Sharif Digital Repository

Positioning refers to the process of estimating the receiver coordinates aiming for an accurate understanding of the surrounding environment. This branch of science has attracted considerable attention in recent years. Today, the influence sphere of positioning is so expanded that encompasses applications in daily life (e.g., navigation) as well as commercial and even military fields. Global Positioning System (GPS) is the most widely used tool in real-time positioning. Because GPS imposes great measurement errors in challenging conditions (e.g., turbulent water environments), alternative methods such as methods based on Wi-Fi, Bluetooth, and visible light have been proposed. Benefiting... 

For neurodegenerative diseases like Multiple Sclerosis, Alzheimer’s, or Parkinson’s disease early detection is required to slow progression and prevent disease onset. To do so, identifying early signs and symptoms of the disease as well as modifying lifestyle can play a crucial role. Nowadays, the increasing use of smart gadgets and sensors has paved the way for collecting behavioral data and therefore analyzing and extracting meaningful patterns. In this study, lifestyle and cognitive performance data have been collected via a platform called OptiMind. Previous studies have shown that the Integrated Cognitive Assessment (ICA) can identify patients with neurodegenerative disorders (such as... 

The complexity and non-linearity of today’s machine learning-based systems make it difficult for both end users and experts in the field to understand the logic and reasoning behind their decisions and outputs. Explainable AI (XAI) methods have gained significant attention in real-world problems as they enhance our understanding of these models, increasing trust and improving their efficiency. By applying different explanation methods on a machine learning model, the same output is not necessarily observed, hence evaluation metrics are needed to assess and compare the quality of explanation methods based on one or more definitions of the goodness of the explanation produced by them. Several... 

The complexity of machine learning models has made it difficult for end-users and even experts in the field to understand the reasoning behind the decisions made by these models. As a result, the need for explanation and interpretation of machine learning models has been increasing. One subset of machine learning models is clustering models. Despite the extensive research conducted on interpreting supervised models, very few studies have been focused on interpreting clustering models. In this research, we aim to propose algorithms for interpreting a clustering model in a model-agnostic and post-hoc manner. In this study, various methods are presented for interpreting a clustering model. The... 

As application demands for online convex optimization accelerate, the need for design-ing new methods that simultaneously cover a large class of convex functions and im-pose the lowest possible regret is highly rising. Known online optimization methods usually perform well only in specific settings, e.g., specific parameters such as the diam-eter of decision space, Lipschitz constant, and strong convexity coefficient, where their performance depends highly on the geometry of the decision space and cost functions. However, in practice, the lack of such geometric information leads to confusion in using the appropriate algorithm. To address these issues, some adaptive methods have been proposed... 

Almost all of the network traffic classification systems use pre-defined extracted features by the experts in computer network. These features include regular expressions, port number, information in the header of different layers and statistical feature of the flow. The main problem of the traffic analysis and anomaly detection system lies in finding appropriate features. The feature extraction is a time consuming process which needs an expert to be done. It is notable that the classification of special kinds of traffic like encrypted traffic is impossible using some subset of mentioned features.The lack of integration in feature detection and classification is also another important issue... 

The representation of data influences the explanation factors of data variations. Thus,the success of learner algorithms depends on the data representation. Our main contribution in this thesis is learning of high level and abstract representation using deep structure. One of the fundamental examples of representation learning is the AutoEncoders. The auto-encoder is a rigid framework that doesn’t consider explanation factors in terms of statistical concepts. So, the auto-encoders can be re-interpreted by seeing the decoder as the statistical model of interest. The role of encoder is a mechanism for inference in the model described by the decoder. Our purpose is to design such model with... 

The application of deep learning algorithms in the processing of telecommunication signals is increasing. One of the issues in this area is the automatic recognition of radio signal modulation. Recognizing the type of signal modulation as the first stage of baseband signal processing on the receiver side is a key issue in military and civilian applications. The problem with classical algorithms for solving this problem is their strong dependence on channel characteristics and factors resulting from the transmitter and receiver being non-ideal. However, modern algorithms based on deep neural networks have been able to make the model somewhat resistant to these factors. However, the detection... 

Network traffic classification has been an essential element for security monitoring in the network security scope and also for quality of service purposes. Every now and then, new traffic classes are added to the available groups which are unknown to the system. In an security scope, the novelties are actually the zero-day attacks which can have huge effects on the system environment. There have been many methods developed for traffic classification which are able to distinguish known traffic using signatures or learning-based methods. In a real world scenario, The primary challenge that new traffic classifiers face, is to detect novelty and separate them from the previously known labels.... 

Today, we live in an information age where all people can access the vast amount of data in the world by connecting to the Internet.Since the Internet has expanded significantly to share information, some individuals and organizations seek to be able to prevent the possible sabotage of some people by monitoring network users. Analysis of computer network traffic is one of the importance issues that many activities have been done in this area. One of the most important questions in traffic analysis is to identify the main content of traffic on the encrypted network. Numerous studies have shown that the traffic of websites visited through the Tor network, including Specific information that... 

