Filters








1,679 Hits in 7.4 sec

Backpropagation method with type-2 fuzzy weight adjustment for neural network learning

Fernando Gaxiola, Patricia Melin, Fevrier Valdez
2012 2012 Annual Meeting of the North American Fuzzy Information Processing Society (NAFIPS)  
In this paper a neural network learning method with type-2 fuzzy weight adjustment is proposed.  ...  In this work an ensemble neural network of three neural networks and average integration for obtain the final result is present. The proposed approach is applied to a case of time series prediction.  ...  The best result with the ensemble neural network with type-2 fuzzy weights for the Mackey-Glass time series is a prediction error of 0.0788 (as shown in Fig.6 and Table 1 ).  ... 
doi:10.1109/nafips.2012.6291056 fatcat:bvkqq6rm2zbe7egofivdqsjka4

Comparison of T-Norms and S-Norms for Interval Type-2 Fuzzy Numbers in Weight Adjustment for Neural Networks

Fernando Gaxiola, Patricia Melin, Fevrier Valdez, Oscar Castillo, Juan Castro
2017 Information  
The interval type-2 fuzzy number weights are used in a neural network with an interval backpropagation learning enhanced method for weight adjustment.  ...  The adjustment of the weights in the backpropagation learning using interval type-2 fuzzy numbers is the main contribution of the proposed work in this paper for neural networks.  ...  . 2 Results for the fuzzy neural network with interval type-2 fuzzy numbers with T-norm of Dombi in time series prediction using Mackey-Glass time series.  ... 
doi:10.3390/info8030114 fatcat:jnsxz3tnr5cyfg2mogbup7d22e

Hybrid system prediction for the stock market: The case of transitional markets

Nebojsa Ralevic, Natasa Glisovic, Vladimir Djakovic, Goran Andjelic
2017 Industrija  
The subject of this paper is the creation and testing of an enhanced fuzzy neural network backpropagation model for the prediction of stock market indexes, including the comparison with the traditional  ...  The objective of the research is to gather information concerning the possibilities of using the enhanced fuzzy neural network backpropagation model for the prediction of stock market indexes focusing  ...  Introduction This paper proposes adjustment of weights in backpropagation model for neural networks by implementing fuzzy logic.  ... 
doi:10.5937/industrija45-11052 fatcat:z5oiqfdlkjfv3aant4iactyhdu

ECG Prediction Based on Classification via Neural Networks and Linguistic Fuzzy Logic Forecaster

Eva Volna, Martin Kotyrba, Hashim Habiballa
2015 The Scientific World Journal  
The paper deals with ECG prediction based on neural networks classification of different types of time courses of ECG signals.  ...  We also experimented with the new method of time series transparent prediction based on fuzzy transform with linguistic IF-THEN rules.  ...  For the iteration , the weight change Δ can be expressed. The backpropagation learning algorithm used in artificial neural networks is shown in many text books [3] [4] [5] [6] . Fuzzy Logic.  ... 
doi:10.1155/2015/205749 pmid:26221620 pmcid:PMC4499654 fatcat:mu7ua5wxfra6noemt7szkzsjva

Daily Weather Forecasting using Artificial Neural Network

Meera Narvekar, Priyanca Fargose
2015 International Journal of Computer Applications  
Among which neural network with the backpropagation algorithm performs prediction with minimal error. Neural network is a complex network which is self-adaptive in nature.  ...  , Radial Basis Function Network, General Regression Neural Network, Genetic Algorithm, Multilayer Perceptron, Fuzzy clustering, etc. which are used for different types of forecasting.  ...  A Neuro evaluative Interval Type -2 TSK Fuzzy System 5. Grey Relational Analysis.  ... 
doi:10.5120/21830-5088 fatcat:nb5lyzmtkffgtajcbpchyimfhq

Integration of connectionist methods and chaotic time-series analysis for the prediction of process data

R. Kozma, N. K. Kasabov, J. S. Kim, A. Cohen
1998 International Journal of Intelligent Systems  
A connectionist-based time-series analysis method is described that includes chaotic characterization, fractal analysis together with statistical data processing in an adaptive Ž . fuzzy neural network  ...  Two major aspects of the present work are 1 incorporating knowledge into the fuzzy neural network based on the nonlinear deterministic, chaotic analysis of the signals and Ž . 2 refining and updating the  ...  In the present study, a special type of network pruning is applied, which is a modified backpropagation learning algorithm with forgetting the connection weights.  ... 
doi:10.1002/(sici)1098-111x(199806)13:6<519::aid-int7>3.0.co;2-o fatcat:37k3zn3k55bvbmhwr3kohylema

Fuzzy adaptive learning control network with on-line neural learning

Chin-Teng Lin, Cheng-Jian Lin, C.S.George Lee
1995 Fuzzy sets and systems (Print)  
The proposed Fuzzy Adaptive Learning COntrol Network (FALCON) can be contrasted with the traditional fuzzy logic control systems in their network structure and learning ability.  ...  The FALCON-ART combines the backpropagation learning scheme for parameter learning and a fuzzy ART algorithm for structure learning.  ...  First, one can use a neural network with its neural learning ability as a separate system from the fuzzy system for automatic determination and adjustment of fuzzy rules and/or membership functions.  ... 
doi:10.1016/0165-0114(94)00195-d fatcat:43omrfbfurgm5efagekyw64o3m

