A5088523664- Data Management and Algorithms
- Human Mobility and Location-Based Analysis
- Automated Road and Building Extraction
- Geographic Information Systems Studies
- Traffic Prediction and Management Techniques
- Recommender Systems and Techniques
- Topic Modeling
- Time Series Analysis and Forecasting
- Privacy-Preserving Technologies in Data
- Video Surveillance and Tracking Methods
- Advanced Database Systems and Queries
- Sentiment Analysis and Opinion Mining
- Data Mining Algorithms and Applications
- Data Quality and Management
- Advanced Clustering Algorithms Research
- Data-Driven Disease Surveillance
- Advanced Text Analysis Techniques
- Natural Language Processing Techniques
- Transportation Planning and Optimization
- Anomaly Detection Techniques and Applications
- Web Data Mining and Analysis
- Image Retrieval and Classification Techniques
- Advanced Bandit Algorithms Research
- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
Soochow University
2022-2024
Soochow University
2021
Queensland University of Technology
2019-2021
The University of Queensland
2017-2021
Polish-Japanese Academy of Information Technology
2021
Hong Kong University of Science and Technology
2021
University of Bologna
2021
East China Normal University
2015-2016
Shanghai Key Laboratory of Trustworthy Computing
2015
Trajectory data has become ubiquitous nowadays, which can benefit various real-world applications such as traffic management and location-based services. However, trajectories may disclose highly sensitive information of an individual including mobility patterns, personal profiles gazetteers, social relationships, etc, making it indispensable to consider privacy protection when releasing trajectory data. Ensuring on demands more than hiding single locations, since are intrinsically sparse...
Shortest path finding is the building block of various applications in road networks and index-based algorithms, especially hub labeling, can boost query performance dramatically. However, traffic condition keeps changing real life, making pre-computed index unable to answer correctly. In this work, we adopt state-of-the-art tree decomposition-based labeling as underlying index, design efficient algorithms incrementally maintain index. Specifically, first analyze structural stability dynamic...
Next Point-of-Interest (POI) recommendation is of great value for location-based services. Existing solutions mainly rely on extensive observed data and are brittle to users with few interactions. Unfortunately, the problem few-shot next POI has not been well studied yet. In this paper, we propose a novel meta-optimized model MFNP, which can rapidly adapt check-in records. Towards cold-start problem, it seamlessly integrates carefully designed user-specific region-specific tasks in...
The Constrained Shortest Path (CSP) problem aims to find the shortest path between two nodes in a road network subject given constraint on another attribute. It is typically processed as skyline attributes, resulting very high computational cost which can be prohibitive for large networks. main bottleneck deal with amount of partial paths, further makes existing index-based methods incapable obtain complete exact paths. In this paper, we propose novel concatenation approach avoid expensive...
Map inference algorithm aims to construct a digital map from other data sources automatically. Due the labour intensity of traditional creation and frequent road change nowadays, is deemed be promising solution automatic construction update. However, existing GPS trajectories suffers low quality, which makes quality constructed unsatisfactory. In this paper, we study algorithms using trajectories. Different previous surveys, (1) include most recent solutions propose new categorisation...
<div>Trajectory data has become ubiquitous nowadays, which can benefit various real-world applications such as traffic management and location-based services. However, trajectories may disclose highly sensitive information of an individual including mobility patterns, personal profiles gazetteers, social relationships, etc, making it indispensable to consider privacy protection when releasing trajectory data. Ensuring on demands more than hiding single locations, since are...
The map-matching is an essential preprocessing step for most of the trajectory-based applications. Although it has been active topic more than two decades and, driven by emerging applications, still under development. There a lack categorisation existing solutions recently and analysis future research directions. In this paper, we review current status problem survey algorithms. We propose new according to their models working scenarios. addition, experimentally compare three representative...
<div>Trajectory data has become ubiquitous nowadays, which can benefit various real-world applications such as traffic management and location-based services. However, trajectories may disclose highly sensitive information of an individual including mobility patterns, personal profiles gazetteers, social relationships, etc, making it indispensable to consider privacy protection when releasing trajectory data. Ensuring on demands more than hiding single locations, since are...