Search for: ffd
0.005 seconds

    High Volume Event Correlation for Long-term Attack Detection

    , M.Sc. Thesis Sharif University of Technology Mahzoon, Niloofar (Author) ; Amini, Morteza (Supervisor)
    The long-term Attacks are some special multi-level attacks which remain inside of systems for a long time to finally perform the damage. One of the most famous kinds of these attacks is Advanced Persistent Threats. These kinds of attack are low-level, distributed inside of the network and their goal is stealing information or corrupting a process in the organization. Banks are one of the most vulnerable organizations which have suffered from these attacks, so the main purpose of this research is detecting them and give warning to the security admin. The goal of financial APTs is stealing money and to achieve that, they have to create some transactions and send them to the core banking. We... 

    Fraud Detection in Financial Transactions

    , M.Sc. Thesis Sharif University of Technology Haghighat, Mohammad (Author) ; Beigy, Hamid (Supervisor)
    With development of electronic payment infrastructures and increase of payment transactions in result, abusing these infrastructures and fraudulent efforts has been increased. Problem of “Fraud Detection in Financial Transactions” is finding these illegal/abnormal transactions while many other legitimate transactions exist. Goal of this thesis is providing a method for fraud detection in financial transactions using representation learning. Many approaches are used for solving fraud detection including classic data mining algorithms and deep learning based methods, which are compared in this thesis. We also covered diverse feature engineering and representation learning ideas for improving... 

    A Novel Model For Financial Fraud Detection Using Machine Learning Techniques

    , M.Sc. Thesis Sharif University of Technology Rahmati, Mahdieh (Author) ; Khedmati, Majid (Supervisor)
    Today, e-commerce systems are used by both types of users. Therefore, the systems will be exposed to systematic fraud, and fraud is one of the main sources of financial losses for organizations. Therefore, it is very important for organizations to use accurate methods to detect fraud. this field is one of the most important applications of data mining in finance. There are various challenges in fraud detection projects, and this research has divided these challenges into three categories, which are: data pre-processing due to the imbalance data set, the accuracy of the machine learning model, and uncertainty. In the first part, both oversampling and undersampling methods will be used in... 

    Cardiac contraction motion compensation in gated myocardial perfusion SPECT: a comparative study

    , Article Physica Medica ; Volume 49 , 2018 , Pages 77-82 ; 11201797 (ISSN) Salehi, N ; Rahmim, A ; Fatemizadeh, E ; Akbarzadeh, A ; Farahani, M. H ; Farzanefar, S ; Ay, M. R ; Sharif University of Technology
    Associazione Italiana di Fisica Medica  2018
    Introduction: Cardiac contraction significantly degrades quality and quantitative accuracy of gated myocardial perfusion SPECT (MPS) images. In this study, we aimed to explore different techniques in motion-compensated temporal processing of MPS images and their impact on image quality and quantitative accuracy. Material and method: 50 patients without known heart condition underwent gated MPS. 3D motion compensation methods using Motion Freezing by Cedars Sinai (MF), Log-domain Diffeomorphic Demons (LDD) and Free-Form Deformation (FFD) were applied to warp all image phases to fit the end-diastolic (ED) phase. Afterwards, myocardial wall thickness, myocardial to blood pool contrast, and...