Pub Date : 2026-02-01DOI: 10.1016/j.icte.2025.08.004
Tae-Yoon Kim , Wonjae Lee , Jae-Hyun Kim
In this letter, we propose a random access channel (RACH)-less conditional handover (RCHO) algorithm that utilizes antenna gain to predict uplink (UL) grant start timing, reducing signaling overhead and enhancing handover (HO) performance in the low Earth orbit (LEO) intra-satellite system. The proposed algorithm mitigates execution timing unpredictability, allowing a user equipment (UE) to HO to any pre-configured target cell while minimizing signaling overhead. We analyze the performance of the proposed RCHO and compare it with basic HO (BHO), conditional HO (CHO), and RCHO without UL grant start timing prediction. Simulation results demonstrate that RCHO achieves comparable or superior HO performance with the lowest latency while reducing overhead by more than 85% compared to conventional RCHO.
{"title":"Enhanced RACH-less conditional handover for LEO intra-satellite system","authors":"Tae-Yoon Kim , Wonjae Lee , Jae-Hyun Kim","doi":"10.1016/j.icte.2025.08.004","DOIUrl":"10.1016/j.icte.2025.08.004","url":null,"abstract":"<div><div>In this letter, we propose a random access channel (RACH)-less conditional handover (RCHO) algorithm that utilizes antenna gain to predict uplink (UL) grant start timing, reducing signaling overhead and enhancing handover (HO) performance in the low Earth orbit (LEO) intra-satellite system. The proposed algorithm mitigates execution timing unpredictability, allowing a user equipment (UE) to HO to any pre-configured target cell while minimizing signaling overhead. We analyze the performance of the proposed RCHO and compare it with basic HO (BHO), conditional HO (CHO), and RCHO without UL grant start timing prediction. Simulation results demonstrate that RCHO achieves comparable or superior HO performance with the lowest latency while reducing overhead by more than 85% compared to conventional RCHO.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 142-146"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154376","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.2025.11.001
Houjin Lu, Seung-Hoon Hwang
Indoor positioning has diverse applications in public safety, industry, and healthcare [1]. This paper presents a robot-assisted data collection method to overcome the inefficiencies of conventional smartphone-based approaches in indoor positioning. By integrating advanced hardware and software optimizations, the robot achieves efficient and comprehensive Wi-Fi RSSI (Received Signal Strength Indicator) data acquisition at reference points (RPs). Experimental results demonstrate that the robot-assisted system achieves a positioning accuracy of 91.92 %, improving accuracy by 1.8 % compared to the smartphone-based method [2], while reducing data collection time by 59 %. The results validate the proposed method’s efficiency, systematization, and effectiveness in improving indoor positioning.
室内定位在公共安全、工业和医疗保健领域有着广泛的应用。本文提出了一种机器人辅助数据收集方法，以克服传统的基于智能手机的室内定位方法的低效率。通过集成先进的硬件和软件优化，机器人在参考点（rp）实现高效全面的Wi-Fi RSSI （Received Signal Strength Indicator，接收信号强度指标）数据采集。实验结果表明，机器人辅助系统的定位精度为91.92%，与基于智能手机的方法[2]相比，定位精度提高了1.8%，数据收集时间减少了59%。结果验证了该方法在改善室内定位方面的高效性、系统性和有效性。
{"title":"Robot-assisted RSSI data collection for indoor fingerprint-based positioning","authors":"Houjin Lu, Seung-Hoon Hwang","doi":"10.1016/j.icte.2025.11.001","DOIUrl":"10.1016/j.icte.2025.11.001","url":null,"abstract":"<div><div>Indoor positioning has diverse applications in public safety, industry, and healthcare [<span><span>1</span></span>]. This paper presents a robot-assisted data collection method to overcome the inefficiencies of conventional smartphone-based approaches in indoor positioning. By integrating advanced hardware and software optimizations, the robot achieves efficient and comprehensive Wi-Fi RSSI (Received Signal Strength Indicator) data acquisition at reference points (RPs). Experimental results demonstrate that the robot-assisted system achieves a positioning accuracy of 91.92 %, improving accuracy by 1.8 % compared to the smartphone-based method [<span><span>2</span></span>], while reducing data collection time by 59 %. The results validate the proposed method’s efficiency, systematization, and effectiveness in improving indoor positioning.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 249-254"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154414","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.2025.12.007
