Yukinobu Hoshino

PSO training of the Neural Network application for a controller of the line tracing car

In this research, a fuzzy controller system is useful as a key technique to design a machine controller because a fuzzy system can be designed by fuzzy sets, which can be represented using linguistic descriptions of natural language. Those natural languages are able capture human knowledge in fuzzy rules. A fuzzy controller system consists of fuzzy rules and involved techniques. Recently, the research of the fuzzy control has controlled various machines. We verified that fuzzy control can be applicable to a line tracing car control, which is running at a high speed. In our research, designers took a huge amount of time to adjust and setup the fuzzy controller. In order to apply the Neural Network (NN) controller, we designed a simple network system, and setup a PSO_VC and parameters. The PSO_VC (a PSO with Velocity Control) is a speed control strategy for all moving particles on the PSO. In order to configure the NN, a very powerful and quick PSO_VC is used. The PSO_VC is able to adjust all weights and threshold levels. In this paper we present the performances of accurate control and compare results between fuzzy controller and the NN controller.

A Proposed Model of Diagnosis and Prescription in Oriental Medicine Using RBF Neural Networks

In this paper, we present a computing model for diagnosis and prescription in oriental medicine. Inputs to the model are severities of symptoms observed on patients and outputs from the model are a diagnosis of disease states and treatment herbal prescriptions. First, having used rule inference with a Gaussian distribution, the most serious disease state in which the patient appears to be infected is determined. Next, an herbal prescription written in suitable herbs with reasonable amounts for treating the infected disease state is given by RBF neural networks. Finally, we show some experiments and their evaluations, and then describe our future works.

A Fuzzy Clustering Based Selection Method to Maintain Diversity in Genetic Algorithms

Optimization requirements often include finding various solutions and search under muti-objective situations. A maintaining diversity of individuals is one of the effective approaches to meet the requirements. Our research aims to maintain the diversity. We also propose a fuzzy clustering based selection method to maintain the diversity and apply the selection method to genetic algorithm (GA). The selection method determines the individual selection probabilities based on fitness values and membership values, which are given by a fuzzy clustering. Here, a preparing a sub-population is one of the effective ways to maintain the diversity. The proposed selection method is treated as a getting the sub-population method by the fuzzy clustering. We also discuss about behavior and search capability of the GA with the proposed selection method via some simulations. Based on results of the simulations, we were able to find out that the GA makes the individuals widely distributed in a solution space.

Townscape Color Planning System Using an Evolutionary Algorithm and Kansei Evaluations

Townscape colours have been a main issue in urban-development. For townscape colours, keeping colour harmony within the environment is a common goal. Expressing characteristics and impressions of the town in townscape colours are other meaningful goals. This paper describes the colour planning support system intended to improve town-scapes. The system offers some colour combination proposals based on three elements: colour harmony, impressions of the townscape, and cost for the change of colours. First, we develop evaluation models to quantify colour harmony and impression of the townscape from the approach of Kansei engineering. Next, the system is constructed using an evolutionary algorithm and the two evaluation models. After the construction, performance tests are conducted. The results show that our system achieved sufficient ability to propose appropriate colour combinations with minimum colour changes.

A portfolio selection by SOM and an asset allocation of risk/nonrisk assets by fuzzy reasoning using the selected brands

A portfolio is an useful method to calculate the rate of expected earnings and risks based on changes in stock prices. However, past methods such as the fundamental analysis, the technical analysis and etc. are not proposed as a decision support system available for real investments. On the other hand, speaking about the asset allocation, those methods determine asset allocation ratio using general indices such as TOPIX independently of the portfolio selections. This paper describes a novel decision support system for assisting in actual investment decisions. First, the system makes a stock investment brand selection using SOM (self-organizing maps). Secondly, the system calculates asset allocation ratio of risk/nonrisk assets using both fuzzy reasoning and the management indices of the brands selected by SOM. We apply this method to actual stock price data and show better results than those by TOPIX. Finally, we discuss an effectiveness of the proposed support system against a steep fall in stock prices, such as IT Bubble collapse that began in 2000.

Development of estimation method about activity states for NIRS-based BCI system

In recent years, BCI (Brain-Computer Interface) is attracting attention as a method of providing an ALS (amyotrophic lateral sclerosis) patient with an alternative communication means. NIRS (near-infrared spectroscopy) is a non-invasive technology that is able to measure changes in cerebral blood flow. This research rewords development of a BCI system, which can be used to operate a machine by recollecting the image of hand movement. As the fundamental experiment, we measured brain activity during hand movement using a NIRS. In this paper, we describe the estimation approach about the start and end timings hand of movement using a neural network. In addition, we describe a method for classifying into right- or left-hand movement from NIRS signals.

Applying Fuzzy Logic and Neural Network to Rheumatism Treatment in Oriental Medicine

In this paper, we present an application of soft computing into a decision support system RETS: Rheumatic Evaluation and Treatment System in Oriental Medicine (OM). Inputs of the system are severities of observed symptoms on patients and outputs are a diagnosis of rheumatic states, its explanations and herbal prescriptions. First, an outline of the proposed decision support system is described after considering rheumatic diagnoses and prescriptions by OM doctors. Next, diagnosis by fuzzy inference and prescription by neural networks are described. By fuzzy inference, RETS diagnoses the most appropriate rheumatic state in which the patient appears to be infected, then it gives a prescription written in suitable herbs with reasonable amounts based on neural networks. Training data for the neural networks is collected from experienced OM physicians and OM text books. Finally, we describe evaluations and restrictions of RETS.

An-FPGA Based Classification System by Using a Neural Network and an Improved Particle Swarm Optimization Algorithm

This paper presents a development of a soft intelligent system on chip. This system is used to solve the classification problem. In this system, a neural network is trained by the particle swarm optimization (PSO) algorithm. This algorithm is hardware implemented on a real device. An improved version of the standard PSO algorithm called the PSOseed algorithm is also introduced in this paper in order to reduce the possibility when the standard PSO gets stuck in the local minimum. The experimental results show that the neural network trained by the particle swarm optimization algorithm was successful hardware implemented. In addition, the PSOseed algorithm also obtained a better performance than the standard PSO algorithm in our experiments.

Evaluation of Optimization Methods for Neural Network

In this research, optimization methods are evaluated for Neural Network (NN) learning. NN is used as a classifier in image recognition and learning is important integrant to improve performance. Back Propagation (BP) is a typical NN learning method. However, BP depends on the number of NN layers and the default value of NN weights. Therefore, Particle Swarm Optimization (PSO) is expected as a multipoint search algorithm rather than BP. Nevertheless, PSO has some risks to stop in local minimum in a complex problem. Hence, Random PSO (RPSO), in which PSO is modified, is suggested by the researchers. RPSO does not fall into local minimum by velocity control. This paper shows that NN using RPSO is able to achieve a high discrimination rate and a high learning performance can be expected in solving complex problems. Additionally, RPSO does not depend on the number of NN layers.

A Hardware Implementation of Particle Swarm Optimization with a Control of Velocity for Training Neural Network

This paper describes a study of a feed forward neural network trained by particle swarm optimization with a control of velocity (NN-PSOCV). A hardware implementation of NN-PSOCV coded using SystemVerilog has been developed. Details of each module in the proposed architecture are presented. This paper also shows results of the implementation when tested on a device called a DE1-SoC board. Experimental results demonstrate that NN-PSOCV was successfully implemented. Results also show that the hardware implementation of NN-PSOCV achieved a better performance over the hardware implementation of the neural network trained by original particle swarm optimization.