A5100424555- Advanced Multi-Objective Optimization Algorithms
- Metaheuristic Optimization Algorithms Research
- Evolutionary Algorithms and Applications
- Formal Methods in Verification
- Software Engineering Research
- Mobile Crowdsensing and Crowdsourcing
- Logic, programming, and type systems
- Software Testing and Debugging Techniques
- Rough Sets and Fuzzy Logic
- Open Source Software Innovations
- Guidance and Control Systems
- Metabolomics and Mass Spectrometry Studies
- Logic, Reasoning, and Knowledge
- Computability, Logic, AI Algorithms
- Imbalanced Data Classification Techniques
- Meteorological Phenomena and Simulations
- Cloud Computing and Resource Management
- Opportunistic and Delay-Tolerant Networks
- Robotic Path Planning Algorithms
- Energy Load and Power Forecasting
- Machine Learning and Data Classification
- Distributed systems and fault tolerance
- Stock Market Forecasting Methods
- Machine Learning and ELM
- Random lasers and scattering media
Ocean University of China
2013-2025
Air Force Engineering University
2024-2025
Beijing University of Technology
2023-2024
Nanchang Institute of Technology
2024
Qingdao National Laboratory for Marine Science and Technology
2022
University of Chinese Academy of Sciences
2019
Chinese Academy of Sciences
2010-2018
Guilin University of Electronic Technology
2017
University of Science and Technology of China
2017
Academy of Mathematics and Systems Science
2010-2013
Deep learning has recently achieved great success in many areas due to its strong capacity data process. For instance, it been widely used financial such as stock market prediction, portfolio optimization, information processing and trade execution strategies. Stock prediction is one of the most popular valuable area finance. In this paper, we propose a novel architecture Generative Adversarial Network (GAN) with Multi-Layer Perceptron (MLP) discriminator Long Short-Term Memory (LSTM)...
Abstract Motivation: Protein–RNA interactions play a key role in number of biological processes, such as protein synthesis, mRNA processing, assembly, ribosome function and eukaryotic spliceosomes. As result, reliable identification RNA binding site is important for functional annotation site-directed mutagenesis. Accumulated data experimental protein–RNA reveal that residue with different neighbor amino acids often exhibits preferences its partners, which turn can be assessed by the...
In the field of message-passing interface (MPI) program path coverage test case generation, evolutionary algorithms (EAs) have been frequently utilized to generate cases. However, relying solely on EAs will incur excessive computational costs. this article, we improve efficiency and quality MPI cases generated by based elite individual selection. First, data within domain is sampled fitness calculated form a shared set. Then, population initialized using EAs, individuals predicted neighbor...
ABSTRACT Unmanned aerial vehicles (UAVs) are expected to fully exploit their maneuvering capabilities conduct aggressive maneuvers complete tasks such as racing and aerobatics even in harsh environments. However, most of the related works often focus on slow movements only suitable for regular well‐structured This motivates us propose a highly robust control scheme designed specifically UAV maneuvers, encoded by rapid large changes either position or attitude. The core our approach is...
Dynamic multi-objective optimization problems (DMOPs) have been of interest to many researchers. These are in which the environment changes during evolutionary process, such as Pareto-optimal set (POS) or front (POF). This kind problem imposes more challenges and difficulties for algorithms, mainly because it demands population track changing POF efficiently accurately. In this paper, we propose a new approach combining key-points-based transfer learning hybrid prediction strategies (KPTHP)....
Multidomain network classification has attracted significant attention in data integration and machine learning, which can enhance or prediction performance by integrating information from different sources. Despite the previous success, existing multidomain learning methods usually assume that views are available for same set of instances, thus, they seek a consistent result all domains. However, many real-world problems, each domain its specific instance set, one may correspond to multiple...
Abstract Many research efforts on reinforcement learning (RL) is dedicated to solving challenging combinatorial optimization problems, including the container relocation problem (CRP) arising from maritime industry. In CRP, large and heavy containers are stacked top of each other, those above target should be relocated elsewhere before retrieving it. This problem, which minimizes number relocations in retrieval process, NP-hard, while existing RL studies do not provide satisfactory results...
Message passing interface (MPI) is a powerful tool for parallel computing, originally designed high-performance computing on massively computers. In this paper, we combine FERPSO-IMPR (fitness Euclidean distance ratio particle swarm optimizer with information migration-based penalty and population reshaping) surrogate-assisted models to generate test cases MPI program path coverage testing. our proposed method, employs dual strategy initialize data calculate fitness. Then, create sample set...
Abstract Sea surface temperature (SST) prediction is a subject of great significance to the marine environment and human society. Changes in SST not only impact ecosystems fishery resources but also trigger extreme weather events disastrous consequences. Therefore, precise essential avoiding these problems. Although numerous data-driven models have emerged recent years, are characterized by lack physical mechanisms related sea changes as well insufficient generalization capabilities...
Background: Crowdsourcing, an emerging paradigm to accomplish tasks by calling unknown workers across the internet compete, is gaining more and popularity in various domains. Crowdsourcing task requesters usually offer different bonuses assure desired worker performance. Most existing studies focus on general crowdsourcing market, lead inconsistent observations impact of incentive strategies There a lack investigating this issue complex or intelligent such as software crowdsourcing. Aims: To...
We make a mixture of Milner's $\pi$-calculus and our previous work on truly concurrent process algebra, which is called $\pi_{tc}$. introduce syntax semantics $\pi_{tc}$, its properties based strongly bisimilarities. Also, we include an axiomatization $\pi_{tc}$ can be used as formal tool in verifying mobile systems flavor.