Sparsh Sharma , Mumin Ahmad Khan , Huzaif Mushtaq Mir , Surbhi Sharma
Masked Face Recognition (MFR) has become a critical research area, accelerated by the widespread adoption of facial masks during and after the COVID-19 pandemic. Traditional face recognition systems struggle under partial occlusion, motivating extensive research into specialized techniques capable of recognizing masked faces with high reliability. This survey provides a comprehensive and systematic review of existing work in the field, covering research published from 2021 onward. The study examines the motivations, methodological evolution, and challenges of MFR, focusing on key deep learning–based approaches such as Occlusion-Robust Feature Extraction (ORFE), Occlusion-Aware Face Recognition (OAFR), and Occlusion Recovery-Based Face Recognition (ORBFR). In addition, the survey analyzes commonly used pipelines, loss functions, network architectures, evaluation metrics, and datasets relevant to MFR. A detailed comparative overview of performance results from existing studies is also presented to support benchmarking and methodological selection. Finally, the paper highlights open challenges, emerging trends, and future research directions, such as dataset limitations, model generalization, validation strategies, and ethical considerations, aimed at guiding researchers toward the development of more accurate, robust, and efficient masked face recognition systems.
{"title":"A comprehensive survey on masked face recognition techniques using deep learning: Motivations, research progress, and future challenges","authors":"Sparsh Sharma , Mumin Ahmad Khan , Huzaif Mushtaq Mir , Surbhi Sharma","doi":"10.1016/j.icte.2025.12.007","DOIUrl":"10.1016/j.icte.2025.12.007","url":null,"abstract":"<div><div>Masked Face Recognition (MFR) has become a critical research area, accelerated by the widespread adoption of facial masks during and after the COVID-19 pandemic. Traditional face recognition systems struggle under partial occlusion, motivating extensive research into specialized techniques capable of recognizing masked faces with high reliability. This survey provides a comprehensive and systematic review of existing work in the field, covering research published from 2021 onward. The study examines the motivations, methodological evolution, and challenges of MFR, focusing on key deep learning–based approaches such as Occlusion-Robust Feature Extraction (ORFE), Occlusion-Aware Face Recognition (OAFR), and Occlusion Recovery-Based Face Recognition (ORBFR). In addition, the survey analyzes commonly used pipelines, loss functions, network architectures, evaluation metrics, and datasets relevant to MFR. A detailed comparative overview of performance results from existing studies is also presented to support benchmarking and methodological selection. Finally, the paper highlights open challenges, emerging trends, and future research directions, such as dataset limitations, model generalization, validation strategies, and ethical considerations, aimed at guiding researchers toward the development of more accurate, robust, and efficient masked face recognition systems.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 55-75"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154370","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.2025.09.014
Md Shahriar Nazim, Md Minhazur Rahman, Md Ibne Joha, Yeong Min Jang
With the growing demand for hybrid UAVs, efficient energy management systems (EMS) are becoming increasingly essential. This study proposes a Deep Q-network-based EMS for hybrid UAVs powered by an internal combustion engine and a battery. The EMS optimizes engine efficiency by maintaining operation within its most effective range while the battery supplies additional power as needed. Simulations under dynamically changing conditions demonstrate that the EMS efficiently distributes energy between sources, ensuring reliable power delivery and significantly improving overall efficiency. The proposed system presents a promising approach to enhancing the performance of hybrid UAVs.
