Article
Engineering, Multidisciplinary
Xiaoyan Chen, Wei Liang, Jianbo Xu, Chong Wang, Kuan-Ching Li, Meikang Qiu
Summary: The study proposes a collaborative filtering service recommendation algorithm based on heterogeneous information networks and topic models, which can provide personalized services in CPSS and effectively improve the quality of service.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Chemistry, Analytical
Rana Alaa El-deen Ahmed, Manuel Fernandez-Veiga, Mariam Gawich
Summary: Machine learning, especially deep learning with neural networks, has achieved remarkable success in various AI problems. The approach of ML differs from classical engineering and ontologies, as it relies on collecting large datasets and processing them through a generic learning algorithm. Combining ontology-based recommendation and ML-based techniques in a hybrid system is a natural and promising method to enhance semantic knowledge with statistical models. This paper presents a novel hybrid recommendation system that blends knowledge-driven recommendations from an ontology with data-driven recommendations generated by classifiers and a neural collaborative filtering. The authors show that the integration of these two worlds provides measurable improvement and enables the transfer of semantic information to ML and statistical knowledge to the ontology. The proposed system also allows for dynamic behavior capturing by updating the ontology with new products and user behaviors.
Article
Computer Science, Information Systems
Wei Liang, Songyou Xie, Jiahong Cai, Jianbo Xu, Yupeng Hu, Yang Xu, Meikang Qiu
Summary: Cyber-physical systems (CPSs) are secure real-time embedded systems that integrate physical and information worlds through high-speed real-time transmission. This study proposes a security collaborative filtering recommendation algorithm based on artificial intelligence to capture complex interaction information and accurately predict rating information.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Hospitality, Leisure, Sport & Tourism
Jia-Li Chang, Hui Li, Jian-Wu Bi
Summary: This study proposes a hybrid method incorporating multi-attribute collaborative filtering and social network analysis to produce personalized travel recommendations, improving travellers' online booking experience. The method includes modules for identifying online opinion experts, constructing a social network, detecting user communities, and interactively generating personalized recommendations. With this method, travellers are presented with a more appropriate set of options, leading to better travel decisions.
CURRENT ISSUES IN TOURISM
(2022)
Article
Chemistry, Analytical
Jingmin An, Wei Jiang, Guanyu Li
Summary: A personalized point-of-interest (POI) recommender system is important for users' daily life, but it faces challenges of trustworthiness and data sparsity. Existing models only consider trust user influence and neglect the trust location role, as well as fail to refine context factors and fusion between user preference and context models. To address these issues, a bidirectional trust-enhanced collaborative filtering model is proposed, incorporating temporal, geographical, textual content factors, and weighted matrix factorization. Extensive experiments demonstrate that the proposed model outperforms the state-of-the-art method, showing improvements in precision@5 and recall@5.
Article
Automation & Control Systems
Le Wu, Peijie Sun, Richang Hong, Yong Ge, Meng Wang
Summary: The paper proposes a collaborative neural social recommendation (CNSR) model that combines the social embedding part and the collaborative neural recommendation (CNR) part, successfully addressing the challenges in social recommendation and demonstrating high recommendation effectiveness.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Hao Tang, Guoshuai Zhao, Xuxiao Bu, Xueming Qian
Summary: The recommendation system is an important technology in the era of Big Data. Current methods have integrated side information to alleviate the sparsity problem, but not all side information can be obtained with high quality. By proposing the DMGCF model and dynamically evolving multi-graph collaborative filtering, the approach successfully mines and reuses side information, as demonstrated by experimental results.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Engineering, Multidisciplinary
Renjie Zhou, Hao Qian, Jilin Zhang, Chang Liu, Jian Wan, Yongjian Ren, Naixue Xiong, Nailiang Zhao, Sanyuan Zhang
Summary: Cyber-Physical-Social Systems provide value to our lives but lead to data overload, personalized recommendation services are efficient means to solve such problems. The key task of personalized recommender systems is to predict user click-through rate, existing models lack exploration of user preferences and habits.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Lamia Berkani, Sami Belkacem, Mounira Ouafi, Ahmed Guessoum
Summary: This article focuses on social network-based user recommendation, which combines semantic and social representations of users and models user credibility based on trust and commitment in the social network. To optimize recommendation performance, two classification techniques are used: K-means and K-Nearest Neighbours algorithms.
