1
|
Anticipating interpersonal sensitivity: A predictive model for early intervention in psychological disorders in college students. Comput Biol Med 2024; 172:108134. [PMID: 38492456 DOI: 10.1016/j.compbiomed.2024.108134] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Revised: 01/17/2024] [Accepted: 02/12/2024] [Indexed: 03/18/2024]
Abstract
Psychological disorders, notably social anxiety and depression, exert detrimental effects on university students, impeding academic achievement and overall development. Timely identification of interpersonal sensitivity becomes imperative to implement targeted support and interventions. This study selected 958 freshmen from higher education institutions in Zhejiang province as the research sample. Utilizing the runge-kutta search and elite levy spreading enhanced moth-flame optimization (MFO) in conjunction with the kernel extreme learning machine (KELM), we propose an efficient intelligent prediction model, namely bREMFO-KELM, for predicting the interpersonal sensitivity of college students. IEEE CEC 2017 benchmark functions and the interpersonal sensitivity dataset were employed as the basis for detailed comparisons with peer-reviewed studies and well-known machine learning models. The experimental results demonstrate the outstanding performance of the bREMFO-KELM model in predicting the sensitivity of interpersonal relationships in college students, achieving an impressive accuracy rate of 97.186%. In-depth analysis reveals that the prediction of interpersonal sensitivity in college students is closely associated with multiple features, including easily hurt in relationships, shy and uneasy with the opposite sex, feeling inferior to others, discomfort when observed or discussed, and blame and criticize others. These features are not only crucial for the accuracy of the prediction model but also provide valuable information for a deeper understanding of the sensitivity of college students' interpersonal relationships. In conclusion, the bREMFO-KELM model excels not only in performance but also possesses a high degree of interpretability, providing robust support for predicting the sensitivity of interpersonal relationships in college students.
Collapse
|
2
|
A hybrid multimodal machine learning model for Detecting Alzheimer's disease. Comput Biol Med 2024; 170:108035. [PMID: 38325214 DOI: 10.1016/j.compbiomed.2024.108035] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2023] [Revised: 01/03/2024] [Accepted: 01/26/2024] [Indexed: 02/09/2024]
Abstract
Alzheimer's disease (AD) diagnosis utilizing single modality neuroimaging data has limitations. Multimodal fusion of complementary biomarkers may improve diagnostic performance. This study proposes a multimodal machine learning framework integrating magnetic resonance imaging (MRI), positron emission tomography (PET) and cerebrospinal fluid (CSF) assays for enhanced AD characterization. The model incorporates a hybrid algorithm combining enhanced Harris Hawks Optimization (HHO) algorithm referred to as ILHHO, with Kernel Extreme Learning Machine (KELM) classifier for simultaneous feature selection and classification. ILHHO enhances HHO's search efficiency by integrating iterative mapping (IM) to improve population diversity and local escaping operator (LEO) to balance exploration-exploitation. Comparative analysis with other improved HHO algorithms, classic meta-heuristic algorithms (MHAs), and state-of-the-art MHAs on IEEE CEC2014 benchmark functions indicates that ILHHO achieves superior optimization performance compared to other comparative algorithms. The synergistic ILHHO-KELM model is evaluated on 202 AD Neuroimaging Initiative (ADNI) subjects. Results demonstrate superior multimodal classification accuracy over single modalities, validating the importance of fusing heterogeneous biomarkers. MRI + PET + CSF achieves 99.2 % accuracy for AD vs. normal control (NC), outperforming conventional and proposed methods. Discriminative feature analysis provides further insights into differential AD-related neurodegeneration patterns detected by MRI and PET. The differential PET and MRI features demonstrate how the two modalities provide complementary biomarkers. The neuroanatomical relevance of selected features supports ILHHO-KELM's potential for extracting sensitive AD imaging signatures. Overall, the study showcases the advantages of capitalizing on complementary multimodal data through advanced feature learning techniques for improving AD diagnosis.
