Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.05.014
Na-Eun Park, Seo-Yi Kim, Il-Gu Lee
In recent times, the proliferation of intelligent internet of things (IoT) and wireless sensor network (WSN) technologies has significantly enhanced both daily life and industrial operations. Despite their widespread application, these networks face challenges with resource monopolization by selfish nodes, which detrimentally impacts network efficiency. This study introduces a novel detection and response strategy for selfish nodes, utilizing backoff adjustment mechanisms to reduce throughput deterioration. The effectiveness of this approach was rigorously evaluated using the NetSim simulator, focusing on the impact of backoff adjustment on network throughput. Simulation results indicate that the implementation of this method in the presence of selfish nodes yields a noteworthy improvement in network throughput, with approximately more than twice. This advancement holds promise for enhancing the robustness and efficiency of IoT and WSN technologies against disruptive selfish node behaviors.
{"title":"Selfish attack detection and response using cooperative backoff adjustment in wireless sensor networks","authors":"Na-Eun Park, Seo-Yi Kim, Il-Gu Lee","doi":"10.1016/j.icte.2024.05.014","DOIUrl":"10.1016/j.icte.2024.05.014","url":null,"abstract":"<div><div>In recent times, the proliferation of intelligent internet of things (IoT) and wireless sensor network (WSN) technologies has significantly enhanced both daily life and industrial operations. Despite their widespread application, these networks face challenges with resource monopolization by selfish nodes, which detrimentally impacts network efficiency. This study introduces a novel detection and response strategy for selfish nodes, utilizing backoff adjustment mechanisms to reduce throughput deterioration. The effectiveness of this approach was rigorously evaluated using the NetSim simulator, focusing on the impact of backoff adjustment on network throughput. Simulation results indicate that the implementation of this method in the presence of selfish nodes yields a noteworthy improvement in network throughput, with approximately more than twice. This advancement holds promise for enhancing the robustness and efficiency of IoT and WSN technologies against disruptive selfish node behaviors.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1295-1300"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141277986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.07.003
Huifen Huang , Xinchang Zhang
Industrial data transfer must rapidly recover from possible link failures to ensure reliability. The backup path mechanism is one of the transfer protections against multiple link failures. In this paper, we study a reliability-satisfied and hop-constrained backup path model that strives to reduce network capacity consumption under constraints on the reliability and maximum hop number of the backup path. The constraint on the maximum hop number is used to ensure the reliability and delay of a backup path. We propose an approximation algorithm to solve the dynamic backup path arrangement problem that is NP-hard.
{"title":"Toward reliability-satisfied and hop-constrained backup paths for industrial internet demands","authors":"Huifen Huang , Xinchang Zhang","doi":"10.1016/j.icte.2024.07.003","DOIUrl":"10.1016/j.icte.2024.07.003","url":null,"abstract":"<div><div>Industrial data transfer must rapidly recover from possible link failures to ensure reliability. The backup path mechanism is one of the transfer protections against multiple link failures. In this paper, we study a reliability-satisfied and hop-constrained backup path model that strives to reduce network capacity consumption under constraints on the reliability and maximum hop number of the backup path. The constraint on the maximum hop number is used to ensure the reliability and delay of a backup path. We propose an approximation algorithm to solve the dynamic backup path arrangement problem that is NP-hard.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1273-1279"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141699269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.07.002
Usman Iqbal , Yejin Lee , Sunghwan Cho , In-Ho Lee , Haejoon Jung
Unmanned aerial vehicles (UAVs) emerge as versatile aerial nodes capable of dynamically filling coverage gaps and enabling mission-critical communication based on their mobile nature. UAV swarms, characterized by the coordinated operation of multiple drones, are employed for a wide range of applications such as surveillance, environmental monitoring, precision farming, and autonomous delivery. While individual UAVs suffer from limited power, group transmissions of UAV swarms can enhance the data rate, reliability, and energy efficiency. However, their mobility may cause severe Doppler spread. The existing orthogonal frequency division multiplexing (OFDM) system exhibits limitations such as susceptibility to the Doppler effect in high-speed mobile environments. To address this issue, orthogonal time–frequency space (OTFS)-aided cooperative transmission (CT) for UAV swarms is considered, which can surmount the aforementioned limitations. The results show the BER improvement of the order of at the SNR value of 10 dB when OTFS modulation is utilized and even better at the higher SNR values. Furthermore, the analytical framework of OTFS-based CT is presented by identifying the key design considerations on the subcarrier spacing, the number of symbols, and the number of subcarriers, which are subject to the maximum speed of the UAV and the cluster size of the UAV swarm. These results provide a significant platform for advancing research in the field of UAV-based CT, especially with the Doppler-resilient OTFS modulation.
