Application of Fuzzy Logic in Biomedical Informatics

Vol. 4, No. 1 Jan 2013

ISSN 2079-8407

Journal of Emerging Trends in Computing and Information Sciences ©2009-2013 CIS Journal. All rights reserved. http://www.cisjournal.org

Application of Fuzzy Logic in Biomedical Informatics 1

Ashish Patel, 2 Shailendra K Gupta, 3 Qamar Rehman, 4 M. K. Verma 1, 3

2

Integral University Lucknow, (U.P.), India, Indian Institute of Toxicology Research Lucknow, (U.P.), India. 1, 4 National Institute of Technology Raipur, (C.G.), India.

ABSTRACT This paper provides the information related to the researches enhanced in the area of fuzzy logic in life sciences and biomedical Informatics. The main emphasis of this paper is to present the general ideas for the time line of the fuzzy logic publications and their applications in the various fields of biology. Literatures from the life sciences and bioinformatics have been reviewed and provided the different experimental & theoretical results to understand the applications of fuzzy logic. The concept of fuzzy logic starts with the fuzzy set. Fuzzy set have partial memberships in multiple sets, which is used in processing of information from the field of molecular biology (for analyzing various properties of the transcriptome and proteome of several organism), clinical practice guidelines, automobile and other vehicle subsystems (automatic transmission), pattern recognition, image processing, remote sensing, language filters etc. Fuzzy inference is an effective tool for the expression of guideline recommendations, and that it can be useful for the management of imprecision and uncertainty, fuzzy logic (FL) as an approach of logic-based modeling with the easy interpretability of Boolean models but significant advantages including the ability to encode intermediate values for inputs and outputs. This review will help the researchers to work on new ideas after knowing the old & current themes. Keywords: Fuzzy logic, uncertainty, linguistic variables, artificial intelligence, hypercube.

1. INTRODUCTION Fuzzy logic is a multi-valued logic obtained from fuzzy set theory deals with the human reasoning that ranges from ‘almost certain’ to ‘very unlikely’. In contrast to classical propositional logic (true/false), the membership value of fuzzy logic variables are not only 0 and 1 but it can b range between 0 and 1. [23]. While using linguistic variables these degrees may be managed by specific functions, as discussed below. For example, let a 100 ml glass contain 40 ml of water. Then we may consider two concepts: Empty and Full. Fuzzy set defines the meaning of both the concepts. Then one might define the glass as being 0.6 empty and 0.4 full. As the concept of emptiness would be subjective and thus would depend on the observer or designer. One might design a set membership function where the glass would be considered full for all values down to 50 ml. It is essential to realize that fuzzy logic uses truth degrees as a mathematical model of the vagueness phenomenon while probability is a mathematical model of randomness. In a probabilistic setting a Scalar variable defines the fullness of the glass, and conditional distribution describes the probability that glass is full to a given a specific fullness level. This model, however, has no sense without accepting occurrence of some event e.g. that after a few minutes, the glass will be half empty. Specific observer that randomly selects label for the glass, and achieve the condition like distribution over deterministic observers, or both. As a result probability and fuzziness are not common; these are simply different concepts. They superficially seem similar because of using the same interval of real numbers (0, 1). Still, since theorems such as De Morgan’s have dual applicability and properties of random variables are analogous to properties of binary logic states, one can see where the confusion might arise.

Zadeh's fuzzy inference methods have found their broad use in control systems. Fuzzy designers have taken advantage of the ability of fuzzy sets to express vague linguistic terms, and perform inference using expert-derived, intuitively phrased rules. They have exploited the capacity of fuzzy inference to create systems with a high tolerance and for uncertain or incomplete information [19]. Fuzzy inference has principally been used in medicine in diagnosis and classification engines [2, 5, 9], in control systems [31, 27], and in pattern recognition and image enhancement [24, 28].

2. THE FUZZY HYPERCUBE In 1992 fuzzy set was geometrically interpreted as mid- point in a hypercube by Kosko [15]. In 1998, unit hypercube was used to represent concomitant mechanisms in stroke by Helgason and Jobe [14]. In a given set

A fuzzy subset is just a mapping and grade of membership was expressed by the value of μ(x).

the element x

X to the fuzzy subset μ.

57

Vol. 4, No. 1 Jan 2013

ISSN 2079-8407


(1) Of course d ( , ) = 0. We know that d is indeed a metric [21]. Hyper-cubical calculus has been described in [33], while some biomedical applications of the fuzzy unit hypercube are given in [14, 22]. Recently, the fuzzy hypercube has been utilized to study differences between polynucleotide [22] and to compare genomes.