Collapse
|
3
|
A Deep Learning-Based Approach for Cervical Cancer Classification Using 3D CNN and Vision Transformer. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:280-296. [PMID: 38343216 DOI: 10.1007/s10278-023-00911-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/18/2023] [Revised: 08/30/2023] [Accepted: 09/19/2023] [Indexed: 03/02/2024]
Abstract
Cervical cancer is a significant health problem worldwide, and early detection and treatment are critical to improving patient outcomes. To address this challenge, a deep learning (DL)-based cervical classification system is proposed using 3D convolutional neural network and Vision Transformer (ViT) module. The proposed model leverages the capability of 3D CNN to extract spatiotemporal features from cervical images and employs the ViT model to capture and learn complex feature representations. The model consists of an input layer that receives cervical images, followed by a 3D convolution block, which extracts features from the images. The feature maps generated are down-sampled using max-pooling block to eliminate redundant information and preserve important features. Four Vision Transformer models are employed to extract efficient feature maps of different levels of abstraction. The output of each Vision Transformer model is an efficient set of feature maps that captures spatiotemporal information at a specific level of abstraction. The feature maps generated by the Vision Transformer models are then supplied into the 3D feature pyramid network (FPN) module for feature concatenation. The 3D squeeze-and-excitation (SE) block is employed to obtain efficient feature maps that recalibrate the feature responses of the network based on the interdependencies between different feature maps, thereby improving the discriminative power of the model. At last, dimension minimization of feature maps is executed using 3D average pooling layer. Its output is then fed into a kernel extreme learning machine (KELM) for classification into one of the five classes. The KELM uses radial basis kernel function (RBF) for mapping features in high-dimensional feature space and classifying the input samples. The superiority of the proposed model is known using simulation results, achieving an accuracy of 98.6%, demonstrating its potential as an effective tool for cervical cancer classification. Also, it can be used as a diagnostic supportive tool to assist medical experts in accurately identifying cervical cancer in patients.
Collapse
|
4
|
Advanced machine learning model for predicting Crohn's disease with enhanced ant colony optimization. Comput Biol Med 2023; 163:107216. [PMID: 37399742 DOI: 10.1016/j.compbiomed.2023.107216] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2023] [Revised: 06/13/2023] [Accepted: 06/25/2023] [Indexed: 07/05/2023]
Abstract
Changes in human lifestyles have led to a dramatic increase in the incidence of Crohn's disease worldwide. Predicting the activity and remission of Crohn's disease has become an urgent research problem. In addition, the influence of each attribute in the test sample on the prediction results and the interpretability of the model still deserves further investigation. Therefore, in this paper, we proposed a wrapper feature selection classification model based on a combination of the improved ant colony optimization algorithm and the kernel extreme learning machine, called bIACOR-KELM-FS. IACOR introduces an evasive strategy and astrophysics strategy to balance the exploration and exploitation phases of the algorithm and enhance its optimization capabilities. The optimization capability of the proposed IACOR was validated on the IEEE CEC2017 benchmark test function. And the prediction was performed on Crohn's disease dataset. The results of the quantitative analysis showed that the prediction accuracy of bIACOR-KELM-FS for predicting the activity and remission of Crohn's disease reached 98.98%. The analysis of important attributes improved the interpretability of the model and provided a reference for the diagnosis of Crohn's disease. Therefore, the proposed model is considered a promising adjunctive diagnostic method for Crohn's disease.
Collapse
|
5
|
An enhanced Runge Kutta boosted machine learning framework for medical diagnosis. Comput Biol Med 2023; 160:106949. [PMID: 37159961 DOI: 10.1016/j.compbiomed.2023.106949] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/24/2022] [Revised: 03/27/2023] [Accepted: 04/15/2023] [Indexed: 05/11/2023]
Abstract
With the development and maturity of machine learning methods, medical diagnosis aided with machine learning methods has become a popular method to assist doctors in diagnosing and treating patients. However, machine learning methods are greatly affected by their hyperparameters, for instance, the kernel parameter in kernel extreme learning machine (KELM) and the learning rate in residual neural networks (ResNet). If the hyperparameters are appropriately set, the performance of the classifier can be significantly improved. To boost the performance of the machine learning methods, this paper proposes to improve the Runge Kutta optimizer (RUN) to adaptively adjust the hyperparameters of the machine learning methods for medical diagnosis purposes. Although RUN has a solid mathematical theoretical foundation, there are still some performance defects when dealing with complex optimization problems. To remedy these defects, this paper proposes a new enhanced RUN method with a grey wolf mechanism and an orthogonal learning mechanism called GORUN. The superior performance of the GORUN was validated against other well-established optimizers on IEEE CEC 2017 benchmark functions. Then, the proposed GORUN is employed to optimize the machine learning models, including the KELM and ResNet, to construct robust models for medical diagnosis. The performance of the proposed machine learning framework was validated on several medical data sets, and the experimental results have demonstrated its superiority.
