Pub Date : 2025-08-01DOI: 10.1016/j.icte.2025.06.002
Md Minhazur Rahman, Md Shahriar Nazim, Md. Ibne Joha, Yeong Min Jang
Optical camera communication (OCC) leverages camera image sensors for data reception from light sources but faces challenges of low data rates and high bit error rates. This study introduces an OCC system combining orthogonal frequency division multiplexing with a UNet-based equalizer for signal denoising. Using pixel rows as transmission units, the system achieves a data rate of 9.2 kbps and a bit error rate of at 1 m. Python scripts facilitate system control, optimization, and embedded deployment, highlighting OCC’s potential for next-generation communication systems with improved performance over conventional methods.
{"title":"Real-time implementation of OFDM modulation for an OCC system: UNet-based equalizer for signal denoising and BER optimization","authors":"Md Minhazur Rahman, Md Shahriar Nazim, Md. Ibne Joha, Yeong Min Jang","doi":"10.1016/j.icte.2025.06.002","DOIUrl":"10.1016/j.icte.2025.06.002","url":null,"abstract":"<div><div>Optical camera communication (OCC) leverages camera image sensors for data reception from light sources but faces challenges of low data rates and high bit error rates. This study introduces an OCC system combining orthogonal frequency division multiplexing with a UNet-based equalizer for signal denoising. Using pixel rows as transmission units, the system achieves a data rate of 9.2 kbps and a bit error rate of <span><math><mrow><mn>8</mn><mo>.</mo><mn>41</mn><mo>×</mo><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span> at 1 m. Python scripts facilitate system control, optimization, and embedded deployment, highlighting OCC’s potential for next-generation communication systems with improved performance over conventional methods.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 728-733"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840813","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}
The rapid development of the Internet of Things (IoT) has driven a significant shift in computing architectures, leading to the rise of the cloud continuum—a flexible framework that combines cloud services with edge and fog computing. While existing survey papers have contributed valuable insights, they often focus narrowly on specific aspects of the continuum or do not fully address its evolving complexities. These limitations underscore the need for a comprehensive and up-to-date analysis of the field. This study bridges these gaps by presenting an extensive review of the cloud continuum, covering its role in enhancing resource management, improving real-time data processing, integrating machine learning approaches, and optimizing user experiences across diverse applications. We examine how edge devices, fog nodes, and cloud infrastructures synergize to enable decentralized data processing, reducing latency in critical areas such as smart cities, healthcare, and autonomous vehicles. Additionally, this study explores the integration of machine learning across edge, fog, and cloud layers, with a focus on inference and distributed learning methods. By highlighting how these technologies enhance efficiency, scalability, and intelligent decision-making, this review provides a holistic perspective on the cloud continuum. Our analysis offers valuable insights into future research directions, emphasizing innovations that can drive next-generation computing systems toward greater efficiency and adaptability.
