Criteria and Procedures for Estimating the Informativity and Feature Selection in Biomedical Signals for their Recognition

Abstract

Introduction. The issues of features informativity evaluation in biomedical signals portraits according to formal comparison of their probability values, obtained during training of supervised learning recognition systems are being considered. The purpose of this work is to increase the effectiveness of the biomedical signals recognition in diagnostic systems with supervised learning, by choosing rational structure of portraits based on the nature of their elements influence on the quality of pattern recognition.Details. Informativity values are used for feature selection in the formation of truncated portraits. Subsequent exclusion of less informative features from consideration relies in this paper in the basis of disclosure and implementation of reserves to increase the probability of correct recognition in diagnostic systems. Content and efficiency of the proposed signal processing technology is illustrated by the test case in the application to the common task of recognition of QRS-complexes types, useful for recognition system training with its data selection.Conclusions. The use of certain components of biomedical signals portraits, studied in the diagnosis of patients can have a positive impact on the quality of pattern recognition, while others create redundancy of portraits or reducing effectiveness of solving this task.

Authors and Affiliations

A. Shulyak

Keywords

Related Articles

Microstrip filter based on 2D inhomogeneities

Realization of microstrip narrow-band filters based on 1D- and 2D-inhomogeneities areconsidered. Features impedance dependencies of filter structures are analyzed. There areillustrated, that 2D-inhomogeneities, as electr...

Temperature stability of ultra low voltage signals multiplier

The paper considers the thermal stability of ultra low voltage signals multipliers that form the basis of discrete-analog programmable filter-correlators. These correlators perform convolution vector of the input signal...

Radiometry notdestroying control of dielectric materials

The system is offered non-destructive radiothermal and radar methods of control of technological parameters of heat-resistant wares from sitall, sitall and quartz ceramics in the workplace. The mechanism of removal and t...

Prognostication of little size radio – controlled apparatus efficiency

Introduction. The achievement of radio electronics open the possibility creature of little size radio – controlled apparatus. Such apparatus application permits the fulfillment of tasks in extreme situations. The efficie...

Research of the potential characteristics of a radar signal with linear frequency modulation in the area of low correlation

The composite radar signal with linear frequency modulation is reviewed. The results of calculations of potential descriptions of signal are resulted for correlation functions are got and contours in the area of low corr...

Download PDF file
  • EP ID EP308271
  • DOI 10.20535/RADAP.2016.66.79-86
  • Views 75
  • Downloads 0

How To Cite

A. Shulyak (2016). Criteria and Procedures for Estimating the Informativity and Feature Selection in Biomedical Signals for their Recognition. Вісник НТУУ КПІ. Серія Радіотехніка, Радіоапаратобудування, 0(66), 79-86. https://europub.co.uk/articles/-A-308271