Lithium battery-based electric vehicles (EVs) are gaining global popularity as an alternative to combat the adverse environmental impacts caused by the utilization of fossil fuels. State of charge (SOC) and state of health (SOH) are vital parameters that assess the battery’s remaining charge and overall health. Precise monitoring of SOC and SOH is critical for effectively operating the battery management system (BMS) in a lithium battery. This article presents an experimental study for the artificial intelligence (AI)-based data-driven prediction of lithium battery parameters SOC and SOH with the help of deep learning algorithms such as Long Short-Term Memory (LSTM) and bidirectional LSTM (BiLSTM). We utilized various gradient descent optimization algorithms with adaptive and constant learning rates with other default parameters. Compared between various gradient descent algorithms, the selection of the optimal one depends on mean absolute error (MAE) and root mean squared error (RMSE) accuracy. We developed an LSTM and BiLSTM model with four hidden layers with 128 LSTM or BiLSTM units per hidden layer that use Panasonic 18650PF Li-ion dataset released by NASA to predict SOC and SOH. Our experimental results advise that the selection of the optimal gradient descent algorithm impacts the model’s accuracy. The article also addresses the problem of overfitting in the LSTM/BiLSTM model. BiLSTM is the best choice to improve the model’s performance but increase the cost. We trained the model with various combinations of parameters and tabulated the accuracies in terms of MAE and RMSE. This optimal LSTM model can predict the SOC of the lithium battery with MAE more minor than 0.0179%, RMSE 0.0227% in the training phase, MAE smaller than 0.695%, and RMSE 0.947% in the testing phase over a 25°C dataset. The BiLSTM can predict the SOC of the 18650PF lithium battery cell with MAE smaller than 0.012% for training and 0.016% for testing. Similarly, using the Adam optimization algorithm, RMSE for training and testing is 0.326% and 0.454% over a 25°C dataset, respectively. BiLSTM with an adaptive learning rate can improve performance. To provide an alternative solution to high power consuming processors such as central processing unit (CPU) and graphics processing unit (GPU), we implemented the model on field programmable gate Aarray (FPGA) PYNQ Z2 hardware device. The LSTM model using FPGA performs better.
{"title":"Accelerating AI-Based Battery Management System's SOC and SOH on FPGA","authors":"Satyashil D. Nagarale, B. Patil","doi":"10.1155/2023/2060808","DOIUrl":"https://doi.org/10.1155/2023/2060808","url":null,"abstract":"Lithium battery-based electric vehicles (EVs) are gaining global popularity as an alternative to combat the adverse environmental impacts caused by the utilization of fossil fuels. State of charge (SOC) and state of health (SOH) are vital parameters that assess the battery’s remaining charge and overall health. Precise monitoring of SOC and SOH is critical for effectively operating the battery management system (BMS) in a lithium battery. This article presents an experimental study for the artificial intelligence (AI)-based data-driven prediction of lithium battery parameters SOC and SOH with the help of deep learning algorithms such as Long Short-Term Memory (LSTM) and bidirectional LSTM (BiLSTM). We utilized various gradient descent optimization algorithms with adaptive and constant learning rates with other default parameters. Compared between various gradient descent algorithms, the selection of the optimal one depends on mean absolute error (MAE) and root mean squared error (RMSE) accuracy. We developed an LSTM and BiLSTM model with four hidden layers with 128 LSTM or BiLSTM units per hidden layer that use Panasonic 18650PF Li-ion dataset released by NASA to predict SOC and SOH. Our experimental results advise that the selection of the optimal gradient descent algorithm impacts the model’s accuracy. The article also addresses the problem of overfitting in the LSTM/BiLSTM model. BiLSTM is the best choice to improve the model’s performance but increase the cost. We trained the model with various combinations of parameters and tabulated the accuracies in terms of MAE and RMSE. This optimal LSTM model can predict the SOC of the lithium battery with MAE more minor than 0.0179%, RMSE 0.0227% in the training phase, MAE smaller than 0.695%, and RMSE 0.947% in the testing phase over a 25°C dataset. The BiLSTM can predict the SOC of the 18650PF lithium battery cell with MAE smaller than 0.012% for training and 0.016% for testing. Similarly, using the Adam optimization algorithm, RMSE for training and testing is 0.326% and 0.454% over a 25°C dataset, respectively. BiLSTM with an