Pub Date : 2023-06-27DOI: 10.1080/00051144.2023.2226946
Vibith A. S., Jobin Christ M C
Breast cancer is the second leading cause of disease death in women, after lung and bronchus cancer. According to measurements, mammography misses breast cancer in 10% to 15% of cases for women aged 50 to 69 years. In the current study, we used the Wisconsin breast cancer dataset to develop a two-stage model for breast cancer diagnosis. The main goal of this study effort is to effectively carry out feature selection and classification tasks. Gradient Boosting Decision Tree-based Mayfly Optimisation (GBDTMO), an innovative and efficient breast cancer diagnostic machine learning system, is provided. In the second stage, we employ a Mayfly search to determine which subset of traits is the best. Two more well-known datasets on breast cancer, the ICCR and the Cancer Corpus, were also compared for classification accuracy. The accuracy of the suggested GBDTMO model was higher than that of the existing GBDT and Practical Federated Gradient Boosting Decision Tree (PFGBDT), which had accuracy values of 93.25% and 94.25%, respectively. Similarly, the recall, F-measure, and ROC area values were 98.52%, 97.52%, and 96.32%, respectively. Furthermore, it demonstrated a lower RMSE of 0.98 than the existing GBDT and PFGBDT.
{"title":"GBDTMO: as new option for early-stage breast cancer detection and classification using machine learning","authors":"Vibith A. S., Jobin Christ M C","doi":"10.1080/00051144.2023.2226946","DOIUrl":"https://doi.org/10.1080/00051144.2023.2226946","url":null,"abstract":"Breast cancer is the second leading cause of disease death in women, after lung and bronchus cancer. According to measurements, mammography misses breast cancer in 10% to 15% of cases for women aged 50 to 69 years. In the current study, we used the Wisconsin breast cancer dataset to develop a two-stage model for breast cancer diagnosis. The main goal of this study effort is to effectively carry out feature selection and classification tasks. Gradient Boosting Decision Tree-based Mayfly Optimisation (GBDTMO), an innovative and efficient breast cancer diagnostic machine learning system, is provided. In the second stage, we employ a Mayfly search to determine which subset of traits is the best. Two more well-known datasets on breast cancer, the ICCR and the Cancer Corpus, were also compared for classification accuracy. The accuracy of the suggested GBDTMO model was higher than that of the existing GBDT and Practical Federated Gradient Boosting Decision Tree (PFGBDT), which had accuracy values of 93.25% and 94.25%, respectively. Similarly, the recall, F-measure, and ROC area values were 98.52%, 97.52%, and 96.32%, respectively. Furthermore, it demonstrated a lower RMSE of 0.98 than the existing GBDT and PFGBDT.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48599041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-27DOI: 10.1080/00051144.2023.2223479
N. Jagadeeswari, V. Mohanraj, Y. Suresh, J. Senthilkumar
The demand for memory capacity has increased, and cloud energy usage has soared. The performance and scalability of virtualization interfaces in cloud computing are hampered by a lack of sufficient memory. To figure out this problem, a technique defined as memory deduplication is widely used to reduce memory consumption utilizing the page-sharing method. However, this method of memory deduplication using KSM has significant drawbacks, such as overhead owing to many online comparisons, which will consume so many CPU resources. In this research, a modified approach of Memory Deduplication of Static Memory Pages (mSMD), which is based on the identification of similar applications by Fuzzy hashing and clustering them using the Hierarchical Agglomerative Clustering approach, followed by similarity detection between static memory pages based on Genetic Algorithm and details stored in Multilevel shared page table, both operations performed in offline and final memory deduplication is carried out during online, is proposed for achieving performance optimization in virtual machines by reducing memory capacity requirements. When compared to existing techniques, the simulation results indicate that the proposed approach mSMD efficaciously minimizes the memory capacity required while improving performance.
