KARKAS: a toolkit for creating a knowledge base
KARKAS: the shell for creating a knowledge base

Registration »         Forgot password »

04 Август 2022

07 Февраль 2019
MODEL OF HIERARCHICAL FUNCTIONAL SYSTEM FOR CLUSTER ANALYSIS Collection of Scientific Papers of KhNUPS 2(56). Kharkiv, 2018, p. 82 - 88. The model of the hierarchical functional system of the subject area...

24 Апрель 2015
Laboratory workshop on the system "KARKAS" / Computer Based Training Contains laboratory work, the purpose of which is the practical development of skills in the construction of knowledge bases by users using a tool...

Application (prototypes of expert systems)

With the help of the "KARKAS" system, a number of prototypes of expert systems have been developed in the following subject areas: medicine, economics, mobile communications and cluster analysis of multidimensional data.
In the field of medicine, there are the following prototypes of ES:
the RIBS system is designed to determine the risk of coronary heart disease (CHD) in a practically healthy person. The relevance of its development is explained by the fact that at present in medicine the process of transition to the concept of CHD prevention, that is, to the concept of risk factors associated with the lifestyle of a particular patient, is clearly expressed. Realizing the importance of this concept, most doctors do little to prevent coronary artery disease in their daily work. One of the reasons for this is the lack of a clear system for identifying risk factors for coronary artery disease, designed to help the doctor diagnose and assess the risk of developing this disease. The purpose of the system is to recognize the presence of risk factors for coronary artery disease with an emphasis on the patient's individual lifestyle, using expert knowledge. The features of the system include the fact that with its help the patient is diagnosed with: type of coronary behavior; the degree of socio-psychological support; level of physical activity; the degree of adequacy of rest;
the "INFARKT" system ─ helps doctors diagnose infarction patients, assess their condition and predict the development of the following complications in myocardial infarction: fibrillation; acute left ventricular failure; chronic heart failure; arrhythmias; thromboembolism; myocardial rupture; re-infarction. The system puts forward two hypotheses: complicated and smooth (without complications) course of myocardial infarction in a patient. Then, in consultation with the doctor, she calculates the odds of these hypotheses based on the patient's symptoms and history. If the first hypothesis is accepted, then the analysis of the calculated posterior probability begins, which serves as the basis for diagnosing the degree of development of the corresponding infarction complication. Logical inference relies on Bayesian decision making;
"HEPATITIS" system is designed for diagnosing acute and chronic liver diseases. The system makes it possible to: recognize the cause of liver disease and, if possible, obtain a therapeutic effect by eliminating it; purposefully include medications for the treatment of liver diseases; conduct a statistical evaluation of therapeutic measures in patients. There are three knowledge clusters in the subject area: clinical data; laboratory data; morphological data that allow a detailed diagnosis of liver disease. The first cluster of knowledge uses the data of the anamnesis and complaints of the patient from the liver, the results of palpation and percussion of the liver, as well as the examination (appearance) of the patient. The second cluster of knowledge based on laboratory and chemical changes in liver function, liver cell damage, cholestasis, mesenchymal activity and immunological response studies makes it possible to determine the type of jaundice, as well as the nature of liver disease. The third cluster allows you to determine the indications for morphological diagnosis. For example, information is given that a percutaneous liver biopsy should be performed or not;
the "ADRAMZH" system (automatic diagnosis of breast cancer) is designed for early diagnosis of breast tumors. Diagnosis is based on the knowledge of an expert oncologist, which are grouped into the following sections: thermography; anamnesis; physical research; echotomography. The system allows to classify the following tumors: lipoma; fibroadenoma; fibrocystic mastopathy diffuse; fibrocystic mastopathy localized; DPA (diffuse); DFA (localized); mastitis.
In the field of economics, the following knowledge bases have been developed and are being modified: to select a commercial bank; to insure commercial loans; to select suppliers of products; to choose a pricing strategy; to assess the creditworthiness of the borrower; to assess the creditworthiness of the enterprise; to select a deposit; to assess the financial condition of the enterprise; for product selection; for marketing management and so on.
In the field of mobile communications, the following ES prototype has been developed:
"MOBILE" system ─ allows you to quickly and efficiently select a mobile phone in the following categories: budget (economy class); Business Class; fashion (very expensive). These categories are conditional, if desired, they can be increased or decreased. In each category, the phone is selected according to certain priority parameters. For example, the following characteristics are important for the budget apparatus: price; design (weight, dimensions of the device); battery capacity; phone book, alarm clock, calculator. And for the business class, the device should have other functional characteristics: a large notebook; Bluetooth (IrDA - infrared port); GPRS. For fashion devices, design comes first when choosing: weight and appearance.
The "KARKAS" system has an intellectual module

2012 г. it-karkas.com.ua
Vladimir Burdaev
Info for users
Site map


Copyright 2012 - it-karkas.com.ua
Website development - alphastudio.com.ua