ICT Express最新文献

英文中文

Combination of RIS and Fountain Codes in NOMA relay wireless networks for enhancing system performance and security RIS和喷泉码在NOMA中继无线网络中的结合，以提高系统性能和安全性

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.05.012

Phu Tran Tin , Minh-Sang Van Nguyen , Tran Trung Duy , Van Huy Pham , Byung-Seo Kim

Non-orthogonal multiple access (NOMA) and reconfigurable intelligent surface (RIS) are critical technologies for future wireless communications that provide spectral efficiency while consuming little power. In this research, we explore the security of a downlink NOMA wireless relay network that incorporates the RIS and Fountain Codes (FCs) technique. To assess system performance and security, we compute closed-form formulas for outage probability (OP) and intercept probability (IP). Furthermore, deep neural networks (DNNs) are used in the system model to evaluate and optimize OP and IP. Monte Carlo simulations are used to validate the theoretical conclusions, yielding the following major insights: (i) The major goal of these simulations is to validate analytical expressions. (ii) This study greatly improves our understanding of RIS-NOMA systems, setting the groundwork for future research into actual implementations. (iii) The results further illustrate the better performance of RIS-NOMA by evaluating important system factors such as the number of reflecting elements, the user threshold rate and the maximum number of encoded packets.

非正交多址（NOMA）和可重构智能表面（RIS）是未来无线通信的关键技术，它们在提供频谱效率的同时消耗较少的功率。在本研究中，我们探讨了采用RIS和喷泉码（fc）技术的下行链路NOMA无线中继网络的安全性。为了评估系统性能和安全性，我们计算了停机概率（OP）和拦截概率（IP）的封闭形式公式。此外，在系统模型中使用深度神经网络（dnn）来评估和优化OP和IP。蒙特卡罗模拟用于验证理论结论，产生以下主要见解：(i)这些模拟的主要目标是验证解析表达式。（ii）本研究极大地提高了我们对RIS-NOMA系统的理解，为未来的实际实施研究奠定了基础。（iii）通过评估反射元素数量、用户阈值率和最大编码包数等重要系统因素，进一步说明RIS-NOMA具有更好的性能。

{"title":"Combination of RIS and Fountain Codes in NOMA relay wireless networks for enhancing system performance and security","authors":"Phu Tran Tin , Minh-Sang Van Nguyen , Tran Trung Duy , Van Huy Pham , Byung-Seo Kim","doi":"10.1016/j.icte.2025.05.012","DOIUrl":"10.1016/j.icte.2025.05.012","url":null,"abstract":"<div><div>Non-orthogonal multiple access (NOMA) and reconfigurable intelligent surface (RIS) are critical technologies for future wireless communications that provide spectral efficiency while consuming little power. In this research, we explore the security of a downlink NOMA wireless relay network that incorporates the RIS and Fountain Codes (FCs) technique. To assess system performance and security, we compute closed-form formulas for outage probability (OP) and intercept probability (IP). Furthermore, deep neural networks (DNNs) are used in the system model to evaluate and optimize OP and IP. Monte Carlo simulations are used to validate the theoretical conclusions, yielding the following major insights: (i) The major goal of these simulations is to validate analytical expressions. (ii) This study greatly improves our understanding of RIS-NOMA systems, setting the groundwork for future research into actual implementations. (iii) The results further illustrate the better performance of RIS-NOMA by evaluating important system factors such as the number of reflecting elements, the user threshold rate and the maximum number of encoded packets.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 5","pages":"Pages 909-913"},"PeriodicalIF":4.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145289705","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}

引用次数: 0

The design of a building facade pollutant detection algorithm based on multi-scale context enhancement and model lightweight improvement for YOLO 基于多尺度上下文增强和模型轻量化改进的YOLO建筑立面污染物检测算法设计

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.08.007

Kexun Li, Zhijun Gao

To address the high complexity, poor real-time performance, and the prevalence of false positives and false negatives in current algorithms for detecting small-target pollutants on UAV-based building facades, this study proposes SDS-YOLOv8. The spatial pyramid pooling structure in the backbone is enhanced to improve feature representation. DySample is incorporated into the neck to adaptively adjust sampling points based on the image feature distribution. Additionally, the SCAM module is introduced to improve the memory of important information, and the loss function is further optimized. Experimental results demonstrate that the accuracy of the proposed algorithm is significantly improved, exhibiting strong generalization capability.

