Sharif Digital Repository

This thesis examines the differences and the similarities between the two famous RNN blocks the Long Short Term Memory and the Gated Recurrent Unit. It measure different aspects such as computational complexity, Word Error Rate, and subjective human evaluation in the task of text generation.In the computational complexity experiment results show that the LSTM takes more time to compute, in comparison to the GRU. Moving on into the next experiment the GRU slightly outperforms the LSTM in terms of WER but the perplexity for the language models tested was the same. This shows that slight differences in the perplexity does not drastically change the WER. Having said, the results suggest that the... 

Obtaining high profit is the ultimate goal of an investor in the financial market. The key to achieve high profits in stock trading is to find the right time to trade with minimum business risk. However, it is difficult, often, to make decision about the best time to buy or sell some stocks due to the extremely dynamic and volatile behavior of the stock market. In order to resolve these problems, two steps have been followed in this research:1) Create a model to predict the final price of the stock with small error rate, and 2) Suggest the best stocks for trading to the trader. In order to achieve the goals of the first step, the stock price data of Hcltech, Maruti, Axisbank is selected and... 

Neural Networks have been applied to Language Modeling to solve a major problem that N-gram language models could not overcome: discreteness of the words. Generally, neural networks were successful in solving this problem and improved Language Modeling by reducing the perplexity of the models. Neural networks can find grammatical and semantic connections among the words using word embedding which maps each word to a low dimensional feature vector of real numbers. In this research, different kinds of neural network applied to Language Modeling has been reviewed. Also, it has been tried to reduce the perplexity of Persian language models on a 100-million scale data set using a single-layer... 

One of the most important problems in the field of robotic surgery is the measurement of the laparoscopic instrument Tip force. Many efforts have been made with the use of distal sensors to issues such as high cost and need to be disinfected, but the use of proximal sensors for estimating the Tip force of the tool is very rare, which can improve distal sensor problems.In this project, first, using data obtained from simulating a set-up for the Sina robot, two static MLP, and dynamic NARX neural networks are trained to evaluate the use of machine learning algorithms to determine whether the Tip force neural network can be used. Did the robot estimate Sina's surgeon? Then, by comparing this... 

Artificial neural networks are mathematical models inspired by the nervous system and brain. The types and applications of these networks are very widespread nowadays, and it seems that they can be used to track the signals well and estimate the data of the next. In this research, we try to present a model that can predict the future of the trend of noisy signals that have unpredictable behavior, or in other words, chaotic signals. Such research is also widely used in the medical sciences, including the diagnosis of epileptic seizures or heart attacks. In this research, a study with high volatility financial data has been done as an example on this issue and the proposed model tries to be... 

Hand pose estimation is something that has applications in many fields, including augmented and virtual reality systems, as well as mixed reality. Hand gesture recognition and classification applications including sign language recognition and non-handheld senarios (such as storefront contactless Survey systems) that have found special cases in the Qovid-19 pandemic period Shows the highest hand pose estimation importance. In our work, we target 2D and 3D estimation at the same time and also use RGB camera as a sensor to record input data. It becomes more economical to achieve Compared with using RGBD or depth sensors . There is only one RGB image in our input. Also there is no contract to... 

In Iranian Sign Language (ISL), alongside the movement of fingers, the movement of the lips is also essential for to perform words completely and correctly. The purpose of current study is to provide an automated lip-reading system using deep neural networks and implement it on Rasa social robot; So that the robot can recognize a limited number of specified Persian words. To do this, we propose an automated lip-reading system based on convolutional neural networks and long short-term memories. Convolutional neural networks in extracting features from images and long short-term memories in modeling temporal dynamics have achieved good results. We have also recorded a database in Persian... 

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... 

Predicting the evolution of viruses is vital in controlling, preventing, and treating diseases. Mutations that evade the host immune system can propagate and persist through generations, making it crucial to anticipate and combat them effectively. The 1918 H1N1 pandemic serves as an example of the devastating impact of pandemics caused by viral mutations. By predicting mutations in advance, we can identify potential future pandemics and take effective preventative measures to mitigate their impact. Proteins play a vital role in the functioning of viruses. They are involved in various processes, such as replication, transcription, and host cell invasion. Any changes in the protein sequence... 

Cryptocurrencies are not only regarded as a trustworthy method of financial transaction validated by a decentralized cryptographic system as opposed to a centralized authority, but also as one of the most popular and lucrative forms of trade and investing. Predicting the price of a cryptocurrency is a challenging topic in time-series research. Its intricacy is due to the volatility and large swings of cryptocurrencies' price. The emergence of brand-new cryptocurrencies, which might present a profitable trading opportunity but lack sufficient historical data for technical analysis, prompted us to develop a trading strategy that could be applied universally. The forecast of the next timestep's... 

This thesis proposes an energy management model for a residential prosumer building which is a multi-carrier energy hub in a grid-connected mode. Power may be bought and sold between the building energy system and the power grid. Solar panels and solar water heaters are integrated into the building's energy system to create electricity and heat, which may be used in a variety of ways: used immediately to meet the home's demands, stored in batteries and heat banks for later use, or sold back to the power grid to earn income. The energy dispatch is managed such that the overall energy consumption cost is minimized, considering the variation in electricity price (grid tariff), renewable energy... 

Creating talking heads from audio input is interesting from both scientific and practical viewpoints, e.g. constructing virtual computer generated characters, aiding hearing-impaired people, live dubbing of videos with translated audio, etc. Due to its wide variety of applications, audio to video has been the focus of intensive research in recent years. Mapping audio to facial images with accurate lip-sync is an extremely difficult task because it is a mapping form 2-Dimensional to 3-Dimensional space and also because humans are expert at detecting any out-of-sync lip movements with respect to an audio.Approaches to automatically generating natural looking speech animation usually involve... 

Identity verification is a key part of identity reidentification process. Nowadays, Identity reidentification using face-based algorithms are popular in learning and vision area due to their generality and accessibility of this body organ. Using a fake image, occlusions on face and appearance changes like makeup can cause distortion in face verification systems which can be a drop in function of such systems. Most of these face verification models like DeepFace, FaceNet, ArcFace and SphereFace use convolution networks as their major architecture. These models, in addition to their large storage consuming and high computational complexity, due to using face as their major feature, are not...