Pub Date : 2023-03-08DOI: 10.1109/ICEPECC57281.2023.10209523
S. Javaid, Yuto Lim, Yasuo Tan
Renewable energy sources (RESs) are now increasing as an essential portion of the power generation system. The main advantage of these RESs is environmental friendliness. However, the instability of power generation by weather conditions can highlight power quality and stability issues when connected to the main power grid. To accommodate the effects of power fluctuations, the energy storage system is an important addition to any power system with renewable power generators and dynamic power loads. Energy storage systems can help in supplying/absorbing power in a situation of excess/shortage of power. The seasonal patterns of power demand have reduced the stability of the power grid even leading to power blackouts. As a result, the optimal size of the storage system is required for efficient storage utilization. This paper proposes an optimization problem that identifies the optimal storage capacity for each season while preserving the safety conditions of the power system. Finally, the feasible solution of the optimization problem is found using Linear Programming Solver in MATLAB.
{"title":"Seasonal Impact on the Storage Capacity Sizing in a Renewable Energy System Under the Condition of Safe Operation","authors":"S. Javaid, Yuto Lim, Yasuo Tan","doi":"10.1109/ICEPECC57281.2023.10209523","DOIUrl":"https://doi.org/10.1109/ICEPECC57281.2023.10209523","url":null,"abstract":"Renewable energy sources (RESs) are now increasing as an essential portion of the power generation system. The main advantage of these RESs is environmental friendliness. However, the instability of power generation by weather conditions can highlight power quality and stability issues when connected to the main power grid. To accommodate the effects of power fluctuations, the energy storage system is an important addition to any power system with renewable power generators and dynamic power loads. Energy storage systems can help in supplying/absorbing power in a situation of excess/shortage of power. The seasonal patterns of power demand have reduced the stability of the power grid even leading to power blackouts. As a result, the optimal size of the storage system is required for efficient storage utilization. This paper proposes an optimization problem that identifies the optimal storage capacity for each season while preserving the safety conditions of the power system. Finally, the feasible solution of the optimization problem is found using Linear Programming Solver in MATLAB.","PeriodicalId":102289,"journal":{"name":"2023 International Conference on Energy, Power, Environment, Control, and Computing (ICEPECC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116139965","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}
Variable renewable energy-based distributed generations (VRE-DG) have extensively penetrated into the conventional distribution network. A virtual power plant (VPP) can group the diversified VRE-DG into one unit. The VPP operator (VPO) can control the VRE-DG operation and coordinate with the distribution system operator (DSO) for electricity trade and economic dispatch. Thus, converting consumers into prosumers. The VPP commissioning can complex or degrade the operation of the protection system. In this paper, a detailed analysis of potential susceptibility degradation of primary-backup overcurrent relay (OCR) coordination owing to VPP is provided. Protection degradation index (PDI) is introduced and a novel strategy to emend the parameters of affected OCR according to PDI is proposed to rehabilitate the coordination among primary-backup OCR. The studied VPP includes wind turbine generator (WTG), Photovoltaic (PV), and communication station-based storage batteries (CSESB). The case studies are conducted on the Tianjin distribution network (TDN) China, modified with the incorporation of VPP to show the impact of VPP on protection coordination and proficiency of the proposed strategy.
