Pub Date : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202147
Sittichai Sukreep, P. Dajpratham, Chakarida Nukoolkit, S. Yamsaengsung, Thanapong Khajontantichaikun, P. Mongkolnam, S. Jaiyen, Vithida Chongsuphajaisiddhi
As the number of elderly living alone is increasing every year, some seemingly common daily activities can potentially raise the risk of serious injuries and fatal accidents for these elderly. While falls can occur anywhere, they most often occur at home, this is especially true among the elderly. Without timely notification to medical personnel and assistance, the resulting injuries could be life-threatening. As falls are caused by many different risk factors, it is necessary to identify potential incidents and make needed changes accordingly in order to reduce the risk and prevent falls. Therefore, we propose a system using surveillance cameras to detect daily activities (e.g., bending down, sitting, standing, and walking) that potentially increase the risk of falling. Moreover, we recognize high risk factors of falls such as ones that involve using the phone while performing an activity, not paying attention to obstacles, and not holding the handrails while going upstairs or downstairs. Convolutional neural network is applied for activity classification in this work. This warning system is utilized for detecting risk factors of falls that commonly occur among the elderly, which could then be used to trigger a message and/or audible alert to designated persons such as a doctor, a caregiver, or family members for timely assistance and care.
{"title":"Recognizing Fall Risk Factors with Convolutional Neural Network","authors":"Sittichai Sukreep, P. Dajpratham, Chakarida Nukoolkit, S. Yamsaengsung, Thanapong Khajontantichaikun, P. Mongkolnam, S. Jaiyen, Vithida Chongsuphajaisiddhi","doi":"10.1109/JCSSE58229.2023.10202147","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202147","url":null,"abstract":"As the number of elderly living alone is increasing every year, some seemingly common daily activities can potentially raise the risk of serious injuries and fatal accidents for these elderly. While falls can occur anywhere, they most often occur at home, this is especially true among the elderly. Without timely notification to medical personnel and assistance, the resulting injuries could be life-threatening. As falls are caused by many different risk factors, it is necessary to identify potential incidents and make needed changes accordingly in order to reduce the risk and prevent falls. Therefore, we propose a system using surveillance cameras to detect daily activities (e.g., bending down, sitting, standing, and walking) that potentially increase the risk of falling. Moreover, we recognize high risk factors of falls such as ones that involve using the phone while performing an activity, not paying attention to obstacles, and not holding the handrails while going upstairs or downstairs. Convolutional neural network is applied for activity classification in this work. This warning system is utilized for detecting risk factors of falls that commonly occur among the elderly, which could then be used to trigger a message and/or audible alert to designated persons such as a doctor, a caregiver, or family members for timely assistance and care.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"42 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120987646","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 : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10201953
Sherrlyn M. Rasdas, Arnel C. Fajardo, J. S. Limbago
Manila Bay is a significant contributor to the Philippines' fish production, but its resources have been depleted due to overfishing, pollution, and damage, leading to a decline in fish catch and a shift towards less valuable species. Conventional approaches to fisheries stock assessment impose constraints on our comprehension of fish population dynamics. These limitations can be overcome through the utilization of machine learning techniques, which enable the forecasting and modeling of fisheries populations with improved accuracy and understanding. In this study, the commercial fisheries populations data collected from 2018 to 2021 in Manila Bay were used to predict the abundance of species fisheries production data using the K-NN - MLP - Logistic Regression (KNMLPR) model based on the majority voting ensemble approach. Analysis revealed that it is possible to combine the strengths of multiple models and improve overall predictive performance. The results also suggest that the k-nearest neighbors and logistic regression models have the best performance in predicting fish species population dynamics, while the neural network model shows slightly lower accuracy. This study provides valuable insights for fishery management and policymaking to support sustainable fishing practices in the region. Further research could focus on exploring additional machine learning algorithms and incorporating environmental factors to improve the prediction accuracy of the model.
