Optimized Kernel Extreme Learning Machine Research Articles

Fault Diagnosis of Check Valve Based on KPLS Optimal Feature Selection and Kernel Extreme Learning Machine

The check valve is the core part of high-pressure diaphragm pumps. It has complex operation conditions and has difficulty characterizing fault states completely with its single feature. Therefore, a fault signal diagnosis model based on the kernel extreme learning machine (KELM) was constructed to diagnose the check valve. The model adopts a multi-feature extraction method and reduces dimensionality through kernel partial least squares (KPLS). Firstly, we divided the check valve vibration signal into several non-overlapping samples. Then, we extracted 16 time-domain features, 13 frequency-domain features, 16 wavelet packet energy features, and energy entropy features from each sample to construct a multi-feature set characterizing the operation state of the check valve. Next, we used the KPLS method to optimize the 45 dimension multi-feature data and employed the processed feature set to establish a KELM fault diagnosis model. Experiments showed that the method based on KPLS optimal feature selection could fully characterize the operating state of the equipment with an accuracy rate of 96.88%. This result indicates the high accuracy and effectiveness of the multi-feature set constructed with the KELM fault diagnosis model.

Boosted machine learning model for predicting intradialytic hypotension using serum biomarkers of nutrition

Intradialytic hypotension (IDH) is a serious complication of hemodialysis (HD), with an incidence of more than 20%. IDH induces ischemic organ damage and even reduces the ultrafiltration and duration of HD sessions. Frequent attacks of IDH are a risk factor for death in HD patients. Malnutrition is common in HD patients and is also associated with mortality. Although the link between IDH episodes and malnutrition has been observed in practice, it has not been supported by the data. To study the relationship, we propose a promising hybrid model called BSCWJAYA_KELM, which is a wrapper feature selection method based on a variant of the JAYA optimization algorithm (SCWJAYA) and Kernel extreme learning machine (KELM). In this paper, we verify the optimization capability of the SCWJAYA algorithm in the model by comparing experiments with some state-of-the-art methods for IEEE CEC2014, IEEE CEC2017, and IEEE CEC2019 benchmark functions. The prediction accuracy of BSCWJAYA_KELM is validated by the public datasets and the HD dataset. In the experiments on the HD dataset, 1940 HD sessions of 178 HD patients are analyzed by the developed BSCWJAYA_KELM model. The key indicators selected from vast amounts of data are serum uric acid, dialysis vintage, age, diastolic pressure, and albumin. The BSCWJAYA_KELM method is a stable and excellent prediction model that can achieve a more accurate prediction of IDH.

Coordinated method fusing improved bubble entropy and artificial Gorilla Troops Optimizer optimized KELM for rolling bearing fault diagnosis

In order to improve the fault identification accuracy of bearing and simultaneously, reduce or even eliminate the influence of parameter discussion, a rolling bearing fault diagnosis method without parameter discussion based on bubble entropy is proposed in this paper. In this method, Variational Mode Decomposition based Refined Composite Multiscale Bubble Entropy (VMD-RCMBE) are combined together to extract fault features, MCFS is used to realize feature screening and dimensionality reduction, and Gorilla Troops Optimizer Optimized Kernel Extreme Learning Machine (GTO-KELM) is used to complete model training and pattern recognition. The effectiveness of the method proposed in this paper is proved by two bearing fault data sets. Through the comparative experiment with the existing methods, it is proved that this method can achieve higher classification accuracy though without the parameter discussion process, and the average detection accuracy for different data sets can reach more than 99.8%.

Fault Diagnosis of Transformer Winding Looseness Based on Vibration Signal and GOA-KELM Model

Aiming at the problem that the latent fault of transformer winding looseness is difficult to identify and the diagnosis accuracy is low, a fault diagnosis method based on vibration signal and grasshopper optimization algorithm (GOA) optimization Kernel Extreme Learning Machine (KELM) is proposed in this paper. The method uses the time-domain and frequency-domain characteristics of the vibration signal. First, the time-frequency features of the vibration signals of multiple sensors are extracted, and a multi-sensor time-frequency feature matrix is constructed. Second, the feature matrix is identified and diagnosed by using GOA to optimize the KELM model. Finally, the feasibility and superiority of the proposed method are verified by the experimental data of 110kV transformer. The experimental results show that the method in this paper can successfully identify the looseness of different degrees of windings and the looseness of different phases, and has a higher diagnostic accuracy than the existing algorithms.