In network science, link prediction is one of the essential tasks that has been neglected. One important application of link prediction in telecommunication networks is analyzing the user's consumption pattern to provide better service. This project aims to predict future links with applications to call data using the users' call history. In previous research, there are two main approaches: 1) heuristic-based approach, and 2) deep-learning-based approach, such as graph neural networks. These methods are mainly used for processing static graphs, and therefore, we cannot generalize them to dynamic graphs. But there are many graphs which are dynamic in nature. For instance, call data records... 

We live in the cyber era in which network-based technologies have become omnipresent. Meanwhile, threats and attacks are rapidly growing in cyberspace. Nowadays, some signature-based intrusion detection systems try to detect these malicious traffics. However, as new vulnerabilities and new zero-day attacks appear, there is a growing risk of bypassing the current intrusion detection systems. Many research studies have worked on machine learning algorithms for intrusion detection applications. Their major weakness is to consider the different aspects of network security concurrently. For example, continuous concept drift in normal and abnormal traffic, the permanent appearance of zero-day... 

Spiking neural networks (SNNs) are third generation of neural networks. Similar to traditional neural networks, SNNs are comprised neurons. However, not only structure but also information processing is inspired by animal neural systems. SNNs can be called the most similar networks to animal neural systems. In such networks, the information is processed based on propagation of spike signals through the network. The type of data flow in these networks leads to being low-power when they are implemented on hardware. Therefore,there has been a upward trend in hardware implementation of them, like their FPGA implementations, for applications such as Big Data and Machine Learning. In this thesis,... 

Market making is a fundamental trading topic in which an agent creates liquidity in an asset by offering to buy and sell on that security. The challenging problem in market-making is related to inventory risk, which may cause the accumulation of unfavorable positions at the end of the market and create losses. Algorithms are designed for making trades to choose the buying and selling prices and the number of orders by predicting the price to minimize the amount of security in the market maker’s portfolio. In this paper, first, we examine the different market-making algorithms and evaluate their performance in the financial markets of Iran. Then, a model using the reinforcement learning... 

This research aims to introduce a mathematical model that is capable of producing an optimal and coordinated timetable for the entire urban rail network to minimize passengers’ travel time and the trains’ energy consumption. The proposed model focuses on different speed profiles and a skip-stop strategy while considering the stochastic nature of passengers’ arrival and departure rates. This novel approach enables it to develop a schedule that can endure unprecedented situations. To solve the model, the multi-agent deep deterministic policy gradient algorithm is implemented. This approach was first implemented in a smaller network and was validated with Genetic Algorithm. Eventually, this... 

This research deals with the problem of dynamic pricing of perishable assets. In this problem there are two sources of randomness: the arrival rate of customers and their reservation prices. In most studies considering this problem, it’s assumed that process of arrivals of customers follows a Poisson process with a given intensity. Thus this process is assumed to have independent increments and the information regarding the arrival times of previous customers doesn’t have any influence on the distribution of arrival times of future customers. In some recent studies it’s assumed that customers’ arrivals follow a conditional Poisson process with an unknown intensity. The distribution of this... 

Opinion formation is one of the major topics in social networks analysis and mining. A number of methods have been introduced for describing and simulating this phenomenon. In this thesis, we proposed a novel optimization framework based on an opinion formation model that used the Deffuant’s model with some changes in neighbors’ selection policy. Its efficiency was compared with a number of benchmark optimization methods including genetic algorithms, differential evolution and particle swarm optimization.The proposed model demonstrated better performance than the others.In the proposed, each person changes his opinion based on one of his neighbors who has the best performance in terms of the... 

The use of multiple sensors that produce different physical parameters of the measured system for its health monitoring raises the reliability of the diagnosis. At the moment, the fault detection capacities of ball bearings by means of proximity probe are detected by exploiting the advantages and reducing its defects by appropriate signal processing of the raw data in the time domain. Also, the application of numerical derivation and integration to achieve to the desired frequency spectrum in defect detection is investigated. A set of experiments with different sizes of internal ring, outer ring and ball defects, four levels of speed and two load levels have been performed. Data acquisition... 

The Automatic Identification System (AIS) is designed to enhance maritime security and can be installed on ships, ground stations, and satellites. This system is used to transmit essential information from ships across four communication bands (two terrestrial bands and two satellite bands). The primary goal of this research is to receive all four communication bands through a satellite in a Low Earth Orbit (LEO). This goal faces two major challenges: the Doppler effect caused by the relative speed of the satellite to the ships and the significant distance of the satellite, which results in temporal signal interference due to the reception of a large volume of signals from ships. To address... 

Today, telecommunication links transmit information wirelessly at high rates; The transmission channel is not ideal and the transmitted signal undergoes changes in the channel and then reaches the receiver; Also, the processing blocks in the transmitter and receiver are not completely similar and ideal; These two factors make it difficult for the receiver to recover the transmitted information and actually receives a signal that bears little resemblance to the transmitted signal. The most important effect that the channel has on the transmitted signal is due to the multi-path of the channel between the transmitter and the receiver, which causes a signal to reach the receiver through the...