{"title":"Cooperative transmission of UAV swarm using orthogonal time–frequency space modulation","authors":"Usman Iqbal , Yejin Lee , Sunghwan Cho , In-Ho Lee , Haejoon Jung","doi":"10.1016/j.icte.2024.07.002","DOIUrl":"10.1016/j.icte.2024.07.002","url":null,"abstract":"<div><div>Unmanned aerial vehicles (UAVs) emerge as versatile aerial nodes capable of dynamically filling coverage gaps and enabling mission-critical communication based on their mobile nature. UAV swarms, characterized by the coordinated operation of multiple drones, are employed for a wide range of applications such as surveillance, environmental monitoring, precision farming, and autonomous delivery. While individual UAVs suffer from limited power, group transmissions of UAV swarms can enhance the data rate, reliability, and energy efficiency. However, their mobility may cause severe Doppler spread. The existing orthogonal frequency division multiplexing (OFDM) system exhibits limitations such as susceptibility to the Doppler effect in high-speed mobile environments. To address this issue, orthogonal time–frequency space (OTFS)-aided cooperative transmission (CT) for UAV swarms is considered, which can surmount the aforementioned limitations. The results show the BER improvement of the order of <span><math><mrow><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mn>3</mn></mrow></msup></mrow></math></span> at the SNR value of 10 dB when OTFS modulation is utilized and even better at the higher SNR values. Furthermore, the analytical framework of OTFS-based CT is presented by identifying the key design considerations on the subcarrier spacing, the number of symbols, and the number of subcarriers, which are subject to the maximum speed of the UAV and the cluster size of the UAV swarm. These results provide a significant platform for advancing research in the field of UAV-based CT, especially with the Doppler-resilient OTFS modulation.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1240-1246"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141696120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.10.006
Asma Ul Hussna , Risul Islam , Md Golam Rabiul Alam , Jia Uddin , Imran Ashraf , Md Abdus Samad
This study explores the global problem of misinformation dissemination on social media, particularly Twitter, due to the COVID-19 pandemic. It identifies prominent disseminators, investigates the spread of false information and the ecosystem of disinformation spreaders, and assesses their online personalities. We track the interaction among fake news spreaders using the User–User Interaction Graph. The study reveals a rapidly growing population of disseminators, including professional spreaders, with over 3% dominating the others. The collaboration among fake news spreaders is high, highlighting the need for further research using publicly available online data to understand the community spreading malicious misinformation about COVID-19.
{"title":"A graph mining-based approach to analyze the dynamics of the Twitter community of COVID-19 misinformation disseminators","authors":"Asma Ul Hussna , Risul Islam , Md Golam Rabiul Alam , Jia Uddin , Imran Ashraf , Md Abdus Samad","doi":"10.1016/j.icte.2024.10.006","DOIUrl":"10.1016/j.icte.2024.10.006","url":null,"abstract":"<div><div>This study explores the global problem of misinformation dissemination on social media, particularly Twitter, due to the COVID-19 pandemic. It identifies prominent disseminators, investigates the spread of false information and the ecosystem of disinformation spreaders, and assesses their online personalities. We track the interaction among fake news spreaders using the User–User Interaction Graph. The study reveals a rapidly growing population of disseminators, including professional spreaders, with over 3% dominating the others. The collaboration among fake news spreaders is high, highlighting the need for further research using publicly available online data to understand the community spreading malicious misinformation about COVID-19.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1280-1287"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143094142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.07.004
Siti Hasunah Mohammad , Yeon Ho Chung , Sudhanshu Arya
The orthogonality characteristics of orbital angular momentum (OAM) can provide a new degree of freedom for optical wireless communication (OWC) systems. By transmitting multiple different orders of OAM states within a single beam, multiple data channels can be carried to the end users simultaneously. As the value of the OAM state increases to a higher order, the conventional single OAM state beam suffers from destructive interference due to decreasing intensity and increasing divergence angle as the beam spreads out. In this paper, we propose a novel OAM beamforming technique for an indoor multiuser OWC network using weighted impulse response, based on the sum of intensity contributions of superposed multiple OAM states carrying Laguerre-Gaussian (LG) ultraviolet (UV) beams. The proposed OAM beamforming method is shown to reduce the destructive interference at the dark region of the beam and to increase the amplitude of intensity distribution of the beamformed OAM states. Consequently, the proposed method shows better performance with increasing OAM states beamformed together in the OWC channel, compared to a conventional single OAM state LG UV beam.
