A5061331291- Traffic Prediction and Management Techniques
- Railway Systems and Energy Efficiency
- Advanced Computational Techniques and Applications
- Transportation Planning and Optimization
- Industrial Technology and Control Systems
- Railway Engineering and Dynamics
- Neural Networks and Applications
- Fuzzy Logic and Control Systems
- Traffic control and management
- Advanced Decision-Making Techniques
- Simulation and Modeling Applications
- IPv6, Mobility, Handover, Networks, Security
- Anomaly Detection Techniques and Applications
- Evaluation Methods in Various Fields
- Advanced Neural Network Applications
- Evaluation and Optimization Models
- Reliability and Maintenance Optimization
- Transportation and Mobility Innovations
- Indoor and Outdoor Localization Technologies
- Risk and Safety Analysis
- Mobile Agent-Based Network Management
- Advanced Sensor and Control Systems
- Advanced Battery Technologies Research
- Data Management and Algorithms
- Fault Detection and Control Systems
Fujian University of Technology
2021-2025
Virginia Tech
2019-2024
Engineering (Italy)
2024
Institute of Electrical and Electronics Engineers
2019-2024
Shantou University
2021-2023
Fuzhou University
2015-2023
Southwest Jiaotong University
2022-2023
First Affiliated Hospital of Shantou University Medical College
2023
Shandong Institute of Automation
2002-2022
Chinese Academy of Sciences
2003-2022
Current research in automatic train operation concentrates on optimizing an energy-efficient speed profile and designing control algorithms to track the profile, which may reduce comfort of passengers impair intelligence operation. Different from previous studies, this paper presents two intelligent (ITO) without using precise model information offline optimized profiles. The first algorithm, i.e., ITOe, is based expert system that contains rules a heuristic inference method. Then, order...
Forecasting the short-term metro ridership is an important issue for operation management of systems. However, it cannot be solved well by single long memory (LSTM) neural network alone irregular fluctuation caused various factors. This paper proposes a hybrid algorithm (STL-LSTM) which combines addition mode Seasonal-Trend decomposition based on Loess (STL) and LSTM to mitigate influences improve performance prediction. First, original series decomposed into three sub-series STL. Then,...
For urban metro systems with platform screen doors, train automatic stop control (TASC) has recently attracted significant attention from both industry and academia. Existing solutions to TASC are challenged by uncertain stopping errors the fast decrease in service life of braking systems. In this paper, we try solve problem using a new machine learning technique propose novel online strategy help precise location data balises installed at stations. By modeling analysis, find that...
In intelligent transportation systems, there are many tasks that rely on the detection of road congestion, such as traffic signal scheduling and accident detection. As traditional methods for congestion difficult to use, expensive, may cause damage surface, this paper presents a method is based multidimensional visual features convolutional neural network (CNN). This first detects density foreground objects by using gray-level co-occurrence matrix; second, speed moving detected Lucas-Kanade...
Considering both the tracking safety of multi-HSTs and operational efficiency a single HST, intelligent safe driving methods (ISDMs) are proposed to obtain better speed- distance curves by integrating hybrid automata (HA) with data mining algorithms in this paper. To begin with, an controller is established using HA ensure multi-HSTs' operation real time. Then, data-driven based on ensemble (Bagging or Adaboost.R) classification regression tree (CART) discover potential rules from field...
The traditional A ∗ algorithm has problems such as low search speed and huge expansion nodes, resulting in efficiency. This article proposes a circular arc distance calculation method the heuristic function, which combines Euclidean Manhattan radius, uses deviation correction, assignes dynamic weights to combined make overall function cost close reality. Furthermore, repulsive potential field turning are introduced into consider relative position of obstacles while minimizing turns path. In...
Data science (DS) devotes to extract useful data from noisy one form actionable insights. It has broad applications in many domains such as internet search, tourism and social media. However, less systematic studies related DS have been done the field of intelligent vehicles (IV). As size IV becomes more enormous than ever before, it is necessary give a high-level view on how utilize for achieving better IV. After briefly retrospecting history DS, we shed light potential prospects domain...
The majority of existing studies in subway train operations focus on timetable optimization and vehicle tracking methods, which may be infeasible with disturbances actual operations. To deal uncertain passenger demands realize real-time (RTOs) satisfying multiobjectives, including overspeed protection, punctuality, riding comfort, energy consumption, this paper proposes two RTO algorithms via expert knowledge an online learning approach. first algorithm is developed by a knowledge-based...
For a high-speed train (HST), quick and accurate localization of its position is crucial to safe effective operation the HST. In this paper, we develop mathematical model by analyzing location report created Then, apply two sparse optimization algorithms, i.e., iterative pruning error minimization (IPEM) L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> -norm improve sparsity both least squares support vector machine (LSSVM) weighted...
For high-speed train (HST), high-precision of positioning is important to guarantee safety and operational efficiency. improving accuracy, we develop a mathematical model by analyzing the wireless position report created HST. To begin with, k-means algorithm integrated with least square support vector machine (LSSVM) differentiate data establish corresponding prediction for each class. Then, ant colony optimization (ACO) introduced adaptively optimize clustering number solve over-fitting...