3. TIME LINE OF PUBLICATION

Fig 1: Two-dimentinal hypercube 1 2 with the 4 non fuzzy subjects (0,0), (1,0), (0,1), (1,1) and the fuzzy set (0.5, 0.5) For example, let X be the set of persons of some population and let the fuzzy set μ be defined as healthy subjects. If John is a member of the population (the set X), then, μ (John) gives the grade of healthiness of John, or the grade of membership of John to the set of healthy subjects. If λ is the fuzzy set that describes the grade of depression, then λ (Mary) is the degree of depression of Mary. Thus, the set of all fuzzy subsets (of X) is precisely the unit hypercube In = [0, 1]n, as any fuzzy subset μ determines a point P In given by

Reciprocally, any point Generates

a .

fuzzy subset μ defined by μ (xi) = ai, Non fuzzy or crisp subsets of x are given by mappings µ x : X→ {0 , 1}, and are located at the 2n corners of the n-dimensional unit hypercube In. For graphical representations of the two-dimensional and threedimensional hypercube [22], given,

both are not equal to empty define the difference between p and q as

, we

FUZZY

LOGIC

The concept of fuzzy logic was given by Lofti Zedah in 1965 after his application of fuzzy set theory. Fuzzy logic has been applied in various fields for designing of artificial intelligence system. Generally, statisticians and control engineers use this concept but some of them prefer Bayesian logic [18]. By the help of Nicholas Sheble the concept of fuzzy logic comes in to the life [35]. Prof. R Russell Rhine heart, Head, Chemical Engineering School, Oklahoma State University, first declared that the fuzzy logic term is originally nonsensical [25]. The fuzzy logic concept is simple but the jargon obscure that because fuzzy logic concept is totally depends on logic. In fact the fuzzy is absurdly simple and it provides both command line function and graphical user interface. Many researchers and also many chemical industries used the fuzzy logic concepts [18]. One of the most important uses of fuzzy logic is analysis of pollutants and guide line for water quality improvement [17]. Fuzzy logic is type of computer software that recognizes human emotions from conversion analysis [8]. Many researchers have developed the computer software’s with help of fuzzy logic, which are capable to recognize the human emotions from programmed voice analysis. This software is also useful for the programming of robot for the performance of different activities in the world. Lot of problems related to the biological fields also been designed and analyzed by the help of fuzzy logic. Description of fuzzy logic applications in different years1965: In 1965, Lotfi A Zadeh of the University of California at Berkelely published fuzzy sets. In 1965 the fuzzy logic concepts are started from fuzzy set theory. 1990: In Nov 1990 Zadeh delineate the novel ideas for analysis of complex systems and decision processes [32]. The fuzzy logic concept mostly used in the field of decision making process and analysis of intricate system during 1990. Total 03 [13] research papers have been published on different topics. Some of them related to data mining techniques based on fuzzy set model. 1992: Main emphasis in the field of design of fuzzy logic controllers and design of machines [34]. This

58

Vol. 4, No. 1 Jan 2013

ISSN 2079-8407


year entirety 20 (Pubmed) research papers have been published. 1993: Fuzzy logic concepts have been used in the area of artificial intelligence this year. The concept of artificial intelligence has been applied to construct various types of systems, robots and machines etc. Nearly 30 research papers [13] have been published on different topics like fuzzy logic and neural networks [28]. 1994: In this year fuzzy logic helps to develop different expert systems (software developments). Total 46 publications [13] came from different topics like optical implementation of fuzzy logic controllers [16]. 1995: Work related to audio command recognition and prediction of protein structure classes have been introduced and applied [14]. Total 73 research papers [13] have been published. 1996: Concept of fuzzy optimization techniques in the area of drug therapy being used. Total 67 research papers [13] have been published on different topics like algorithms for optimizing drug therapy. 1997: This was the year of inventions, related to data processing with the help of fuzzy logic operations. Total 95 research papers [13] have been published. 1998: In 1998 the fuzzy logic used the controllers, design of fuzzy logic controllers, frameworks of implementing etc. Total 84 [13] research papers are published in different topics like steady state error of a system with fuzzy controller. 1999: Fuzzy logic activity concerned with the design, development and testing of model of a spacecraft control have been initiated this year [6]. Total 90 research papers [13] have been published. 2000: In 2000 total 96 research papers have been published on different topics such as controlled genetic algorithm using fuzzy logic, belief functions for job-shop scheduling, design and stability analysis of single-input fuzzy logic controller etc. [29]. 2001: Total 151 research papers have been published on self-learning fuzzy discrete system [7, 30]. 2002: In pub med total 119 results have been found. Researches conceded onward on designing of decision support system in the medical field [3]. 2003: In 2003 total 141 research papers are published in different topics. Research work on fuzzy logic with support vector machine has been done this year [12, 27].

