Soft computing

About: Soft computing is a research topic. Over the lifetime, 6710 publications have been published within this topic receiving 118508 citations.

Soft Computing Techniques in Stainless Steel Welding

Abstract: Advancement in Soft Computing is a live process in which new and newer methods of solving nonlinear systems are continuously emerging. Fuzzy logic systems, artificial neural networks, and evolutionary computation are the main methodologies of soft computing. Soft Computing techniques are being increasingly used in solving the complex problems of welding both at the scientific and engineering level. In welding, soft computing is finding applications in real time control of the welding process, adaptive control of the welding process, weld-pool geometry control, quality monitoring, intelligent sensing, seam tracking control, robotic welding, prediction of microstructure, mechanical properties, residual stresses and distortion in welds, and others. The present article is focused on the author's experiences in using core soft computing techniques in modeling and prediction of microstructures in stainless steel welds, modeling weld-bead geometry, optimization of process parameters during arc welding of stainle...

Advancement and applicability of classifiers for variant exponential model to optimize the accuracy for deep learning

Abstract: The exploratory increment in database technology has facilitated researchers and scientist’s throughout the globe to determine best possible knowledge for discovery of hidden patterns and rules among large databases. Unfortunately, several technologies were intervened to measure the hidden patterns but tend to be incompetent, but soft computing techniques solely evaluated the different application domains and its success has potentially driven in prediction of future prognosis. In proposed study we have generalized our approach to discover a combinational model to measure the accuracy among the applicability of the classifiers. A soft computing solutions that we have utilized three different classifiers such as Random Forest, Naive Bayes and K Nearest Neighbor with pancreatic cancer datasets utilizing varied training test data and ten fold cross validation techniques. Further, varied performance indicators were utilized to measure accuracy among the classifiers which include Area under Curve, F measure, Specificity and others. The Experimental results prove that the proposed approach can benefit end users to discriminate diversified method which can explicitly has potentially higher performance.

Soft Computing for Intelligent Control and Mobile Robotics

Abstract: Even though it is known that chaotic time series cannot be accurately predicted, there is a need to forecast their behavior in may decision processes. Therefore several non-linear prediction strategies have been developed, many of them based on soft computing. In this chapter we present a new neural network architecutre, called Hybrid and based-on-Wavelet-Reconstructions Network (HWRN), which is able to perform recursive long-term prediction over highly dynamic and chaotic time series. HWRN is based on recurrent neural networks embedded in a two-layer neural structure, using as a learning aid, signals generated by wavelets coefficients obtained from the training time series. In the results reported here, HWRN was able to predict better than a feed-forward neural network and that a fully-connected, recurrent neural network with similar number of nodes. Using the benchmark known as NN5, which contains chaotic time series, HWRN obtained in average a SMAPE = 26% compared to a SMAPE = 61% obtained by a fully-connected recurrent neural network and a SMAPE = 49% obtained by a feed forward network.

A general framework for computing with words in object-oriented programming

Abstract: Computing with words (CWW) techniques have been shown to be useful in the management of imperfect information. From the programmer's standpoint, new tools are necessary to ease the use of these techniques within current programming platforms. This paper presents a step in this direction by describing a general framework that supports the implementation of applications dealing with fuzzy objects. We pay special attention to the study of the object comparison problem by offering both a theoretical analysis and a simple and transparent way to use our theoretical results in practice.