Collapse
|
6
|
SMS sentiment classification using an evolutionary optimization based fuzzy recurrent neural network. MULTIMEDIA TOOLS AND APPLICATIONS 2023:1-32. [PMID: 37362691 PMCID: PMC10107590 DOI: 10.1007/s11042-023-15206-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/17/2022] [Revised: 09/13/2022] [Accepted: 03/30/2023] [Indexed: 06/28/2023]
Abstract
Sentiment analysis using the inbox message polarity is a challenging task in text mining, this analysis is used to differentiate spam and ham messages in mail. Polarity estimation is mandatory for spam and ham identification, whereas developing a perfect architecture for such classification is the hot demanding topic. To fulfill that, fuzzy based Recurrent Neural network-based Harris Hawk optimization (FRNN-HHO) is introduced, which performs post-classification over the classified messages (spam and ham). Previously the authors tried to classify the spam and ham messages from the collection of SMSs. But sometimes, the spam messages may incorrectly be classified within the ham classes. This misclassification may reduce the accuracy. The sentiment analysis process is performed over the classified messages to improve such classification accuracy. The spam and ham messages from the available data are classified using a Kernel Extreme Learning Machine (KELM) classifier. The sentiment analysis and classification based experimental evaluation is carried out using accuracy, recall, f-measure, precision, RMSE, and MAE. The performance of the proposed architecture is evaluated using threedifferent datasets: SMS, Email, and spam-assassin. The Area under the curve (AUC) of the proposed approach is found to be 0.9699 (SMS dataset), 0.958 (Email dataset), and 0.95 (spam assassin).
Collapse
|
7
|
A novel prediction model based on decomposition-integration and error correction for COVID-19 daily confirmed and death cases. Comput Biol Med 2023; 156:106674. [PMID: 36871336 PMCID: PMC9942481 DOI: 10.1016/j.compbiomed.2023.106674] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2022] [Revised: 01/15/2023] [Accepted: 02/11/2023] [Indexed: 02/25/2023]
Abstract
Coronavirus disease (COVID-19) has infected billion people around the world and affected the economy, but most countries are considering reopening, so the COVID-19 daily confirmed and death cases have increased greatly. It is very necessary to predict the COVID-19 daily confirmed and death cases in order to help every country formulate prevention policies. To enhance the prediction performance, this paper proposes a prediction model based on improved variational mode decomposition by sparrow search algorithm (SVMD), improved kernel extreme learning machine by Aquila optimizer algorithm (AO-KELM) and error correction idea, named SVMD-AO-KELM-error for short-term prediction of COVID-19 cases. Firstly, to solve mode number and penalty factor selection of variational mode decomposition (VMD), an improved VMD based on sparrow search algorithm (SSA), named SVMD, is proposed. SVMD decomposes the COVID-19 case data into some intrinsic mode function (IMF) components and residual is considered. Secondly, to properly selected regularization coefficients and kernel parameters of kernel extreme learning machine (KELM) and improve the prediction performance of KELM, an improved KELM by Aquila optimizer (AO) algorithm, named AO-KELM, is proposed. Each component is predicted by AO-KELM. Then, the prediction error of IMF and residual are predicted by AO-KELM to correct prediction results, which is error correction idea. Finally, prediction results of each component and error prediction results are reconstructed to get final prediction results. Through the simulation experiment of the COVID-19 daily confirmed and death cases in Brazil, Mexico, and Russia and comparison with twelve comparative models, simulation experiment gives that SVMD-AO-KELM-error has best prediction accuracy. It also proves that the proposed model can be used to predict the pandemic COVID-19 cases and offers a novel approach for COVID-19 cases prediction.