2005: Total 194 results are found as research articles. Researchers have been carried out on identification of uncertain nonlinear systems for robust fuzzy control and brain segmentation with competitive level sets and fuzzy control etc [4]. 2006: Research articles related to the adaptive fuzzy association were coming; and total 277 research papers have been published. 2007: Total 253 research papers have been published on different topic such as data mining techniques and fuzzy neural based systems. 2008: A neuro-fuzzy approach has been applied by the most of the researchers this year and in totality 290 research papers came out as result. 2009: In 2009 major research contributions in fuzzy logic came from the clinical area and total 312 research papers have been published on different topics. 2010: Total 306 research papers have been published on different topics. 2011: During this year different articles related to the diverse field have been published. Nearly 146 research article found till now.

4. FUZZY LOGIC ARTICLE IN PUBMED Pubmed source have been used to identify the number of publications related to fuzzy in the area of Bioinformatics, Life Sciences and all area. The total number of articles per year from 2000 to 2010 appears in Table1 indicates a comparison in the number of publications per year indexed in PUBMED [13] based on fuzzy logic. Table1: Number of papers per year in Pubmed using fuzzy logic.

Year 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010

Number of Publication Life BioAll Fields Sciences Informatics 5 2 96 7 2 151 11 5 119 16 14 141 18 12 182 10 13 194 27 21 277 28 16 253 31 16 290 32 25 312 33 28 306

2004: Total 182 results have been found in the form published research articles. Fuzzy vector median based researches have been started this year [20, 1].

59

Vol. 4, No. 1 Jan 2013

ISSN 2079-8407


5. APPLICATIONS OF FUZZY LOGIC 5.1 Fuzzy logic in Bioinformatics Bioinformatics combines the multi-disciplinary area such as computer science, biology, physical and chemical principles, designing of tools utilized for the analysis and modeling of large biological data sets, chronic diseases management, learning of molecular computing and cloning etc.[6]. The field of bioinformatics is intensifying for research and development of new technology [10]. Now fuzzy inference technologies are repeatedly applied in bioinformatics. For example, increase the suppleness of protein motifs and learn about the distinction among polynucleotide, utilizing the fuzzy adaptive resonance theory for the analysis of experimental expression data, applying the dynamic programming algorithm for the alignment of the sequences based on fuzzy recast, fuzzy k-nearest neighbors algorithm used to identify the proteins sub-cellular locations from their dipeptide composition, applying fuzzy c-means and partitioning method for characteristic cluster relationship values of genes, analysis of gene appearance data, functional and ancestral relationships between amino acids with the help of fuzzy alignment method, fuzzy classification rules generated by neural network architecture for the analysis of affairs between genes and decipher of a genetic set-up to process micro-array images, use of fuzzy vector filtering framework in the classification of amino acid sequences in to different super families etc.

5.3 Fuzzy logic and Anesthetics The anesthetic experts manage the consciousness and unconsciousness, pain and its relief, movement of muscles and relaxation during prescribed time range [11]. In the operation theatre anesthetized patient is part of a ‘feedback circuit’ (Figure 2) for the period of an operation. During examine the consistency of the patients, if any change occurs in blood pressure and respiratory rate then regulate the ventilation and modify the drug dosages [12]. In this process anesthetist will play the role of decision-maker and controller, who will make his own decision to perform best. In a series of ventilated patients Schaublin and co-workers [27] tested a fuzzy logic program that monitored CO2 and end tidal CO2 and altered ventilator frequency and tidal volume to keep end-tidal CO2 at a desired level. The performance of system was not less well than the anesthetist usual practice under similar conditions. Fuzzy logic have been applied to measure the heart rate, tidal volume, breathing frequency and oxygen saturation , to establish the requirement for pressure support ventilation in intensive care [20].

