• M.S.C.2013 Avg: 3.34 of 4

    Master of Artificial Intelligence

    Shahrood University of Thechnology

  • B.S.C.2009 Avg: 3.02 of 4

    Bachelor of Computer Engineering (Software)

    Ferdowsi University of Mashhad, Mashhad, Iran.

  • H.S.1993 Avg: 3.73 of 4

    High school in Math

    Koasar High Scool


  • M.S.C. 2013
    Desired Human Movement Recognition Using EEG Signals
    Supervisor: Dr. Morteza Zahedi
    Advisor: Dr. Alireza Ahmadifard
    GPA: 3.34 of 4
  • 2011
    Analysis and Design an Antivirus in VB.NET
    Supervisor: Dr. Reza Monsefi
    GPA: 3 of 4

Filter by type:

Sort by year:

An Anti-Spam System using Naive Bayes Method and Feature Selection Methods

Masume Esmaeili, Arezoo Arjomandzadeh, Reza Shams
Journal Papers International Journal of Computer Applications (0975 – 8887) Volume 165 – No.4, May 2017


Electronic mail is one of the important means of communication. Thus, this useful tool has invaded by invaders for different purposes. One such Invasion is the posting of useless, unwanted e-mails known as spam or junk e-mails. Several methods of spam detection exist, but each has certain weaknesses. This paper address these weaknesses by implementing and describing a spam detection system in text classification mode, which uses Bayesian method vs. PCA to filter out written spam mails from the user’s mail box. In the proposed method first extract all tokens that exist in body of emails for classifying emails based on them. But sum of these tokens aren’t useful. Sum of them are repeated in two categories spam and non-spam mails equally, so they aren’t appropriate for distinguishing two types of emails. So proposed method finds best tokens as main features using feature selection methods such as genetic algorithm (GA), forward and backward feature selection methods.

Static Partitioning of EEG Signals by GA Using Multi_CSP

Masume Esmaeili Morteza Zahedi
Journal Papers Elixir Comp. Engg. 82 (2015) 32134-32138.


In this paper a method has been proposed that uses static partitioning for improving classification of time components of EEG signals. The main idea is that different windows of signals have different power in classification. So with removing some ineffective windows from signals, the power of classification might be increased. For finding best combination of windows, Genetic Algorithm (GA) was applied. For extracting appropriate features, Common Spatial Pattern (CSP) was derived for five class problem. It applied onto each window distinguishably, and the final feature vector was obtained from placing these feature vectors altogether. LDA was used for classifying tasks. The proposed method was applied on a dataset of five mental tasks in which 30% of dataset were used for testing system. The experimental results show that window selection by GA will increase the accuracy of algorithm. This technique increased the accuracy from 69% into 95.3% for 25 windows and into 100% for 50 windows. So with changing number of windows, the accuracy of algorithm will be changed. Another important parameter is ’m’ that is the number of spatial patterns selected by CSP.

Performance Analysis of PSO and GA Algorithms in Order to Classifying EEG Data

Masume Esmaeili Morteza Zahedi , Nasser Hafezi-Motlagh
Journal Paper Elixir Comp. Engg. 82 (2015) 32129-32133


In this Research, a new method has been proposed in order to classify the mental tasks which represent the Electroencephalogram (EEG) signal as time series. Time series are kind of data format which depict signal voltage varieties in time domain. Different parts of the different signals have different powers, so in first step and in the preprocessing, signal partitioning into several fixed windows is needed. Toward the extracting appropriate features from each EEG signal window, PCA algorithm is used. So for each window, a feature vector is made by PCA, and a general vector is created from these primary vectors. In order to refuse redundancy caused by non-important windows, the best combination of such vectors, that have the best results in classification, should be probed. Toward this goal, two feature extraction methods, Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), are applied. K-Nearest Neighbor (KNN) was used as fitness function for PSO and GA. These methods select such windows whose combination of feature vectors are best and increase TP (true positive) of the classifier. The results show that GA and PSO improve the power of classification, but GA is more efficient.

