Pub Date : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815491
L. Tan, M. Jadin, K. Ghazali, A. Shah, M. K. Osman
Possible faults in the photovoltaic modules must be detected early in order to preserve their long-term reliability while maximizing power output. Aerial thermal image inspection is frequently used to detect and locate photovoltaic module hotspots. However, noises can make it difficult to detect a hotspot from this image, causing the hotspot to be incorrectly located due to thermal reflection from the environment. Examining both visual and thermal images of photovoltaic modules appears to be one of the solutions. The multispectral image matching of photovoltaic modules is presented in this paper. The absolute structure map (SMi) and the directional structure map (DSMi) are proposed. The local region of each interest point is then described using a histogram of the oriented gradient based on the SMi and DSMi. For the SMi, the Gabor wavelet filter is applied, whereas the average filter is applied to the DSMi for the construction of the histogram bins. Finally, the normalized feature vectors are merged. Experiments were carried out to evaluate the performance of the proposed structure map feature descriptor. According to the findings, this approach could give precision and recall up to 0.82 and 0.97 respectively.
{"title":"Local Feature Descriptor for Multispectral Image Matching of a Large-Scale PV Array","authors":"L. Tan, M. Jadin, K. Ghazali, A. Shah, M. K. Osman","doi":"10.1109/i2cacis54679.2022.9815491","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815491","url":null,"abstract":"Possible faults in the photovoltaic modules must be detected early in order to preserve their long-term reliability while maximizing power output. Aerial thermal image inspection is frequently used to detect and locate photovoltaic module hotspots. However, noises can make it difficult to detect a hotspot from this image, causing the hotspot to be incorrectly located due to thermal reflection from the environment. Examining both visual and thermal images of photovoltaic modules appears to be one of the solutions. The multispectral image matching of photovoltaic modules is presented in this paper. The absolute structure map (SMi) and the directional structure map (DSMi) are proposed. The local region of each interest point is then described using a histogram of the oriented gradient based on the SMi and DSMi. For the SMi, the Gabor wavelet filter is applied, whereas the average filter is applied to the DSMi for the construction of the histogram bins. Finally, the normalized feature vectors are merged. Experiments were carried out to evaluate the performance of the proposed structure map feature descriptor. According to the findings, this approach could give precision and recall up to 0.82 and 0.97 respectively.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129532441","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}
Pub Date : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815487
Md. Tanjil Sarker, A. H. Tan, Timothy Tzen Vun Yap
In this paper, perturbation signal design for multi-input multi-output (MIMO) systems is presented for the output error (OE) and the autoregressive with exogenous inputs (ARX) model structures. The problem is handled via the investigation of multi-input single-output (MISO) systems, since a MIMO system can be formed as a combination of MISO systems. Comparison is performed between the flat, MOOSE2 and optexcit signal designs under three different signal-to-noise ratios (SNRs) in the open loop setting. The effectiveness of signal designs obtained for the single-input case and applied on MISO systems is analysed. The mean determinant of the covariance matrix of parameter estimates is utilised as a measure of estimation accuracy. Equations for MISO system are constructed and the amplitude spectrum design of perturbation signals is investigated based on the determinant of the covariance matrix for the ARX model structure.
