Medium Gaussian Support Vector Machine Research Articles

An Analysis of the WPT Function for Pattern Optimization to Detect Defects in Bearings

New trends in maintenance techniques are oriented to digitization and prognosis. The new electronic devices based on IoT (Internet of Things) technology among others that support the industry 4.0 paradigm let enhance the traditional condition monitoring techniques to better understand and predict the state of a machine in service. Related to maintenance applications, one of the important steps in condition monitoring tasks for fault diagnosis is the selection of the optimal pattern to provide accurate results (avoiding fault positives/negatives) with adequate computation time. When implementing this, the selection of optimal parameters and thresholds for setting alarms are important to detect problems in the machine before the failure occurs. Vibratory signals have been proved to be a good variable to determine their mechanical behavior. Nevertheless, parameters obtained from time domain measurements are not computationally efficient nor good patterns to compare different machine conditions. In this sense, tools that represent the frequency domain or time–frequency domain have been useful to detect defects in rotating elements such as bearings. In this work, defects in ball bearings are studied using wavelet packet transform. For this, a methodology will be developed for the optimal selection of the mother wavelet, incorporating intelligent classification systems, and using a medium Gaussian support vector machine model. In this way, it will be verified that the correct selection of this function influences both the results and the ease and reliability of detection. The results using the selected mother wavelet will be compared to those using Daubechies 6, since it is the mother wavelet that has been used in previous works and which was selected based on experience. For it, vibratory signals are obtained from a testbench with different bearing conditions: healthy bearings and defective bearings (inner and outer race).

Impact of Velocity of Detonation and Charge per Bank Cubic Meters on Flyrock Throw Prediction Using Support Vector Machine

One of the ambient effects of production blasting is flyrock. To effectively manage flyrock throw distance in mining, there is the necessity to successfully envisage blasting output without sacrificing the hazardous impact of flyrock which may result in fatality and operational shutdown. For flyrock throw distance prediction, velocity of detonation (VOD) and charge per bank cubic meter (CPBCM) are not usually included. This paper focuses on the use of support vector machine (SVM) regression to ascertain the impact of VOD and CPBCM on flyrock throw predictions. The machine learning models were linear support vector machine (LSVM), quadratic Gaussian support vector machine (QGSVM), fine Gaussian support vector machine (FGSVM), medium Gaussian support vector machine (MGSVM), and cubic Gaussian support vector machine (CGSVM). The outcome indicates that FGSVM was the most sensitive with a 4% improvement when VOD and CPBCM were included. As a result, the LSVM model provides a suitable AI competitive alternative tool for flyrock throw prediction in mining operations by incorporating VOD and CPBCM.

Modeling spinel oxide based-photocatalytic degradation of organic pollutants from industrial wastewater

Rapid population growth has resulted in rapid growth in industrialization to meet various human needs. As a result of this, huge volume of effluent is being generated from the industrial processes and released into the water bodies. These anthropogenic activities are often detrimental to human and aquatic lives. In this study, a modeling approach to evaluate the photocatalytic degradation of organic pollutants from industrial wastewater using spinel oxide is investigated. Four machine learning algorithms namely, linear regression, decision tree ensemble, medium Gaussian support vector machine, and exponential Gaussian process regression were employed. The parametric analysis of the predictors (particle size of the spinel oxides, the initial dye concentration, the amount of photocatalysts, the band gap, and the irradiation time) and the targeted output of the photocatalytic degradation efficiency shows that a non-linear relationship exists between the predictors and the targeted output. This was further confirmed by the linear regression model with R2 of 0.220. Besides, the decision tree ensemble and medium Gaussian support vector machine regression offer poor performances in predicting the photocatalytic degradation efficiency as indicated by R2 of 0.420 and 0.490, respectively. A superior performance in predicting the photocatalytic degradation efficiency was displayed by the exponential Gaussian process regression with R2 of 0.991.

