Sharif Digital Repository

In this research, we introduce a semi-supervised manifold regularization framework for hu- man pose estimation. Here we aim the three major challenges in discriminative human pose estimation. We utilize the unlabeled data to reduce the need to labeled data and compen- sate for the complexities in the input space. We model the underlying manifold by a nearest neighbor graph. Due to depth ambiguity which is the main challenge in this problem, the true underlying manifold of the data bends and gets too close to itself is some areas which results in poor graph construction. To solve this problem, we argue that the optimal graph is a subgraph of the k-nearest neighbor graph and employ an... 

Mobile Ad hoc networks or MANETs consist of autonomous selfish nodes, which usually have a limited source of energy and choose their own transmission power independently. Nodes are mobile; hence the network topology changes continuously in time, therefore a topology control protocol is required to preserve the network connectivity and to adjust the transmission range of the nodes. Also in the absence of any infrastructure in the network, since the energy source of each node is limited and nodes are not eager to consume it for others, in order to stimulate the selfish nodes to cooperate to provide network services (such as relaying data packets) , we need to exert an incentive mechanism in... 

Communication among people over the emerging networks has been the focus of attention in different branches of science during last decades. Online Social Networks (OSNs), with more than hundreds of millions of users are powerful means for directing information within and across societies. Thus, studying various aspects of OSNs is an important issue for researchers. Due to large number of users and friendship relationships among them, gathering complete information from an OSN is not feasible. On the other hand, hiding users information and crawlers limitations are challenges for gathering complete data. A Common solution for this problem is Sampling from OSNs. Sampling from OSNs (and... 

In this thesis, we have discussed image classification by sparse representation. Sparse representation is used in two different ways for image classification. The first goal of sparse representation is to make an efficient classifier, that can learn the subspace, in which the data lies. In this field we have surveyed various methods. We also proposed a method, called ”Locality Preserving Dictionary Learning” that works approximately better than state of the art similar methods, specially when training data is limited. We have reported the result of lassification on four datasets including MNIST, USPS, COIL2 and ISOLET. Another use of sparse representation, is to extract local features from... 

Compressive Sensing (CS) is a new paradigm in signal processing and information theory, which proposes to sample and compress sparse signals simultaneously and has drawn much attention in recent years. Many signals in lots of applications have a sparse representation in some bases, so CS is used as an efficient way of data compression in many applications such as image processing and medical applications in the last couple of years. Since some of the distributed information in complex networks are compressible too, CS can be used in order to gather the distribted information on the nodes or links efficiently. Traffic analysis and performance monitoring in computer networks, topology... 

Image retrieval, simply put, is the process of finding images in a predefined set , that are similar to an image specified by the user. In particular, the user inputs an image as query, and expects to see images similar to the query. Our purpose is to retrieve the images, by means of visual features, without any use of latent information such as tags and annotations.Afer the first round of retrieval, the answers can become more accurate, by means of user feedbacks. In this state, using active learning methods may be usefull. By using active data selection, we hope to achieve the answer faster. Learning based on manifold assumption, is another means which may be used in image retrieval.... 

Many real-world communication systems such as Internet, online social networks, and brain networks can be modeled as a complex network of interacting dynamical nodes. These networks have non-trivial topological features, i.e., features that do not occur in simple networks such as lattices or random networks. The tremendous growth of Internet and its applications in recent years has resulted in creation of large-scale complex networks involving tens or hundreds of millions of nodes and links. Thus, it may be impossible or costly to obtain a complete picture of these large networks, and sampling methods are essential for practical estimation of network properties. Therefore, in this thesis, we... 

Visual tracking is a classic problem, but is continuously an active area of research, in computer vision. Given a bounding box defining the object of interest (target) in the first frame of a video sequence, the goal of a general tracker is to determine the ob-ject’s bounding box in subsequent frames. Utilizing sparse representation, we propose a robust tracking algorithm to handle challenges such as illumination variation, pose change, and occlusion. Object appearance is modeled using a dictionary composed of target patch images contained in previous frames. In each frame, the target is found from a set of candidates via a likelihood measure that is proportional to the sum of the... 

The emergence of applications such as spam detection and online advertising coupled with the dramatic growth of user-generated content has attracted more and more attention to stream classification. The data stream in such applications is large or even unbounded; moreover, the system is often required to respond in an online manner. Furthermore, one of the main challenges of stream classification is that often the process that generates the data is non-stationary. This phenomenon, known as concept drift, poses different challenges to the classification problem.Therefore, an adaptive approach is required that can manage concept drift in an online fashion. This thesis presents a probabilistic... 

Nowadays, Online Social Networks (OSNs) play an important role in the exchange of information among people. Some previous studies indicate that diffusion behavior and network structure are tightly related. Community structure is one of the most important features of OSNs. Access to the whole network topology is the necessary and prevalent requirement for most of community detection methods, so the limited access to full or partial topology can decrease their accuracy. Using traceable information over diffusion network is a solution to surmount this difficulty. In this work, we are concerned with the community detection by only using the diffusion information, while unlike the previous... 