{"title":"Amplitude Spectrum Design for Multivariable System Identification in Open Loop","authors":"Md. Tanjil Sarker, A. H. Tan, Timothy Tzen Vun Yap","doi":"10.1109/i2cacis54679.2022.9815487","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815487","url":null,"abstract":"In this paper, perturbation signal design for multi-input multi-output (MIMO) systems is presented for the output error (OE) and the autoregressive with exogenous inputs (ARX) model structures. The problem is handled via the investigation of multi-input single-output (MISO) systems, since a MIMO system can be formed as a combination of MISO systems. Comparison is performed between the flat, MOOSE2 and optexcit signal designs under three different signal-to-noise ratios (SNRs) in the open loop setting. The effectiveness of signal designs obtained for the single-input case and applied on MISO systems is analysed. The mean determinant of the covariance matrix of parameter estimates is utilised as a measure of estimation accuracy. Equations for MISO system are constructed and the amplitude spectrum design of perturbation signals is investigated based on the determinant of the covariance matrix for the ARX model structure.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114520194","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}
Pub Date : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815471
Brian R. Tan, M. Lee
The energy demand in Malaysia has shown a drastic increase over the years. The primary energy supply is natural gas, coal, and coke energy extraction. However, these energy extractions are considered unclean and not sustainable. Therefore, renewable energy could be the immediate solution. Furthermore, previous studies in ocean engineering indicated that Malaysia’s sea condition is favorable to be utilized. Overtopping wave energy converters are primarily used for high mechanical to electrical conversion efficiencies. The current study optimizes the turbine for overtopping wave energy conversion devices through computational fluid dynamics simulation software, ANSYS. Findings indicate that the larger the turbine blade diameter, the higher the torque acting on the turbine. This is because the water pressure impact on the linear blade surface is more significant when the diameter of the blade is prominent, resulting in higher torque acting on the turbine. Unlike the diameter of the turbine blade, the number of the turbine blade is not directly proportional to the torque acting on the turbine. Turbine models with four blades illustrate a higher torque value than three and five blades turbines. The highest turbine performance efficiency for straight flow casing is 62.87% with 3091.30W, while spiral casing turbine exhibited outstanding performance efficiency of 94.44% with 4643.82W under the same power input condition. This study calls for future study in the system design optimization of overtopping wave energy conversion technology, such as ocean wave conditions, power take-off systems design, and location selection.
{"title":"Optimization of Turbine for Overtopping Wave Energy Conversion Device through Computational Fluid Dynamics Simulation","authors":"Brian R. Tan, M. Lee","doi":"10.1109/i2cacis54679.2022.9815471","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815471","url":null,"abstract":"The energy demand in Malaysia has shown a drastic increase over the years. The primary energy supply is natural gas, coal, and coke energy extraction. However, these energy extractions are considered unclean and not sustainable. Therefore, renewable energy could be the immediate solution. Furthermore, previous studies in ocean engineering indicated that Malaysia’s sea condition is favorable to be utilized. Overtopping wave energy converters are primarily used for high mechanical to electrical conversion efficiencies. The current study optimizes the turbine for overtopping wave energy conversion devices through computational fluid dynamics simulation software, ANSYS. Findings indicate that the larger the turbine blade diameter, the higher the torque acting on the turbine. This is because the water pressure impact on the linear blade surface is more significant when the diameter of the blade is prominent, resulting in higher torque acting on the turbine. Unlike the diameter of the turbine blade, the number of the turbine blade is not directly proportional to the torque acting on the turbine. Turbine models with four blades illustrate a higher torque value than three and five blades turbines. The highest turbine performance efficiency for straight flow casing is 62.87% with 3091.30W, while spiral casing turbine exhibited outstanding performance efficiency of 94.44% with 4643.82W under the same power input condition. This study calls for future study in the system design optimization of overtopping wave energy conversion technology, such as ocean wave conditions, power take-off systems design, and location selection.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115622158","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}
Pub Date : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815476
M. Nageh, M. P. Abdullah, Belal Yousef
The produced electrical energy from a solar photovoltaic (PV) system can be increased via using manual or auto solar tracking strategy. Generally, compared with the fixed solar system, the auto dual (two) axis tracker will give the highest energy output improvement, followed by the auto single (one) axis tracker then the manual adjusted tilt angle (monthly and seasonally) solar system’s respectively. However, the magnitude of the improvement varies from one location to another location due to the latitude angle difference between them. The improvement can be high at one location, but its low at another location. Thus, an exhaustive simulation analysis for each strategy is needed to be conducted before their energy output improvement can be determined for a specific location. Not only it will be time consuming, but also it will be impossible for a person with no PV simulation tool skills to perform this task. This research presents a simpler method for estimating the generated energy performance (the energy gain, %) of the large scale solar (LSS) system for various tracking strategies. The mathematical equations are developed from the exhaustive simulation results. The proposed method is tested on (12 selected cites) that included in our research recently as well as it also tested on another (two new cities) with the main error (between 0.0% and 0.56%) is observed.
