نوع مقاله : علمی - پژوهشی
نویسندگان
1 کارشناس ارشد GIS و سنجش از دور، دانشگاه تربیت مدرس
2 دانشیار گروه مهندسی GIS، دانشگاه صنعتی خواجه نصیرالدین طوسی
3 استادیار گروه سنجش از دور و GIS، دانشگاه تربیت مدرس
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسندگان [English]
Management and planning of urban water supply in metropolis is very important. Development of the region urban and make cities to metropolis and increase of effective complex factor on water usage in the cities make consumption management and supply and distribution Water difficult. So rule extraction plays an important role in exploring patterns over data and decreasing complex. Rough Set Algorithm, which was developed in 1980s by Pawlak, is a powerful and flexible method to deal with uncertain and ambiguous data which has been used in this research to extract dominant rules over data set. The method used in this paper is combination of the rough set and genetic algorithms from data mining methods to develop rule extraction and data classification of water usage in Tehran city as the studying area. Socio-economic, environmental, time and water consumption and management zones have been used as the explanatory variables for prediction of the water use that database divided to 2 part 60% for result extraction and 40% as test set. Independent test sets have been used for evaluation of the accuracy of the extracted rules. Results have shown that, combination of the genetic algorithms and Rough Set leads to extraction of more reliable rules. Classification accuracy of the extracted rules from Rough sets was 77 percent. But optimization of rules by combination of the genetic algorithm with Rough sets, resulted in classification accuracy of 88 percent in 6th generation with average speed of convergence. By using the same speed of convergence in the accuracy increased to 92 percent in 10th generation. According to the extracted rules, important effective factors on annual water consumption are respectively the resident population, water price, population density, family size, spatial location (latitude), education levels, and per capita green spaces.
کلیدواژهها [English]