Sharif Digital Repository

Graph signals are sets of values residing on sets of nodes that are connected via edges. Graph Neural Networks (GNNs) are a type of machine learning model for working with graph-structured data, such as graph signals. GNNs have applications in graph classification, node classification, and link prediction. They can be thought of as learnable filters. In this thesis, our focus is on graph filters and enhancing the performance of GNNs. In the first part, we aim to reduce computational costs in graph signal processing, particularly in graph filters. We explore methods to transform signals to the frequency domain with lower computational cost. In the latter part, we examine regulations in... 

In recent years, the national health systems have supported the idea of home-based rehabilitation, since receiving cares at hospital environments is too expensive both in money and time. This method reduces the patients’ commuting to the clinics. Moreover, it enables them to practice the prescribed movements at any time.Most of the existing systems compute the patient’s motion performance in a zero-one manner which does not distinguish any small progress in his condition. Thus, a non-task based method which can assess precisely the patient’s level is yet missing. This project aims to develop a set of motion performance indices which can judge the upper limb motions in a home-based... 

This thesis proposes a novel method for enhancing the speech signal based on compressed sensing. Compressed sensing, as a new rapidly growing research field, promises to effectively recover a sparse signal at the rate of below Nyquist rate. This revolutionary technology strongly relies on the sparsity of the signal and incoherency between sensing basis and representation basis. Exact recovery of a sparse signal will be occurred in a situation that the signal of interest sensed randomly and the measurements are also taken based on sparsity level and log factor of the signal dimension.
In this research, compressed sensing method is proposed to reconstruct speech signal and for noise... 

Pulsed packed columns are among the most important devices used in liquid-liquid extraction, with wide application in petroleum and petrochemical industries, metal salt extraction, pharmaceutical industries, metallurgy, and other areas. Liquid-membrane technology is an alternative separation technique to the liquid-liquid extraction for the extraction and recovery of metal ions from aqueous solutions. There are three main types of liquid membranes: emulsion liquid membrane (ELM), Bulk Liquid Membrane (BLM), and Supported Liquid Membrane (SLM). Liquid emulsion membrane is one of the pertraction methods with phase dispersion. It is a three-phase dispersion system, consisting: external phase,...