Collaborative fuzzy rule learning for Mamdani type fuzzy inference system with mapping of cluster centers

A search in the literature reveals that the use of fuzzy inference system (FIS) in criterion-referenced assessment (CRA) is not new. However, literature describing how an FIS-based CRA can be implemented in practice is scarce. Besides, for an FIS-based CRA, a large set of fuzzy rules is required and it is a rigorous work in obtaining a full set of rules. The aim of this chapter is to propose an FIS-based CRA procedure that incorporated with a rule selection and a similarity reasoning technique, i.e., analogical reasoning (AR) technique, as a solution for this problem. AR considers an antecedent with an unknown consequent as an observation, and it deduces a conclusion (as a prediction of the consequent) for the observation based on the incomplete fuzzy rule base. A case study conducted in Universiti Malaysia Sarawak is further reported.

Download Full-text

Genetic fuzzy system for prediction of respiratory rate of chicks subject to thermal challenges

Revista Brasileira de Engenharia Agrícola e Ambiental ◽

10.1590/1807-1929/agriambi.v22n6p412-417 ◽

2018 ◽

Vol 22 (6) ◽

pp. 412-417 ◽

Cited By ~ 4

Author(s):

Patrícia F. P. Ferraz ◽

Tadayuki Yanagi Junior ◽

Yamid F. Hernandez-Julio ◽

Gabriel A. e S. Ferraz ◽

Maria A. J. G. Silva ◽

...

Keyword(s):

Respiratory Rate ◽

Fuzzy Inference System ◽

Prediction Accuracy ◽

Fuzzy Inference ◽

Fuzzy Rule ◽

System Model ◽

Inference System ◽

Rule Based ◽

Rule Based System ◽

Genetic Fuzzy System

ABSTRACT The aim of this study was to estimate and compare the respiratory rate (breath min-1) of broiler chicks subjected to different heat intensities and exposure durations for the first week of life using a Fuzzy Inference System and a Genetic Fuzzy Rule Based System. The experiment was conducted in four environmentally controlled wind tunnels and using 210 chicks. The Fuzzy Inference System was structured based on two input variables: duration of thermal exposure (in days) and dry bulb temperature (°C), and the output variable was respiratory rate. The Genetic Fuzzy Rule Based System set the parameters of input and output variables of the Fuzzy Inference System model in order to increase the prediction accuracy of the respiratory rate values. The two systems (Fuzzy Inference System and Genetic Fuzzy Rule Based System) proved to be able to predict the respiratory rate of chicks. The Genetic Fuzzy Rule Based System interacted well with the Fuzzy Inference System model previously developed showing an improvement in the respiratory rate prediction accuracy. The Fuzzy Inference System had mean percentage error of 2.77, and for Fuzzy Inference System and Genetic Fuzzy Rule Based System it was 0.87, thus indicating an improvement in the accuracy of prediction of respiratory rate when using the tool of genetic algorithms.

Download Full-text

Prediksi Kelulusan Mata Kuliah Menggunakan Hybrid Fuzzy Inference System

Register Jurnal Ilmiah Teknologi Sistem Informasi ◽

10.26594/r.v2i2.548 ◽

2016 ◽

Vol 2 (2) ◽

pp. 60

Author(s):

Abidatul Izzah ◽

Ratna Widyastuti

Keyword(s):