{"title":"Predicting Abundance of Fish Species Populations in Manila Bay, Philippines Based on Ensemble Learning Approach","authors":"Sherrlyn M. Rasdas, Arnel C. Fajardo, J. S. Limbago","doi":"10.1109/JCSSE58229.2023.10201953","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10201953","url":null,"abstract":"Manila Bay is a significant contributor to the Philippines' fish production, but its resources have been depleted due to overfishing, pollution, and damage, leading to a decline in fish catch and a shift towards less valuable species. Conventional approaches to fisheries stock assessment impose constraints on our comprehension of fish population dynamics. These limitations can be overcome through the utilization of machine learning techniques, which enable the forecasting and modeling of fisheries populations with improved accuracy and understanding. In this study, the commercial fisheries populations data collected from 2018 to 2021 in Manila Bay were used to predict the abundance of species fisheries production data using the K-NN - MLP - Logistic Regression (KNMLPR) model based on the majority voting ensemble approach. Analysis revealed that it is possible to combine the strengths of multiple models and improve overall predictive performance. The results also suggest that the k-nearest neighbors and logistic regression models have the best performance in predicting fish species population dynamics, while the neural network model shows slightly lower accuracy. This study provides valuable insights for fishery management and policymaking to support sustainable fishing practices in the region. Further research could focus on exploring additional machine learning algorithms and incorporating environmental factors to improve the prediction accuracy of the model.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130549895","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 : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202117
Sutthiphan Prananpaeng, Thiradon Thaiyanto, Ratsameetip Wita, N. Anukul
Analysis of blood group characteristics using next-generation sequencing can be used to ensure blood transfusion safety. With the aim of avoiding adverse effects in blood transfusions caused by blood group incompatibility, this research studies genomic characteristics of blood groups using whole-exome sequencing analysis. Whole-Exome Sequencing, although time-consuming and data-intensive, provides crucial information for blood group analysis. The research proposes a two-step analysis framework including WES raw data pipeline analysis using GATK, resulting in single nucleotide polymor-phisms and variant information in ABO specific gene, and allele-specific analysis and potential blood group identification. The proposed framework helps identify specific alleles of ABO subgroup based on genomics data which can ensure blood type compatibility in the transfusion process which ultimately leading to improved safety in blood transfusions.
{"title":"Whole-Exome Sequencing (WES) Analysis for ABO Subgroups Identification","authors":"Sutthiphan Prananpaeng, Thiradon Thaiyanto, Ratsameetip Wita, N. Anukul","doi":"10.1109/JCSSE58229.2023.10202117","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202117","url":null,"abstract":"Analysis of blood group characteristics using next-generation sequencing can be used to ensure blood transfusion safety. With the aim of avoiding adverse effects in blood transfusions caused by blood group incompatibility, this research studies genomic characteristics of blood groups using whole-exome sequencing analysis. Whole-Exome Sequencing, although time-consuming and data-intensive, provides crucial information for blood group analysis. The research proposes a two-step analysis framework including WES raw data pipeline analysis using GATK, resulting in single nucleotide polymor-phisms and variant information in ABO specific gene, and allele-specific analysis and potential blood group identification. The proposed framework helps identify specific alleles of ABO subgroup based on genomics data which can ensure blood type compatibility in the transfusion process which ultimately leading to improved safety in blood transfusions.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123367701","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 : 2023-06-28DOI: 10.1109/jcsse58229.2023.10202112
{"title":"Copyright Page","authors":"","doi":"10.1109/jcsse58229.2023.10202112","DOIUrl":"https://doi.org/10.1109/jcsse58229.2023.10202112","url":null,"abstract":"","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121167165","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 : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202054
Md. Shakhawat Hossain, U. Salsabil, M. M. Syeed, Md Mahmudur Rahman, K. Fatema, Mohammad Faisal Uddin
The outbreak of chicken disease has been a major concern around the world, as the poultry industry supplies a significant portion of t he global protein needs. Such an outbreak can cause enormous financial loss to the poultry farmers and induce food insecurity. The COVID-19 lessons have taught us that chicken disease outbreak can be a threat to human lives as well if not detected in time. Currently, Poultry farmers rely on their experience to detect diseases and to seek professional's help, which occasionally fails, resulting in widespread chicken death. Thus, early detection of chicken disease is of great importance for sustainable poultry farming, reducing poultry losses and preventing the spread of zoonotic diseases to humans. Several methods proposed previously for this purpose have failed to achieve sufficient a ccuracy and practical usability. In this paper, we present an AI-assisted automated system for detecting chicken diseases at an early stage from smart-phone captured fecal images. The proposed method utilized an ensemble network of four fine-tuned convolutional neural networks that were selected through an exhaustive literature search. The proposed method outperformed existing methods, achieving 99.99% accuracy and we demonstrated its practical usability in terms of time, robustness, user friendliness and cost.
