相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Engineering, Multidisciplinary
Zhiwei Guo et al.
Summary: With the increasing demand for personalized social services, researchers propose a deep learning-embedded social Internet of Things (IoT) solution to address the data management and preference ambiguity issues in social recommendation. Experimental results show that the proposed solution outperforms benchmark methods and exhibits good robustness.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Huazhong Liu et al.
Summary: This paper focuses on developing an efficient big data processing framework based on tensor networks and provides an incremental tensor train decomposition approach for streaming big data, which outperforms the nonincremental TT decomposition in terms of execution time.
IEEE TRANSACTIONS ON BIG DATA
(2021)
Article
Automation & Control Systems
Yuan Gao et al.
Summary: In modern industrial applications and data science, data is becoming increasingly multidimensional and complex, requiring joint analysis for high-dimensional data sharing common patterns. This article introduces a joint high-order orthogonal iterative algorithm and federated tensor decomposition model for feature extraction under the federated learning framework. The method achieves similar accuracy to centralized training models while respecting privacy.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Business
Huazhong Liu et al.
Summary: This paper addresses the issue of high-dimensional curse in multivariate Markov models by proposing a tensor-train (TT)-based computation approach with scalable implementation. Experimental results show that the TT-HODED algorithm significantly improves computation efficiency and reduces memory usage while maintaining almost consistent prediction accuracy compared to the original HODED algorithm.
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT
(2021)
Article
Computer Science, Information Systems
Cheng Xie et al.
Summary: This article proposes a knowledge graph-based multilayer IoT middleware that introduces a new layer to bridge the gap between devices with different communication protocols and can uniformly manage all devices. Evaluation of the proposed approach in a real-world project shows that it effectively resolves communication gap and heterogeneous access issues in the system.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Automation & Control Systems
Yangfan Li et al.
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
Automation & Control Systems
Zhiwei Guo et al.
Summary: This article proposes a social recommendation framework based on deep graph neural networks for future IoT recommendation systems. It encodes user and item feature spaces and completes missing values in user-item rating matrices through matrix factorization. Experiments confirm the efficiency and stability of the proposed framework.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Zhiwei Guo et al.
Summary: Spamming is a rising threat to IoT-based social media applications, with AI-based detection techniques being widely explored. Existing literature on IoT cybersecurity focuses on behavior pattern-based and semantic pattern-based approaches, but struggles with handling complex, hidden spamming activities. An article proposes a Collaborative neural network-based spammer detection mechanism that leverages both behavior and semantic patterns for improved spam detection performance. Empirical experiments on real-world data sets show an average 5% performance improvement compared to baseline methods.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Engineering, Multidisciplinary
Huazhong Liu et al.
Summary: This paper introduces a scalable tensor train (TT) based higher order dominant Z-eigen decomposition (HODZED) for multivariate multi-order Markov models under cloud/edge computing environments to provide quick and accurate predictions. By extending dominant Z-eigen decomposition to HODZED and proposing two scalable TT-based algorithms, computation efficiency is significantly improved while maintaining almost consistent prediction accuracy.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2021)
Review
Computer Science, Artificial Intelligence
Xiaojun Chen et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2020)
Article
Computer Science, Information Systems
Swarna R. M. Priya et al.
COMPUTER COMMUNICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Hoang Long Nguyen et al.
INFORMATION FUSION
(2020)
Proceedings Paper
Computer Science, Hardware & Architecture
Zhipeng Cai et al.
2019 39TH IEEE INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS 2019)
(2019)
Proceedings Paper
Computer Science, Information Systems
Xiang Wang et al.
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING
(2019)
Article
Computer Science, Hardware & Architecture
Luigi Atzori et al.
Article
Mathematics, Applied
I. V. Oseledets
SIAM JOURNAL ON SCIENTIFIC COMPUTING
(2011)