{"title":"Vulnerability Assessment for Primary-Backup Overcurrent Relay Coordination Deprivation Due to Virtual Power Plant","authors":"M. Rizwan, Ciwei Gao, Xingyu Yan, Gujing Lin, Yuan Gu, Minghe Wu","doi":"10.1109/ICEPECC57281.2023.10209438","DOIUrl":"https://doi.org/10.1109/ICEPECC57281.2023.10209438","url":null,"abstract":"Variable renewable energy-based distributed generations (VRE-DG) have extensively penetrated into the conventional distribution network. A virtual power plant (VPP) can group the diversified VRE-DG into one unit. The VPP operator (VPO) can control the VRE-DG operation and coordinate with the distribution system operator (DSO) for electricity trade and economic dispatch. Thus, converting consumers into prosumers. The VPP commissioning can complex or degrade the operation of the protection system. In this paper, a detailed analysis of potential susceptibility degradation of primary-backup overcurrent relay (OCR) coordination owing to VPP is provided. Protection degradation index (PDI) is introduced and a novel strategy to emend the parameters of affected OCR according to PDI is proposed to rehabilitate the coordination among primary-backup OCR. The studied VPP includes wind turbine generator (WTG), Photovoltaic (PV), and communication station-based storage batteries (CSESB). The case studies are conducted on the Tianjin distribution network (TDN) China, modified with the incorporation of VPP to show the impact of VPP on protection coordination and proficiency of the proposed strategy.","PeriodicalId":102289,"journal":{"name":"2023 International Conference on Energy, Power, Environment, Control, and Computing (ICEPECC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129696229","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 : 2023-03-08DOI: 10.1109/ICEPECC57281.2023.10209465
M. Rizwan, Ciwei Gao, Muhammad Wasif, M. Waseem, M. Usama, Asad Muneer
Electrical power system (EPS) mainly comprises of three major parts i.e. power generation, transmission and distribution (PGTD). To enhance the practical and research capabilities of engineering students, laboratory education of PGTD is a crucial requirement of electrical engineering program. In this paper, the basic phenomenons related to power generation (PG) i.e. generator behavior with resistive, inductive and capacitive loads, effect of variable frequency drive (VFD), governor and voltage regulation (VR) operation, open and short circuit test of generator, $X_{d}$ and $X_{q}$ characteristics, prime mover behavior and synchronization of generator with main grid are demonstrated and investigation from laboratory point of view. The power generation trainer (PGT) model No. EM-PRT-EG $3 varphi$ is used for experiment purpose. Further, some shortcomings in the power generation trainer are highlighted. Finally, Some needful suggestions are drawn to expedite the functionality of PGT for enhancement of hand-on experience in the laboratory.
{"title":"Evaluation and Characterization of Power Generation Trainer EM-PRT-EG3ϕ for Laboratory Education","authors":"M. Rizwan, Ciwei Gao, Muhammad Wasif, M. Waseem, M. Usama, Asad Muneer","doi":"10.1109/ICEPECC57281.2023.10209465","DOIUrl":"https://doi.org/10.1109/ICEPECC57281.2023.10209465","url":null,"abstract":"Electrical power system (EPS) mainly comprises of three major parts i.e. power generation, transmission and distribution (PGTD). To enhance the practical and research capabilities of engineering students, laboratory education of PGTD is a crucial requirement of electrical engineering program. In this paper, the basic phenomenons related to power generation (PG) i.e. generator behavior with resistive, inductive and capacitive loads, effect of variable frequency drive (VFD), governor and voltage regulation (VR) operation, open and short circuit test of generator, $X_{d}$ and $X_{q}$ characteristics, prime mover behavior and synchronization of generator with main grid are demonstrated and investigation from laboratory point of view. The power generation trainer (PGT) model No. EM-PRT-EG $3 varphi$ is used for experiment purpose. Further, some shortcomings in the power generation trainer are highlighted. Finally, Some needful suggestions are drawn to expedite the functionality of PGT for enhancement of hand-on experience in the laboratory.","PeriodicalId":102289,"journal":{"name":"2023 International Conference on Energy, Power, Environment, Control, and Computing (ICEPECC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129358364","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 : 2023-03-08DOI: 10.1109/ICEPECC57281.2023.10209458
Mohd Shahrimie Mohd Asaari, Syahanis Shamsudin, Lin Jian Wen
Deep learning has seen significant growth in its use in agriculture over the past decade due to the environmental challenges faced by this sector. While there have been many deep learning-based approaches proposed in the literature, there are only a few that focus on the detection of plant stress symptoms. This research applied deep learning object detection methods to detect plant stress in eggplant crops during the juvenile vegetative phase. The plants were divided into three classes based on their physical condition: healthy, early stress, and severe stress. Water status, specifically drought stress, was identified as a key factor in plant stress as it can alter normal plant equilibrium and molecular changes, negatively impacting growth and productivity. Three deep learning object detection algorithms, You Only Look Once version-3 (YOLOv3), You Only Look Once version-4 (YOLOv4), and Single Shot Detector (SSD), were explored as potential methods for building a plant stress detection model. The results of the quantitative experiments on eggplant plant images showed that YOLOv3 achieved a mean average precision value of 52%, YOLOv4 achieved 83%, and SSD achieved 56%.