{"title":"SmartPoultry: Early Detection of Poultry Disease from Smartphone Captured Fecal Image","authors":"Md. Shakhawat Hossain, U. Salsabil, M. M. Syeed, Md Mahmudur Rahman, K. Fatema, Mohammad Faisal Uddin","doi":"10.1109/JCSSE58229.2023.10202054","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202054","url":null,"abstract":"The outbreak of chicken disease has been a major concern around the world, as the poultry industry supplies a significant portion of t he global protein needs. Such an outbreak can cause enormous financial loss to the poultry farmers and induce food insecurity. The COVID-19 lessons have taught us that chicken disease outbreak can be a threat to human lives as well if not detected in time. Currently, Poultry farmers rely on their experience to detect diseases and to seek professional's help, which occasionally fails, resulting in widespread chicken death. Thus, early detection of chicken disease is of great importance for sustainable poultry farming, reducing poultry losses and preventing the spread of zoonotic diseases to humans. Several methods proposed previously for this purpose have failed to achieve sufficient a ccuracy and practical usability. In this paper, we present an AI-assisted automated system for detecting chicken diseases at an early stage from smart-phone captured fecal images. The proposed method utilized an ensemble network of four fine-tuned convolutional neural networks that were selected through an exhaustive literature search. The proposed method outperformed existing methods, achieving 99.99% accuracy and we demonstrated its practical usability in terms of time, robustness, user friendliness and cost.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114340000","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 : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10201937
Sittisak Saechueng, Ungsumalee Suttapakti
Accurate spondylolisthesis classification is crucial for planning effective patient treatment. The machine learning technique is widely used to efficiently analyze spondylolisthesis from X-ray images. However, existing methods are sensitive to noise effects when using X-ray images. Moreover, the effectiveness of existing feature extraction is insufficiently accurate. Therefore, the weighting Canny histogram of oriented gradients (HOG) method is proposed to increase the accuracy of spondylolisthesis classification. This method uses an anisotropic filter to reduce noise in a pre-processing step. Then Canny operator is applied instead of x-and y-derivative filter of the HOG method to achieve better gradient images. After that, the slope value of the lumbar vertebra is calculated to weigh the texture HOG features. Thus, our features have properties of texture and shift of lumbar vertebrae. On the BUU Spine dataset, the weighting Canny HOG method yields high recall, precision, F1-score, and classification accuracy of 0.7488, 0.8526, 0.7832, and 0.9155. Our method is able to efficiently extract texture and shift features, thus improving the effectiveness of classifying spondylolisthesis from X-ray images.