Article
Chemistry, Multidisciplinary
Bin Cheng, Ping Chen, Xin Zhang, Keyu Fang, Xiaoli Qin, Wei Liu
Summary: With the rapid development of ubiquitous data collection and analysis, data privacy in recommended systems is facing challenges. Differential privacy technology can protect privacy but introduces unwanted noise. Considering personalized requirements, a collaborative filtering algorithm is proposed to reduce unwanted noise and protect privacy. Experimental results show improved recommendation performance and privacy protection.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Cybernetics
Fan Wang, Haibin Zhu, Gautam Srivastava, Shancang Li, Mohammad R. Khosravi, Lianyong Qi
Summary: This study introduces a Trust-based Collaborative Filtering algorithm and a Hybrid Collaborative Filtering Recommendation approach to address the issue of preference prediction for new users in recommendation systems.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Sahraoui Dhelim, Nyothiri Aung, Mohammed Amine Bouras, Huansheng Ning, Erik Cambria
Summary: This survey examines the development and classification of personality-aware recommendation systems, discussing their design choices, personality modeling methods, recommendation techniques, and challenges.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Chemistry, Multidisciplinary
Min Ma, Qiong Cao, Xiaoyang Liu
Summary: This study proposed a graph convolution collaborative filtering recommendation method integrating social relations, and experimental results show that this method outperforms existing algorithms in accuracy.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Quan Shen, Yanming Shen
Summary: This paper presents a comprehensive and interactive method for network access and user authentication utilizing a zero-trust framework. It dynamically controls user permissions and offers a solution that coexists with legacy infrastructures.
COMPUTERS & SECURITY
(2024)
Article
Chemistry, Analytical
Aitizaz Ali, Bander Ali Saleh Al-rimy, Abdulwahab Ali Almazroi, Faisal S. Alsubaei, Abdulaleem Ali Almazroi, Faisal Saeed
Summary: This paper presents an innovative approach using consortium blockchain technology to address privacy challenges in cyber-physical systems (CPSs). The proposed design establishes a decentralized and tamper-resistant framework for privacy preservation, ensuring the security and integrity of sensitive information. By leveraging consortium blockchain, secrets in CPSs can be securely stored, shared, and accessed only by authorized entities, mitigating unauthorized access and data breaches.
Article
Automation & Control Systems
Yang Xu, Md Zakirul Alam Bhuiyan, Tian Wang, Xiaokang Zhou, Amit Kumar Singh
Summary: In this article, we propose a framework called C-fDRL to protect the context-aware privacy of task offloading using context-aware federated deep reinforcement learning. The framework operates in three stages (CloudAI, EdgeAI, and DeviceAI) of the overall system, decoupling data from tasks through a context-aware data management approach for local and edge computation, leading to improved data privacy protection.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Liang Wang, Zhiwen Yu, Kaishun Wu, Dingqi Yang, En Wang, Tian Wang, Yihan Mei, Bin Guo
Summary: Mobile Crowdsensing (MCS) is an appealing paradigm for collaboratively collecting data from surrounding environments by assigning outsourced sensing tasks to volunteer workers. However, unpredictable disruptions during task implementation often result in task execution failure and impair the benefit of MCS systems. In this work, we propose a robust task assignment scheme that proactively creates assignments offline, aiming to strengthen the robustness of the scheme and minimize workers' traveling detour cost. By leveraging workers' spatiotemporal mobility, we construct an assignment graph and use an evolutionary multi-tasking optimization algorithm (EMTRA) to achieve adequate Pareto-optimal schemes. Comprehensive experiments on real-world datasets validate the effectiveness and applicability of our approach.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Automation & Control Systems
Chenhui Jiang, Ze Tang, Ju H. Park, Neal N. Xiong
Summary: This article mainly studies the projective quasisynchronization for an array of nonlinear heterogeneous-coupled neural networks with mixed time-varying delays and a cluster-tree topology structure. The conditions for achieving cluster projective quasisynchronization are derived, and the synchronization error bound is optimized.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Chemistry, Multidisciplinary
Chunfeng Lv, Jianping Zhu, Naixue Xiong, Zhengsu Tao
Summary: This paper proposes an improved multitarget tracking method based on a PMBM filter with adaptive detection probability and adaptive newborn distribution to address the problems of unknown detection probability, random target newborn distribution, and high energy consumption in limited computational and processing capacity in sensor networks. The proposed method introduces the gamma distribution to represent the augmented state of unknown and changing target detection probability. The intensity of newborn targets is adaptively derived from the inverse gamma distribution based on this augmented state. The effectiveness of this IGGM-PMBM method is verified through comprehensive experiments, and comparisons with other multitarget tracking filters demonstrate significant improvements in tracking behaviors, especially in reducing tracking energy consumption and enhancing tracking accuracy.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Xiaoheng Deng, Jian Yin, Peiyuan Guan, Neal N. Xiong, Lan Zhang, Shahid Mumtaz
Summary: The development of Industrial Internet of Things (IIoT) and Industry 4.0 has transformed the traditional manufacturing industry. With the mobile-edge computing (MEC) system, computation-intensive tasks can be offloaded from resource-constrained IIoT devices to nearby MEC servers, resulting in lower delay and energy consumption for better Quality of Service (QoS).
