Navigation provided by FengMap
Application, Xi'an Jiaotong-Liverpool University, Suzhou, China
Simulated navigation app provided by the FengMap.
Talks and presentations
Energy-efficient and Priority-aware Task Scheduling for Dynamic Vehicular Edge Computing
Research project, Xi'an Jiaotong-Liverpool University, Suzhou, China
Introduction:
Deep Reinforcement Learning based Multi-Agent Collaborative Navigation System for Dynamic Trajectory Planning
Research project, Xi'an Jiaotong-Liverpool University, Suzhou, China
Multi-agent collaborative navigation is prevalent in modern transportation systems, including delivery logistics, warehouse automation, and personalised tourism, where multiple agents must converge at a common destination from different starting points. However, the challenges lie in optimising routes for multiple agents while dynamically adjusting the common destination in response to changing traffic conditions. Therefore, we would like to propose a generic Multi-Agent Collaborative Navigation System (MACNS) to address the challenges.
Edge Computing-based Urban Design for the Optimal Deployment of Roadside Units
Research project, Xi'an Jiaotong-Liverpool University, Suzhou, China
The existing practice of creating structure plans in urban design seems to be arbitrary, and few practitioners consider employing algorithms(DL) to meet functional demands and minimize budgets.
Real-time Position Sharing
Application, Xi'an Jiaotong-Liverpool University, Suzhou, China
An Android application (App) is designed, which is mainly used for sharing real-time positions with others. In addition, some interesting functions are also provided.
Polychromatic Sets Theory based Dynamic and Scalable User-Centric Route Planning
Research project, Xi'an Jiaotong-Liverpool University, Suzhou, China
Introduction:
Online Monitoring of Overhead Power Lines Against Tree Intrusion via a Low-cost Camera and Mobile Edge Computing Approach
Research project, Xi'an Jiaotong-Liverpool University, Suzhou, China
Introduction:
Deep Reinforcement Learning based Energy-efficient Task Scheduling for Vehicular Edge Computing
Research project, Xi'an Jiaotong-Liverpool University, Suzhou, China
Description
In this project, we focus on designing an energy-efficient task scheduling strategy based on the Deep Reinforcement Learning (DRL) algorithm, with the target of reducing task completion time and energy consumption in vehicular edge computing scenarios.
Intrusion Detection based on Improved Genetic Algorithm and Deep Belief Network
Research project, Shanghai Maritime University, Shanghai, China
Contributions:
Through multiple iterations of the GA, the optimal number of hidden layers and the number of neurons in each layer are generated.