Prediction of PM2.5 concentration based on improved secondary decomposition and CSA-KELM

Exposure to high concentration PM2.5 will increase the risk of human illness and death, so it is of great significance to establish a high-accuracy PM2.5 prediction model. Because PM2.5 concentration sequence is nonlinear, non-stationary and complex, how to accurately predict PM2.5 concentration becomes a difficult problem. To improve the prediction accuracy, a PM2.5 prediction model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), differential symbolic entropy (DSE), variational mode decomposition improved by butterfly optimization algorithm (BVMD) and kernel extreme learning machine optimized by crow search algorithm (CSA-KELM), named CEEMDAN-DSE-BVMD-CSA-KELM, is proposed. The idea of CEEMDAN-DSE-BVMD-CSA-KELM is roughly as follows. Firstly, CEEMDAN is selected as the main decomposition technology, and PM2.5 concentration sequence is decomposed into several IMFs and residual term. Calculate the DSE of each component to judge the complexity and find out the high complexity components. Secondly, BVMD decomposes the sum of the high complexity components again, and obtains several new components. Finally, CSA-KELM is used to predict the residual components of primary decomposition and the components of secondary decomposition, and the prediction is completed by summing up the component prediction results. To prove the superiority of the proposed model, it is compared with single prediction model, single multi-factor prediction model and other combined prediction models. Taking the PM2.5 concentrations in Beijing, Shenyang and Shanghai from January 1, 2016 to March 31, 2021 as examples, the simulation experiment is carried out by using MATLAB platform. The fitting coefficient R2 of each city is as high as 0.99, and the RMSE, MAE and MAPE values of Shanghai are 0.7911, 0.5978 and 0.0167, which are lower than those of other comparison models. This proves the proposed model has high prediction accuracy and stability.

(Retracted) Blockchain enabled secure image transmission and diagnosis scheme in medical cyber-physical systems

Medical cyber-physical systems (MCPSs) are life critical, context aware, networked systems of medical devices that are increasingly used in hospitals to achieve seamless high-quality healthcare. The design of the MCPS for the healthcare sector necessitates significant attention to achieving security. As the medical images need to be communicated regularly for timely and accurate diagnosis, medical images need to be secured by encryption and blockchain technologies. In this aspect, we present a blockchain enabled secure image transmission and diagnosis (BESITD) for the MCPS environment. The BESITD technique encompasses an image acquisition process that enables the wearable devices to capture the medical images. Then, the presented model executes an intrusion detection system using recurrent neural network to determine the presence of intruders in the MCPS. In addition, the block-wise encryption process takes place in which the medical image is partitioned into n blocks, each of which is individually encrypted using the signcryption technique. Moreover, a consortium blockchain technology is used to store the encrypted image along with the hash value of the original medical image to accomplish integrity and traceability. At the cloud server side, the disease diagnosis process takes place in different stages, namely, multilevel thresholding-based segmentation, MobileNet-based feature extraction, and optimal kernel extreme learning machine (OKELM)-based classification. Furthermore, a multiobjective political optimizer is designed for effective selection of threshold values and KELM parameters. A wide range of simulations was performed on two benchmark medical image datasets, and the experimentation results highlighted the promising performance of the BESITD technique over the recent techniques with the maximum accuracy of 0.9816.

Performance Prediction of Rolling Bearing Using EEMD and WCDPSO-KELM Methods

Research on bearings performance degradation trend is significant, and can greatly reduce the loss caused by potential faults in the whole life-cycle of rolling bearings. It is also a very important part of Prognostic and Health Management (PHM). This paper proposed a new performance degradation prediction method based on optimized kernel extreme learning machine (KELM), improved particle swarm optimization (PSO) and Ensemble Empirical Mode Decomposition (EEMD). Firstly, the particle swarm optimization algorithm was improved by adjusting the inertia weight and linear learning factor and introducing a disturbance term, namely WCDPSO. Then, the penalty coefficient and kernel parameters of KELM were optimized by the WCDPSO, and the WCDPSO-KELM model was obtained. Subsequently, the EEMD method was used to extract original features from sample data, and a performance degradation index is selected from the EEMD feature space, which was input into the WCDPSO-KELM model in order to build a bearing performance degradation prediction trend model. Finally, the proposed method was verified by datasets of rolling bearings that were provided by the PRONOSTIA platform. Experimental results confirmed that the proposed method can efficiently predict the performance degradation trend of rolling bearings.

