Sharif Digital Repository

Despite recent advancements in deep learning methods, these methods rely on a huge amount of training data to work. Recently the problem of solving classification and recently semantic segmentation problems with a few training data have gained attention to tackle this issue. In this research, we propose a meta-learning method by combining optimization-based and prototypical approaches in which a small portion of parameters are optimized with task-specific initialization. In addition to this and designing other parts of the method, we propose a new approach to use query data as an unlabeled sample to enhance task-specific learning. Alongside the mentioned method, we propose an approach to use... 

Recent developments of internet technology and digital media have led to the rapid growth of the steganography systems. Steganography is the art and science of concealing a secret message in a cover without leaving a perceptible or detectable trace of the message. Therefore, steganography methods, capable of embedding the largest possible amount of data with least distortion to the cover media, are highly demanding. The LSB steganography is a primary and simple method with high embedding capacity, where higher robustness is achieved if it is applied to the cover signal in the transform domain. However, regardless of the embedding domain, an essential robustness issue with the LSB... 

Advance in VLSI integration level has realized multi-core system-on-chip. For inter-IP communication on-chip network is proposed as a substitute for simple interconnects such as bus fabrics and expensive point-to-point links. Although onchip networks have some superiorities over simple interconnects, but they need more of real estate resource. Although buses are not scalable, they are still popular for their simple communication mechanism. There are so many proposed mechanisms to make buses more scalable and more popular. Most of them try to change bus structure by segmenting and using reconfigurable methods. In this thesis, we explore buses delay by considering the number of component in a... 

Sensor networks is a set of sensors (nodes) which are communicating with each other, and gather information from different environments, and process them to give us valuable results. Sensors have a small energy source like a small battery which have to be used efficiently. Congestion detection and avoidance, together are of great importance in Wireless Sensor Networks (WSNs) in case of traffic load, data loss, and power consumption. In this work, we propose a new APS layer (application support sub-layer), which is another key standard component of Application layer, offering a well-defined interface and several control services. It functions as a bridge between the network layer and other... 

SAR image noise is a significant problem for SAR image analysis.The inherent noise of SAR images, known as speckle, seriously affects the SAR image interpretation. It also has adverse effects on the classification and segmentation of SAR images. Due to its great significance, the SAR image processing has received considerable attention in recent years and many researchers have developed techniques to reduce the inherent noise accompanying the SAR images. A survey of the literature shows that the wavelet analysis is one of the most common methods used for speckle reduction. While the power of the morphological analysis method has mostly not been recognized, we have utilized this efficient... 

The Revenue management concept has been studied and noticed by researchers for more than forty years. Although the applications of revenue management grow in different industries continuously, airline industry which is the origin of this research area is the pioneer of developing and representing new models. In the last few years, there has been a trend to enrich traditional revenue management models. In this thesis we first, reviewed most aspects of revenue management studies especially in airline industry, then choice-based customer behavior concept is introduced. Also a case sample study in customer choice behavior has been developed with time scale considering and remodeled. According to... 

Underground reservoirs are highly complicated due to the presence of spatial heterogeneities at length scales that span from micrometer in pore structure of the rocks to kilometer in the reservoir models. While large-scale flow units need to be characterized using seismic and well data, detailed displacements of fluids in pore space need to be modeled using thin section analysis and pore network modeling. It is therefore necessary to adopt a multi-scale approach to reservoir description to make best use of all the available data that vary over several orders of magnitude, from micro-scale in pore structure to field scale in reservoir flow models. In this thesis, an integrated framework for... 

One of the most applicable fields in data mining is customer relationship management (CRM). CRM process includes four aspects: Customer identification, Customer attraction, Customer retention, and Customer development. Data mining can be a supportive tool for decision making in each of these CRM aspects. Huge volume of data and information corresponding to CRM that exists in companies' databases, has made sufficient potential for data mining process and discovering hidden knowledge. Importance of concepts like customer needs identification, customer retention, and increasing customer value for companies has made the need to use of data mining techniques more valuable. Saipa Yadak Co., as a... 

Semantic segmentation is the tash of labeling each pixel of an input image. It is one of the main problems in computer vision and plays an important role in scene understanding. State of the art methods of solving it are based on Convolutional Neural Networhs (CNNs). While many real world tasks like autodriving cars and robot navigation require fast and lightweight models, CNNs inherently tend to give beter accuracy when they are deeper and bigger, and this has raised interest in designing compact networks. Knowledge distillation is one of the popular methods of training compact networhs and helps to transfer a big and powerful network’s knowledge to a small and compact one. In this research... 

In recent years, the tourism industry has become one of the most influential industries in the income generation of countries and has attracted the attention of researchers. Identifying the important features of the hotel from the users' point of view is one of the areas that have been considered, while the segmentation of hotel customers based on the extracted features has been less in the focus of researchers and the need for more research in this field has been felt by experts.Given that the desire to return to the hotel by travelers has always been one of the factors affecting the financial performance of hotels, the factors affecting it are of great importance. It can be very valuable... 

