János Botzheim

Improvements to the bacterial memetic algorithm used for fuzzy rule base extraction

In this paper we discuss new methods to improve the bacterial memetic algorithm (BMA) used for fuzzy rule base extraction. The first two methods are knot order violation handling methods which improves the performance of the BMA rather in the case of more complex fuzzy rule base. The third method is a new modification of the BMA in which the order of the operators is modified. This method improves the performance of the BMA rather in the case of less complex fuzzy rule base.

A novel multimodal communication framework using robot partner for aging population

It is expected that the population of elderly in the world will double in 2050.This paper proposes a human-friendly robot partner to assist the elderly.A new communication framework between the human and robot partner is developed.Informationally structured space was proposed to realize natural communication.Experiments using three case studies show the strength of the proposed framework. In developed country such as Japan, aging has become a serious issue, as there is a disproportionate increasing of elderly population who are no longer able to look after themselves. In order to tackle this issue, we introduce human-friendly robot partner to support the elderly people in their daily life. However, to realize this, it is essential for the robot partner to be able to have a natural communication with the human. This paper proposes a new communication framework between the human and robot partner based on relevance theory as the basis knowledge. The relevance theory is implemented to build mutual cognitive environment between the human and the robot partner, namely as the informationally structured space (ISS). Inside the ISS, robot partner employs both verbal as well as non-verbal communication to understand human. For the verbal communication, Rasmussens behavior model is implemented as the basis for the conversational system. While for the non-verbal communication, environmental and human state data along with gesture recognition are utilized. These data are used as the perceptual input to compute the robot partners emotion. Experimental results have shown the effectiveness of our proposed communication framework in establishing natural communication between the human and the robot partner.

Comparison of Various Evolutionary and Memetic Algorithms

Optimization methods known from the literature include gradient based techniques and evolutionary algorithms. The main idea of the former methods is to calculate the gradient of the objective function at the actual point and then to step towards better values according to this function value. Evolutionary algorithms imitate a simplified abstract model of evolution observed in the nature. Memetic algorithms traditionally combine evolutionary and other, e.g. gradient techniques to exploit the advantages of both methods. Our current research aims to discover the properties, especially the efficiency (i.e. the speed of convergence) of particular evolutionary and memetic algorithms. For this purpose the techniques are compared by applying them on several numerical optimization benchmark functions and on machine learning problems.

Bacterial memetic algorithm for offline path planning of mobile robots

The goal of the path planning problem is to determine an optimal collision-free path between a start and a target point for a mobile robot in an environment surrounded by obstacles. This problem belongs to the group of combinatorial optimization problems which are approached by modern optimization techniques such as evolutionary algorithms. In this paper the bacterial memetic algorithm is proposed for path planning of a mobile robot. The objective is to minimize the path length and the number of turns without colliding with an obstacle. The representation used in the paper fits well to the algorithm. Memetic algorithms combine evolutionary algorithms with local search heuristics in order to speed up the evolutionary process. The bacterial memetic algorithm applies the bacterial operators instead of the genetic algorithm’s crossover and mutation operator. One advantage of these operators is that they easily can handle individuals with different length. The method is able to generate a collision-free path for the robot even in complicated search spaces. The proposed algorithm is tested in real environment.

Estimating fuzzy membership functions parameters by the Levenberg-Marquardt algorithm

In previous papers from the authors fuzzy model identification methods were discussed. The bacterial algorithm for extracting fuzzy rule base from a training set was presented. The Levenberg-Marquardt algorithm was also proposed for determining membership functions in fuzzy systems. In this paper the Levenberg-Marquardt technique is improved to optimise the membership functions in the fuzzy rules without Ruspini-partition. The class of membership functions investigated is the trapezoidal one as it is general enough and widely used. The method can be easily extended to arbitrary piecewise linear functions as well.

Human gesture recognition for robot partners by spiking neural network and classification learning

Recently, the rate of elderly people rises in the super-aging society. Human-friendly robots can be used to support the mental and physical care for elderly people and to assist the care of caregivers to elderly people. Robotic conversation can activate the brain of such elderly people and improve their concentration and memory abilities. However, it is difficult for a robot to converse appropriately with a person even if many contents of the conversation are designed in advance because the performance of voice recognition is not enough in the daily conversation. Recognition of human gestures is also important in order to perform smooth communication. This paper deals with human gestures recognition using spiking neural network and classification learning. The proposed method is able to handle the cultural differences in the human communication.

Modeling of loss aversion in solving fuzzy road transport traveling salesman problem using eugenic bacterial memetic algorithm

The aim of the traveling salesman problem (TSP) is to find the cheapest way of visiting all elements in a given set of cities and returning to the starting point. In solutions presented in the literature costs of travel between nodes (cities) are based on Euclidean distances, the problem is symmetric and the costs are constant and crisp values. Practical application in road transportation and supply chains are often fuzzy. The risk attitude depends on the features of the given operation. The model presented in this paper handles the fuzzy, time dependent nature of the TSP and also gives solution for the asymmetric loss aversion by embedding the risk attitude into the fitness function of the bacterial memetic algorithm. Computational results are presented as well.

Genetic and Bacterial Programming for B-Spline Neural Networks Design

The design phase of B-spline neural networks is a highly computationally complex task. Existent heuristics have been found to be highly dependent on the initial conditions employed. Increasing interest in biologically inspired learning algorithms for control techniques such as Artificial Neural Networks and Fuzzy Systems is in progress. In this paper, the Bacterial Programming approach is presented, which is based on the replication of the microbial evolution phenomenon. This technique produces an efficient topology search, obtaining additionally more consistent solutions.

Single-Stroke Character Recognition with Fuzzy Method

In this paper an on-line single-stroke recognition method based on fuzzy logic is introduced. Each of the characters is defined by only one nine dimensional fuzzy rule. In addition to the low resource requirement the solution is able to satisfy many of the user’s current demands in handwriting recognizers, like speed and learning. Eight of the nine features are extracted using a four-by-four grid. For the learning phase we designed a new punish/reward bacterial evolutionary algorithm which tunes the character parameters represented by fuzzy sets.

Comparative Investigation of Various Evolutionary and Memetic Algorithms

Optimization methods known from the literature include gradient techniques and evolutionary algorithms. The main idea of gradient methods is to calculate the gradient of the objective function at the actual point and then to step towards better values according to this value. Evolutionary algorithms imitate a simplified abstract model of evolution observed in nature. Memetic algorithms traditionally combine evolutionary and gradient techniques to exploit the advantages of both methods. Our current research aims to discover the properties, especially the efficiency (i.e. the speed of convergence) of particular evolutionary and memetic algorithms. For this purpose the techniques are compared on several numerical optimization benchmark functions and on machine learning problems.