A5103082616- Advanced Multi-Objective Optimization Algorithms
- Metaheuristic Optimization Algorithms Research
- Vehicle Routing Optimization Methods
- Advanced Text Analysis Techniques
- Evolutionary Algorithms and Applications
- Emotions and Moral Behavior
- Software Engineering Techniques and Practices
- Topic Modeling
- Advanced Image Fusion Techniques
- Advanced Manufacturing and Logistics Optimization
- Vehicle License Plate Recognition
- Optimization and Packing Problems
- Mindfulness and Compassion Interventions
- Text and Document Classification Technologies
- Robotic Path Planning Algorithms
- Image and Video Quality Assessment
- Software System Performance and Reliability
- Child and Adolescent Psychosocial and Emotional Development
- Optimal Experimental Design Methods
- Multi-Agent Systems and Negotiation
- Transportation and Mobility Innovations
- Advanced Image Processing Techniques
- Psychological Well-being and Life Satisfaction
- Child Abuse and Trauma
- Advanced Control Systems Optimization
Southern University of Science and Technology
2021-2024
City University of Hong Kong
2024
Harbin Institute of Technology
2023
In dealing with the expensive multiobjective optimization problem, some algorithms convert it into a number of single-objective subproblems for optimization. At each iteration, these conduct surrogate-assisted on one or multiple subproblems. However, may be unnecessary resolved. Operating such can cause server inefficiencies, especially in case To overcome this shortcoming, we propose an adaptive subproblem selection (ASS) strategy to identify most promising further modeling. better leverage...
This article proposes utilizing a single deep reinforcement learning model to solve combinatorial multiobjective optimization problems. We use the well-known traveling salesman problem (MOTSP) as an example. Our proposed method employs encoder-decoder framework learn mapping from MOTSP instance its Pareto-optimal set. Specifically, it leverages novel routing encoder extract information for both entire aspect and every individual objective instance. The global embeddings each objective's are...
Heuristics are commonly used to tackle various search and optimization problems. Design heuristics usually require tedious manual crafting with domain knowledge. Recent works have incorporated Large Language Models (LLMs) into automatic heuristic search, leveraging their powerful language coding capacity. However, existing research focuses on the optimal performance target problem as sole objective, neglecting other criteria such efficiency scalability, which vital in practice. To this...
The dual-factor model (DFM) of mental health has received increasing support in recent years. However, researchers have limited knowledge regarding the longitudinal changes DFM health. This study considered among adolescents using latent profile analysis (LPA). It explored impact childhood maltreatment on transition (LTA). sample comprised who reported depression, anxiety, and life satisfaction. An interpretable LTA solution identified three classes: flourishing, moderately mentally healthy,...
Multiobjective evolutionary algorithms (MOEAs) are major methods for solving multiobjective optimization problems (MOPs). Many MOEAs have been proposed in the past decades, of which search operators need a carefully handcrafted design with domain knowledge. Recently, some attempts made to replace manually designed learning-based (e.g., neural network models). However, much effort is still required designing and training such models, learned might not generalize well on new problems. To...
As a research hotspot across logistics, operations research, and artificial intelligence, route planning has become key technology for intelligent transportation systems. Recently, data-driven machine learning heuristics, including construction methods improvement methods, have achieved remarkable success in solving single-objective problems. However, many practical scenarios must simultaneously consider multiple conflict objectives. For example, modern logistics companies often need to...
Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities. However, existing benchmarks predominantly focused on simplified or isolated aspects of programming, such as single-file code generation repository issue debugging, falling short measuring the full spectrum challenges raised by real-world programming activities. To this end, we propose DevBench, a comprehensive benchmark that evaluates LLMs across various stages software development...
Abstract This study investigates the relationship between labor values and two forms of envy—benign malicious—as well as potential mediating role mindfulness using a reperceiving model. Two thousand three hundred sixty Chinese teenagers participated in longitudinal over an eight-month period, completing questionnaires measuring values, benign envy, malicious mindfulness. The cross-sectional data showed that had immediate negative effect on with partially this relationship. Additionally,...
The min-max vehicle routing problem (min-max VRP) traverses all given customers by assigning several routes and aims to minimize the length of longest route. Recently, reinforcement learning (RL)-based sequential planning methods have exhibited advantages in solving efficiency optimality. However, these fail exploit problem-specific properties representations, resulting less effective features for decoding optimal routes. This paper considers process VRPs as two coupled optimization tasks:...
Neural combinatorial optimization (NCO) is a promising learning-based approach to solving complex problems such as the traveling salesman problem (TSP), vehicle routing (VRP), and orienteering (OP). However, how efficiently train powerful NCO solver for remains crucial challenge. The widely used reinforcement learning method suffers from sparse rewards low data efficiency, while supervised requires large number of high-quality solutions (i.e., labels) that could be costly obtain. In this...
Heuristics are commonly used to tackle diverse search and optimization problems. Design heuristics usually require tedious manual crafting with domain knowledge. Recent works have incorporated large language models (LLMs) into automatic heuristic leveraging their powerful coding capacity. However, existing research focuses on the optimal performance target problem as sole objective, neglecting other criteria such efficiency scalability, which vital in practice. To this challenge, we propose...