{"title":"The journey to cloud as a continuum: Opportunities, challenges, and research directions","authors":"Md. Mahmodul Hasan , Tangina Sultana , Md. Delowar Hossain , Ashis Kumar Mandal , Thien-Thu Ngo , Ga-Won Lee , Eui-Nam Huh","doi":"10.1016/j.icte.2025.04.015","DOIUrl":"10.1016/j.icte.2025.04.015","url":null,"abstract":"<div><div>The rapid development of the Internet of Things (IoT) has driven a significant shift in computing architectures, leading to the rise of the cloud continuum—a flexible framework that combines cloud services with edge and fog computing. While existing survey papers have contributed valuable insights, they often focus narrowly on specific aspects of the continuum or do not fully address its evolving complexities. These limitations underscore the need for a comprehensive and up-to-date analysis of the field. This study bridges these gaps by presenting an extensive review of the cloud continuum, covering its role in enhancing resource management, improving real-time data processing, integrating machine learning approaches, and optimizing user experiences across diverse applications. We examine how edge devices, fog nodes, and cloud infrastructures synergize to enable decentralized data processing, reducing latency in critical areas such as smart cities, healthcare, and autonomous vehicles. Additionally, this study explores the integration of machine learning across edge, fog, and cloud layers, with a focus on inference and distributed learning methods. By highlighting how these technologies enhance efficiency, scalability, and intelligent decision-making, this review provides a holistic perspective on the cloud continuum. Our analysis offers valuable insights into future research directions, emphasizing innovations that can drive next-generation computing systems toward greater efficiency and adaptability.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 666-689"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840806","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 : 2025-08-01DOI: 10.1016/j.icte.2025.06.004
Hyeon-Jin Im , Jiye Kim , Sunyoung Kwon
Epilepsy is a neurological disorder characterized by repetitive seizures, making early prediction crucial for patient safety and quality of life. Traditional detection methods primarily rely on time–frequency information from EEG signals. However, since EEG signals are interconnected and abnormal activity spreads across brain regions, understanding their connectivity is essential. This study proposes CoCL, a novel representation learning approach that employs contrastive learning with EEG connectivity-guided supervision to capture these interconnections. When applied during pretraining and transferred to seizure detection, CoCL outperforms state-of-the-art methods and maintains high accuracy with only 6 EEG channels, reducing the need for numerous electrodes.
{"title":"CoCL: EEG connectivity-guided contrastive learning for seizure detection","authors":"Hyeon-Jin Im , Jiye Kim , Sunyoung Kwon","doi":"10.1016/j.icte.2025.06.004","DOIUrl":"10.1016/j.icte.2025.06.004","url":null,"abstract":"<div><div>Epilepsy is a neurological disorder characterized by repetitive seizures, making early prediction crucial for patient safety and quality of life. Traditional detection methods primarily rely on time–frequency information from EEG signals. However, since EEG signals are interconnected and abnormal activity spreads across brain regions, understanding their connectivity is essential. This study proposes CoCL, a novel representation learning approach that employs contrastive learning with EEG connectivity-guided supervision to capture these interconnections. When applied during pretraining and transferred to seizure detection, CoCL outperforms state-of-the-art methods and maintains high accuracy with only 6 EEG channels, reducing the need for numerous electrodes.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 703-708"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840809","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 : 2025-08-01DOI: 10.1016/j.icte.2025.04.007
Md Mahinur Alam , Mohamed A. Dini , Dong-Seong Kim , Taesoo Jun
In the evolving field of emotion recognition, which intersects psychology, human–computer interaction, and social robotics, there is a growing demand for more advanced and accurate frameworks. The traditional reliance on single-modal approaches has given way to a focus on multimodal emotion recognition, which offers enhanced performance by integrating multiple data sources. This paper introduces TMNet, an innovative multimodal emotion recognition framework that leverages both speech and Electroencephalography (EEG) signals to deliver superior accuracy. This framework utilizes cutting-edge technology, employing a Transformer model to effectively fuse the CNN-BiLSTM and BiGRU architectures, creating a unified multimodal representation for enhanced emotion recognition performance. By utilizing a diverse set of datasets RAVDESS, SAVEE, TESS, and CREMA-D for speech, along with EEG signals captured via the Muse headband. The multimodal model achieves impressive accuracies of 98.89% for speech and EEG signal processing.