adaptive learning rate can improve performance. To provide an alternative solution to high power consuming processors such as central processing unit (CPU) and graphics processing unit (GPU), we implemented the model on field programmable gate Aarray (FPGA) PYNQ Z2 hardware device. The LSTM model using FPGA performs better.","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":"47 1","pages":"2060808:1-2060808:18"},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75116893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Covid-19 has been a life-changer in the sphere of online education. With complete lockdown in various countries, there has been a tumultuous increase in the need for providing online education, and hence, it has become mandatory for examiners to ensure that a fair methodology is followed for evaluation, and academic integrity is met. A plethora of literature is available related to methods to mitigate cheating during online examinations. A systematic literature review (SLR) has been followed in our article which aims at introducing the research gap in terms of the usage of soft computing techniques to combat cheating during online examinations. We have also presented state-of-the-art methods followed, which are capable of mitigating online cheating, namely, face recognition, face expression recognition, head posture analysis, eye gaze tracking, network data traffic analysis, and detection of IP spoofing. A discussion on improvement of existing online cheating detection systems has also been presented.
{"title":"Computational Intelligence and Soft Computing Paradigm for Cheating Detection in Online Examinations","authors":"S. Kaddoura, S. Vincent, D. Hemanth","doi":"10.1155/2023/3739975","DOIUrl":"https://doi.org/10.1155/2023/3739975","url":null,"abstract":"Covid-19 has been a life-changer in the sphere of online education. With complete lockdown in various countries, there has been a tumultuous increase in the need for providing online education, and hence, it has become mandatory for examiners to ensure that a fair methodology is followed for evaluation, and academic integrity is met. A plethora of literature is available related to methods to mitigate cheating during online examinations. A systematic literature review (SLR) has been followed in our article which aims at introducing the research gap in terms of the usage of soft computing techniques to combat cheating during online examinations. We have also presented state-of-the-art methods followed, which are capable of mitigating online cheating, namely, face recognition, face expression recognition, head posture analysis, eye gaze tracking, network data traffic analysis, and detection of IP spoofing. A discussion on improvement of existing online cheating detection systems has also been presented.","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":"58 1","pages":"3739975:1-3739975:23"},"PeriodicalIF":0.0,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80162105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Asaad Shakir Hameed, Haiffa Muhsan B. Alrikabi, Abeer A. Abdul-Razaq, Z. Ahmed, H. Nasser, M. Mutar
The discrete differential evolution (DDE) algorithm is an evolutionary algorithm (EA) that has effectively solved challenging optimization problems. However, like many other EAs, it still faces problems such as premature convergence and stagnation during the iterative process. To address these concerns in the DDE algorithm, this work aims to achieve the following objectives: (i) investigate the causes of premature convergence and stagnation in the DDE algorithm; (ii) propose techniques to prevent premature convergence and stagnation in DDE, including a quantitative measurement of premature convergence based on the level of mismatching between the population solutions and then divide the population into individual groups based on the level of mismatching between the population solutions and the best solution; and applying the roulette wheel selection (RWS) approach to determine whether a higher degree of nonmatching is more suitable for choosing a population of separate groups to be able to produce a new solution with more options to prevent the occurrence of premature convergence; (iii) evaluate the effectiveness of the proposed techniques through employing the DDE algorithm to solve the quadratic assignment problem (QAP) as a standard to evaluate our results and their effect on avoiding premature convergence and stagnation issues, which led to the enhancement of the algorithm’s accuracy. Our comparative study based on the statistical analysis shows that the DDE algorithm that uses the proposed techniques is more efficient than the traditional DDE algorithm and the state-of-the-art methods.