Collapse
|
8
|
An evolutionary machine learning for multiple myeloma using Runge Kutta Optimizer from multi characteristic indexes. Comput Biol Med 2022; 150:106189. [PMID: 37859284 DOI: 10.1016/j.compbiomed.2022.106189] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2022] [Revised: 10/02/2022] [Accepted: 10/08/2022] [Indexed: 11/26/2022]
Abstract
Multiple myeloma (MM) is a malignant plasma cell disease that is the second most prevalent hematological malignancy in high-income nations and accounts for around 1.8% of all cancers and 18% of hematologic malignancies in the United States. In this research, we try to design a machine learning framework for MM diagnosis from multi characteristic indexes using slime mould Runge Kutta Optimizer (MSRUN) and kernel extreme learning machine, which is called as MSRUN-KELM. An efficient slime mould learning operator is introduced to the initial Runge Kutta Optimizer in MSRUN, ensuring that the trade-off between intensity and diversity is satisfied. The MSRUN was evaluated using IEEE CEC2014 benchmark functions, and the statistical results indicate a significant increase in the search performance of MSRUN. In MSRUN-KELM, kernel extreme machine learning is constructed on MM from multi-characteristic indexes with MSRUN, parameter optimization, and feature selection synchronized by MSRUN. The results of MSRUN-KELM on MM are accuracy of 93.88%, a Matthews correlation coefficient of 0.922677, and sensitivities of 93.41% and 93.19%. The suggested MSRUN-KELM may be utilized to analyze MM from multi-characteristic indexes well, and it can be treated as a potential tool for MM diagnosis.
Collapse
|
9
|
A new hybrid prediction model of air quality index based on secondary decomposition and improved kernel extreme learning machine. CHEMOSPHERE 2022; 305:135348. [PMID: 35718028 DOI: 10.1016/j.chemosphere.2022.135348] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/21/2022] [Revised: 05/26/2022] [Accepted: 06/12/2022] [Indexed: 06/15/2023]
Abstract
Air quality index (AQI) prediction is important to control air pollution. To improve its accuracy, a new hybrid prediction model of AQI based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), multivariate multiscale dispersion entropy (mvMDE), variational mode decomposition optimized by bald eagle search (BES) algorithm (BVMD) and kernel extreme learning machine optimized by rat swarm optimizer (RSO) algorithm (RSO-KELM), named CEEMDAN-mvMDE-BVMD-RSO-KELM, is proposed. Firstly, AQI series is decomposed by CEEMDAN to obtain multiple intrinsic mode function (IMF) components, and each IMF component's complexity is calculated by mvMDE. Secondly, VMD optimized by BES algorithm, named BVMD, is proposed to solve the problem of choosing the decomposition level K and penalty factor α of VMD, and BVMD is used to perform the secondary decomposition of high complexity components. Thirdly, the penalty coefficient and kernel parameter of KELM optimized by RSO algorithm, named RSO-KELM, is proposed, and all IMF components are predicted by RSO-KELM. Finally, the final prediction results are obtained by reconstructing the prediction results of all IMF components. The objective of this study is to propose a new hybrid prediction model of AQI based on secondary decomposition and improved KELM. Taking Shanghai, Beijing and Xi'an as examples, the results show that compared with the comparison models, the proposed model has the highest prediction accuracy.