Identification of Important Factors in the Diagnosis of Breast Cancer Cells Using Machine Learning Models and Principal Component Analysis

Breast cancer (BC) is now identified as a disease with a significant impact on morbidity and mortality that is growing and widespread worldwide. This study uses a publicly available clinical dataset of 699 patients from the University of Wisconsin with 9 variables: (1) clump thickness, (2) uniformity of cell size, (3) uniformity of cell shape, (4) marginal adhesion, (5) single epithelial cell size, (6) bare nuclei, (7) bland chromatin, (8) normal nucleoli, and (9) mitoses. This dataset has been used for many studies in the past to pinpoint critical factors in patient diagnosis. Here, we use this data to ensure its unbiasedness and accuracy. We then apply principal component analysis and machine learning models to identify factors in diagnosing a malignant or benign tumor. We investigate and compare the classification accuracy of different machine learning models, including tree, linear discriminant, quadratic discriminant, logistic regression, naive Bayes, support vector machine (SVM), K-nearest neighbor (KNN), ensemble, neural network, and kernel. The best models that can achieve the highest accuracy are medium Gaussian SVM, coarse Gaussian SVM, and cosine KNN, with an accuracy of 96.5%. The principal component analysis method is then performed to identify crucial components and build an accurate model with fewer parameters. The medium Gaussian SVM has the highest cross-validation classification accuracy of 96.98% and requires only three predictors: normal nucleoli, bare nuclei, and cell size uniformity.

STEP TOWARDS INTELLIGENT TRANSPORTATION SYSTEM WITH VEHICLE CLASSIFICATION AND RECOGNITION USING SPEEDED-UP ROBUST FEATURES

<p>Vehicle classification is a crucial task owing to vehicles' diverse and intricate features, such as edges, colors, shadows, corners, and textures. The accurate classification of vehicles enables their detection and identification on roads and facilitates the development of an electronic tollcollection system for smart cities. Furthermore, vehicle classification is useful for traffic signal control strategy. However, achieving accurate vehicle classification poses significant challenges due to the limited processing time for real-time applications, image resolution, illumination variations in the video, and other interferences. This study proposes a method for automated automobile detection, recognition, and classification using statistics derived from approximately 11,000 images. We employ SURF-based detection and different classifiers to categorize vehicles into three groups. The Traffic Management System (TMS) is crucial for studying mobility and smart cities. Our study achieves a high automobile classification rate of 91% with the medium Gaussian Support Vector Machine (SVM) classifier. The paper's main objective is to analyze five object classifiers for vehicle recognition: Decision Tree, Discriminant Analysis, SVM, K-Nearest Neighbor Classifier (KNN), and Ensemble Classifier. In the discussion section, we present the limitations of our work and provide insights into future research directions.</p>

Analyzing of salient features and classification of wine type based on quality through various neural network and support vector machine classifiers

Wine quality certification is crucial to the wine industry. Indian wine’s superior quality is well-known around the world. Wine quality certification is crucial to the wine industry. Our main objective in this study is to find out a machine-learning model based on experimental data that has been gathered from various places across India and available synthetic data in order to predict wine quality. We utilized 178 wine samples with 13 different physiochemical characteristics. All the features have been analyzed and shown the values of max, min, mean, Kurt, skewness, and standard deviation of each variable. Important attributes that can be selected by comparing the values of all the above-mentioned feature selection approaches were required very much to improve wine quality. Five neural network methods and six support vector methods were trained and tested on all features of the dataset. Narrow neural network, Wide neural network, Quadratic support vector machine and Medium Gaussian support vector machine — all these classifiers showed 97.8% accuracy when trained and evaluated with all features but Quadratic support vector machine achieved this accuracy with the lowest training time 0.92556 sec ad the highest prediction speed 6400 obs/sec. These results demonstrate that the anticipated and experimental responses are extremely well aligned, according to this accuracy and the preferred model is appropriate to classify wine quality based on physiochemical components.

