Article
Automation & Control Systems
Yangfan Li, Cen Chen, Mingxing Duan, Zeng Zeng, Kenli Li
Summary: The recent trend focuses on using heterogeneous graphs for facilitating the application of deep learning in the Internet of Things, but existing models struggle to accurately represent complex semantics and attributes. To address this challenge, attention-aware encoder-decoder graph neural network called HGAED has been developed to improve accuracy using attention-based separate-and-merge method and encoder-decoder architecture. Extensive experiments show superior performance of HGAED over state-of-the-art baselines in fusing heterogeneous structures and contents of nodes hierarchically.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Xiangjian Zuo, Lixiang Li, Shoushan Luo, Haipeng Peng, Yixian Yang, Linming Gong
Summary: This article presents an efficient and privacy-preserving verifiable graph intersection scheme with cryptographic accumulators in social networks, offering secure verifiable graph intersection operation in an untrusted cloud. The scheme is shown to be secure and feasible through detailed correctness proof and performance analysis, providing strong protection for data owners' graph data privacy and user authentication.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Hao Tang, Donghong Ji, Qiji Zhou
Summary: Graph neural networks have shown excellent performance on graph-based tasks such as abstract meaning representation text generation and graph reasoning. By considering triples as basic calculation units, a novel structure called triple-based graph neural network is proposed, achieving significant improvement in various experiments.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Yongjing Yin, Jiali Zeng, Jinsong Su, Chulun Zhou, Fandong Meng, Jie Zhou, Degen Huang, Jiebo Luo
Summary: This paper proposes a graph-based multi-modal fusion encoder for neural machine translation. It represents the input sentence and image using a unified multi-modal graph, and learns node representations through graph-based fusion layers. Experimental results show that the proposed model achieves significant improvements over baselines and achieves state-of-the-art performance on the Multi30K dataset.
ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Cybernetics
Yuhua Xu, Junli Wang, Mingjian Guang, Chungang Yan, Changjun Jiang
Summary: This article proposes a Multistructure graph classification method with Attention mechanism and Convolutional neural network (CNN) called MAC, which evaluates the importance of nodes using multiple strategies, updates node representations with an attention mechanism, and captures multiple different substructures of a graph using a hierarchical architecture. Experimental results demonstrate that our method outperforms state-of-the-art graph classification methods.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Cuiying Huo, Dongxiao He, Chundong Liang, Di Jin, Tie Qiu, Lingfei Wu
Summary: In this work, we propose a new GNN-based trust evaluation method named TrustGNN, which integrates the propagative and composable nature of trust graphs into a GNN framework for better trust evaluation. TrustGNN designs specific propagative patterns for different propagative processes of trust, and distinguishes the contribution of different propagative processes to create new trust. Experiments show that TrustGNN significantly outperforms the state-of-the-art methods on widely-used real-world datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Fang Fang, Xiaolun Wu
Summary: This article explores the complementarity and coexistence of 5G networks and edge computing, proposing a win-win mode for their cooperation. It summarizes applicable scenarios and potential challenges, providing valuable insights for research and development in integration deployment.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Xuefei Ning, Yin Zheng, Zixuan Zhou, Tianchen Zhao, Huazhong Yang, Yu Wang
Summary: Neural architecture search (NAS) can automatically discover well-performing architectures in a large search space and has been shown to bring improvements to various applications. To improve the sample efficiency of search space exploration, GATES++ incorporates multifaceted information about NN's operation-level and architecture-level computing semantics into its construction and training, and it can discover better architectures after evaluating the same number of architectures.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yang Gao, Peng Zhang, Hong Yang, Chuan Zhou, Yue Hu, Zhihong Tian, Zhao Li, Jingren Zhou
Summary: Graph neural networks (GNNs) are widely used for analyzing non-euclidean graph data, but their design requires manual work and domain knowledge. To address this, we propose GraphNAS, a graph neural architecture search algorithm that leverages reinforcement learning to automatically design the best graph neural architectures. GraphNAS uses a recurrent network as the controller to generate variable-length strings describing the architectures, and trains it with policy gradient to maximize the expected accuracy on a validation dataset.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Jiajia Chen, Xin Xin, Xianfeng Liang, Xiangnan He, Jun Liu
Summary: Generating recommendations based on user-item interactions and user-user social relations is a common use case in web-based systems. Existing graph-based methods fail to consider the bias offsets of users (items). We propose Graph-Based Decentralized Collaborative Filtering for Social Recommendation (GDSRec) which treats biases as vectors and incorporates them into the learning process of user and item representations. Experimental results show that GDSRec achieves superior performance compared with state-of-the-art related baselines.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Information Systems