©2025 The Korean Institute of Communications and Information Sciences. Publishing Services by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

为了解决当前基于无人机的建筑立面小目标污染物检测算法的高复杂性、实时性差以及假阳性和假阴性盛行的问题，本研究提出了SDS-YOLOv8。增强主干空间金字塔池化结构，提高特征表示。颈部加入DySample，根据图像特征分布自适应调整采样点。此外，还引入了SCAM模块来提高重要信息的记忆能力，并对损失函数进行了进一步优化。实验结果表明，该算法的准确率显著提高，具有较强的泛化能力。©2025韩国通信与信息科学研究所。这是一篇基于CC by-nc-nd许可（http://creativecommons.org/licenses/by-nc-nd/4.0/）的开放获取文章。

引用次数: 0

Optimized implementation of SMAUG-T on resource-constrained 16-bit MSP430 MCU smaugt在资源受限的16位MSP430单片机上的优化实现

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.07.007

MinGi Kim , DongHyun Shin , WooHyung Ko , YoungBeom Kim , Seog Chung Seo

In this paper, we present an optimized implementation of SMAUG-T, one of Round 2 Key Encapsulation Mechanism algorithms in Korean Post-quantum Cryptography Competition, on a widely used 16-bit MSP430 MCU. To achieve performance efficiency of polynomial multiplication, one of the most time-consuming operations in SMAUG-T, we find the optimal method by investigating several latest algorithms such as the Toom–Cook method and the Number-Theoretic Transform (NTT)-based methods (32-bit single moduli version and 16-bit multi-moduli version). Through the investigation, we found that 32-bit single moduli version is the best approach for polynomial multiplication in SMAUG-T on 16-bit MSP430 MCU. To enhance the performance of NTT-based polynomial multiplication, we proposed an improved 32-bit signed Montgomery multiplication method with a newly found Montgomery prime (0x250001) and the intrinsic hardware multiplier. We also apply the state-of-the-art techniques for NTT and inverse NTT (iNTT) such as the layer merging, CT butterfly by tuning them proper to the target device. As a result, our NTT implementation achieves around 35% of improved performance compared to the previous best result of 32-bit single moduli version implementation proposed for Dilithium on 16-bit MSP430 MCU. Finally, our SMAUG-T implementation with the proposed NTT implementation provides 43%–63%, 92%–99%, and 85%–95% of improved performance for key generation, encapsulation, and decapsulation compared to the reference implementation, respectively.

本文提出了一种在广泛使用的16位MSP430单片机上优化实现韩国后量子密码学竞赛中第二轮密钥封装机制算法之一smaugt的方法。为了提高SMAUG-T中最耗时运算之一的多项式乘法的性能效率，我们研究了几种最新算法，如Toom-Cook方法和基于数论变换（NTT）的方法（32位单模版本和16位多模版本），找到了最优方法。通过研究，我们发现32位单模版本是在16位MSP430单片机上smag - t中多项式乘法的最佳方法。为了提高基于ntt的多项式乘法的性能，我们提出了一种改进的32位signed Montgomery乘法方法，该方法使用新发现的Montgomery素数（0x250001）和固有硬件乘法器。我们还应用了最先进的NTT和逆NTT （iNTT）技术，如层合并，CT蝴蝶，通过调整它们适合目标设备。因此，与之前在16位MSP430 MCU上为diilithium提出的32位单模块版本实现的最佳结果相比，我们的NTT实现实现了约35%的性能提升。最后，与参考实现相比，我们的SMAUG-T实现和提议的NTT实现在密钥生成、封装和解封装方面的性能分别提高了43%-63%、92%-99%和85%-95%。

