Sharif Digital Repository

Many Text-to-Speech (TTS) systems, particularly in low-resource environments, struggle to produce natural and intelligible speech from grapheme sequences. One solution to this problem is to use Grapheme-to-Phoneme (G2P) conversion to increase the information in the input sequence and improve the TTS output. However, current G2P systems are not accurate or efficient enough for Persian texts due to the language’s complexity and the lack of short vowels in Persian grapheme sequences. In our study, we aimed to improve resources for the Persian language. To achieve this, we introduced two new G2P training datasets, one manually-labeled and the other machine-generated, containing over five million... 

With the explosion of mobile smart devices, many computation intensive applications have emerged, such as interactive gaming and augmented reality. Mobile edge computing (EC) is put forward, as an extension of cloud computing, to meet the low-latency require- ments of the applications. In mobile edge computing systems, an edge node may have a high load when a large number of mobile devices offload their tasks to it. those offloaded tasks may experience large processing delay or even be dropped when their deadlines expire. Due to the uncertain load dynamics at the edge nodes, it is challenging for each device to determine its offloading decision (i.e., whether to offload or not, and which... 

Using “Searchable Encryption” enables us to encrypt the data, while preserving the possibility of running search queries. One of the most important applications of the mentioned is in Cloud Storage. As users do not trust the Cloud space, they are not inclined to store their data on the Could. The solution to this problem is of course, Cryptography. However, ordinary Cryptography methods, eliminate the data’s searchability. Hence, we need encryption schemes that code the data while retaining their searchability. So far, various schemes has been proposed that differ in their performance, security level, and usage. In this thesis, we aim to discuss and analyze these methods  

In this thesis, the aim is designing an optical temporal imaging system. In recent years, due to many applications, including the receipt of high-rate data by slow receivers and compensation of dispersion in telecommunication systems, researchers have considered the topic of temporal imaging. This field of research is based on dispersion, electro-optical modulators or time lenses and space-time theory. By modeling dispersion properties as a depth dimension and taking ideas from three-dimensional spatial imaging systems we intended to increase the temporal resolution and depth of focus of the structure. We also present a novel technique for multiplexing and demultiplexing telecommunication... 

In the last decades, due to the growing demand of transferring information with high transmission rates, the complexity and development of telecommunication and optical systems is remarkable. Researchers around the world attempt to explore extraordinary potential of light to process information. In the mid-19th century, scientists discovered a mathematical symmetry between the spatial and temporal optics fields, which originated from the similarity of equations governing the paraxial diffraction of beams and the dispersion of narrow-band pulses known as space– time duality in scientific texts. This new approach provides more advanced and potent methods to temporal processing and... 

One of the most vital aspects of understanding the traffic phenomenon is scrutinizing the traffic transition status, such as the transition from free flow to congestion. The Percolation Theory is a renowned theory focusing on analyzing various network types to detect the critical zones, which are the zones including links that are important to control to improve stability. By calculating the quality indices of network links, the Percolation Theory can simulate the traffic percolation propagation in the network and determine possible critical zones for further analysis. Most studies in this field assume access to data of several traffic parameters for the entire transportation network, such... 

In recent years, optical biomedical imaging techniques show great potential in noninvasive imaging. Although these methods have many advantages over other biomedical imaging methods (such as Computerized Tomography (CT), Magnetic Resonance Imaging (MRI) and etc.), these techniques confront with some problems such as optical scattering, light absorption and etc. For in vivo imaging, the short-wavelength infrared region (SWIR; 1,000–2,000 nm) provides several advantages over the visible and near-infrared regions: general lack of auto-fluorescence, low light absorption by blood and tissue, and reduced scattering. In this thesis we want to analyze the traditional IR imaging techniques and... 

Strain imaging is a non-invasive ultrasound modality for assessing cardiac function in echocardiography systems. In this thesis, we implemented a fully automated strain imaging system containing 5 steps: 1) echocardiographic view recognition, 2) cardiac cycle phase detection, i.e., the events of end-diastole (ED) and end-systole (ES), 3) segmentation of left ventricular (LV) myocardium, 4) motion estimation of this wall and 5) strain calculation. In this work, we propose a novel deep learning-based framework for phase detection of cardiac cycle by the use of echocardiographic images in multibeat videos. Further, by applying the augmentation technique, the model has been able to detect events... 

Resolvers, due to their robust structure, are widely used in automation systems. Among the types of resolvers, the accuracy of the Wound Rotor (WR) resolver in the occurrence of common mechanical errors is higher than other types of resolvers. therefore, in this thesis, an AFWRR is studied to improve the performance. Increasing the number of poles in WR resolvers is a good solution for increasing the accuracy of these electromagnetic position sensors. However, high-speed WR resolvers due to employing fractional slot windings suffer from rich sub-harmonics in the induced voltages. A common solution for suppressing the undesirable sub-harmonics is using multi-layer winding with appropriate... 

The Coronary artery bypass grafting surgery is one of the most complicated and invasive surgeries, in which the chest is cleaved up to 20 cm. Also, heart motion with 1-2Hz frequency bothers surgeons to perform on. This leads surgeons to get interested in minimally invasive robotic surgery methods. The idea is to synchronize the robot motion with heart, in order for surgeons to perceive it stationary. This needs 3 major stages: online taking of data, estimate the future heart motion, and control the robot. First studies employ visual seroving for control demand. Later studies, although differ in data collection methods, rely on classic error-based feedback controllers, such as PID. Fast... 

Using visual information of an environment is the immediate way of detecting and identifying an unknown environment. These information maybe obtained using straight visibility detecting sensors. One of the formal models of these visual information is the visibility graph which have a vertex for each vertex (corner point) of the environment and two vertices have an edge whenever their corresponding corners see each other. Then, the problem is to characterize such a graph and reconstruct the target environment with equivalent visibility graph. Despite existence of plenty of research results, these are open problems in computational geometry and rigid results exist only for limited special... 

Housing is among the most primary fundamental needs of the household ,which consumes a high Proportion of the household expenditure and therefore it remains An important topic in macro economical analysis. Estimating and determining housing prices in different urban , areas is also important for planning .Estimations are also use in many decision making and process for the urban , regional , public, privet and organizational policy making. Due to the heterogeneity housing prices and the fact that it’s prices are affected by it’s characteristics , in this research housing prices of a few regions in tehran metropoly are assessed by the hedonic price model using macro and micro...