Sharif Digital Repository

Persistent homology is one of the main tools in Topological Data Analysis. Indeed, to deal with a huge dataset while noise sensitivity is important, persistent homology can reflect some information about data in the form of persistent homology groups and persistence diagrams. Note that statistical or linear algebraic tools are not suitable to work with huge datasets with very high dimensions. In this thesis, we discuss the concept of persistent homology and investigate some of its properties such as the stability of the persistence diagrams. Indeed, persistence diagrams are obtained from the generating sets of the persistent homology groups. Further, we discuss an application of persistent... 

In this work, we aim to find a way to identify and forecast transients in nuclear power plants with the aid of semi-supervised machine learning algorithm. Forecasting and identifying transients in nuclear power plants at the early stages of formation are essential for safety considerations and precautionary measures. The use of machine learning algorithms provides an intelligent control mechanism that, along with the main operator of the power plant, raises the transient detection and identification rate. Our algorithm of choice is to change the way data is presented, which is a semi-supervised learning approach. The algorithm consists of two methods: quantum dynamics clustering... 

Clustered Regularly Interspaced Short Palindromic Repeats, or in short, CRISPR is a relatively new technology that enables geneticists and medical researchers to edit parts of the genome by removing, adding, or altering parts of the DNA. Initially found in the genomes of prokaryotic organisms such as bacteria and archaea, this technology can cure many illnesses such as blindness and cancer. A significant issue for a practical application of CRISPR systems is accurately predicting the single guide RNA (sgRNA) on-target efficacy and off-target sensitivity. While some methods classify these designs, most algorithms are on separate data with different genes and cells. The lack of... 

Causal discovery is of utmost importance for agents who must plan and decide based on observations. Since mistaking correlation with causation might lead to un- wanted consequences. The gold standard to discover causal relation is to perform experiments. However, experiments are in many cases expensive, unethical or impossible to perform. In these situations, there is a need for observational causal discovery. Causal discovery in the observational data setting involves making significant assumptions on the data and on the underlying causal model. This thesis aims to alleviate some of the assumptions and tries to identify the causal relationships and causal mechanisms using generative neural... 

With the rapid development of the economy, more people have started investing in the stock market. Predicting price changes can reduce the risk of investing in stocks. Technical data such as price and volume in the stock market is usually used to predict stock prices, and less often other types of data such as market data or fundamental data are used. In this study, we want to determine what impact each of the available data types has on stock prices. For example, data of buy and sell for per capita, capital inflows and outflows for small and large natural and legal investors, information related to the stocks themselves, indicators, fundamental data such as earnings per share (EPS) and... 

In competitive environment of quick market changes, developing an interoperable manufacturing system is a necessity. Process planning as a connection link between design and manufacturing, has never been able to integrate these up/down stream activities and in spite of employing computer systems, CAPP’s information has been managed in an isolated manner. To realize interoperability, the exchange of part and product data must be independent of their platforms. There are two basic approaches for this purpose: i) Utilizing interface and ii) Utilizing neutral formats. STEP (Standard for the Exchange of Product data) plays a significant role as a neutral data model to integrate design,... 

Conversation modeling is one of the most important goals in the field of understanding natural language and machine intelligence. Recently, with the enormous growth of the Internet and social networks, the amount of available data on the Web has increased significantly.This makes it possible to use data-driven approaches to solve the modeling problem of conversation.One of the most recent data-driven methods is the sequence to sequence modeling. In this document, after providing the necessary prerequisites, we examined the various models that have used the sequence to sequence approach for conversation modeling. We further examined the ways of improving the efficiency of this modeling... 

Today's smartphone devices include several cores, such as CPU, GPU, and different accelerators, in order to maximize user experience. However, due to meeting the power budget and limited capacity battery, power and energy of their cores should be managed using dynamic power management methods such as dynamic voltage and frequency scaling (DVFS). For this purpose, we should find optimal frequency and voltage settings of processing cores for each time, to minimize energy consumption while retaining user experience. Finding this optimal frequency and voltage settings is a challenging problem that depends on many parameters. We propose to use deep reinforcement learning (DRL) method to... 

Autism spectrum disorder (ASD) is a strong genetic perturbation that encompasses a wide range of clinical symptoms, including functional at different regions of the brain, repetitive behaviors, and interests, weaknesses in social relationships, some sensitivities to environmental factors and etc. Genetic complexity and the impact of environmental factors put the disease in the category of Level 1 complex developmental disorders.We proposed a pilot, combined, and highly effective structure to identify biomarkers in the autism spectrum disorder that could be extended to other diseases that have a similar genetic architecture with autism. We also develop a Gene-tissue interaction network to... 

In this study, given the increasing challenges urban and intercity transportation face in the modern world, including population growth, urban development, and environmental concerns, an innovative approach to optimize the use of car-sharing vehicles is presented. The research aims to develop a multi-objective mathematical programming model for the optimal allocation of car-sharing vehicles, considering key factors such as transportation costs, travel time, and environmental pollution. This seeks to reduce costs, increase efficiency, shorten travel times, and contribute to environmental sustainability. Initially, a thorough literature review was conducted to provide a comprehensive... 