Object tracking is an important tool for video analysis which has been applied to public surveillance, road safety, and scene analysis. In multiobject tracking, the goal is to extract the trajectory of every target using spacial and temporal information. Since new objects can enter the tracking area, an object detector is required to detect their presence. This detector locates target objects in all frames and its (noisy) output is delivered to an associator that returns each object’s trajectory. The associator uses the motion and appearance model of the objects to discover their relation and find the trajectories. In this thesis, each target is partitioned into a number of non-overlapping... 

Over the past few years, various studies have demonstrated that the complex networks can be used to model the structure and functions of human brain. Some of these studies indi- cated that diseases such as Alzheimer, Epilepsy, and Schizophrenia can cause changes in this network. The main idea behind the methods proposed to analyze human brain’s behav- ior, is to identify regions of the brain with specific tasks. Recent studies show that multiple regions of human brain are involved in complex activities, so it’s important to detect their interactions. Using functional high resolution multichannel neurophysiological signals, like electroencephalographic (EEG) and magnetoencephalographic... 

Hyperspectral imaging is one of the remote sensing methods that has been widely applied in different applications. A hyperspectral image is composed of a set of pixels showing the spectral signatures in different frequency bands recorded by sensor cells. The process that detects the proportion of pure elements in the combination of pixels is called hyperspectral unmixing. Noisy and incomplete data, high mutual coherence of spectral libraries and different sensor settings are some challenges of the unmixing problem. In this work, we focus on semi-supervised linear hyperspectral unmixing in which a spectral library is given. The resulting linear equation is an underdetermind problem with... 

Nowadays, many entities and the relationships between them create different types of networks. Graphs are appropriate tools to model these networks. In a graph, nodes show individuals and edges show the relations between them. One of the most important research problems in the field of network analysis is community detection. In a network, a community is a group of nodes that has a lot of connections to the nodes inside the same group and a few to the ones which are outside. Community detection has many real world applications. Recommending items in recommender systems, detecting spy and terrorist groups and predicting future links between members in a social network are some examples where... 

At the molecular level, proteins control almost all the biochemical reactions in the cells. In order for proteins to function, they must be able to fold into their unique 3D structure. Deformation of protein structure due to some environmental phenomena such as pH, high temperature, and stress may cause unfolding of proteins and finally result in formation of protein fibrils called "amyloid". Amyloid has been found in a number of human diseases such as Alzheimer, type II diabetes, and Parkinson. Recently pyridazine has been under spotlight due to its unique chemical properties such as high dipole moment and higher solubility in biological solvents. In this study, we aim at using a... 

The goal of crowd labeling is to find labels of given samples using humans’ mind power.Since crowds are not necessarily experts, their provided labels are rather noisy and erroneous.This challenge is usually resolved by collecting multiple labels for each sample and aggregating them to estimate its true label. Although this mechanism leads to high-quality labels, it is not actually cost effective. Adaptive methods consider that only some samples are challenging and require more labels. They spend the budget more wisely, and iteratively collect the required labels. Using adaptive methods approach, we utilize statistical latent models to model and analyze the collected labels and low-rank... 

A number of questions from a variety of areas of mathematics lead one to the problem of analyzing the topology of a simplicial complex. However, there are few general techniques available to aid us in this study. On the other hand, some very general theories have been developed for the study of smooth manifolds. One of the most powerful, and useful, of these theories is Morse Theory. We present a combinatorial adaptation of Morse Theory, which we call discrete Morse theory that may be applied to any simplicial complex (or more general cell complex). Our goal is to present an overview of the subject of discrete Morse Theory that is sufficient both to understand the major applications of the... 

Online social networks have become very popular in recent years. Most people usually get involved in multiple social networks to enjoy new contents and different social interactions. Many new social networks try to attract users of other existing networks to increase the number of their users. Once a user (called source user) of a social network (called source network) joins a new social network (called target network), a new internetwork link, known as anchor link, is formed between the source and target networks. In this thesis, we concentrate on predicting the formation of such anchor links between heterogeneous social networks. Unlike conventional link prediction problems in which the... 

Social networks play an important role in the spread of information, news and users’decisions. An important type of these networks are location-based networks where users can post the time and location of their checks in different places. Check-ins of a user may incentivize her friends to visit the same location in the near future.This phenomena is called diffusion process. Previous works often assume that the generation of an event just increases the probability of subsequent events in a near future. Even though the assumption is quite valid in the social networks like Twitter,it is not the sufcient assumption in spatio-temporal social networks where the users’physical limitations and... 

Bioorthogonal chemistry defines any reaction, inside or outside the living systems, without interfering with native chemical processes and 3dimensional structure of proteins. In these types of reactions water is the sole solvent; a neutral pH is required; the temperature must be up to 40 oC. The kinetics of reactions must be on the hour scale and the nontoxic reagents with low concentration must be used. One of the simplest methods of visualizing protein molecule is covalent attachment of fluorescein to protein. In this work several fluorescent compounds were synthesized. These novel compounds include acylchloride fluorescein, N-hydroxysuccinimide fluorescein, thiophenol fluorescein, and...