In wireless sensor networks (WSN), machine learning (ML) algorithms have an important role in cluster head (CH) selection according to several quality of service (QoS) metrics. This paper provides a comprehensive review and a case study on an experimental testbed of the implementation of various ML algorithms within various clustering protocols in WSNs.
{"title":"Performance Analysis of Machine Learning Algorithms with Clustering Protocol in Wireless Sensor Networks","authors":"Rahma Gantassi, Zaki Masood, Sol Lim, Quota Alief Sias, Yonghoon Choi","doi":"10.1109/ICAIIC57133.2023.10067019","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067019","url":null,"abstract":"In wireless sensor networks (WSN), machine learning (ML) algorithms have an important role in cluster head (CH) selection according to several quality of service (QoS) metrics. This paper provides a comprehensive review and a case study on an experimental testbed of the implementation of various ML algorithms within various clustering protocols in WSNs.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121671849","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 : 2023-02-20DOI: 10.1109/ICAIIC57133.2023.10067073
Seo-Lim Park, Gayeong Lee, Jaeyoung Shin, Seung-Ho Lee, Young-woo Lee
A fast-growing manufacturing technology of memory devices leads to further increased design complexity, density and test cost. In general, the high cost of automated test equipment (ATE) is required to test the high-speed memory devices, which can exceed its memory performance. To solve this problem, the manufacturers are seeking more cost-effective methods, especially for at-speed testing. In order to reduce the test cost, we propose the instruction-based march test pattern generation scheme which can be applied to the low-end ATE with multiple pattern generators. The proposed method can generate linear patterns based on instructions, which can distribute them to multiple ALPGs of a low-end ATE to implement the high-speed test patterns. The experimental results show that the various march test patterns for at-speed testing can be implemented by using the several fixed commands, regardless of the memory cell sizes.
{"title":"Instruction-based March Test Pattern Generation Scheme for At-Speed Test Cost Reduction","authors":"Seo-Lim Park, Gayeong Lee, Jaeyoung Shin, Seung-Ho Lee, Young-woo Lee","doi":"10.1109/ICAIIC57133.2023.10067073","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067073","url":null,"abstract":"A fast-growing manufacturing technology of memory devices leads to further increased design complexity, density and test cost. In general, the high cost of automated test equipment (ATE) is required to test the high-speed memory devices, which can exceed its memory performance. To solve this problem, the manufacturers are seeking more cost-effective methods, especially for at-speed testing. In order to reduce the test cost, we propose the instruction-based march test pattern generation scheme which can be applied to the low-end ATE with multiple pattern generators. The proposed method can generate linear patterns based on instructions, which can distribute them to multiple ALPGs of a low-end ATE to implement the high-speed test patterns. The experimental results show that the various march test patterns for at-speed testing can be implemented by using the several fixed commands, regardless of the memory cell sizes.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117084724","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 : 2023-02-20DOI: 10.1109/ICAIIC57133.2023.10067048
U. Nuha, Chih-Hsueh Lin
Sentiment analysis has a critical role to reveal an opinion in a text-based form. Therefore, we exploit this analysis to discover the sentiment polarity of Taiwan Social Distancing mobile application. This paper proposes a semi-supervised scheme for annotating this mobile application's reviews. The semi-supervised scheme utilized a combination of numeric rating and lexicon-based sentiment. In addition, we also perform the sentiment analysis on an aspect-based level. Based on the experiment, we decide to select three aspects to be analyzed. This paper also evaluates the proposed scheme by implementing bidirectional encoder representations from transformers (BERT) and multilayer perceptron (MLP) as the classification model using the sentiment label of the proposed scheme. The result shows that the annotation of the proposed scheme outperforms the data annotation using counterpart models.
{"title":"Aspect-Based Sentiment Analysis with Semi-Supervised Approach on Taiwan Social Distancing App User Reviews","authors":"U. Nuha, Chih-Hsueh Lin","doi":"10.1109/ICAIIC57133.2023.10067048","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067048","url":null,"abstract":"Sentiment analysis has a critical role to reveal an opinion in a text-based form. Therefore, we exploit this analysis to discover the sentiment polarity of Taiwan Social Distancing mobile application. This paper proposes a semi-supervised scheme for annotating this mobile application's reviews. The semi-supervised scheme utilized a combination of numeric rating and lexicon-based sentiment. In addition, we also perform the sentiment analysis on an aspect-based level. Based on the experiment, we decide to select three aspects to be analyzed. This paper also evaluates the proposed scheme by implementing bidirectional encoder representations from transformers (BERT) and multilayer perceptron (MLP) as the classification model using the sentiment label of the proposed scheme. The result shows that the annotation of the proposed scheme outperforms the data annotation using counterpart models.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115579853","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 : 2023-02-20DOI: 10.1109/ICAIIC57133.2023.10067045
P. Kim, Su Yeol Kim
In this paper, an automatic vehicle speed control system with PID controller and Kalman filter is designed with consideration of various uncertainties, such as disturbance, system variation and feedback sensor noise, and then verified through computer simulations. The performance degradation due to disturbance and system variation in the basic open-loop control is shown. To resolve this problem, a PID controller based feedback system is designed for the automatic vehicle speed control system. In addition, to improve the performance degradation due to feedback sensor noise that may occur during the feedback process, the Kalman filter is applied for the automatic vehicle speed control system. Ultimately, it is verified that the designed automatic vehicle speed control system with PID controller and Kalman filter not only satisfies all performance criteria but also has the ability to reject disturbance, cope with system variation and reduce feedback sensor noise.
