Pub Date : 2026-02-01DOI: 10.1016/j.icte.2025.11.017
Seungseok Sin , Sangmi Moon , Cheol Hong Kim , Intae Hwang
Accurate localization is essential for next-generation wireless systems. Traditional millimeter-wave (mmWave) techniques rely heavily on line-of-sight (LOS) paths, which limits their performance in non-line-of-sight (NLOS) environments. To overcome this challenge, we propose a non-terrestrial network (NTN) framework that employs an unmanned aerial vehicle–mounted reconfigurable intelligent surface (UAV-RIS) in conjunction with a Transformer-based refinement model. Unlike conventional regression or filtering approaches, the Transformer leverages self-attention mechanisms to refine coarse geometric estimates. Simulations using the DeepMIMO dataset show that more than 90% of users achieve sub-meter localization accuracy, representing a 35% improvement over existing baselines. These results demonstrate the novelty and effectiveness of integrating RIS adaptability with Transformer-based learning to enable robust, high-precision localization.
Pub Date : 2026-02-01DOI: 10.1016/j.icte.2025.11.013
Li Wang , Jun Kit Chaw , Mei Choo Ang , Xiang Cheng , Halimah Badioze Zaman , Saraswathy Shamini Gunasekaran , Moamin A. Mahmoud
Deploying deep learning models for predictive maintenance (PdM) is often constrained by high computational costs, limiting real-time industrial deployment. Knowledge distillation (KD) offers a lightweight alternative by transferring knowledge from large teachers to compact students. Despite growing research on KD in PdM, no systematic review has consolidated existing progress. This paper fills that gap by analyzing 48 KD-based PdM studies, identifying six key paradigms and analyzing their efficiency–accuracy trade-offs. This review highlights unresolved challenges and outlines future directions toward adaptive, cross-domain, and resource-efficient KD frameworks for intelligent industrial maintenance.
{"title":"A systematic review of knowledge distillation in industrial predictive maintenance: Applications, methods and challenges","authors":"Li Wang , Jun Kit Chaw , Mei Choo Ang , Xiang Cheng , Halimah Badioze Zaman , Saraswathy Shamini Gunasekaran , Moamin A. Mahmoud","doi":"10.1016/j.icte.2025.11.013","DOIUrl":"10.1016/j.icte.2025.11.013","url":null,"abstract":"<div><div>Deploying deep learning models for predictive maintenance (PdM) is often constrained by high computational costs, limiting real-time industrial deployment. Knowledge distillation (KD) offers a lightweight alternative by transferring knowledge from large teachers to compact students. Despite growing research on KD in PdM, no systematic review has consolidated existing progress. This paper fills that gap by analyzing 48 KD-based PdM studies, identifying six key paradigms and analyzing their efficiency–accuracy trade-offs. This review highlights unresolved challenges and outlines future directions toward adaptive, cross-domain, and resource-efficient KD frameworks for intelligent industrial maintenance.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 147-167"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01DOI: 10.1016/j.icte.2026.01.005
Sumesh Kharnotia , Bhavna Arora , Ravdeep Kour
The extensive embrace of Android has amplified malware risks, resulting in a need for better detection methods. This article investigates the area of static analysis, which analyses applications without execution by examining code and manifest files. We focus on studies from 2022 to 2025, regarding the feature extraction, datasets, feature selection, and approaches based on Machine Learning (ML) and Deep Learning (DL). We conclude by defining the major limitations and research gaps presented in studies regarding static analysis, and many insights for potential development of detection models that are efficient, accurate, and lightweight to improve detection patterns of Android malware.
