A5100399584- Traffic Prediction and Management Techniques
- Human Mobility and Location-Based Analysis
- Transportation Planning and Optimization
- Advanced Graph Neural Networks
- Traffic control and management
- Urban Transport and Accessibility
- Quantum chaos and dynamical systems
- Topic Modeling
- Advanced Computational Techniques and Applications
- Machine Learning and Data Classification
- Single-cell and spatial transcriptomics
- Recommender Systems and Techniques
- Complex Network Analysis Techniques
- Chaos control and synchronization
- Reinforcement Learning in Robotics
- Graph Theory and Algorithms
- IoT and Edge/Fog Computing
- Computational Drug Discovery Methods
- Domain Adaptation and Few-Shot Learning
- Advanced Clustering Algorithms Research
- Biomedical Text Mining and Ontologies
- Bioinformatics and Genomic Networks
- Human Pose and Action Recognition
- IoT Networks and Protocols
- Video Surveillance and Tracking Methods
Computer Network Information Center
2016-2025
Chinese Academy of Sciences
2013-2025
University of Chinese Academy of Sciences
2014-2025
Southeast University
2004-2024
Dalian University of Technology
2021-2024
East China Normal University
2024
Harbin Engineering University
2024
Hainan Normal University
2024
Institute of Electrical Engineering
2024
Institute of Atmospheric Physics
2013-2023
Data augmentation is a series of techniques that generate high-quality artificial data by manipulating existing samples. By leveraging techniques, AI models can achieve significantly improved applicability in tasks involving scarce or imbalanced datasets, thereby substantially enhancing models' generalization capabilities. Existing literature surveys only focus on certain type specific modality data, and categorize these methods from modality-specific operation-centric perspectives, which...
While exploring human mobility can benefit many applications such as smart transportation, city planning, and urban economics, there are two key questions that need to be answered: (i) What is the nature of spatial diffusion across regions with different functions? (ii) How spot trace trip purposes trajectories? To answer these questions, we study large-scale city-wide taxi trajectories; furtherly organize them arrival sequences according chronological time. We figure out an important...
Demographic attributes play an important role in retail market to characterize different types of users. Such signals however are often only available for a small fraction users practice due the difficulty manual collection process by retailers. In this paper, we aim harness power big data automatically infer users' demographic based on their purchase data. Typically, prediction can be formalized as multi-task multi-class problem, i.e., multiple (e.g., gender, age and income) inferred each...
The representation of feature space is a crucial environment where data points get vectorized and embedded for upcoming modeling. Thus the efficacy machine learning (ML) algorithms closely related to quality engineering. As one most important techniques, generation transforms raw into an optimized conducive model training further refines space. Despite advancements in automated engineering generation, current methodologies often suffer from three fundamental issues: lack explainability,...
Driving is a complex activity that requires multi-level skilled operations (e.g., acceleration, braking, turning). Analyzing driving behavior can help us assess driver performances, improve traffic safety, and, ultimately, promote the development of intelligent and resilient transportation systems. While some efforts have been made for analyzing behavior, existing methods be improved via representation learning by jointly exploring peer temporal dependencies behavior. To end, in this paper,...
Feature selection is the preprocessing step in machine learning which tries to select most relevant features for subsequent prediction task. Effective feature could help reduce dimensionality, improve accuracy and increase result comprehensibility. It very challenging find optimal subset from space as be large. While much effort has been made by existing studies, reinforcement can provide a new perspective searching strategy more global way. In this paper, we propose multi-agent framework...
Forecasting future traffic flows from previous ones is a challenging problem because of their complex and dynamic nature spatio-temporal structures. Most existing graph-based CNNs attempt to capture the static relations while largely neglecting dynamics underlying sequential data. In this article, we present (DST-GCNNs) by learning expressive features represent structures predict surveillance video particular, DST-GCNN two stream network. flow prediction stream, novel convolutional layer...
Tabular data is one of the most widely used formats across industries, driving critical applications in areas such as finance, healthcare, and marketing. In era data-centric AI, improving quality representation has become essential for enhancing model performance, particularly centered around tabular data. This survey examines key aspects emphasizing feature selection generation techniques space refinement. We provide a systematic review methods, which identify retain relevant attributes,...
With the development of transportation networks, countless trajectory data are accumulated, and understanding human mobility from traffic could be helpful for smart cities, urban computing, planning. Extracting valuable insights data, such as taxi trajectories, can significantly improve residents’ daily lives. There many studies on spatiotemporal mining. As we know, arrival prediction or regional function detection encompasses important tasks management However, often mutilated because...
What is the purpose of a trip? are unique human mobility patterns and spatial contexts in or near pickup points delivery trajectories for specific trip purpose? Many prior studies have modeled urban regions; however, these analytics mainly focus on interpreting semantic meanings geographic topics at an aggregate level. Given lack information about activities pick-up dropoff points, it challenging to convert into effective tools inferring purposes. To address this challenge, article, we study...
The identification of urban functional areas is essential for planning and sustainable development. Spatial grids are the basic units implementation plans management by cities or development zones. emergence internet “big data” provides new ideas areas. Based on point interest (POI) data from Baidu Maps, Xicheng District Beijing was divided into with side lengths 200, 500, 1000 m in this study. kernel density method used to analyze spatial structure POI data. Two indicators, that is,...
Drug-drug interaction (DDI) prediction can discover potential risks of drug combinations in advance by detecting pairs that are likely to interact with each other, sparking an increasing demand for computational methods DDI prediction. However, existing mostly rely on the single-view paradigm, failing handle complex features and intricate patterns DDIs due limited expressiveness single view. To this end, we propose a Hierarchical Triple-view Contrastive Learning framework Drug-Drug...
Temporal knowledge graph (TKG) reasoning aims to predict the future missing facts based on historical information and has gained increasing research interest recently. Lots of works have been made model structural temporal characteristics for task. Most existing structure mainly depending entity representation. However, magnitude TKG entities in real-world scenarios is considerable, an number new will arise as time goes on. Therefore, we propose a novel architecture modeling with relation...