International Journal of e-Healthcare Information Systems (IJe-HIS), Volume 4, Issue 1, June 2017Knowledge Acquisition for an Expert System for Diabetic Type-2 DietIbrahim M.Ahmed1, Abeer M.Mahmoud2, Abdel-Badeeh M.Salem21Karray University, Khartoum, Sudan2Ain Shams University, Cairo, EgyptAbstractDiabetes is a serious health problem today. Mostof the people are unaware that they are in risk of ormay even have type-2 diabetes. Type-2 diabetes isbecoming more common due to risk factors like olderage, obesity, lack of exercise, family history ofdiabetes, heart diseases . Along with good lifestyleand healthy diet, reduces the risk of development oftype 2 diabetes for treatment of elder people , propercare of diet, exercise and medication as well is moreimportant. The research in developing intelligenceknowledge base systems in diabetic domain isimportant for both health industry and diabetespatients. Recently expert systems technology providesan efficient tools for diagnosing diabetes and henceproviding a sufficient treatment. The main challengein building such systems is the knowledge acquisitionand development of the knowledge base of thesesystems. Our research was motivated by the need ofsuch an efficient tool. This paper presents theknowledge acquisition process for developing theknowledge base of diabetic type-2 diet.1. IntroductionDiabetes is one of the major risky diseases forhealth care in our lives. If people were aware of thefactors of diabetes and know how much risks they areof getting diabetes, diabetes may be prevented early. Type 2 diabetes is a disease resulting from arelative, rather than an absolute, insulin deficiencywith an underlying insulin resistance. Type 2diabestes is associated with obesity, age, and physicalinactivity [2, 3]. It is more common as compare totype-1 diabetes, usually 90 to 95%. It is diagnosed inboth adults and young people. In this type pancreasdoes not produce enough insulin to control keepingblood sugar level within normal ranges. Actually it isserious type of diabetes where mostly people are notaware they are suffering from it. Three major causesof diabetes type 2 are lifelong bad diet, inactive orsedentary lifestyle, and overweight .Actually, In the domain of medical treatment bycontrolling patient food (healthy diet) there arenumerous variables that affect the decision process ofselecting interesting food list from the patient point ofview and efficient list in treatment from theCopyright 2017, Infonomics Societydoctor's point of view. These numerous variablescausing the differences in the opinions of thepractitioners. Also, there are many uncertain riskfactors resulted from eating certain types of food withcertain amount. Therefore, an accurate tool will be ofa great help for an expert to consider all these riskfactors and show certain results.On the other hand the research in developingintelligence knowledge base systems in diabeticdomain is important for both health industry anddiabetes. Expert system is a computer program thatprovides expert advice as if a real person had beenconsulted where this advice can be decisions,recommendations or solutions. A few numbers ofexpert systems are utilized in diabetic health researchwhere each of these systems attempts solving part orwhole of a significant problem to reduce the essentialneed for human experts and facilitates the effort ofnew graduates .The paper is organized as follows. Section 2presents major risk factors Diabetic Diet and DiabeticFood Pyramid. Section 3 describes the related work.Section 4 present the knowledge acquisition and therepresentation process. Section 5 screening ofdiabetics. Section 6 reasoning techniques in diabeticexpert systems. Section seven ends up withConclusion.2. Related workM. Beulah et. al (2007)  introduced the abilityto access diabetic expert system from any part of theworld.They collect, organize, and distribute relevantknowledge and service information to the individuals.The project was designed and programmed via the dotnet framework. The system allows the availability todetect and give early diagnosis of three types ofdiabetes namely type 1, 2, gestational diabetes forboth adult and children.Szajnar and Setlak  proposed a concept ofbuilding an intelligence system of support diabetesdiagnostics, where they implemented start-of-artmethod based on artificial intelligence forconstructing a tool to model and analyze knowledgeacquired from various sources. The initial target oftheir system was to function as a medical expertdiagnosing diabetes and replacing the doctor in thefirst phase of illness. Diagnostics the sequence of120
