Innovative Formalism for Biological Data Analysis

Innovative Formalism for Biological Data Analysis

Calin Ciufudean (Stefan cel Mare University, Romania)
Copyright: © 2018 |Pages: 11
DOI: 10.4018/978-1-5225-2255-3.ch158
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Modern medical devices involves information technology (IT) based on electronic structures for data and signals sensing and gathering, data and signals transmission as well as data and signals processing in order to assist and help the medical staff to diagnose, cure and to monitors the evolution of patients. By focusing on biological signals processing we may notice that numerical processing of information delivered by sensors has a significant importance for a fair and optimum design and manufacture of modern medical devices. We consider for this approach fuzzy set as a formalism of analysis of biological signals processing and we propose to be accomplished this goal by developing fuzzy operators for filtering the noise of biological signals measurement. We exemplify this approach on neurological measurements performed with an Electro-Encephalograph (EEG).
Chapter Preview
Top

Introduction

Modern medical devices involves information technology (IT) based on electronic structures for data and signals sensing and gathering, data and signals transmission as well as data and signals processing in order to assist and help the medical staff to diagnose, cure and to monitors the evolution of patients. By focusing on biological signals processing we may notice that numerical processing of information delivered by sensors has a significant importance for a fair and optimum design and manufacture of modern medical devices. We consider for this approach fuzzy set as a formalism of analysis of biological signals processing and we propose to be accomplished this goal by developing fuzzy operators for filtering the noise of biological signals measurement. We exemplify this approach on neurological measurements performed with an Electro-Encephalograph (EEG).

We mention that automatic diagnosis based on fuzzy approach becomes more and more used in artificial intelligence framework of proposing new methods and tools for developing automatic medical diagnosis. Fuzzy techniques of analysis and diagnosis have a significant advantage compared to classical techniques, respectively the ability to deal with typical uncertainty and estimation that characterizes any physical system, including the human body.

This chapter is focused on reasoning with fuzzy logic for designing new type of filters capable to reject noises which overload the biological signals taken by invasive ad/or non-invasive medical tools. We will exemplify our approach on EEG measurements. This goal will be accomplished by using a new structure and inference mechanism of fuzzy operators which will implement a new design of filters against impulsive and uniform distributed noise. This approach is inspired by the class 1-D (signals) and 2-D (images) of fuzzy filters proposed in (Zadeh, 1988; Russo & Ramponi, 1994; Russo, 1994). Building our approach we were guided by Professor Lofthi Zadeh`s statement (Zadeh, 1988): “Fuzzy logic is a precise conceptual system of reasoning, deduction and computation in which the objects of discourse and analysis are, or are allowed to be, associated with imperfect information. Imperfect information is information which in one or more respects is imprecise, uncertain, incomplete, unreliable, vague or partially true”. We assume that the reader is familiarized with fuzzy logic systems, or we address the reader to (Kumar, s.a., 2001; Adlassnig, 2007; Chin, 1991; Fathi-Torbaghan & Meyer, 1994; Nguyen & Kreinovich, 2001; Bounds, 1999). We notice that literature treat intensively the subject of applying fuzzy logic to biological data acquisition and processing for medical diagnosis (John & Innocent, 2005; Perner, 2002); therefore we try to add a piece in this puzzle hoping to speed up the process of having a clear picture. Automatic processing of sensory information is an actual research area, and fuzzy techniques are well framed in this content, and represents a useful and widely applicable technique with long run perspective. This chapter is focused on implementing rule-based fuzzy systems for processing, e.g. filtering, measured biologic data in order to determine the availability of the most important ones for the final diagnosis. We appreciate that our approach will framework the computer systems for medical diagnosis. An example will emphasize our approach.

This chapter is organized as follows: section 2 briefly discuss the chapter`s position on the topic of biological data processing and analysis, section 3 presents our fuzzy filter approach, section 4 deals with fuzzy inference mechanism for filtering electric signals, section 5 illustrates our approach by an example and section 6 concludes the present work and gives a few directions for future research in the area.

Key Terms in this Chapter

Availability: The degree to which a system, subsystem is in a specified operable and committable state at the start of a mission, when the mission is called for at an unknown, i.e. a random, time.

Electroencephalography: ( EEG ): A monitoring medical procedure to record electrical activity of the brain.

Fuzzy Logic: A mathematic analysis formalism which deal with concepts that cannot be expressed as the “true” or “false” but rather as “partially true” similar to human operators thinking.

Neurologist: A medical specialist in the nervous system.

Automatic Processes: A category of cognitive processing.

Inference Mechanism: A tool from artificial intelligence analysis formalisms which addresses the search and control techniques.

Data Analysis: A process of inspecting, adapting, and modeling data with the goal of discovering useful information and decision making.

Diagnosis: Identification of the nature and cause of anything.

Complete Chapter List

Search this Book:
Reset