Design of a reference intelligence expert system for sheep breeding in national private farms

• Main Author: Dmytro Lubko
• Format: Article
• Language: English
• Published: Profi.Net.Ua Group; Department of Informatics and Cybernetics; Melitopol Bohdan Khmelnytsky State Pedagogical University 2017-09-01
• Series: Ukrainian Journal of Educational Studies and Information Technology
• Subjects: інтелектуальна експертна система; вівчарство; довідковий модуль; вівці; технологія розведення
• Online Access: http://ojs.mdpu.org.ua/index.php/itse/article/view/1924

The paper deals with the design of a reference intelligence expert system for sheep breeding. The process of its design and its functional capabilities are described. The developed reference intelligence expert system makes it possible to display recommendations and tips on the computer screen to select a rational and effective sheep breeding technology, as well as to print the received data. The developed system has a two-tier structure, namely, dialog selection of input criteria (data), as well as a module for logical processing and output of reasonable technology recommendations (output data). The step-by-step method of designing the system is determined. The first step is to obtain a technical specification from the customer (farm, enterprise, farmer, etc.) for the development of a reference system. The second step is to determine criteria for the technology in keeping with the farm requirement specification according to the literature and sheep breeding requirements. The third step is to identify the most important factors influencing the process of sheep raising for each of these criteria. The fourth step is to define the main production rules for which the system will be programmed, namely, the module for logical knowledge processing for this technology (and these are the input parameters (factors) when designing the system). The fifth step is to determine the main output criteria (factors) that will be displayed after processing the input rules of the system based on logical deduction rules according to the appropriate sheep breeding technology. The sixth step is to design buttons for more convenient system usage, in addition, if necessary, or at the request of the customer (for example, a button for deleting previous information in windows, a button for storing recommendations in a separate text file, the exit button, etc.). The seventh step is to test the system by users and the customer. The eighth step is to adopt the developed system by the customer and correct it, if necessary. The ninth step is to provide maintenance of the developed system. The block of input data of the developed intelligence expert system has the following elements: a) sheep handling (pasture-stall, stall-pasture); b) sheep condition (higher condition, average condition, lower than average condition); c) sheep breeding type (meat, milk, meat and milk, wool); d) sheep feeding (meat-and-wool sheep, rams of meat-and-goat sheep, sucking females to lactation); e) methods of breeding (purebred, crossing). The block of output factors where appropriate rational recommendations for sheep breeding technology comprises: a) recommendations for sheep handling; b) recommendations for treatment of sheep diseases; c) recommendations for sheep feeding; d) sheep slaughter and storage of products; e) recommended sheep breeds; f) recommendations for sheep breeding; g) characteristics of products. The developed system is intended primarily for private national farmers or interested private householders. It is noted that the use of this system will allow private households to increase the production and quality of meat, wool, lambskin and furs when breeding sheep. This will reduce the cost of the breeding technology, save the farmer time, allow to save on medicines, feeds, which, in turn, will increase profits and profitability of farms.