{"title":"TMNet: Transformer-fused multimodal framework for emotion recognition via EEG and speech","authors":"Md Mahinur Alam , Mohamed A. Dini , Dong-Seong Kim , Taesoo Jun","doi":"10.1016/j.icte.2025.04.007","DOIUrl":"10.1016/j.icte.2025.04.007","url":null,"abstract":"<div><div>In the evolving field of emotion recognition, which intersects psychology, human–computer interaction, and social robotics, there is a growing demand for more advanced and accurate frameworks. The traditional reliance on single-modal approaches has given way to a focus on multimodal emotion recognition, which offers enhanced performance by integrating multiple data sources. This paper introduces TMNet, an innovative multimodal emotion recognition framework that leverages both speech and Electroencephalography (EEG) signals to deliver superior accuracy. This framework utilizes cutting-edge technology, employing a Transformer model to effectively fuse the CNN-BiLSTM and BiGRU architectures, creating a unified multimodal representation for enhanced emotion recognition performance. By utilizing a diverse set of datasets RAVDESS, SAVEE, TESS, and CREMA-D for speech, along with EEG signals captured via the Muse headband. The multimodal model achieves impressive accuracies of 98.89% for speech and EEG signal processing.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 657-665"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840805","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 : 2025-08-01DOI: 10.1016/j.icte.2025.04.012
Se-Gwon Cheon, Hyuk-Jin Shin, Seung-Hwan Bae
Recent knowledge distillation (KD) for 3D object detection often involves costly LiDAR or multi-camera data. We focus on monocular camera-based 3D detectors, where missing 3D cues cause large feature gaps. To address this, we propose region-aware KD, aligning object features by matching their scales and pyramid levels. We introduce a probabilistic distribution to weigh region importance. Applied to MonoRCNN++ and MonoDETR on the KITTI and Waymo dataset, our approach achieves reduced complexity and strong performance with a lightweight backbone. Compared to recent KD methods, ours excels in both effectiveness and efficiency.
{"title":"Region-aware knowledge distillation between monocular camera-based 3D object detectors","authors":"Se-Gwon Cheon, Hyuk-Jin Shin, Seung-Hwan Bae","doi":"10.1016/j.icte.2025.04.012","DOIUrl":"10.1016/j.icte.2025.04.012","url":null,"abstract":"<div><div>Recent knowledge distillation (KD) for 3D object detection often involves costly LiDAR or multi-camera data. We focus on monocular camera-based 3D detectors, where missing 3D cues cause large feature gaps. To address this, we propose region-aware KD, aligning object features by matching their scales and pyramid levels. We introduce a probabilistic distribution to weigh region importance. Applied to MonoRCNN++ and MonoDETR on the KITTI and Waymo dataset, our approach achieves reduced complexity and strong performance with a lightweight backbone. Compared to recent KD methods, ours excels in both effectiveness and efficiency.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 696-702"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840808","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 : 2025-08-01DOI: 10.1016/j.icte.2025.04.014
Nai-Wei Lo , Chi-Ying Chuang , Jheng-Jia Huang , Yu-Xuan Luo
With the rise of the Internet of Vehicles (IoV), secure and efficient authentication is essential to prevent cyber threats. This paper proposes a session key establishment protocol using Zero-Knowledge Proofs (zk-SNARKs) and Elliptic Curve Cryptography (ECC), including the Elliptic Curve Diffie–Hellman (ECDH) key exchange, to ensure privacy and efficiency. While zk-SNARK computations introduce additional verification overhead, our optimizations, such as precomputed proof parameters and lightweight session re-authentication, mitigate delays. Performance evaluation shows a 20% reduction in computation overhead and a 75% faster re-authentication time compared to existing methods, making it a secure and practical solution for real-world IoV applications.