{"title":"An Automatic Vehicle Speed Control System with Consideration of Various Uncertainties*","authors":"P. Kim, Su Yeol Kim","doi":"10.1109/ICAIIC57133.2023.10067045","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067045","url":null,"abstract":"In this paper, an automatic vehicle speed control system with PID controller and Kalman filter is designed with consideration of various uncertainties, such as disturbance, system variation and feedback sensor noise, and then verified through computer simulations. The performance degradation due to disturbance and system variation in the basic open-loop control is shown. To resolve this problem, a PID controller based feedback system is designed for the automatic vehicle speed control system. In addition, to improve the performance degradation due to feedback sensor noise that may occur during the feedback process, the Kalman filter is applied for the automatic vehicle speed control system. Ultimately, it is verified that the designed automatic vehicle speed control system with PID controller and Kalman filter not only satisfies all performance criteria but also has the ability to reject disturbance, cope with system variation and reduce feedback sensor noise.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128704899","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 : 2023-02-20DOI: 10.1109/ICAIIC57133.2023.10066979
Evdokia Xygi, Andreas D. Andriopoulos, Dimitrios A. Koutsomitropoulos
Professionals as well as the general public need effective help to access, understand and consume complex biomedical concepts. The existence of an interaction environment capable of automatically processing such information - thus replacing human intervention - such as chatbots, is however challenging. In this paper we propose a method of utilizing chatbots in the domain of biomedicine. In the implementation we choose to incorporate the BERT algorithm, so as to adopt a modern technique for natural language processing tasks. We use several pre-trained models (RoBERTa, XLM-R, BERT Large, and BioBert) in order to evaluate their ability to back the chatbot infrastructure. The data is retrieved from the PubMed repository, with the final set being formed into full sentences or potential chatbot responses, thus preserving their conceptual meaning. Response selection is performed using similarity metrics and F-score. The results create a ranking of the models placing related ones closely, recognizing the ability to always answer each question and highlighting the importance of the training previously applied to them. These are compared to the Count Vectorizer technique, which appears to perform better, but with several weaknesses, as many questions could not be answered.
{"title":"Question Answering Chatbots for Biomedical Research Using Transformers","authors":"Evdokia Xygi, Andreas D. Andriopoulos, Dimitrios A. Koutsomitropoulos","doi":"10.1109/ICAIIC57133.2023.10066979","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10066979","url":null,"abstract":"Professionals as well as the general public need effective help to access, understand and consume complex biomedical concepts. The existence of an interaction environment capable of automatically processing such information - thus replacing human intervention - such as chatbots, is however challenging. In this paper we propose a method of utilizing chatbots in the domain of biomedicine. In the implementation we choose to incorporate the BERT algorithm, so as to adopt a modern technique for natural language processing tasks. We use several pre-trained models (RoBERTa, XLM-R, BERT Large, and BioBert) in order to evaluate their ability to back the chatbot infrastructure. The data is retrieved from the PubMed repository, with the final set being formed into full sentences or potential chatbot responses, thus preserving their conceptual meaning. Response selection is performed using similarity metrics and F-score. The results create a ranking of the models placing related ones closely, recognizing the ability to always answer each question and highlighting the importance of the training previously applied to them. These are compared to the Count Vectorizer technique, which appears to perform better, but with several weaknesses, as many questions could not be answered.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130647263","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 : 2023-02-20DOI: 10.1109/ICAIIC57133.2023.10067080
Mohammed A Althamir, Jawhara Z. Boodai, Mohammad Sohel Rahman
Cybersecurity worldwide has become a challenge for organisations and individuals to be protected against all attacks and malware. Working closely and directly with cyber-attacks and attackers has become a challenge to be updated with all new zero-day threats and vulnerabilities. The cybersecurity teams have been facing challenges in examining the advisory tactics, techniques, and procedures (TTP) and what are Indicators of Compromise (IOCs) can be used in addressing these issues. Other than this, incorporating the most suitable cyber security framework can assist in dealing with these technological threats. A direct relationship exists between threat intelligence and artificial intelligence, which contributes to addressing technological threats and protecting the necessary assets and information. Cyberspace and other technological software highly contribute to addressing this issue.