Desoky Abdelqawy, Abeer El-Korany, Amr Kamel, Soha Makady
Summary: The Internet of Things (IoT) faces challenges due to vendor diversity and lack of a common communication interface, resulting in reduced resource utilization and additional costs. This study proposes an IoT computing platform architecture, called Hub-OS, for efficient management of devices and applications from different vendors, enabling seamless integration and real-time processing.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
George Kyriakides, Konstantinos Margaritis
Summary: As NAS becomes popular for designing network architectures, performance-predicting models can speed up the process, while GCNs are increasingly used for various tasks, enabling deep learning on graphs.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Narges Akhound, Sahar Adabi, Ali Rezaee, Amir Masoud Rahmani
Summary: Fog computing is widely used as a mediation layer to bridge the gap between IoT nodes and cloud datacenters. The proposed architecture integrates IoT, fog, and cloud layers to provide higher availability, better resource utilization, and response time for time-sensitive applications. The architecture includes clustering and scheduling flows to improve manageability of mobile IoT nodes, reduce energy consumption, and provide acceptable completion time for time-sensitive IoT applications.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Seyedeh Shabnam Jazaeri, Sam Jabbehdari, Parvaneh Asghari, Hamid Haj Seyyed Javadi
Summary: In this paper, a new scheme is proposed for caching IoT content on the edge with SDN-based processing capability. The proposed Moth-Flame Optimization-Edge Caching (MFO-EC) algorithm can provide data with lower latency on upcoming requests, and it improves the Quality of Service (QoS) in the SDN-based IoT environment.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sahraoui Dhelim, Huansheng Ning, Fadi Farha, Liming Chen, Luigi Atzori, Mahmoud Daneshmand
Summary: With the rapid advancement of IoT and the increase in connectivity, social relationships in the IoT network are rapidly growing, leading to social relationships explosion. However, the emerging field of artificial social intelligence shows promise in addressing this issue.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Jimmy Ming-Tai Wu, Zhongcui Li, Norbert Herencsar, Bay Vo, Jerry Chun-Wei Lin
Summary: This article proposes a new framework structure that combines CNN and LSTM algorithms for accurate stock price prediction. Through experiments, it has been verified that this new algorithm performs better in terms of prediction performance.
MULTIMEDIA SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Xuhong Cheng, Zhiwei Guo, Yu Shen, Keping Yu, Xu Gao
Summary: This paper proposes a hybrid control and prediction system for wastewater treatment processes (WTP) called AS-CL, which combines the Activated Sludge model, Convolutional neural network, and Long short-term memory neural networks. The AS-CL model improves modeling efficiency and reduces the impact of fuzziness on WTP.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Tinhinane Mezair, Youcef Djenouri, Asma Belhadi, Gautam Srivastava, Jerry Chun-Wei Lin
Summary: In recent years, extensive research has been conducted to improve people's living comfort. The development of the Internet of Things, big data, and artificial intelligence has led to the emergence of the Internet of Behaviors, which analyzes behavioral patterns. However, current IoB technologies face challenges in handling diverse data formats and inefficient hyperparameter tuning strategies. This paper presents an Advanced Deep Learning framework (ADLIoB) for connected vehicles, which uses different deep learning architectures and an intelligent hyperparameter selection technique. Experimental results show that ADLIoB outperforms baseline solutions in terms of accuracy and runtime.
ACM TRANSACTIONS ON SENSOR NETWORKS
(2023)
Article
Computer Science, Information Systems
Cai Xiaohong, Sun Yi, Lin Zhaowen, Muhammad Imran, Yu Keping
Summary: With the development of multimedia technology and applications in the financial services industry, this paper proposes a lightweight data storage approach for privacy-preserving financial services images in the cloud and validates its effectiveness in experiments.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Usman Ahmed, Jerry Chun-Wei Lin, Gautam Srivastava
Summary: This article presents the approach of embedding trajectory deviation points and deep clustering. The proposed learning trajectory embedding approach successfully captures the structural identity and outperforms competing strategies in detecting outliers in the trajectory and deviation locations.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2023)
Article
Chemistry, Multidisciplinary
Trisha Das Mou, Saadia Binte Alam, Md. Hasibur Rahman, Gautam Srivastava, Mahady Hasan, Mohammad Faisal Uddin
Summary: This paper introduces a novel method based on convolutional neural network dual attention unit and selective kernel feature synthesis for enhancing dark images under low-light conditions. The proposed model achieves standard image enhancement and denoising results with better precision than previously established models. The output of the model shows its potential applications in medical image processing and robotic visualization in dark environments.