{"title":"Optimization of virtual machines performance using fuzzy hashing and genetic algorithm-based memory deduplication of static pages","authors":"N. Jagadeeswari, V. Mohanraj, Y. Suresh, J. Senthilkumar","doi":"10.1080/00051144.2023.2223479","DOIUrl":"https://doi.org/10.1080/00051144.2023.2223479","url":null,"abstract":"The demand for memory capacity has increased, and cloud energy usage has soared. The performance and scalability of virtualization interfaces in cloud computing are hampered by a lack of sufficient memory. To figure out this problem, a technique defined as memory deduplication is widely used to reduce memory consumption utilizing the page-sharing method. However, this method of memory deduplication using KSM has significant drawbacks, such as overhead owing to many online comparisons, which will consume so many CPU resources. In this research, a modified approach of Memory Deduplication of Static Memory Pages (mSMD), which is based on the identification of similar applications by Fuzzy hashing and clustering them using the Hierarchical Agglomerative Clustering approach, followed by similarity detection between static memory pages based on Genetic Algorithm and details stored in Multilevel shared page table, both operations performed in offline and final memory deduplication is carried out during online, is proposed for achieving performance optimization in virtual machines by reducing memory capacity requirements. When compared to existing techniques, the simulation results indicate that the proposed approach mSMD efficaciously minimizes the memory capacity required while improving performance.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42048660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-27DOI: 10.1080/00051144.2023.2225344
C. Anjali, Julia Punitha Malar Dhas, J. Amar Pratap Singh
For the automated root cause analysis (ARCA) method and simplified RCA technique, their empirical assessment is presented in this study. A focus group meeting is a foundation for the target problem identification in the ARCA technique. This is compared to earlier RCA methodologies which rely on problem sampling for target problem discovery and high beginning costs. In this research, we suggest a naïve Bayes based machine learning method for identifying the underlying causes of newly reported software issues, which will facilitate a quicker and more effective resolution of software bugs. The ARCA technique produced a large number of high-quality corrective actions while requiring a reasonable amount of effort. The strategy is an effective way to find new opportunities for process improvement and produce fresh process improvement ideas in contrast to the organization’s corporate practices. In addition it is simple to utilize. Ultimately, we compared the methodology with other machine learning classifiers including support vector machine and decision tree.
{"title":"Automated program and software defect root cause analysis using machine learning techniques","authors":"C. Anjali, Julia Punitha Malar Dhas, J. Amar Pratap Singh","doi":"10.1080/00051144.2023.2225344","DOIUrl":"https://doi.org/10.1080/00051144.2023.2225344","url":null,"abstract":"For the automated root cause analysis (ARCA) method and simplified RCA technique, their empirical assessment is presented in this study. A focus group meeting is a foundation for the target problem identification in the ARCA technique. This is compared to earlier RCA methodologies which rely on problem sampling for target problem discovery and high beginning costs. In this research, we suggest a naïve Bayes based machine learning method for identifying the underlying causes of newly reported software issues, which will facilitate a quicker and more effective resolution of software bugs. The ARCA technique produced a large number of high-quality corrective actions while requiring a reasonable amount of effort. The strategy is an effective way to find new opportunities for process improvement and produce fresh process improvement ideas in contrast to the organization’s corporate practices. In addition it is simple to utilize. Ultimately, we compared the methodology with other machine learning classifiers including support vector machine and decision tree.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45304694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-21DOI: 10.1080/00051144.2023.2220203
A. Kavitha, S. Mary Praveena
In wireless networks, the traffic metrics often play a significant role in forecasting the traffic condition in traffic management systems. The accuracy of prediction in data-driven model gets reduced when it is influenced by non-routing or non-recurring traffic events. The analytical data model used in the proposed method takes into account not only traffic volume and congestion, but also the characteristics of individual applications and user behaviour. This allows for more accurate traffic prediction and better traffic management in wireless networks. The simulation conducted in the paper evaluates the performance of the proposed method in terms of connection success probability and latency. The results show that the proposed method achieves a connection success probability of 93% and a latency of less than 2 ms, demonstrating its effectiveness in improving traffic prediction and management in wireless networks.
