A5112465302- Cryptography and Data Security
- Indoor and Outdoor Localization Technologies
- Chaos-based Image/Signal Encryption
- Traffic Prediction and Management Techniques
- Context-Aware Activity Recognition Systems
- Internet Traffic Analysis and Secure E-voting
- Security in Wireless Sensor Networks
- Robotics and Sensor-Based Localization
- Energy Efficient Wireless Sensor Networks
- Privacy-Preserving Technologies in Data
- Music Technology and Sound Studies
- Video Surveillance and Tracking Methods
- Human Mobility and Location-Based Analysis
- Mobile Crowdsensing and Crowdsourcing
- Advanced Steganography and Watermarking Techniques
- Cloud Data Security Solutions
China University of Mining and Technology
2018-2024
Ministry of Education of the People's Republic of China
2018
Underground personnel localization is highly important in the operations of coal mines. Considering special underground environment, this paper introduces a novel scheme based on step detection and image recognition technologies, which makes use unique characteristics environment like dark miner's lamp. Since topology relatively simple, miner can be located only by information. However, with information always causes problem cumulative error. To solve problem, we rebuild base station camera...
Opportune and accurate position information of the ubiquitous shared bikes can help users rapidly find available bicycle around them. In order to remove professional locating device bicycles reduce industrial costs, a passive positioning method for named PSA is proposed in this paper with support activity recognition based on deep learning. First, an action module LSTM algorithm constructed through training three-axis accelerator data collected by commercial mobile phone distinguish user's...
Aiming at problems of under-fitting and poor model robustness in learning-based wireless sensing methods caused by the lack large-scale datasets, this paper proposes a privacy-friendly collaborative framework, called Co-Sense. It builds community with multiple clients server, which aggregates clients' local models into federated cross-domain capability. To protect privacy users' data, we innovatively introduce idea learning field sensing, uploading parameters instead their data. Then,...