Sharif Digital Repository

The performance of visible light communication (VLC), as a key technology for next-generation wireless communication networks, 6G, can be significantly enhanced through the integration of metasurface-based optical reconfigurable intelligent surfaces (RIS). This research work introduces a novel channel model for a VLC system incorporating RIS-equipped transmitters, where the transparent optical RIS is directly integrated with the array of LEDs in VLC transmitter, enabling beam-steering. To harness the beam-steering capabilities of the modeled RIS-equipped transmitter, a traffic-aware resource allocation scheme is proposed and efficiently solved using a tailored fractional programming... 

Cardiovascular diseases are the leading cause of death globally so early diagnosis of them is important. Many researchers focused on this field. First signs of cardiac diseases appear in the electrocardiogram signal. This signal represents the electrical activity of the heart so it’s primarily used for the detection and classification of cardiac arrhythmias. Permanent monitoring of this signal is not possible for specialists so we should do this by means of Artificial Intelligence. In this thesis, we use recurrent neural networks to classify electrocardiogram’s arrhythmias. This deep learning method, use two sources of data to learn from. The first part of data is global for everyone and the... 

Among different natural disasters, earthquake has always been known as one of the most effective ones on human lives, and this is only because we still cannot predict the exact time and place of its happening. So, giving special attention to the methods which can omit or minimize the damages of this natural event is needed for controlling the loss in the event of an earthquake. On the other hand schools are known as places which are full of people from younger ages for at least half of each day, and they are considered to be not well educated about how to react in an earthquake in comparison to older people and also considered vulnerable at the time of this natural event. According to what... 

Nowadays, Multi-Object Tracking (MOT) plays a crucial role in various computer vision applications such as autonomous vehicles, surveillance, and robotics. Traditional MOT methods often struggle with challenges such as high errors when dealing with complex scenarios involving occlusion, scale variations, and object interactions. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNNs) and Transformer models, have demonstrated significant capabilities in addressing these challenges. This thesis presents a study on the use of deep learning techniques, specifically CNNs and Transformer models, for solving the problem of Multi-Object Tracking. It begins by... 

Procedural Content Generation (PCG) is a critical challenge in video game design, aimed at automating the creation of complex maps and levels. This thesis presents a novel deep learning-based approach for PCG that integrates transformer architectures with reinforcement learning techniques. Building on previous works, this research seeks to enhance the quality, diversity, and success rate of generated playable levels. The proposed method utilizes transformer architectures to model sequences of actions, states, and rewards, predicting optimal game content based on past trajectories. Offline datasets, generated by semi-expert agents trained in the PCGRL framework, serve as the foundation for... 

The increasing trend of Green House gases’ emission, after the Industrial Revolution, has changed the balance of these gases in the atmosphere. Aggregation of these gases in the atmosphere has caused the temperature increase at the Earth’s surface. This temperature increase has altered the stationary trend of climatic variables. This change has been entitled, Climate Change. One of the important impacts and challenges of Climate Change is Sea Level Fluctuation, which has so many factors. Due the last researches, changes in Land Water Storage are one of the probable factors that change the sea level. Land water storage consists of all of the waters in lakes, ponds, ground waters, snow and... 

In many neuroscience studies, the aim is to investigate the functional role of a population of neurons in response to a certain stimulus. Electrophysiology methods usually can only record from a small population of neurons and this is not sufficient for studying functional properties of the cortex. An alternative is to use functional neuroimaging methods. However, some of these methods are expensive and also they do not offer suitable spatial and temporal resolutions. Optical imaging systems can solve these problems because they are low-cost, easy to design, and also have good temporal and spatial resolutions. These systems can generate functional maps from the brain. In this study, a... 

Data envelopment Analysis is a non parametric technique which estimates the efficiency of a decision making unit in compare with others. In correspondent literature this unit’s Inputs and outputs are often assumed to be deterministic, but in recent years different approaches which viewing the data as non deterministic are presented. In this study we propose an algorithm for determining the stability region of a DMU while we assume other DMUs’ data are fixed. This algorithm is based on changing the reference set of the under investigation DMU. In fact applying these changes make the DMU move toward other DMUs’ efficient frontiers and by using this fact it is possible to determine the... 

The objective of OCR systems is to retrieve machine-encoded text from a raster image. Despite the abundance of powerful OCR algorithms for English, there are not many for Farsi. Our proposed algorithm is comprised of pre-processing, line detection, sub-word detection and segmentation, feature extraction and classification. Furthermore, hardware implementation and acceleration of this system on a GPGPU is presented. This algorithm was tested on 5 fonts including Titr, Lotus,Yekan, Koodak and Nazanin and an average accuracy above 90% was achieved  

Spiking Neural Networks(SNN) are networks which are consisted of layers of neurons, like other typical artificial neural networks. The main difference between SNN and other neural networks is the type of data transportation among neurons which is done by spikes. Spiking neural networks and their models are considered as the nearest networks and neurons to animals’ nervous systems. In aspects of hardware implementation, the type of data transportation in SNN causes them to be ultra-low power. So, implementation of these networks on chips like FPGA and also usage of SNN in applications with high processing load have startling germination, recently. In this work, we have tried to propose some... 

There have been many works on generative networks and image generation in the past few years, but the problem with this work is that there is no control over the generated images. The goal of disentangled image synthesis is to generate new images with specific detail and have control over the generated images. Image-based virtual try-on aims to synthesize the customer image with an in-shop clothes image to acquire seamless and natural try-on results, which have attracted increasing attention. The main procedures of image-based virtual try-on usually consist of clothes image generation and try-on image synthesis. In contrast, prior arts cannot guarantee satisfying clothes results when facing... 

Many mobile applications running on smartphones, wearable devices, tiny autonomous robots and IoT devices would potentially benefit from the accuracy and scalability of deep CNN-based machine learning algorithms. However,performance and energy consumption limitations make the execution of such computationally intensive algorithms on embedded mobile devices prohibitive.We present a GPU-accelerated engine, dubbed mCNN, for execution of trained deep CNNs on mobile platforms. The proposed solution takes the trained model as input and automatically optimizes its parallel implementation on the target mobile platform for efficient use of hardware resources such as mobile GPU threads and SIMD units.... 

Many chip manufacturers have recently introduced high-performance deep-learning hardware accelerators. In modern GPUs, programmable tensor cores accelerate the heavy operations involved in deep neural networks. This paper presents a novel solution to re-purpose tensor cores in modern GPUs for high-throughput implementation of turbo decoders. Turbo codes closely approach Shannon’s limit on channel capacity, and are widely used in many state-of-the-art wireless systems including satellite communications and mobile communications. Experimental evaluations show that the proposed solution achieves about 1.2 Gbps throughput, which is higher compared to previous GPU-accelerated solutions  

In the current era, artificial intelligence and machine learning have become vital and widely used technologies across various industries. These technologies enable companies and organizations to optimize processes, predict trends, and uncover hidden patterns in data with high accuracy and speed. However, fully leveraging the capabilities of AI and ML requires the effective and efficient deployment of ML models in production environments. MLOps, a combination of DevOps and ML concepts, aids in managing the lifecycle of ML models from development to deployment and maintenance. In this research, due to international sanctions and limited access to external services such as Google Vertex AI,... 

In this project, a method is emoloyed to implement a Viterbi decoder on GPGPU. This method is based on combining all steps of the algorithm. This combination has some challenges that are related to differences between different steps of the algorithm. So in this project, some solutions are found to handle these challenges and a high-throughput Viterbi decoder is acheived