B.Tech CSE · AI/ML Researcher · Patent Holder · Multi-Conference Author & Presenter
Undergraduate researcher at Birla Institute of Technology, Mesra (Ranchi), specialising in deep learning, computer vision, and TinyML for edge deployment. As a lead author and presenter, I have published datasets on IEEE DataPort and Mendeley Data, hold an Indian patent, authored papers at WCAIAA 2026 (NFSU Goa) and MIND 2025, co-authored a CRC Press book chapter (under Taylor & Francis journal review), and am currently working on a real-time deep-vision sports analytics system — all as an undergraduate.
| Institution | BIT Mesra, Ranchi, India |
| Department | Computer Science & Engineering |
| Degree | B.Tech (CSE) — Undergraduate |
| Nationality | Indian |
| Languages | Hindi · English · German |
| ORCID | 0009-0005-7308-6401 |
Assistant Professor, Dept. of CSE
Birla Institute of Technology, Mesra (Jaipur Extension)
PhD (CSE) from MNIT Jaipur · 8 years teaching experience · Research areas: Blockchain Technology, IoT Security, Information Security & Cyber Forensics · IEEE & IEEE Computer Society Member · PI on Seed Money project on Blockchain-based Academic Credentials
Founder & Director, MaxBrain Technologies
Durgapura, Rajasthan, India
IT professional specialising in web development, digital marketing, and software engineering consultancy. Founded MaxBrain Technologies (est. April 2018), serving clients across WordPress development, eCommerce, and digital marketing strategies.
Building CNN and transformer-based architectures for real-world image classification — including agricultural disease detection from leaf imagery, with a publicly released dataset on IEEE DataPort.
Designing lightweight, optimised deep learning models deployable on resource-constrained microcontrollers (Arduino, ESP32). Research published at WCAIAA 2026 (NFSU Goa) by SCRS.
Exploring the mathematical foundations of ML — loss landscape geometry, weight pruning, knowledge distillation, INT8 quantisation, and out-of-distribution generalisation strategies.
Data-driven decision modelling for algorithmic and high-frequency trading — statistical signal generation, backtesting frameworks, and risk-adjusted performance analysis.
🏛️ Presented at WCAIAA 2026 · National Forensic Sciences University, Goa · Conference proceedings link to be added once published
🏛️ Main author & presenter · MIND 2025 Conference
📖 Main author · Currently under peer review · Link will be updated upon acceptance
🔗 Main author · Link to be updated shortly
📖 Main author · Link to be updated upon publication
Lightweight deep learning models (MobileNet1D, CNN+BiLSTM) for real-time HAR on smartphones and microcontrollers. MobileNet1D achieved 92.77% accuracy; quantised to ~1.4 MB with <100ms inference latency and <50mW power on Arduino/ESP32. Research resulted in a paper presented at WCAIAA 2026 (NFSU Goa).
End-to-end deep learning pipeline classifying ridge gourd leaves as Healthy, Leaf Minor Infested, or Mosaic Virus infected. A dataset of 9,000 preprocessed images was collected, augmented, and published publicly on IEEE DataPort for the global research community.
Deep learning model for automated fruit classification using convolutional neural networks. Explores preprocessing, augmentation strategies, and transfer learning to achieve robust classification across multiple fruit categories.
A fully functional Spotify-inspired music streaming UI built as part of a web development project collection. Features a responsive player interface, playlist management UI, and music browsing layout closely mirroring the original Spotify experience.
Currently building a production-grade computer vision system for real-time football match analysis. The system performs multi-object tracking of players and the ball, computes live possession statistics, generates tactical heat maps, and reconstructs a 2D top-down tactical view from broadcast footage — all in real time using YOLO-based detection pipelines.
Research work featured in Punjab Kesari, one of India's leading Hindi-language newspapers — recognising the contribution to agricultural AI research as an undergraduate student.
View Clipping →Research paper on TinyML-based Human Activity Recognition presented at the World Conference on AI Applications and Advancements (WCAIAA 2026) organised by SCRS at the National Forensic Sciences University, Goa.
View Project →Agricultural leaf disease dataset (9,000 images, 3 classes) published and made freely available on IEEE DataPort, contributing open-access resources to the global AI research community.
View Dataset →Indian patent granted for an AI-assisted method for agricultural leaf disease detection and classification — a notable achievement for an undergraduate researcher in India.
View Patent →Main author and presenter at the MIND 2025 conference for research on agricultural leaf disease detection. Represented the work before an academic audience and contributed to proceedings.
View Paper →Main author of a book chapter published through CRC Press, currently under review for a Taylor & Francis journal — an exceptional output for an undergraduate researcher.
View Publication →Main author of a publicly available Brinjal (Eggplant) leaf disease image dataset on Mendeley Data, with an accompanying Data in Brief paper currently under review at Elsevier.
Mendeley Dataset →I'm open to research collaborations, internship opportunities, and connections with academics and industry professionals in AI/ML or quantitative finance.