{"title":"Orbital angular momentum beamforming techniques for indoor multiuser optical wireless communications","authors":"Siti Hasunah Mohammad , Yeon Ho Chung , Sudhanshu Arya","doi":"10.1016/j.icte.2024.07.004","DOIUrl":"10.1016/j.icte.2024.07.004","url":null,"abstract":"<div><div>The orthogonality characteristics of orbital angular momentum (OAM) can provide a new degree of freedom for optical wireless communication (OWC) systems. By transmitting multiple different orders of OAM states within a single beam, multiple data channels can be carried to the end users simultaneously. As the value of the OAM state increases to a higher order, the conventional single OAM state beam suffers from destructive interference due to decreasing intensity and increasing divergence angle as the beam spreads out. In this paper, we propose a novel OAM beamforming technique for an indoor multiuser OWC network using weighted impulse response, based on the sum of intensity contributions of superposed multiple OAM states carrying Laguerre-Gaussian (LG) ultraviolet (UV) beams. The proposed OAM beamforming method is shown to reduce the destructive interference at the dark region of the beam and to increase the amplitude of intensity distribution of the beamformed OAM states. Consequently, the proposed method shows better performance with increasing OAM states beamformed together in the OWC channel, compared to a conventional single OAM state LG UV beam.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1220-1225"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141709492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.09.001
Chanin Eom , Dongsu Lee , Minhae Kwon
Deep reinforcement learning (RL) has emerged as a promising solution for autonomous devices requiring sequential decision-making. In the online RL framework, the agent must interact with the environment to collect data, making sample efficiency the most challenging aspect. While the off-policy method in online RL partially addresses this issue by employing a replay buffer, learning speed remains slow, particularly at the beginning of training, due to the low quality of data collected with the initial policy. To overcome this challenge, we propose Reward-Adaptive Pre-collected Data RL (RAPD-RL), which leverages pre-collected data in addition to online RL. We employ two buffers: one for pre-collected data and another for online collected data. The policy is trained using both buffers to increase the objective and imitate the actions in the dataset. To maintain resistance to poor-quality (i.e., low-reward) data, our method selectively imitates data based on reward information, thereby enhancing sample efficiency and learning speed. Simulation results demonstrate that the proposed solution converges rapidly and achieves high performance across various dataset qualities.