International Journal of e-Healthcare Information Systems (IJe-HIS), Volume 4, Issue 1, June 2017dealing with their system were as flow: (1) gettingpatient information and symptoms (2) competingbasic medical examination in details (3) based onprevious information the system find out whether thepatient has diabetes and decides whether it is type1 ortype2. The systems used decision tree as a model forclassification.Kumar and Bhimrao  developed a naturaltherapy system for healing diabetic, they aim to helppeople's health and wellness, which don't cost theearth. Their main goal was to integrate all the naturaltreatment information of diabetes in one place usingESTA (Expert System Shell for Text Animation) asknowledge based system. ESTA has all facilities towrite the rules that will make up a knowledge base.Further, ESTA has an inference engine which can usethe rules in the knowledge base to determine whichadvice is to be given to the user.Their system begins with Consultation asking theusers to select the disease (Diabetes) for which theywant different type of natural treatment solution thendescribes the diabetes diseases and their symptoms.After that describes the Natural Care (Herbal /ProperNutrition) treatment solution of diabetes disease.Bayu Adhi Tama, Rodiyatul and Hermansyah proposed and boosted algorithm acquires informationfrom historical data of patient’s medical records ofMohammad Hoesin public hospital in SouthernSumatera. Rules are extracted from Decision tree tooffer decision-making support through early detectionof Type-2 diabetes for clinicians, table 1.Table 1. Expert systems for diabetestheir glucose level in their blood. It also helps toprevent diabetes patient from heart and blood vesselrelated diseases .Research shows that regardless of the makeup ofthe diet, eating just enough calories to maintain anideal weight is the most effective dietary strategy toprevent the onset of diabetic. Recommendations ofdiabetic diet differ for person to person, based on theirnutritional needs, lifestyle, and the action and timingof medications. In Type 2 diabetic, the concern may be moreoriented to weight loss in order to improve the body'sability to utilize the insulin it does produce. Thus,learning about the basic of food nutrition will be ableto help in adjusting diet to suite the particularcondition. Recommended daily food portion containscarbohydrates, protein and fat.A Registered Dietitian assesses the nutritionalneeds of a person with diabetes and calculates theamounts of carbohydrate, fat, protein, and totalcalories needed per day. He will then convert thisinformation into a recommended list of food for dailydiet  (see Table 2).Table 2. Recommended daily food portion3.2. Diabetic Food Pyramid3. Diabetic Diet and Food groups3.1. Diabetic DietDiabetic Diet for diabetics is simply a balancedhealthy diet which is vital for diabetic treatment. Theregulation of blood sugar in the non-diabetic isautomatic, adjusting to whatever foods are eaten. But,for the diabetic, extra caution is needed to balancefood intake with exercise, insulin injections and anyother glucose altering activity. This helps diabeticpatient to maintain the desirable weight and controlCopyright 2017, Infonomics SocietyFigure 1. Food PyramidThe Diabetes Food Guide Pyramid is a tool thatshows how much you should eat each day from eachfood group for a healthy diet. The Diabetes Food121
