Regarding enhancement and contribution to the Human Activity Recognition Project

[Akshat-Rastogi-6]

Hello @bhimmetoglu,

I hope this message finds you well. My name is Akshat Rastogi, and I’ve been working with the dataset from your project. I wanted to share that I’ve achieved results that outperform those currently mentioned in the repository.

Initially, I developed an LGBM model with hyperparameter tuning, which yielded a test accuracy of 95.21%. However, since this was still slightly lower than the XGBoost model, I explored deep learning approaches. After experimenting with several architectures, I was able to build a deep learning model that achieved an accuracy of 95.56%, surpassing the performance of the CNN model you implemented.

As an enthusiastic machine learning practitioner, I would love to contribute to your project. I have the complete code ready and would be happy to share it or collaborate further. Kindly consider my request for involvement in this exciting work.

Thank you for your time, and I look forward to your response.

Best regards,
Akshat Rastogi
Machine Learning Enthusiast