Qi Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qi Yu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Bin He
Tongji University
1 shared publication - Ding Liu
College of Transport & Communications, Shanghai Maritime University, Shanghai 201306, China
1 shared publication - Dongyang Li
Sino-German College of Applied Sciences, Tongji University, Shanghai, China
1 shared publication - Hao Xu
College of Transport & Communications, Shanghai Maritime University, Shanghai 201306, China
1 shared publication - Hong Li
College of Electronic and Information Engineering, Tongji University, 4800 Cao’an Road, Shanghai, P. R. China
1 shared publication J. Yu
State Grid Zibo Electric Power Supply Company, Zibo, People's Republic of China
1 shared publication
Latest Publications
- Open Access
Advancing Dynamic Emergency Route Optimization with a Composite Network Deep Reinforcement Learning Model
Emergency logistics is essential for rapid and efficient disaster response, ensuring the timely availability and deployment of resources to affected areas. In the process of rescue work, the dynamic changes in rescue point information greatly increase the difficulty of rescue. This paper establishes a combined neural network model considering soft time-window penalty and applies deep reinforcement learning (DRL) to address the dynamic routing problem in emergency logistics. This method utilizes the actor–critic framework, combined with attention mechanisms, pointer networks, and long short-term memory neural networks, to determine effective disaster relief path, and it compares the obtained scheduling scheme with the results obtained from the DRL algorithm based on the single-network model and ant colony optimization (ACO) algorithm. Simulation experiments show that the proposed method reduces the solution accuracy by nearly 10% compared to the ACO algorithm, but it saves nearly 80% in solution time. Additionally, it slightly increases solution times but improves accuracy by nearly 20% over traditional DRL approaches, demonstrating a promising balance between performance efficiency and computational resource utilization in emergency logistics.
Open AccessAdvancing Dynamic Emergency Route Optimization with a Composite Network Deep Reinforcement Learning Model
Emergency logistics is essential for rapid and efficient disaster response, ensuring the timely availability and deployment of resources to affected areas. In the process of rescue work, the dynamic changes in rescue point information greatly increase the difficulty of rescue. This paper establishes a combined neural network model considering soft time-window penalty and applies deep reinforcement learning (DRL) to address the dynamic routing problem in emergency logistics. This method utilizes the actor–critic framework, combined with attention mechanisms, pointer networks, and long short-term memory neural networks, to determine effective disaster relief path, and it compares the obtained scheduling scheme with the results obtained from the DRL algorithm based on the single-network model and ant colony optimization (ACO) algorithm. Simulation experiments show that the proposed method reduces the solution accuracy by nearly 10% compared to the ACO algorithm, but it saves nearly 80% in solution time. Additionally, it slightly increases solution times but improves accuracy by nearly 20% over traditional DRL approaches, demonstrating a promising balance between performance efficiency and computational resource utilization in emergency logistics.
- 29 November 2024
- Published by World Scientific Pub Co Pte Ltd in Unmanned Systems
- Vol. 14 (01) , 95-117
A Particle Swarm Optimizer with Biased Exploration and Exploitation for High-Dimensional Optimization and Feature Selection
Autonomous intelligent systems have been widely implemented in a broad range of applications. These applications often involve data-dense tasks where an efficient feature selection process is required to eliminate redundant features and improve model performance. However, the feature selection tasks with high dimensionality still remain challenging to deal with. In order to address high-dimensional feature selection problems with greater effectiveness and efficiency, this paper proposes a particle swarm optimizer variant named PSO-BEE that allows the swarm to take full advantage of exploration and exploitation at due evolutionary stages. At the early stage, a large size of candidate exemplar group is formed for diversity enhancement, attempting to find as many new combinations of features as possible. At the later stage, a tiny size of candidate exemplar group is constructed, allowing updated particles to learn from the few best elite exemplars to continuously refine feature selection solutions with a lower classification error rate. Three PSO-BEE variants with distinct preferences for exploration and exploitation are proposed based on different parameter adjustment strategies. Experiments are executed on 500, 1000, and 2000-dimensional benchmark suites presented by CEC and real-world feature selection datasets from the Machine Learning Repository. Experimental results demonstrate the competitive performance of PSO-BEE in high-dimensional global optimization and feature selection when compared with several state-of-the-art approaches.