{"title":"Authentication protocol for vehicular networks using Zero-Knowledge Proofs and Elliptic Curve Cryptography","authors":"Nai-Wei Lo , Chi-Ying Chuang , Jheng-Jia Huang , Yu-Xuan Luo","doi":"10.1016/j.icte.2025.04.014","DOIUrl":"10.1016/j.icte.2025.04.014","url":null,"abstract":"<div><div>With the rise of the Internet of Vehicles (IoV), secure and efficient authentication is essential to prevent cyber threats. This paper proposes a session key establishment protocol using Zero-Knowledge Proofs (zk-SNARKs) and Elliptic Curve Cryptography (ECC), including the Elliptic Curve Diffie–Hellman (ECDH) key exchange, to ensure privacy and efficiency. While zk-SNARK computations introduce additional verification overhead, our optimizations, such as precomputed proof parameters and lightweight session re-authentication, mitigate delays. Performance evaluation shows a 20% reduction in computation overhead and a 75% faster re-authentication time compared to existing methods, making it a secure and practical solution for real-world IoV applications.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 636-642"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840802","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 : 2025-08-01DOI: 10.1016/j.icte.2025.05.002
Sun-Jin Lee, Il-Gu Lee
As machine learning technology advances, data security becomes increasingly important. In this study, we propose an intrusion detection mechanism based on federated learning (FL) that updates only the learning weights to minimize the risk of information leakage. Considering the limited resources of industrial Internet of Things (IIoT) nodes, we propose a learning method based on data pruning. The proposed FL-based intrusion detection model was found to be more secure than the centralized model in terms of the data leakage rate. Data pruning technology reduced the memory usage by 1.4 times while maintaining 97.7 % accuracy. The proposed method detects attacks in industrial sites where large-scale IIoT nodes are installed efficiently, and protects industrial secrets and personal information effectively.
{"title":"Lightweight federated learning-based intrusion detection system for industrial internet of things","authors":"Sun-Jin Lee, Il-Gu Lee","doi":"10.1016/j.icte.2025.05.002","DOIUrl":"10.1016/j.icte.2025.05.002","url":null,"abstract":"<div><div>As machine learning technology advances, data security becomes increasingly important. In this study, we propose an intrusion detection mechanism based on federated learning (FL) that updates only the learning weights to minimize the risk of information leakage. Considering the limited resources of industrial Internet of Things (IIoT) nodes, we propose a learning method based on data pruning. The proposed FL-based intrusion detection model was found to be more secure than the centralized model in terms of the data leakage rate. Data pruning technology reduced the memory usage by 1.4 times while maintaining 97.7 % accuracy. The proposed method detects attacks in industrial sites where large-scale IIoT nodes are installed efficiently, and protects industrial secrets and personal information effectively.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 690-695"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840807","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 : 2025-08-01DOI: 10.1016/j.icte.2025.05.010
Kurnianingsih , Sou Nobukawa , Melyana Nurul Widyawati , Cipta Pramana , Nurseno Bayu Aji , Afandi Nur Aziz Thohari , Dwiana Hendrawati , Eri Sato-Shimokawara , Naoyuki Kubota
Addressing imbalanced data is essential for accurate prediction. We propose a novel ensemble method of XGBoost and deep Q-learning networks (DQN) for pregnancy risk prediction. First, we train the majority class utilizing XGBoost. We subsequently utilize DQN to train the minority class into binary classifications. Finally, we use the trained models from DQN and XGBoost in ensemble learning to generate the final classification results. The XGBoost-DQN model achieves high performance with 0.9819 in precision, recall, F1-score, and accuracy, outperforming several baseline classifiers on private data from 5313 pregnant women in Indonesia and showing superior results on public datasets.