{"title":"Estimation of Energy Gain Improvement of Various Tracking Techniques for LSS Photovoltaic System","authors":"M. Nageh, M. P. Abdullah, Belal Yousef","doi":"10.1109/i2cacis54679.2022.9815476","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815476","url":null,"abstract":"The produced electrical energy from a solar photovoltaic (PV) system can be increased via using manual or auto solar tracking strategy. Generally, compared with the fixed solar system, the auto dual (two) axis tracker will give the highest energy output improvement, followed by the auto single (one) axis tracker then the manual adjusted tilt angle (monthly and seasonally) solar system’s respectively. However, the magnitude of the improvement varies from one location to another location due to the latitude angle difference between them. The improvement can be high at one location, but its low at another location. Thus, an exhaustive simulation analysis for each strategy is needed to be conducted before their energy output improvement can be determined for a specific location. Not only it will be time consuming, but also it will be impossible for a person with no PV simulation tool skills to perform this task. This research presents a simpler method for estimating the generated energy performance (the energy gain, %) of the large scale solar (LSS) system for various tracking strategies. The mathematical equations are developed from the exhaustive simulation results. The proposed method is tested on (12 selected cites) that included in our research recently as well as it also tested on another (two new cities) with the main error (between 0.0% and 0.56%) is observed.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123453269","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}
Pub Date : 2022-06-25DOI: 10.1109/I2CACIS54679.2022.9815492
Eltimar T. Castro, Nephi P. Romano
Senior citizens are among the most vulnerable members of society. Each country is concerned about how to improve their level of life and secure their social support and services. The Philippines faced with the problem of improving social services for its expanding population of elderly. Several agencies are tasked with the responsibility of providing improved social services that promote the welfare of the city's senior citizens. To achieve highest degree of satisfaction to all elderly, rigorous steps must be taken to identify process gaps and build a system that aid in the process's acceleration. Data mining technique help to generate insights and visualization, thus facilitating government organizations that oversee health and social services. The results can aid for policy and decision making of the National and Local Government Agency. The results showed that there are increasing number of senior citizens profiled with an estimated average of 3,338 per year started last 2017. The target numbers of elderlies to be profiled is around 25,000 in 2022, these figures are aligned to Philippines Statistic Authority (PSA). The findings revealed that 25 percent of profiled elderlies are not registered in PhilHealth, and 85 percent of them are not pensioner thus, the results are implying that there are elderlies entitled to receive benefits as mandated by Law. Overall, the assessment showed that there are areas in social services that needs immediate actions to deliver quality social services for senior citizens in future. Furthermore, researcher recommends more dataset to be analyze and system integration for real-time monitoring and immediate actions.
{"title":"Mining on Senior Citizens Data: Empirical Evidence in the Philippines Locale \"Basis for Social Services Improvement and Decision Making\"","authors":"Eltimar T. Castro, Nephi P. Romano","doi":"10.1109/I2CACIS54679.2022.9815492","DOIUrl":"https://doi.org/10.1109/I2CACIS54679.2022.9815492","url":null,"abstract":"Senior citizens are among the most vulnerable members of society. Each country is concerned about how to improve their level of life and secure their social support and services. The Philippines faced with the problem of improving social services for its expanding population of elderly. Several agencies are tasked with the responsibility of providing improved social services that promote the welfare of the city's senior citizens. To achieve highest degree of satisfaction to all elderly, rigorous steps must be taken to identify process gaps and build a system that aid in the process's acceleration. Data mining technique help to generate insights and visualization, thus facilitating government organizations that oversee health and social services. The results can aid for policy and decision making of the National and Local Government Agency. The results showed that there are increasing number of senior citizens profiled with an estimated average of 3,338 per year started last 2017. The target numbers of elderlies to be profiled is around 25,000 in 2022, these figures are aligned to Philippines Statistic Authority (PSA). The findings revealed that 25 percent of profiled elderlies are not registered in PhilHealth, and 85 percent of them are not pensioner thus, the results are implying that there are elderlies entitled to receive benefits as mandated by Law. Overall, the assessment showed that there are areas in social services that needs immediate actions to deliver quality social services for senior citizens in future. Furthermore, researcher recommends more dataset to be analyze and system integration for real-time monitoring and immediate actions.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128588645","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}
Pub Date : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815269
W. I. Ibrahim, M. R. Mohamed, R. Ismail
This paper proposes a hybrid maximum power point tracking (MPPT) algorithm for the stand-alone hydrokinetic technology in river application. The fixed stepsize Hill Climbing Search (HCS) algorithm is widely used due to its simplicity. However, the operating point oscillates around the maximum power point (MPP) during dynamic steady-state resulting waste some amount of energy. The proposed algorithm is the combination of the Fuzzy Logic Controller (FLC) and HCS algorithm to provide the variable step-size to eradicate the limitation of conventional HCS algorithm. The proposed algorithm has been compared with the Small Step HCS (SS-HCS) to investigate the performance of the algorithm. The simulation results illustrated the proposed algorithm (Fuzzy-HCS) improved the output power with 89.91 % efficiency and minimizes oscillation during dynamic steady-state.