{"title":"Deep learning model for traffic flow prediction in wireless network","authors":"A. Kavitha, S. Mary Praveena","doi":"10.1080/00051144.2023.2220203","DOIUrl":"https://doi.org/10.1080/00051144.2023.2220203","url":null,"abstract":"In wireless networks, the traffic metrics often play a significant role in forecasting the traffic condition in traffic management systems. The accuracy of prediction in data-driven model gets reduced when it is influenced by non-routing or non-recurring traffic events. The analytical data model used in the proposed method takes into account not only traffic volume and congestion, but also the characteristics of individual applications and user behaviour. This allows for more accurate traffic prediction and better traffic management in wireless networks. The simulation conducted in the paper evaluates the performance of the proposed method in terms of connection success probability and latency. The results show that the proposed method achieves a connection success probability of 93% and a latency of less than 2 ms, demonstrating its effectiveness in improving traffic prediction and management in wireless networks.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44543629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-13DOI: 10.1080/00051144.2023.2220207
P. Visu, P. Smitha, M. Velayutham, Mohd Wazih Ahmad
Electroencephalography (EEG) signals contain important information about the inner functioning of the brain. Effective extraction of this information will help in the detection of brain-related health conditions and emotions of a person or it can also be used as a communication medium between humans and machines. In our proposed system, we introduced Adaptive DWT by combining the temporal resolution capability of DWT, with the special capability of Fourier transform to remove the artefacts in the signal. This is achieved by using an adaptive thresholding function rather than hard or soft thresholding to improve the quality parameters of the signal. The proposed filtering model has improved the Signal to Noise ratio when compared to traditional filtering techniques. EEG features are extracted with the help of Heuristic-Independent Component Analysis (ICA) by applying covariance to equalize or improve the data. The main drawback with the existing CNN algorithm is gradient vanishing during training, this reduces the overall performance of the algorithm during classification. Therefore, using the memory function to store the previous value of iteration improves the classification accuracy and reduces the gradient vanishing problem. The proposed technique is found to have better accuracy of about 98% in classifying autism and epilepsy datasets.
{"title":"Enhanced EEG classification using adaptive DWT and heuristic-ICA algorithm","authors":"P. Visu, P. Smitha, M. Velayutham, Mohd Wazih Ahmad","doi":"10.1080/00051144.2023.2220207","DOIUrl":"https://doi.org/10.1080/00051144.2023.2220207","url":null,"abstract":"Electroencephalography (EEG) signals contain important information about the inner functioning of the brain. Effective extraction of this information will help in the detection of brain-related health conditions and emotions of a person or it can also be used as a communication medium between humans and machines. In our proposed system, we introduced Adaptive DWT by combining the temporal resolution capability of DWT, with the special capability of Fourier transform to remove the artefacts in the signal. This is achieved by using an adaptive thresholding function rather than hard or soft thresholding to improve the quality parameters of the signal. The proposed filtering model has improved the Signal to Noise ratio when compared to traditional filtering techniques. EEG features are extracted with the help of Heuristic-Independent Component Analysis (ICA) by applying covariance to equalize or improve the data. The main drawback with the existing CNN algorithm is gradient vanishing during training, this reduces the overall performance of the algorithm during classification. Therefore, using the memory function to store the previous value of iteration improves the classification accuracy and reduces the gradient vanishing problem. The proposed technique is found to have better accuracy of about 98% in classifying autism and epilepsy datasets.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44823544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-13DOI: 10.1080/00051144.2023.2222251
K. J. Nigel, R. Rajeswari
ABSTRACT Solar models have been drawing much attention in the contemporary electricity environment. Solar energy installations employ various MPPT techniques that generate the most energy. Increasing a solar (PV) device's energy effectiveness has become a key concern for scientists. Multiple MPPT approaches that collect the most power possible using a PV array have been researched. Both primary and intermediate-type procedures will be used in most procedures. The performance and convergence velocity of such a PV device become significant depending on its practical deployment under various conditions. The energy attributes of unit sections collectively serve as the primary energy-extracting elements in specific systems, dependent upon all interior and exterior elements. Considering specific external dynamical circumstances, traditional maximal power point tracing systems will not have the required translation efficacy. For assessing the overall effectiveness of the proposed intelligent maximal power point outlining methodology in partially shaded situations having significant and dynamical variations within ambient parameters, that study contrasts its efficacy using traditional maximal power point tracing techniques.
