Fuzzy-neuro System Research Articles

Chaotic Interval Type-2 Fuzzy Neuro-oscillatory Network (CIT2-FNON) for Worldwide 129 Financial Products Prediction

In this paper, the author proposes an innovative Chaotic Interval Type-2 Fuzzy Neuro-oscillatory Network (CIT2-FNON) for worldwide financial prediction. Inspired by the author’s original work on Lee-oscillator—a chaotic discrete-time neural oscillator with profound transient-chaotic property, CIT2-FNON provides: (1) effective modeling of Interval Type-2 Fuzzy Logic with Chaotic Transient-Fuzzy Membership Function (CTFMF); and (2) time-series recurrent neural network training and prediction with Chaotic Bifurcation Transfer Function (CBTF). Different from the contemporary research on Type-2 Fuzzy Logic Systems (T2FLS) which mainly focus on the RD and (2) different from contemporary fuzzy-neuro systems which focus on the integration of fuzzy logic and neural networks as separated functional modules, the CIT2-FNON introduced in this paper is constructed by Lee-oscillators which serves as “transient-fuzzy input neurons” of the recurrent network and effectively converts it into CT2TFL system. In other words, the chaotic transient-fuzzification process is actually part of the neural model of the CIT2-FNON. From the implementation perspective, CIT2-FNON is integrated with 2048-trading day time-series financial data and Top-10 major financial signals as financial fuzzy signals (FFS) for the real-time prediction of 129 worldwide financial products.

Comparative study of maximum power point tracking techniques for hybrid renewable energy system

ABSTRACTThe power generation demand is increasing day-by-day throughout the world, therefore, the use of hybrid systems becomes a significant solution. The hybrid renewable energy system (HRES) is used for delivering power in various regions in order to overcome intermittence of wind and solar resources. Because of increasing environmental problems, for example, greenhouse gas emission and energy cost have interested novel research into substitute methods in favour of electrical power generation. Maximum Power Point Tracking (MPPT) control method is a vast deal of novel research used for enhancing the efficiency of HRES. The authors have revealed that the hybrid techniques i.e. Global MPPT, fuzzy-neuro systems, Adaptive Neuro-Fuzzy Inference System (ANFIS), Perturbed and Observe (P&O) + Adaptive Neural Network (ANN) etc. can provide best results as compared to other MPPT control methods. This paper offering a state of art review of MPPT control techniques for HRES.

FNDSB: A fuzzy-neuro decision support system for back pain diagnosis

Back pain is a common pain felt in the back. In the world, it is the fifth common reason for physician visits and in the U.S. about 90% of human adults have back pain at some time in their life. In this paper, we proposed a decision support system for intelligent diagnosis of back pain using a fuzzy-neuro technique to manage the fuzzy concepts. It is also provide an intelligent decision support platform that can assist physicians to diagnose and produce accurate medical advices. The proposed system consists of a user interface that receive symptoms and produce accurate diagnosis with its severity, a fuzzy inference system which contains the strategies of reasoning process based on fuzzification and defuzzification techniques, a fuzzy-neuro system that composed of neural network with fuzzy logic concepts, and a knowledge base which collects of linguistic fuzzy rules. The FNDSB describe knowledge acquisition and representation methods, a way of production linguistic fuzzy rules organization, fuzzification and defuzzification of clinical parameters as input and output values using a Triangular Membership Function (TMF) and Centroid of Area (CoA) techniques respectively. The FNDSB was evaluated using a case study of 10 patients from Al-diwaniyah teaching hospital. According to the evaluation results the system performance around 83.6% efficiency in producing accurate back pain diagnosis.

Intelligent control for avoiding the joint limits of redundant planar manipulators

This article presents an intelligent control system for a redundant manipulator to avoid physical limits such as joint angle limits and joint velocity limits. In this method, a back-propagation neural network (NN) is introduced for the kinematic inversion of the manipulator. Since this inverse kinematics has an infinite number of joint angle vectors, a fuzzy-neuro system is constructed to provide an approximate value for that vector. This vector is fed into the NN as a hint input vector in order to guide the output of the NN within the self-motion. Simulations and a comparative study are made based on a four-link redundant manipulator to prove the efficacy of the proposed control system.

S6 ファジィニューロシステムを用いたゴルフクラブの感覚的評価方法に関する研究(ゴルフ(1))

Development of sporting equipment made considerable advance for CAE (computer-aided engineering). CAE is a computer simulation method for measuring the characteristic of dynamics from the design of the appearance of sporting equipment. Many such evaluation methods are studied by various organizations. Most of these methods evaluate the physical characteristics of the sporting equipment. However, they do not consider the preference of players when a player evaluates the sporting equipment. And demands based on the personal preference of each player are very important in producing many different kinds of sporting equipment. In other words, an evaluation method baced on human subjectivity is needed in order to support the development of sporting equipment. In this research, the authors consider that player evaluation is related to the physical characteristics and investigate the evaluation process. In the model, a fuzzy neuro system that deals with the human subjectivity is used. The author's propose that an evaluation method of sporting equipment based on human subjectivity in order to support the development of sporting equipment.

ファジィニューロシステムを用いたスポーツ用具の評価方法に関する研究(釣り,スポーツ全般)

ファジィニューロシステムを用いたスポーツ用具の評価方法に関する研究(釣り,スポーツ全般)

Development of a Fuzzy-Neuro System for Parameter Resetting of Injection Molding

An intelligent system has been used for injection molding. Five molded part defects, two mold parameters and the part weight are used as system inputs which are described by fuzzy terms. Twenty process parameter adjusters on an injection molding machine are used as the outputs. A neural network has been trained using the data obtained from test-runs of injection molding. The intelligent system can predict the amount to be adjusted for each parameter towards reducing or eliminating the observed defects. Using this system for the parameter resetting, production time and efforts can be saved drastically. Feasibility studies showed that this intelligent system is capable of reducing the test run time by at least 80 percent.

Automatic fault detection in gearboxes by dynamic fuzzy data analysis

The main objective of machine diagnosis is the early recognition of mechanical defects in a machine, which is often referred to as preventive maintenance. This may result in the reduction of faults and higher machine availability. Preventive maintenance can be performed periodically in fixed time intervals, by demand due to machine faults, or continuously, depending on the state of a machine. To minimize maintenance and repair time, state-dependent maintenance of machines is usually applied. It assumes precise and reliable monitoring of machine's states, which is often provided by an expert who can distinguish malfunctions in operation from other changes in machine's states. In Fuzzy-Neuro Systems '98 — Computational Intelligence, pp. 98–105, and Int. J. Fuzzy Sets and Systems 105 (1999) 81–90, we have introduced a clustering method for dynamic objects, i.e., objects which are described by (time) trajectories of features. The aim of this paper is to show exemplarily that this method can be used for early recognition of changes in a machine's state and thus for automatic fault detection. Moreover, the method can be applied to automatic feature selection. A major advantage of this method is that it requires less expert knowledge than traditional approaches.

ファジィ・ニューラルネットワーク複合システムの特徴と適用例(<特集>ファジィ・ニューラルネットワーク)

ファジィ・ニューラルネットワーク複合システムの特徴と適用例(<特集>ファジィ・ニューラルネットワーク)