Pub Date : 2023-02-20DOI: 10.1109/ICAIIC57133.2023.10066964
Jina Lee, Minhyeok Lee
Two evaluation metrics for GAN models have been proposed in existing studies: Inception score (IS) and Fréchet Inception distance (FID). We propose a new GAN model based on the idea that backpropagating the FID score would guide the GAN to efficiently learn the distribution of real images and generate high-quality images. Based on such an idea, we propose a training loss for the generator to minimize a modified FID loss. Trained with the CIFAR-10 dataset, FIDGAN exhibited an FID of 11.78, which corresponds to a reduced FID compared to an existing model called BigGAN by 20.0%.
{"title":"FIDGAN: A Generative Adversarial Network with An Inception Distance","authors":"Jina Lee, Minhyeok Lee","doi":"10.1109/ICAIIC57133.2023.10066964","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10066964","url":null,"abstract":"Two evaluation metrics for GAN models have been proposed in existing studies: Inception score (IS) and Fréchet Inception distance (FID). We propose a new GAN model based on the idea that backpropagating the FID score would guide the GAN to efficiently learn the distribution of real images and generate high-quality images. Based on such an idea, we propose a training loss for the generator to minimize a modified FID loss. Trained with the CIFAR-10 dataset, FIDGAN exhibited an FID of 11.78, which corresponds to a reduced FID compared to an existing model called BigGAN by 20.0%.","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":"115582768","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/ICAIIC57133.2023.10067127
Safa Altaha, Mohammad Sohel Rahman
Governments, organizations, and companies shall implement some measures to ensure the security and continuity of their business operations especially those with high criticality and availability. If cyber threats can bring down a company for a long time and create reputational impacts which cause painful financial losses of hundreds of thousands or millions of Saudi riyals and significant disruptions to business operations, then we should think of business continuity. As a result, as organizations build their business continuity and disaster recovery plans and procedures, cybersecurity measures must be integrated throughout the entire process. This paper focuses on falling the gaps between cybersecurity and business continuity and integrating them in order to establish resilience systems and enable organizations to ensure that the proper processes are being put in place and resources are allocated to help facilitate a smooth transition as they recover from cyber incidents.
{"title":"A Mini Literature Review on Integrating Cybersecurity for Business Continuity","authors":"Safa Altaha, Mohammad Sohel Rahman","doi":"10.1109/ICAIIC57133.2023.10067127","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067127","url":null,"abstract":"Governments, organizations, and companies shall implement some measures to ensure the security and continuity of their business operations especially those with high criticality and availability. If cyber threats can bring down a company for a long time and create reputational impacts which cause painful financial losses of hundreds of thousands or millions of Saudi riyals and significant disruptions to business operations, then we should think of business continuity. As a result, as organizations build their business continuity and disaster recovery plans and procedures, cybersecurity measures must be integrated throughout the entire process. This paper focuses on falling the gaps between cybersecurity and business continuity and integrating them in order to establish resilience systems and enable organizations to ensure that the proper processes are being put in place and resources are allocated to help facilitate a smooth transition as they recover from cyber incidents.","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":"125354082","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/ICAIIC57133.2023.10066970
S. Awang, Mohd Qhairel Rafiqi Rokei, J. Sulaiman
Property theft is one of the crimes that increases in which leads to a major concern in Malaysia. Despite of having surveillance cameras (CCTV) everywhere, the crimes keep occur due to the lack of security system. The security system can be developed by utilizing the existence of CCTVs specifically home surveillance CCTV. Therefore, this paper introduces a security system known as Suspicious Activity Trigger System (SATS) that able to automatically trigger an alarm or an alert message whenever suspicious activity is detected from the CCTV video image. The activity will be detected in a video image using Deep Learning technique which is YOLOv6 Convolutional Neural Network (CNN) algorithm. The algorithm will detect an object which is a person in the video and classify it as a suspicious activity or not. If the activity is classified as the suspicious activity, the system will automatically display a trigger message to alert SATS user. The user can therefore take whatever appropriate measure to prevent being a victim. Experiments have been conducted using a dataset taken from Google Open Image. We also implemented the experiments on the self-obtained dataset. Based on the experiment, 92.53% for precision and 96.6% of the accuracy is obtained using this algorithm. Therefore, YOLOv6 can be implemented in the security system to prevent crimes in residency areas.
