پديد آورنده :
سمبلستان، محسن
عنوان :
نمايانسازي تماسي بي درنگ قرنيه چشم با استفاده از شبكه عصبي مصنوعي
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
طراحي كاربردي (ديناميك، كنترل و ارتعاشات)
محل تحصيل :
اصفهان : دانشگاه صنعتي اصفهان
صفحه شمار :
سيزده، 58ص.: مصور، جدول، نمودار
استاد راهنما :
سعيد بهبهاني
استاد مشاور :
محمد سيلاني
توصيفگر ها :
نمايانسازي تماسي , يادگيري ماشين , شبكه عصبي مصنوعي , اجسام تغييرشكلپذير , چندجملهاي زرنيك
استاد داور :
محمد دانش، مصطفي غيور
تاريخ ورود اطلاعات :
1399/07/21
رشته تحصيلي :
مهندسي مكانيك
تاريخ ويرايش اطلاعات :
1399/07/21
چكيده انگليسي :
Real time Haptic Rendering of Cornea Based on Artificial Neural Network Seyed Mohsen Sombolestan m sombolestan@me iut ac ir September 21 2020 Department of Mechanical Engineering Isfahan University of Technology Isfahan 84156 83111 IranDegree Master of Science Language FarsiSupervisor Dr Saeed Behbahani Assoc Prof Behbahani@cc iut ac ir AbstractDuring the last decade haptic has been a new emerged and interesting subject for many researchers which canbe classified into three topics such as human haptics machine haptics and computer haptics Haptic renderingis the most important technology for computer haptics which means the process of calculating the force ortactile feedback to give the user a sense of touch or interaction with the virtual object Smooth haptic feedbackis an important task for haptic rendering with complex virtual objects However commonly the update rateof the haptic rendering may drop down during contact in complex scenarios because the high computationalcost is required for physics based dynamic simulation If the haptic rendering is done at a lower update rate it may cause discontinuous or unstable force feedback Therefore to implement smooth and accurate hapticrendering the update rate of force calculation should be kept in a high and constant frequency In the currentmaster thesis we propose a novel real time method based on machine learning to calculate smooth and accuratehaptic feedback in complex scenarios The method consists of two phases data generator module and designingappropriate artificial neural network In the first phase we proposed an automated data generator module whichprovides data required for learning procedures There are three sets of data position of the haptic tool inputdata feedback force resulting from virtual object and the haptic tool interaction output data 1 and deformedshape of virtual object after interaction output data 2 Before going to phase two preprocessing analysis isperformed on the data Three steps were done 1 All data normalize using the Z Score function 2 The inputdata are transformed from Cartesian coordinate to cylindrical coordinate 3 By using Zernike polynomials the dimension of data acquired from deformed shape reduced as it can make the training calculation moreefficient These three steps make the learning procedure easier and faster In the second phase two artificialneural networks are designed in order to estimate the feedback force and deformed shape respectively Thehyperparameters are tuned due to the systems complexity and dimension of inputs and outputs The resultshows that the proposed method can provide smooth and accurate haptic force feedback at a high update rate forcomplex scenarios Moreover it can predict the shape of the deformed object after interaction with reasonableerror KeywordsHaptic Rendering Machine Learning Artificial Neural Network Deformable Objects Zernike Polynomials
استاد راهنما :
سعيد بهبهاني
استاد مشاور :
محمد سيلاني
استاد داور :
محمد دانش، مصطفي غيور