fahong yu

Dr. fahong yu

orcid

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 December 2017 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
FYfahong yu
fahong yu
MCMeijia Chen
Meijia Chen
BYBolin Yu
Bolin Yu
WLWenping Li
Wenping Li
LMLonghua Ma
Longhua Ma
HGHuimin Gao
Huimin Gao

11 August 2016 in Soft Computing
Verified
Journal Article
Closed access
PDF file
FYfahong yu
fahong yu
XXXiaoyun Xia
Xiaoyun Xia
WLWenping Li
Wenping Li
JTJiang Tao
Jiang Tao
LMLonghua Ma
Longhua Ma
ZCZhao-Quan Cai
Zhao-Quan Cai

1 June 2004 in Biochemical Genetics
Verified
Journal Article
Closed access
PDF file
SLShunqing Lu
Shunqing Lu
ZYZhi-Gang Yuan
Zhi-Gang Yuan
JPJunfeng Pang
Junfeng Pang
DYDatong Yang
Datong Yang
FYfahong yu
fahong yu
YZYa-Ping Zhang
Ya-Ping Zhang

1 January 2024 in International Journal of Information Technologies and Systems Approach
Verified
Journal Article
Open access
PDF file
FYfahong yu
fahong yu
MCMeijia Chen
Meijia Chen
XXXiaoyun Xia
Xiaoyun Xia
DZDongping Zhu
Dongping Zhu
QPQiang Peng
Qiang Peng
KDKuibiao Deng
Kuibiao Deng
Multi-depot vehicle routing problem with time windows (MDVRPTW) is a valuable practical issue in urban logistics. However, heuristic methods may fail to generate high-quality solutions for massive problems instantly. Thus, this article presents a novel reinforcement learning algorithm integrated with a multi-head attention mechanism and a local search strategy to solve the problem efficiently. The routing optimization was regarded as a vehicle tour generation process and an encoder-decoder was used to generate routes for vehicles departing from different depots iteratively. A multi-head attention strategy was employed for mining complex spatiotemporal correlations within time windows in the encoder. Then, a decoder with multi-agent was designed to generate solutions by optimizing reward and observing transition state. Meanwhile, a local search strategy was employed to improve the quality of solutions. The experiments results demonstrate that the proposed method can significantly outperform traditional methods in effectiveness and robustness.

20 April 2017 in Journal of Ambient Intelligence and Humanized Computing
Verified
Journal Article
Closed access
PDF file
FYfahong yu
fahong yu
MCMeijia Chen
Meijia Chen
KDKun Deng
Kun Deng
XXXiaoyun Xia
Xiaoyun Xia
BYBolin Yu
Bolin Yu
ZCZhao-Quan Cai
Zhao-Quan Cai

1 January 2022 in International Journal of Cognitive Informatics and Natural Intelligence
Verified
Journal Article
Open access
PDF file
FYfahong yu
fahong yu
MCMeijia Chen
Meijia Chen
BYBolin Yu
Bolin Yu
Aimed to improve the efficiency of computing offloading in internet of vehicles (IoV), a collaborative multi-task computing offloading decision mechanism with adaptive estimation of distribution algorithm for MEC-IoV was proposed in this paper. The algorithm considered the energy and time consumption as well as priority among different tasks. It presented a local search strategy and an adaptive learning rate according to the characteristics of the problem to improve the estimation of distribution algorithm. Experimental results show that compared with other offloading strategies, the proposed offloading strategy has obvious effects on the total cost optimization; the solutions quality of AEDA is 86.6% of PSO and 67.3% of GA.