International Journal of e-Healthcare Information Systems (IJe-HIS), Volume 4, Issue 1, June 2017Guide Pyramid is the best food guide for people withdiabetes. The Diabetes Food Guide Pyramid placesstarchy vegetables such as peas, corn, potatoes, sweetpotatoes, winter squash, and beans at the bottom of thepyramid, with grains. These foods are similar incarbohydrate content to grains. Cheese is in the Meatand others group instead of the Milk group becausecheese has little carbohydrate content and is similar inprotein and fat content to meat .Choosing foods from the Diabetes Food GuidePyramid can help you get the nutrients you need whilekeeping your blood glucose under control .Foods that are high in carbohydrates increase bloodglucose levels and are in the Grains, Beans, andStarchy Vegetables group, the Fruits group, and theMilk group.Other foods that raise blood glucose are Sweets,found in the top of the Pyramid. Starchy foods, sweetfoods, fruits and milk are high in carbohydrate. Foodslows in carbohydrates are found in the Vegetablesgroup, Meat and Others group and Fats. Diabetespatient should eat 6 to 11 servings Grains, 2 to 5servings Group Vegetable, 2 to 4 servings GroupFruit, 2 to3 servings Group Milk, 2 to 3 servings groupprotein, Group sugars and oils should rarely be eaten.4. Knowledge acquisition andrepresentation4.1. Knowledge acquisitionKnowledge acquisition is a very important phasein developing expert systems . Our knowledge hasbeen gained by consultation of nutritionist. Actually,knowledge acquisition required time of three monthsform major Ibtehal and Nasik nutritionist of diabetesin the military hospital in Khartoum, in addition tosome related books and internet medical web sites. Inaddition we determine Sudanese food groups in Fig. 2and analyse the amount of each item in the foodgroups in Table 3.3.3. Food groupsFood groups are exchange lists of foods thatcontain roughly the same mix of carbohydrates,protein, fat, and calories, serving sizes are defined sothat each will have the same amount of carbohydrate,fat, and protein as any other. Foods can be"exchanged" with others in a category while stillmeeting the desired overall nutrition requirements.Food groups can be applied to almost any eatingsituation and make it easier to follow a prescribed diet.Figure 2. Sudanese food servings according to thediabetes food guide pyramidTable 3. Standards of itemsThere are six food groups :1. Vegetables2. Starches and Breads3. Fruits4. Milk5. Fat6. Meats and Meat SubstitutesThe food groups are based on principles of goodnutrition that apply to everyone. The reason fordividing food into six different groups is that foodsvary in their carbohydrate, protein, fat, and caloriecontent. Each group contains foods that are alike; eachfood choice on a group contains about the sameamount of carbohydrate, protein, fat, and calories asthe other choices on that group .Copyright 2017, Infonomics Society4.2. Knowledge representationKnowledge representation allows one to specifyand emulate systems of a growing complexity.Knowledge representation schemes indeed haveknown an important evolution, from basic schemessupporting a rather heuristic approach, to advancedschemes involving a deeper consideration of the122
International Journal of e-Healthcare Information Systems (IJe-HIS), Volume 4, Issue 1, June 2017various dependencies between knowledge elements. The main Types of diabetes are Type1, Type2and Gestational .figure 3 describes Knowledgerepresentation of the diabetic serving.Figure 3. Knowledge representation4.3. Food groups servingsSome diseases increase the risk of diabetic diseaseand affect the number of serving in the food groups ,the major diseases we get from our Knowledgeacquisition are Anorexia, Surgery , Blood pressure,Typhoid, Bitter, Liver problems, Heart disease andGout . Other factors affect the serving are the patientactivity, and weight see fig 4. Fig 5 shows a sample ofthis frame based representation.4.4. Knowledge analysisThe following is the algorithm to specify thenumbers of serving to each patient according to fig 4.1. Determine whether the patient is slim or moderateor obese.2. Determine