Spam detection by ANFIS with feature selection by GA

Masume Esmaeili , Morteza Zahedi
Journal PaperElixir Comp. Engg. 77 (2014) 28908-28911


Spam is the sending unwanted e-mail messages frequently with different contents, in large quantities to an indiscriminate set of recipients, and often proselytes a service or a website. Many intelligent systems have been developed for detecting spam emails, but many of them don‟t have enough speed. In this paper, a fuzzy spam detection system in text classification mode is described that has been implemented in MATLAB. Because of the ANFIS uses the approximation capability of FIS and ANN as adaptive, it acts simple and powerful. In the proposed method, first extractor starts to extract all the tokens in the body of all emails. Genetic algorithm (GA) is then applied, to select the appropriate features of the tokens. These features are saved in a dictionary. Then ANFIS uses this dictionary for classifying emails. In this project, ANFIS has three inputs and one output. For obtaining ANFIS‟ inputs, calculate a spamicity for each token. This criterion shows the rate of dangerous of each token. Then tokens of each email are classified into three categories, based on the amounts of their spamicity. Counts of tokens in each category, are three inputs to ANFIS system. ANFIS‟ output determines that each email is spam or not.

Farsi Handwritten Discrete Rcognition Using CSP in Radon Space

Masoumeh Esmaeili, Elham Hosseinzade
Journal Paper Indian J.Sci.Res.3(4):06-10, 2014


Farsi Handwritten Digits Recognition can be used in applications that need auto recognition of handwritten such as sorting Mailing Packages. For this, many efforts were done to decrease the error of Farsi handwritten digits recognition. In this paper a method has been proposed that first transfers handwritten images in radon space and then with using CSP, extracts appropriate features from them. CSP or Common Spatial Pattern is a powerful method that is used in EEG signals for extracting features from several channels. Because EEG signals are recorded from different places of head by several electrodes, and with joining the data of them, EEG signals are created. CSP extract common features from these channels. We use CSP for colorful radon images. R, G and B components of radon images are considered as those channels of EEG. Results show that this method is successful in recognizing handwritten digits. With using KNN as classifier and euclid distance as similarity measure, error rate was decreased

Currrent Teaching

  • Present 2013

    Data Base Lab

  • Present 2013

    Computer Lab

  • Present 2013

    Computer Networks

Teaching History

  • 2014 2016

    Artificial intelligent

  • 2014 2015

    Design of Expert Systems

  • 2016 2016

    Operating system

  • 2010 2014

    Linux Lab

  • 2013 2016

    Network programming

  • 2013 2016

    Electronic commerce

  • 2013 2015

    Management and measurement of wide area networks

  • 2013 2015

    Management and measurement of wide area networks

  • 2013 2017

    Value-added services

  • 2013 2014


  • 2013 2017

    Web Designing

  • 2013 2017

    Internet Service Provider

  • 2013 2015

    TCP/IP concepts

  • 2013 2016

    Advanced Programming(C++ C#)

  • 2013 2014

    Assembly programming

  • 2014 2016

    Advanced Web Programming

  • 2011 2012

    Information Storage And Retieval

At My Office

You can find me at my University located at Quchan University of Advanced Technologies Engineering.

I am at University Saturdays from 8:00am until 20:00 pm.

At My Work

You can find me at my work located at Faramohaseb Company Mashhad,Iran.

I am at my work from Sunday to Thursday from 9:00am until 14:00 pm.

At My Lab

You can find me at Computer Lab located at Quchan University of Advanced Technologies Engineering.

I am at Computer Lab Saturdays from 10:00am until 20:00 pm.

Job Experiences

  • IT Organizations Mashhad Municipality trainee6/21/2008 9/5/2008

    • Web Designing using ASP (Web Form Application) using c#

    • SQL Server

    • ADO.NET

    • Windows Form Application using C#

    • HTML

  • Kaspid Company, Mashhad, Iran trainee7/10/2016 9/12/2016

    • Web Designing using ASP (Web Form Application) using c#

    • Code first ( using Linq)

  • Golden Brand Company, Mashhad, Iran trainee10/23/2017 12/14/2017

    • Web Designing using ASP (Web Form Application) using c#

    • ADO.NET

  • Faramohaseb Company, Mashhad, Iran Programmer7/15/2017 Till Present

    • Web Designing using ASP (MVC) using c#

    • Entity Framework Code first

    • Delphi Programmer

    • Android using VB(Basic for Android(B4A))

    • Web Service Using Soap

  • Andishe sazan Pamchal, Mashhad, Iran
    Web Designer 5/25/2017 Till Present

    • Web Designing using ASP (MVC) using c#

    • Entity Framework Code first