Himanshu Kumar Bhagat
AI/ML Engineer & Researcher | Crafting Real-World Solutions with Machine Learning & Generative AI | Passionate about LLMs & Deep Learning
About Me
I am a Computer Science and Engineering undergraduate at Chandigarh University, specializing in Artificial Intelligence and Machine Learning. I have a strong command of Python, SQL, and core concepts like data structures, algorithms, and database systems. My focus lies in applying AI to real-world challenges using techniques from large language models (LLMs), machine learning, deep learning, natural language processing, and computer vision.
Through my internship at AICAN Automate, I gained hands-on experience with real-world datasets, performing exploratory data analysis and delivering actionable insights using Python and visualization tools. Alongside this, I published research on hybrid deep learning approaches for rice leaf disease detection, demonstrating my ability to translate complex AI concepts into impactful applications. I also hold certifications in Microsoft Azure AI Fundamentals and Oracle Cloud Infrastructure Generative AI, which strengthen my academic foundation with exposure to real-world cloud-based AI systems. Constantly exploring innovative ways to leverage AI for impact, I am eager to contribute to forward-thinking, interdisciplinary teams.
Coding Language
Python, SQL
AI/ML
LLMs, Generative AI, Deep Learning, NLP, Computer Vision, Transformer, Training & Fine-Tuning, Prompt Engineering
Data Analysis & Business Intelligence
Pandas, Matplotlib, Numpy, Seaborn, Excel, Power BI(DAX, Data Modelling, Dashboards
Data Engineering
Pyspark, Azure Data Factory, Databricks
Featured Projects
A selection of projects that showcase my technical skills and problem-solving approach
MedInstructAI – Multilingual Medical Report Explainer
MedInstructAI is an intelligent voice and text-based assistant that helps users understand complex medical reports in simple, layman-friendly language. It can read reports from typed text, PDFs, or images and explain them clearly using a Large Language Model (LLM). The assistant supports multilingual responses, voice-based interaction, and alerts users about serious medical risks.
AI News Anchor – Automated News Video Generator
AI News Anchor is a fully autonomous system that fetches real-time news based on a user-given topic, generates human-like anchor scripts, converts them to realistic voiceovers, and produces complete news videos featuring a talking AI avatar with relevant B-roll visuals. This project showcases the power of generative AI in media automation and the future of AI-driven journalism.
AI Poetry Generator
AI Poetry Generator is a custom-built generative AI system that produces original poetry using a transformer-based language model. This project demonstrates the creation and fine-tuning of a GPT-2 architecture from scratch on a curated poetry dataset. Despite limited compute, the system achieves fluent and stylistically rich poetic generation, showcasing core understanding of language modeling and creative AI applications.
Rice Leaf Disease Detection – Hybrid Deep Learning Model
A high-accuracy deep learning system built to identify and classify rice leaf diseases using computer vision. This project combines a pretrained ResNet-50v2 model with a custom-connected neural network, trained on a large image dataset to support timely and precise agricultural diagnostics. It enables farmers and agronomists to detect crop diseases early, reducing crop loss and improving yield.
Sentiment Analysis Using VADER
A lightweight Natural Language Processing (NLP) project that analyzes the sentiment of user-generated text, such as customer reviews or social media comments. This system uses the VADER (Valence Aware Dictionary and sEntiment Reasoner) sentiment analysis model to classify text into positive, negative, or neutral sentiment. The project demonstrates real-world application of rule-based NLP in opinion mining and product feedback analysis.
Research Publications
Published academic research in AI and machine learning with real-world applications
Enhanced Rice Leaf Disease Detection: A Hybrid Deep Learning Approach
n International Journal of Scientific Research in Engineering and Management • 2025
This research proposes a hybrid deep learning model for automated rice leaf disease detection, addressing the limitations of traditional methods. A pre-trained ResNet50V2 CNN is combined with a custom fully connected network, enhanced with batch normalization, dropout, and L2 regularization. Trained on 15,023 images from nine disease classes and healthy leaves, the model utilizes extensive data augmentation techniques such as rotation, shifts, zoom, and flipping to improve robustness. The model achieved 99.53% accuracy, surpassing existing benchmarks, and provides a reliable system for timely disease detection, enhancing rice crop management and yield.
Let's Connect
I'm always interested in discussing new opportunities, collaborations, or just talking about technology