whether the patient activity is high ormoderate or little.3. Determine whether the patient infected with(Anorexia, Surgery, Blood pressure, Typhoid, Bitter,Liver problems, Heart disease, Gout)4. Calculate number of servings as follows:Vegetable- servings 3If (anorexia 1) or (surgery 1) or (age 65) thenfruit- servings 4 else fruit- servings 2If activity "normal" then crabs-servings 6Else if activity "high" then crabs-servings 8If the patient underweight then crabs-servings 10If ((gout 1) or (Heart disease 1) or (Bitter 1) or(liver problems 1) or (Blood pressure 1) or(Typhoid 1)) then protein-servings 2 else proteinservings 3If ((gout 1) or (Heart disease 1) or (Bitter 1) or(liver problems 1) or (Blood pressure 1) or(Typhoid 1)) then milk-servings 2 else milkservings 3.5. Screening of diabeticsFigure 4. Diabetics numbers of allowed servingsEarly Warning Signs for Type 2 Diabetes a bloodglucose level should be checked. The criteria testingfor Type 2 diabetes in children and adolescents is,overweight (BMI 85th percentile for age andgender, weight for height 85th percentile or weight 120% of ideal for height). And frequency test shouldbe every 2 years and fasting plasma glucose is thepreferred method for screening. Diabetes may bediagnosed based on A1C criteria or plasma glucosecriteria, either the fasting plasma glucose (FPG) or the2-h plasma glucose (2-h PG) value after a 75-g oralglucose tolerance test (OGTT), the same tests are usedto screen diabetes every 3 month to assess the mealplanning that If the patient used the meal plan beforeand his BGL still above 140 or A1C above 6,5 , itrecommend to visit the doctor .6. Reasoning techniques in diabetic expertsystemsFigure 5. Sample of diabetics food framerepresentationCopyright 2017, Infonomics SocietyThe abilities of inference, reasoning, and learningare the main features of any expert system. Theresearch area in this field covers a variety of reasoningmethodologies, e.g.; automated reasoning, case-basedreasoning, commonsense reasoning, multi-modelreasoning, fuzzy reasoning, geometric reasoning, nonmonotonic reasoning, model-based reasoning,probabilistic reasoning, causal reasoning, qualitativereasoning, spatial reasoning and temporal reasoning123
International Journal of e-Healthcare Information Systems (IJe-HIS), Volume 4, Issue 1, June 2017. In this section we focus our discussion about themain characteristics of three of the reasoningmethodologies which are commonly used indeveloping diabetic expert systems, namely;reasoning with production rules, fuzzy-rules, andcase-based reasoning.6.1. Reasoning with Production RulesProduction rules are the most commonly techniqueused in developing the inference engine of expertsystem. Forward chaining can be used to produce newfacts (hence the term “production” rules), andbackward chaining can deduce whether statements aretrue or not. Rule-based systems were one of the firstlarge-scale commercial successes of artificialintelligence research.6.2. Reasoning with CasesCase-Based Reasoning (CBR) means reasoningfrom experiences (old cases) in an effort to solveproblems, critique solutions and explain anomaloussituations. The CBR systems’ expertise is embodiedin a collection (library) of past cases rather, than beingencoded in classical rules.CBR allows the case-libraryto be developed incrementally, while its maintenanceis relatively easy and can be carried out by domainexperts .6.3. Reasoning with Fuzzy RulesIn the rich history of rule-based reasoning in AI,the inference engines almost without exception werebased on Boolean or binary logic. However, in thesame way that neural networks have enriched the AIlandscape by providing an alternative to symbolprocessing techniques, fuzzy logic has provided analternative to Boolean logic-based systems. UnlikeBoolean logic, which has only two states, true or false,fuzzy logic deals with truth values which rangecontinuously from 0 to 1. Thus something could behalf true 0.5 or very likely true 0.9 or probably not true0.1. The use of fuzzy logic in reasoning systemsimpacts not only