财产盗窃是日益增加的犯罪之一,在马来西亚引起了很大的关注。尽管到处都有监控摄像头(CCTV),但由于缺乏安全系统,犯罪事件不断发生。安全系统可以利用现有的闭路电视,特别是家庭监控闭路电视来开发。因此,本文介绍了一种称为可疑活动触发系统(SATS)的安全系统,该系统能够在从CCTV视频图像中检测到可疑活动时自动触发警报或警报消息。使用深度学习技术,即YOLOv6卷积神经网络(CNN)算法,将在视频图像中检测活动。该算法将检测视频中是否有人的物体,并将其归类为可疑活动。如果该活动被归类为可疑活动,系统将自动显示触发消息以提醒SATS用户。因此,用户可以采取任何适当的措施来防止成为受害者。实验使用了来自Google Open Image的数据集。我们还在自己获得的数据集上进行了实验。实验结果表明,该算法的准确率为96.6%,精密度为92.53%。因此,YOLOv6可以在安全系统中实施,以防止居民区的犯罪。
{"title":"Suspicious Activity Trigger System using YOLOv6 Convolutional Neural Network","authors":"S. Awang, Mohd Qhairel Rafiqi Rokei, J. Sulaiman","doi":"10.1109/ICAIIC57133.2023.10066970","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10066970","url":null,"abstract":"Property theft is one of the crimes that increases in which leads to a major concern in Malaysia. Despite of having surveillance cameras (CCTV) everywhere, the crimes keep occur due to the lack of security system. The security system can be developed by utilizing the existence of CCTVs specifically home surveillance CCTV. Therefore, this paper introduces a security system known as Suspicious Activity Trigger System (SATS) that able to automatically trigger an alarm or an alert message whenever suspicious activity is detected from the CCTV video image. The activity will be detected in a video image using Deep Learning technique which is YOLOv6 Convolutional Neural Network (CNN) algorithm. The algorithm will detect an object which is a person in the video and classify it as a suspicious activity or not. If the activity is classified as the suspicious activity, the system will automatically display a trigger message to alert SATS user. The user can therefore take whatever appropriate measure to prevent being a victim. Experiments have been conducted using a dataset taken from Google Open Image. We also implemented the experiments on the self-obtained dataset. Based on the experiment, 92.53% for precision and 96.6% of the accuracy is obtained using this algorithm. Therefore, YOLOv6 can be implemented in the security system to prevent crimes in residency areas.","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":"124865768","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}
Media access control (MAC) protocol identification is key to obtain the full awareness of wireless environments in both civil as well as military communications. In recent years, deep learning (DL) based MAC protocol identification has attracted great attention due to flourishing of deep neural networks (DNNs). However, existing research on DL based MAC protocol identification mostly exploits only one DNN to complete the identification task, which inevitably suffers from low identification accuracy. To combat the problem, this paper proposes a multi-network based algorithm that utilizes three DNNs, including a convolutional neural network (CNN), a long short-term memory (LSTM), and a gated recurrent unit (GRU), for MAC protocol identification. A decision fusion rule is adopted to fuse the individual results of three DNNs and make the final decision. Experiment results show that the proposed multi-network based algorithm performs better than the DL based methods using the single network.
