A New Method for Constructing Confidence Intervals on the Parameters of Continuous Distributions

, M.Sc. Thesis Sharif University of Technology Motaei, Amir (Author) ; Akhavan Niaki, Taghi (Supervisor)

Abstract

In this research, a new Bayesian method for constructing confidence intervals on the parameters of any continuous distribution is first developed. The main idea behind developing this method is to model uncertainty. As an application of the proposed methodology, confidence intervals for the two parameters of the Weibull distribution along with their joint confidence interval are then derived in which data can be of type I censored data, type II censored data or uncensored. The new confidence intervals are next compared to other existing exact confidence intervals in the literature and shown to have better performances. Furthermore, we show the lengths of the existing exact confidence...

Modeling & Analysis of CAES Considering Reliability

, M.Sc. Thesis Sharif University of Technology Motaei، Sajad (Author) ; Rajabi Qahnuyeh, Abbas (Supervisor)

Abstract

All over the world availability of electrical power is an important matter. Electrical power is a basic requirement in each country so with increasing the demand, supply system should be adjusted.Compressed Air Energy System (CAES) stores the excessive produced energy as compressed air and will inject it to gas turbine to produce energy in peak load hours.This project aim is modeling and analyzing of CAES considering reliability. In this project some of failure mechanisms have been identified and modeled and then the performance effect on system failure have been surveyed. This project innovation is incorporating operational models with reliability to determine the best performance for...

Adversarial Attack to Deep Learning Networks via Imperceptible Sparse Perturbation

, M.Sc. Thesis Sharif University of Technology Heshmati, Alireza (Author) ; Ghaemmaghami, Shahrokh (Supervisor) ; Marvasti, Farokh (Supervisor) ; Amini, Sajad (Co-Supervisor)

Abstract

Nowadays, methods based on deep learning networks are the most effective artificial in telligence methods. Although they have achieved success in various fields (such as machine vision and object recognition), practical and experimental cases show the fragility of deep learning networks against perturbations and unwanted changes of the input pattern. All these perturbations must be in a way that the main class of the perturbed input pattern can be rec ognized by human, but the network makes a mistake in recognizing its correct class. This thesis seeks a more accurate evaluation by designing adversarial attacks such that the main class of the adversarial pattern is detectable by human...

Dynamic response of metal foam FG porous cylindrical micro-shells due to moving loads with strain gradient size-dependency

, Article European Physical Journal Plus ; Volume 134, Issue 5 , 2019 ; 21905444 (ISSN) Sajad Mirjavadi, S ; Forsat, M ; Barati, M. R ; Abdella, G. M ; Mohasel Afshari, B ; Hamouda, A. M. S ; Rabby, S ; Sharif University of Technology

Springer Verlag 2019

Abstract

The dynamic characteristics of functionally graded (FG) metal foam cylindrical micro-scale shells in contact with a moving load will be analyzed thorough this paper accounting for strain-gradient size-dependency. In the material structure of a metal foam, pores can diffuse uniformly or non-uniformly. Based upon Laplace transform, the dynamical governing equations of the first-order micro-shell model can be established in a new domain. In order to go back into the time domain, an inverse Laplace transform will be required. Thus, on can express the time response or dynamic deflection of the micro-shell under moving load. In the presented results, it is easy to see the prominence of...