Eduacational Email: kapurba@laurentian.ca
Personal Email: kaysarulanas2@gmail.com
Greetings! I am Kaysarul Anas Apurba, a passionate Computer Science and Engineering graduate with a strong academic and research background.
I hold a Master of Science in Computational Sciences (Course-Based) from Laurentian University, Sudbury, Canada (Sept 2023 – Apr 2025), where I graduated with a CGPA of 9.10/10. My graduate studies deepened my expertise in cybersecurity, applied cryptography, network security, autonomous mobile robotics, image processing, and computer vision. Throughout the program, I completed hands-on projects that strengthened my skills in Python, C#, and machine learning applications. I was also honored with the Mabel Jean and Bob Lye Memorial Award (2024–2025) for academic excellence.
Beyond academics, I actively participated in university clubs and technical initiatives that built my teamwork, leadership, and problem-solving skills.
Outside of my professional and academic life, I enjoy reading thriller books, watching action-thriller movies and TV series, exploring new technologies, and playing football and video games.
Apr 2025
Graduation: Successfully completed my M.Sc. in Computational Sciences at Laurentian University with a CGPA of 9.10/10.
Award: Received the Mabel Jean and Bob Lye Memorial Award (2024–2025) for academic excellence.
Sept 2023
Online Presentation : On Sept 5th 2023 I along with my team mates succesfully presented our research paper "Accurate Prediction of Pulmonary Fibrosis Progression Using EfficientNet and Quantile Regression: A High Performing Approach" in TENSYMP 2023 which as held in Canberra, Australia.
Masters Study: On Sept 6th I started my Masters in Computational Sciences at Laurentian University.
Our paper can be found online at "Accurate Prediction of Pulmonary Fibrosis Progression Using EfficientNet and Quantile Regression: A High Performing Approach".
June 2023
Paper accepted: 2023 IEEE Region 10 Symposium (TENSYMP) “Accurate Prediction of Pulmonary Fibrosis Progression Using EfficientNet and Quantile Regression: A High Performing Approach”.