{"title":"Multi-network based MAC Protocol Identification with Decision Fusion","authors":"Anibal Roque Seraponzo, Qinggeng Guo, Shengliang Peng","doi":"10.1109/ICAIIC57133.2023.10067028","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067028","url":null,"abstract":"Media access control (MAC) protocol identification is key to obtain the full awareness of wireless environments in both civil as well as military communications. In recent years, deep learning (DL) based MAC protocol identification has attracted great attention due to flourishing of deep neural networks (DNNs). However, existing research on DL based MAC protocol identification mostly exploits only one DNN to complete the identification task, which inevitably suffers from low identification accuracy. To combat the problem, this paper proposes a multi-network based algorithm that utilizes three DNNs, including a convolutional neural network (CNN), a long short-term memory (LSTM), and a gated recurrent unit (GRU), for MAC protocol identification. A decision fusion rule is adopted to fuse the individual results of three DNNs and make the final decision. Experiment results show that the proposed multi-network based algorithm performs better than the DL based methods using the single network.","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":"122744998","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/ICAIIC57133.2023.10067090
Hojun Lee, Kye-Won Kim, Tae-Ho Chung, Haklim Ko
In ultra-short baseline (USBL), the locations of near-field sources are estimated by using the difference between the propagation delays for the received signals of sensors. Since the sensor spacing is very narrow in the USBL, the difference between the propagation delays for the received signals is very small, which induces ambiguities in positioning for the sources. For low sampling rate scenarios with low signal-to-noise power ratios (SNRs), the ambiguities increase significantly because not only the sample delays for the received signals may not be exactly estimated, but also the difference between the sample delays for the received signals decreases. To solve this problem, this paper proposes a deep learning-based USBL positioning network. The inputs of the proposed network are the estimated distances from the source to the sensors, which are measured by cross-correlation, and the outputs are the range and direction-of-arrival (DOA) of the near-field source. The proposed network improves the positioning performances even if outliers, i.e., incorrectly estimated sample delays, are mixed in the input by learning the relationship between the input and output. Computer simulations demonstrate that the proposed network has 50 times better positioning performances than the conventional method in low SNR regions.
{"title":"Deep Learning-based Ultra Short Baseline Underwater Positioning","authors":"Hojun Lee, Kye-Won Kim, Tae-Ho Chung, Haklim Ko","doi":"10.1109/ICAIIC57133.2023.10067090","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067090","url":null,"abstract":"In ultra-short baseline (USBL), the locations of near-field sources are estimated by using the difference between the propagation delays for the received signals of sensors. Since the sensor spacing is very narrow in the USBL, the difference between the propagation delays for the received signals is very small, which induces ambiguities in positioning for the sources. For low sampling rate scenarios with low signal-to-noise power ratios (SNRs), the ambiguities increase significantly because not only the sample delays for the received signals may not be exactly estimated, but also the difference between the sample delays for the received signals decreases. To solve this problem, this paper proposes a deep learning-based USBL positioning network. The inputs of the proposed network are the estimated distances from the source to the sensors, which are measured by cross-correlation, and the outputs are the range and direction-of-arrival (DOA) of the near-field source. The proposed network improves the positioning performances even if outliers, i.e., incorrectly estimated sample delays, are mixed in the input by learning the relationship between the input and output. Computer simulations demonstrate that the proposed network has 50 times better positioning performances than the conventional method in low SNR regions.","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":"122817046","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/ICAIIC57133.2023.10067041
J. Byun
All drone-based communication protocols have used an unique pseudonym as a drone identifier (Did). Despite Did's obvious applications, however, its properties have not been much studied. In this paper, we study how to securely make a Did based on physically unclonable function (PUF). For this, first we propose four Did properties (uniqueness, identification, authenticity, and privacy) and present two PUF-based drone identifiers (PUFDid) that securely include own identifier and PUF's evaluation. We show that our PUFDid satisfies four properties proposed. We also apply our PUFDid into an inquiry system and analyze its security.
{"title":"PUFDid: PUF-based Drone IDentifier and Its Application","authors":"J. Byun","doi":"10.1109/ICAIIC57133.2023.10067041","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067041","url":null,"abstract":"All drone-based communication protocols have used an unique pseudonym as a drone identifier (Did). Despite Did's obvious applications, however, its properties have not been much studied. In this paper, we study how to securely make a Did based on physically unclonable function (PUF). For this, first we propose four Did properties (uniqueness, identification, authenticity, and privacy) and present two PUF-based drone identifiers (PUFDid) that securely include own identifier and PUF's evaluation. We show that our PUFDid satisfies four properties proposed. We also apply our PUFDid into an inquiry system and analyze its security.","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":"123084147","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/ICAIIC57133.2023.10067095
Ezra Gabriel Malachi, Ritchie Tunggara, Yohannes Cahyadi, Meiliana, Muhamad Fajar
Virtual Reality is a major step in the technology field. Recently, Virtual Reality has been used in various fields, one of which is in the field of sports. In the field of sports, the relationship between experimental and subject behavior in real conditions is a major problem. Virtual Reality can be used in sports because of its situational productivity and animation control in situations that are similar to the real world. This paper presents a research review to understand the use of Virtual Reality in sports. This paper uses a systematic literature review (SLR) as a research method. Research Question(RQ) was determined in the first step. Popular database journals included IEEE Xplore, Science Direct, ACM Digital Library, Springer Open, JSTOR. Twenty-five related articles were produced from the search, then reviewed. The study concluded that there were four purposes of using virtual reality for sports, three types of Virtual Reality Devices used, and three types of approaches.
