داده نمايي با استفاده از الگوريتم ژنتيك; مطالعه موردي : بار برق مصرفي اصفهان

چكيده انگليسي :

83Data visualization with genetic algorithm case study Electrical Daily Load of Esfahan Vahid Golmah v golmah@in iut ac ir Department of Industrial Engineering Isfahan University of Technology Isfahan 84156 83111 IranDegree M Sc Language FarsiJamshid Parvizian japa@cc iut ac ir Supervisor AbstractWith the rapid growth of database in many modern enterprise data mining has became an increasingly importantapproach for data analysis Data mining activities include both direct and indirect approaches Direct data miningfocuses on one target variable whereas in undirected data mining the goal is understand the relationship amongstall of the variables Data visualization is a key component of undirected data mining Visualization of multi dimensional data is a challenging task The goal is not display of multiple data dimensions but user comprehension of multi dimensional data Data visualization techniques have become important toolsfor analyzing large multi dimensional data sets and providing insight with respect to scientific economic andengineering applications The most common methods allocate a representation for each data point in a lower dimensional space and try tooptimize these representations so that the distances between them are as similar as possible to original distance ofthe corresponding data items The methods differ in that how the different distances are weighted and how therepresentations are optimized Linear mapping like principle component analysis is effective but cannot trulyreflect the data structure Non linear mapping like Sammon mapping Multi dimensional scaling MDS and SelfOrganization Map SOM requires more computation but is better at preserving the data structure We propose a discretization of the data visualization problem that allows us to formulate is computationallydifficult to solve optimally using an exact approach We investigate the use of Genetic Algorithm GA for thedata visualization problem Genetic algorithms are efficient and robust searching and optimization methods thatare used in data mining Volume of data in data mining is large and Genetic Algorithm search on all of points using of genetic algorithmto solve this problem require to high computatations Therefore to improve the quality of solutions of geneticalgorithm develop a Self Adaptive Island Genetic Algorithm SAIGA Where parameters of crossover rate mutation rate survival rate and migration rate of each population are adaptively fixed In addition to effective ofcommunications topology between subpopulations that ignore in adaptive genetic algorithm developed GeneticAlgorithm use different communications topology and analyze them This algorithm is a more focused and concentrated search of heuristically high yielding region whilesimultaneously performing a highly explorative search on the other regions of the search In other word thisalgorithm improves the power of exploration and exploitation independently In order to compare the proposed technique QAP GA and famous algorithm self organization map SOM weuse a empirical study and run these technique on it Used data set in this research includes 24 hour electrical loadof 366 days from 20 March 2008 in Esfahan Result of different methods shows that resulted solution of proposed

گلماه، وحيد

داده نمايي با استفاده از الگوريتم ژنتيك; مطالعه موردي : بار برق مصرفي اصفهان

تخصيص درجه دو , نگاشت خود سازمان يافته