Loading...
Search for:
ghandi--narges
1.998 seconds
Analyzing Dermatological Data for Disease Detection Using Interpretable Deep Learning
, M.Sc. Thesis Sharif University of Technology ; Rabiee, Hamid Reza (Supervisor) ; Sharifi Zarchi, Ali (Supervisor) ; Ghandi, Narges (Co-Supervisor)
Abstract
We present a deep neural network to classify dermatological disease from patient images. Using self-supervised learning method we have utilized large amount of unlabeled data. We have pre-trained our model on 27000 dermoscopic images gathered from razi hospital, the best dermatological hospital in Iran, along with 33000 images from ISIC 2020 dataset. We have evaluated our model performance in semi-supervised and transfer learning approaches. Our experiments show that using this approach can improve model accuracy and PRC up to 20 percent on semi-supervised setting. The results also show that pretraining can improve classification PRC up to 20 percent on transfer learning task on HAM10000...
Synthesis and Characterization of Vanadium (IV)-SNO & ONO Tridentate Schiff-Base Complexes and Their Applications in Sulfide and Alcohol Oxidation in Ionic Liquid Media
, M.Sc. Thesis Sharif University of Technology ; Bagherzadeh, Mojtaba (Supervisor)
Abstract
In recent years, application of transition metal biphasic catalytic systems for different reactions is an area of intense research activity. Among these reactions, oxidation of sulfides to sulfoxides and sulfones due to their importance as an intermediate in synthesis of organic compounds is a center of interest. Also, the catalytic conversion of alcohols to the corresponding aldehydes or ketones is a fundamental transformation in both laboratory and industrial synthetic chemistry. From environmental perspectives, the development of new catalytic oxidation systems with molecular oxygen as green oxidant is particularly attractive. In recent years, ionic liquids have been extensively studied...
Agent-based Programming and it's Application Using GOAL
,
M.Sc. Thesis
Sharif University of Technology
;
Ramezanian, Rasoul
(Supervisor)
Abstract
With the significant advances in software engineering and developing complicated systems, it’s important to investigate the interaction between systems. Agentoriented software engineering is a new paradigm for developing distributed intelligent systems. Agent technology currently plays an important role in complex software development. The underlying paradigm offers a large repertoire of original concepts, architectures, interaction protocols, and methodologies for the analysis and the specification of complex systems built as Multi-Agent Systems (MAS). Several efforts, originating from academia, industry, and several standardisation consortium, have been made in order to provide new tools,...
Auto-selection of space-time Interest Points for Action Recognition
Application in Fisherposes Method
,
M.Sc. Thesis
Sharif University of Technology
;
Mohammadzadeh, Narges Hoda
(Supervisor)
Abstract
In this project, a novel action recognition method, named Fisherposes, is proposed, which is improved by several space-time (spatio-temporal) methods afterwards. The proposed method utilizes skeleton data obtained from Kinect sensor. First, pre-processing is performed in which the scales of bodies are canceled and the skeletons become aligned in order to make the method robust to location, orientation, and scale of people. In Fisherposes method, every action is defined as a sequence of body poses. Using the training samples for the poses, a Fisher subspace is created which we name it Fisherposes. Moreover, a novel distance measuring function, named regularized Mahalanobis distance, is...
Simulation of Plasma Gasification and Power Generation Based on Solid Waste
, M.Sc. Thesis Sharif University of Technology ; Saboohi, Yadollah (Supervisor)
Abstract
Along with the development of social and economical development and expansion of urban areas the rate of municipal solid waste (MSW) generation has been increased. Waste-to-Energy technologies consist of any waste treatment process that enables generating energy from a waste source. In recent years many studies have shown that plasma gasification has a considerable potential as an effective method for solid waste treatment and energy recovery. Plasma gasification converts MSW to a clean syngas and its application could reduce MSW volume and the environmental risks of waste landfill. In the present study the methods of waste conversion to energy has been reviewed, then plasma gasification of...
Sales and Marketing Cooperation: Mechanisms and Consequences
, Ph.D. Dissertation Sharif University of Technology ; Najmi, Manoochehr (Supervisor)
Abstract
Previous studies and field evidences show that creating appropriate interactions between sales and marketing departments is a challenge for many organizations. The main objective of this research is to develop and elaborate a conceptual framework in which "cooperation mechanisms" between sales and marketing and it’s "consequences" determined and provide an explanation that shows how configuration of sales and marketing relationship affects its consequences. The results show that "organizational ambidexterity" is the core consequence in proper architecture of the relationship between sales and marketing. In the strategy literature, combination of the dual capabilities of exploration and...