Fig 2: The Control Loop 5.2 Fuzzy logic and Control of Inspired Oxygen in Ventilated Newborn Infants Development of chronic lung disease in new born infant due to the toxicity in the oxygen, at this stage mechanical ventilation is required [26, 30]. Insufficient repairs of tissue oxygenation in premature infants are concerned with the development of retinopathy of prematurity [3]. For the control delivery of oxygen, ventilated newborns has kept in neonatal intensive care to avoid the effects of too much or too little oxygen. The procedure to provide the control oxygen to mechanically ventilated newborn infants is quite intensive but it must balance sufficient tissue oxygenation against possible toxic effects of oxygen exposure. Many researches in the area of computational programming increase our ability to control the mechanical ventilation, while a very small number of studies are in continuation related to the newborn infants. Fuzzy controller system can be executed to adjust the inspired oxygen concentration in the ventilated newborn. The rules generated by neonatologists and utilized by the controller, which functions in real-time. To check the efficacy of this controller, currently setup a clinical trial at Children's Hospital, Boston, MA, in the neonatal intensive care unit (NICU).

5.4 Fuzzy Logic In Medicine In the field of medicine fuzzy logic play an imperative role [1, 4] some examples in which fuzzy logic have been implemented are as follows: Detection of diabetic retinopathy in the early hours and analyze diabetic neuropathy, to decide the suitable lithium dosage, brain tissue volume have been calculated from magnetic resonance imaging (MRI) and to analyze functional MRI data. To identify breast cancer, prostate cancer, or lung cancer, to support the diagnosis of tumors in central nervous systems (astrocytic tumors), to distinguish benign skin gashes from malignant melanomas, to visualize nerve fibers in the human brain, to signify the quantitative estimation of drug use, to study the auditory P50 component in schizophrenia, to learn fuzzy epidemics, to formulate decisions in nursing.

6. CONCLUSION Fuzzy logic play vital role in the field of drug designing, bioinformatics, management of diseases, clinical trials. All of these directly or indirectly affect the life, so these are also integrated with life sciences. Researchers may take advantage of this paper in the form of complete information related to the fuzzy logic from its inception to formulate the new ideas and utilize this information for innovative research.

60

Vol. 4, No. 1 Jan 2013

ISSN 2079-8407


REFERENCES [1]

Abbod MF, von Keyserlingk DG, Linkens DA, Mahfouf M., 2001, Survey of utilization of fuzzy technology in Medicine and Healthcare, Fuzzy Sets and Systems, 120(2):331–349.

[15]

Kosko B., 1992, Neural Networks and Fuzzy Systems. Englewood Cliffs, NJ: Prentice-Hall.

[16]

Kosko B., 1998, Neural Networks and Fuzzy Systems,J. Acoust. Soc. Am., 103(6), 3131-3131.

[17]

Luc A. Andriantiatsaholiniaina, Vassilis S. Kouikoglou, Yannis A. Phillis,2004, Evaluating strategies for sustainable development:fuzzy logic reasoning and sensitivity analysis,Ecological Economics, 48, 149– 172.

[18]

Mizikar R.A., Susan J. Chinn,1997, Using a fuzzy logic decision system to detect engine leaks, Computational Cybernetics and Simulation, 1, 686 - 689.

[2]

Adlassnig KP, Kolarz G, Scheithauer W, et al., 1985, CADIAG: Approaches to computer-assisted medical diagnosis, Comput. Biol. Med., 15(5), 315335.

[3]

Avery,G.; Glass,P.,1988,Retinopathy of prematurity: what causes it?, Clin perinatol, 15, 917-28.

[4]

Barro S, Marín R., 2002, Fuzzy Logic in Medicine. Heidelberg, Germany: Physical, pp- 6-7.

[19]

Binaghi E, De Giorgi 0, Maggi G, Motta T, Rampini A., 1993, Computer-assisted diagnosis of postmenopausal osteoporosis using a fuzzy expert system shell, Comput. Biomed.Res., 26,98-516.

Munakata T, Jani Y., 1994, Fuzzy systems: an overview, Communications of the ACM, 37(3), 6976.

[20]

Nemoto T, Hatzakis GE, Thorpe CW, Olivenstein R, Dial S, Bates JH.,1999, Automatic control of pressure support mechanical ventilation using fuzzy logic., Am J Respir Crit Care Med, 160, 550556.

[21]

Nieto,J.J. and Torres,A. and V´azquez-Trasande, M.M., 2003, A metric space to study differences between polynucleotides., Appl.Math.Lett., 27, 81101.

