A5100411139- Human Mobility and Location-Based Analysis
- Data Management and Algorithms
- Topic Modeling
- Advanced Graph Neural Networks
- Time Series Analysis and Forecasting
- Context-Aware Activity Recognition Systems
- Recommender Systems and Techniques
- Traffic Prediction and Management Techniques
- Advanced Database Systems and Queries
- Natural Language Processing Techniques
- Human Pose and Action Recognition
- Geographic Information Systems Studies
- Advanced Neural Network Applications
- Air Quality Monitoring and Forecasting
- Complex Network Analysis Techniques
- Advanced Image and Video Retrieval Techniques
- Stock Market Forecasting Methods
- Advanced Text Analysis Techniques
- Anomaly Detection Techniques and Applications
- Image and Signal Denoising Methods
- Advanced Computational Techniques and Applications
- International Student and Expatriate Challenges
- Usability and User Interface Design
- Advanced Image Fusion Techniques
- Video Surveillance and Tracking Methods
Zhejiang University
2016-2025
Statistical Service
2025
Washington University in St. Louis
2024
Hunan Normal University
2023-2024
Sichuan Agricultural University
2024
Emory University
2024
University of Technology Sydney
2016-2024
Nanjing University of Science and Technology
2023-2024
Yangzhou University
2005-2024
University of Massachusetts Amherst
2022-2024
Traffic forecasting is of great importance to transportation management and public safety, very challenging due the complicated spatial-temporal dependency essential uncertainty brought about by road network traffic conditions. Latest studies mainly focus on modeling spatial utilizing graph convolutional networks (GCNs) throughout a fixed weighted graph. However, edges, i.e., correlations between pair-wise nodes, are much more interact with each other. In this paper, we propose Multi-Range...
Traffic flow prediction plays an important role in ITS (Intelligent Transportation System). This task is challenging due to the complex spatial and temporal correlations (e.g., constraints of road network law dynamic change with time). Existing work tried solve this problem by exploiting a variety spatiotemporal models. However, we observe that more semantic pair-wise among possibly distant roads are also critical for traffic prediction. To jointly model spatial, temporal, various global...
The proliferation of digital cameras and the growing practice online photo sharing using social media sites such as Flickr have resulted in huge volumes geotagged photos available on Web. Based users' traveling preferences elicited from their travel experiences exposed by photos, we propose a new method for recommending tourist locations that are relevant to users (i.e., personalization) given context awareness). We obtain user-specific his/her history one city use these recommend another...
Multivariate time series (MTS) forecasting plays an important role in the automation and optimization of intelligent applications. It is a challenging task, as we need to consider both complex intra-variable dependencies inter-variable dependencies. Existing works only learn temporal patterns with help single However, there are multi-scale many real-world MTS. Single make model prefer one type prominent shared patterns. In this article, propose adaptive graph neural network (MAGNN) address...
The burgeoning field of Large Language Models (LLMs), exemplified by sophisticated models like OpenAI's ChatGPT, represents a significant advancement in artificial intelligence. These models, however, bring forth substantial challenges the high consumption computational, memory, energy, and financial resources, especially environments with limited resource capabilities. This survey aims to systematically address these reviewing broad spectrum techniques designed enhance efficiency LLMs. We...
Human activity recognition (HAR) is a promising research issue in ubiquitous and wearable computing. However, there are some problems existing traditional methods: 1) They treat HAR as single label classification task, ignore the information from other related tasks, which helpful for original task. 2) need to predesign features artificially, heuristic not tightly To address these problems, we propose AROMA (human using deep multi-task learning). activities can be divided into simple complex...
The problem of air pollution threatens public health. Air quality forecasting can provide the index hours or even days later, which help to prevent in advance. Previous works focus on citywide and cannot solve nationwide city problem, whose difficulties lie capturing latent dependencies between geographically distant but highly correlated cities. In this paper, we propose group-aware graph neural network (GAGNN), a hierarchical model for forecasting. constructs group spatial cities,...
Summary In road network, vehicles' location may be identified, and their transmissions even tracked by eavesdrops (eg, safety messages) that contain sensitive personal information such as identity of the vehicle. This type communication leads to breaking users' trajectory privacy. Frequently changing pseudonyms are widely accepted a solution protects privacy users in networks. However, this become invalid if vehicle changes its pseudonym at an improper occasion. To cope with issue, we...
Activity recognition (AR) and user (UR) using wearable sensors are two key tasks in ubiquitous mobile computing. Currently, they still face some challenging problems. For one thing, due to the variations how users perform activities, performance of a well-trained AR model typically drops on new users. another, existing UR models powerless activity changes, as there significant differences between sensor data different scenarios. To address these problems, we propose METIER (deep multi-task...
Traffic flow prediction is a fundamental part of ITS (Intelligent Transportation System). Since the correlations traffic data are complicated and affected by various factors, challenging task. Existing methods generally take limited static factors (e.g., distance between sensors road network topological structure) into consideration model separately to predict future traffic. In this paper, we propose AARGNN (Attentive Attributed Recurrent Graph Neural Network), GNN (graph neural network)...
The decentralization of blockchain technology greatly improves the trust relationship in supply chain network. In view lack trust, uncertainty, and asymmetry network, this paper integrates to build a network dynamics model representation, calculation, propagation, explores how influences result indicates that scale increased by 115.89%, connectivity 60.31%, average shortest path decreased 4.95%, after framework had been deployed agricultural chain. Meanwhile, topology performance such as...
In recent years, several catastrophic landslide events have been observed throughout the globe, threatening to lives and infrastructures. To minimize impact of landslides, need susceptibility map is important. The study aims extract high-quality non-landslide samples improve accuracy modelling (LSM) outcomes by applying a coupled method ensemble learning Machine Learning (ML). Zigui-Badong section Three Gorges Reservoir area (TGRA) in China was considered present study. Twelve influencing...
Human activity recognition is an important area of ubiquitous computing. Most current researches in mainly focus on simple activities, e.g., sitting, running, walking, and standing. Compared with complex activities are more complicated high-level semantics, working, commuting, having a meal. This paper presents hierarchical model to recognize as mixtures multiple actions. We generate the components using clustering algorithm, represent by applying topic these components. It data-driven...
China's economic success derives from the co-evolution of political and systems. There is no single 'China model'. Rather, three successive generations China model can be identified, corresponding to 'growth equilibria' that emerged when policy responded effectively specific challenges. The structure interaction between determined by basic governance strategy Chinese Communist Party.