由于农业面临的环境挑战，在过去十年中，深度学习在农业中的应用显著增长。虽然文献中提出了许多基于深度学习的方法，但只有少数方法专注于植物胁迫症状的检测。本研究应用深度学习目标检测方法对茄子作物幼期营养期的植物胁迫进行检测。这些植物根据它们的身体状况被分为三类:健康、早期胁迫和严重胁迫。水分状况，特别是干旱胁迫，被认为是植物胁迫的关键因素，因为它可以改变植物的正常平衡和分子变化，对生长和生产力产生负面影响。探讨了You Only Look Once version-3 (YOLOv3)、You Only Look Once version-4 (YOLOv4)和Single Shot Detector (SSD)三种深度学习目标检测算法作为构建植物应力检测模型的潜在方法。茄子植物影像定量实验结果表明，YOLOv3平均精度为52%，YOLOv4平均精度为83%，SSD平均精度为56%。
{"title":"Detection of Plant Stress Condition with Deep Learning Based Detection Models","authors":"Mohd Shahrimie Mohd Asaari, Syahanis Shamsudin, Lin Jian Wen","doi":"10.1109/ICEPECC57281.2023.10209458","DOIUrl":"https://doi.org/10.1109/ICEPECC57281.2023.10209458","url":null,"abstract":"Deep learning has seen significant growth in its use in agriculture over the past decade due to the environmental challenges faced by this sector. While there have been many deep learning-based approaches proposed in the literature, there are only a few that focus on the detection of plant stress symptoms. This research applied deep learning object detection methods to detect plant stress in eggplant crops during the juvenile vegetative phase. The plants were divided into three classes based on their physical condition: healthy, early stress, and severe stress. Water status, specifically drought stress, was identified as a key factor in plant stress as it can alter normal plant equilibrium and molecular changes, negatively impacting growth and productivity. Three deep learning object detection algorithms, You Only Look Once version-3 (YOLOv3), You Only Look Once version-4 (YOLOv4), and Single Shot Detector (SSD), were explored as potential methods for building a plant stress detection model. The results of the quantitative experiments on eggplant plant images showed that YOLOv3 achieved a mean average precision value of 52%, YOLOv4 achieved 83%, and SSD achieved 56%.","PeriodicalId":102289,"journal":{"name":"2023 International Conference on Energy, Power, Environment, Control, and Computing (ICEPECC)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131044727","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 : 2023-03-08DOI: 10.1109/ICEPECC57281.2023.10209429
Nouman Aziz, Wasif Muhammad, Irfan Qaiser, Ali Asghar, M. J. Irshad, Y. Bilal
Convolutional Neural Network (CNN) has performed better for recent application of object recognition and object detection especially for image data but problem with CNN is that they require labels as learning signals. It is quite impossible to label all types of anomalies in a particular environment. Unsupervised methods used for video anomaly detection has drawback that they require too much data so that accurate results should be produced using unlabeled data which in turn increases computational cost. For this research a Few shot anomaly detection method is introduced using spatio-temporal autoencoder model for detecting suspicious activities in videos is proposed which doesn’t require any labels during training and also has very less computational cost then traditional unsupervised deep learning methods. Spatiotemporal autoencoder model has two components. Spatial autoencoder is used for spatial feature representation while temporal autoencoder extracts features from temporal dimensions. Few shot anomaly detection technique comprises the fact that it takes few images in each batch of training loop and trains the model on those images. At last averages the learning of all images and compute the loss for reconstruction by taking average loss of all batches. Experimental results on Avenue Dataset gives better results and achieves much lesser computational cost then other unsupervised anomaly detection methods.