Data Mining ◽

Decision Tree ◽

Fuzzy Inference System ◽

Fuzzy Inference ◽

Educational Data Mining ◽

Fuzzy Rule ◽

Posttest Score ◽

Inference System ◽

Is Implementation ◽

Attention To Students

AbstrakPerguruan Tinggi merupakan salah satu institusi yang menyimpan data yang sangat informatif jika diolah secara baik. Prediksi kelulusan mahasiswa merupakan kasus di Perguruan Tinggi yang cukup banyak diteliti. Dengan mengetahui prediksi status kelulusan mahasiswa di tengah semester, dosen dapat mengantisipasi atau memberi perhatian khusus pada siswa yang diprediksi tidak lulus. Metode yang digunakan sangat bervariatif termasuk metode Fuzzy Inference System (FIS). Namun dalam implementasinya, proses pembangkitan rule fuzzy sering dilakukan secara random atau berdasarkan pemahaman pakar sehingga tidak merepresentasikan sebaran data. Oleh karena itu, dalam penelitian ini digunakan teknik Decision Tree (DT) untuk membangkitkan rule. Dari uraian tersebut, penelitian bertujuan untuk memprediksi kelulusan mata kuliah menggunakan hybrid FIS dan DT. Data yang digunakan dalam penelitian ini adalah data nilai Posttest, Tugas, Kuis, dan UTS dari 106 mahasiswa Politeknik Kediri pengikut mata kuliah Algoritma dan Struktur Data. Penelitian ini diawali dari membangkitkan 5 rule yang selanjutnya digunakan dalam inferensi. Tahap selanjutnya adalah implementasi FIS dengan tahapan fuzzifikasi, inferensi, dan defuzzifikasi. Hasil yang diperoleh adalah akurasi, sensitivitas, dan spesifisitas masing-masing adalah 94.33%, 96.55%, dan 84.21%.Kata kunci: Decision Tree, Educational Data Mining, Fuzzy Inference System, Prediksi. AbstractCollege is an institution that holds very informative data if it mined properly. Prediction about student’s graduation is a common case that many discussed. Having the predictions of student’s graduation in the middle semester, lecturer will anticipate or give some special attention to students who would be not passed. The method used to prediction is very varied including Fuzzy Inference System (FIS). However, fuzzy rule process is often generated randomly or based on knowledge experts that not represent the data distribution. Therefore, in this study, we used a Decision Tree (DT) technique for generate the rules. So, the research aims to predict courses graduation using hybrid FIS and DT. Dataset used is the posttest score, tasks score, quizzes score, and middle test score from 106 students of the Polytechnic Kediri who took Algorithms and Data Structures. The research started by generating 5 rules by decision tree. The next is implementation of FIS that consist of fuzzification, inference, and defuzzification. The results show that the classifier give a good result in an accuracy, sensitivity, and specificity respectively was 94.33%, 96.55% and 84.21%.Keywords: Decision Tree, Educational Data Mining, Fuzzy Inference System, Prediction.

Download Full-text

Fuzzy Tsukamoto for Determinen Linen Priority

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.a9764.109119 ◽

2019 ◽

Vol 9 (1) ◽

pp. 2749-2755

Keyword(s):

Fuzzy Inference System ◽

Fuzzy Inference ◽

Fuzzy Rule ◽

Average Amount ◽

Inference System ◽

Average Loss ◽

One Year

With problems at the hospital Dr. Cipto Mangunkusumo, namely borrowing linen when nurses make loans to the logistics division, so that the logistics division has difficulty in determining which linen is used more frequently or lent by nurses, because the type of linen that is very much causes difficulties in the division in determining which linen is obliged to return it quickly to the logistics division. In order for linen to be available again in the logistics division, in addition to a very large loan every month, the logistics division had difficulty determining the average loss of linen in one year. That way the problem that occurs to solve this problem is to use a method namely Fuzzy Tsukamoto to determine the average amount of loss of linen and to determine priority linen that will be replaced earlier when the linen change schedule is in progress or the linen return is speeded up by returning the type of linen that is very often used for. After calculating using the Fuzzy Tsukamoto method, priority linen can be produced, including a Bolster, Blanket, Mattress Pad, and Bed Cover. Based on the calculation of Fuzzy Tsukamoto by doing several stages, namely Fuzzyfication, Fuzzy Rule, Fuzzy Inference System, and Defuzzyfication resulting in an average amount of linen loss in one year is 222.