{"title":"Weighting Histogram of Oriented Gradients for Spondylolisthesis Classification from X-Ray Images","authors":"Sittisak Saechueng, Ungsumalee Suttapakti","doi":"10.1109/JCSSE58229.2023.10201937","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10201937","url":null,"abstract":"Accurate spondylolisthesis classification is crucial for planning effective patient treatment. The machine learning technique is widely used to efficiently analyze spondylolisthesis from X-ray images. However, existing methods are sensitive to noise effects when using X-ray images. Moreover, the effectiveness of existing feature extraction is insufficiently accurate. Therefore, the weighting Canny histogram of oriented gradients (HOG) method is proposed to increase the accuracy of spondylolisthesis classification. This method uses an anisotropic filter to reduce noise in a pre-processing step. Then Canny operator is applied instead of x-and y-derivative filter of the HOG method to achieve better gradient images. After that, the slope value of the lumbar vertebra is calculated to weigh the texture HOG features. Thus, our features have properties of texture and shift of lumbar vertebrae. On the BUU Spine dataset, the weighting Canny HOG method yields high recall, precision, F1-score, and classification accuracy of 0.7488, 0.8526, 0.7832, and 0.9155. Our method is able to efficiently extract texture and shift features, thus improving the effectiveness of classifying spondylolisthesis from X-ray images.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124300007","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 : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202056
Pakin Siwathammarat, P. Jesadaporn, Jakarin Chawachat
Usually, elderly patients in hospitals suffer from malnutrition because they are unable to consume food as prescribed by doctors or nutritionists. Analyzing food intake is labor-intensive and time-consuming. Therefore, machine learning is used to analyze the food intake. Major food analysis tasks include food classification and food weight estimation. The basic machine learning approach to this problem is to combine a food classification model with a food weight estimate model sequentially. When we deployed it, we found that a large amount of memory and models were required. One solution is to use multi-task learning. In this study, we proposed multi-task learning frameworks that could recognize food and predict weight based on a single image. The performance of our frameworks was compared to the baseline models, which only utilized either regression or classification. Although baseline accuracy is higher, our framework has MAPE values that are lower than the baseline. To improve the performance, we explored different approaches for weighting loss, including manual weighting and auto weighting, using uncertainty and auxiliary tasks. From the experiment, our results showed that our multi-task learning framework that adjusted the weight of loss using auxiliary tasks outperformed the baseline models in terms of MAPE and Accuracy. Moreover, we demonstrate our framework when scaling up the backbone from ResNet50 to ResNet101 and ResNet152.
{"title":"Multi-Task Learning Frameworks to Classify Food and Estimate Weight From a Single Image","authors":"Pakin Siwathammarat, P. Jesadaporn, Jakarin Chawachat","doi":"10.1109/JCSSE58229.2023.10202056","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202056","url":null,"abstract":"Usually, elderly patients in hospitals suffer from malnutrition because they are unable to consume food as prescribed by doctors or nutritionists. Analyzing food intake is labor-intensive and time-consuming. Therefore, machine learning is used to analyze the food intake. Major food analysis tasks include food classification and food weight estimation. The basic machine learning approach to this problem is to combine a food classification model with a food weight estimate model sequentially. When we deployed it, we found that a large amount of memory and models were required. One solution is to use multi-task learning. In this study, we proposed multi-task learning frameworks that could recognize food and predict weight based on a single image. The performance of our frameworks was compared to the baseline models, which only utilized either regression or classification. Although baseline accuracy is higher, our framework has MAPE values that are lower than the baseline. To improve the performance, we explored different approaches for weighting loss, including manual weighting and auto weighting, using uncertainty and auxiliary tasks. From the experiment, our results showed that our multi-task learning framework that adjusted the weight of loss using auxiliary tasks outperformed the baseline models in terms of MAPE and Accuracy. Moreover, we demonstrate our framework when scaling up the backbone from ResNet50 to ResNet101 and ResNet152.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126017375","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 : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202156
Amonrat Prasitsupparote, P. Pasitsuparoad, Sirathee Itsarapongpukdee
Road accidents in product distribution businesses frequently occur during long weekends or festival periods. The cause of accidents usually comes from tired or fatigue drivers due to overwork or continuous long work. For some companies, the accident can cost up to 20% of the registered capital. This payment heavily affects the company's cash flow a nd account balance. Unfortunately, commercial devices for drowsiness detection or prevention are too expensive for SMEs. Therefore, SMEs required a low-cost, real-time, easy-to-use, and easy to install system. An Android smartphone based system to detect drowsy drivers was created. The application evaluates the drowsy drivers using ML Kit's face detection API and sends a message through Line Notify API. The results showed that the application can differentiate between normal and drowsy drivers as well as send an alarm to the drivers and manager. Moreover, the application is tolerated to the low FPS smartphone down to 3 FPS.