Intelligent control of air servodrives using neural networks

Polian LIU, Peter DRANSFIELD
1993 Proceedings of the JFPS International symposium on fluid power  
Two popular methods for implementing intelligent control, namely fuzzy set theory and neural networks, are discussed.  ...  Current work involving the application of neural networks to air servodrive systems, is introduced.  ...  Backpropagation is the standard method used to adjust the weights of the neural net. Hence the error, the difference between y(t) and 9(t), is used for adjusting the weights.  ... 
doi:10.5739/isfp.1993.743 fatcat:e4ta5st5tvf4nmvt2ca7f2sq7a

Review on Fuzzy and Neural Prediction Interval Modelling for Nonlinear Dynamical Systems

Oscar Cartagena, Sebastian Parra, Diego Munoz-Carpintero, Luis G. Marin, Doris Saez
2021 IEEE Access  
In this work, a review of the state-of-the-art of methodologies for prediction interval modelling based on fuzzy systems and neural networks is presented.  ...  INDEX TERMS Prediction intervals, fuzzy interval, neural network intervals, uncertainty.  ...  INTRODUCTION The use of fuzzy logic systems (FLS) and neural networks (NNs) has proliferated in the literature for the modeling of systems and time series.  ... 
doi:10.1109/access.2021.3056003 fatcat:tzifk4mofjezdedhayj4vlnrqq

A Comprehensive Review of Soft Computing Models for Permeability Prediction

Mubarak Saad Almutairi
2020 IEEE Access  
In this paper, we present an extensive review of the existing research that has been conducted on applications of soft computing for permeability prediction.  ...  This paper finds out that traditional approaches for permeability prediction are still relevant in the oil and gas industry.  ...  It has been applied in several applications such as data mining, time series modeling, reservoir characterization, and permeability prediction.  ... 
doi:10.1109/access.2020.3046698 fatcat:az4zmfyd5fa4lnk4nxpglmy7fa

POTENTIAL AREA MAPPING FOR SEAWEED AQUACULTURE BASED ON INTERVAL TYPE-2 FUZZY SETS AND MULTI-LAYER PERCEPTRON ALGORITHM

Sarinah a
2019 International Journal of Advanced Research  
This paper proposes a mapping model for seaweed aquaculture based on Interval Type-2 Fuzzy Sets (IT2FS) and Multi-Layer Perceptron (MLP) algorithm as a new framework to map potential area for seaweed cultivation  ...  The decision output from IT2FS is potential or not potential with specific prediction of production size for each region.  ...  The results of this prediction are used in the next stage to predict the availability of seaweed. This stage is called the time series learning stage for attribute predictions.  ... 
doi:10.21474/ijar01/8584 fatcat:7lc5ki5dj5c4fgbaoe6bx4jisi

Neurocontroller alternatives for "fuzzy" ball-and-beam systems with nonuniform nonlinear friction

P.H. Eaton, D.V. Prokhorov, D.C. Wunsch
2000 IEEE Transactions on Neural Networks  
We have used truncated backpropagation through time with the Node-Decoupled Extended Kalman Filter (NDEKF) algorithm to update the weights in the networks.  ...  The ball-and-beam problem is a benchmark for testing control algorithms. In the World Congress On Neural Networks, 1994, Prof.  ...  The set of matrices H i in (1), (2), (4) is obtained by truncated backpropagation through time with depth 10.  ... 
doi:10.1109/72.839012 pmid:18249772 fatcat:sqiqb2uspbblxi2aszemezjiry

Multinodal load forecasting for distribution systems using a fuzzy-artmap neural network

Thays Abreu, Aline J. Amorim, Carlos R. Santos-Junior, Anna D.P. Lotufo, Carlos R. Minussi
2018 Applied Soft Computing  
neural networks converge significantly faster than backpropagation neural networks (improved benchmark in precision).  ...  ., artificial neural networks (ANNs) [4], fuzzy logic [5], etc. However, multinodal prediction is complex in comparison to global prediction.  ...  Acknowledgment The authors thank CAPES (Brazilian Research Foundation) and CNPq (National Council for Scientific and Technological Development) for financial support.  ... 
doi:10.1016/j.asoc.2018.06.039 fatcat:o6myurjjmvdmvggokvwemmkunq

Neurocontrol and fuzzy logic: Connections and designs

Paul J. Werbos
1992 International Journal of Approximate Reasoning  
Artificial neural networks (ANNs) and fuzzy logic are complementary technologies.  ...  For example, one can learn rules in a hybrid fashion and then calibrate them for better whole-system performance.  ...  Then, we can use generalized backpropagation directly to adjust the weights (or uncertainty levels or other parameters) in that network.  ... 
doi:10.1016/0888-613x(92)90017-t fatcat:ebkzw6hoejeldhginfnvtxz2pi

Comparison of BPA and LMA Methods for Takagi - Sugeno type MIMO Neuro-Fuzzy Network to Forecast Electrical Load Time Series

Felix Pasila
2008 Jurnal Teknik Elektro  
Finally, the above training algorithm is tested on neuro-fuzzy modeling and forecasting application of Electrical load time series.  ...  This paper describes an accelerated Backpropagation algorithm (BPA) that can be used to train the Takagi-Sugeno (TS) type multi-input multi-output (MIMO) neuro-fuzzy network efficiently.  ...  application of electrical load time series.  ... 
doi:10.9744/jte.7.2.101-109 fatcat:bvnx3c3ex5bibmqvydzvasp2dq
« Previous Showing results 1 — 15 out of 1,679 results