Sharif Digital Repository

Underwater robots are capable of performing a wide range of underwater operations such as research, sampling, hydrography, rescue, and more. These robots are generally categorized into two main types: remotely operated vehicles (ROVs) and autonomous underwater vehicles (AUVs). AUVs offer significant advantages due to their lack of reliance on human operators, including extended operational range, longer operational duration, and reduced human risk. In the design process of any underwater robot, a specific dynamic model is developed based on the robot’s geometric features and the specifications of its appendages, including control surfaces, thrusters, and buoyancy tanks. This involves... 

The ever increasing usage of modified binders in road construction requires that the effect of different modifiers on the performance characteristics of the asphalt binder be determined through laboratory testing. The current Superpave protocol for performance grading asphalt binders has proven to be insufficient to properly characterize modified binders, thus researchers have searched for other testing methods to complement or possibly replace some of the Superpave tests. Most notable are the time sweep test for fatigue resistance, the multiple stress creep and recovery test (MSCR) for rutting resistance and the direct tension test (DTT) for low temperature cracking characteristics. In the... 

In recent years, there has been a growing interest in using intelligent methods in healthcare systems, particularly for predicting the probability of various diseases occurring. According to official statistics from the World Health Organization, heart disease is one of the leading causes of mortality worldwide. Therefore, predicting heart disease using machine learning methods, as a decision-support tool for physicians, can significantly aid healthcare systems in the prevention, diagnosis, and treatment of these conditions. This study utilizes machine learning techniques to classify and predict the occurrence of heart disease in individuals visiting medical centers. The objective is to... 

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,... 

The deleterious effect of moisture on the structural integrity of asphalt mixtures has been recognized as one of the main causes of early deterioration of asphalt pavements. This phenomenon, usually referred to as moisture damage, is defined as the progressive loss of structural integrity of the mixture. Moisture damage is associated with the development of different physical, mechanical and chemical processes occurring within the microstructure of the mixture at different intensities and rates. Although there have been important advancements in identifying and characterizing this phenomenon, there is still a lack of understanding of the damage mechanisms occurring at the... 

Warm mix asphalt has received considerable attention over the past decade particularly due to its potential environmental benefit such as lower energy consumption and emission, its ability to be placed at lower ambient temperatures making it a suitable material for areas with short construction season. There are three warm mix asphalt (WMA) techniques are available; organic additive, foaming, and chemical additive. This study examined Sasobit, a micro crystalline wax which is an organic additive. The concentrations tested were 1.5, 2.5 and 3.5 percent of the base binder. A PG 64-22 asphalt binder from an Iranian refinery (Tehran refinery) was used as the base binder. Superpave binder... 

Bitumen ageing is one of the principal factors causing the deterioration of asphalt pavements. Ageing is a complex process that is affected by different parameters.With the rapid growth of modified binders in road paving applications over the past twodecades, it is important to study the ageing properties of these binders. A number of laboratory methods are used tosimulatethe bitumenageing at various stages of the production and service of hot mix asphalt.Recent studies have shown that Superpave testing protocol does not fully address the ageing of modified binders. To study the ageing properties of modified binders, three different types of binder modifiers, plastomer, elastomer, and ground... 

With a surge in consumption of modified binders in recent years, different methods have been used to evaluate the properties of modified binders with relative success. None of these methods are able to fulfill all the requirements for evaluation and intrerpretation of the physical, chemical and rheologocal properties of modified binders. Since rheological master curves can present a mechanical interpretation of the binders in a wide range of times and temperatures, in conjunction with other evaluation metheods, they are considered a promising means of evaluating the suitability of modified bindrers. The available master curve models do not possess the sufficient diversity for this purpose.... 

In this study performance of tack coat (thin layer bonding asphalt concrete layers) was evaluated. The shear strength of tack coat layer was considered as its measure of performance. Direct shear tests were conducted on two layered HMA specimens. The test variables included the type of tack coat material, application rate (amount of residual bitumen per unit area), substrate condition, normal stress and shear loading rate. Four types of liquid asphalt (CSS, CRS, modified CRS and MC-250) were applied as tack coat. Three substrates conditions were used in the tests. These were 3-days old, 17-days old and long term aged substrates were used. It was found that optimum application rate depends... 

Pavement preventive maintenance methods such as slurry seals are cost-effective treatments that enhance pavement longevity. Incorporation of recycled materials such as reclaimed asphalt pavement (RAP) into asphalt pavements helps further reduce costs and energy consumption. Because the use of emulsions and pavement preventive methods is uncommon in Iran, there is little experience with the technology in this area. The present study designed and developed slurry seal and emulsion test devices at Sharif University lab to study the feasibility of incorporation of RAP into slurry seal mixtures while respecting the limits specified by the ISSA and ASTM. Two slurry seal mixtures in which cement... 

This investigative study intends to identify and characterize bitumen from seven Iranian bitumen production plants according to the Superpave Performance Grading (PG) system, conventional classic tests, and chemical separation tests. The study then compares the identified performance grades with the thirteen performance-grade binders required for specific climatic zones in Iran. It is observed that the variety of available binders is not adequate to fully cover the required PGs. Blending was initially considered as a suitable and economic method for production of the missing performance grades. However due to similar rheological properties of bitumen samples, resulting in nearly identical...