{"title":"Feature-driven static analysis for learning-based android malware detection: A review","authors":"Sumesh Kharnotia , Bhavna Arora , Ravdeep Kour","doi":"10.1016/j.icte.2026.01.005","DOIUrl":"10.1016/j.icte.2026.01.005","url":null,"abstract":"<div><div>The extensive embrace of Android has amplified malware risks, resulting in a need for better detection methods. This article investigates the area of static analysis, which analyses applications without execution by examining code and manifest files. We focus on studies from 2022 to 2025, regarding the feature extraction, datasets, feature selection, and approaches based on Machine Learning (ML) and Deep Learning (DL). We conclude by defining the major limitations and research gaps presented in studies regarding static analysis, and many insights for potential development of detection models that are efficient, accurate, and lightweight to improve detection patterns of Android malware.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 186-208"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01DOI: 10.1016/j.icte.2025.11.002
Dong Hyuck Woo , Ho Young Hwang
As the number of devices in the Internet of Things (IoT) continues to grow, security threats from suspicious communications have become a critical concern. This paper proposes a quality-of-service (QoS)-aware energy-efficient attack scheme that degrades the performance of suspicious devices through eavesdropping and jamming while preserving the QoS of legitimate devices. The scheme optimizes the attacker’s power to maximize attacker energy efficiency (AEE) under QoS constraints. Additionally, the model is extended to multicast scenarios with multiple legitimate receivers. Analytical and simulation results validate the accuracy of the model, demonstrating the scheme’s effectiveness in achieving high energy efficiency without compromising legitimate QoS.
{"title":"QoS-aware energy-efficient attacks in IoT: Eavesdropping and jamming with power optimization for single and multicast receiver scenarios","authors":"Dong Hyuck Woo , Ho Young Hwang","doi":"10.1016/j.icte.2025.11.002","DOIUrl":"10.1016/j.icte.2025.11.002","url":null,"abstract":"<div><div>As the number of devices in the Internet of Things (IoT) continues to grow, security threats from suspicious communications have become a critical concern. This paper proposes a quality-of-service (QoS)-aware energy-efficient attack scheme that degrades the performance of suspicious devices through eavesdropping and jamming while preserving the QoS of legitimate devices. The scheme optimizes the attacker’s power to maximize attacker energy efficiency (AEE) under QoS constraints. Additionally, the model is extended to multicast scenarios with multiple legitimate receivers. Analytical and simulation results validate the accuracy of the model, demonstrating the scheme’s effectiveness in achieving high energy efficiency without compromising legitimate QoS.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 267-272"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01DOI: 10.1016/j.icte.2025.11.021
Hyunjin Jo, Nilesh Maharjan, Byung Wook Kim
This paper presents a robust vehicle detection method for Low Earth Orbit satellite imagery degraded by environmental factors. To enhance feature representation from RGB and IR images, a denoising autoencoder and a multimodal fusion (MF) module with multi-head squeeze excitation are used. To compensate for texture loss in small vehicles at low resolution, a spatial attention module (SAM) is embedded into the YOLOv5 backbone, and a modified wide activation super-resolution (WDSR) branch is attached for learning finer-grained representations. Experiments on degraded images show that the proposed model outperforms the YOLO series and SuperYOLO in terms of mean average precision (mAP).
{"title":"Spatial attention and wide activation-based deep super-resolution scheme for vehicle detection in noisy and low-resolution LEO satellite imagery","authors":"Hyunjin Jo, Nilesh Maharjan, Byung Wook Kim","doi":"10.1016/j.icte.2025.11.021","DOIUrl":"10.1016/j.icte.2025.11.021","url":null,"abstract":"<div><div>This paper presents a robust vehicle detection method for Low Earth Orbit satellite imagery degraded by environmental factors. To enhance feature representation from RGB and IR images, a denoising autoencoder and a multimodal fusion (MF) module with multi-head squeeze excitation are used. To compensate for texture loss in small vehicles at low resolution, a spatial attention module (SAM) is embedded into the YOLOv5 backbone, and a modified wide activation super-resolution (WDSR) branch is attached for learning finer-grained representations. Experiments on degraded images show that the proposed model outperforms the YOLO series and SuperYOLO in terms of mean average precision (mAP).</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 26-31"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01DOI: 10.1016/j.icte.2025.11.018
Victor Ikenna Kanu, Simeon Okechukwu Ajakwe, Jae Min Lee, Dong-Seong Kim
Reproducibility is a critical issue in protein structure analysis, especially in drug discovery workflows. Previous methods do not consistently produce reliable results across systems and do not provide deterministic outcomes in protein analysis. This work proposes a tri-layered blockchain-inspired architecture that leverages cryptographic metadata and capabilities to validate protonation states and guarantee deterministic results and data integrity across protein structure preparation and ensure reproducible binding site analysis. The results show 100% reproducibility with a 1745.1% performance overhead with execution time still under 11 s, enhancing data security and offering a reliable solution for computational drug discovery workflows. This system enhances confidence in computational drug discovery workflows.