{"title":"Real-Time Driver Drowsiness Alert System for Product Distribution Businesses in Phuket Using Android Devices","authors":"Amonrat Prasitsupparote, P. Pasitsuparoad, Sirathee Itsarapongpukdee","doi":"10.1109/JCSSE58229.2023.10202156","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202156","url":null,"abstract":"Road accidents in product distribution businesses frequently occur during long weekends or festival periods. The cause of accidents usually comes from tired or fatigue drivers due to overwork or continuous long work. For some companies, the accident can cost up to 20% of the registered capital. This payment heavily affects the company's cash flow a nd account balance. Unfortunately, commercial devices for drowsiness detection or prevention are too expensive for SMEs. Therefore, SMEs required a low-cost, real-time, easy-to-use, and easy to install system. An Android smartphone based system to detect drowsy drivers was created. The application evaluates the drowsy drivers using ML Kit's face detection API and sends a message through Line Notify API. The results showed that the application can differentiate between normal and drowsy drivers as well as send an alarm to the drivers and manager. Moreover, the application is tolerated to the low FPS smartphone down to 3 FPS.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121779670","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 : 2023-06-28DOI: 10.1109/jcsse58229.2023.10202057
{"title":"Keynotes","authors":"","doi":"10.1109/jcsse58229.2023.10202057","DOIUrl":"https://doi.org/10.1109/jcsse58229.2023.10202057","url":null,"abstract":"","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131917217","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 : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202079
Karnkitti Kittikamron, Natthanon Manop, Adsadawut Chanakitkarnchok, K. Rojviboonchai
Location-based service (LBS) is necessary and useful for several applications including navigation and games. These real-time applications require high accuracy and low delay. In general, the complexity of indoor localization algorithms used in LBS depends on the size of fingerprint data. This can lead to long delays when operating in large-scale areas. In this paper, we propose a novel optimization framework for edge service placement, aiming at minimizing the overall cost of edge computing deployment and service response time. Our placement strategy is used to solve the formulated edge node placement problems. The simulated annealing approach is then used in solution space exploration to discover the optimal solution efficiently. The results show that our proposed framework can outperform the existing work with a 27.58% improvement in the service response time on the simulated data, and a 41.94% improvement in the service response time on the real-world large-scale data.
{"title":"Edge Service Placement Optimization for Location-Based Service","authors":"Karnkitti Kittikamron, Natthanon Manop, Adsadawut Chanakitkarnchok, K. Rojviboonchai","doi":"10.1109/JCSSE58229.2023.10202079","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202079","url":null,"abstract":"Location-based service (LBS) is necessary and useful for several applications including navigation and games. These real-time applications require high accuracy and low delay. In general, the complexity of indoor localization algorithms used in LBS depends on the size of fingerprint data. This can lead to long delays when operating in large-scale areas. In this paper, we propose a novel optimization framework for edge service placement, aiming at minimizing the overall cost of edge computing deployment and service response time. Our placement strategy is used to solve the formulated edge node placement problems. The simulated annealing approach is then used in solution space exploration to discover the optimal solution efficiently. The results show that our proposed framework can outperform the existing work with a 27.58% improvement in the service response time on the simulated data, and a 41.94% improvement in the service response time on the real-world large-scale data.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130791239","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：