the inference engine but theknowledge representation itself .7. ConclusionsType-2 diabetes is the most common form ofdiabetes. This paper presents the first phase ofdeveloping an efficient expert system for diabeticType-2 diet. The structure of the system contains threesteps. First calculate total needs of calories, seconddetermines the amount calories of the items andfinally determines the proper diet.Self-monitor for patient of type 2 diabetes ispossible by getting proper amount of daily proper dietCopyright 2017, Infonomics Societysatisfy the amount of calories. The servings of mealscalculate according to Body Mass Index (MBI) andthe type of activity for the patient and the additionalpatientdiseases. The food groups contain the same amountof carbohydrate, protein, fat, and calories Sudanesefood groups contains different meals so you don’thave to eat the same foods all the time.After collectingknowledge and perform the necessary analysissemantic network and food serving representation,Currently we are working on developing mobilebased expert system in Arabic language interface fordiabetes diet that intended to be used in Sudan andArab countries.The research area in this field covers a variety ofreasoning methodologies, e.g.; case-based reasoning,ontology case-based reasoning, fuzzy reasoning andrule reasoning. Case based reasoning is the moreefficient, powerful and less cost. Our research wasmotivated by the need of such techniques, thereforethe reasoning techniques for diabetics expert systemhas been presented in this paper as platform towardsdesigning and implementation expert systems fordiabetes.Initially capitalize only the first word of eachfigure caption and table title. Figures and tables mustbe numbered separately. For example: “Figure 1.Database contexts”, “Table 1. Input data”. Figurecaptions are to be centered below the figures. Tabletitles are to be centered above the tables.8. References Huiqing H. Yang and Sharnei Miller, "A PHP-CLIPSBased Intelligent System for Diabetic Self-Diagnosis",Department of Math & Computer Science, Virginia StateUniversity Petersburg, 2006. Edward H. Shortliffe, Leslie E. Perreault, et al, MedicalInformatics: Computer Applications in Health Care andBiomedicine, Springer-Verlag New York, Inc, 2001. Federal Bureau of Prisons Management of DiabetesClinical Practice Guidelines June 2012. David Forbes, Pornpit Wongthongtham and JaipalSingh, "Development of Patient-Practitioner AssistiveCommunications (PPAC) Ontology for Type 2 DiabetesManagement", Curtin University, Perth, Australia, 2013. Byoung-Ho Song, Kyoung-Woo Park and Tae YeunKim. "U-health Expert System with Statistical NeuralNetwork", Advances on Information Sciences and ServiceSciences. vol. 3, no.1, pp 54-61, 2011. P. M. Beulah Devamalar, V. Thulasi Bai, and Srivatsa S.K. "An Architecture for a Fully Automated Real-Time WebCentric Expert System", World Academy of Science,Engineering and Technology, 2007.124
International Journal of e-Healthcare Information Systems (IJe-HIS), Volume 4, Issue 1, June 2017 Wioletta SZAJNAR and Galina SETLAK. " A conceptof building an intelligence system to support diabetesdiagnostics", Studia Informatica, 2011. Sanjeev Kumar and Babasaheb Bhimrao, "Developmentof knowledge Base Expert System for Natural treatment ofDiabetes disease", (IJACSA) International Journal ofAdvanced Computer Science and Applications, Vol. 3, No.3, 2012. Bayu.A.T et.al ,” An Early Detection Method of Type-2Diabetes Mellitus in Public Hospital “,2 TELKOMNIKA,Vol.9, No.2, pp. 287-294 , August 2011. The Diabetic Exchange List. (2013) [Online].Available: http://www.glycemic.com/Diabetic Exchange(Access Date: 25 September 2016) Diet for diabetes patient. (2013) [Online]. /Diabetics7.html (Access Date: 25 September 2016) Igbal.A and Nagwa. M,"health guide for diabetics",Sudan Federal ministry of health, 2010. Mario A Garcia, Amit J.Gandhi, Tinu Singh, LeoDuarte, Rui Shen, Maruthi Dantu Steve Ponder, and HildaRamirez. "ESDIABETES (AN EXPERT SYSTEM INDIABETES)", JCSC 16, pp 166-175. 