[22]

Juan J. Nieto, A. Torres, D. N. Georgiou and T. E. Karakasidis, 2006, Fuzzy polynucleotide spaces and metrics, Bulletin of Mathematical Biology, 68(3), 703-725.

[23]

Novák, V., Perfilieva, I. and Močkoř, J., 1999, Mathematical principles of fuzzy logic Dodrecht: Kluwer Academic., ISBN 0-7923-8595-0, 39-46.

[24]

Peters RM, Shanies SA, Peters JC., 1995, Fuzzy cluster analysis of positive stress tests, a new method of combining exercise test variables to predict extent of coronary artery disease., Am. J. Cardiol., 76(10), 648-651.

[25]

R. Russell Rhinehart, 2000, The century's greatest contributions to control practice, ISA Transactions, 39, 3-13.

[26]

Saugstad, 0., 1990, Oxygen toxicity in the neonatal period., Acta paediatr Scand, 79, 881.

[27]

Schaublin J, Derighetti M, Feigenwinter P, Petersen-Felix S, Zbinden AM., 1996, Fuzzy logic control of mechanical ventilation during anaesthesia. Br. J. Anesth., ; 77(5): 636-641.

[28]

Shiomi S, Kuroki T, Jomura H, et al., 1995, Diagnosis of chronic liver disease from liver

[5]

[6]

[7]

[8]

Bourbakis NG., 2003, Bio-imaging and bioinformatics IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics. 33(5), 726– 727. Castelli V,Aury J-M,JaillonO,et al.,2004, Whole genome sequence comparison and “full length”cDNA sequences:a combined approach to evaluate and improve Arabidopsis genome annotation.genome Research, 14(3), 406-413. Erik Cambria, Amir Hussain, Catherine Havasi, and Chris Eckl,2009, AffectiveSpace: Blending Common Sense and Affective Knowledge to Perform Emotive Reasoning, Troyano, Cruz, Díaz (Eds.): WOMSA'09, 32-41.

[9]

Fathi-Torbaghan M, Meyer D. MEDUSA, 1994, A fuzzy expert system for medical diagnosis of acute abdominal pain, Meth. Inf J Med, 33(5), 522-529.

[10]

Fuchs R., 2002, From sequence to biology: the impact on bioinformatics, Bioinformatics, 18(4), 505-506.

[11]

Grant P, Naesh O., 2005, Fuzzy logic and decisionmaking in anaesthetics, J R Soc Med, 98(1), 7-9

[12]

Hayward G, Davidson V., 2003, Fuzzy logic applications, Analyst, 128, 1304-06.

[13]

http://www.ncbi.nlm.nih.gov/pubmed .

[14]

Jobe TH, Helgason CM., 1998, The fuzzy cube and causal efficacy: representation of concomitant, mechanisms in stroke, Neural Networks., 11(3), 549–555.

61

Vol. 4, No. 1 Jan 2013

ISSN 2079-8407


[29]

scintiscans by fuzzy reasoning., J. Nucl. Med., 36(4), 593-598.

[33]

Torres,A., Nieto,J.J.,2003, polynucleotide space:basic Bioinformatics., 19(5), 587-592.

Zaus,M., 1999, Crisp and Soft Computing with Hypercubical Calculus. Physica , Heidelberg, 1736, ISBN:3-7908-1172-6..

[34]

Zeyad Assi Obaid, Nasri Sulaiman, M. N. Hamidon, Mohammed Obaid Ali,2009, Design Representation of the Multipurpose Fuzzy Logic Controller using Hardware Description Language,Proceedings of the International Conference on Man-Machine Systems (ICoMMS), 11 – 13 .

[35]

Zhao Changhong,Yuan Jiahai,2005, An open multi-agent platform for price strategy optimization of generators in market environment, Int. Conf. on computational intelligence, man-machine systems and cybernetics, 17-19, 281-287.

The fuzzy properties.,

[30]

Wise,J.; Roberts,R.,1987, Molecular basis of pulmonary oxygen toxicity. Clin Perinatol, 14, 651-66.

[31]

Ying H, McEachem M, Eddleman DW, Sheppard LC., 1992, Fuzzy control of mean arterial pressure in postsurgical patients with sodium nitroprusside infusion, IEEE Trans Biomed. Eng., 39(10), 10601070.

[32]

Zadeh, L., 1965, "Fuzzy Sets” Information and Control., 8, 338–353.

62