{"title":"Few Shot Spatio-Temporal Anomaly Detection Model For Suspicious Activities","authors":"Nouman Aziz, Wasif Muhammad, Irfan Qaiser, Ali Asghar, M. J. Irshad, Y. Bilal","doi":"10.1109/ICEPECC57281.2023.10209429","DOIUrl":"https://doi.org/10.1109/ICEPECC57281.2023.10209429","url":null,"abstract":"Convolutional Neural Network (CNN) has performed better for recent application of object recognition and object detection especially for image data but problem with CNN is that they require labels as learning signals. It is quite impossible to label all types of anomalies in a particular environment. Unsupervised methods used for video anomaly detection has drawback that they require too much data so that accurate results should be produced using unlabeled data which in turn increases computational cost. For this research a Few shot anomaly detection method is introduced using spatio-temporal autoencoder model for detecting suspicious activities in videos is proposed which doesn’t require any labels during training and also has very less computational cost then traditional unsupervised deep learning methods. Spatiotemporal autoencoder model has two components. Spatial autoencoder is used for spatial feature representation while temporal autoencoder extracts features from temporal dimensions. Few shot anomaly detection technique comprises the fact that it takes few images in each batch of training loop and trains the model on those images. At last averages the learning of all images and compute the loss for reconstruction by taking average loss of all batches. Experimental results on Avenue Dataset gives better results and achieves much lesser computational cost then other unsupervised anomaly detection methods.","PeriodicalId":102289,"journal":{"name":"2023 International Conference on Energy, Power, Environment, Control, and Computing (ICEPECC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133758428","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 : 2023-03-08DOI: 10.1109/ICEPECC57281.2023.10209533
Asif Durez, Muzaffar Ali, Sudhakar Kumarasamy
Due to an immense increase in population and technological developments, energy demand is growing at a rapid rate across the world. To overcome this issue, it is important to opt for a limitless, economical renewable energy source for energy demand. This paper presents a methodology for selecting the most suitable phase change material that can effectively reduce the PV panels temperature, thereby improving their overall efficiency and output. The climate conditions of Malaysia are under research in this paper. Monthly and Daily analysis is carried out for two Malaysian cities (Kuala Lumpur and Pahang). Phase Change Materials having a melting point of 21°C and 27°C named RT21 and RT27 respectively are used in combination to predict the best result. To determine the most suitable phase-changing material, a daily and monthly analysis was performed on two distinct climatic zones identified within the Koppen Climate Classification, namely Af and Cfb. Af climate is related to tropical humid climate while Cfbis focused on oceanic climate. The conclusions drawn from this research suggest that the using PCM RT21 results in the cooling of PV panel surface temperature, causing a consequent expansion in efficiency and electrical output of 2% and 6%, respectively. While with PCM RT27 these numbers are not that much significant. Using PCM with a melting point of 21°C, the maximum cell temperature can be lowered from 32°C to 25°C in Kuala Lumpur and 33°C to 26°C in Pahang duiing the hottest month of May. The results show that PCM-RT21 is appropriate for cooling PV systems for climate classification of (Cfb) and (Af) as compared to PCM-RT27.
{"title":"Investigation of Optimum Phase Change Material for PV Panels in Malaysian Climatic Conditions","authors":"Asif Durez, Muzaffar Ali, Sudhakar Kumarasamy","doi":"10.1109/ICEPECC57281.2023.10209533","DOIUrl":"https://doi.org/10.1109/ICEPECC57281.2023.10209533","url":null,"abstract":"Due to an immense increase in population and technological developments, energy demand is growing at a rapid rate across the world. To overcome this issue, it is important to opt for a limitless, economical renewable energy source for energy demand. This paper presents a methodology for selecting the most suitable phase change material that can effectively reduce the PV panels temperature, thereby improving their overall efficiency and output. The climate conditions of Malaysia are under research in this paper. Monthly and Daily analysis is carried out for two Malaysian cities (Kuala Lumpur and Pahang). Phase Change Materials having a melting point of 21°C and 27°C named RT21 and RT27 respectively are used in combination to predict the best result. To determine the most suitable phase-changing material, a daily and monthly analysis was performed on two distinct climatic zones identified within the Koppen Climate Classification, namely Af and Cfb. Af climate is related to tropical humid climate while Cfbis focused on oceanic climate. The conclusions drawn from this research suggest that the using PCM RT21 results in the cooling of PV panel surface temperature, causing a consequent expansion in efficiency and electrical output of 2% and 6%, respectively. While with PCM RT27 these numbers are not that much significant. Using PCM with a melting point of 21°C, the maximum cell temperature can be lowered from 32°C to 25°C in Kuala Lumpur and 33°C to 26°C in Pahang duiing the hottest month of May. The results show that PCM-RT21 is appropriate for cooling PV systems for climate classification of (Cfb) and (Af) as compared to PCM-RT27.","PeriodicalId":102289,"journal":{"name":"2023 International Conference on Energy, Power, Environment, Control, and Computing (ICEPECC)","volume":"81 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116345551","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 : 2023-03-08DOI: 10.1109/ICEPECC57281.2023.10209444
