A5103232473- Human Mobility and Location-Based Analysis
- Spacecraft Dynamics and Control
- Space Satellite Systems and Control
- Data Management and Algorithms
- Traffic Prediction and Management Techniques
- Complex Network Analysis Techniques
- Recommender Systems and Techniques
- Traditional Chinese Medicine Studies
- Distributed Control Multi-Agent Systems
- Imbalanced Data Classification Techniques
- Anomaly Detection Techniques and Applications
- Transportation Planning and Optimization
- Artificial Intelligence in Healthcare
- Advanced Neural Network Applications
- Caching and Content Delivery
- Building Energy and Comfort Optimization
- Metabolomics and Mass Spectrometry Studies
- Vehicle emissions and performance
- Advanced Clustering Algorithms Research
- Adaptive Control of Nonlinear Systems
- Electricity Theft Detection Techniques
- Urban Transport and Accessibility
- Astro and Planetary Science
- Text and Document Classification Technologies
- Adversarial Robustness in Machine Learning
Chengdu University of Information Technology
2017-2024
Northwestern Polytechnical University
2018-2024
Xi’an University of Posts and Telecommunications
2021
First Affiliated Hospital of Zhengzhou University
2021
Key Laboratory of Guangdong Province
2019
Southwest Jiaotong University
2014-2017
Yanshan University
2011
Beihang University
2008
Chengdu University of Traditional Chinese Medicine
2008
Sichuan University
2006
Trajectory prediction of objects in moving databases (MODs) has garnered wide support a variety applications and is gradually becoming an active research area. The existing trajectory algorithms focus on discovering frequent patterns or simulating the mobility via mathematical models. While these models are useful certain applications, they fall short describing position behavior network-constraint environment. Aiming to solve this problem, hidden Markov model (HMM)-based algorithm proposed,...
The existing approaches for trajectory prediction (TP) are primarily concerned with discovering frequent patterns (FTPs) from historical movement data. Moreover, most of these work by using a linear TP model to depict the positions objects, which does not lend itself complexities real-world applications. In this research, we propose three-in-one in road-constrained transportation networks called TraPlan. TraPlan contains three essential techniques: 1) constrained network R-tree (CNR-tree),...
Community discovery plays an essential role in the analysis of structural features complex networks. Since online networks grow increasingly large and over time, methods traditionally used for community cannot efficiently handle large-scale network data. This introduces important problem how to effectively discover communities from In this study, we propose a fast parallel model called picaso (a algorithm based on approximate optimization), which integrates two new techniques: (1) Mountain...
With the development of location-based services and Big data technology, vehicle map matching techniques are growing rapidly, which is fundamental in study exploring global positioning system (GPS) data. The pre-processed GPS can provide guarantee high-quality for research mining passenger's points interest urban computing services. existing surveys mainly focus on map-matching algorithms, but there few descriptions key phases acquisition sampling data, floating car road preprocessing...
Aiming at the problem of coal structure identification 8 # seam in Benxi Formation Ordos Basin, this study is based on core observation data to clarify logging response characteristics different structures; multi-parameter intersection pattern constructed conventional curve quantitatively divide types. results show that, The highlight image homogeneous block native structure, large time difference acoustic wave (>420μs/m), Neutron value (>54%); Cucut electroimaging highlight,...
Bike-sharing systems are becoming popular and generate a large volume of trajectory data. In bike-sharing system, users can borrow return bikes at different stations. particular, system will be affected by weather, the time period, other dynamic factors, which challenges scheduling shared bikes. this article, new shared-bike demand forecasting model based on convolutional neural networks, called SDF , is proposed to predict chooses most relevant weather features from real data using Pearson...
With the development of network services and location-based systems, many mobile applications begin to use users' geographical location provide better services. In terms social networks, is actively shared by users. some with recommendation services, before provided, authors have obtain user's permission. This kind integrated information called networks (abbreviate for LBSNs). LBSN, each user has when he or she checked in hotels feature spots. Based on this information, they can identify...
This article studies the problem of cooperative substructure transportation using multiple modular robots in an on-orbit assembly mission. Two kinds robots, termed as force and torque are used to provide control forces for substructure, respectively. Using framework games, a set Pareto optimal problems formulated solve such that they can cooperatively bring dock with main body large space structure. Additionally, event-triggered coordinated compensatory mechanism model predictive principles...
The problem of personalized next point-of-interest (POI) recommendation is significant and practical value in location-based social networks (LBSNs). Due to the sparsity data regard check-ins, POI recommendations remain a challenging problem. Previous work developed models by taking into consideration properties user's mobility, for example, spatio-temporal information similarity movement rules. However, they ignore influence trip-purpose on memory effect historical check-in behavior at same...