people

members of the lab

mazlaghani_1.jpg

Assoc. Prof. Maryam Amirmazlaghani, PhD

Maryam Amirmazlaghani is an associate professor in Artificial Intelligence group of the Computer Engineering Department at Amirkabir University of Technology. Also, she is the head of Statistical Data Analysis (SDA) lab. She received the M.S. degree from Sharif University of Technology in 2005, and the Ph.D. degree from Amirkabir University of Technology in 2009 both in electrical engineering. Her research interests include deep learning, image processing, medical data analysis, statistical learning and adversarial learning.

roshanfekr.jpg

Behnam Roshanfekr, PhD Student

I am a PhD candidate in the department of Computer Engineering at Amirkabir University of Technology (Tehran Polytechnic) where I received my M.Sc. in 2017. My research field of academia is Graph Signal Processing. In my free time, I thoroughly enjoy playing chess.

Education

  • Amirkabir University of Technology (Tehran Polytechnic), Ph.D. in Artificial Intelligence, Sep.2017 - Present
  • Amirkabir University of Technology (Tehran Polytechnic), M.Sc. in Artificial Intelligence, Sep.2014 – Feb.2017
  • Ferdowsi University of Mashhad, B.Sc. in Computer Engineering, Software, Sep.2010 – Sep.2014

Publications

  • B. Roshanfekr, S. Khadivi, and M. Rahmati, “Sentiment analysis using deep learning on Persian texts.” Iranian Conference on Electrical Engineering (ICEE) on IEEE, pp. 1503-1508, 2017.
  • S. Mohtaj, B. Roshanfekr, A. Zafarian, and H. Asghari, “Parsivar: A Language Processing Toolkit for Persian”, LREC, 2018.
  • B. Roshanfekr, M. Amirmazlaghani, and M. Rahmati. “Learning graph from graph signals: An approach based on sensitivity analysis over a deep learning framework.” Knowledge-Based Systems 260 (2023): 110159.
  • A. Amouzad, Z. Dehghanian, S. Saravani, M. Amirmazlaghani, and B. Roshanfekr. “Graph isomorphism U-Net.” Expert Systems with Applications 236 (2024): 121280.

Projects

  • Parsivar: A Language Processing Toolkit for Persian
    • Parsivar is a Python library for preprocessing Persian texts. This toolkit performs various kinds of activities comprised of normalization, space correction, tokenization, stemming, parts of speech tagging and shallow parsing.

Skills

  • Programming Languages: Python, C/C++, Java, Matlab
  • Deep learning frameworks: Tensorflow, Keras, Pytorch
  • Tools & Software: PostgreSQL/MySQL, Apache spark

Interests

  • Graph Signal Processing
  • Deep Learning
  • Machine Learning

Contact

firouzbakht.jpg

Mahdi Firouzbakht, MSc Student

I am a Master’s student at Amirkabir University of Technology (Tehran Polytechnic) pursuing a degree in computer engineering. My specialization focuses on deep learning and computer vision. I obtained my undergraduate degree in computer engineering from Kharazmi University and have since dedicated my academic journey to the development of practical methodologies in deep learning and machine learning, particularly in the context of supervised learning tasks. My passion is centered on the application of these methodologies within the fields of computer vision and image processing. I am particularly interested in the processing of medical images, where the application of deep learning can bring significant advancements. Currently, my research is deeply engaged in exploring the potential of vision transformer networks for tasks such as detection and classification. This ongoing work fuels my enthusiasm for the exciting possibilities within the field of artificial intelligence.

Research Interests

My primary research interest lies at the intersection of Deep Learning, Machine Learning, and Computer Vision, with a specific focus on Image Processing and Medical Image Analysis. I am deeply passionate about advancing the frontiers of artificial intelligence, particularly through the development and application of state-of-the-art deep learning techniques in the realm of computer vision. The field of Computer Vision captivates me due to its potential to revolutionize industries ranging from healthcare to autonomous vehicles. In this context, I aim to leverage the power of deep learning models to enhance the accuracy and efficiency of image processing. I am driven by the opportunity to make significant contributions in the development of AI-driven solutions for medical diagnostics, enabling more accurate and timely disease detection, ultimately improving patient outcomes and healthcare delivery. My research endeavors are geared toward addressing the complex challenges in this interdisciplinary field and propelling the advancement of AI applications in the healthcare domain.

Education

I will be graduating with a Master’s in Computer Engineering (Artificial Intelligence) from Amirkabir University of Technology (Tehran Polytechnic) with a GPA of 3.31. My thesis, titled “Cancer Detection in Medical Images,” explores the implementation of a cutting-edge vision transformer-based neural network for breast cancer classification. Extensive research was conducted, focusing on historical methods and deep learning techniques for this critical medical task. I hold a Bachelor’s degree in Computer Engineering ( Software Engineering ) from Kharazmi University of Tehran, achieving GPA of 3.70. My Bachelor’s Project involved the creation of a Python and Django-based Cloud system, tailored to optimize the administration of operating systems within university labs. This cutting-edge innovation marks a substantial advancement by enhancing privacy, fortifying security, and improving operational efficiency, thereby redefining the approach to OS management in academic settings.

Contact Information

amiryan.jpg

Ali Amiryan

I’m a student at Amirkabir University of Tehran, originally from Mashhad but currently living in Tehran. I’m in my third term, and so far, I’ve maintained a GPA of 4. I believe in the power of teamwork and have always been dedicated to collaborative efforts. Before my current program, I earned my Bachelor of Science in Computer Engineering from Ferdowsi University of Mashhad with a GPA of 4. trading, with a focus on Forex and Crypto markets. I’ve also completed tangible projects in backend development using Django and Laravel.