Machine translation has been an important subject in the field of natural language processing (NLP). In recent years, because of providing essential linguistic data resources, statistical approached have been deployed in machine translation. Although there have been several attempt to create English to Persian automatic translator, there has not been sufficient effort in the reverse direction. In this project, we reviewed previous works in machine translator for Persian and implemented a statistical machine translator from Persian to English. We needed a bilingual corpus for building the translator. For this purpose, we used a corpus of Phd and MSc abstracts in Persian and their translation... 

The aim of this thesis is to investigate recent methods for Image Processing(Any signal process which it’s input is an image and it’s ouput is an image or a set of Image parameters) using Calculus of variation tools. Methods which are to be investigated has been divided into two well known parts of Image Processing : Image Restoration and Image Segmentation.Image Processing Chapter includes two sections: one calculus of variations methods(energy method), other methods based on PDEs(heat equation and Malik-Perona equation). In studing each of this methods, It has been tried to include experimental results and negative and positive points of them.In Image Segmentation Chapter, first... 

In image processing applications, sensors (Camera, LiDAR and Stereo) are essential for scene perception and Deep learning methods outperform most of the image processing tasks like 3D and 2D object detection and semantic segmentation. Different sensors are used in image processing tasks. Sensor fusion is using multiple sensors data to get better performance. Each sensor captures different data (e.g, color, texture, and depth). Some of them are distorted in inclement weather, intense illuminance changes, and dark environments which multi-sensor data fusion is used to overcome sensor weaknesses. One of the most important fields that sensor fusion used is Auto Driving cars (AD). Different... 

Image segmentation has a huge amount of applications in machine vision, target detection, medical image processing, etc. In many medical researches such as Organ and Gland Volume Specification, Analysis of Anatomical Structures and Multimodal Image Registration, Organ
Segmentation is the first step of preprocessing.Since detection of diseases out of medical images depends on organ segmentation results,the segmentation process is done by experts which has a lot of disadvantages such as high time computation, high cost, etc. Hence, designing algorithms that can segment images with high accuracy and need minimum user interaction are desirable. So, in this thesis, a new
knowledge based... 

Image segmentation is middle and an important task in image analysis and machine vision applications. The output images of imaging systems are often fuzzy because of noise, limitation in spatial and temporal resolution, blurring and intensity inhomogeneity in the objects. The goal of this thesis is exploring the fuzzy methods in multispectral image segmentation and proposing a new one to solve some of the recent difficulties and problems. The difficulties and problems such as simultaneous utilization of spatial and spectral information, necessity for dimension reduction, spatial and spectral and intra-cluster image information redundancy, existence of regions with widely varying size,... 

Image segmentation in medical imaging, as one of the most important branches of medical image analysis, often faces the challenge of limited labeled data for application in deep learning methods. The high cost of data collection and the need for expertise in image segmentation, particularly in three-dimensional images such as MRI and CT or sequence images like CMR, have all contributed to this problem, even for popular networks like U-Net, which struggle to achieve high accuracy. As a result, research efforts have focused on semi-supervised learning approaches, weakly supervised learning, as well as multi-instance learning in medical image segmentation. Unfortunately, each of these methods... 

Environment Identification and recognizing surrounding objects is an exigent need in future applications. For example one of the emerging technologies in car industry is driverless cars. In driverless cars, navigation system should be able to detect and recognize pedestrians, traffic signs, roads, surrounding cars and so on. Therefore, conventional single-object recognition systems are not capable of handling the needs of advanced machine vision based applications. In recent years, designing and analyzing multi-class object detection and recognition systems have become a big challenge in machine vision. In this thesis our goal is to identify and analyze the existing problems in designing... 

When a crack is subjected to a compression field, it will close and its edges will get into contact with each other. Depending on the direction and magnitude of the loads and also the coefficient of friction, ‘stick’ or ‘slip’ situationsbetween the edges will occur. This type of crack is known as ‘frictional crack.’ In this project, first these cracks are studied analytically and the order of singularity is derived using asymptotic analysis and also the analytical fields are determined for both ‘isotropic’ and ‘orthotropic’ materials. Then, numerical simulations are carried out using extended finite element method which is considered as the most powerful means for analyzing the problems... 

Modelling passengers’ itinerary choice behaviour is valuable to understand the increasingly competitive airline market and predicting air travel demand. Research in the choice behaviour of air travellers has evolved to include an analytical focus on variation in the sensitivities of travellers to factors influencing itinerary choice. That is, some choice studies have moved beyond a focus on assumed representative, mean-level sensitivities toward a goal of representing the distribution of preferences across a sample. An important issue that remains is whether the insight gained in previous studies, which focussed on preferences in mature markets with relatively high per-capita rates of air...