{"title":"AI-based performance optimization of MPTT algorithms for photovoltaic systems","authors":"K. J. Nigel, R. Rajeswari","doi":"10.1080/00051144.2023.2222251","DOIUrl":"https://doi.org/10.1080/00051144.2023.2222251","url":null,"abstract":"ABSTRACT Solar models have been drawing much attention in the contemporary electricity environment. Solar energy installations employ various MPPT techniques that generate the most energy. Increasing a solar (PV) device's energy effectiveness has become a key concern for scientists. Multiple MPPT approaches that collect the most power possible using a PV array have been researched. Both primary and intermediate-type procedures will be used in most procedures. The performance and convergence velocity of such a PV device become significant depending on its practical deployment under various conditions. The energy attributes of unit sections collectively serve as the primary energy-extracting elements in specific systems, dependent upon all interior and exterior elements. Considering specific external dynamical circumstances, traditional maximal power point tracing systems will not have the required translation efficacy. For assessing the overall effectiveness of the proposed intelligent maximal power point outlining methodology in partially shaded situations having significant and dynamical variations within ambient parameters, that study contrasts its efficacy using traditional maximal power point tracing techniques.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46681961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-09DOI: 10.1080/00051144.2023.2218168
G. Rashmi, M. Linda
A significant problem is enhancing the reliability of the wind energy conversion system (WECS), when that runs in unpredictable weather. Therefore, it is essential to construct a maximum power point tracker (MPPT), a controller for measuring the optimum power that the WECS is expected to generate. Hill climbing-based techniques were used to simulate the tracker, but they had drawbacks in terms of tracking efficiency and speed. The Grey Wolf optimization algorithm (GWO) for modelling MPPT integrated with the WECS is proposed in this work as a novel, effective method. The system is made up of a wind turbine (WT) conjoined to a permanent magnet synchronous generator (PMSG), a 3-phase rectifier that converts the generator’s AC output power to direct current (DC), and a boost converter whose input DC voltage is controlled by the MOSFET duty cycle. The goal of the modelling procedure is the system’s electrical output power, which is presented as an optimization problem. The results confirmed the GWO-reliability MPPT’s in reaching the desired WECS performance.
