About Me

I am an enthusiastic and adaptable individual with a strong foundation in Artificial Intelligence, Machine Learning, and Full Stack Development. Passionate about solving real-world problems through technology, I enjoy combining creativity with analytical thinking to deliver impactful solutions. My experience spans building intelligent systems, designing user-friendly interfaces, and optimizing backend processes for efficiency. I am a quick learner who thrives in collaborative environments, embracing challenges as opportunities to grow. With a commitment to continuous learning, I aim to contribute to innovative projects that create meaningful value.

Projects

Sentiment Analysis

The Sarcasm Analysis project focuses on detecting sarcastic intent in text using advanced Natural Language Processing techniques.
It leverages deep learning models to capture subtle linguistic cues and contextual meanings behind words.
The system is trained on labeled datasets containing both sarcastic and non-sarcastic sentences.
Preprocessing steps include tokenization, stopword removal, and embedding generation for better feature representation.
Our model applies attention mechanisms to understand context dependencies effectively.
Evaluation is performed using metrics like accuracy, precision, recall, and F1-score.
The project aims to improve sentiment analysis systems by handling sarcasm more accurately.
It can be integrated into chatbots, social media monitoring tools, and customer feedback analysis systems.

Crop Pest Disease Classification

The Crop Pest Disease Classification project aims to identify pest-induced crop diseases from plant images using deep learning.
It utilizes a custom ResNet18_KAN model to capture both visual and structural features effectively.
The dataset includes multi-class images of crops affected by various pests and diseases.
Preprocessing involves image resizing, normalization, and data augmentation to improve model generalization.
Feature extraction is optimized through hybrid convolutional and Kolmogorov-Arnold Network layers.
Performance is evaluated using accuracy, F1-score, and confusion matrix analysis.
The system provides fast, accurate disease identification to assist farmers and agricultural experts.
It can be integrated into mobile and IoT-based smart farming solutions for real-time detection.

University school of Automation and Robotics	B.tech in AIML	2025
Mount Olivet Sr. Sec. School	12th (Science)	2021

About Me

Education

Projects

Sentiment Analysis

Crop Pest Disease Classification

Contact Us