Raju Talukder
Raju Talukder's blog
Cyber Security Researcher.
Daffodil International University
Software Engineering
2017 - 2021
B.S.C. in Software Engineering Major in CyberSecurity
Introduction to software, Computer Fundamentals, (C, JAVA, PHP, C#) Programming, Mathematics, Statistics & Probabilities, Computer Architecture & Organization, Cybersecurity fundamental, System Security, Cryptography & Secure application, Ethical Hacking & Countermeasures, Security analysis and Penetration testing, Information security & Risk Management, Information system audit & assurance, Digital Forensics, Cyber Laws & Ethics in cybersecurity, and so on.
Advanced Cyber Security Engineer
ITCOM (Philippines)
July 2023 – Present
Job Responsibilities:
Engineer Security Operations
Enterprise Infosec Consultants (EIC), Dhaka, Bangladesh
Oct 2022 - Jun 2023
Job Responsibilities:
Junior Research Fellow
Cyber Security Centre, Daffodil International University, Dhaka, Bangladesh
Sep 2020 - Oct 2022
Job Responsibilities:
Certified Ethical Hacker
EC-Council
2021
A Certified Ethical Hacker is a skilled professional who understands and knows how to look for weaknesses and vulnerabilities in target systems and uses the same knowledge and tools as a malicious hacker, but in a lawful and legitimate manner to assess the security posture of a target system(s).
Car Make and Model Recognition using CNN: Fine-Tune AlexNet Architecture
Indonesian Journal of Electrical Engineering and Computer Science
# ISSN: 2502-4752
January 12, 2024
Artificial intelligence (AI) has significantly contributed to car make and model recognition in this current era of intelligent technology. By using AI, it is much easier to identify car models from any picture or video. This paper introduces a new model by fine-tuning the AlexNet architecture to determine the car model from images. First of all, our car image dataset has been created. Some of these images were taken by us, and others were taken from the website of The Car Connection. Then we cleaned all the unwanted images for better performance. Our dataset has ten classes containing 5000 car images split into train and test data. After that, we augmented our data with random flip, rotation, and zoom to reduce overfitting. Finally, we used a pre-trained CNN model AlexNet architecture. We fine-tuned AlexNet by adding three extra layers for better classification and compared it with the original AlexNet. To measure the performance of these models, accuracy, precision, recall, and f1-score were used. The results show that fine-tune AlexNet architecture outperforms the original AlexNet architecture. The results prove that recognition accuracy has increased due to our improvement approach.