Download Full-text

Z Number Based Fuzzy Inference System for Dynamic Plant Control

Advances in Fuzzy Systems ◽

10.1155/2016/8950582 ◽

2016 ◽

Vol 2016 ◽

pp. 1-7 ◽

Cited By ~ 6

Author(s):

Rahib H. Abiyev

Keyword(s):

Transient Response ◽

Fuzzy Inference System ◽

Fuzzy Inference ◽

Fuzzy Controller ◽

Fuzzy Rule ◽

Response Characteristic ◽

Rule Base ◽

Inference System ◽

Dynamic Plant ◽

Comparative Results

Frequently the reliabilities of the linguistic values of the variables in the rule base are becoming important in the modeling of fuzzy systems. Taking into consideration the reliability degree of the fuzzy values of variables of the rules the design of inference mechanism acquires importance. For this purpose, Z number based fuzzy rules that include constraint and reliability degrees of information are constructed. Fuzzy rule interpolation is presented for designing of an inference engine of fuzzy rule-based system. The mathematical background of the fuzzy inference system based on interpolative mechanism is developed. Based on interpolative inference process Z number based fuzzy controller for control of dynamic plant has been designed. The transient response characteristic of designed controller is compared with the transient response characteristic of the conventional fuzzy controller. The obtained comparative results demonstrate the suitability of designed system in control of dynamic plants.

Download Full-text

Monotone Fuzzy Rule Relabeling for the Zero-Order TSK Fuzzy Inference System

IEEE Transactions on Fuzzy Systems ◽

10.1109/tfuzz.2016.2540059 ◽

2016 ◽

Vol 24 (6) ◽

pp. 1455-1463 ◽

Cited By ~ 15

Author(s):

Lie Meng Pang ◽

Kai Meng Tay ◽

Chee Peng Lim

Keyword(s):

Fuzzy Inference System ◽

Fuzzy Inference ◽

Fuzzy Rule ◽

Zero Order ◽

Inference System

Download Full-text

Rain prediction using fuzzy rule based system in North-West malaysia

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v14.i3.pp1564-1573 ◽

2019 ◽

Vol 14 (3) ◽

pp. 1564

Author(s):

Noor Zuraidin Mohd Safar ◽

Azizul Azhar Ramli ◽

Hirulnizam Mahdin ◽

David Ndzi ◽

Ku Muhammad Naim Ku Khalif

Keyword(s):

Fuzzy Logic ◽

Fuzzy Inference System ◽

Fuzzy Inference ◽

Expert Knowledge ◽

Fuzzy Rule ◽

Complex Problem ◽

Dew Point ◽

Inference System ◽

North West ◽

Rainfall Prediction

The warm and humid condition is the characteristic of Malaysia tropical climate. Prediction of rain occurrences is important for the daily operations and decisions for the country that rely on agriculture needs. However predicting rainfall is a complex problem because it is effected by the dynamic nature of the tropical weather parameters of atmospheric pressure, temperature, humidity, dew point and wind speed. Those parameters have been used in this study. The rainfall prediction are compared and analyzed. Fuzzy Logic and Fuzzy Inference System can deal with ambiguity that often occurred in meteorological prediction; it can easily incorporate with expert knowledge and empirical study into standard mathematical. This paper will determine the dependability of Fuzzy Logic approach in rainfall prediction within the given approximation of rainfall rate, exploring the use of Fuzzy Logic and to develop the fuzzified model for rainfall prediction. The accuracy of the proposed Fuzzy Inference System model yields 72%

Download Full-text

Noise Reduction with Inference Based on Fuzzy Rule Interpolation at an Infinite Number of Activating Points: Toward Fuzzy Rule Learning in a Unified Inference Platform

Journal of Advanced Computational Intelligence and Intelligent Informatics ◽

10.20965/jaciii.2018.p0883 ◽

2018 ◽

Vol 22 (6) ◽

pp. 883-899 ◽

Cited By ~ 1

Author(s):

Kiyohiko Uehara ◽

Kaoru Hirota ◽

◽

Keyword(s):