Analyzing IoT System Using Location-Base Data
,
M.Sc. Thesis
Sharif University of Technology
;
Gholampour, Iman
(Supervisor)
Abstract
Nowadays, using different types of data has shown significant impacts on analyzing the related systems. Growth in data volume, systems complexity and existence of error and obscurity in collecting the data, increased the necessity of inventing new data analysis methods. Location-based data is an important data type for such analyses which are collected from sensors in different places. These data besides other official organization's information like municipality or Google … provide us a bulk volume of raw data. Such collections of raw data are mostly diverse, heterogeneous, bulk and outspread. Inspite of that, raw data with machine learning algorithms lead to considerable practical...
A Framework for Identifying Critical Areas in Urban Road Networks Based on Percolation Theory Using Real Data
, M.Sc. Thesis Sharif University of Technology ; Amini, Zahra (Supervisor)
Abstract
Transportation networks serve as the primary foundation for economic growth and the development of nations. These networks play a pivotal role by facilitating the movement of goods and passengers, as well as providing essential resources for human activities. With the rapid urbanization and increasing population in cities, the importance and efficiency of these networks have become even more critical. Among the significant challenges faced in urban areas is traffic congestion, which leads to substantial costs, including wasted time and energy, and has negative impacts on public health. As a result, numerous studies have been conducted on the formation and spread of congestion in streets and...
Null Controllability and Stabilizability of Compressible Navier-stokes System in One Dimension
, M.Sc. Thesis Sharif University of Technology ; Hesaraki, Mahmoud (Supervisor)
Abstract
In this thesis we study the exponential stabilization of the one dimensional compressible Navier-Stokes system, in a bounded interval locally around a constant steady state by a localized distributed control acting only in the velocity equation. In fact this is an analysis of a paper that published by Shirshendu Chowdhury, Debayan Maity, Mithily Ramaswamy and Jean-Pierre Raymond in Journal of Differential Equations. We determine a linear feedback law able to stabilize a nonlinear transformed system. Coming back to the original nonlinear system, we obtain a nonlinear feedback law able to stabilize locally this nonlinear system. The result is providing feedback control laws stabilizing...
Some nonlinear/adaptive methods for fast recovery of the missing samples of signals
, Article Signal Processing ; Volume 88, Issue 3 , 2008 , Pages 624-638 ; 01651684 (ISSN) ; Jahani Yekta, M. M ; Marvasti, F ; Sharif University of Technology
2008
Abstract
In this paper an iterative method for recovery of the missing samples of signals is investigated in detail, and some novel linear, nonlinear, and adaptive extrapolation techniques are proposed to be used along with it to increase the convergence rate of the recovery system. The proposed methods would remarkably speed up the convergence rate, save processing power, and reduce the delay of the system compared to some well known accelerated versions of the aforementioned iterative algorithm. © 2007 Elsevier B.V. All rights reserved
A novel context modeling scheme for motion vectors context-based arithmetic coding
, Article Canadian Conference on Electrical and Computer Engineering; Technology Driving Innovation, 2004, Niagara Falls, 2 May 2004 through 5 May 2004 ; Volume 4 , 2004 , Pages 2021-2024 ; 08407789 (ISSN); 0780382536 (ISBN) ; Ghandi, M. M ; Shamsollahi, M. B ; Sharif University of Technology
2004
Abstract
In this paper a new context modelling scheme for arithmetic coding of Motion Vectors (MVs) is proposed. The model uses the correlation between the horizontal and vertical components of MVs to improve the probability estimation of symbols. The accurate probability estimation can therefore improve the efficiency of the context-based arithmetic coder. The proposed scheme has been adapted to the H.264 advanced video codec and the simulation results show that a considerable bit rate saving can be achieved in MV coding
Analysis of People Appearance Variation in Multi-Camera Networks
, M.Sc. Thesis Sharif University of Technology ; Behroozi, Hamid (Supervisor) ; Mohammadzadeh, Narges Hoda (Co-Supervisor)
Abstract
Analysis of people appearance variation in multi-camera networks for person re-identification or person retrieval is a very challenging problem due to the many intra-class variations between different cameras. Like any problem in the field of machine vision, it is generally divided into two parts. The first part is feature extraction and the second part is feature matching for person retrieval. So far, various methods have been proposed for the extraction of discriminative features, which are generally divided into three categories: stripe-based, patch-based, and body-based methods. However, methods based on stripes, although simpler, have performed better due to their greater compatibility...
Software Product Line Testing Optimization Based on Regression Test Techniques
, M.Sc. Thesis Sharif University of Technology ; Mirian Hosseinabadi, Hassan (Supervisor)
Abstract
A software product line is a set of products with common features. The design of this set is such that the core assets that are common features between products are implemented only once. All products in the product line use the core assets to reduce development costs. The number of products that can be produced in a software product line is exponential to the number of capabilities in the core assets and the set is very large, so the cost of testing the software product line will be very high. In the software product line testing, various methods have been provided to reduce costs, among which we can mention product prioritization and regression test techniques. In prioritization, the...