{"title":"Optimizing energy efficiency in hybrid UAVs using DQN-based energy management system","authors":"Md Shahriar Nazim, Md Minhazur Rahman, Md Ibne Joha, Yeong Min Jang","doi":"10.1016/j.icte.2025.09.014","DOIUrl":"10.1016/j.icte.2025.09.014","url":null,"abstract":"<div><div>With the growing demand for hybrid UAVs, efficient energy management systems (EMS) are becoming increasingly essential. This study proposes a Deep Q-network-based EMS for hybrid UAVs powered by an internal combustion engine and a battery. The EMS optimizes engine efficiency by maintaining operation within its most effective range while the battery supplies additional power as needed. Simulations under dynamically changing conditions demonstrate that the EMS efficiently distributes energy between sources, ensuring reliable power delivery and significantly improving overall efficiency. The proposed system presents a promising approach to enhancing the performance of hybrid UAVs.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 76-82"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154371","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.2026.01.001
Ali Aouto , Jung-Hyeon Kim , Jae-Min Lee , Dong-Seong Kim
This paper presents BlackNet, a vision-based black ice detection system designed for real-time vehicular safety. Unlike traditional methods that require expensive environmental sensors, BlackNet leverages existing onboard surround-view cameras. The proposed architecture integrates ResNet-style residual connections into a lightweight MobileNetV2 backbone to optimize feature extraction for subtle road surface variations. To enhance visibility in low-light and high-glare conditions, Contrast Limited Adaptive Histogram Equalization (CLAHE) is utilized for image preprocessing. The model was trained and validated on a comprehensive dataset of 15,200 images, achieving an accuracy of 92.4%. We propose a cloud-assisted deployment framework where inference is performed remotely in cloud, overcoming the computational constraints of edge devices. This approach offers a scalable, hardware-efficient solution for autonomous and connected vehicle safety.
{"title":"Vision-based black ice identification using lightweight CNN and CLAHE-enhanced imagery","authors":"Ali Aouto , Jung-Hyeon Kim , Jae-Min Lee , Dong-Seong Kim","doi":"10.1016/j.icte.2026.01.001","DOIUrl":"10.1016/j.icte.2026.01.001","url":null,"abstract":"<div><div>This paper presents BlackNet, a vision-based black ice detection system designed for real-time vehicular safety. Unlike traditional methods that require expensive environmental sensors, BlackNet leverages existing onboard surround-view cameras. The proposed architecture integrates ResNet-style residual connections into a lightweight MobileNetV2 backbone to optimize feature extraction for subtle road surface variations. To enhance visibility in low-light and high-glare conditions, Contrast Limited Adaptive Histogram Equalization (CLAHE) is utilized for image preprocessing. The model was trained and validated on a comprehensive dataset of 15,200 images, achieving an accuracy of 92.4%. We propose a cloud-assisted deployment framework where inference is performed remotely in cloud, overcoming the computational constraints of edge devices. This approach offers a scalable, hardware-efficient solution for autonomous and connected vehicle safety.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 180-185"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154380","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.2026.01.007
Donghee Yi, Sumin Jeong, Suk Chan Kim
We propose a robust joint time of flight and velocity estimation framework for ultrasonic sensing in near-range parking environments, where strong multipath often masks the direct path and degrades the reliability of conventional peak-based methods. The proposed approach integrates a direct-path likelihood function that reconstructs the physically valid first-arrival path and a zero-Doppler residual suppression method eliminating static-reflector clutter in the cross-ambiguity function domain. Simulation results confirm that the method significantly improves robustness under multipath-dominant conditions. The framework is highly suitable for practical automotive ultrasonic sensing systems.
