A5100637724- Cryptography and Data Security
- Privacy-Preserving Technologies in Data
- Advanced Malware Detection Techniques
- Network Security and Intrusion Detection
- Advanced Authentication Protocols Security
- Complex Network Analysis Techniques
- User Authentication and Security Systems
- Blockchain Technology Applications and Security
- Cloud Data Security Solutions
- Internet Traffic Analysis and Secure E-voting
- Opinion Dynamics and Social Influence
- Anomaly Detection Techniques and Applications
- Security and Verification in Computing
- Advanced Computational Techniques and Applications
- Target Tracking and Data Fusion in Sensor Networks
- Biometric Identification and Security
- Recommender Systems and Techniques
- Face and Expression Recognition
- Inertial Sensor and Navigation
- Topic Modeling
- 3D Shape Modeling and Analysis
- Vehicular Ad Hoc Networks (VANETs)
- Advanced SAR Imaging Techniques
- Advanced Graph Neural Networks
- Advanced Neural Network Applications
Xidian University
2016-2025
Northeast Agricultural University
2019-2024
China Jiliang University
2020-2023
Southwest University of Science and Technology
2023
Wuhan University of Technology
2012-2022
Sun Yat-sen University
2022
China Aerodynamics Research and Development Center
2022
Anhui University of Science and Technology
2022
Wannan Medical College
2014-2021
Arizona State University
2021
The rise of e-commerce has not only given consumers more choice but also caused information overload. In order to quickly find favorite items from vast resources, users are eager for technology by which websites can automatically deliver in they may be interested. Thus, recommender systems created and developed automate the recommendation process. field collaborative filtering recommendations, accuracy requirement algorithm always makes it complex difficult implement one algorithm. slope is...
With the rapid development of distributed renewable energy (DRE), demand response (DR) programs, and proposal internet, current centralized trading electricity market model is unable to meet needs energy. As a decentralized accounting mode, blockchain technology fits requirements participate in market. Corresponding transaction principle, blockchain-based integrated mechanism proposed, which divides process into two stages: call auction stage continues stage. The transactions among heat...
VCC leverages the underutilized storage and computing resources of vehicles to collaboratively provide traffic management, road safety, infotainment services end users, such as drivers passengers. It is a hybrid technology that improves resource utilization on able perform complex tasks cannot be handled by single vehicle. Despite appealing advantages, security privacy threats are severe in due sharing among unfamiliar vehicles. In this article, we identify goals for interoperability with an...
Body condition score (BCS) of dairy cows is the direct reflection their nutritional status. The timely estimation BCS beneficial to improving cow health, milk production and reproduction. In this work, we propose an intelligent Edge-IoT platform with deep learning for estimating cow, by integrating inference capability low latency edge computing in IoT framework. Through capturing images cow's back RGB-D camera, module deployed device firstly performs detection localize separate area each...
Only identities of the server and user are authenticated in traditional smart cards based password authentication schemes, but platform does not be verified, which cannot provide enough protection on personal information user. A mutual scheme is proposed under trusted computing, hash functions used to authenticate identities, remote attestation verify platform. Analysis showed that our can resist most possible attacks, secure efficient, fulfills designed security goals, such as session key...
The past decades have seen the rapid development of Internet Things (IoT) in various domains. Identifying IoT devices connected to network is a crucial aspect security. However, existing work on identifying based manually extracted features and prior knowledge, leading low efficiency identification accuracy. In this paper, we propose an automatic end-to-end device method (IoT ETEI) CNN+BiLSTM deep learning model, which outperforms traditional methods from perspective overhead identify We...
Analog circuit fault isolation is crucial for ensuring the reliability and performance of robotic systems. Test point selection plays a key role in enabling effective isolation, yet traditional methods often struggle to balance number test points with accuracy. This paper proposes novel method by extending fault-pair Boolean table into distributional framework. The approach enhances employing Bhattacharyya Coefficient quantify overlap using kernel density estimation (KDE) model response...
Motivated by the problem of radar target recognition, we develop a label-aided factor analysis (LA-FA) model for statistical modeling high-resolution range profile (HRRP) under prerequisite that HRRP data are Gaussian distributed. The LA-FA is extension multitask learning-based (MTL-FA) model, which mainly applied to recognition with small training size. Compared MTL-FA our introduces discrete class labels via Sigmoid-Bernoulli hierarchy restrict learning parameters, offers potential enhance...
Notwithstanding the tremendous success of deep neural networks in a range realms, previous studies have shown that these learning models are exposed to an inherent hazard called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">adversarial example</i> — images which elaborate perturbation is maliciously added could deceive network, entails study countermeasures urgently. However, existing solutions suffer from some weaknesses, e.g. parameters...