Biphasic majority voting-based comparative COVID-19 diagnosis using chest X-ray images

The COVID-19 pandemic has been affecting the world since December 2019, and nowadays, the number of infected is increasing rapidly. Chest X-ray images are clinical adjuncts that can be used in the diagnosis of COVID-19 disease. Because of the rapid spread of COVID-19 disease worldwide and the limited number of expert radiologists, the proposed method uses the automatic diagnosis method rather than a manual diagnosis method. In the paper, COVID-19 Positive/Negative (2275 Positive, 4626 Negative) and Normal/Pneumonia (2313 Normal, 2313 Pneumonia) are diagnosed using chest X-ray images. Herein, 80 % and 20 % of the images are used in the training and validation set, respectively. In the proposed method, six different classifiers are trained using chest X-ray images, and the five most successful classifiers are used in both phases. In Phase-1 and Phase-2, image features are extracted using the Bag of Features method for Cosine K-Nearest Neighbor (KNN), Linear Discriminant, Logistic Regression, Bagged Trees Ensemble, Medium Gaussian Support Vector Machine (SVM), excluding SqueezeNet Deep Learning (K = 2000 and K = 1500 for Phase-1 and Phase-2, respectively). In both phases, the five most successful classifiers are determined, and images classify with the help of the Majority Voting (Mathematical Evaluation) method. The application of the proposed method is designed for users to diagnose COVID-19 Positive, Normal, and Pneumonia. The results show that accuracy values obtained by Majority Voting (Mathematical Evaluation) method for Phase-1 and Phase-2 are equal to 99.86 % and 99.28 %, respectively. Thus, it indicates that the accuracy of the whole system is 99.63 %. When we analyze the classification performance metrics for Phase-1 and Phase-2, Specificity (%), Precision (%), Recall (%), F1 Score (%), Area Under Curve (AUC), and Matthews Correlation Coefficient (MCC) are equal to 99.98–99.83–99.07–99.51–0.9974–0.9855 and 99.73–99.69–98.63–99.23–0.9928–0.9518, respectively. Moreover, if the classification performance metrics of the whole system are examined, it is seen that Specificity (%), Precision (%), Recall (%), F1 Score (%), AUC, and MCC are 99.88, 99.78, 98.90, 99.40, 0.9956, and 0.9720, respectively. When the studies in the literature are examined, the results show that the proposed model is better than its counterparts. Because the best performance metrics for the dataset used were obtained in this study. In addition, since the biphasic majority voting technique is used in the study, it is seen that the proposed model is more reliable. On the other hand, although there are tens of thousands of studies on this subject, the usability of these models is debatable since most of them do not have graphical user interface applications. Already, in artificial intelligence technologies, besides the performance of the developed models, their usability is also important. Because the developed models can generally be used by people who are less knowledgeable about artificial intelligence.

Feasibility of ultrasound radiomics-based models for classification of hepatic echinococcosis

To investigate the feasibility of establishment of ultrasound radiomics-based models for classification of hepatic echinococcosis, so as to provide insights into precision ultrasound diagnosis of hepatic echinococcosis. The ultrasonographic images were retrospectively collected from 200 patients with hepatic echinococcosis in Shiqu County, Ganzi Tibetan Autonomous Prefecture, Sichuan Province in October 2014, and the regions of interest were plotted in ultrasonographic images of hepatic echinococcosis lesions. The ultrasound radiomics features of hepatic echinococcosis were extracted with 25 methods, and screened using pre-selection and the least absolute shrinkage and selection operator. Then, all ultrasonographic images were randomly assigned into the training and independent test sets according to the type of lesions at a ratio of 7:3. Machine learning models for classification of hepatic echinococcosis were created based on two classifiers, including kernel logistic regression (KLR) and medium Gaussian support vector machine (MGSVM). The receiver operating characteristic (ROC) curves were plotted, and the sensitivity, specificity and areas under the curves (AUC) of the created machine learning models for classification of hepatic echinococcosis were calculated. A total of 5 005 ultrasound radiomics features were extracted from 200 patients with hepatic echinococcosis using 25 methods, and 36 optimal radiomics features were screened through feature selection, based on which two machine learning models were created, including KLR and MGSVM. ROC curve analysis showed that MGS-VM presented a higher efficacy for hepatic echinococcosis classification than KLR in the training set, with a sensitivity of 0.82, a specificity of 0.78 and AUC of 0.88, while KLR presented a higher efficacy for hepatic echinococcosis classification than MGSVM in the independent test set, with a sensitivity of 0.82, a specificity of 0.72 and AUC of 0.86, respectively. Ultrasound radiomics-based machine learning models are feasible for hepatic echinococcosis classification.