{"title":"Optimized implementation of SMAUG-T on resource-constrained 16-bit MSP430 MCU","authors":"MinGi Kim , DongHyun Shin , WooHyung Ko , YoungBeom Kim , Seog Chung Seo","doi":"10.1016/j.icte.2025.07.007","DOIUrl":"10.1016/j.icte.2025.07.007","url":null,"abstract":"<div><div>In this paper, we present an optimized implementation of SMAUG-T, one of Round 2 Key Encapsulation Mechanism algorithms in Korean Post-quantum Cryptography Competition, on a widely used 16-bit MSP430 MCU. To achieve performance efficiency of polynomial multiplication, one of the most time-consuming operations in SMAUG-T, we find the optimal method by investigating several latest algorithms such as the Toom–Cook method and the Number-Theoretic Transform (NTT)-based methods (32-bit single moduli version and 16-bit multi-moduli version). Through the investigation, we found that 32-bit single moduli version is the best approach for polynomial multiplication in SMAUG-T on 16-bit MSP430 MCU. To enhance the performance of NTT-based polynomial multiplication, we proposed an improved 32-bit signed Montgomery multiplication method with a newly found Montgomery prime (0x250001) and the intrinsic hardware multiplier. We also apply the state-of-the-art techniques for NTT and inverse NTT (iNTT) such as the layer merging, CT butterfly by tuning them proper to the target device. As a result, our NTT implementation achieves around 35% of improved performance compared to the previous best result of 32-bit single moduli version implementation proposed for Dilithium on 16-bit MSP430 MCU. Finally, our SMAUG-T implementation with the proposed NTT implementation provides 43%–63%, 92%–99%, and 85%–95% of improved performance for key generation, encapsulation, and decapsulation compared to the reference implementation, respectively.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 5","pages":"Pages 851-857"},"PeriodicalIF":4.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145289695","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}

引用次数: 0

Deep learning-based diabetic retinopathy recognition and grading: Challenges, gaps, and an improved approach — A survey 基于深度学习的糖尿病视网膜病变识别和分级：挑战、差距和改进的方法-一项调查

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.08.001

Md Ilias Bappi , Jannat Afrin Juthy , Kyungbaek Kim

Diabetic Retinopathy (DR) is a leading cause of vision impairment and blindness worldwide. Early diagnosis is crucial for preventing irreversible vision loss, but manual screening methods are time-consuming and often inconsistent. Deep learning (DL) techniques have shown promise in automating DR detection; however, many existing models still struggle to capture subtle lesions and distinguish fine-grained severity stages. In this survey, we comprehensively review recent DL-based approaches for DR classification, emphasizing attention mechanisms, feature fusion strategies, and stage-wise grading. To address current gaps, we propose a hybrid taxonomy that identifies effective combinations such as texture-based attention, CNN-Transformer fusion, and multi-modal integration. Additionally, we validate our previously published model, STMFNet, a spatial texture-aware attention network based on EfficientNet, across four benchmark datasets. On EyePACS and Messidor, STMFNet achieves up to 98.10% accuracy, outperforming several state-of-the-art (SOTA) models under similar settings. This study provides both a consolidated overview of DR detection advancements and a practical benchmark framework to guide future research in AI-assisted DR classification.

糖尿病视网膜病变（DR）是世界范围内视力损害和失明的主要原因。早期诊断对于防止不可逆的视力丧失至关重要，但人工筛查方法耗时且往往不一致。深度学习（DL）技术在自动化DR检测方面显示出了前景；然而，许多现有的模型仍然难以捕捉细微的病变并区分细粒度的严重程度阶段。在这项调查中，我们全面回顾了最近基于dl的DR分类方法，强调了注意机制、特征融合策略和阶段分级。为了解决目前的差距，我们提出了一种混合分类法，可以识别有效的组合，如基于纹理的注意力、CNN-Transformer融合和多模态集成。此外，我们在四个基准数据集上验证了我们之前发布的模型STMFNet，这是一个基于effentnet的空间纹理感知注意力网络。在EyePACS和Messidor上，STMFNet的准确率高达98.10%，在类似设置下优于几种最先进的（SOTA）模型。本研究提供了DR检测进展的综合概述，并提供了一个实用的基准框架，以指导ai辅助DR分类的未来研究。