{"title":"Deterministic protein structure and binding site analysis through blockchain-integrated workflow verification","authors":"Victor Ikenna Kanu, Simeon Okechukwu Ajakwe, Jae Min Lee, Dong-Seong Kim","doi":"10.1016/j.icte.2025.11.018","DOIUrl":"10.1016/j.icte.2025.11.018","url":null,"abstract":"<div><div>Reproducibility is a critical issue in protein structure analysis, especially in drug discovery workflows. Previous methods do not consistently produce reliable results across systems and do not provide deterministic outcomes in protein analysis. This work proposes a tri-layered blockchain-inspired architecture that leverages cryptographic metadata and capabilities to validate protonation states and guarantee deterministic results and data integrity across protein structure preparation and ensure reproducible binding site analysis. The results show 100% reproducibility with a 1745.1% performance overhead with execution time still under 11 s, enhancing data security and offering a reliable solution for computational drug discovery workflows. This system enhances confidence in computational drug discovery workflows.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 83-91"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01DOI: 10.1016/j.icte.2025.10.008
Jiaqi Li, Seung-Hoon Hwang
In this paper, the architecture and mechanism of 5G New Radio indoor positioning schemes such as downlink time difference of arrival (DL-TDOA), uplink (UL) TDOA, multiple-cell round trip time (Multi-RTT), DL angle of departure, UL angle of arrival (AOA), and enhanced cell-ID, are comprehensively described. In addition, their performances are investigated under different channel bandwidths and conditions, and antenna configurations. Numerical results show the time-based schemes provide more benefit by wider bandwidth, while the angle-based schemes give gains by more antenna elements. Note that the Multi-RTT achieves the best accuracy with line-of-sight (LOS) conditions, while the UL-AOA does with non-LOS.
{"title":"Indoor positioning in 5G new radio: how it works, status quo of research, and the road ahead","authors":"Jiaqi Li, Seung-Hoon Hwang","doi":"10.1016/j.icte.2025.10.008","DOIUrl":"10.1016/j.icte.2025.10.008","url":null,"abstract":"<div><div>In this paper, the architecture and mechanism of 5G New Radio indoor positioning schemes such as downlink time difference of arrival (DL-TDOA), uplink (UL) TDOA, multiple-cell round trip time (Multi-RTT), DL angle of departure, UL angle of arrival (AOA), and enhanced cell-ID, are comprehensively described. In addition, their performances are investigated under different channel bandwidths and conditions, and antenna configurations. Numerical results show the time-based schemes provide more benefit by wider bandwidth, while the angle-based schemes give gains by more antenna elements. Note that the Multi-RTT achieves the best accuracy with line-of-sight (LOS) conditions, while the UL-AOA does with non-LOS.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 223-248"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sixth generation (6G) wireless networks are poised to revolutionize connectivity by integrating terrestrial, aerial, and satellite communication segments into a unified 3D architecture. However, this integration introduces unprecedented challenges in mobility management due to the dynamic and heterogeneous nature of the network. The high mobility of low earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and ground users requires frequent and seamless handovers, complicating channel estimation, resource allocation, and routing. These challenges arise from the rapid relative motion between network entities, leading to time-varying channels, Doppler shifts, and unpredictable visibility windows. In addition, the diverse operational altitudes and energy constraints of UAVs further complicate trajectory planning and energy-efficient operation. This paper provides a comprehensive analysis of these mobility management challenges, exploring their underlying causes and importance in ensuring reliable, low-latency communication in 6G networks. We examine key techniques such as time-varying channel estimation, dynamic resource allocation, seamless handovers, energy-aware UAV trajectory planning, and 3D dynamic routing. A case study demonstrates joint optimization of the UAV trajectory and satellite handovers using online learning, showcasing the role of AI in addressing these issues. The paper concludes with a discussion on future directions, including the need for distributed mobility management architectures, mobility-aware modulation schemes, and proactive handover strategies, all critical for realizing the full potential of 6G networks.