Application of machine learning techniques to simulate the evaporative fraction and its relationship with environmental variables in corn crops

BackgroundThe evaporative fraction (EF) represents an important biophysical parameter reflecting the distribution of surface available energy. In this study, we investigated the daily and seasonal patterns of EF in a multi-year corn cultivation located in southern Italy and evaluated the performance of five machine learning (ML) classes of algorithms: the linear regression (LR), regression tree (RT), support vector machine (SVM), ensembles of tree (ETs) and Gaussian process regression (GPR) to predict the EF at daily time step. The adopted methodology consisted of three main steps that include: (i) selection of the EF predictors; (ii) comparison of the different classes of ML; (iii) application, cross-validation of the selected ML algorithms and comparison with the observed data.ResultsOur results indicate that SVM and GPR were the best classes of ML at predicting the EF, with a total of four different algorithms: cubic SVM, medium Gaussian SVM, the Matern 5/2 GPR, and the rational quadratic GPR. The comparison between observed and predicted EF in all four algorithms, during the training phase, were within the 95% confidence interval: the R2 value between observed and predicted EF was 0.76 (RMSE 0.05) for the medium Gaussian SVM, 0.99 (RMSE 0.01) for the rational quadratic GPR, 0.94 (RMSE 0.02) for the Matern 5/2 GPR, and 0.83 (RMSE 0.05) for the cubic SVM algorithms. Similar results were obtained during the testing phase. The results of the cross-validation analysis indicate that the R2 values obtained between all iterations for each of the four adopted ML algorithms were basically constant, confirming the ability of ML as a tool to predict EF.ConclusionML algorithms represent a valid alternative able to predict the EF especially when remote sensing data are not available, or the sky conditions are not suitable. The application to different geographical areas, or crops, requires further development of the model based on different data sources of soils, climate, and cropping systems.

Periodontal bone loss detection based on hybrid deep learning and machine learning models with a user-friendly application

As artificial intelligence in medical imaging is used to diagnose many diseases, it can also be employed to diagnose whether a person has periodontal bone loss or not. Accurate and early diagnosis performs a vital task in the treatment of the patient’s dental disorder. Therefore, such medical images are known to be an important clinical adjunct. In this manuscript, whether the patient has periodontal bone loss or non-periodontal bone loss is diagnosed employing hybrid artificial intelligence-based systems. Herein, after tagging a total of 1432 images by an expert, we extract 1000 deep image features for each image using AlexNet and SqueezeNet deep learning architectures. On the other hand, we classify these images directly without extracting the image features using the EfficientNetB5 deep learning architecture. First, we categorize AlexNet-based deep image features using the Coarse Tree, Weighted K-Nearest Neighbor (KNN), Gaussian Naïve Bayes, RUSBoosted Trees Ensemble, and Linear Support Vector Machine (SVM) classifiers. Afterward, we classify SqueezeNet-based deep image features using Medium Tree, Gaussian Naïve Bayes, Boosted Trees Ensemble, Coarse KNN, and Medium Gaussian SVM classifiers. With the help of the ten classifiers employed in this study, we also design a user-friendly Graphical User Interface (GUI) application. Thanks to this application, we aim to reduce the workload of experts, save time and help to diagnose dental disorders early. The results show that the best classifiers for AlexNet-based, SqueezeNet-based, and Direct-Convolutional Neural Network (CNN) are Linear SVM, Medium Gaussian SVM, and EfficientNetB5, respectively. Among these classifiers, the best classifier is Linear SVM, and its accuracy, error, sensitivity, specificity, precision, and F1 score values are 81.49%, 18.51%, 84.57%, 79.14%, 75.68%, and 79.88%, respectively.

Machine Learning-Based Fault Diagnosis for a PWR Nuclear Power Plant

Fault detection and diagnosis (FDD) systems can reduce high costs and energy consumption. This paper presents a machine learning-based fault detection and diagnosis (FDD) technique for actuators and sensors in a pressurized water reactor (PWR). In the proposed FDD framework, faults are first detected using a shallow neural network. Second, fault diagnosis is performed using 15 different classifiers provided in the MATLAB Classification Learner toolbox, including support vector machine (SVM), K-nearest neighbor (KNN), and ensemble. Several classifiers were found to provide superior classification performance, including medium KNN, cubic KNN, cosine KNN, weighted KNN, fine Gaussian SVM, quadratic SVM, medium Gaussian SVM, coarse Gaussian, bagged trees, and subspace KNN. The accuracy of the FDD approach was demonstrated using a set of simulation results.