{"title":"A novel MPPT design for a wind energy conversion system using grey wolf optimization","authors":"G. Rashmi, M. Linda","doi":"10.1080/00051144.2023.2218168","DOIUrl":"https://doi.org/10.1080/00051144.2023.2218168","url":null,"abstract":"A significant problem is enhancing the reliability of the wind energy conversion system (WECS), when that runs in unpredictable weather. Therefore, it is essential to construct a maximum power point tracker (MPPT), a controller for measuring the optimum power that the WECS is expected to generate. Hill climbing-based techniques were used to simulate the tracker, but they had drawbacks in terms of tracking efficiency and speed. The Grey Wolf optimization algorithm (GWO) for modelling MPPT integrated with the WECS is proposed in this work as a novel, effective method. The system is made up of a wind turbine (WT) conjoined to a permanent magnet synchronous generator (PMSG), a 3-phase rectifier that converts the generator’s AC output power to direct current (DC), and a boost converter whose input DC voltage is controlled by the MOSFET duty cycle. The goal of the modelling procedure is the system’s electrical output power, which is presented as an optimization problem. The results confirmed the GWO-reliability MPPT’s in reaching the desired WECS performance.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48855099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-07DOI: 10.1080/00051144.2023.2219099
T. Thanya, Wilfred Franklin S
One of the most dangerous tumours in the world, pancreatic cancer (PC), has an unimpressive five-year survival rate of about 5%. An early PC identification is crucial for raising patient survival rates. Diagnosis of PC requires computed tomography (CT), magnetic resonance imaging (MRI) with magnetic resonance cholangiopancreatography (MRCP), or biopsy. The proposed CAD design approach includes image preprocessing, segmentation, feature extraction, and classification phases. Preprocessing is done by using Colour conversion and an isotropic diffusion filter approaches. After that, proposed Fuzzy K-NN Equality algorithm used in segmentation procedures. Deep Learning with feature extraction is used as a classification tool. Tumour cells are classified using the features collected from the pancreatic sample. Train values and testing datasets are part of the image classification criterion. For the purpose of detecting pancreatic cancer, a hybrid Deep Convolutional Neural Network with Deep Belief Network (DCNN_DBN) algorithm is used. According to the experimental findings, the current CAD system offers massive prospects as well as safety in the automated diagnosis of both benign as well as malignant cancers and produces the accuracy of 99.6%. Using this classifier, computing complexity is massively diminished. The suggested technique could be enhanced to detect more pancreatic cancer cell abnormalities.
{"title":"Novel computer aided diagnostic system using hybrid neural network for early detection of pancreatic cancer","authors":"T. Thanya, Wilfred Franklin S","doi":"10.1080/00051144.2023.2219099","DOIUrl":"https://doi.org/10.1080/00051144.2023.2219099","url":null,"abstract":"One of the most dangerous tumours in the world, pancreatic cancer (PC), has an unimpressive five-year survival rate of about 5%. An early PC identification is crucial for raising patient survival rates. Diagnosis of PC requires computed tomography (CT), magnetic resonance imaging (MRI) with magnetic resonance cholangiopancreatography (MRCP), or biopsy. The proposed CAD design approach includes image preprocessing, segmentation, feature extraction, and classification phases. Preprocessing is done by using Colour conversion and an isotropic diffusion filter approaches. After that, proposed Fuzzy K-NN Equality algorithm used in segmentation procedures. Deep Learning with feature extraction is used as a classification tool. Tumour cells are classified using the features collected from the pancreatic sample. Train values and testing datasets are part of the image classification criterion. For the purpose of detecting pancreatic cancer, a hybrid Deep Convolutional Neural Network with Deep Belief Network (DCNN_DBN) algorithm is used. According to the experimental findings, the current CAD system offers massive prospects as well as safety in the automated diagnosis of both benign as well as malignant cancers and produces the accuracy of 99.6%. Using this classifier, computing complexity is massively diminished. The suggested technique could be enhanced to detect more pancreatic cancer cell abnormalities.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43657712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-07DOI: 10.1080/00051144.2023.2218167
R. Sujitha, B. Paramasivan
Data used in big data applications are typically kept in decentralized computing resources in the real world, which has an impact on the design of artificial intelligence algorithms. When there are significantly more observations from one class than from another, the dataset is said to be imbalanced. Therefore, in this work, the study elaborates the model as SMOTE-SVM which resolves imbalance issues in sampling the data and improves overall accuracy to 94%. The model deploys K-nearest neighbours to compute the difference between samples and to balance the samples, it computes the kernel space. Further, to optimize the classification, GWO optimizer merges with SMOTE-SVM to achieve enhanced performance. GWO (Grey Wolf Optimizer) induces greedy selection to perform optimization among classification. It is important to remember that grey wolves have a flexible social structure that might change the hierarchy. As the mobilization continues, the grey wolves are reconstructed with the distance between them and their prey, or more specifically, in accordance with the resultant value of the fitness. In addition, to prove the efficiency, the following performance metrics are measured-Overall Accuracy, Classification Accuracy, AUC and ROC.