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Qinghua Gu, Song Gao, Xuexian Li, Neal N. Xiong, Rongrong Liu
Summary: This paper proposes an adaptive adjacent maximum distance crossover operator to improve the convergence and diversity of the genetic algorithm. The distance-based mating selection strategy purposefully selects parents to produce better offspring, and the adaptive crossover strategy based on population convergence increases the convergence speed of the algorithm by controlling the crossover probability. Experimental results show that the algorithm using the adaptive adjacent maximum distance crossover operator achieves better optimization results.
Article
Multidisciplinary Sciences
Xin Liu, Yang Xu, Dan Luo, Gang Xu, Neal Xiong, Xiu-Bo Chen
Summary: This paper studies the similarity problem of geometric graphics and proposes a graphic similarity security decision protocol, which has wide application value in various fields.
SCIENTIFIC REPORTS
(2023)
Editorial Material
Physics, Mathematical
Bin Wang, Naixue Xiong, Fengming Xin
ADVANCES IN MATHEMATICAL PHYSICS
(2023)
Article
Computer Science, Theory & Methods
Xuanwei Zeng, Yong Yang, Qiaoqiao Xu, Huimiao Zhan, Haoan Lv, Zhiqiang Zhou, Xin Ma, Xiaojuan Liu, Jiaojiao Gui, Qianruo Kang, Neal Xiong, Junfeng Gao, Hua Zheng
Summary: Postoperative delirium is a common and preventable complication after cardiovascular surgery, with increased morbidity and mortality risk. Limited strategies exist for identifying at-risk patients. This observational study collected intraoperative electroencephalography data from 50 cardiothoracic surgery patients and found that those who experienced delirium postoperatively had enhanced causal effects in the default mode network (DMN), particularly in the delta band. Using these findings, the CatBoost classifier accurately distinguished between delirious and non-delirious patients with an 89.1% success rate. These results help explain disrupted information processing in delirious patients and aid in predicting postoperative delirium.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Information Systems
Xuezheng Yang, Zhiwen Zeng, Anfeng Liu, Neal N. Xiong, Tian Wang, Shaobo Zhang
Summary: In this paper, a decentralized trust inference approach is proposed to improve the data collection quality for mobile crowd sensing. The approach includes trust evaluation and data filling components, which assess the trust level of workers and fill missing data using Bayesian probabilistic matrix factorization. Furthermore, a worker recruitment method based on trust prioritization and bid ratio is proposed to preferentially select reliable and low-bid workers, thereby improving data quality and reducing costs.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Fuhu Wu, Jian Sun, Shun Zhang, Neal Xiong, Hong Zhong
Summary: This paper proposes an efficient reversible data hiding scheme through a double-peak two-layer embedding and prediction error expansion. By utilizing the higher significant bit (HSB) plane and double prediction error peaks, the redundancy space of images can be fully utilized. Moreover, the size of the auxiliary information is reduced through pre-processing. Experimental results demonstrate that this scheme performs better in high capacity embedding scenarios and achieves a 83% higher embedding rate on real-world datasets, such as BOSSbase, BOWS2, and UCID, compared to state-of-the-art approaches.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Guoxiang Tong, Yueyang Li, Haoyu Zhang, Naixue Xiong
Summary: This paper proposes a dynamic CNN-GRU-Attention (CGA) model based on fine-grained channel state information (CSI) in Wi-Fi for gesture recognition system. The influence of gestures on CSI's amplitude and phase difference is studied, and data processing methods are used to extract valid data for the model. Experimental results show that the system has high accuracy.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Ziqing Xia, Zhangyang Gao, Anfeng Liu, Neal N. Xiong
Summary: In this paper, an asymmetric quorum-based neighbor discovery (AQND) protocol is proposed to reduce delay, improve energy utilization and lifetime, and outperform previous strategies in main performance indicators.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Information Systems
Xiaohuan Liu, Anfeng Liu, Shaobo Zhang, Tian Wang, Neal N. Xiong
Summary: This paper proposes a delay differentiated services routing (DDSR) scheme to reduce the deployment costs for wireless sensor networks (WSNs) with wake-up radio (WuR) functionality, while meeting the delay requirement of forwarding urgent data and maintaining a long lifetime.
INFORMATION SCIENCES
(2024)
Article
Computer Science, Artificial Intelligence
Qinghua Gu, Yan Wang, Peipei Wang, Xuexian Li, Lu Chen, Neal N. Xiong, Di Liu
Summary: This paper proposes a new ensemble clustering method that combines the influence of cluster level and the base clustering level in a unified framework. The method inserts a global weighting strategy into a local ensemble cluster learning framework, improving the robustness and stability of clustering.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)