{"title":"Deep learning-based diabetic retinopathy recognition and grading: Challenges, gaps, and an improved approach — A survey","authors":"Md Ilias Bappi , Jannat Afrin Juthy , Kyungbaek Kim","doi":"10.1016/j.icte.2025.08.001","DOIUrl":"10.1016/j.icte.2025.08.001","url":null,"abstract":"<div><div>Diabetic Retinopathy (DR) is a leading cause of vision impairment and blindness worldwide. Early diagnosis is crucial for preventing irreversible vision loss, but manual screening methods are time-consuming and often inconsistent. Deep learning (DL) techniques have shown promise in automating DR detection; however, many existing models still struggle to capture subtle lesions and distinguish fine-grained severity stages. In this survey, we comprehensively review recent DL-based approaches for DR classification, emphasizing attention mechanisms, feature fusion strategies, and stage-wise grading. To address current gaps, we propose a hybrid taxonomy that identifies effective combinations such as texture-based attention, CNN-Transformer fusion, and multi-modal integration. Additionally, we validate our previously published model, STMFNet, a spatial texture-aware attention network based on EfficientNet, across four benchmark datasets. On EyePACS and Messidor, STMFNet achieves up to 98.10% accuracy, outperforming several state-of-the-art (SOTA) models under similar settings. This study provides both a consolidated overview of DR detection advancements and a practical benchmark framework to guide future research in AI-assisted DR classification.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 5","pages":"Pages 993-1013"},"PeriodicalIF":4.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145289691","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}

引用次数: 0

Optimized implementation of HQC on Cortex-M4 在Cortex-M4上优化实现HQC

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.07.001

DongCheon Kim , JunHyeok Choi , SeungYong Yoon , Seog Chung Seo

In March 2025, NIST selected HQC as a standardized PQC algorithm. Since HQC relies on binary polynomial operations, optimizations for prime-field schemes like Kyber are not directly applicable. Furthermore, optimizing HQC on Cortex-M4 involves constraints that complicate objective performance evaluation, which has hindered active research in this area. We address these issues and optimize dense-dense polynomial multiplication, HQC’s main computational bottleneck. Using the PQM4 benchmark framework, our implementation achieves speedups of 1139.53–1347.69% in key generation, 1139.53–1253.73% in encapsulation, and 1042.09–1198.78% in decapsulation over PQClean, and 38.78–45.81%, 38.18–45.58%, and 34.76–43.56% improvements over the NTL-based reference, depending on the security level.

2025年3月，NIST选择HQC作为标准化的PQC算法。由于HQC依赖于二元多项式运算，所以像Kyber这样的素域方案的优化并不直接适用。此外，在Cortex-M4上优化HQC涉及到复杂的客观性能评价约束，阻碍了该领域的积极研究。我们解决了这些问题，并优化了高密度多项式乘法，这是HQC的主要计算瓶颈。使用PQM4基准框架，我们的实现在PQClean上实现了密钥生成1139.53-1347.69%，封装1139.53-1253.73%，解封装1042.09-1198.78%的速度提升，以及基于ntl的参考的38.78-45.81%,38.18-45.58%和34.76-43.56%的速度提升，具体取决于安全级别。

引用次数: 0

EDAS: Effective Data Augmentation Strategies for test-time adaptation EDAS：测试时间适应的有效数据增强策略

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.07.011

Mansoo Jung , Sunbeom Jeong , Youngwook Kim , Jungwoo Lee

Test-time adaptation (TTA) is a method of updating model parameters during inference using only unlabeled test data. Unlike supervised learning where labels are provided, data augmentation may not function effectively in TTA settings due to discrepancies between predictions using original and augmented samples. We address this limitation by introducing a novel approach that employs selected augmentations with distinct adaptation strategies customized for each transformation. Our approach is designed as a plug-in solution that can easily be integrated into existing methods. Extensive experiments demonstrate that our approach outperforms existing baselines in the ImageNet-C, VisDA2021, and ImageNet-Sketch dataset under various challenging scenarios.

测试时间自适应（TTA）是一种在推理过程中仅使用未标记的测试数据更新模型参数的方法。与提供标签的监督学习不同，由于使用原始样本和增强样本的预测之间存在差异，数据增强在TTA设置中可能无法有效地发挥作用。我们通过引入一种新方法来解决这一限制，该方法采用为每个转换定制的具有不同适应策略的选择增强。我们的方法被设计为一个插件解决方案，可以很容易地集成到现有的方法中。大量的实验表明，在各种具有挑战性的场景下，我们的方法优于ImageNet-C、VisDA2021和ImageNet-Sketch数据集中现有的基线。