{"title":"Multipath-robust joint ToF and velocity estimation for automotive ultrasonic sensors using Delay–Doppler processing","authors":"Donghee Yi, Sumin Jeong, Suk Chan Kim","doi":"10.1016/j.icte.2026.01.007","DOIUrl":"10.1016/j.icte.2026.01.007","url":null,"abstract":"<div><div>We propose a robust joint time of flight and velocity estimation framework for ultrasonic sensing in near-range parking environments, where strong multipath often masks the direct path and degrades the reliability of conventional peak-based methods. The proposed approach integrates a direct-path likelihood function that reconstructs the physically valid first-arrival path and a zero-Doppler residual suppression method eliminating static-reflector clutter in the cross-ambiguity function domain. Simulation results confirm that the method significantly improves robustness under multipath-dominant conditions. The framework is highly suitable for practical automotive ultrasonic sensing systems.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"12 1","pages":"Pages 209-213"},"PeriodicalIF":4.2,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154398","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 : 2025-12-01DOI: 10.1016/j.icte.2025.11.010
Hanseon Joo , Hayoung Choi , Ook Lee , Minjong Cheon
Kolmogorov–Arnold Networks (KANs) have garnered attention for replacing fixed activation functions with learnable univariate functions, but they exhibit practical limitations, including high computational costs and performance deficits in general classification tasks. In this paper, we propose the Modulation Joint KAN (MJKAN), a novel neural network layer designed to overcome these challenges. MJKAN integrates a FiLM (Feature-wise Linear Modulation)-like mechanism with Radial Basis Function (RBF) activations, creating a hybrid architecture that combines the non-linear expressive power of KANs with the efficiency of Multilayer Perceptrons (MLPs). We empirically validated MJKAN’s performance across a diverse set of benchmarks, including function regression, image classification, and natural language processing. The results demonstrate that MJKAN achieves superior approximation capabilities in function regression tasks, significantly outperforming MLPs, with performance improving as the number of basis functions increases. Conversely, in image and text classification, its performance was competitive with MLPs but revealed a critical dependency on the number of basis functions. We found that a smaller basis size was crucial for better generalization, highlighting that the model’s capacity must be carefully tuned to the complexity of the data to prevent overfitting. In conclusion, MJKAN offers a flexible architecture that inherits the theoretical advantages of KANs while improving computational efficiency and practical viability.
Kolmogorov-Arnold网络（KANs）因用可学习的单变量函数取代固定的激活函数而引起了人们的关注，但它们表现出实际的局限性，包括高计算成本和一般分类任务的性能缺陷。在本文中，我们提出了调制联合KAN (MJKAN)，一种新的神经网络层，旨在克服这些挑战。MJKAN将类似FiLM （Feature-wise Linear Modulation）的机制与径向基函数（RBF）激活集成在一起，创建了一个混合架构，将KANs的非线性表达能力与多层感知器（mlp）的效率相结合。我们通过各种基准测试验证了MJKAN的性能，包括函数回归、图像分类和自然语言处理。结果表明，MJKAN在函数回归任务中实现了优越的近似能力，显著优于mlp，并且随着基函数数量的增加，性能有所提高。相反，在图像和文本分类中，它的性能与mlp相当，但对基函数的数量有很大的依赖性。我们发现，较小的基大小对于更好的泛化至关重要，强调模型的容量必须仔细调整到数据的复杂性，以防止过拟合。综上所述，MJKAN提供了一种灵活的体系结构，它继承了KANs的理论优势，同时提高了计算效率和实际可行性。
{"title":"Bridging KAN and MLP: MJKAN, a hybrid architecture with both efficiency and expressiveness","authors":"Hanseon Joo , Hayoung Choi , Ook Lee , Minjong Cheon","doi":"10.1016/j.icte.2025.11.010","DOIUrl":"10.1016/j.icte.2025.11.010","url":null,"abstract":"<div><div>Kolmogorov–Arnold Networks (KANs) have garnered attention for replacing fixed activation functions with learnable univariate functions, but they exhibit practical limitations, including high computational costs and performance deficits in general classification tasks. In this paper, we propose the Modulation Joint KAN (MJKAN), a novel neural network layer designed to overcome these challenges. MJKAN integrates a FiLM (Feature-wise Linear Modulation)-like mechanism with Radial Basis Function (RBF) activations, creating a hybrid architecture that combines the non-linear expressive power of KANs with the efficiency of Multilayer Perceptrons (MLPs). We empirically validated MJKAN’s performance across a diverse set of benchmarks, including function regression, image classification, and natural language processing. The results demonstrate that MJKAN achieves superior approximation capabilities in function regression tasks, significantly outperforming MLPs, with performance improving as the number of basis functions increases. Conversely, in image and text classification, its performance was competitive with MLPs but revealed a critical dependency on the number of basis functions. We found that a smaller basis size was crucial for better generalization, highlighting that the model’s capacity must be carefully tuned to the complexity of the data to prevent overfitting. In conclusion, MJKAN offers a flexible architecture that inherits the theoretical advantages of KANs while improving computational efficiency and practical viability.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 6","pages":"Pages 1021-1025"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705600","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 : 2025-12-01DOI: 10.1016/j.icte.2025.10.004
Anshika Sharma , Shalli Rani , Mohammad Shabaz