Early detection of digital mammogram using kernel extreme learning machine

AbstractAn automated computer‐assisted medical diagnosis that combines latest medical approaches and the advanced machine learning algorithms is a very crucial multidisciplinary technology, generating correct and noninvasive diagnoses of multiple diseases like breast cancer. The work proposed in this article focuses on the development of a biomedical computer‐assisted diagnosis model that can classify digital mammography as normal (healthy) or abnormal, and further, as malignant or benign. The proposed approach employs the discrete Chebyshev transform to extract the features. Then, the kernel principal component analysis technique is used to extract the discriminating features from the original feature vector. Subsequently, an optimized kernel extreme learning machine is proposed as a classifier to detect the tumors present in the mammographic images. Because the efficiency of the proposed classifier depends on its characteristic kernel variable, the main idea of the present work is to choose the most appropriate features from the downsized feature set and simultaneously obtain the optimized value of the aforementioned parameter. To validate the efficiency of the proposed work, the proposed scheme is performed on two publicly available data sets, namely the Mammographic Image Analysis Society data set and the INbreast data set. From the experimental analysis and its results, it is showed that for both normal–abnormal and malignant–benign classification, the proposed approach results in accuracy of 100% for the first data set. However, in the case of malignant–benign classification, the proposed approach gives an accuracy of 99.93% for the second data set. Further, it is also observed that the proposed approach exhibits highest performance as compared to that of the other approaches. Additionally, the ANOVA test is evaluated to demonstrate that the achievement of the proposed approach is significantly good than that of the other existing approaches.

An optimized Kernel Extreme Learning Machine for the classification of the autism spectrum disorder by using gaze tracking images

Autism spectrum disorder (ASD) is a lifelong neurological condition that affects how a person interacts and learns. The early and accurate diagnosis of ASD is vital to developing a comprehensive rehabilitation plan that improves the quality of life and the integration of the ASD person in the social, family, and work environment. However, the accurate diagnosis of ASD is usually affected since it is linked to the judgment of an expert, which produces biases related to the lack of objectivity. In consequence, several works have been dedicated to developing early detection techniques for ASD based on Machine Learning (ML) technologies and eye-tracking tools. The present work aims to introduce a new methodology for ASD classification, which uses Kernel Extreme Learning Machine (KELM), an objective dataset based on gaze tracking, feature extraction techniques, and data augmentation for training the model. In turn, to enhance the accuracy in ASD classification, the KELM model is optimized through the Giza Pyramids Construction (GPC) algorithm. The proposed approach includes pipeline data augmentation, dimensionality reduction, and a posterior normalization to classify ASD subjects accurately. Statistical tests and analyses were performed to validate the performance of the proposed methodology, resulting in an average accuracy of 98.8% in ASD classification.

Intelligent deep learning based ethnicity recognition and classification using facial images

Recently, computer vision-based face image analysis has sparked considerable interest in a variety of applications such as surveillance, security, biometrics and so on. The goal of the facial analysis was to derive facial soft biometrics such as identification, gender, age, ethnicity, expression and so on. Among these, ethnicity recognition remains a hot study topic, a major aspect of society with profound linkages to a variety of environmental and social concerns. The introduction of machine learning (ML) and deep learning (ML) technologies has proven advantageous for effective ethnicity recognition and classification. In this regard, the IDL-ERCFI technique, which is based on intelligent DL, is designed in this paper. The IDL-ERCFI technique's purpose is to distinguish and classify ethnicity based on facial photos. The IDL-ERCFI technique uses face landmarks to align photos before sending them to the network. Furthermore, the proposed model employs an Exception network as a feature extractor. Because the retrieved features are high-dimensional, the feature reduction procedure employs the principal component analysis (PCA) technique, which is effective in overcoming the “curse of dimensionality.” Furthermore, the ethnicity classification procedure is carried out using an optimal kernel extreme learning machine (KELM), with parameter tuning of the KELM model carried out using the glow worm swarm optimization (GSO) technique. A complete experimental analysis is carried out to demonstrate the superiority of the IDL-ERCFI technique over the other techniques.

