Survey Methodology

Survey Methodology, May-June 2015 Vol. 44, No. 1, pp. 94-118 Canada, Catalogue No. 12-001-X Catalogue no. 12-001-X ISSN 0714-0045 On aligned composite estimates from overlapping samples for growth rates and totals

Survey Methodology

On aligned composite estimates from overlapping samples for growth rates and totals

by Paul Knottnerus Release date: 2014-2015

Canada, Catalogue No. 12-001-X

226

Survey Methodology, May-June 2015 Vol. 44, No. 1, pp. 94-118 Canada, Catalogue No. 12-001-X

227

How to obtain more information For information about this product or the wide range of services and data available from Canadian researches, visit our website, http://survmethodjournal.org You can also contact us by email at [email protected] telephone, from Monday to Friday, 8:30 a.m. to 4:30 p.m., at the following toll-free numbers: Statistical Information Service

1-800-263-1136

National telecommunications device for the hearing impaired

1-800-363-7629

Fax line Depository Services Program

1-877-287-4369

Inquiries line

1-800-635-7943

Fax line To access this product

1-800-565-7757

This product, Catalogue no. 12-001-X, is available free in electronic format. To obtain a single issue, visit our website, http://survmethodjournal.org Standards of service to the public survmethodjournal is committed to serving its clients in a prompt, reliable and courteous manner. To this end, survmethodjournal has developed standards of service that its employees observe. To obtain a copy of these service standards, please contact survmethodjournal toll-free at 1-800-263-1136. The service standards are also published on http://survmethodjournal.org under “About us” > “The agency” > “Providing services to researchers.” Published by authority of the Minister responsible for survmethodjournal © Minister of Industry, 2014 All rights reserved. Use of this publication is governed by the survmethodjournal Open License Agreement (survmethodjournal.org). Cette publication est aussi disponible en français.



228

Ranking the Temperature of Fever Diseases in Iranian Traditional Medicine Using Fuzzy Logic Mohammad Dehghandar11, Hamid Khaloozadeh2, Mahdi Alizadeh3, Fahimeh

1

Soltanian1, Mansoor Keshavarz4 Department of Mathematics, Payame Noor University, Tehran, Iran

2

Department of Systems and Control, K.N. Toosi University of Technology, Tehran, Iran

3

School of Iranian Traditional Medicine, Tehran University of Medical Sciences, Tehran, Iran

4

Department of Physiology, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran

Abstract In Iranian Traditional Medicine (ITM) each pulse is evaluated by several ‎ ‎parameters‎that ‎ ‎‎ ‎give very useful information about the condition and status of the human body. The temperature of Fever diseases like sanguine (of blood), melancholic, phlegmatic, daily fever, and so on were determined using complex rules of pulse in ITM and is of paramount importance. Pulse parameters such as length, width, ‎height, strength, speed, frequency, regularity, harmony ,fullness and‎‎ vascular consistency were used and output parameters such as temperature, the supply ability state‎, humidity ,vascular wall consistency and the demand state‎ of the body were categorized‎ and fuzzy logic was used to inference the rules of pulse. These rules have eleven (11) input parameters and five (5) output parameters. Therefore, the temperature of Fever diseases was determined using thirty-two (32) rules of pulse in ITM, by using fuzzy logic in MATLAB. Key words: temperature, pulse, Iranian Traditional Medicine, Fuzzy logic. Introduction Pulse Parameters in Iranian Traditional Medicine Iranian Traditional medicine (ITM) pulse diagnosis is one of the major clinical diagnostic methods in ITM. It has been used by ITM doctors to assess patients’ health conditions for many thousand years. In ITM each pulse is evaluated by several‎ ‎parameters that ‎give very useful information about ‎the condition and status of the human body and ‎major vital organs ‎ [1, 2]. More details of the most important of these parameters is ‎mentioned below:

1

Corresponding author: Department of Mathematics Payame Noor University, Tehran, Iran.

E-mail address: [email protected]‫‏‬ Canada, Catalogue No. 12-001-X


229

1. The extent of the expansion of a vessel in the dimension of length ‎during the passage of a pulse in comparison to the span width of a set ‎of four examining fingers placed with a defined ‎pressure on the radial artery. 2. The extent of the expansion of a vessel in the dimension of width ‎during the passage of a pulse in regard to the width of the fingers placed with a ‎defined ‎pressure on the radial artery. 3. The extent of the expansion of a vessel in the dimension of ‎height ‎during the passage of a pulse in regard to the examining fingers placed with a ‎defined ‎pressure on the radial artery.‎ 4. The “pulse strength” which is the impact of the pulse-beat on the examining fingers 5. The “pulse velocity” relating to pulse movements duration. 6. The “pulse frequency” relating to the rest period intervals duration. 7. The “vascular wall consistency” meaning the rigidity vs. elasticity of the vessels. 8. The degree of vessel fullness. 9. The “artery's temperature” in comparison with the surrounding tissue and also the normal population 10. The “resemblance” or “diversity” of pulses. 11. The “regularity” or “irregularity” of the diverse pulse ‎ ach above mentioned parameter guides the traditional physician to at least one of the E retentive ‎causes of pulse such as temperature, the supply ability state‎, humidity ,vascular wall consistency and the demand state‎ of the body. In traditional medicine, fever was divided into different types like sanguine (of blood), melancholic, phlegmatic, daily fever, and so on. In Iranian traditional medicine careful examination of the patient as well as the background leading to fever were of utmost importance and a lot of foods prescribed for the treatment of fever were consistent with the standards of modern medicine. [1, 3-7]. Fuzzy Logic Fuzzy logic is based on the theory of fuzzy sets, where an object’s membership of a set is gradual ‎rather than just being a member or not a member. It includes different processes Canada, Catalogue No. 12-001-X