Artificial Intelligence (AI) has been used extensively in all aspects of everyday life among people in recent times. Many techniques utilizing machine learning (ML) and deep learning (DL) models are being presented in this rapidly growing field of study. Most such models are generally regarded as “Black-Box” models since they are intrinsically complex and lack interpretable explanations for their decisions and conclusions. The lack of transparency increases the issue in the field of cybersecurity as implementing critical decisions in a system that cannot provide explanations for itself offers some evident risks. The lack of interpretability and transparency in existing AI techniques would make users distrust the models used to defend against cyberattacks, particularly given the increasingly complex and diverse nature of cyberattacks. Thus, Explainable Artificial Intelligence (XAI) must be utilized to construct cyber security models that are more understandable while keeping high accuracy and that enable users to understand, be reliable, and manage the future of cyber defence systems. This study provides a comprehensive survey of existing literature on using XAI to mitigate these challenges of cybersecurity black-box models. It emphasizes the significance of explainability in boosting faith and transparency in AI-driven systems and presents a thorough taxonomy of XAI techniques and technologies for cybersecurity applications. The study describes the evaluation criteria that are used to evaluate the effectiveness of XAI models, addresses different kinds of attacks like malware, phishing, and network intrusions, and shows how XAI techniques may mitigate these risks by providing a comprehensible understanding of model decisions. Along with the real-world case studies, it also explores the industrial applications of XAI in cybersecurity and examines the challenges in implementing XAI technology. The survey concludes with a review of the limitations of the existing XAI techniques and makes recommendations for future research, such as the requirement for more reliable XAI frameworks that can function in real-time and across a variety of cyber threat situations.
{"title":"A comprehensive review of explainable AI in cybersecurity: Decoding the black box","authors":"Anshika Sharma , Shalli Rani , Mohammad Shabaz","doi":"10.1016/j.icte.2025.10.004","DOIUrl":"10.1016/j.icte.2025.10.004","url":null,"abstract":"<div><div>Artificial Intelligence (AI) has been used extensively in all aspects of everyday life among people in recent times. Many techniques utilizing machine learning (ML) and deep learning (DL) models are being presented in this rapidly growing field of study. Most such models are generally regarded as “Black-Box” models since they are intrinsically complex and lack interpretable explanations for their decisions and conclusions. The lack of transparency increases the issue in the field of cybersecurity as implementing critical decisions in a system that cannot provide explanations for itself offers some evident risks. The lack of interpretability and transparency in existing AI techniques would make users distrust the models used to defend against cyberattacks, particularly given the increasingly complex and diverse nature of cyberattacks. Thus, Explainable Artificial Intelligence (XAI) must be utilized to construct cyber security models that are more understandable while keeping high accuracy and that enable users to understand, be reliable, and manage the future of cyber defence systems. This study provides a comprehensive survey of existing literature on using XAI to mitigate these challenges of cybersecurity black-box models. It emphasizes the significance of explainability in boosting faith and transparency in AI-driven systems and presents a thorough taxonomy of XAI techniques and technologies for cybersecurity applications. The study describes the evaluation criteria that are used to evaluate the effectiveness of XAI models, addresses different kinds of attacks like malware, phishing, and network intrusions, and shows how XAI techniques may mitigate these risks by providing a comprehensible understanding of model decisions. Along with the real-world case studies, it also explores the industrial applications of XAI in cybersecurity and examines the challenges in implementing XAI technology. The survey concludes with a review of the limitations of the existing XAI techniques and makes recommendations for future research, such as the requirement for more reliable XAI frameworks that can function in real-time and across a variety of cyber threat situations.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 6","pages":"Pages 1200-1219"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705492","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 : 2025-12-01DOI: 10.1016/j.icte.2025.09.005
Jung Hoon Lee , Pansoo Kim , Jae-Young Lee , Kyungrak Son
This paper proposes an efficient beamforming technique to mitigate the beam squint effect in wideband low Earth orbit (LEO) satellite communication systems. Based on the dynamic-subarray with fixed-true-time-delays (DS-FTTD) architecture, the proposed method optimizes the beamforming structure for multi-user transmission using statistical channel state information (CSI). Unlike the original DS-FTTD design, which assumes point-to-point communication and relies on instantaneous CSI, the proposed scheme is tailored for the practical constraints of LEO systems. Simulation results demonstrate that the proposed approach significantly improves beamforming gain and system throughput compared to conventional methods.
