A passionate technologist with expertise in artificial intelligence, machine learning, and cybersecurity. Building intelligent systems that solve real-world problems while maintaining the highest security standards. My journey spans from developing complex ML algorithms to implementing robust cybersecurity solutions.
Currently pursuing advanced studies in cybersecurity with focus on digital forensics, network security, and ethical hacking. Serving as a Research Assistant while completing coursework.
Graduated with focus on artificial intelligence, machine learning, and software development. Participated in numerous hackathons and served as Course Instructor at Computer and Programming Club (CPC).
Completed HSC with excellence in mathematics, physics, and chemistry.
Completed SSC with distinction in science subjects, laying the foundation for future technical pursuits.
Conducting research in cybersecurity and AI integration, focusing on developing secure ML systems and exploring advanced threat detection mechanisms using artificial intelligence.
Developed custom learning solutions for clients across various industries. Projects ranged from image classification systems to predictive analytics platforms and recommendation engines.
International Conference on Computer Communication and Informatics systems
This research introduces a novel neural network architecture optimized for detecting data with minimal computational overhead.
View PublicationEuropean Chemical Bulletin
Presented a hybrid deep learning methodology combining CNN and LSTM networks to identify sophisticated images with 99.99% accuracy, surpassing traditional detection methods.
View PublicationJournal of Emerging Technologies and Innovative Research
We have used some algorithm that are VGG16 with 96% accuracy and VGG19 with 97% accuracy. Here we have taken 200 pictures of each leaf of the medicinal plant from different angles. And with the help of these algorithm, we have determined different parameters including height, weight, size, and color of leaves. Then we trained in the deep learning algorithms. After training with some algorithms, our best accuracy is 99% with ResNet50 algorithm. If we can apply this model through our mobile app or web, then everyone will be able to understand by scanning the leaves of the tree through it, which medicinal plant it is.
View PublicationSSRN 4671018
This study introduces a comprehensive dataset tailored for the precise identification of medicinal plant leaves. The dataset encompasses diverse species, capturing variations in leaf morphology, texture, and color. Collected through rigorous curation, the dataset serves as a valuable resource for training and evaluating computer vision-based deep learning models aimed at accurate medicinal plant recognition. Leveraging advanced image processing techniques, this dataset facilitates the development of robust algorithms crucial for automating the identification of medicinal plants based on their leaves. The dataset's richness and diversity make it a cornerstone for enhancing the reliability and efficiency of medicinal plant identification systems, thereby contributing to advancements in botanical research and healthcare. This dataset includes 11040 leaf images (original 1380, augmented 9660) of medicinal plants encompassing six different medicinal plant classes (Arjun Leaf, Curry Leaf, Marsh Pennywort Leaf, Mint Leaf, Neem Leaf, and Rubble Leaf), collected from June 10 to November 20, 2023, in a real nursery. This dataset, hosted by Daffodil International University's Department of Computer Science and Engineering, is publicly available at https://data. mendeley. com/datasets/fj93rrfv2y/2.
View PublicationAI-based forensic image authenticity detection tool using zero-shot CLIP embeddings combined with forensic-level features to distinguish between real and AI-generated images.
Multipurpose AI generation platform capable of producing high-quality images, structured PDFs, and formatted DOC files from textual prompts using state-of-the-art AI models.
A Django middleware plugin that restricts login attempts based on IP addresses to enhance admin security and reduce brute-force attacks on web applications.
Social platform for IELTS learners featuring Facebook-style timeline, test analytics, and smart community system tailored for language test preparation.
Speech-enabled AI assistant built with Python, capable of executing tasks like opening apps, fetching information, and processing complex voice commands.
Smart system that predicts the probability of dengue fever based on user inputs by merging Django's web capabilities with backend ML classifiers.
Computer and Programming Club (CPC)
Led specialized workshops on machine learning, Python programming, and web development. Mentored junior students on project development and competitive programming techniques.
Multiple National & International Events
Participated in and won awards at several hackathons, developing innovative solutions under time constraints and collaborating with diverse teams.
Various GitHub Projects
Actively contributed to open-source projects related to AI/ML, cybersecurity tools, and Python libraries, helping improve documentation and adding new features.
Personal Blog & Medium
Published technical articles on AI/ML implementation, cybersecurity best practices, and software development tutorials to share knowledge with the broader community.