phase includes the segmentation of images using a k-means algorithm. The fourth phase consists of the training of support vector machine, and finally, in the last phase, the testing is performed. Particle swarm optimization algorithm is used for selecting the best possible value of the initialization parameter in both the segmentation and classification processes. The proposed work achieves higher experimental results, such as sensitivity = 0.9581, specificity = 0.9676, and accuracy = 0.9759, for segmentation and classification accuracy = 95.23 when compared with other methods.

Particle Swarm Optimization based Support Vector Machine for Diabetes Mining

Particle Swarm Optimization based Support Vector Machine for Diabetes Mining

Generalized composite multiscale permutation entropy and Laplacian score based rolling bearing fault diagnosis

Abstract Multiscale permutation entropy (MPE) is a recently proposed nonlinear dynamic method for measuring the randomness and detecting the nonlinear dynamic change of time series and can be used effectively to extract the nonlinear dynamic fault feature from vibration signals of rolling bearing. To solve the drawback of coarse graining process in MPE, an improved MPE method called generalized composite multiscale permutation entropy (GCMPE) was proposed in this paper. Also the influence of parameters on GCMPE and its comparison with the MPE are studied by analyzing simulation data. GCMPE was applied to the fault feature extraction from vibration signal of rolling bearing and then based on the GCMPE, Laplacian score for feature selection and the Particle swarm optimization based support vector machine, a new fault diagnosis method for rolling bearing was put forward in this paper. Finally, the proposed method was applied to analyze the experimental data of rolling bearing. The analysis results show that the proposed method can effectively realize the fault diagnosis of rolling bearing and has a higher fault recognition rate than the existing methods.

A quantitative approach to design alternative evaluation based on data-driven performance prediction

Design alternative evaluation in the early stages of engineering design plays an important role in determining the success of new product development, as it influences considerably the subsequent design activities. However, existing approaches to design alternative evaluation are overly reliant on experts’ ambiguous and subjective judgments and qualitative descriptions. To reduce subjectivity and improve efficiency of the evaluation process, this paper proposes a quantitative evaluation approach through data-driven performance predictions. In this approach, the weights of performance characteristics are determined based on quantitative assessment of expert judgments, and the ranking of design alternatives is achieved by predicting performance values based on historical product design data. The experts’ subjective and often vague judgments are captured quantitatively through a rough number based Decision-Making Trial and Evaluation Laboratory (DEMATEL) method. In order to facilitate performance based quantitative ranking of alternatives at the early stages of design where no performance calculation is possible, a particle swarm optimization based support vector machine (PSO-SVM) is applied for historical data based performance prediction. The final ranking of alternatives given the predicted values of multiple performance characteristics is achieved through Višekriterijumska Optimizacija I kompromisno Rešenje (VIKOR). A case study is carried out to demonstrate the validity of the proposed approach.

Particle Swarm Optimization based support vector machine for damage level prediction of non-reshaped berm breakwater

The damage analysis of coastal structure is very much essential for better and safe design of the structure. In the past, several researchers have carried out physical model studies on non-reshaped berm breakwaters, but failed to give a simple mathematical model to predict damage level for non-reshaped berm breakwaters by considering all the boundary conditions. This is due to the complexity and non-linearity associated with design parameters and damage level determination of non-reshaped berm breakwater. Soft computing tools like Artificial Neural Network, Fuzzy Logic, Support Vector Machine (SVM), etc, are successfully used to solve complex problems. In the present study, SVM and hybrid of Particle Swarm Optimization (PSO) with SVM (PSO–SVM) are developed to predict damage level of non-reshaped berm breakwaters. Optimal kernel parameters of PSO–SVM are determined by PSO algorithm. Both the models are trained on the data set obtained from experiments carried out in Marine Structures Laboratory, Department of Applied Mechanics and Hydraulics, National Institute of Technology Karnataka, Surathkal, India. Results of both models are compared in terms of statistical measures, such as correlation coefficient, root mean square error and scatter index. The PSO–SVM model with polynomial kernel function outperformed other SVM models.

Application of particle swarm optimization-based least square support vector machine in quantitative analysis of extraction solution of yangxinshi tablet using near infrared spectroscopy

A particle swarm optimization (PSO)-based least square support vector machine (LS-SVM) method was investigated for quantitative analysis of extraction solution of Yangxinshi tablet using near infrared (NIR) spectroscopy. The usable spectral region (5400–6200 cm-1) was identified, then the first derivative spectra smoothed using a Savitzky–Golay filter were employed to establish calibration models. The PSO algorithm was applied to select the LS-SVM hyperparameters (including the regularization and kernel parameters). The calibration models of total flavonoids, puerarin, salvianolic acid B and icariin were established using the optimum hyperparameters of LS-SVM. The performance of LS-SVM models were compared with partial least squares (PLS) regression, feed-forward back-propagation network (BPANN) and support vector machine (SVM). Experimental results showed that both the calibration results and prediction accuracy of the PSO-based LS-SVM method were superior to PLS, BP-ANN and SVM. For PSO-based LS-SVM models, the determination coefficients (R2) for the calibration set were above 0.9881, and the RSEP values were controlled within 5.772%. For the validation set, the RMSEP values were close to RMSEC and less than 0.042, the RSEP values were under 8.778%, which were much lower than the PLS, BP-ANN and SVM models. The PSO-based LS-SVM algorithm employed in this study exhibited excellent calibration performance and prediction accuracy, which has definite practice significance and application value.

Solving the Imbalanced Data Classification Problem with the Particle Swarm Optimization Based Support Vector Machine

Solving the Imbalanced Data Classification Problem with the Particle Swarm Optimization Based Support Vector Machine

Particle Swarm Optimization Based Support Vector Regression for Blind Image Restoration

This paper presents a swarm intelligence based parameter optimization of the support vector machine (SVM) for blind image restoration. In this work, SVM is used to solve a regression problem. Support vector regression (SVR) has been utilized to obtain a true mapping of images from the observed noisy blurred images. The parameters of SVR are optimized through particle swarm optimization (PSO) technique. The restoration error function has been utilized as the fitness function for PSO. The suggested scheme tries to adapt the SVM parameters depending on the type of blur and noise strength and the experimental results validate its effectiveness. The results show that the parameter optimization of the SVR model gives better performance than conventional SVR model as well as other competent schemes for blind image restoration.