{"title":"Beamforming for beam-squint effect mitigation in LEO satellite communication systems","authors":"Jung Hoon Lee , Pansoo Kim , Jae-Young Lee , Kyungrak Son","doi":"10.1016/j.icte.2025.09.005","DOIUrl":"10.1016/j.icte.2025.09.005","url":null,"abstract":"<div><div>This paper proposes an efficient beamforming technique to mitigate the beam squint effect in wideband low Earth orbit (LEO) satellite communication systems. Based on the dynamic-subarray with fixed-true-time-delays (DS-FTTD) architecture, the proposed method optimizes the beamforming structure for multi-user transmission using statistical channel state information (CSI). Unlike the original DS-FTTD design, which assumes point-to-point communication and relies on instantaneous CSI, the proposed scheme is tailored for the practical constraints of LEO systems. Simulation results demonstrate that the proposed approach significantly improves beamforming gain and system throughput compared to conventional methods.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 6","pages":"Pages 1103-1109"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705498","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 : 2025-12-01DOI: 10.1016/j.icte.2025.09.015
Jun Hee Jo, Kae Won Choi
This paper proposes a novel approach for early time-series classification, addressing the trade-off between prediction accuracy and earliness, which is critical in real-time applications. The Sequential Probability Ratio Test (SPRT) provides an optimal solution but relies on prior knowledge of the data’s probability distribution, which is an assumption often impractical in real-world scenarios. Existing studies commonly assume a normal distribution, which limits classification performance in complex data. To overcome this limitation, we integrate normalizing flow into the SPRT framework, enabling the estimation of conditional probability distributions through a series of invertible transformations. This approach allows for precise probability estimation, improving the accuracy of early classification. Experimental results on a preprocessed dataset demonstrate that the proposed model significantly enhances classification performance, offering a promising direction for advancing early time-series classification.
{"title":"Early time-series classification with SPRT and normalizing flow","authors":"Jun Hee Jo, Kae Won Choi","doi":"10.1016/j.icte.2025.09.015","DOIUrl":"10.1016/j.icte.2025.09.015","url":null,"abstract":"<div><div>This paper proposes a novel approach for early time-series classification, addressing the trade-off between prediction accuracy and earliness, which is critical in real-time applications. The Sequential Probability Ratio Test (SPRT) provides an optimal solution but relies on prior knowledge of the data’s probability distribution, which is an assumption often impractical in real-world scenarios. Existing studies commonly assume a normal distribution, which limits classification performance in complex data. To overcome this limitation, we integrate normalizing flow into the SPRT framework, enabling the estimation of conditional probability distributions through a series of invertible transformations. This approach allows for precise probability estimation, improving the accuracy of early classification. Experimental results on a preprocessed dataset demonstrate that the proposed model significantly enhances classification performance, offering a promising direction for advancing early time-series classification.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 6","pages":"Pages 1097-1102"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705500","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