Transformer Fault Diagnosis Technology Based on Maximally Collapsing Metric Learning and Parameter Optimization Kernel Extreme Learning Machine

Aiming at the problem of unsatisfactory diagnosis performance of conventional fault diagnosis methods for transformer, a novel method based on maximally collapsing metric learning algorithm (MCML) and parameter optimization kernel extreme learning machine (KELM) is proposed in this study. First, a new set of dissolved gas analysis (DGA) features combination, which can reflect the transformer fault information, is used to form the input feature space. Then, the MCML is employed to reduce the feature space dimension to extract a set of optimal DGA features combination. Finally, the salp swarm algorithm (SSA) is utilized to optimize the parameters in KELM to establish an SSA‐KELM model, which is adopted to diagnose and identify transformer faults. The proposed method is applied to the International Electrotechnical Commission (IEC) TC 10 database, and the results show that the feature extraction effect of MCML is superior than that of linear discriminant analysis, neighborhood preserving embedding, and Laplacian eigenmaps. The optimal DGA feature set is more advantageous than the frequent‐used DGA data, IEC ratios, Rogers ratios, and Doernenburg Ratios. The diagnosis accuracy of SSA‐KELM is better than that of KELM, particle swarm optimization‐KELM, genetic algorithm‐KELM, and loin swarm optimization‐KELM. Furthermore, the generalization and robustness ability of the MCML and SSA‐KELM is confirmed by the China DGA samples, the obtained results verify the reliability and validity of the proposed method again. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

A comparative study of different machine learning methods for reservoir landslide displacement prediction

This paper compares the performance of five popular machine learning methods, namely, particle swarm optimization–extreme learning machine (PSO–ELM), particle swarm optimization–kernel extreme learning machine (PSO–KELM), particle swarm optimization–support vector machine (PSO–SVM), particle swarm optimization–least squares support vector machine (PSO–LSSVM), and long short-term memory neural network (LSTM), in the prediction of reservoir landslide displacement. The Baishuihe, Shuping, and Baijiabao landslides in the Three Gorges reservoir area of China were used for case studies. Cumulative displacement was decomposed into trend displacement and periodic displacement by the Hodrick–Prescott filter. The double exponential smoothing method and the five machine learning methods were used to predict the trend and periodic displacement, respectively. The five machine learning methods are compared in three aspects: highest single prediction accuracy, mean prediction accuracy, and prediction stability. The results show that no method performed the best for all three aspects in the three landslide cases. LSTM and PSO–ELM achieved better single prediction accuracy, but worse mean prediction accuracy and stability. PSO–KELM, PSO–LSSVM, and PSO–SVM always yielded consistent predictions with slight variations. On the whole, PSO–KELM and PSO–LSSVM are recommended for their superior mean prediction accuracy and prediction stability.

An Intelligent Deep Learning Enabled Marine Fish Species Detection and Classification Model

In recent times, marine fish species recognition becomes an important research area to protect the ocean environment. It is a tough and time-consuming operation to manually detect marine fish species on the ocean floor. Depending on the situation, extensive sample efforts may be required. These efforts might be harmful to the marine ecosystem. Automated classification methods are capable of properly classifying these fish on a consistent basis. An increasing number of people are becoming interested in utilizing electronic monitoring and reporting with artificial intelligence for the aim of fish identification and enhancing present techniques. It is becoming more usual to use video and pictures of fish (either underwater or on ships) in fishing operations. These techniques are operational, transportable, and non-invasive, and they provide high-quality pictures at a lower cost than traditional approaches. Automated image processing techniques such as Deep Learning (DL) and Machine Learning (ML) are now available, and they may be customized to perform efficient fish species identification and segmentation. In this aspect, this paper presents an Intelligent DL based Marine Fish Species Classification (IDL-MFSC) technique. The proposed IDL-MFSC technique involves three major processes such as pre-processing, fish detection and fish classification. Primarily, Weiner filtering-based noise removal process takes place as a pre-processing step. In addition, Mask R-CNN (Mask Region Based Convolutional Neural Networks) with Residual Network as a backbone network is used for fish detection. Moreover, Optimal Deep Kernel Extreme Learning Machine (ODKELM) based classification method is employed for determining the class labels of the marine fish species in which the parameter tuning of the DKELM model takes place using Water Wave Optimization (WWO) technique. The performance of the proposed method is tested using an openly accessible Fish4Knowledge dataset. The experimental result highlights the supremacy of the IDL-MFSC technique over the recent techniques with respect to various measures.