230

in itself such as fuzzification, defuzzification, membership functions, domain, linguistic variables and rules. Domain determines the range of values in which membership of fuzzy is performed. The basic part of fuzzy sets is the membership function. The relationship between domain value and degree of membership was determined by a membership function. Fuzzy logic exhibits many similarities and differences with Boolean logic. Fuzzy logic operates Boolean logic results, when all the fuzzy membership functions are restricted from 0 to 1. So there are infinite values between 0 and 1 in fuzzy logic. Fuzzy logic uses natural language techniques and variables which are based on the degree of truth and is easier for human beings to understand‎. The application of fuzzy logic in medicine and bioinformatics has received much appreciation [8, 9, 10, 11, 15, 16]. In this research, a Fuzzy Inference System (FIS) was developed for ranking the temperature of Fever diseases in Iranian Traditional Medicine using MATLAB [12]. The model can be viewed as an alternative to the use of addition, in aggregating the scores from all categories, to produce a final score [13, 14]. The factors used for evaluating the performance are considered as input parameters for fuzzification. The study utilized FIS to deal with the problem associated with rule explosion. The proposed FIS was implemented using the Mamdani-type inference. Design of Fuzzy Logic Based Pulse parameters Input and Output Parameters The first step in using fuzzy logic within this model is to identify the parameters that will be fuzzified and to determine their respective range of values. The final result of this interaction is the value for each performance parameter. MATLAB was used for the development of FIS.The input and output parameters were created in the FIS editor. Eleven (11) input and five (5) output parameters were applied to the FIS. For the design process, the extent of the expansion in three dimensions, Strength, velocity, frequency, vascular ‎wall ‎consistency, artery's ‎temperature, fullness, ‎resemblance and regularity were used as input parameters and Temperature, The Supply Ability State‎, Humidity, vascular wall consistency and The Demand State‎ of the body were obtained as output. For fuzzification of these parameters, the linguistic variables Very High, High, Medium, Low and Very Low were used. For the inference mechanism, the Mamdani max-min inference was applied. The rating scale of input and output parameters were classified into different categories, as given in Tables 1 - 3.



231

Table 1: Rating scales of input parameters Linguistic

Very High ‎

High‎

Medium

Low

Very Low

The extent of the expansion in length The extent of the expansion in width The extent of the expansion in height Strength Velocity Frequency

Input Name

Vascular ‎wall ‎consistency Artery's ‎temperature Fullness Resemblance Regularity Table 2: Rating scales Output Parameters Linguistic

Very High ‎

Very High

Output Name

High‎ Medium

Low

Very Low

Very Low

Temperature Table 3: Rating Scales Output Parameters

Linguistic

Very High ‎

High‎

Medium

Low

Supply Ability State Humidity Output Name

Vascular Wall Consistency Demand State


Very Low


232

Membership Functions Fuzzification comprises the process of transforming crisp value into grade of membership [17]. The membership function is used to associate a grade to each linguistic term. The membership function editor is used to define the properties of the membership function for the system variables. Figure 1 shows fuzzification of input parameters for the first fuzzy module with membership function as explained in Table 1, the membership function overlap with each other for achieving better results.Figure 2 and 3 shows the fuzzification of output parameter performance with membership function as explained in Table 2 and 3; the membership functions touch each other for achieving better results.

Figure 1: Membership function for input pulse‫‏‬in ‫ ‏‬Iranian Traditional Medicine.

Figure 2: Membership function for output “Temperature”.



233

Figure 3: Membership function for output “Humidity” 2.

Rule Base A fuzzy rule base is a collection of knowledge in the If-Then format from experts. It describes the relationship between fuzzy input parameters and output. It is used to display how an output is dependent on any one or two of the inputs. The rule editor enables the user to define and edit the rules that describe the behavior of the system. As per the fuzzified input and output parameters, rule base is generated by applying pulse parameters in Iranian Traditional Medicine to determine and ranking the temperature of Fever diseases‎. A total of 32 rules were generated. The following are the sample rules collected from the rule base which determine the temperature of Fever diseases and the other output parameters:‎ If (extent of the expansion in in length is very high) and (extent of the expansion in width is very high) and (extent of the expansion in height is very high) and (strength is medium) and (velocity is very high) and (frequency is very high) and (vascular ‎wall ‎consistency is medium) and (artery's ‎temperature is medium) and (fullness is medium) and (‎resemblance is medium) and (regularity is medium) then (temperature is very very high) and (supply ability state is medium) and (humidity is medium) and (vascular wall consistency is medium) and (demand state is very high). For the inference mechanism, the Mamdani max-min inference was applied. Results and Discussion The proposed method was applied to determine and ranking the temperature of Fever diseases because fever was divided into different types like sanguine (of blood), melancholic, phlegmatic, daily fever, and so on. In Iranian traditional medicine careful examination of the patient as well as the background leading to fever were of utmost importance and a lot of foods prescribed for the treatment of fever were consistent with the standards of modern medicine .This is an example of the activation of rules relative to retentive causes of pulse‎ body in ITM, for the initial FIS. Figures 4, 5 and 6 show