Diverse Video Captioning Using Recurrent Neural Networks and Part of Speech
, M.Sc. Thesis Sharif University of Technology ; Mohammadzadeh, Narges Al Hoda (Supervisor) ; Behroozi, Hamid (Co-Supervisor)
Abstract
In recent years, the simultaneous analysis of image and text by artificial intelligence has gained much attention. Video description is one of the topics used to help the blind, automate video content analysis, and more. This issue is usually examined in the context of supervised learning and is very similar to image description and machine translation.The proposed solutions to this problem are mainly in the framework of encoder-decoder and attention-based neural networks. Selection of various pre-trained networks to extract 2D and 3D visual features (description of objects and actions in the image), various hierarchical structures and different teaching methods (based on reinforcement...
Modeling of Fischer-Tropsch Synthesis Reactor for GTL Process
, M.Sc. Thesis Sharif University of Technology ; Khorasheh, Farhad (Supervisor) ; Taghikhani, Vahid (Supervisor)
Abstract
There is a need from the natural gas and energy industries to seek for an economically attractive way of converting remote gas reserves into transportable products, such as high quality fuels or petrochemicals. A possible way for the conversion of natural gas to middle distillates is based on a three-step process. Firstly, production of syngas from natural gas. Secondly,catalytic conversion of syngas into hydrocarbons, mostly parafins from C5 to C100. (Fischer-Tropsch (F-T) synthesis). Thirdly, hydrocracking of the heavy paraffinic hydrocarbons to middle distillates. The F-T synthesis step is highly exothermic. In order to control the temperature within the reactor, when considering high...
Water-energy nexus approach for optimal design of hybrid cooling system in direct reduction of iron plant
, Article Journal of Cleaner Production ; Volume 287 , 2021 ; 09596526 (ISSN) ; Morad Bazofti, M ; Akbari Mohammadi, A ; Mokhtari, H ; Saboohi, Y ; Golkar, B ; Ghandi, A. H ; Sharif University of Technology
Elsevier Ltd
2021
Abstract
Direct reduction of iron process in steel industry has special production conditions. Low quality cooling water, low cold and high hot cooling water temperature, space limitation for new equipment installation, high value-added of product and severe effect of cooling water temperature on production rate are of these conditions. Considering technical and economic constraints and limitations, this situation makes this process an attractive case study for converting the existing wet cooling tower to hybrid cooling system. In this paper, based on integration of process, dry and wet cooling system and ambient conditions profiles, a new method for designing hybrid cooling system has been proposed....
The online atlas of the languages of Iran: Design, methodology and initial results
, Article Language Related Research ; Volume 12, Issue 2 , 2021 , Pages 231-291 ; 23223081 (ISSN) ; Anonby, E ; Hayes, A ; Azin, Z ; Ebrahimi, Z ; Öpengin, E ; Atabaki, N. A ; Stone, A ; Stilo, D ; Esmaeelpour, E ; Amani Babadi, M ; Ourang, M ; Izadi, E ; Oikle, R ; Bahrani, N ; Borjian, H ; Bahrami, A ; Poshtvan, H ; Piryaee, S ; Pishyardehkordi, P ; Sabethemmatabadi, P ; Jaafari Dehaghi, S ; Doab, M. J ; Jamaleddin, F ; Joulaei, K ; Shabaniyan, H. H ; Khanjani, J ; Dianat, L ; Rashidi, A ; Borujeni, R. R ; Rahnema, Z ; Zamani Gandomani, Z ; Schreiber, L ; Sherafat, N ; Sheyholislami, J ; Salehi, M ; Talebi Dastenaei, M ; Kasgari, A. A. A ; Ghiasian, M. S ; Fattahi, M ; Ghandi, S ; Gheitasi Doolabi, M ; Kamali, R ; Goshtasb, F ; Bahmani, H. M ; Mohammadi, M ; Moradi, R ; Meshkinfam, M ; Khoo, R. M ; Bahram, A. N ; Nemati, F ; Nourzaei, M ; Wang, E ; Hashemi Zarajabad, H ; Sharif University of Technology
Tarbiat Modares University
2021
Abstract
Iran is home to a treasury of languages representing diverse language families: Iranic, Turkic, Semitic, Indic, Dravidian, Armenian, and Kartvelian, as well as sign languages. Despite valuable research carried out by Iranian and western scholars, there is still no comprehensive publication depicting the geographic distribution and linguistic status of language varieties in Iran. In order to work toward this goal, the Atlas of the Languages of Iran (ALI) (www.iranatlas.net) was officially launched in 2015 as an international, online research programme. The present study opens with a historical overview of the research context and underlines the ongoing necessity of constructing such an atlas...