引用次数: 0

Deep Q-learning intrusion detection system (DQ-IDS): A novel reinforcement learning approach for adaptive and self-learning cybersecurity 深度q -学习入侵检测系统（DQ-IDS）：一种新的自适应和自学习网络安全强化学习方法

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.05.007

Md. Alamgir Hossain

With the increasing sophistication of cyber threats, traditional Intrusion Detection Systems (IDS) often fail to adapt to evolving attack patterns, leading to high false positive rates and inadequate detection of zero-day attacks. This study proposes the Deep Q-Learning Intrusion Detection System (DQ-IDS), a novel reinforcement learning (RL)-based approach designed to dynamically learn network attack behaviors and continuously enhance detection performance. Unlike conventional machine learning (ML) and deep learning (DL)-based IDS models that depend on static, pre-trained classifiers, DQ-IDS employs Deep Q-Networks (DQN) with experience replay and adaptive ε-greedy exploration to autonomously classify benign and malicious network traffic. The integration of experience replay mitigates catastrophic forgetting, while adaptive exploration ensures an optimal trade-off between learning efficiency and threat detection. A reward-driven training mechanism reinforces correct classifications and penalizes errors, thereby reducing both false positive and false negative rates. Extensive empirical evaluations on real-world network datasets demonstrate that DQ-IDS achieves a detection accuracy of 97.18%, significantly outperforming conventional IDS solutions in both attack detection and computational efficiency. This work introduces a paradigm shift toward adaptive, self-learning cybersecurity systems capable of real-time, robust threat mitigation in dynamic network environments.

随着网络威胁的日益复杂，传统的入侵检测系统（IDS）往往无法适应不断变化的攻击模式，导致高误报率和对零日攻击的检测不足。本研究提出深度q -学习入侵检测系统（DQ-IDS），这是一种基于强化学习（RL）的新型方法，旨在动态学习网络攻击行为并不断提高检测性能。与传统的机器学习（ML）和基于深度学习（DL）的IDS模型依赖于静态的预训练分类器不同，DQ-IDS采用深度q网络（DQN），具有经验回放和自适应贪婪探索功能，可以自主对良性和恶意网络流量进行分类。经验回放的整合减轻了灾难性遗忘，而自适应探索确保了学习效率和威胁检测之间的最佳权衡。奖励驱动的培训机制加强了正确的分类并惩罚错误，从而降低了假阳性和假阴性率。对真实网络数据集的大量实证评估表明，DQ-IDS的检测准确率达到97.18%，在攻击检测和计算效率方面都明显优于传统的IDS解决方案。这项工作引入了一种向自适应、自我学习的网络安全系统的范式转变，该系统能够在动态网络环境中实时、强大地缓解威胁。

{"title":"Deep Q-learning intrusion detection system (DQ-IDS): A novel reinforcement learning approach for adaptive and self-learning cybersecurity","authors":"Md. Alamgir Hossain","doi":"10.1016/j.icte.2025.05.007","DOIUrl":"10.1016/j.icte.2025.05.007","url":null,"abstract":"<div><div>With the increasing sophistication of cyber threats, traditional Intrusion Detection Systems (IDS) often fail to adapt to evolving attack patterns, leading to high false positive rates and inadequate detection of zero-day attacks. This study proposes the Deep Q-Learning Intrusion Detection System (DQ-IDS), a novel reinforcement learning (RL)-based approach designed to dynamically learn network attack behaviors and continuously enhance detection performance. Unlike conventional machine learning (ML) and deep learning (DL)-based IDS models that depend on static, pre-trained classifiers, DQ-IDS employs Deep Q-Networks (DQN) with experience replay and adaptive ε-greedy exploration to autonomously classify benign and malicious network traffic. The integration of experience replay mitigates catastrophic forgetting, while adaptive exploration ensures an optimal trade-off between learning efficiency and threat detection. A reward-driven training mechanism reinforces correct classifications and penalizes errors, thereby reducing both false positive and false negative rates. Extensive empirical evaluations on real-world network datasets demonstrate that DQ-IDS achieves a detection accuracy of 97.18%, significantly outperforming conventional IDS solutions in both attack detection and computational efficiency. This work introduces a paradigm shift toward adaptive, self-learning cybersecurity systems capable of real-time, robust threat mitigation in dynamic network environments.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 5","pages":"Pages 875-880"},"PeriodicalIF":4.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145289699","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}