{"title":"Appling the Roulette Wheel Selection Approach to Address the Issues of Premature Convergence and Stagnation in the Discrete Differential Evolution Algorithm","authors":"Asaad Shakir Hameed, Haiffa Muhsan B. Alrikabi, Abeer A. Abdul-Razaq, Z. Ahmed, H. Nasser, M. Mutar","doi":"10.1155/2023/8892689","DOIUrl":"https://doi.org/10.1155/2023/8892689","url":null,"abstract":"The discrete differential evolution (DDE) algorithm is an evolutionary algorithm (EA) that has effectively solved challenging optimization problems. However, like many other EAs, it still faces problems such as premature convergence and stagnation during the iterative process. To address these concerns in the DDE algorithm, this work aims to achieve the following objectives: (i) investigate the causes of premature convergence and stagnation in the DDE algorithm; (ii) propose techniques to prevent premature convergence and stagnation in DDE, including a quantitative measurement of premature convergence based on the level of mismatching between the population solutions and then divide the population into individual groups based on the level of mismatching between the population solutions and the best solution; and applying the roulette wheel selection (RWS) approach to determine whether a higher degree of nonmatching is more suitable for choosing a population of separate groups to be able to produce a new solution with more options to prevent the occurrence of premature convergence; (iii) evaluate the effectiveness of the proposed techniques through employing the DDE algorithm to solve the quadratic assignment problem (QAP) as a standard to evaluate our results and their effect on avoiding premature convergence and stagnation issues, which led to the enhancement of the algorithm’s accuracy. Our comparative study based on the statistical analysis shows that the DDE algorithm that uses the proposed techniques is more efficient than the traditional DDE algorithm and the state-of-the-art methods.","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":"452 1","pages":"8892689:1-8892689:16"},"PeriodicalIF":0.0,"publicationDate":"2023-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77518888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study aims to develop a hybridized deep learning model for generating semantically meaningful image captions in Amharic Language. Image captioning is a task that combines both computer vision and natural language processing (NLP) domains. However, existing studies in the English language primarily focus on visual features to generate captions, resulting in a gap between visual and textual features and inadequate semantic representation. To address this challenge, this study proposes a hybridized attention-based deep neural network (DNN) model. The model consists of an Inception-v3 convolutional neural network (CNN) encoder to extract image features, a visual attention mechanism to capture significant features, and a bidirectional gated recurrent unit (Bi-GRU) with attention decoder to generate the image captions. The model was trained on the Flickr8k and BNATURE datasets with English captions, which were translated into Amharic Language with the help of Google Translator and Amharic Language experts. The evaluation of the model showed improvement in its performance, with a 1G-BLEU score of 60.6, a 2G-BLEU score of 50.1, a 3G-BLEU score of 43.7, and a 4G-BLEU score of 38.8. Generally, this study highlights the effectiveness of the hybrid approach in generating Amharic Language image captions with better semantic meaning.
