Chuanhua Zeng

Learn More
A central problem in reinforcement learning is balancing exploration-exploitation dilemma in non-stationary environment. To address this problem, a data-driven Q-learning is presented. In this study, firstly, the information system of behavior is formed by experience of agent. Then the trigger mechanism of environment is constructed to trace changes of(More)
A new method based on rough set theory to classify goods is put forward in this paper. Firstly, we set up a decision table of goods classification; secondly we get some certain rules from this decision table and get a new totally disharmonious decision table by deleting the objects, which can be identified by these certain rules; finally, we get the(More)
A sort of software for peanut shape identification based on artificial neural network was developed. Images of peanut which is advantageous for carries on the characteristic extraction were acquired by means of red component extraction, filter, image division, edge examination, and so on. The method to describe the shape of irregular peanut was studied, in(More)
Particle Swarm Optimization (PSO) is an effective tool in solving optimization problems. However, PSO usually suffers from the premature convergence due to the quick losing of the swarm diversity. In this paper, we first analyze the motion behavior of the swarm based on the probability characteristic of learning parameters. Then a PSO with double learning(More)