Education

Awards and Honors

  • Rank 2nd among about 150 graduated students of Ferdowsi university of Mashhad
  • 15th Place in ACM ICPC in 2018 which is held in the Tehran site (Sharif University)
  • Rank 144th in the Iranian university entrance exam

Research Interests

  • Time series method of forecasting
  • Interpretability
  • Transformers
  • Deep Learning
  • Financial markets
  • NLP

Skills

Programming

python, MQL, Mathlab, C++, JS, Java, C#, GO

Frameworks/Libraries

Pytorch, Pandas, Numpy, Matplotlib, Scikit-learn, Boekeh, Vue-JS, Django, Laravel, Selenium, ZMQ

Database

SQL Server, MySQL, Redis

Miscellaneous

Git, Docker, Ubuntu, Latex, Office

Contact

  • Email : aliamiryance@gmail.com
  • Telegram : @A_Amiryan
  • LinkedIn
  • GitHub
SamanMohammadiRaouf.jpg

Saman Mohammadi Raouf

Ever since high school, I’ve been interested in studying fields related to computers. This led me to pursue a degree in Computer Engineering at the Iran University of Science and Technology. I graduated with a Bachelor’s in the summer of 2023 and immediately afterward, began my studies in Artificial Intelligence due to my passion for the subject. I’m particularly interested in machine learning, deep learning, data analysis, and research topics in this area and dedicate most of my time to them.

Research Interests

  • Deep Learning
  • Graph-based Machine Learning
  • Statistical Models for Time Series

Education

  • High School Diploma: Atomic Energy High School (GPA 19.82)
  • Bachelor’s: Computer Engineering, Iran University of Science and Technology (GPA 18.79)
  • Currently Pursuing Master’s: Artificial Intelligence and Robotics, Amirkabir University of Technology

Projects

  • Team member in the design and implementation of the logic part for a fraud detection system in online websites and outlier data detection.
  • Implementation of a platform for financial data analysis using Apache Spark. Researched optimizations for algorithm execution, tailored to the type of algorithm and runtime environment.
  • Tile crack detection using image processing and computer vision techniques.
  • Forecasting future values of time series using algorithms like ARIMA, ARMA, etc.
  • Team member in implementing Kafka streaming for the transfer and real-time processing of bulk data sent from GPS in vehicles and phones.
  • Member of a student team project to design and implement the “Shanbe” app for a software engineering course.
  • Adding special commands to the xv6 operating system for an Operating Systems course project.
  • Implemented an open-source version of a part of OpenUnderstand software.
Newsha.jpg

Newsha Shahbodaghkhan, (MSc Student)

I am a master’s student currently pursuing my studies in Artificial Intelligence with a focus on explainable and interpretable deep models for medical images. Alongside my academic pursuits, I also have a keen interest in psychology and find great enjoyment in exploring this field. Under the guidance of Dr. Rahmati and Dr. Amirmazlaghani, I am actively involved in research that aims to bridge the gap between advanced machine learning techniques and the healthcare domain. Throughout my academic journey, I have gained hands-on experience in various computer vision and machine learning techniques. I am proficient in programming languages such as Python, along with frameworks like TensorFlow and PyTorch, enabling me to implement state-of-the-art algorithms and models.

RESEARCH INTERESTS
  • Deep Learning
  • Machine Learning
  • Computer Vision
  • Explainable Artificial Intelligence (XAI)
  • Natural Language Processing (NLP)

EDUCATION

  • Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
    • M.Sc., Artificial Intelligence
    • September 2022 - now
    • Supervisors: Prof. Mohammad Rahmati, Prof. Maryam Amirmazlaghani
  • Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
    • B.Sc., Computer Engineering
    • September 2017 - February 2022
    • Supervisor: Prof. Saeedeh Momtazi

EXPERIENCES AND PROJECTS

  • Implementing a Persian Question Answering System based on Reading Comprehension (PQuAD)
  • Evaluation of soft skills of job applicants based on their output in online cognitive games in Iran’s national Elites foundation Competitions
  • Senior software expert of Healthium company

PAPERS

TECHNICAL SKILLS

  • Programming Languages: Python, Java, C/C++, JavaScript, Matlab, Racket
  • Deep learning frameworks: Tensorflow, Keras, Pytorch
  • Database operation: MySQL, Sql Server, MariaDB
  • Web development: HTML, CSS, JavaScript, JQuery, PHP, Wordpress, Woocommerce
  • Operating Systems: Linux(Ubuntu), MacOS, Windows
  • Miscellaneous: Git, UML, Verilog, VHDL, Arduino, Proteus, Boson NetSim, Orcad Pspice, GNS3, power designer
  • Microsoft Office package: Microsoft Word, PowerPoint, Excel
S_mahdi.jpg

Soroush Mahdi, MSc Student

Hello! I’m currently an MSc student in Artificial Intelligence at Amirkabir University of Technology. Alongside my studies, I’m actively engaged as a research assistant in the Statistical Data Analysis Laboratory, under the expert guidance of Prof. AmirMazlaghani. I’m particularly intrigued by the challenge of enhancing the adversarial robustness of neural networks and working to improve them. Moreover, I’m fervently exploring opportunities to contribute to cutting-edge research as I actively seek out Ph.D. positions to continue my academic journey.

Prior to my MSc I finished my 𝐁𝐒𝐜 in Computer Engineering at the Department of Computer Engineering, Bu-Ali Sina University.

Research Interests
  • Adversarial Robustness
  • Computer Vision
  • Computational Neuroscience
  • Trustworthy AI
  • Generative AI
Contact