{"title":"Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural Networks","authors":"Rodas Solomon, Mesfin Abebe","doi":"10.1155/2023/9397325","DOIUrl":"https://doi.org/10.1155/2023/9397325","url":null,"abstract":"This study aims to develop a hybridized deep learning model for generating semantically meaningful image captions in Amharic Language. Image captioning is a task that combines both computer vision and natural language processing (NLP) domains. However, existing studies in the English language primarily focus on visual features to generate captions, resulting in a gap between visual and textual features and inadequate semantic representation. To address this challenge, this study proposes a hybridized attention-based deep neural network (DNN) model. The model consists of an Inception-v3 convolutional neural network (CNN) encoder to extract image features, a visual attention mechanism to capture significant features, and a bidirectional gated recurrent unit (Bi-GRU) with attention decoder to generate the image captions. The model was trained on the Flickr8k and BNATURE datasets with English captions, which were translated into Amharic Language with the help of Google Translator and Amharic Language experts. The evaluation of the model showed improvement in its performance, with a 1G-BLEU score of 60.6, a 2G-BLEU score of 50.1, a 3G-BLEU score of 43.7, and a 4G-BLEU score of 38.8. Generally, this study highlights the effectiveness of the hybrid approach in generating Amharic Language image captions with better semantic meaning.","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":"48 1","pages":"9397325:1-9397325:11"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76194891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To improve power quality in power systems vulnerable to current disturbances and unbalanced loads, a hybrid control scheme is proposed in the present paper. A hybrid adaptive robust control strategy is devised for an SMIB power system equipped with a static VAR compensator to ensure robust transient stability and voltage regulation (SVC). High-order sliding mode control is combined with a dynamic adaptive backstepping algorithm to form the basis of this technique. To create controllers amenable to practical implementation, this method uses a high-order SMIB-SVC model and introduces dynamic constraints, in contrast to prior approaches. Improved transient and steady-state performances of the turbine steam-valve system are the goals of the dynamic backstepping controller. A Lyapunov-based adaptation law is developed to address the ubiquitous occurrence of parametric and nonparametric uncertainty in electrical power transmission systems due to the damping coefficient, unmodeled dynamics, and external disturbance. High-order sliding mode (HOSM) control is used for generator excitation and SVC devices to construct finite-time controllers. The necessary derivatives for HOSM control are calculated using high-order numerical differentiators to prevent simulation instability and convergence issues. Simulations demonstrate that the suggested method outperforms conventionally coordinated and hybrid adaptive control schemes regarding actuation efficiency and stability.
{"title":"Coordinate Control for an SMIB Power System with an SVC","authors":"B. Kada, A. Bensenouci","doi":"10.1155/2023/7883177","DOIUrl":"https://doi.org/10.1155/2023/7883177","url":null,"abstract":"To improve power quality in power systems vulnerable to current disturbances and unbalanced loads, a hybrid control scheme is proposed in the present paper. A hybrid adaptive robust control strategy is devised for an SMIB power system equipped with a static VAR compensator to ensure robust transient stability and voltage regulation (SVC). High-order sliding mode control is combined with a dynamic adaptive backstepping algorithm to form the basis of this technique. To create controllers amenable to practical implementation, this method uses a high-order SMIB-SVC model and introduces dynamic constraints, in contrast to prior approaches. Improved transient and steady-state performances of the turbine steam-valve system are the goals of the dynamic backstepping controller. A Lyapunov-based adaptation law is developed to address the ubiquitous occurrence of parametric and nonparametric uncertainty in electrical power transmission systems due to the damping coefficient, unmodeled dynamics, and external disturbance. High-order sliding mode (HOSM) control is used for generator excitation and SVC devices to construct finite-time controllers. The necessary derivatives for HOSM control are calculated using high-order numerical differentiators to prevent simulation instability and convergence issues. Simulations demonstrate that the suggested method outperforms conventionally coordinated and hybrid adaptive control schemes regarding actuation efficiency and stability.","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":" 18","pages":"7883177:1-7883177:11"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91515020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andrzej Janusz, Andżelika Zalewska, Lukasz Wawrowski, Piotr Biczyk, Jan Ludziejewski, M. Sikora, D. Ślęzak
{"title":"BrightBox - A rough set based technology for diagnosing mistakes of machine learning models","authors":"Andrzej Janusz, Andżelika Zalewska, Lukasz Wawrowski, Piotr Biczyk, Jan Ludziejewski, M. Sikora, D. Ślęzak","doi":"10.2139/ssrn.4348262","DOIUrl":"https://doi.org/10.2139/ssrn.4348262","url":null,"abstract":"","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":"12 1","pages":"110285"},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88821790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Babak Rezaei, F. G. Guimarães, R. Enayatifar, P. Haddow
{"title":"Combining genetic local search into a multi-population Imperialist Competitive Algorithm for the Capacitated Vehicle Routing Problem","authors":"Babak Rezaei, F. G. Guimarães, R. Enayatifar, P. Haddow","doi":"10.2139/ssrn.4263547","DOIUrl":"https://doi.org/10.2139/ssrn.4263547","url":null,"abstract":"","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":"91 1","pages":"110309"},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87071026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：