Naofumi Matsumoto

Particle Swarm Optimization with Adaptive Parameters

Particle swarm optimization is an effective evolution algorithm for global optimizing. Based on analysis of particle movements during evolution, parameter p is brought up to control the value of C1 and C2, which effects convergence rate of PSO. Aiming at solving different problems, corresponding p is adopted to improve performance. Particle confidence coefficient q is applied to weigh proper emphasize on itself best solution and global solution. Adaptive value of q is introduced to PSO to satisfy specific situation for each particle. Finally, performance of PSO with parameters p and q is testified by optimizing benchmark functions.

Multi-robot Path Planning Based on Cooperative Co-evolution and Adaptive CGA

Multi-robot path planning is a challenge for mobile robots in AI. Multi-objective optimized algorithm based on cooperative co-evolution and CGA is brought up in this paper. Shortest path length, minimum time cost, smoothest and limited speed, obstacle-collide free and robot-collide free are the objectives and constraints to optimize. Linear combination of them is designed as evaluation function for CGA with self-adaptive crossover and mutation rate, combined with chaos disturbs. Finally 2D dynamic simulation has proved the efficiency of the algorithm.

Proposing a high performance face detector based on UKF

In this paper, we propose a high performance algorithm for detecting human faces in a still image. Human faces help to communicate and interact in a better way that may be either in human-human interaction or human-machine interaction. The success points for our algorithm is the use of different individual algorithms along with the Unscented Kalman filter (UKF) process, as a novelty of our process. We have modified the algorithms as well. We used Viola Jones eye detector, skin color detector and the Haar cascade classifier for face detection process. Finally, we have conducted a benchmark test for our proposed algorithm using image databases of CMU-MIT, MIT training sets, INRIA Graz-01, and FDDB database. Then, we clarify its effectiveness using ROC curves.