Collapse
|
10
|
An evolutionary machine learning for pulmonary hypertension animal model from arterial blood gas analysis. Comput Biol Med 2022; 146:105529. [PMID: 35594682 DOI: 10.1016/j.compbiomed.2022.105529] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2022] [Revised: 04/11/2022] [Accepted: 04/13/2022] [Indexed: 11/03/2022]
Abstract
Pulmonary hypertension (PH) is a rare and fatal condition that leads to right heart failure and death. The pathophysiology of PH and potential therapeutic approaches are yet unknown. PH animal models' development and proper evaluation are critical to PH research. This work presents an effective analysis technology for PH from arterial blood gas analysis utilizing an evolutionary kernel extreme learning machine with multiple strategies integrated slime mould algorithm (MSSMA). In MSSMA, two efficient bee-foraging learning operators are added to the original slime mould algorithm, ensuring a suitable trade-off between intensity and diversity. The proposed MSSMA is evaluated on thirty IEEE benchmarks and the statistical results show that the search performance of the MSSMA is significantly improved. The MSSMA is utilised to develop a kernel extreme learning machine (MSSMA-KELM) on PH from arterial blood gas analysis. Comprehensively, the proposed MSSMA-KELM can be used as an effective analysis technology for PH from arterial Blood gas analysis with an accuracy of 93.31%, Matthews coefficient of 90.13%, Sensitivity of 91.12%, and Specificity of 90.73%. MSSMA-KELM can be treated as an effective approach for evaluating mouse PH models.
Collapse
|
11
|
Chaotic simulated annealing multi-verse optimization enhanced kernel extreme learning machine for medical diagnosis. Comput Biol Med 2022; 144:105356. [PMID: 35299042 DOI: 10.1016/j.compbiomed.2022.105356] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2021] [Revised: 02/25/2022] [Accepted: 02/25/2022] [Indexed: 01/09/2023]
Abstract
Classification models such as Multi-Verse Optimization (MVO) play a vital role in disease diagnosis. To improve the efficiency and accuracy of MVO, in this paper, the defects of MVO are mitigated and the improved MVO is combined with kernel extreme learning machine (KELM) for effective disease diagnosis. Although MVO obtains some relatively good results on some problems of interest, it suffers from slow convergence speed and local optima entrapment for some many-sided basins, especially multi-modal problems with high dimensions. To solve these shortcomings, in this study, a new chaotic simulated annealing overhaul of MVO (CSAMVO) is proposed. Based on MVO, two approaches are adopted to offer a relatively stable and efficient convergence speed. Specifically, a chaotic intensification mechanism (CIP) is applied to the optimal universe evaluation stage to increase the depth of the universe search. After obtaining relatively satisfactory results, the simulated annealing algorithm (SA) is employed to reinforce the capability of MVO to avoid local optima. To evaluate its performance, the proposed CSAMVO approach was compared with a wide range of classical algorithms on thirty-nine benchmark functions. The results show that the improved MVO outperforms the other algorithms in terms of solution quality and convergence speed. Furthermore, based on CSAMVO, a hybrid KELM model termed CSAMVO-KELM is established for disease diagnosis. To evaluate its effectiveness, the new hybrid system was compared with a multitude of competitive classifiers on two disease diagnosis problems. The results demonstrate that the proposed CSAMVO-assisted classifier can find solutions with better learning potential and higher predictive performance.
Collapse
|
12
|
Evolving kernel extreme learning machine for medical diagnosis via a disperse foraging sine cosine algorithm. Comput Biol Med 2021; 141:105137. [PMID: 34953358 DOI: 10.1016/j.compbiomed.2021.105137] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2021] [Revised: 12/11/2021] [Accepted: 12/11/2021] [Indexed: 11/16/2022]
Abstract
Kernel extreme learning machine (KELM) has been widely used in the fields of classification and identification since it was proposed. As the parameters in the KELM model have a crucial impact on performance, they must be optimized before the model can be applied in practical areas. In this study, to improve optimization performance, a new parameter optimization strategy is proposed, based on a disperse foraging sine cosine algorithm (DFSCA), which is utilized to force some portions of search agents to explore other potential regions. Meanwhile, DFSCA is integrated into KELM to establish a new machine learning model named DFSCA-KELM. Firstly, using the CEC2017 benchmark suite, the exploration and exploitation capabilities of DFSCA were demonstrated. Secondly, evaluation of the model DFSCA-KELM on six medical datasets extracted from the UCI machine learning repository for medical diagnosis proved the effectiveness of the proposed model. At last, the model DFSCA-KELM was applied to solve two real medical cases, and the results indicate that DFSCA-KELM can also deal with practical medical problems effectively. Taken together, these results show that the proposed technique can be regarded as a promising tool for medical diagnosis.
