پديد آورنده :
يوسفيان، علي
عنوان :
تحليل سيگنال‌هاي مغزي مبتني بر شبكه‌هاي پيچيده براي بهبود تشخيص اوتيسم
مقطع تحصيلي :
كارشناسي ارشد
محل تحصيل :
اصفهان : دانشگاه صنعتي اصفهان
صفحه شمار :
دوازده،74ص.:مصور،جدول،نمودار
استاد راهنما :
زينب مالكي، فرزانه شايق
توصيفگر ها :
شبكه مغزي , شبكه‌هاي پيچيده , سيگنال‌هاي مغزي، , اوتيسم , يادگيري بازنمايي , قدم‌زن ناشناس
استاد داور :
ناصرقديري، محمد حسين منشئي
تاريخ ورود اطلاعات :
1399/09/15
دانشكده :
مهندسي برق و كامپيوتر
تاريخ ويرايش اطلاعات :
1399/09/16
چكيده انگليسي :
Analysis of brain signals based on complexnetworks to improve the diagnosis of autism Ali Youse an a youse an@ec iut ac ir July 2020 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Under supervison of Dr Maleki Dr ShayeghAbstract This study proposed to use representational learning algorithms to improve the identi cation of peo ple with autism People with autism They have a type of brain based disorder that is born with socialdefects and repetitive behaviors According to recent data from the Centers for Disease Control one in68 children in the United States who have autism Brain images of people with autism from two databases each from several sites and universitiesworldwide known as ABIDE Diagnosing people with autism is one of the most critical goals in cognitivescience research The topic of discussion in this eld is studying people with autism disorders andthe brain areas that cause these disorders Cognitive science proposes to help diagnose the disease byexamining brain areas and comparing these areas in healthy people to people with the disease One of the methods that have recently been considered is the connectome matrix This approach hasled to the analysis of brain graphs and their comparison using complex networks The connection matrixis usually analyzed using a complex network Numerous papers examining the brain using sophisticatednetwork metrics have attempted to improve the diagnosis of autism In recent years attempts have beenmade to study this disease using in depth learning methods which consider the connection matrix animage The nature of this matrix is not an image but a graph that has complex grid metrics The methods introduced in this study try to optimize the processing and reduce the time complexityin the deep learning network by using representational learning to increase the accuracy to help diagnosepeople with autism Therefore in this dissertation we have tried to improve the diagnosis of autism byusing representational learning methods to analyze complex networks with deep learning methods Inthis study we were able to increase the accuracy in classifying people with autism and healthy peopleand maintain the connectome graphic structure in the analysis In this study the overall accuracy of theentire autism database reached 65 percent and the accuracy of each university site for the databasesshowed a good improvement and the accuracy of each university site for the databases showed a goodimprovement Key Words fMRI Embedding Representation learning Node2vec struct2vec DeepWalk
استاد راهنما :
زينب مالكي، فرزانه شايق
استاد داور :
ناصرقديري، محمد حسين منشئي
