Fuzzy perceptron neural networks for classifiers with numerical data and linguistic rules as inputs

2000 ◽  
Vol 8 (6) ◽  
pp. 730-745 ◽  
Author(s):  
Jyh-Yeong Chang ◽  
Jia-Lin Chen
Keyword(s):  
Neural Networks ◽  
Numerical Data ◽  
Linguistic Rules

Off-line classification of Polish vowel spectra using artificial neural networks

2004 ◽  
Vol 34 (1) ◽  
pp. 37-52
Author(s):  
Wiktor Jassem ◽  
Waldemar Grygiel
Keyword(s):  
Neural Networks ◽  
Numerical Data ◽  
Word List ◽  
Original Data ◽  
Data Matrix ◽  
Probabilistic Neural Networks ◽  
Independent Variable ◽  
The Individual ◽  
Vowel Phoneme

The mid-frequencies and bandwidths of formants 1–5 were measured at targets, at plus 0.01 s and at minus 0.01 s off the targets of vowels in a 100-word list read by five male and five female speakers, for a total of 3390 10-variable spectrum specifications. Each of the six Polish vowel phonemes was represented approximately the same number of times. The 3390* 10 original-data matrix was processed by probabilistic neural networks to produce a classification of the spectra with respect to (a) vowel phoneme, (b) identity of the speaker, and (c) speaker gender. For (a) and (b), networks with added input information from another independent variable were also used, as well as matrices of the numerical data appropriately normalized. Mean scores for classification with respect to phonemes in a multi-speaker design in the testing sets were around 95%, and mean speaker-dependent scores for the phonemes varied between 86% and 100%, with two speakers scoring 100% correct. The individual voices were identified between 95% and 96% of the time, and classifications of the spectra for speaker gender were practically 100% correct.

Nonlinear Models Used to Analyze the Relation between Inflation and Unemployment

2020 ◽  
Vol 11 (2) ◽  
pp. 667
Author(s):  
Laura UNGUREANU ◽  
Madalina CONSTANTINESCU ◽  
Cristina POPÎRLAN
Keyword(s):  
Neural Networks ◽  
Mathematical Models ◽  
Nonlinear Models ◽  
Numerical Data ◽  
Optimization Models ◽  
Numerical Application ◽  
Forecasting Methods ◽  
Nonlinear Forecasting ◽  
The Relationship

Many mathematical models have been developed in the last years in order to analyze economic phenomena and processes. Some of these models are optimization models, static or dynamic, while others are developed specially to study the evolution of economic phenomena. The topic of this paper is forecasting with nonlinear models. A few well-known nonlinear models are introduced, and their properties are discussed. The variety of nonlinear relationships is important both from the perspective of estimation and from the precision of forecasts in the medium and especially long term. Most nonlinear forecasting methods and all methods based on neural networks lead to predictions that have a better quality than the forecasts obtained by linear methods. The last section of this paper contains a detailed study of the relationship between inflation and unemployment and a numerical application with numerical data from Romania.

scholarly journals Neuro-Fuzzy: Artificial Neural Networks & Fuzzy Logic

2021 ◽  
Vol 9 (9) ◽  
pp. 128-135
Author(s):  
Amey Thakur
Keyword(s):  
Neural Networks ◽  
Fuzzy Logic ◽  
Artificial Neural Networks ◽  
Fuzzy Inference ◽  
Numerical Data ◽  
Parameter Estimate ◽  
Fuzzy Logic Systems ◽  
Pattern Clustering ◽  
Neuro Fuzzy ◽  
Artificial Neural

Abstract: Neuro Fuzzy is a hybrid system that combines Artificial Neural Networks with Fuzzy Logic. Provides a great deal of freedom when it comes to thinking. This phrase, on the other hand, is frequently used to describe a system that combines both approaches. There are two basic streams of neural network and fuzzy system study. Modelling several elements of the human brain (structure, reasoning, learning, perception, and so on) as well as artificial systems and data: pattern clustering and recognition, function approximation, system parameter estimate, and so on. In general, neural networks and fuzzy logic systems are parameterized nonlinear computing methods for numerical data processing (signals, images, stimuli). These algorithms can be integrated into dedicated hardware or implemented on a general-purpose computer. The network system acquires knowledge through a learning process. Internal parameters are used to store the learned information (weights). Keywords: Artificial Neural Networks (ANNs), Neural Networks (NNs), Fuzzy Logic (FL), Neuro-Fuzzy, Probability Reasoning, Soft Computing, Fuzzification, Defuzzification, Fuzzy Inference Systems, Membership Function.

scholarly journals Extracting numerical data from unstructured Arabic texts (ENAT)

2021 ◽  
Vol 21 (3) ◽  
pp. 1759
Author(s):  
Abeer K. AL-Mashhadany ◽  
Dalal N. Hamood ◽  
Ahmed T. Sadiq Al-Obaidi ◽  
Waleed K. Al-Mashhsdany
Keyword(s):  
Text Analysis ◽  
Extraction Method ◽  
Numerical Data ◽  
High Accuracy ◽  
Unstructured Data ◽  
Arithmetic Operations ◽  
Unstructured Text ◽  
Linguistic Rules ◽  
High Level ◽  
Proper Operation

