JWJinyan Wang

Jinyan Wang

*This is an algorithmically generated author record based on publicly available information.

Jinyan Wang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Two-Phase Multiobjective Local Search for the Device Allocation in the Distributed Integrated Modular Avionics

    by Qing Zhou, Jinyan Wang, Guoquan Zhang, Keqing Guo, Xinye Cai, Lisong Wang, Yuhua Huang

    In the distributed integrated modular avionics (DIMA), it is desirable to assign the DIMA devices to the installation locations of the aircraft for obtaining the optimal quality and cost, subject to the resource and safety constraints. Currently the routine device assignments in DIMA are conducted manually or by experience, which becomes more and more difficult with the increasing number of devices. Especially in the face of large-scale device assignment problems (DAPs), manual allocation will become an almost impossible task. In this paper, a bi-objective safety-constraint device assignment model in DIMA is formulated with the integer encoding for better scalability. A two-Phase multiobjective local search (2PMOLS) is proposed for addressing it. In the first phase of 2PMOLS, the fast convergence of the population towards the Pareto front (PF) is achieved by the weighted sum approach. In the second phase, Pareto local search is conducted on the solutions delivered in the first phase for the extension of the PF approximation. 2PMOLS is compared with three decomposition-based approaches and one domination-based approach on DAPs of different sizes in the experimental studies. The experimental results show that 2PMOLS outperforms all the compared algorithms, in terms of both the convergence and diversity. It has also been demonstrated that the solution obtained by 2PMOLS is better in terms of both objectives (mass and ship set costs), compared with the solution designed by the domain expert. The experimental results show that 2PMOLS performs increasingly better with the increase of the problem size, compared with other algorithms, which indicates it has better scalability.


  • A Multi-agent Simulation for the Research on the Market Equilibrium Phenomena Using Q-Network Algorithm

    by Jinyan Wang, Bo Chen

    For the problems related to market equilibrium in complex market environments, analyses are conducted in the past, using some mathematical models and the game theory. These methods are based on the economic structural equations themselves, ignoring the interactions between economic subjects, and the hypothesis of subject homogeneity has no reference in the real world. On contrast, this paper proposes a multi-agent simulation model, from the microscopic point of view. In such simulation, agents interact with each other, and the decisions are made by agent-embedded AI systems, the Q-network. Therefore, there is no need to elaborate the behavioral rule for each agent, or manually set up too many assumptions. This paper assumes that the simulated market operates in a hypothetical way, in which there are two types of economic entities, namely, banks and enterprises. Banks and enterprises lending behaviors lead to a symbiotic relationship between the banks and the enterprises, while business-to-business transactions make the enterprises symbiotically compete with each other. In the experiment, the observed behavior of each agent can be reasonably explained. Agents endogenously generate intelligent behavioral patterns compatible with the environment. Therefore, this AI-based method can replace the artificially designated decision-making strategy in simulations of market, thus facilitating related economic researches.