234

snapshots of results of work done in MATLAB. The rule viewer is a read only tool that displays the whole fuzzy inference diagram. The surface viewer is also a read only tool.

Figure 4: Rule viewer view of input, output parameters.

Figure 5: Surface viewer view of input, output parameters.



235

Figure 6: Surface viewer view of input, output parameters

According to the Iranian Traditional Medicine and by using fuzzy logic, a fuzzy expert system was designed that can Rank the temperature of Fever diseases as a doctor of ITM. Therefore, 32 rules of pulse in ITM by fuzzy logic in MATLAB were reviewed; respectively. These rules have eleven (11) input parameters as the extent of the expansion in three dimensions, Strength, velocity, frequency, vascular ‎wall ‎consistency, artery's ‎temperature, fullness, ‎resemblance and regularity. As well, these rules have five (5) output parameters namely Temperature, The Supply Ability State‎, Humidity, vascular wall consistency and The Demand State‎ of the body. The linguistic variables for these parameters namely Very High, High, Medium, low and Very low were used. Finally, based on input parameters, a reasonable ranking of the fever diseases temperature was obtained using fuzzy logic. Therefore, doctors can use it to better assess patients. References 1. Anson Chui Yan Tang, et al‎, Validation of a Novel Traditional Chinese Medicine Pulse Diagnostic Model Using an Artificial Neural Network, Evidence-Based Complementary and Alternative Medicine,2012. doi:10.1155/2012/685094. 2. Azam Khan M. Aksir ‎Azam ‎(Persian), the Institute for Medical ‎History-‎Islamic and Complementary ‎Medicine,‎Tehran University of Medical ‎Sciences;‎Tehran,‎2004. 3. C. C. Lee, Fuzzy logic controller-part 1, IEEE Transactions on Systems, Man and Cybernetics, Vol. 20, No. 2, 1990. 4. ‎Emaratkar E, et al, Avicenna's view on the prevention of thrombosis, Int J Cardiol ,2013.



236

5. Emtiazy M, Keshavarz M, et al. Relation between Body Humors and Hy‎percholesterolemia: ‎An Iranian Traditional Medicine Perspective Based on ‎the Teaching of Avicenna. Iran Red ‎Crescent Med J. 2012;14(3):133–8‎. 6. Faran Baig. Muhammad Waseem Ashraf, Fuzzy Logic based Fuel Consumption System, Bahria University Journal of Information & Communication Technology Vol. 5, Issue1, december 2012. 7. Fuzzy Logic Toolbox for use with Matlab – Users Guide. 8. G.A.Bhosale. R. S. Kamath, Fuzzy Inference System for Teaching Staff Performance Appraisal, International Journal of Computer and Information Technology (ISSN: 2279 – 0764) Volume 02– Issue 03, May 2013. 9. Ibn Sina AAH. Medicine. In: al-in ‎IS, ‎editor. Al-Qanun fi al-Tibb [The Canon ‎of ‎Medicine] (Arabic). Lebanon: Alamy Le-‎Al- ‎MatbooatInstitute, 2005.‎ 10. J. Pouramini and A. Saeedi, “Fuzzy model identification for intelligent control of a vehicle speed limit,” Journal of Mathematics and Computer Science, Vol. 2, pp. 337347, 2011. 11. Lathak.C. Madhub. Ayesha S. Ramya R., Visualization of risk in breast cancer using fuzzy logic in MATLAB, International Journal of Computational Intelligence Techniques, 2013. 12. Li-Xin Wang, A course in fuzzy systems and control, 1996. 13. M. Alizadeh, M. Keshavarz, M. ‎Ebadiani, E.Nazem,M.Isfahani, Complexity ‎and rationality of Avicenna's pulsology, ‎doi:10.1016/j.ijcard.2012.03.168. 14. Shikha Rao, Lini Mathew, Rahul Gupta, Performance Comparison of Fuzzy Logic Controller with Different Types of Membership Function using Matlab Tools, IRNet Transactions on Electrical and Electronics Engineering. 15. Torres A. and Nieto J.J, Journal of Biomedicine and Biotechnology, 2005. 16. Valarmathi S., Harathi P.B., Prashanthi Devi M., Guhan P. and Balasubramanian S. Geoinformation Technology for Better Health, pp.141-144, 2008. 17. Zarshenas MM, Abolhassanzadeh Z, Faridi P, Mohagheghzadeh A. Ibn Sina's treaties on pulsology‎, Int J Cardiol ‎2010.