A Novel Power Transformer Fault Diagnosis Model Based on Harris-Hawks-Optimization Algorithm Optimized Kernel Extreme Learning Machine

Dissolved gas analysis (DGA) method is widely used to detect the incipient fault of power transformers. This paper presents a novel DGA method for power transformer fault diagnosis based on Harris-Hawks-optimization (HHO) algorithm optimized kernel extreme learning machine (KELM). The non-code ratios of the gases are used as the characterizing vector for the KELM model, and the Harris-Hawks-optimization (HHO) algorithm is introduced to optimize the KELM parameters, which promotes the fault diagnostic performance of KELM. Based on dataset collected from IEC TC 10, the fault diagnosis capability of the proposed method is validated by different characterizing vectors and is compared with conventional KELM and other optimized KELM. Moreover, the generalization ability of the proposed method is confirmed by China DGA data. The results demonstrate that the proposed method is superior to other methods and is more effective and stable for power transformer fault diagnosis with high accuracy.

Illumination correction with optimized kernel extreme learning machine based on improved marine predators algorithm

AbstractAiming at the problem of poor image illumination correction accuracy, a kernel extreme learning machine optimized based on the differential evolution‐improved marine predators algorithm is proposed to estimate the scene illumination information and restore the image. First, in order to solve the problem of randomization of the initial population of the marine predators algorithm, differential evolutions is used to provide a set of suitable initial populations to the algorithm. Then, an improved algorithm is used to optimize the weight and bias of the kernel extreme learning machine to solve the problem of the randomness of the weight and bias, so that the learning machine converges to the global optimal value and avoids the unstable predictions. Finally, after obtaining the predicted illumination information, the image model is corrected to the image effect under standard illumination through diagonal transformation. It can be seen from the experimental results that the best predictive value of the differential evolution marine predator algorithm learning machine is 0.0135915, and the quasi‐bias is only 0.001687. Compared with traditional illumination estimation algorithms such as random vector functional link and extreme learning machine, the differential evolution marine predator algorithm learning machine algorithm proposed in this article has better stability, higher accuracy of calculated predicted values, and better image restoration effect.

A new gear intelligent fault diagnosis method based on refined composite hierarchical fluctuation dispersion entropy and manifold learning

Accurate judgment of gear working state is essential to the normal operation of mechanical equipment. To effectively extract the dynamic features representing the gear state from the vibration signals, this paper proposes refined composite hierarchical fluctuation dispersion entropy (RCHFDE), where the composite hierarchical decomposition is employed to replace the traditional hierarchical decomposition to improve the performance of HFDE. Combining RCHFDE and manifold learning, a new gear fault diagnosis method is proposed. Firstly, RCHFDE is used to extract the original fault features. After that, optimized discriminant diffusion maps analysis is adopted to map high-dimensional features to low-dimensional subsets. Finally, the low-dimensional features are input into optimized kernel extreme learning machine to identify different fault states of gear. The experimental results show that, compared with other contrastive methods, the proposed method enjoys better performance, which can effectively complete the determination of different gear fault states.