{"title":"A Mini Literature Review on Challenges and Opportunity in Threat Intelligence","authors":"Mohammed A Althamir, Jawhara Z. Boodai, Mohammad Sohel Rahman","doi":"10.1109/ICAIIC57133.2023.10067080","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067080","url":null,"abstract":"Cybersecurity worldwide has become a challenge for organisations and individuals to be protected against all attacks and malware. Working closely and directly with cyber-attacks and attackers has become a challenge to be updated with all new zero-day threats and vulnerabilities. The cybersecurity teams have been facing challenges in examining the advisory tactics, techniques, and procedures (TTP) and what are Indicators of Compromise (IOCs) can be used in addressing these issues. Other than this, incorporating the most suitable cyber security framework can assist in dealing with these technological threats. A direct relationship exists between threat intelligence and artificial intelligence, which contributes to addressing technological threats and protecting the necessary assets and information. Cyberspace and other technological software highly contribute to addressing this issue.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127046932","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 : 2023-02-20DOI: 10.1109/ICAIIC57133.2023.10067007
Cuong Manh Ho, D. Lakew, Anh-Tien Tran, Chunghyun Lee, D. Hua, Sungrae Cho
Unmanned aerial vehicles (UAVs) and Satellites are promising as power frameworks for 5G and 6G networks to provide solutions for the limitation in deployment, batteries, and transference reliability in areas. It leads to efficiency in terrestrial systems, broken Base stations (BSs) substitution, reduced cost infrastructures, and mobility management. It is also an indispensable role to improve the quality of Internet Of Things (IoTs) systems. Besides, Rate-Splitting Multiple Access (RSMA) has emerged as a promising technique to manage interference in multiple access (MA) systems, and optimize the non-orthogonal transmission (non-OT) for 5G and 6G networks. In the current, one of the most impressive schemes for the Unmanned Aerial Vehicle (UAV) and Satellite-based networks is RSMA. This paper details a comprehensive review on UAV and Satellite networks with RSMA of wireless network 6G. After analyzing the overview of UAV and Satellite-based networks with RSMA, the main applications of RSMA scheme in networks based on UAV and Satellite-based networks will be exploited. Finally, the main challenges and future directions are suggested and defined.
{"title":"A Review on Unmanned Aerial Vehicle-based Networks and Satellite-based Networks with RSMA: Research Challenges and Future Trends","authors":"Cuong Manh Ho, D. Lakew, Anh-Tien Tran, Chunghyun Lee, D. Hua, Sungrae Cho","doi":"10.1109/ICAIIC57133.2023.10067007","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067007","url":null,"abstract":"Unmanned aerial vehicles (UAVs) and Satellites are promising as power frameworks for 5G and 6G networks to provide solutions for the limitation in deployment, batteries, and transference reliability in areas. It leads to efficiency in terrestrial systems, broken Base stations (BSs) substitution, reduced cost infrastructures, and mobility management. It is also an indispensable role to improve the quality of Internet Of Things (IoTs) systems. Besides, Rate-Splitting Multiple Access (RSMA) has emerged as a promising technique to manage interference in multiple access (MA) systems, and optimize the non-orthogonal transmission (non-OT) for 5G and 6G networks. In the current, one of the most impressive schemes for the Unmanned Aerial Vehicle (UAV) and Satellite-based networks is RSMA. This paper details a comprehensive review on UAV and Satellite networks with RSMA of wireless network 6G. After analyzing the overview of UAV and Satellite-based networks with RSMA, the main applications of RSMA scheme in networks based on UAV and Satellite-based networks will be exploited. Finally, the main challenges and future directions are suggested and defined.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123186544","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}
A key issue in the research and development of next-generation mobile communication systems (Beyond 5G/6G) is the availability of novel frequency bands. Currently, the frequency band below 6 GHz, which is suitable for mobile communications, is already tight, and technologies for highly efficient utilization of finite spectrum resources are required. Therefore, many researches have been conducted on the practical application of dynamic spectrum sharing technology for the effective use of spectrum. For this technology, it is important to precisely estimate the spectrum utilization of the wireless system and the propagation characteristics changes in each environment. Furthermore, in Beyond 5G/6G, non-terrestrial networks (NTNs) such as satellites and drones are expected to be utilized to expand the communication area, which will require spectrum management in the height direction. In this paper, we design and develop a 5-dimensional (5D) spectrum database that extends the spectrum database of radio environment information from the 2-dimensional (2D) plane of latitude and longitude to a 3-dimensional (3D) space that includes height information, as well as time domain and frequency domain. Additionally, we describe the design details for the mobile satellites in the NTNs incorporated into the database. Finally, test results from the measurement campaign and calculated data size in the developed database are discussed.
