Daozheng Chen

Mr. Daozheng Chen

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
7 February 2025 in Electronics
Verified
Journal Article
Open access
PDF file
GCGuangqiao Chen
Guangqiao Chen
JGJun Gao
Jun Gao
DCDaozheng Chen
Daozheng Chen
The Vehicle Routing Problem with Time Window (VRPTW) is of crucial importance in modern societies, where the aim is to optimize resource utilization, reduce costs and address constraints such as time and vehicle capacity. Traditional genetic algorithms often face premature convergence and slow speed in solving such problems. This paper proposes an Improved Genetic Ant Colony Optimization (IGA-ACO) algorithm to efficiently solve VRPTW. The algorithm combines the strengths of a genetic algorithm with the Generalized Variable Neighborhood Search (GVNS) and Ant Colony Optimization (ACO), aiming to minimize the total cost and optimize balance. The Solomon insertion heuristic is employed to initialize the population and enhance local search capabilities, while the two-population structure improves global search performance by exchanging the optimal solutions between the two populations, helping to avoid local optima. Experiments on the Solomon benchmark dataset show that the IGA-ACO algorithm matches the Best Known Solution (BKS) in Class C instances, reduces vehicle usage by 24.45% in Class R, with a travel distance deviation of 9.19%, and slightly reduces vehicle usage by 0.19% in Class RC, with a travel distance deviation of 7.05%. These results demonstrate the algorithm’s effectiveness in optimizing vehicle routing, particularly under complex constraints, and its competitive advantage over other methods.

1 January 2016 in BioMed Research International
Verified
Journal Article
Open access
PDF file
DCDaozheng Chen
Daozheng Chen
XTXiaoyu Tian
Xiaoyu Tian
BZBo Zhou
Bo Zhou
JGJun Gao
Jun Gao
Protein fold classification plays an important role in both protein functional analysis and drug design. The number of proteins in PDB is very large, but only a very small part is categorized and stored in the SCOPe database. Therefore, it is necessary to develop an efficient method for protein fold classification. In recent years, a variety of classification methods have been used in many protein fold classification studies. In this study, we propose a novel classification method called proFold. We import protein tertiary structure in the period of feature extraction and employ a novel ensemble strategy in the period of classifier training. Compared with existing similar ensemble classifiers using the same widely used dataset (DD-dataset), proFold achieves 76.2% overall accuracy. Another two commonly used datasets, EDD-dataset and TG-dataset, are also tested, of which the accuracies are 93.2% and 94.3%, higher than the existing methods. ProFold is available to the public as a web-server.