A Novel Fault Diagnosis Method for Motor Bearing Based on DTCWT and AFSO-KELM

Aiming at the defects of wavelet transform-based feature extraction and extreme learning machine-based classification, a novel fault diagnosis method for motor bearing, based on dual tree complex wavelet transform and artificial fish swarm optimization-kernel extreme learning machine (DTCWT-AFSO-KELM), is proposed in this paper. Firstly, the dual tree complex wavelet transform instead of the discrete wavelet transform is used to decompose the motor bearing signal; then, the features with large differentiation of motor-bearing fault are extracted; finally, the states of motor bearing are classified by using artificial fish swarm optimization-kernel extreme learning machine. In order to better prove the superiority of this method, four kinds of state data of motor bearing under the conditions of 0 HP (horsepower) load, 1 HP load, 2 HP load, and 3 HP load are used to test. The experimental results indicate that the diagnosis accuracies of DTCWT-AFSO-KELM are obviously better than those of discrete wavelet transform and artificial fish swarm optimization-kernel extreme learning machine (DWT-AFSO-KELM) or discrete wavelet transform and extreme learning machine (DWT-ELM) under different loads.

A newly-designed fault diagnostic method for transformers via improved empirical wavelet transform and kernel extreme learning machine

In order to solve the problems of unsatisfactory diagnosis performance and unstable model of conventional fault diagnosis methods for transformers, a new approach based on improved empirical wavelet transform (IEWT) and salp swarm algorithm (SSA) optimized kernel extreme learning machine (KELM) is proposed in this study. Firstly, IEWT is used to adaptively decompose the vibration signal to obtain a set of empirical wavelet functions (EWFs). Secondly, the first n-order components with high correlation coefficient are collected. Thirdly, the mean value, variance, kurtosis, refine composite multiscale entropy (RCMSE), and time-frequency entropy(TFE) of these n-order components are calculated to construct a fusion feature vector. Finally, a two-level diagnostic model based on SSA-KELM is established. The first-level of it is applied to identify normal and abnormal states, and the second-level is selected to identify fault categories in the abnormal states. The proposed method can effectively diagnose the existing fault categories in the training set and accurately identify the unknown categories of faults. Experimental results show that the proposed method can efficiently extract features of different vibration signals and identify the faults, with an average classification accuracy of 96.25%. It is better than other methods, such as wavelet packet energy spectrum analysis-KELM and EWT-fisher.

Optimization of regularization coefficient and kernel parameters of KELM in face recognition using genetic algorithm

Extreme Learning machine (ELM), a linear system model introduced originally for feedforward neural networks having single-hidden layer, which is non-iteratively tuned. In ELM feature mapping is achieved explicitly with the help of activation functions. ELM was further prospected with kernel functions for performance improvement by exploiting implicit feature mapping. The classification accuracy of kernel ELM relies on the kernel and structural parameters, which are experimentally tuned. It is very challenging and computationally hard to assess the optimal choice of these parameters from a specific domain of values using Brute force method. Therefore an optimal algorithm is required to find the finest combination of these parameters for enhanced performance. In this paper optimized kernel ELM is unveiled, in which genetic algorithm is utilized to evaluate the optimal solution of regularization coefficient and kernel parameters. Experiments on face image databases denote that the developed algorithm is more accurate and efficacious than state of art existing algorithms in literature.

Optimal kernel extreme learning machine model for predicting the fracture state and impact response of laminated glass panels

The structural calculations of laminated glass (LG) under impact are commonly not available in sophisticated load scenarios such as consecutive impacts in typhoon or calculating the post-fracture response of LG. In this work, a flexible prediction model based on kernel extreme learning machine (KELM) was proposed for assessing the fracture state and characteristic impact response of LG under impact, which only used rough material properties and preliminary experimental data. Multiple design variables such as glass make-up, panel size, interlayer type and thickness, and support conditions were considered. Impact tests with consecutive impact attempts were first conducted. Then, a comprehensive database was established which include the fracture state of each glass layer and characteristic impact response, which encompasses peak impact force, contact duration and impact energy dissipation ratio. 567 groups of polyvinyl butyral (PVB) LG data and 210 groups of SentryGlas® (SG) LG data were finally recorded and collected for the database. An optimal KELM model was subsequently developed via introducing whale optimization algorithm (WOA). The modelling results were compared with those from two popular models, i.e. support vector machine (SVM) and least squares SVM (LSSVM) based models to identify both potential strengths and shortcomings. The results show that the proposed model has better performance in both prediction accuracy and computation cost than other examined models. The proposed model has the highest prediction accuracy of 88.45% in evaluating the fracture state, more than 86% in the characteristic impact response.