A5017164563- Data Management and Algorithms
- Human Mobility and Location-Based Analysis
- Traffic Prediction and Management Techniques
- Graph Theory and Algorithms
- Video Surveillance and Tracking Methods
- Recommender Systems and Techniques
- Topic Modeling
- Advanced Database Systems and Queries
- Fire Detection and Safety Systems
- Robotic Path Planning Algorithms
- Mobile Agent-Based Network Management
- Advanced Graph Neural Networks
- Data-Driven Disease Surveillance
- Mobile Ad Hoc Networks
- Advanced Image and Video Retrieval Techniques
- Context-Aware Activity Recognition Systems
Beijing University of Technology
2023-2024
Northeastern University
2018-2022
With the widespread of location-based social networks (LBSNs), amount check-in data grows rapidly, which helps to recommend next point-of-interest (POI). Extracting sequential patterns from has become a meaningful way for POI recommendation, since human movement exhibits in LBSNs. However, due check-ins’ sparsity problem, exploiting recommendation is challenging issue, makes learned unreliable. Inspired by fact that auxiliary information can be incorporated alleviate this situation, paper,...
A lot of scholars have focused on developing effective techniques for package queries, and a excellent approaches been proposed.Unfortunately, most the existing methods focus small volume data.The rapid increase in data means that traditional queries find it difficult to meet increasing requirements.To solve this problem, novel optimization method (HPPQ) is proposed paper.First, preprocessed into regions.Data preprocessing segments dataset multiple subsets centroid used effectively reduces...
With the vigorous development of transportation infrastructure in various countries, traffic network within city is becoming more and complex, when an emergency occurs one or areas city, it will inevitably cause congestion area keep spreading. There are still many challenges to solve urban route planning problem. In this paper, we have employed a double layer search structure, where empowered traditional A* model with neural network, construct region-level dynamic path known as "Double Layer...
Mobility data collected from location-based social networks are imperative for user movement behaviour analysis and marketing strategy customization. However, due to personal privacy temporary failure of GPS devices, mobility suffer missing issues. The hide beneficial information that can lead distorted analysis. To this end, we propose a multi-task generative adversarial network, termed as MDI-MG, mitigate the negative impact by imputing possible records. Specifically, in first introduce...
With the widespread use of Global Positioning System (GPS) in fields such as traffic monitoring, sports navigation, and track recording, trajectory data recording users' spatial temporal information has grown dramatically. The huge volume causes high cost poses a great challenge to storage, network transmission, query analysis. Therefore, compression becomes crucial issue. This paper proposes an online algorithm based on vector extraction (VOLTCom), which aims achieve efficient while...