Simon Peter Khabusi, Prishika Pheroijam, Satchidanand Kshetrimayum
Cassava is a food crop that is rich in carbohydrates. However, the crop is vulnerable to many diseases. Research has revealed that image recognition using machine learning and deep learning techniques can be applied in automatic identification of cassava leaf diseases. Therefore this study focuses on using strongly discriminative features of the leaf regions affected by disease and weakening regions of low interest to improve the classification accuracy. A convolutional block attention module (CBAM) is a common attention mechanism integrated in feed-forward convolutional neural networks. In this study, CBAM is added to the pretrained ResNet50 and VGG19 models to recognize the cassava leaf regions affected by disease. This is done by sequentially inferring attention maps along two dimensions, channel and spatial for every intermediate feature map. The attention maps are then multiplied to the input feature map for adaptive feature refinement. The performance of baseline models such as EfficientNet, ResNet50, Inceptionv3, and Xception is compared with the attention-based models trained, validated and tested on a public dataset from Makerere University AI laboratory. ResNet50+CBAM achieve the highest performance with accuracy of 97%, precision of 96%, recall of 94% and F-measure of 95%. Conclusively, attention-based models perform better than the baseline models with a performance improvement of over 1%.
{"title":"Attention-Based Approach for Cassava Leaf Disease Classification in Agriculture","authors":"Simon Peter Khabusi, Prishika Pheroijam, Satchidanand Kshetrimayum","doi":"10.1109/ICEPECC57281.2023.10209444","DOIUrl":"https://doi.org/10.1109/ICEPECC57281.2023.10209444","url":null,"abstract":"Cassava is a food crop that is rich in carbohydrates. However, the crop is vulnerable to many diseases. Research has revealed that image recognition using machine learning and deep learning techniques can be applied in automatic identification of cassava leaf diseases. Therefore this study focuses on using strongly discriminative features of the leaf regions affected by disease and weakening regions of low interest to improve the classification accuracy. A convolutional block attention module (CBAM) is a common attention mechanism integrated in feed-forward convolutional neural networks. In this study, CBAM is added to the pretrained ResNet50 and VGG19 models to recognize the cassava leaf regions affected by disease. This is done by sequentially inferring attention maps along two dimensions, channel and spatial for every intermediate feature map. The attention maps are then multiplied to the input feature map for adaptive feature refinement. The performance of baseline models such as EfficientNet, ResNet50, Inceptionv3, and Xception is compared with the attention-based models trained, validated and tested on a public dataset from Makerere University AI laboratory. ResNet50+CBAM achieve the highest performance with accuracy of 97%, precision of 96%, recall of 94% and F-measure of 95%. Conclusively, attention-based models perform better than the baseline models with a performance improvement of over 1%.","PeriodicalId":102289,"journal":{"name":"2023 International Conference on Energy, Power, Environment, Control, and Computing (ICEPECC)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124099309","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 : 2023-03-08DOI: 10.1109/ICEPECC57281.2023.10209525
M. A. Aslam, Shahzadi Mahnoor, Muhammad Asif Munir, Saman Cheema, Khawaja Humble Hassan, Abdullah Sajid
Now fluorescent scan images are extensively used for the detection of antigens. The identification and treatment of the tumor is done with the help of these images The speed of detection is the major part for such systems. Although, bulk of research has already been done, segmentation of images is the area still need improvement. Characterization of the images is difficult task due to the diverse nature of the input images. This paper presents a novel method for the segmentation. The segmentation is done using superpixels. In the proposed algorithm the super pixels are studied on the basis of their average value. This value is computed with the help of Principal component analysis and then PCA system is utilized to compute a feature vector corresponding to the each superpixel. The stated method was implemented in MATLAB 2017. Our system integrates a series of algorithms. These algorithms are used for quantitative image analysis.