<span id="docs-internal-guid-5dcc170c-7fff-e8e4-10d4-4a07701ca923"><span>Unstructured data becomes challenges because in recent years have observed the ability to gather a massive amount of data from annotated documents. This paper interested with Arabic unstructured text analysis. Manipulating unstructured text and converting it into a form understandable by computer is a high-level aim. An important step to achieve this aim is to understand numerical phrases. This paper aims to extract numerical data from Arabic unstructured text in general. This work attempts to recognize numerical characters phrases, analyze them and then convert them into integer values. The inference engine is based on the Arabic linguistic and morphological rules. The applied method encompasses rules of numerical nouns with Arabic morphological rules, in order to achieve high accurate extraction method. Arithmetic operations are applied to convert the numerical phrase into integer value. The proper operation is determined depending on linguistic and morphological rules. It will be shown that applying Arabic linguistic rules together with arithmetic operations succeeded in extracting numerical data from Arabic unstructured text with high accuracy reaches to 100%.</span></span>

scholarly journals A cost-effective neural network–based damage detection procedure for cylindrical equipment

2019 ◽  
Vol 11 (7) ◽  
pp. 168781401986694 ◽  
Author(s):  
R Karami-Mohammadi ◽  
M Mirtaheri ◽  
M Salkhordeh ◽  
MA Hariri-Ardebili
Keyword(s):  
Neural Networks ◽  
Damage Detection ◽  
Damage Index ◽  
Principal Component ◽  
Numerical Data ◽  
Cost Effective ◽  
Voltage Transformer ◽  
Detection Model ◽  
The Neural Networks ◽  
Parametric Analyses

This article presents a vibration-based technique for damage detection in the cylindrical equipment. First, a damage index based on the residual frequency responses is defined. This technique uses the principal component analysis for data reduction by eliminating the components that have the minimum contribution to the damage index. Then, the principal components are fed into neural networks to identify the changes in the damage pattern. Furthermore, the efficiency of this technique in the field condition is investigated by adding different noise levels to the output data. This study aims at proposing a cost-effective damage detection model using only one sensor. Therefore, the optimal location of the sensor is also discussed. A case study of capacitive voltage transformer is used for validation of finite element models. The neural networks are trained using numerical data and tested with experimental one. Several parametric analyses are performed to investigate the sensitivity of the model.

scholarly journals Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?

2018 ◽  
Author(s):  
Fréderic Godin ◽  
Kris Demuynck ◽  
Joni Dambre ◽  
Wesley De Neve ◽  
Thomas Demeester
Keyword(s):  
Neural Networks ◽  
Word Level ◽  
Linguistic Rules

scholarly journals Subgrid modelling for two-dimensional turbulence using neural networks

2018 ◽  
Vol 858 ◽  
pp. 122-144 ◽  
Author(s):  
R. Maulik ◽  
O. San ◽  
A. Rasheed ◽  
P. Vedula
Keyword(s):  
Neural Networks ◽  
A Priori ◽  
Numerical Data ◽  
Test Case ◽  
Two Dimensional ◽  
A Posteriori ◽  
Optimization Analysis ◽  
Turbulence Closures ◽  
Flow Evolution ◽  
Promising Development

In this investigation, a data-driven turbulence closure framework is introduced and deployed for the subgrid modelling of Kraichnan turbulence. The novelty of the proposed method lies in the fact that snapshots from high-fidelity numerical data are used to inform artificial neural networks for predicting the turbulence source term through localized grid-resolved information. In particular, our proposed methodology successfully establishes a map between inputs given by stencils of the vorticity and the streamfunction along with information from two well-known eddy-viscosity kernels. Through this we predict the subgrid vorticity forcing in a temporally and spatially dynamic fashion. Our study is botha priorianda posterioriin nature. In the former, we present an extensive hyper-parameter optimization analysis in addition to learning quantification through probability-density-function-based validation of subgrid predictions. In the latter, we analyse the performance of our framework for flow evolution in a classical decaying two-dimensional turbulence test case in the presence of errors related to temporal and spatial discretization. Statistical assessments in the form of angle-averaged kinetic energy spectra demonstrate the promise of the proposed methodology for subgrid quantity inference. In addition, it is also observed that some measure ofa posteriorierror must be considered during optimal model selection for greater accuracy. The results in this article thus represent a promising development in the formalization of a framework for generation of heuristic-free turbulence closures from data.

Vehicle Sideslip Angle Estimation Through Neural Networks: Application to Numerical Data

2006 ◽  
Author(s):  
Stefano Melzi ◽  
Ferruccio Resta ◽  
Edoardo Sabbioni
Keyword(s):  
Neural Networks ◽  
Vehicle Dynamics ◽  
Network Performance ◽  
Numerical Data ◽  
Sideslip Angle ◽  
Network Training ◽  
The Neural Network ◽  
Road Friction ◽  
Complete Series ◽  
Real Vehicle

Aim of this paper is to evaluate the possibility of estimating the vehicle sideslip angle through a non-structured algorithm based on neural networks. Results reported are relevant to a numerical investigation of the network performance which can be regarded as preliminary stage for the application on a real vehicle. A numerical model is used to describe the vehicle dynamics and to generate the inputs for the neural network; with an appropriate set of manoeuvres for network training the non-structured algorithm provides reliable results when applied to a complete series of handling manoeuvres carried out with different tire-road friction coefficients.

Sign in / Sign up

Export Citation Format

Share Document