{"title":"Hybrid HCS-Fuzzy MPPT Algorithm for Hydrokinetic Energy Harnessing","authors":"W. I. Ibrahim, M. R. Mohamed, R. Ismail","doi":"10.1109/i2cacis54679.2022.9815269","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815269","url":null,"abstract":"This paper proposes a hybrid maximum power point tracking (MPPT) algorithm for the stand-alone hydrokinetic technology in river application. The fixed stepsize Hill Climbing Search (HCS) algorithm is widely used due to its simplicity. However, the operating point oscillates around the maximum power point (MPP) during dynamic steady-state resulting waste some amount of energy. The proposed algorithm is the combination of the Fuzzy Logic Controller (FLC) and HCS algorithm to provide the variable step-size to eradicate the limitation of conventional HCS algorithm. The proposed algorithm has been compared with the Small Step HCS (SS-HCS) to investigate the performance of the algorithm. The simulation results illustrated the proposed algorithm (Fuzzy-HCS) improved the output power with 89.91 % efficiency and minimizes oscillation during dynamic steady-state.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127424371","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}
Pub Date : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815472
Ruby Jon M. Kagalingan, Bernard Piolo M. Tolentino, Jessie R. Balbin
Indoor gardening is concerned with the difficult task of maintaining plant life within the confines of the premises. Indoor gardening lacks the abundance of sunlight which causes imbalance in plant irrigation. Because plants require sunlight to thrive, it appears that keeping them outside is the best option. The vertical garden monitoring system aims to alleviate the difficulties by incorporating an ESP32 module board MCU, controlled lights, automated water irrigation, productive fertilizers, and data monitoring via capacitive soil moisture and DHT11 sensors, displayed within an HTML webpage. The research prototype aids the inefficiencies of indoor gardening in terms of plant growth by ANOVA test findings of sample p-value 0.121373 for Plant Height, and sample p-value 0.945192 for length of leaves. An indication that the comparison for traditional and indoor vertical garden systems had no significant difference.
{"title":"Aiding Plant Growth Difference for Indoor Vertical Garden against Traditional Outdoor Vertical Garden Setup using DHT11 and Capacitive Soil Moisture Sensor","authors":"Ruby Jon M. Kagalingan, Bernard Piolo M. Tolentino, Jessie R. Balbin","doi":"10.1109/i2cacis54679.2022.9815472","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815472","url":null,"abstract":"Indoor gardening is concerned with the difficult task of maintaining plant life within the confines of the premises. Indoor gardening lacks the abundance of sunlight which causes imbalance in plant irrigation. Because plants require sunlight to thrive, it appears that keeping them outside is the best option. The vertical garden monitoring system aims to alleviate the difficulties by incorporating an ESP32 module board MCU, controlled lights, automated water irrigation, productive fertilizers, and data monitoring via capacitive soil moisture and DHT11 sensors, displayed within an HTML webpage. The research prototype aids the inefficiencies of indoor gardening in terms of plant growth by ANOVA test findings of sample p-value 0.121373 for Plant Height, and sample p-value 0.945192 for length of leaves. An indication that the comparison for traditional and indoor vertical garden systems had no significant difference.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122339658","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}
Pub Date : 2022-06-25DOI: 10.1109/I2CACIS54679.2022.9815489
Reem Emad Nafiaa, A. Z. Yonis
Wireless Power Transfer (WPT) is considered an important technology in recent years especially the magnetic resonance coupling technique (MRC), and also considered a great technology where have numerous advantage such as reliability, safety, and getting rid of cables that cause damage to the device, and flexibility. Due to the high development and complexity of the smart device industry, it is necessary to rely on a technology that facilitates the handling of modern smart applications. The paper clarified a simple model of technology and illustrated the factors that led to producing a splitting in frequency, in the result reaches that the coupling factor changing with different frequencies causes a splitting in frequency and this is called the FSP frequency splitting phenomenon. Some technique has been discussed to eliminate this problem.