2001. Diabetes Education and Prevention" World DiabetesDay. (2012) [Online]. Available: http://www.diabetesdiabetic-diet.com," (Access Date: 25 September, 2016) Stephan Grimm, Pascal Hitzler and Andreas Abecker,"Knowledge Representation and Ontologies Logic,Ontologies and SemanticWeb Languages", University ofKarlsruhe, Germany, pp 37-87,2007.Abdulla Al-Malaise Al-Ghamdi et al," An ExpertSystem of Determining Diabetes Treatment Based on CloudComputing Platforms", International Journal of ComputerScience and Information Technologies, Vol. 2 (5), pp 19821987, 2011.M. Sue Kirkman, MD. And Vanessa Jones Briscoe,"Diabetes in Older Adults: A Consensus Report", AmericanDiabetes Association and the American Geriatrics Society,2012. Zadeh, L. A., “Fuzzy Sets”, Information and Control,8, 338-353, 1965. Salem, A-B.M., Roushdy, M. and HodHod, R. A., “ARule-Base Expert System for Diagnosis of Heart Diseases”,Proceedings of 8th International Conference on SoftComputing MENDEL. Brno, Czeeh Republic, June 5-7,2002, pp. 258-263. Abdel-Badeeh M. Salem and Michael Gr.Voskoglou,“Applications of CBR Methodology to Medicine “,Egyptian Computer Science Journal, ISSN 1110-2586,Special Issue for EMMIT 9th Int. Conf. for Scientific andSocial Development in Mediterranean Countries ,Nador,Morocco, October 21-23,2013, Vol.37,No.7,pp.68-77,2013.Copyright 2017, Infonomics Society125
Diabetic Diet Diabetic Diet for diabetics is simply a balanced healthy diet which is vital for diabetic treatment. The regulation of blood sugar in the non-diabetic is automatic, adjusting to whatever foods are eaten. But, for the diabetic, extra caution is needed to balance food intake with exercise, insulin injections and any other glucose .
Bruksanvisning för bilstereo . Bruksanvisning for bilstereo . Instrukcja obsługi samochodowego odtwarzacza stereo . Operating Instructions for Car Stereo . 610-104 . SV . Bruksanvisning i original
10 tips och tricks för att lyckas med ert sap-projekt 20 SAPSANYTT 2/2015 De flesta projektledare känner säkert till Cobb’s paradox. Martin Cobb verkade som CIO för sekretariatet för Treasury Board of Canada 1995 då han ställde frågan
service i Norge och Finland drivs inom ramen för ett enskilt företag (NRK. 1 och Yleisradio), fin ns det i Sverige tre: Ett för tv (Sveriges Television , SVT ), ett för radio (Sveriges Radio , SR ) och ett för utbildnings program (Sveriges Utbildningsradio, UR, vilket till följd av sin begränsade storlek inte återfinns bland de 25 största
Hotell För hotell anges de tre klasserna A/B, C och D. Det betyder att den "normala" standarden C är acceptabel men att motiven för en högre standard är starka. Ljudklass C motsvarar de tidigare normkraven för hotell, ljudklass A/B motsvarar kraven för moderna hotell med hög standard och ljudklass D kan användas vid
LÄS NOGGRANT FÖLJANDE VILLKOR FÖR APPLE DEVELOPER PROGRAM LICENCE . Apple Developer Program License Agreement Syfte Du vill använda Apple-mjukvara (enligt definitionen nedan) för att utveckla en eller flera Applikationer (enligt definitionen nedan) för Apple-märkta produkter. . Applikationer som utvecklas för iOS-produkter, Apple .
och krav. Maskinerna skriver ut upp till fyra tum breda etiketter med direkt termoteknik och termotransferteknik och är lämpliga för en lång rad användningsområden på vertikala marknader. TD-seriens professionella etikettskrivare för . skrivbordet. Brothers nya avancerade 4-tums etikettskrivare för skrivbordet är effektiva och enkla att
Den kanadensiska språkvetaren Jim Cummins har visat i sin forskning från år 1979 att det kan ta 1 till 3 år för att lära sig ett vardagsspråk och mellan 5 till 7 år för att behärska ett akademiskt språk.4 Han införde två begrepp för att beskriva elevernas språkliga kompetens: BI
**Godkänd av MAN för upp till 120 000 km och Mercedes Benz, Volvo och Renault för upp till 100 000 km i enlighet med deras specifikationer. Faktiskt oljebyte beror på motortyp, körförhållanden, servicehistorik, OBD och bränslekvalitet. Se alltid tillverkarens instruktionsbok. Art.Nr. 159CAC Art.Nr. 159CAA Art.Nr. 159CAB Art.Nr. 217B1B