A Novel Peak Detection Algorithm Using Particle Swarm Optimization for Chew Count Estimation of a Contactless Chewing Detection

This paper uses a proximity sensor to perform non-contact-based (sensing) chewing activity detection, capturing the temporalis muscle movement during food intake. The proposed approach is validated using data from a larger number of participants, 20, and different food types, eight. The proposed chewing detection classifies the chewing activity with an overall accuracy of 96.4% using a medium Gaussian Support Vector Machine (SVM). In accordance with the result, this paper proposes a novel chew count estimation based on particle swarm optimization (PSO). First, the base of the algorithm is developed based on counting the peak of the chewing signal. Next, the insignificant peak is removed by introducing an argument of minimum peak prominence and maximum peak width where the value of the parameters needs to be determined. As the individual chewing pattern varies from person to person, this paper uses a novel parameter search using the PSO method to find the multiplier (parameter values) according to the average peak prominence and width value within each chewing episode. The proposed estimation approach simplifies the typical trial-and-error method. During optimization, within 100 iterations, the chewing count is reduced by 12.9% from its first iteration. Overall, the proposed methods achieve a 4.26% mean absolute error of chewing count estimation.

Automated differential diagnosis method for iron deficiency anemia and beta thalassemia trait based on iterative Chi2 feature selector.

The differential diagnosis of anemia is an important issue for hematology laboratories. We aimed at investigating the performance of a powerful computer-based model to aid diagnosis. Our work presents a new feature selection-based automated disease diagnosis model. To create a testbed, a new corpus is collected retrospectively. Our data sets contain beta thalassemia trait, iron deficiency anemia, and healthy groups. Our presented automated ailment classification model consists iterative chi2 (IChi2) feature selection and classification phases. The used data set includes 25 features, and IChi2 selects the 20 most valuable of them. These are forwarded to 24 traditional classifiers. In this work, two data sets have been used to test our proposal. In the classification phase of this model, 24 shallow classifiers have been used and the best accurate classifiers are Medium Gaussian Support Vector Machine (MGSVM) and Coarse Tree (CT) for the first and second data sets, respectively. These classifiers have been attained 97.48% and 99.73% classification accuracies using the first and second data sets, consecutively. These results are calculated using 10-fold cross-validation. Moreover, hold-out validation has been used in this work, and the results are given in the experiments. Our results denoted the success of IChi2-based classification model for diagnosis on the laboratory data set. We have found a new and robust model to differentiate iron deficiency anemia and beta thalassemia trait. This model may be beneficial for rational laboratory use.

Application of Machine Learning to a Medium Gaussian Support Vector Machine in the Diagnosis of Motor Bearing Faults

In recent years, artificial intelligence technology has been widely used in fault prediction and health management (PHM). The machine learning algorithm is widely used in the condition monitoring of rotating machines, and normal and fault data can be obtained through the data acquisition and monitoring system. After analyzing the data and establishing a model, the system can automatically learn the features from the input data to predict the failure of the maintenance and diagnosis equipment, which is important for motor maintenance. This research proposes a medium Gaussian support vector machine (SVM) method for the application of machine learning and constructs a feature space by extracting the characteristics of the vibration signal collected on the spot based on experience. Different methods were used to cluster and classify features to classify motor health. The influence of different Gaussian kernel functions, such as fine, medium, and coarse, on the performance of the SVM algorithm was analyzed. The experimental data verify the performance of various models through the data set released by the Case Western Reserve University Motor Bearing Data Center. As the motor often has noise interference in the actual application environment, a simulated Gaussian white noise was added to the original vibration data in order to verify the performance of the research method in a noisy environment. The results summarize the classification results of related motor data sets derived recently from the use of motor fault detection and diagnosis using different machine learning algorithms. The results show that the medium Gaussian SVM method improves the reliability and accuracy of motor bearing fault estimation, detection, and identification under variable crack-size and load conditions. This paper also provides a detailed discussion of the predictive analytical capabilities of machine learning algorithms, which can be used as a reference for the future motor predictive maintenance analysis of electric vehicles.