虚拟现实是技术领域的重大进步。近年来,虚拟现实技术已被应用于各个领域,其中之一就是体育领域。在体育领域,实验行为和被试行为在真实条件下的关系是一个主要问题。虚拟现实可以用于体育运动,因为它的情景生产力和动画控制在类似于现实世界的情况下。本文对虚拟现实技术在体育运动中的应用进行了综述。本文采用系统文献回顾法(SLR)作为研究方法。第一步确定研究问题(Research Question, RQ)。常用数据库期刊包括IEEE explore、Science Direct、ACM Digital Library、b施普林格Open、JSTOR等。从搜索中产生了25篇相关文章,然后进行了审查。该研究得出结论,在体育运动中使用虚拟现实有四个目的,使用的虚拟现实设备有三种类型,方法有三种类型。
{"title":"A Systematic Literature Review of Virtual Reality Implementation in Sports","authors":"Ezra Gabriel Malachi, Ritchie Tunggara, Yohannes Cahyadi, Meiliana, Muhamad Fajar","doi":"10.1109/ICAIIC57133.2023.10067095","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067095","url":null,"abstract":"Virtual Reality is a major step in the technology field. Recently, Virtual Reality has been used in various fields, one of which is in the field of sports. In the field of sports, the relationship between experimental and subject behavior in real conditions is a major problem. Virtual Reality can be used in sports because of its situational productivity and animation control in situations that are similar to the real world. This paper presents a research review to understand the use of Virtual Reality in sports. This paper uses a systematic literature review (SLR) as a research method. Research Question(RQ) was determined in the first step. Popular database journals included IEEE Xplore, Science Direct, ACM Digital Library, Springer Open, JSTOR. Twenty-five related articles were produced from the search, then reviewed. The study concluded that there were four purposes of using virtual reality for sports, three types of Virtual Reality Devices used, and three types of approaches.","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":"133556392","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/ICAIIC57133.2023.10067030
Yuna Sim, S. Sin, Ji-Haeng Cho, Kyunam Kim, Sangmi Moon, I. Hwang
Unmanned aerial vehicles (UAVs) and millimeter wave frequencies play a key role in supporting 5G wireless communication systems. They expand the area of wireless communication by increasing the data capacity in communication systems and supporting high data rates. However, short wavelengths, due to their high millimeter wave frequencies cause problems arising from signal attenuation and path loss. To address these limitations, research centered on high directional beamforming technology continues to gather interest. Furthermore, due to the mobility of UAVs, it is essential to track the beam angle accurately to obtain full beamforming gain. In this study, we propose a beam tracking method based on the unscented Kalman filter using hybrid beamforming. By expanding analog beamforming to hybrid beamforming, our proposed algorithm can be used even in multi-user and multi-stream environments, increasing the data capacity, and, thus increasing utilization in new radio multiple-input multiple-output orthogonal frequency diversity multiplexing systems.