{"title":"Optimal progressive classification study using SMOTE-SVM for stages of lung disease","authors":"R. Sujitha, B. Paramasivan","doi":"10.1080/00051144.2023.2218167","DOIUrl":"https://doi.org/10.1080/00051144.2023.2218167","url":null,"abstract":"Data used in big data applications are typically kept in decentralized computing resources in the real world, which has an impact on the design of artificial intelligence algorithms. When there are significantly more observations from one class than from another, the dataset is said to be imbalanced. Therefore, in this work, the study elaborates the model as SMOTE-SVM which resolves imbalance issues in sampling the data and improves overall accuracy to 94%. The model deploys K-nearest neighbours to compute the difference between samples and to balance the samples, it computes the kernel space. Further, to optimize the classification, GWO optimizer merges with SMOTE-SVM to achieve enhanced performance. GWO (Grey Wolf Optimizer) induces greedy selection to perform optimization among classification. It is important to remember that grey wolves have a flexible social structure that might change the hierarchy. As the mobilization continues, the grey wolves are reconstructed with the distance between them and their prey, or more specifically, in accordance with the resultant value of the fitness. In addition, to prove the efficiency, the following performance metrics are measured-Overall Accuracy, Classification Accuracy, AUC and ROC.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":" ","pages":""},"PeriodicalIF":1.9,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42852778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Smart Grid is an intelligent power grid with a bidirectional flow of electricity and information, that applies intelligent techniques to operate the grid autonomously near the stability limit. An intelligent technique is developed to identify and predict the abnormalities due to changes in customer behaviour and the unexpected disruption in the grid. A cost-sensitive stacked ensemble classifier (CS-SEC) is proposed for predicting the operations in smart grid that combines four cost-sensitive base classifiers, namely Extreme gradient boosting, Naive Bayes, Nu-support vector machine and Random forest at level-1 and the support vector machine as the meta classifier in level-2. The meta classifier uses the probability of prediction of the first-level classifiers with stratified 5-fold cross-validation to predict the decentralized smart grid stability. The proposed stacked ensemble classifier achieved an accuracy of 98.6% with specificity, recall and precision of 98.34%, 99.0% and 99.06%, respectively. Extensive experimental evaluation and results show that the proposed CS-SEC provides an accurate prediction of grid stability compared with other state-of-the-art models. The results reveal the robustness and competency of the proposed CS-SECs with optimized parameters.
{"title":"Assessment and classification of grid stability with cost-sensitive stacked ensemble classifier","authors":"Karthikeyan Ramasamy, Arivoli Sundaramurthy, Durgadevi Velusamy","doi":"10.1080/00051144.2023.2218164","DOIUrl":"https://doi.org/10.1080/00051144.2023.2218164","url":null,"abstract":"Smart Grid is an intelligent power grid with a bidirectional flow of electricity and information, that applies intelligent techniques to operate the grid autonomously near the stability limit. An intelligent technique is developed to identify and predict the abnormalities due to changes in customer behaviour and the unexpected disruption in the grid. A cost-sensitive stacked ensemble classifier (CS-SEC) is proposed for predicting the operations in smart grid that combines four cost-sensitive base classifiers, namely Extreme gradient boosting, Naive Bayes, Nu-support vector machine and Random forest at level-1 and the support vector machine as the meta classifier in level-2. The meta classifier uses the probability of prediction of the first-level classifiers with stratified 5-fold cross-validation to predict the decentralized smart grid stability. The proposed stacked ensemble classifier achieved an accuracy of 98.6% with specificity, recall and precision of 98.34%, 99.0% and 99.06%, respectively. Extensive experimental evaluation and results show that the proposed CS-SEC provides an accurate prediction of grid stability compared with other state-of-the-art models. The results reveal the robustness and competency of the proposed CS-SECs with optimized parameters.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135557660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：