A new imputation-based incomplete data-driven fuzzy modeling for accuracy improvement in ubiquitous computing applications

Purpose In real-world decision-making, high accuracy data analysis is essential in a ubiquitous environment. However, we encounter missing data while collecting user-related data information because of various privacy concerns on account of a user. This paper aims to deal with incomplete data for fuzzy model identification, a new method of parameter estimation of a Takagi–Sugeno model in the presence of missing features. Design/methodology/approach In this work, authors proposed a three-fold approach for fuzzy model identification in which imputation-based linear interpolation technique is used to estimate missing features of the data, and then fuzzy c-means clustering is used for determining optimal number of rules and for the determination of parameters of membership functions of the fuzzy model. Finally, the optimization of the all antecedent and consequent parameters along with the width of the antecedent (Gaussian) membership function is done by gradient descent algorithm based on the minimization of root mean square error. Findings The proposed method is tested on two well-known simulation examples as well as on a real data set, and the performance is compared with some traditional methods. The result analysis and statistical analysis show that the proposed model has achieved a considerable improvement in accuracy in the presence of varying degree of data incompleteness. Originality/value The proposed method works well for fuzzy model identification method, a new method of parameter estimation of a Takagi–Sugeno model in the presence of missing features with varying degree of missing data as compared to some well-known methods.

CLASSIFICATION OF SHORT TECHNICAL TEXTS USING SUGENO FUZZY INFERENCE SYSTEM

The paper presents the results of classification of the short technical texts on the purpose of instruments using fuzzy sets theory and fuzzy logic. An important stage in designing special-purpose technical systems is the choice of equipment with specific operational characteristics. The need to categorize short technical texts, which present a brief description of equipment, annotations, fragments of databases, appears due to the fact that information about the equipment found in thematic abstract collections, technical and design documentation or in contextual advertising is often not structured and scattered. The other problems are a large number of typos, incorrect word usage and definitions in the texts. Much attention is paid to the characteristics of the objects of research and to recording their specific features – a large number of technical terms, abbreviations, symbols. The classifying technique is described, the expediency of application of fuzzy inference of Sugeno system associated with fuzziness of the natural language, the simplicity of mathematical calculations in the course of the experiment. A Sugeno model combines the description of the objects of research in the form of linguistic rules and functional dependencies. This approach greatly facilitates the interpretation of classification results

Development of an algorithm for tuning a suboptimal scaling factor in the SINS filtering problem

A modified strong tracking unscented Kalman filter for nonlinear dynamical systems is proposed. A matrix of the suboptimal scaling factor is introduced into the prediction covariance to ensure evaluation stability and smoothness at appearance of the process model uncertainty. It is shown that the use of a fuzzy algorithm to adjust the softening coefficient in real time allows to avoid the loss of accuracy in the segments in which the process model is defined. As a result of modeling the SINS correction task, it was found that the proposed fuzzy filter has good evaluation smoothness and high accuracy. Keywords SINS; suboptimal scaling factor; softening coefficient; fuzzy Takagi — Sugeno model