APPLIED SCIENCES-BASEL
(2023)
Article
Automation & Control Systems
Bin Cao, Yanlong Yan, Yu Wang, Xin Liu, Jerry Chun-Wei Lin, Arun Kumar Sangaiah, Zhihan Lv
Summary: The wide area measurement system based on synchronous phasor measurement technology is crucial for dynamic monitoring and wide area protection in modern power systems. This article discusses incomplete observability under single PMU loss and its impact on PMU placement, proposing an improved two-archive algorithm for placement optimization and a fuzzy decision-making method for selecting the best solution. Tests on IEEE bus systems and the Polish 2383-bus system confirm the effectiveness of the proposed method.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Nizamud Din, Abdul Waheed, Shamsher Ullah, Noor Ul Amin, Gautam Srivastava, Farhan Ullah, Jerry Chun-Wei Lin
Summary: This research proposes the method of combining multicast public-key encryption with digital signatures, known as Multi-Receiver Signcryption (MRSC), to ensure the security and efficacy of multicast communication over 5G and 6G networks. Compared to multicast encryption and signature, MRSC significantly improves the effectiveness of secure information delivery through multicast communication. This paper provides the formal model of MRSC schemes used in Public Key Infrastructure, Identity-based Cryptography, and Certificateless Cryptography, and presents a typology of MRSC, as well as a summary of an in-depth investigation of the qualities of security, the cost of computing, and the overhead of communication over the networks.
INTERNATIONAL JOURNAL OF INFORMATION SECURITY
(2023)
Article
Computer Science, Information Systems
Jingwei Liu, Weiyang Jiang, Rong Sun, Ali Kashif Bashir, Mohammad Dahman Alshehri, Qiaozhi Hua, Keping Yu
Summary: Electronic Medical Records (EMRs) are valuable research materials for AI and machine learning. Traditional centralized data sharing architectures cannot balance privacy and traceability effectively. Our proposed scheme using decentralized blockchain allows trackable anonymous remote healthcare data storing and sharing, providing efficient overall performance.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Green & Sustainable Science & Technology
Manash Kumar Mondal, Riman Mandal, Sourav Banerjee, Utpal Biswas, Jerry Chun-Wei Lin, Osama Alfarraj, Amr Tolba
Summary: Elephants, one of the largest animals on earth, are found in forests, grasslands, and savannahs in Asia and Africa. The northeastern region of India, covered by dense forests, is home to many elephants. Train accidents with elephants are increasing due to poor visibility in the forests. The most effective solution is to stop the train immediately.
Article
Computer Science, Hardware & Architecture
Usman Ahmed, Jerry Chun-Wei Lin, Gautam Srivastava
Summary: Approximately 19 million people die each year from cardiovascular and chronic respiratory diseases. This study uses machine learning to categorize and predict these diseases, providing timely alerts to healthcare professionals. The proposed model improves classification accuracy and outperforms existing algorithms in diagnosing cardiovascular and chronic respiratory diseases.
SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS
(2023)
Editorial Material
Medicine, General & Internal
Govind Srivastava, Gautam Srivastava
EUROPEAN JOURNAL OF INTERNAL MEDICINE
(2023)
Article
Computer Science, Cybernetics
Usman Ahmed, Jerry Chun-Wei Lin, Gautam Srivastava
Summary: The proliferation of false and erroneous information on the Internet has posed a challenge to the accurate exchange of information. To address this issue, a semisupervised system based on self-embedding has been proposed. This system verifies information before it is shared, allowing only reliable and accurate content to be disseminated and protecting individuals from the negative effects of false information.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Information Systems
Martin Kiac, Pavel Sikora, Lukas Malina, Zdenek Martinasek, Gautam Srivastava
Summary: This study focuses on the deployment of artificial intelligence in Intelligent Transportation Cyber-Physical Systems to improve efficiency, reliability, and safety. It presents a novel system called ADEROS that combines elements of CPS systems, object detection, and computer vision to analyze traffic participants and dangerous situations at crossroads and railway crossings.
IEEE SYSTEMS JOURNAL
(2023)
Article
Computer Science, Information Systems
Ashutosh Dhar Dwivedi, Gautam Srivastava
Summary: This paper presents the differential cryptanalysis of two lightweight ciphers, SIMON and SIMECK. The primary goal is to find high probability differential characteristics for the ciphers. The paper uses nested tree search-based methods to find these characteristics in reduced time and simpler framework.
INTERNET OF THINGS
(2023)