Collapse
|
13
|
Evolutionary warning system for COVID-19 severity: Colony predation algorithm enhanced extreme learning machine. Comput Biol Med 2021; 136:104698. [PMID: 34426165 PMCID: PMC8323529 DOI: 10.1016/j.compbiomed.2021.104698] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2021] [Revised: 07/20/2021] [Accepted: 07/23/2021] [Indexed: 12/22/2022]
Abstract
Coronavirus Disease 2019 (COVID-19) was distributed globally at the end of December 2019 due to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Early diagnosis and successful COVID-19 assessment are missing, clinical care is ineffective, and deaths are high. In this study, we investigate whether the level of biochemical indicators helps to discriminate and classify the severity of the COVID-19 using the machine learning method. This research creates an efficient intelligence method for the diagnosis of COVID-19 from the perspective of biochemical indexes. The framework is proposed by integrating an enhanced new stochastic called the colony predation algorithm (CPA) with a kernel extreme learning machine (KELM), abbreviated as ECPA-KELM. The core feature of the approach is the ECPA algorithm which incorporates the two main operators that have been abstained from the grey wolf optimizer and moth-flame optimizer to improve and restore the CPA research functions and are simultaneously used to optimize the parameters and to select features for KELM. The ECPA output is checked thoroughly using IEEE CEC2017 benchmark to verify the capacity of the proposed methodology. Finally, in the diagnosis of COVID-19 using biochemical indexes, the designed ECPA-KELM model and other competing KELM models based on other optimization are used. Checking statistical results will display improved predictive properties for all metrics and higher stability. ECPA-KELM can also be used to discriminate and classify the severity of the COVID-19 as a possible computer-aided method and provide effective early warning for the treatment and diagnosis of COVID-19.
Collapse
|
14
|
Intelligent fault diagnosis of high-voltage circuit breakers using triangular global alignment kernel extreme learning machine. ISA TRANSACTIONS 2021; 109:368-379. [PMID: 33077172 DOI: 10.1016/j.isatra.2020.10.018] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/17/2019] [Revised: 06/15/2020] [Accepted: 10/04/2020] [Indexed: 06/11/2023]
Abstract
In recent years, vibration-based intelligent fault diagnosis of high-voltage circuit breakers (HVCBs) exhibits excellent performance. It requires a reliable machine learning method to develop an automatically diagnostic model to recognize the mechanical state from vibration signals. However, the traditional machine learning methods tend to produce unstable diagnostic results under the case of sampling asynchrony caused by the fluctuation of the control voltage. To address this problem, an improved kernel extreme learning machine (K-ELM) called triangular global alignment kernel (TGAK) extreme learning machine (TGAK-ELM) was presented in this study, which was developed by introducing TGAK into K-ELM. The TGAK is an elastic kernel which was designed by considering all the possible alignments between samples. Therefore, it provides a flexible similarity measure for samples, resulting in the improvement of the diagnostic performance. Experiments on the 35kV HVCB verified the effectiveness of the proposed method. Compared to other state-of-the-art machine learning methods, the proposed TGAK-ELM produced better diagnostic results. And further experiments on eight datasets picked from UCR repository suggested the applicability of TGAK-ELM in other fields.