{"title":"Mobility management in 3D unified 6G networks: Challenges, opportunities and future directions","authors":"Ehab Mahmoud Mohamed , Sherief Hashima , Kohei Hatano , Mohamed Rihan","doi":"10.1016/j.icte.2025.11.011","DOIUrl":"10.1016/j.icte.2025.11.011","url":null,"abstract":"<div><div>Sixth generation (6G) wireless networks are poised to revolutionize connectivity by integrating terrestrial, aerial, and satellite communication segments into a unified 3D architecture. However, this integration introduces unprecedented challenges in mobility management due to the dynamic and heterogeneous nature of the network. The high mobility of low earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and ground users requires frequent and seamless handovers, complicating channel estimation, resource allocation, and routing. These challenges arise from the rapid relative motion between network entities, leading to time-varying channels, Doppler shifts, and unpredictable visibility windows. In addition, the diverse operational altitudes and energy constraints of UAVs further complicate trajectory planning and energy-efficient operation. This paper provides a comprehensive analysis of these mobility management challenges, exploring their underlying causes and importance in ensuring reliable, low-latency communication in 6G networks. We examine key techniques such as time-varying channel estimation, dynamic resource allocation, seamless handovers, energy-aware UAV trajectory planning, and 3D dynamic routing. A case study demonstrates joint optimization of the UAV trajectory and satellite handovers using online learning, showcasing the role of AI in addressing these issues. The paper concludes with a discussion on future directions, including the need for distributed mobility management architectures, mobility-aware modulation schemes, and proactive handover strategies, all critical for realizing the full potential of 6G networks.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 255-266"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01DOI: 10.1016/j.icte.2025.11.024
Dhiraj P. Tulaskar , Battina Sindhu , Nitin Chakole , Rina Parteki , A. Anny Leema , P. Balakrishnan , Ankita Avthanka , Rangnath Girhe , Madhusudan B. Kulkarni , Manish Bhaiyya
Artificial Intelligence (AI) and Machine Learning (ML) technologies are becoming more important in wireless telecommunications networks, especially in the transition from 5G to 6G, a more advanced AI networking environment. While in 5G networks AI is used basically to get better performance from the individual tasks, in 6G, AI will be a model that is used at each layer of the system design-from the physical retransmission of the signals right through to the management of the services. The paper will examine the advanced AI technologies of Deep Learning, Reinforcement Learning, Generative Models, and Federated Learning, and their impact on core processes in the networking framework like beamforming, channel estimation, spectrum access, and anomaly detection which are evaluated against core metrics of accuracy, latency, power consumption, privacy, and comprehensibility. In the process of going beyond technical detail, the review situates AI-based wireless innovations in different fields including autonomous vehicles, telesurgery, industrial IoT, and smart cities. It also points out the persistent challenges, such as data scarcity, real-time inference, edge deployment, and ethical concerns, and presents some promising future research directions, including digital twins, AI–quantum convergence, and regulatory frameworks. This work presents a strategic roadmap to achieve scalable, secure, and intelligent 6G networks by providing a cross-layer and cross-domain synthesis.
{"title":"AI and ML empowering 5G and shaping the 6G future: Models, metrics, architectures, and applications","authors":"Dhiraj P. Tulaskar , Battina Sindhu , Nitin Chakole , Rina Parteki , A. Anny Leema , P. Balakrishnan , Ankita Avthanka , Rangnath Girhe , Madhusudan B. Kulkarni , Manish Bhaiyya","doi":"10.1016/j.icte.2025.11.024","DOIUrl":"10.1016/j.icte.2025.11.024","url":null,"abstract":"<div><div>Artificial Intelligence (AI) and Machine Learning (ML) technologies are becoming more important in wireless telecommunications networks, especially in the transition from 5G to 6G, a more advanced AI networking environment. While in 5G networks AI is used basically to get better performance from the individual tasks, in 6G, AI will be a model that is used at each layer of the system design-from the physical retransmission of the signals right through to the management of the services. The paper will examine the advanced AI technologies of Deep Learning, Reinforcement Learning, Generative Models, and Federated Learning, and their impact on core processes in the networking framework like beamforming, channel estimation, spectrum access, and anomaly detection which are evaluated against core metrics of accuracy, latency, power consumption, privacy, and comprehensibility. In the process of going beyond technical detail, the review situates AI-based wireless innovations in different fields including autonomous vehicles, telesurgery, industrial IoT, and smart cities. It also points out the persistent challenges, such as data scarcity, real-time inference, edge deployment, and ethical concerns, and presents some promising future research directions, including digital twins, AI–quantum convergence, and regulatory frameworks. This work presents a strategic roadmap to achieve scalable, secure, and intelligent 6G networks by providing a cross-layer and cross-domain synthesis.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 111-135"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","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