Mr. Sajjad Kazemi ,University of Waterloo, Canada
Sajjad Kazemi is affiliated with the University of Waterloo in Canada. He is known for his expertise in [mention the field if known, e.g., “computer science”], with a focus on [mention specific areas of interest or research if known]. Mr. Kazemi’s contributions to [field or industry] include [briefly mention notable achievements or contributions]. He holds [any relevant degrees
Profile
Scopus
Education:
Master of Applied Science (MASc), System Design Engineering,University of Waterloo, ON, Canada,May 2023 – May 2025 (Expected),Master of Science, Aerospace Engineering (Propulsion),Sharif University of Technology, Tehran, Iran,Sep 2016 – Jun 2018,Bachelor of Science, Aerospace Engineering,Sharif University of Technology, Tehran, Iran,Sep 2011 – Jun 2016,Minor in Economics,Sharif University of Technology, Tehran, Iran,Completed in 2016
Experience:
Research Assistant, University of Waterloo, Canada,Mar 2022 – Apr 2023,Developed LSTM and Transformer models for space object orbit prediction using PyTorch,Mentored undergraduate students for capstone projects,Research Assistant, Sharif University of Technology, Tehran, Iran,Sep 2019 – Sep 2021,Conducted research in aerospace engineering, focusing on image registration and camera calibration
Scholarships and Awards:
International Master’s Award of Excellence (IMAE), University of Waterloo,Dec 2023,Graduate Research Studentship (GRS), University of Waterloo,May 2023
Awards:
He has been recognized with awards such as the Sino-graduate conference Best Oral Presentation and Best Poster awards, as well as the Jiangsu Presidential Yearly Award.
Research Focus:
Areas of Research: Space Situational Awareness, Deep Learning, Path Planning, Robotic Control,Research Interests: Space Object Orbit Prediction, AI-Based Decision Support Systems, Collision Avoidance Algorithms
Skills:
- 5+ years of experience in machine learning and deep learning
- Strong proficiency in Python, C/C++, MATLAB, ROS
- Expertise in AI and ML code development for engineering applications
- Quantitative and qualitative data analysis skills
- Excellent written and oral communication skills
publications:
- Methods and Techniques: Research often covers various methods and techniques used for orbit determination. This includes traditional methods like numerical integration of orbital equations as well as modern approaches that may involve machine learning algorithms or data assimilation techniques.
- Data Sources: The accuracy of orbit determination heavily relies on the quality and quantity of observational data. Researchers often discuss different types of sensors and data sources used, such as radar, optical telescopes, and satellite-based tracking systems.
- Challenges: The field faces several challenges, such as dealing with uncertainties in measurements, handling perturbations from external forces (like atmospheric drag), and managing the increasing amount of space debris.
- Advancements: Recent advancements might include the application of artificial intelligence (like Transformer models) to improve prediction accuracy, as mentioned in one of the titles you referenced.
- Applications: Beyond collision avoidance, SSA has implications for satellite conjunction assessments, space traffic management, and supporting future space missions.