Collapse
|
15
|
Groundwater contamination sources identification based on kernel extreme learning machine and its effect due to wavelet denoising technique. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2020; 27:34107-34120. [PMID: 32557044 DOI: 10.1007/s11356-020-08996-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/11/2019] [Accepted: 04/22/2020] [Indexed: 06/11/2023]
Abstract
Measurements of contaminant concentrations inevitably contain noise because of accidental and systematic errors. However, groundwater contamination sources identification (GCSI) is highly dependent on the data measurements, which directly affect the accuracy of the identification results. Thus, in the present study, the wavelet hierarchical threshold denoising method was employed to denoise concentration measurements and the denoised measurements were then used for GCSI. A 0-1 mixed-integer nonlinear programming optimization model (0-1 MINLP) based on a kernel extreme learning machine (KELM) was applied to identify the location and release history of a contamination source. The results showed the following. (1) The wavelet hierarchical threshold denoising method was not very effective when applied to concentration measurements observed every 2 months (the number of measurements is small and relatively discrete) compared with those obtained every 2 days (the number of measurements is large and relatively continuous). (2) When the concentration measurements containing noise were employed for GCSI, the identifications results were further from the true values when the measurements contained more noise. The approximation of the identification results to the true values improved when the denoised concentration measurements were employed for GCSI. (3) The 0-1 MINLP based on the surrogate KELM model could simultaneously identify the location and release history of contamination sources, as well reducing the computational load and decreasing the calculation time by 96.5% when solving the 0-1 MINLP.
Collapse
|
16
|
A novel hybrid feature selection strategy in quantitative analysis of laser-induced breakdown spectroscopy. Anal Chim Acta 2019; 1080:35-42. [PMID: 31409473 DOI: 10.1016/j.aca.2019.07.012] [Citation(s) in RCA: 39] [Impact Index Per Article: 7.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2019] [Revised: 07/03/2019] [Accepted: 07/07/2019] [Indexed: 10/26/2022]
Abstract
Laser-induced breakdown spectroscopy (LIBS) has been recognized as a significant tool for quantitative analysis of elements with its unique advantages, especially in combination with multivariate calibration methods. However, LIBS spectra typically include large amounts of high-dimensional data that affect the predictive accuracy of multivariate calibration based on LIBS. Feature selection, as an important preprocessing step in data mining, can improve the performance of the multivariate calibration model by eliminating the redundant and irrelevant features. In this study, a hybrid feature selection method based on V-WSP-PSO was proposed to improve the accuracy of LIBS analysis. The proposed method combines the advantages of V-WSP based filter method and particle swarm optimization (PSO) based wrapper method. The uncorrelated and redundant features were first eliminated by V-WSP method to form a simplified input subset, and then the retained features were further refined by PSO method to find a small set of features with high predictive accuracy. In order to evaluate the performance of proposed method, LIBS experiments were performed using 28 coal samples, and a nonlinear multivariate calibration method based on kernel extreme learning machine (KELM) was selected to implement the proposed hybrid feature selection method for calorific value determination of coal. Comparing the proposed method with several other feature selection methods shows that the V-WSP-PSO method is best in terms of number of selected features and predictive accuracy. Finally, 114 features were selected from full spectrum (27620 features) by V-WSP-PSO method and the best root mean square error of cross validation (RMSECV) and determination coefficient of cross validation (RCV2) were 0.4013 MJ/kg and 0.9908, root mean square error of prediction (RMSEP) and determination coefficient of prediction (RP2) were 0.3534 MJ/kg and 0.9894. The overall results demonstrate that the V-WSP-PSO method is more efficient to reduce the redundant features, calculation time and improve the model performance, and it is a good alternative for feature selection in multivariate calibration.
Collapse
|
17
|
A fast kernel extreme learning machine based on conjugate gradient. NETWORK (BRISTOL, ENGLAND) 2019; 29:70-80. [PMID: 30688136 DOI: 10.1080/0954898x.2018.1562247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/19/2018] [Revised: 10/27/2018] [Accepted: 12/17/2018] [Indexed: 06/09/2023]
Abstract
Kernel extreme learning machine (KELM) introduces kernel leaning into extreme learning machine (ELM) in order to improve the generalization ability and stability. But the Penalty parameter in KELM is randomly set and it has a strong impact on the performance of KELM. A fast KELM combining the conjugate gradient method (CG-KELM) is presented in this paper. The CG-KELM computes the output weights of the neural network by the conjugate gradient iteration method. There is no penalty parameter to be set in CG-KELM. Therefore, the CG-KELM has good generalization ability and fast learning speed. The simulations in image restoration show that CG-KELM outperforms KELM. The CG-KELM provides a balanced method between KELM and ELM.
Collapse
|