Noise Reduction ◽

Infinite Number ◽

Fuzzy Inference ◽

Mathematical Proof ◽

Rule Learning ◽

Fuzzy Rule ◽

Reduction Process ◽

Global Smoothness ◽

Fuzzy Rule Learning ◽

Learning Data

In order to provide a unified platform for fuzzy inference and fuzzy rule learning with noise-corrupted data, a method is proposed for reducing noise in learning data on the basis of a fuzzy inference method called α-GEMINAS (α-level-set and generalized-mean-based inference with fuzzy rule interpolation at an infinite number of activating points). It is expected to prevent fuzzy rules from overfitting to noise in learning data, especially when there is less learning data available for fuzzy rule optimization. The proposed method is named α-GEMI-ES (α-GEMINAS-based local-evolution toward slight linearity for global smoothness) in this paper. α-GEMI-ES iteratively performs α-GEMINAS and reduces the noise in each iteration. This paper mathematically proves that α-GEMI-ES effectively reduces the noise. The noise-reduction process is decisive and thus relies less on trial-and-error-based progress. The noise is reduced by a large amount in the early iterations and the amount of its reduction is decelerated in the later iterations where the deviation in the learning data is suppressed to a great extent. This property makes it easy to determine the termination conditions for the iterative process. Simulation results demonstrate that α-GEMI-ES properly reduces noise as the mathematical proof suggests. The above-mentioned properties indicate that α-GEMI-ES is feasible in practice for the unified platform.

Download Full-text

Adapted Neuro-Fuzzy Inference System on indirect approach TSK fuzzy rule base for stock market analysis

Expert Systems with Applications ◽

10.1016/j.eswa.2009.11.020 ◽

2010 ◽

Vol 37 (7) ◽

pp. 4742-4748 ◽

Cited By ~ 67

Author(s):

Akbar Esfahanipour ◽

Werya Aghamiri

Keyword(s):

Stock Market ◽

Fuzzy Inference System ◽

Fuzzy Inference ◽

Fuzzy Rule ◽

Market Analysis ◽

Rule Base ◽

Inference System ◽

Indirect Approach ◽

Fuzzy Rule Base ◽

Neuro Fuzzy

Download Full-text

Algorithm Apriori Association Rule in Determination of Fuzzy Rule Based on Comparison of Fuzzy Inference System (FIS) Mamdani Method and Sugeno Method

Business Management and Strategy ◽

10.5296/bms.v7i1.9410 ◽

2016 ◽

Vol 7 (1) ◽

pp. 103

Author(s):

Muhammad Fadli Arif ◽

Bima Anoraga ◽

Samingun Handoyo ◽

Harisaweni Nasir

Keyword(s):

Fuzzy Logic ◽

Fuzzy Inference System ◽

Fuzzy Inference ◽

Expert Knowledge ◽

Fuzzy Rule ◽

Percentage Error ◽

Inference System ◽

Rule Based ◽

Accuracy Measurement ◽

First Order

The economic stability of a country can be determined from the changes in the rate of inflation. Inflation is measured by the annual percentage change in the Consumer Price Index. Since there exists some uncertainties in the inflation data, fuzzy logic is one of the ways to analyse the data. Decisions in fuzzy logic can be made using the fuzzy rule-based inference system. Fuzzy rule-based inference can be obtained from expert knowledge, but the knowledge from the experts on the working of a system is not always available. Therefore, the use of association rules approach could solve the problem. Using three methods of fuzzy inferences; namely the Mamdani Methods, zero-order Sugeno method, and the first-order Sugeno method, this study was carried out to determine which method fits to predict the general monthly inflation data in Indonesia. The Inflation data were derived from the inflation of foodstuff price, X1; inflation of food, drinks, cigarettes and tobacco prices, X2; inflation of housing, water, electricity, gas, and fuel prices, X3; inflation of clothing price, X4; inflation of health care price, X5; inflation of education, recreation, and sports prices, X6; and inflation of transportation, communication, and financial services prices, X7. The performance of the three methods was compared using mean squared error (MSE) and mean absolute percentage error (MAPE) as the accuracy measurement to establish the best fuzzy inference method that fits the inflation value. It was found that the most appropriate method which generated the most accurate results to fit the fuzzy inference system to the inflation data was the first-order Sugeno method.

Download Full-text