- 29 November 2024
- Published by World Scientific Pub Co Pte Ltd in Unmanned Systems
- Vol. 14 (01) , 95-117
A Particle Swarm Optimizer with Biased Exploration and Exploitation for High-Dimensional Optimization and Feature Selection
Autonomous intelligent systems have been widely implemented in a broad range of applications. These applications often involve data-dense tasks where an efficient feature selection process is required to eliminate redundant features and improve model performance. However, the feature selection tasks with high dimensionality still remain challenging to deal with. In order to address high-dimensional feature selection problems with greater effectiveness and efficiency, this paper proposes a particle swarm optimizer variant named PSO-BEE that allows the swarm to take full advantage of exploration and exploitation at due evolutionary stages. At the early stage, a large size of candidate exemplar group is formed for diversity enhancement, attempting to find as many new combinations of features as possible. At the later stage, a tiny size of candidate exemplar group is constructed, allowing updated particles to learn from the few best elite exemplars to continuously refine feature selection solutions with a lower classification error rate. Three PSO-BEE variants with distinct preferences for exploration and exploitation are proposed based on different parameter adjustment strategies. Experiments are executed on 500, 1000, and 2000-dimensional benchmark suites presented by CEC and real-world feature selection datasets from the Machine Learning Repository. Experimental results demonstrate the competitive performance of PSO-BEE in high-dimensional global optimization and feature selection when compared with several state-of-the-art approaches.
- 31 August 2023
- Published by Springer Nature
- p. 360-375
An Investigation on the Effects of Exemplars Selection on Convergence and Diversity in Large-Scale Particle Swarm Optimizer
- 31 August 2023
- Published by Springer Nature
- p. 360-375
An Investigation on the Effects of Exemplars Selection on Convergence and Diversity in Large-Scale Particle Swarm Optimizer
- 22 July 2022
- Published by Institution of Engineering and Technology (IET) in IET Conference Proceedings
- Vol. 2022 (5) , 1201-1205
Fault location method for MMC-HVDC transmission line based on adaptive optimal feature reconstruction
Applying the regression mechanism of intelligent algorithm to transmission line fault location is a new research direction in recent years.The location accuracy of such methods largely depends on the feature selection of the training samples of the algorithm model.This paper proposes a feature extraction method that combines regression algorithm, waveform decomposition and optimization algorithm, which can adaptively extract optimal features according to training samples, thereby ensuring the location accuracy of the algorithm model to the greatest extent. Through the test in a MMC-HVDC transmission line simulation model, the optimal feature reconstruction method proposed in this paper can greatly improve the fault location accuracy of transmission line, and has good location performance in case of high resistance grounding fault.
- 22 July 2022
- Published by Institution of Engineering and Technology (IET) in IET Conference Proceedings
- Vol. 2022 (5) , 1201-1205
Fault location method for MMC-HVDC transmission line based on adaptive optimal feature reconstruction
Applying the regression mechanism of intelligent algorithm to transmission line fault location is a new research direction in recent years.The location accuracy of such methods largely depends on the feature selection of the training samples of the algorithm model.This paper proposes a feature extraction method that combines regression algorithm, waveform decomposition and optimization algorithm, which can adaptively extract optimal features according to training samples, thereby ensuring the location accuracy of the algorithm model to the greatest extent. Through the test in a MMC-HVDC transmission line simulation model, the optimal feature reconstruction method proposed in this paper can greatly improve the fault location accuracy of transmission line, and has good location performance in case of high resistance grounding fault.