{"title":"Unscented Kalman Filter-based Beam Tracking in NR MIMO System using Hybrid Beamforming","authors":"Yuna Sim, S. Sin, Ji-Haeng Cho, Kyunam Kim, Sangmi Moon, I. Hwang","doi":"10.1109/ICAIIC57133.2023.10067030","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067030","url":null,"abstract":"Unmanned aerial vehicles (UAVs) and millimeter wave frequencies play a key role in supporting 5G wireless communication systems. They expand the area of wireless communication by increasing the data capacity in communication systems and supporting high data rates. However, short wavelengths, due to their high millimeter wave frequencies cause problems arising from signal attenuation and path loss. To address these limitations, research centered on high directional beamforming technology continues to gather interest. Furthermore, due to the mobility of UAVs, it is essential to track the beam angle accurately to obtain full beamforming gain. In this study, we propose a beam tracking method based on the unscented Kalman filter using hybrid beamforming. By expanding analog beamforming to hybrid beamforming, our proposed algorithm can be used even in multi-user and multi-stream environments, increasing the data capacity, and, thus increasing utilization in new radio multiple-input multiple-output orthogonal frequency diversity multiplexing systems.","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":"130021747","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/ICAIIC57133.2023.10067000
Seulki Kim, Kwi-Ok Kim, Taeyoung Kim
Recently, as the impact of AI technology on society has increased, education to develop students' AI capabilities has been emphasized. Along with the importance of AI technology, the importance of datasets, which are an axis of technological development, is being emphasized, and many studies on datasets for AI are being conducted. In order to provide meaningful AI education to students from an educational perspective, this paper reconstructs libraries to utilize synthetic dataset generation libraries in different classroom instruction environments and confirms the applicability of educational purposes.
{"title":"Development of AI Educational Datasets Library Using Synthetic Dataset Generation Method","authors":"Seulki Kim, Kwi-Ok Kim, Taeyoung Kim","doi":"10.1109/ICAIIC57133.2023.10067000","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067000","url":null,"abstract":"Recently, as the impact of AI technology on society has increased, education to develop students' AI capabilities has been emphasized. Along with the importance of AI technology, the importance of datasets, which are an axis of technological development, is being emphasized, and many studies on datasets for AI are being conducted. In order to provide meaningful AI education to students from an educational perspective, this paper reconstructs libraries to utilize synthetic dataset generation libraries in different classroom instruction environments and confirms the applicability of educational purposes.","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":"114003760","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/ICAIIC57133.2023.10067050
Y. Pramitarini, R. Perdana, Kyusung Shim, Beongku An
In this paper, we propose a novel antenna selection scheme to enhance the secrecy performance in a relay-aided non-orthogonal multiple access (NOMA) network against an eavesdropper. Different from the conventional antenna selection schemes that does not use channel information, the proposed antenna selection scheme can employ each channel information to maximize the main channel capacity and minimize the eaves-dropper channel capacity, respectively. In order to evaluate the secrecy performance, we propose a deep learning (DL)-based framework that can do real-time configuration since the DL-based framework is based on a compact mapping function. In detail, the proposed min-max relay transmit antenna selection (MMRTAS) scheme can improve the secrecy performance compared to that of the benchmark scheme. Numerical results show that the proposed MMRTAS scheme improves the secrecy performance compared to that of the benchmark scheme. The proposed DL-based framework can estimate the main channel and eavesdropper channel capacities for the near user and far user with an accuracy of 99.79%, respectively.
{"title":"Exploiting TAS schemes to Enhance the PHY-security in Cooperative NOMA Networks: A Deep Learning Approach","authors":"Y. Pramitarini, R. Perdana, Kyusung Shim, Beongku An","doi":"10.1109/ICAIIC57133.2023.10067050","DOIUrl":"https://doi.org/10.1109/ICAIIC57133.2023.10067050","url":null,"abstract":"In this paper, we propose a novel antenna selection scheme to enhance the secrecy performance in a relay-aided non-orthogonal multiple access (NOMA) network against an eavesdropper. Different from the conventional antenna selection schemes that does not use channel information, the proposed antenna selection scheme can employ each channel information to maximize the main channel capacity and minimize the eaves-dropper channel capacity, respectively. In order to evaluate the secrecy performance, we propose a deep learning (DL)-based framework that can do real-time configuration since the DL-based framework is based on a compact mapping function. In detail, the proposed min-max relay transmit antenna selection (MMRTAS) scheme can improve the secrecy performance compared to that of the benchmark scheme. Numerical results show that the proposed MMRTAS scheme improves the secrecy performance compared to that of the benchmark scheme. The proposed DL-based framework can estimate the main channel and eavesdropper channel capacities for the near user and far user with an accuracy of 99.79%, respectively.","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":"132051638","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}