{"title":"Selective imitation for efficient online reinforcement learning with pre-collected data","authors":"Chanin Eom , Dongsu Lee , Minhae Kwon","doi":"10.1016/j.icte.2024.09.001","DOIUrl":"10.1016/j.icte.2024.09.001","url":null,"abstract":"<div><div>Deep reinforcement learning (RL) has emerged as a promising solution for autonomous devices requiring sequential decision-making. In the online RL framework, the agent must interact with the environment to collect data, making sample efficiency the most challenging aspect. While the off-policy method in online RL partially addresses this issue by employing a replay buffer, learning speed remains slow, particularly at the beginning of training, due to the low quality of data collected with the initial policy. To overcome this challenge, we propose Reward-Adaptive Pre-collected Data RL (RAPD-RL), which leverages pre-collected data in addition to online RL. We employ two buffers: one for pre-collected data and another for online collected data. The policy is trained using both buffers to increase the <span><math><mi>Q</mi></math></span> objective and imitate the actions in the dataset. To maintain resistance to poor-quality (i.e., low-reward) data, our method selectively imitates data based on reward information, thereby enhancing sample efficiency and learning speed. Simulation results demonstrate that the proposed solution converges rapidly and achieves high performance across various dataset qualities.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1308-1314"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143094082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.06.004
Donghyeon Kim , Jung-Bin Kim , Haejoon Jung , In-Ho Lee
In the heterogeneous network (HetNet) employing downlink non-orthogonal multiple access (NOMA), we focus on the non-convex optimization problem to optimize the spectral efficiency (SE) while the users satisfy the quality-of-service (QoS) requirement. In the previous work, the optimal joint successive interference cancellation and power allocation (JSPA) algorithm for maximizing SE is proposed to solve the mixed-integer non-linear programming (MINLP) problem in NOMA-enabled HetNet. However, the optimal solution requires exponential complexity by the number of base stations (BSs). Therefore, we present a deep neural network (DNN)-based algorithm for JSPA to reduce the complexity. In particular, to deal with the MINLP-based JSPA problem, we reformulate it into an equivalently simple problem that optimizes only the power consumption of BSs. Then, we introduce the unsupervised DNN-based method for JSPA to handle the simplified problem. The presented scheme yields improved SE and outage performance compared with traditional DNN-based methods. Additionally, we propose a user selection scheme with low complexity to enhance the SE of the proposed DNN-based power allocation. Through simulations, we illustrate that the suggested DNN-based scheme can attain SE performance similar to that of the optimal scheme.
{"title":"DNN-based algorithm for joint SIC ordering and power allocation in downlink NOMA-enabled heterogeneous networks","authors":"Donghyeon Kim , Jung-Bin Kim , Haejoon Jung , In-Ho Lee","doi":"10.1016/j.icte.2024.06.004","DOIUrl":"10.1016/j.icte.2024.06.004","url":null,"abstract":"<div><div>In the heterogeneous network (HetNet) employing downlink non-orthogonal multiple access (NOMA), we focus on the non-convex optimization problem to optimize the spectral efficiency (SE) while the users satisfy the quality-of-service (QoS) requirement. In the previous work, the optimal joint successive interference cancellation and power allocation (JSPA) algorithm for maximizing SE is proposed to solve the mixed-integer non-linear programming (MINLP) problem in NOMA-enabled HetNet. However, the optimal solution requires exponential complexity by the number of base stations (BSs). Therefore, we present a deep neural network (DNN)-based algorithm for JSPA to reduce the complexity. In particular, to deal with the MINLP-based JSPA problem, we reformulate it into an equivalently simple problem that optimizes only the power consumption of BSs. Then, we introduce the unsupervised DNN-based method for JSPA to handle the simplified problem. The presented scheme yields improved SE and outage performance compared with traditional DNN-based methods. Additionally, we propose a user selection scheme with low complexity to enhance the SE of the proposed DNN-based power allocation. Through simulations, we illustrate that the suggested DNN-based scheme can attain SE performance similar to that of the optimal scheme.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1301-1307"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143094083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.10.007
Amenah S.M. Thabit , Chaker Abdelaziz Kerrache , Carlos T. Calafate
Nowadays, the rise in traffic density derived from the population growth in urban areas, has resulted in more traffic congestion. Despite advancements in Intelligent Transportation Systems (ITS), this still remains a considerable challenge. In this study, we provide a comprehensive survey of monitoring and management of traffic systems (MMTS) techniques. At first, we split the whole scope of research into four phases: (i) traffic data gathering, (ii) traffic data transmission, (iii) traffic data analysis, and finally (iv) traffic data dissemination. Furthermore, we discuss the security aspects of traffic monitoring and management, and discuss emerging research challenges and opportunities.
