• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.8
• /
• pp.1195-1200
• /
• 2013

In this paper, we proposed an enhanced Max-Min neural network by auto-tuning of learning rate using fuzzy control method. For the reduction of training time required in the competition stage, the method was proposed that arbitrates dynamically the learning rate by applying the numbers of the accuracy and the inaccuracy to the input of the fuzzy control system. The experiments using real concrete crack images showed that the enhanced Max-Min neural network was effective in the recognition of direction of the extracted cracks.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.776-782
• /
• 2004

Generally, Max-Min CRI (Compositional Rule of Inference ) method by Zadeh and Mamdani is used in the conventional fuzzy inference. However, owing to the problems of Max-Min CRI method, the inference often results in significant error regions specifying the difference between the desired outputs and the inferred outputs. In this paper, I propose a New Max-Min CRI method which can solve some problems of the conventional Max-Min CRI method. And then this method is simulated in a D.C.series motor, which is a bench marking system in control systems, and showed that the new method performs better than the other fuzzy inference methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.1
• /
• pp.15-21
• /
• 2004

This paper deals with asymptotic stabilization problems for linear systems with time-varying input disturbances. In order to eliminate the influence of a disturbance on the system, a disturbance observer is designed and the time-varying disturbance can be rejected using its estimated value. Since the disturbance observer is kind of low-pass filter, it has inevitably estimation errors. To eliminate the inflences on the performance due to these errors, the additional control is designed based on these estimation errors using a well-known min-max control method. It is shown that the asymptotic stability of the closed-loop system is guaranteed. In general, the min-max control method requires the switching of control inputs and the switching magnitude of the control input is determined by the disturbance estimation error bounds. As the error bounds can be made arbitrarily small by choosing the high gain for the disturbance observer, the control method suggested in this paper can reduce the chattering phenomena as small as possible. Therefore, it has superior performance to the existing ones.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.367-367
• /
• 2000

In this paper, an Adaptive neuro-fuzzy Inference system(ANFIS) using fuzzy min-max network(FMMN) is proposed. Fuzzy min-max network classifier that utilizes fuzzy sets as pattern classes is described. Each fuzzy set is an aggregation of fuzzy set hyperboxes. Here, the proposed method transforms the hyperboxes into gaussian membership functions, where the transformed membership functions are inserted for generating fuzzy rules of ANFIS. Finally, we applied the proposed method to the classification problem of iris data and obtained a better performance than previous works.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1457-1464
• /
• 2011

In this paper, we go one step further in that the number of competitive layers is not determined by experience but can be determined by fuzzy control rules based on input pattern information. In our method, we design a set of membership functions and corresponding rules and used Max-Min reasoning proposed by Mamdani. Also, we use centroid method as a defuzzification. In experiment that has various patterns of English inputs, this new method works beautifully to determine the number of competitive layers and also efficient in overall accuracy as a result.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.9
• /
• pp.33-38
• /
• 2014

The FCM based hybrid RBF network is a heterogeneous learning network model that applies FCM algorithm between input and middle layer and applies Max_Min algorithm between middle layer and output. The Max-Min neural network uses winner nodes of the middle layer as input but shows inefficient learning in performance when the input vector consists of too many patterns. To overcome this problem, we propose a dynamic learning rate control based on fuzzy logic. The proposed method first classifies accurate/inaccurate class with respect to the difference between target value and output value with threshold and then fuzzy membership function and fuzzy decision logic is designed to control the learning rate dynamically. We apply this proposed RBF network to the character recognition problem and the efficacy of the proposed method is verified in the experiment.

• Water for future
• /
• v.19 no.4
• /
• pp.339-346
• /
• 1986

A real-time single reservoir operation model using the Min-max Dynamic Programming for the flood control of Soyanggang Dam and Choongju Dam is developed. The objective function is to minimize the maximum release from each dam and the constraints are those from ther reservoir and channel characteristics. Control and utilization efficiencies are used to measure the performance of the reservoir operation method (ROM). In comparison with those of simulation models(such as the Rigid ROM, the Technical ROM and the Linear Decision Rule), the efficiencies of the optimization model are superior for all return periods.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.11
• /
• pp.167-173
• /
• 2002

The look up table method conventionally applied to control the inner temperature and humidity of a laver drying machine has repeatedly occurred not only laver's damage but also inferior goods since the reaching time at the optimum state takes a long time. In this paper, a fuzzy control theory instead of the look up table was proposed to reduce the reaching time at the optimum state. The proposed method used six input variables and four output variables for the fuzzy control, and a triangle rule for a fuzzifier, The Mandani's min-max method was applied to a fuzzy inference. Also, the mean method of maximum was applied to a defuzzifier. The method applied to the fuzzy controller contributed to reduce the reaching time at the optimum state, and to minimize not only laver's damage but also inferior goods.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.106.2-106
• /
• 2001

The two typical composite operations of fuzzy relation are the max-min and the min-max composite operations. It is known that the two operations can be completely dual. This paper pays attention to the nature that these two typical operations are completely dual and investigates the correlation between the max-min composite relation equation and the min-max composite relation equation. An important scheme of correlation is in the characteristic of solution sets derived from these two fuzzy relation equations. The paper explains that one of the composite fuzzy relation equations is solvable using the solution method of the other fuzzy relation equation. The above-mentioned duality plays an important role in this solution procedure. Since it is not necessary to build the solution method separately like before, calculation efficiency can be raised. Moreover, the solution for the relation ...

• Proceedings of the IEEK Conference
• /
• 2001.06a
• /
• pp.379-382
• /
• 2001

In this paper, a new enhanced early fair rate allocation(EFRA＋) algorithm is proposed for ATM switches supporting ABR service. The central issue of explicit rate control algorithms for ABR service is the computation of max-min fair rates for every connection. The EFRA＋ inherits the main feature of the EFRA, uses the connection control information during the connection setup to prevent potential congestion in switches, and enhances the computation method of the max-min fair rate.