{"title":"5D Spectrum Database","authors":"Hirofumi Nakajo, Yusuke Itayama, Shougo Matsuo, Takeo Fujii","doi":"10.1109/ICAIIC57133.2023.10067018","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067018","url":null,"abstract":"A key issue in the research and development of next-generation mobile communication systems (Beyond 5G/6G) is the availability of novel frequency bands. Currently, the frequency band below 6 GHz, which is suitable for mobile communications, is already tight, and technologies for highly efficient utilization of finite spectrum resources are required. Therefore, many researches have been conducted on the practical application of dynamic spectrum sharing technology for the effective use of spectrum. For this technology, it is important to precisely estimate the spectrum utilization of the wireless system and the propagation characteristics changes in each environment. Furthermore, in Beyond 5G/6G, non-terrestrial networks (NTNs) such as satellites and drones are expected to be utilized to expand the communication area, which will require spectrum management in the height direction. In this paper, we design and develop a 5-dimensional (5D) spectrum database that extends the spectrum database of radio environment information from the 2-dimensional (2D) plane of latitude and longitude to a 3-dimensional (3D) space that includes height information, as well as time domain and frequency domain. Additionally, we describe the design details for the mobile satellites in the NTNs incorporated into the database. Finally, test results from the measurement campaign and calculated data size in the developed database are discussed.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115921635","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 : 2023-02-20DOI: 10.1109/ICAIIC57133.2023.10067085
Qin Rui, Liu Sinuo, Teoh Teik Toe, Brian Brister
The purpose of this paper is to apply convolutional neural networks to help diagnose patients with kidney disease. Findings are divided into four types: kidney tumor, cyst, normal and stones. Currently large numbers of people engage in unhealthy lifestyles with poor diet, sedentary activity, and insufficient sleep, often resulting in kidney disease. Early detection is necessary so preventative actions can be taken to help the kidneys recover. Traditional detection is complex and imprecise, while computational diagnosis promises more rapid and accurate results. Convolutional Neural Networks (CNN), part of deep learning, are appropriate diagnostic tools already being used in medical image identification and disease classification. Here we show CNN diagnosis with ultimate training accuracies up to 98% and test accuracies up to 99%.
{"title":"Kidney Diseases Detection Based on Convolutional Neural Network","authors":"Qin Rui, Liu Sinuo, Teoh Teik Toe, Brian Brister","doi":"10.1109/ICAIIC57133.2023.10067085","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067085","url":null,"abstract":"The purpose of this paper is to apply convolutional neural networks to help diagnose patients with kidney disease. Findings are divided into four types: kidney tumor, cyst, normal and stones. Currently large numbers of people engage in unhealthy lifestyles with poor diet, sedentary activity, and insufficient sleep, often resulting in kidney disease. Early detection is necessary so preventative actions can be taken to help the kidneys recover. Traditional detection is complex and imprecise, while computational diagnosis promises more rapid and accurate results. Convolutional Neural Networks (CNN), part of deep learning, are appropriate diagnostic tools already being used in medical image identification and disease classification. Here we show CNN diagnosis with ultimate training accuracies up to 98% and test accuracies up to 99%.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116761511","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 : 2023-02-20DOI: 10.1109/ICAIIC57133.2023.10067111
J. Youn
Recently, various applications using artificial intelligence (AI) are deployed in edge network. In particular, An intelligence applications demanded with high computation and low end-to-end latency are executed on edge computing environments. Thus, in this paper, for the optimization of the resource of edge servers in multi-edge network environments, we propose the intelligent task offloading method based on Deep Q-network that can optimize computation capability of the multi-edge computing environments. For this, first at all, we formulate the problem of multi-edge computing allocation with a Markov decision process and propose the policy for allocating edge resource adopting a deep reinforcement learning algorithm. In the simulation, the results show the proposed method gets a better performance in terms of the end-to-end latency of the offloaded task than the existing methods.
{"title":"Intelligent Task Offloading Method using Deep Q-Network for Collaborative Edge Computing System","authors":"J. Youn","doi":"10.1109/ICAIIC57133.2023.10067111","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067111","url":null,"abstract":"Recently, various applications using artificial intelligence (AI) are deployed in edge network. In particular, An intelligence applications demanded with high computation and low end-to-end latency are executed on edge computing environments. Thus, in this paper, for the optimization of the resource of edge servers in multi-edge network environments, we propose the intelligent task offloading method based on Deep Q-network that can optimize computation capability of the multi-edge computing environments. For this, first at all, we formulate the problem of multi-edge computing allocation with a Markov decision process and propose the policy for allocating edge resource adopting a deep reinforcement learning algorithm. In the simulation, the results show the proposed method gets a better performance in terms of the end-to-end latency of the offloaded task than the existing methods.","PeriodicalId":105769,"journal":{"name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122893467","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}