Radiomics and Machine Learning with Multiparametric Breast MRI for Improved Diagnostic Accuracy in Breast Cancer Diagnosis.

The purpose of this multicenter retrospective study was to evaluate radiomics analysis coupled with machine learning (ML) of dynamic contrast-enhanced (DCE) and diffusion-weighted imaging (DWI) radiomics models separately and combined as multiparametric MRI for improved breast cancer detection. Consecutive patients (Memorial Sloan Kettering Cancer Center, January 2018–March 2020; Medical University Vienna, from January 2011–August 2014) with a suspicious enhancing breast tumor on breast MRI categorized as BI-RADS 4 and who subsequently underwent image-guided biopsy were included. In 93 patients (mean age: 49 years ± 12 years; 100% women), there were 104 lesions (mean size: 22.8 mm; range: 7–99 mm), 46 malignant and 58 benign. Radiomics features were calculated. Subsequently, the five most significant features were fitted into multivariable modeling to produce a robust ML model for discriminating between benign and malignant lesions. A medium Gaussian support vector machine (SVM) model with five-fold cross validation was developed for each modality. A model based on DWI-extracted features achieved an AUC of 0.79 (95% CI: 0.70–0.88), whereas a model based on DCE-extracted features yielded an AUC of 0.83 (95% CI: 0.75–0.91). A multiparametric radiomics model combining DCE- and DWI-extracted features showed the best AUC (0.85; 95% CI: 0.77–0.92) and diagnostic accuracy (81.7%; 95% CI: 73.0–88.6). In conclusion, radiomics analysis coupled with ML of multiparametric MRI allows an improved evaluation of suspicious enhancing breast tumors recommended for biopsy on clinical breast MRI, facilitating accurate breast cancer diagnosis while reducing unnecessary benign breast biopsies.

CFD Optimization of the Pre-Chamber Geometry for a Gasoline Spark Ignition Engine

In the present paper, an efficient optimization method based on Bayesian updating strategy is developed for the design of a spark-ignition engine equipped with pre-chamber. 3D computational fluid dynamics (CFD) simulation coupled with strategies including design of experiment, genetic algorithm, and machine learning methods is used to optimize the pre-chamber with desired combustion phasing. The optimization process starts from a design of experiment matrix of 11 design parameters, which are used to analytically characterize the pre-chamber geometry and set up the 3D combustion CFD. Taking CA50 as the single objective, the CFD results are then used to train the machine learning models. Different machine learning models are evaluated based on their Root Mean Square Error. Five machine learning models from five different categories are selected for second round evaluation. The trained machine learning model is used in the genetic algorithm optimization, which yields the optimized configuration and is again justified by CFD. The new CFD results based on the optimized design are added into the database to further refine the machine learning model. After 24 iterations for each selected machine learning models, the medium Gaussian support vector machine model is identified as the best method for the present application. Iterations using the medium Gaussian support vector machine model continue until a satisfactory result is achieved. Detailed combustion analysis is conducted to investigate the physical mechanism about how the design of pre-chamber influences the engine's performance. It is found that larger volume of the upper part of the pre-chamber results in stronger jet flow and turbulent intensity which further accelerates the flame propagation inside the pre-chamber, dominating the contrary effects from reduced pressure and temperature. Regression analysis shows that the radius of the pre-chamber is the most influential design parameter. The current work not only sheds light on the optimization of engine design, but also has demonstrated a general strategy applicable to the purpose of arbitrary engine optimization and mechanical system design.

Statistical analysis of machine learning techniques for predicting powdery mildew disease in tomato plants

Powdery mildew is a dangerous disease that reduces the quality and the yield of tomato fruit rapidly. Its early prediction is a prior requirement for obtaining good quality fruit. Therefore, in this study, the best classifier amongst various classifiers has been discovered using different machine learning algorithms. This classifier can precisely classify whether the meteorological conditions of a particular day are conducive to the development of powdery mildew disease or not. Tomato powdery mildew disease dataset has been tested using various performance measures and the results computed for all the classifiers are promising. Friedman test has been used to rank multiple classifiers and post hoc analysis has also been done using the Nemenyi test. It has been observed in comparison that 62.05% of the total pairs of classifiers perform significantly different from each other, and medium Gaussian support vector machine (MGSVM) is the best classifier with 94.74% accuracy.

