Sharif Digital Repository

In the transportation industry, one of the most important and fundamental problems is the traffic of vehicles in the transportation roads. This problem is especially seen in large and densely populated cities such as Tehran. If traffic control is not done properly, it can lead to problems such as reduced traffic dynamics, environmental pollution, wasted drivers' time, disorder and loss of energy. If the traffic control is done after creating a traffic problem, it will not bring good results and will have low efficiency. For this reason, optimal traffic management and control has been raised as an important issue, especially in large cities. Predicting traffic flow is one of the important and... 

3D reconstruction and tracking of deformable surfaces has received lots of attention in the past decade. This field has been studied from two major aspects: 1) machine vision and 2) computer graphic, and has been used in many applications ranging from industrial design, animation and medical surgeries. One of the most challenging problems in this area is monocular 3D reconstruction, which is an ill-posed problem and involves many ambiguities. Generally, methods which are proposed for monocular 3D reconstruction can be divided into two categories: 1) Template-based methods and 2) Structure from motion methods. Methods of the first category utilize a template model which consists of an image... 

It is of fundamental importance to find algorithms obtaining optimal performance for learning of statistical models in distributed and communication limited systems. In this thesis, we aim at characterizing the best learning strategies over distributed datasets such that the communications between storing machines are minimized. We have addressed two problems in distributed setting: learning of Gaussian processes, and structure learning of Gaussian Graphical Models (GGM). The performance of the proposed methods are analyzed theoritically and verified experimentally. The experimental results show that with spending few bits the proposed distributed methods have close performance to the... 

Inverse reinforcement learning (IRL) is one of the machine learning frameworks based on learning from humans; That is, instead of producing a decision process maximizing a predefined reward function, seeks to find the reward function based on the observed behavior of an agent. The biggest motivation of IRL is that, usually, determining a reward function for a problem is very difficult. We consider IRL in Markov decision processes; that is, the problem of extracting a reward function with the assumption of knowing the optimal behavior. IRL could be useful for apprenticeship learning to obtain skilled behavior, and for optimizing a reward function by a natural system. We first, determine a set... 

Error concealment is one of the effective ways to alleviate the effect of packet loss in video communication over error-prone environments. In order to estimate lost macro-blocks, we have employed Bayesian estimation as an efficient and robust framework. Gaussian process regression has been used as the modeling approach through this framework. Considering luminance component as Gaussian process,a minimum mean squared error estimation of the lost macro-block is obtained. This estimator, as a function of the existing data, is only determined by the covariance matrix defined over them. Therefore,the main step in Gaussian process regression, is construction of the convenient covariance matrix... 

Respiration signal is one of the biological information required to monitor patient respiratory activities. Noninvasive respiratory monitoring is an extensive field of research, which has seen widespread interest for several years. It is well known that the respiratory activity influences electrocardiographic measurements (ECG) in various ways. Therefore, different signal processing techniques have been developed for extracting this respiratory information from the ECG, namely ECG derived respiratory (EDR). Potential advantages of such techniques are their low cost, high convenience and the ability to simultaneously monitor cardiac and respiratory activity. One of the aims of this thesis is... 

Huge availability of data in last decade has raised the opportunity to use data for decision making. The idea of using existing data to achieve more coherent reality solution has led to a branch of optimization called data-driven optimization. Presence of uncertain variables makes it crucial to design robust optimization methods for this area. On the other hand, in many real-world problems, the closed-form of the objective function is not available and a meta-model based framework is necessary. Motivated by this, we are using a Gaussian process in a Bayesian optimization framework to design a method that is consistent with the data in predefined confidence level. The goodness of the... 

The goal of human action recognition systems is to label the sensory observation data, using one of the predefined action verbs in the system. During recent years, human action recognition has received a growing interest due to its application in automatic scene interpretation. For instance, automatic surveillance systems in public places should be able to discriminate normal and suspicious actions. Human-computer-interface (HCI) systems (which have became popular in recent years) mostly need a similar system to recognize the gesture of their users without using any keyboard (or similar input devices). Human action recognition technologies can also boost the video retrieval systems.
An... 

The voice biometric is used in today’s telephone based speaker verification because of its unique feature for remote access. However, there are significant challenges in implementing such systems. One of these challenges is the need for sufficient data in the enrollment phase. In fact, the speaker verification system needs a dataset that covers phonetic variations of the language to be able to discriminate between different speakers. In real applications it’s not easy to ask the speakers to say long utterances. Therefore, an ideal speaker verification system should be able to find imposters without any constraint on the input lexicon whether the utterances are long or short.The results of... 

The use of the Internet of Things in buildings has become increasingly important. Meanwhile, sensors and actuators play a very important role. With the help of sensors, various data of residents' environment and behavior can be obtained and various parameters can be controlled through actuators. Data from the presence, measurement and decision making of the components of this structure in a building can be used to model and predict the behavior of residents with methods of machine learning, data mining and artificial intelligence such as deep learning and Gaussian processes, helping to achieve the goal of residents' comfort and energy saving.In the desired structure, the sensor- actuator...