The process of portfolio construction and optimization can be broken down into three main steps: selecting appropriate assets, allocating capital, and monitoring and adjusting the portfolio. This study focuses on evaluating the performance of the Hierarchical Risk Parity (HRP) method for capital allocation in investment portfolios, specifically in Iran’s capital market. The aim is to enhance the method's effectiveness by implementing alternative correlation calculation approaches, such as Wavelet and Chatterjee correlations. The study utilizes three different portfolios containing assets from the Tehran Stock Exchange, the US stock market, and the cryptocurrency market. The primary objective... 

A Brain-Computer Interface (BCI) is a communication system that does not need any peripheral muscular activity. The huge goal of BCI is to translate brain activity into a command for a computer. One of the most important topics in the brain-computer interface is motor imagery (MI), which shows the reconstruction of subjects. The electrical activities of the brain are measured as electroencephalogram (EEG). EEG signals behave as low to noise ratio also show the dynamic behaviors.In the present work, a novel approach has been employed which is based on feature extraction with discretion wavelet transform (DWT), support vector machine (SVM), Artificial Neural Network (ANN) and Convolutional... 

The applications that consist ofprecedence-constrained parallel taskshave used in business activities and scientific projects and the energy consumption of these application has become a major concern in datacenters. At the software level, energy-aware task scheduling algorithmsare an effective technique for energy reduction and optimizing performance in data centers. The related works in this areahave traditionally ignore the utilization value of physical machines (PMs) and while the main reason of the energy inefficiency in datacenters is low average utilization of the PMs.In this paper, we propose a new energy-aware scheduling (EASy) algorithm forprecedence-constrained parallel taskswith... 

There is a significant amount of data in the healthcare domain and it is unfeasible to process such volume of data manually in order to diagnose the diseases and develop a treatment method in the short term. Diabetes mellitus has attracted the attention of data miners for a couple of reasons among which significant effects on the health and well-being of the contracted people and the economic burdens on the health care system are of prime importance. Researchers are trying to find a statistical correlation between the causes of this disease and factors like patient's lifestyle, hereditary information, etc. The purpose of data mining is to discover rules that facilitate the early diagnosis... 

Entanglement is one of the key resources of quantum information science which makes identification of entangled states essential to a wide range of quantum technologies and phenomena.This problem is however both computationally and experimentally challenging.Here we use autoencoder neural networks to find semi-optimal measurements for detection of entangled states. We show that it is possible to find high-performance entanglement detectors with as few as three measurements. Also, with the complete information of the state, we develop a neural network that can identify all two-qubits entangled states almost perfectly.This result paves the way for automatic development of efficient... 

large-scale data collection from multiple sources to a single entity, such as a cloud provider, poses a challenging problem for implementing centralized machine learning algorithms. Constraints such as privacy protection and restrictive access policies that prevent accessing personally identifiable information hinder the development of centralized machine learning algorithms in important and sensitive domains like healthcare. However, from early disease detection to discovering new drugs, leveraging artificial intelligence in this domain is a fun-damental necessity. As a potential solution, federated learning has been proposed, allowing data owners (users) to jointly train a shared machine... 

Using statistical tools in machine learning and artificial intelligence to infer knowledge from high-dimensional data, namely data science, has attracted a siginificant research interest over the past two decades. The number of real databases around the world continues to grow with an increasing pace, which are used to store huge amounts of high-dimensional data points of various types. However, applying machine learning tools to high-dimensional data has also raised potential concerns, specially with respect to the fundamental capability of such tools to be useful in practical situations. In fact, the large dimension of a data could eventually damage the outcome of any statistical... 

Detecting phase transitions is one of the challenging problems in condensed matter physics. For systems, which show phase transitions, in which an order parameter smoothly becomes nonzero, identifying critical points needs finite-size scaling of very large systems. There also exist phase transitions in nature, that the order parameter is not precisely specified. Hence the detection of the phase transitions is a difficult task. Machine Learning methods are supposed to be powerful tools for investigating phase transition. In this thesis, we first introduce the structure of machine learning algorithms and describe the corresponding building blocks. We then introduce neural networks algorithms... 

Compressed Sensing (CS) technique refers to the digitalization process that efficiently reduces the number of measurements below the Nyquist rate while preserving signal structure. This technique was originally developed for the analysis of vector datasets. An x ∈R^n vector is transformed into an y ∈R^m vector so that n≪m. For a sufficient number of measurements, this transformation has been shown to preserve the signal structure. Therefore, the technique has been applied to machine learning applications.2D-CS was further developed for matrices (image datasets) so that they could be directly applied to matrices without flattening. X ∈R^(n×n) is transformed into Y ∈R^(m×m) via 2D-CD such...