Detection of induction motor broken rotor bar faults under no load condition by using support vector machines

An important fault in induction motor is the broken rotor bar. Many techniques have been proposed for the detection of the rotor fault. However, the traditional techniques like motor current signature analysis have difficulty in detecting the rotor faults at 'no load' condition due to low slip. In this study, an algorithm which uses fast Fourier transform, principal component analysis and intelligent classifiers is proposed. The proposed algorithm was able to accurately detect the rotor faults of different severity levels at low slip. Experiments were carried out with three submersible induction motors. Four different rotor faults and healthy motor conditions were investigated for each motor. The motors were loaded different load levels to test the proposed algorithm. The best results were achieved with medium Gaussian support vector machine. The condition of having any faulted bar in the motor was obtained with 100% accuracy. Faults classification carried out by 92.2% accuracy.

Applicability of machine learning in modeling of atmospheric particle pollution in Bangladesh.

Atmospheric particle pollution causes acute and chronic health effects. Predicting the concentrations of PM2.5 and PM10, therefore, is a prerequisite to avoid the consequences and mitigate the complications. This research utilized the machine learning (ML) models such as linear-support vector machine (L-SVM), medium Gaussian-support vector machine (M-SVM), Gaussian process regression (GPR), artificial neural network (ANN), random forest regression (RFR), and a time series model namely PROPHET. Atmospheric NOX, SO2, CO, and O3, along with meteorological variables from Dhaka, Chattogram, Rajshahi, and Sylhet for the period of 2013 to 2019, were utilized as exploratory variables. Results showed that the overall performance of GPR performed better particularly for Dhaka in predicting the concentration of both PM2.5 and PM10 while ANN performed best in case of Chattogram and Sylhet for predicting PM2.5. However, in terms of predicting PM10, M-SVM and RFR were selected respectively. Therefore, this study recommends utilizing “ensemble learning” models by combining several best models to advance application of ML in predicting pollutants’ concentration in Bangladesh.Electronic supplementary materialThe online version of this article (10.1007/s11869-020-00878-8) contains supplementary material, which is available to authorized users.

Epileptic Seizure Detection Based on New Hybrid Models with Electroencephalogram Signals

Objectives: Epileptic seizures are one of the most common diseases in society and difficult to detect. In this study, a new method was proposed to automatically detect and classify epileptic seizures from EEG (Electroencephalography) signals.Methods: In the proposed method, EEG signals classification five-classes including the cases of eyes open, eyes closed, healthy, from the tumor region, an epileptic seizure, has been carried out by using the support vector machine (SVM) and the normalization methods comprising the z-score, minimum-maximum, and MAD normalizations. To classify the EEG signals, the support vector machine classifiers having different kernel functions, including Linear, Cubic, and Medium Gaussian, have been used. In order to evaluate the performance of the proposed hybrid models, the confusion matrix, ROC curves, and classification accuracy have been used. The used SVM models are Linear SVM, Cubic SVM, and Medium Gaussian SVM.Results: Without the normalizations, the obtained classification accuracies are 76.90%, 82.40%, and 81.70% using Linear SVM, Cubic SVM, and Medium Gaussian SVM, respectively. After applying the z-score normalization to the multi-class EEG signals dataset, the obtained classification accuracies are 77.10%, 82.30%, and 81.70% using Linear SVM, Cubic SVM, and Medium Gaussian SVM, respectively. With the minimum-maximum normalization, the obtained classification accuracies are 77.20%, 82.40%, and 81.50% using Linear SVM, Cubic SVM, and Medium Gaussian SVM, respectively. Moreover, finally, after applying the MAD normalization to the multi-class EEG signals dataset, the obtained classification accuracies are 76.70%, 82.50%, and 81.40% using Linear SVM, Cubic SVM, and Medium Gaussian SVM, respectively.Conclusion: The obtained results have shown that the best hybrid model is the combination of cubic SVM and MAD normalization in the classification of EEG signals classification five-classes.