{"title":"Analysis of Frequency Splitting Phenomenon in WPT for Intelligent Applications","authors":"Reem Emad Nafiaa, A. Z. Yonis","doi":"10.1109/I2CACIS54679.2022.9815489","DOIUrl":"https://doi.org/10.1109/I2CACIS54679.2022.9815489","url":null,"abstract":"Wireless Power Transfer (WPT) is considered an important technology in recent years especially the magnetic resonance coupling technique (MRC), and also considered a great technology where have numerous advantage such as reliability, safety, and getting rid of cables that cause damage to the device, and flexibility. Due to the high development and complexity of the smart device industry, it is necessary to rely on a technology that facilitates the handling of modern smart applications. The paper clarified a simple model of technology and illustrated the factors that led to producing a splitting in frequency, in the result reaches that the coupling factor changing with different frequencies causes a splitting in frequency and this is called the FSP frequency splitting phenomenon. Some technique has been discussed to eliminate this problem.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129248211","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}
Pub Date : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815272
S. Ajibade, Muhammad Ayaz, Dai-Long Ngo-Hoang, Almighty C. Tabuena, F. Rabbi, Getahun Fikadu Tilaye, Mbiatke Anthony Bassey
Evolutionary Algorithms (EAs) are powerful heuristic search approaches which relies on Darwinian evolution that capture global solutions to complex optimization problems which has powerful features of reliability and versatility. (EAs) such as Particle swarm optimization (PSO) is a global optimization method that is extremely effective. PSO's flaws include slow convergence, premature convergence, and getting stuck at local optima. In this paper, chaotic map and dynamic-weight Particle Swarm Optimization (CHDPSOA) are combined with PSO to enhance the search strategy through adjusting the inertia weight of PSO and changing the position update formula in the (CHDPSOA), resulting in efficient balancing for local and global PSO feature selection processes. The performance of CHDPSOA was compared to that of three metaheuristic techniques: Differential Evolution (DE) and the original PSO, using eight numerical functions. The validation of this technique is carried out on four different datasets. The results show that the CHDPSOA is a good feature selection technique that balances the exploration and exploitation search processes to produce good results. The proposed CHDPSOA method performed well in correctly categorizing features using the KNN Classifier for all four datasets.
{"title":"Analysis of Improved Evolutionary Algorithms Using Students’ Datasets","authors":"S. Ajibade, Muhammad Ayaz, Dai-Long Ngo-Hoang, Almighty C. Tabuena, F. Rabbi, Getahun Fikadu Tilaye, Mbiatke Anthony Bassey","doi":"10.1109/i2cacis54679.2022.9815272","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815272","url":null,"abstract":"Evolutionary Algorithms (EAs) are powerful heuristic search approaches which relies on Darwinian evolution that capture global solutions to complex optimization problems which has powerful features of reliability and versatility. (EAs) such as Particle swarm optimization (PSO) is a global optimization method that is extremely effective. PSO's flaws include slow convergence, premature convergence, and getting stuck at local optima. In this paper, chaotic map and dynamic-weight Particle Swarm Optimization (CHDPSOA) are combined with PSO to enhance the search strategy through adjusting the inertia weight of PSO and changing the position update formula in the (CHDPSOA), resulting in efficient balancing for local and global PSO feature selection processes. The performance of CHDPSOA was compared to that of three metaheuristic techniques: Differential Evolution (DE) and the original PSO, using eight numerical functions. The validation of this technique is carried out on four different datasets. The results show that the CHDPSOA is a good feature selection technique that balances the exploration and exploitation search processes to produce good results. The proposed CHDPSOA method performed well in correctly categorizing features using the KNN Classifier for all four datasets.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115160128","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}
Pub Date : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815459
{"title":"I2CACIS 2022 Cover Page","authors":"","doi":"10.1109/i2cacis54679.2022.9815459","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815459","url":null,"abstract":"","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121073410","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：