{"title":"A survey on monitoring and management techniques for road traffic congestion in vehicular networks","authors":"Amenah S.M. Thabit , Chaker Abdelaziz Kerrache , Carlos T. Calafate","doi":"10.1016/j.icte.2024.10.007","DOIUrl":"10.1016/j.icte.2024.10.007","url":null,"abstract":"<div><div>Nowadays, the rise in traffic density derived from the population growth in urban areas, has resulted in more traffic congestion. Despite advancements in Intelligent Transportation Systems (ITS), this still remains a considerable challenge. In this study, we provide a comprehensive survey of monitoring and management of traffic systems (MMTS) techniques. At first, we split the whole scope of research into four phases: (i) traffic data gathering, (ii) traffic data transmission, (iii) traffic data analysis, and finally (iv) traffic data dissemination. Furthermore, we discuss the security aspects of traffic monitoring and management, and discuss emerging research challenges and opportunities.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1186-1198"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143102794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.09.014
Jeonghwan Kim, Jeongho Kwak
Despite the rapid growth of the Internet industry, the provision of full Internet service to remote regions is still challenging. As a solution, the combination of Low Earth Orbit (LEO) satellite communication and Mobile Edge Computing (MEC) is gaining attention. However, considering the high speed of LEO satellites in network environments remains a significant challenge. To this end, this paper introduces a dynamic computation offloading and resource allocation framework in the LEO satellite MEC architecture. Using Lyapunov optimization, we propose an efficient DCOOL algorithm to minimize average power consumption and propagation delay constrained by queue stability. Finally, comparative analysis and simulations demonstrate the superior performance of DCOOL while achieving lower power consumption and stable workload processing.
{"title":"DCOOL: Dynamic computation offloading and resource allocation for LEO satellite-assisted edge computing in a ground-space integrated framework","authors":"Jeonghwan Kim, Jeongho Kwak","doi":"10.1016/j.icte.2024.09.014","DOIUrl":"10.1016/j.icte.2024.09.014","url":null,"abstract":"<div><div>Despite the rapid growth of the Internet industry, the provision of full Internet service to remote regions is still challenging. As a solution, the combination of Low Earth Orbit (LEO) satellite communication and Mobile Edge Computing (MEC) is gaining attention. However, considering the high speed of LEO satellites in network environments remains a significant challenge. To this end, this paper introduces a dynamic computation offloading and resource allocation framework in the LEO satellite MEC architecture. Using Lyapunov optimization, we propose an efficient <em>DCOOL</em> algorithm to minimize average power consumption and propagation delay constrained by queue stability. Finally, comparative analysis and simulations demonstrate the superior performance of <em>DCOOL</em> while achieving lower power consumption and stable workload processing.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1212-1219"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143094080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.icte.2024.09.008
Rokas Gipiškis , Chun-Wei Tsai , Olga Kurasova
Explainable AI (XAI) has found numerous applications in computer vision. While image classification-based explainability techniques have garnered significant attention, their counterparts in semantic segmentation have been relatively neglected. Given the prevalent use of image segmentation, ranging from medical to industrial deployments, these techniques warrant a systematic look. In this paper, we present the first comprehensive survey on XAI in semantic image segmentation. We analyze and categorize the literature based on application categories and domains, as well as the evaluation metrics and datasets used. We also propose a taxonomy for interpretable semantic segmentation, and discuss potential challenges and future research directions.
{"title":"Explainable AI (XAI) in image segmentation in medicine, industry, and beyond: A survey","authors":"Rokas Gipiškis , Chun-Wei Tsai , Olga Kurasova","doi":"10.1016/j.icte.2024.09.008","DOIUrl":"10.1016/j.icte.2024.09.008","url":null,"abstract":"<div><div>Explainable AI (XAI) has found numerous applications in computer vision. While image classification-based explainability techniques have garnered significant attention, their counterparts in semantic segmentation have been relatively neglected. Given the prevalent use of image segmentation, ranging from medical to industrial deployments, these techniques warrant a systematic look. In this paper, we present the first comprehensive survey on XAI in semantic image segmentation. We analyze and categorize the literature based on application categories and domains, as well as the evaluation metrics and datasets used. We also propose a taxonomy for interpretable semantic segmentation, and discuss potential challenges and future research directions.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"10 6","pages":"Pages 1331-1354"},"PeriodicalIF":4.1,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143094085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号