{"title":"A novel ensemble XGBoost and deep Q-network for pregnancy risk prediction on multi-class imbalanced datasets","authors":"Kurnianingsih , Sou Nobukawa , Melyana Nurul Widyawati , Cipta Pramana , Nurseno Bayu Aji , Afandi Nur Aziz Thohari , Dwiana Hendrawati , Eri Sato-Shimokawara , Naoyuki Kubota","doi":"10.1016/j.icte.2025.05.010","DOIUrl":"10.1016/j.icte.2025.05.010","url":null,"abstract":"<div><div>Addressing imbalanced data is essential for accurate prediction. We propose a novel ensemble method of XGBoost and deep Q-learning networks (DQN) for pregnancy risk prediction. First, we train the majority class utilizing XGBoost. We subsequently utilize DQN to train the minority class into binary classifications. Finally, we use the trained models from DQN and XGBoost in ensemble learning to generate the final classification results. The XGBoost-DQN model achieves high performance with 0.9819 in precision, recall, F1-score, and accuracy, outperforming several baseline classifiers on private data from 5313 pregnant women in Indonesia and showing superior results on public datasets.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 648-656"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840804","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 : 2025-08-01DOI: 10.1016/j.icte.2025.04.013
Bin Lyu, Wenqing Hong
This paper proposes a cooperative commensal and parasitic (CCP) scheme for reconfigurable intelligent surface (RIS) enabled symbiotic radio communications, utilizing movable antennas to improve the performance of both primary and secondary systems by dynamically updating their positions. Two types of RIS utilize the CCP scheme to send their respective secondary information to the primary user (PU) by reusing the primary signals from the base station (BS). A primary transmission rate maximization problem is formulated and further solved by a proposed two-layer alternating optimization algorithm with advanced techniques. Numerical results show that compared to the scheme with fixed position antennas, our proposed scheme can increase the primary transmission rate by 11.7%, demonstrating its effectiveness.
{"title":"RIS-enabled cooperative symbiotic radio communications with movable antennas","authors":"Bin Lyu, Wenqing Hong","doi":"10.1016/j.icte.2025.04.013","DOIUrl":"10.1016/j.icte.2025.04.013","url":null,"abstract":"<div><div>This paper proposes a cooperative commensal and parasitic (CCP) scheme for reconfigurable intelligent surface (RIS) enabled symbiotic radio communications, utilizing movable antennas to improve the performance of both primary and secondary systems by dynamically updating their positions. Two types of RIS utilize the CCP scheme to send their respective secondary information to the primary user (PU) by reusing the primary signals from the base station (BS). A primary transmission rate maximization problem is formulated and further solved by a proposed two-layer alternating optimization algorithm with advanced techniques. Numerical results show that compared to the scheme with fixed position antennas, our proposed scheme can increase the primary transmission rate by 11.7%, demonstrating its effectiveness.</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 709-714"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840810","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}
Semantic Interoperability (SI) enables cross-domain data integration by allowing diverse systems to share and process information effectively. While existing reviews focus on general AI-driven interoperability, this systematic literature review (SLR) is the first to exclusively analyze the integration of Large Language Models (LLMs) with SI. This SLR uniquely evaluates LLMs' role in schema alignment, knowledge integration, and security risks. It also introduces a novel taxonomy and identifies challenges like bias propagation and computational costs, providing a new research framework for adversarial robustness, ethical AI, and real-world SI optimization.
This is an open access article under the CC BY-NCND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
{"title":"Using large language models for semantic interoperability: A systematic literature review","authors":"Bilal Abu-Salih , Salihah Alotaibi , Albandari Lafi Alanazi , Ruba Abu Khurma , Bashar Al-Shboul , Ansar Khouri , Mohammed Aljaafari","doi":"10.1016/j.icte.2025.06.011","DOIUrl":"10.1016/j.icte.2025.06.011","url":null,"abstract":"<div><div>Semantic Interoperability (SI) enables cross-domain data integration by allowing diverse systems to share and process information effectively. While existing reviews focus on general AI-driven interoperability, this systematic literature review (SLR) is the first to exclusively analyze the integration of Large Language Models (LLMs) with SI. This SLR uniquely evaluates LLMs' role in schema alignment, knowledge integration, and security risks. It also introduces a novel taxonomy and identifies challenges like bias propagation and computational costs, providing a new research framework for adversarial robustness, ethical AI, and real-world SI optimization.</div><div>This is an open access article under the CC BY-NC<img>ND license (<span><span>http://creativecommons.org/licenses/by-nc-nd/4.0/</span><svg><path></path></svg></span>).</div></div>","PeriodicalId":48526,"journal":{"name":"ICT Express","volume":"11 4","pages":"Pages 819-837"},"PeriodicalIF":4.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144840758","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