引用次数: 0

A lightweight remote sensing image fusion method for vehicle perception 一种用于车辆感知的轻型遥感图像融合方法

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.06.012

Yangyang Zhao , Jiannan Su , Wenjun Li , Zhiyong Yu , Xiaowei Dai

Remote sensing image fusion plays a crucial role in enhancing image information. However, the limitations of existing fusion technologies in terms of computational resources and storage capacity make real-time processing difficult. Therefore, a lightweight fusion method based on knowledge distillation is proposed for vehicle remote sensing image fusion. The knowledge distillation technology is used to transfer the complex teacher model knowledge to the lightweight student model, which realizes the significant reduction of model complexity while maintaining high fusion accuracy. Experimental results show that the proposed method performs well on DroneVehicle dataset and the model weight is only 0.641M.

2025 The Korean Institute of Communications and Information Sciences. Publishing Services by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

遥感图像融合是增强遥感图像信息的重要手段。然而，现有融合技术在计算资源和存储容量方面的局限性使得实时处理变得困难。为此，提出了一种基于知识蒸馏的轻型汽车遥感图像融合方法。利用知识蒸馏技术将复杂的教师模型知识转移到轻量级的学生模型中，在保持较高融合精度的同时显著降低了模型复杂度。实验结果表明，该方法在无人机数据集上表现良好，模型权值仅为0.641M.2025韩国通信与信息科学研究所。这是一篇基于CC by-nc-nd许可（http://creativecommons.org/licenses/by-nc-nd/4.0/）的开放获取文章。

引用次数: 0

Neural-NGBoost: Natural gradient boosting with neural network base learners neural - ngboost：基于神经网络学习器的自然梯度增强

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.08.003

Jamshidjon Ganiev , Deok-Woong Kim , Seung-Hwan Bae

NGBoost has shown promising results in probabilistic and point estimation tasks. However, it is vague still whether this method can be scalable to neural architecture system since its base learner is based on decision trees. To resolve this, we design a Neural-NGBoost framework by replacing the base learner with lightweight neural networks and introducing joint gradient estimation for boosting procedure. Based on natural gradient boosting, we iteratively update the neural based learner by inferring natural gradient and update the parameter score with its probabilistic distribution. Experimental results show Neural-NGBoost achieves superior performance across various datasets compared to other boosting methods.

NGBoost在概率和点估计任务中显示出了令人鼓舞的结果。然而，由于该方法的基础学习器是基于决策树的，因此该方法是否可以扩展到神经结构系统中还不清楚。为了解决这个问题，我们设计了一个neural - ngboost框架，用轻量级神经网络取代基础学习器，并引入联合梯度估计用于提升过程。在自然梯度增强的基础上，通过推断自然梯度迭代更新神经学习器，并根据其概率分布更新参数得分。实验结果表明，与其他增强方法相比，Neural-NGBoost在各种数据集上都取得了更好的性能。

引用次数: 0

Artificial intelligence based prediction of refractive index profile of graded refractive index optical fiber 基于人工智能的梯度折射率光纤折射率分布预测

IF 4.2 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

ICT Express

Pub Date : 2025-10-01 DOI: 10.1016/j.icte.2025.05.011

Seung-Yeol Lee , Hyuntai Kim

This research presents a deep neural network (DNN) approach for predicting the refractive index profile in graded-index multimode fibers (GRIN MMFs). The model was trained using simulated data and achieved an average loss less than 1% across both selected (or structured) and random test sets. This artificial intelligence-driven approach has potential applications in custom fiber design, nonlinear optics, and rapid fiber performance characterization. Future developments may include the use of real-world data and the extension of the model to predict refractive index profiles, further enhancing its versatility.

提出了一种基于深度神经网络（DNN）的梯度折射率多模光纤折射率预测方法。该模型使用模拟数据进行训练，并在选择（或结构化）和随机测试集中实现了小于1%的平均损失。这种人工智能驱动的方法在定制光纤设计、非线性光学和快速光纤性能表征方面具有潜在的应用前景。未来的发展可能包括使用实际数据和扩展模型来预测折射率分布，进一步增强其通用性。

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

ICT Express

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