{"title":"Carcinoembryonic Antigens Segmentation and Quantitative Analysis from Fluorescent Images using Principal Component Analysis and Adaptive K-means Clustering","authors":"M. A. Aslam, Shahzadi Mahnoor, Muhammad Asif Munir, Saman Cheema, Khawaja Humble Hassan, Abdullah Sajid","doi":"10.1109/ICEPECC57281.2023.10209525","DOIUrl":"https://doi.org/10.1109/ICEPECC57281.2023.10209525","url":null,"abstract":"Now fluorescent scan images are extensively used for the detection of antigens. The identification and treatment of the tumor is done with the help of these images The speed of detection is the major part for such systems. Although, bulk of research has already been done, segmentation of images is the area still need improvement. Characterization of the images is difficult task due to the diverse nature of the input images. This paper presents a novel method for the segmentation. The segmentation is done using superpixels. In the proposed algorithm the super pixels are studied on the basis of their average value. This value is computed with the help of Principal component analysis and then PCA system is utilized to compute a feature vector corresponding to the each superpixel. The stated method was implemented in MATLAB 2017. Our system integrates a series of algorithms. These algorithms are used for quantitative image analysis.","PeriodicalId":102289,"journal":{"name":"2023 International Conference on Energy, Power, Environment, Control, and Computing (ICEPECC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124868503","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 : 2023-03-08DOI: 10.1109/ICEPECC57281.2023.10209499
M. Rasheduzzaman, A. Doulah, Ramit Kumar Sadhukhan, M. M. Hossain
The majority of Dhaka’s transportation system consists of internal combustion engine vehicles (ICEVs) that use gasoline and compressed natural gas (CNG). Incorporation of battery electric vehicles (BEVs) can help to lessen air pollution caused by the automobiles’ exhaust systems. The impact of ICEVs on Dhaka’s air pollution, particularly based on the average speed and types of fuels used, have not yet been thoroughly studied. In this work, the emissions produced by the fleet of ICEVs already on the road and the emission decrease that would occur if electric vehicles were gradually brought to the city of Dhaka are predicted. It has been determined that the adoption of EVs will greatly lower emissions of greenhouse gases (GHGs) and particulate matter (PM). According to our analysis, the CO2, NOx, and PM2.5 emissions can be lowered by 4.76%, 7.93%, and 8.96% respectively by 2050 using the existing primary energy sources for generating electricity, however the SO2 emissions will rise by 27S.34%. In the case of a primary energy mix with reduced emission factors, it has been observed that S.95%, 9.5S%, and 9.12% reductions in CO2, NOx, and PM2.5 emissions, respectively, can be derived from the same number of EV integration by 2050, whereas SO2 emission will increase by 57.47%.
{"title":"Assessing the Environmental Consequences of ICEVs and BEVs in Dhaka City via Vehicle Fleet Modeling and Support Vector Regression","authors":"M. Rasheduzzaman, A. Doulah, Ramit Kumar Sadhukhan, M. M. Hossain","doi":"10.1109/ICEPECC57281.2023.10209499","DOIUrl":"https://doi.org/10.1109/ICEPECC57281.2023.10209499","url":null,"abstract":"The majority of Dhaka’s transportation system consists of internal combustion engine vehicles (ICEVs) that use gasoline and compressed natural gas (CNG). Incorporation of battery electric vehicles (BEVs) can help to lessen air pollution caused by the automobiles’ exhaust systems. The impact of ICEVs on Dhaka’s air pollution, particularly based on the average speed and types of fuels used, have not yet been thoroughly studied. In this work, the emissions produced by the fleet of ICEVs already on the road and the emission decrease that would occur if electric vehicles were gradually brought to the city of Dhaka are predicted. It has been determined that the adoption of EVs will greatly lower emissions of greenhouse gases (GHGs) and particulate matter (PM). According to our analysis, the CO2, NOx, and PM2.5 emissions can be lowered by 4.76%, 7.93%, and 8.96% respectively by 2050 using the existing primary energy sources for generating electricity, however the SO2 emissions will rise by 27S.34%. In the case of a primary energy mix with reduced emission factors, it has been observed that S.95%, 9.5S%, and 9.12% reductions in CO2, NOx, and PM2.5 emissions, respectively, can be derived from the same number of EV integration by 2050, whereas SO2 emission will increase by 57.47%.","PeriodicalId":102289,"journal":{"name":"2023 International Conference on Energy, Power, Environment, Control, and Computing (ICEPECC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129057551","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：