I’m a Computer Science Engineering student at Maharaja Surajmal Institute of Technology, Delhi. I build practical machine-learning and automation projects, with particular interest in deep learning, audio signal processing, medical imaging, and API-driven workflows.
- Deep learning: Python, TensorFlow/Keras, PyTorch, Scikit-learn, NumPy, and Pandas
- Audio ML: log-mel spectrograms, CNNs, Bi-GRU models, attention, and pretrained audio encoders
- Automation: n8n, VAPI, Telegram Bot API, Twitter/X API, and REST APIs
An end-to-end TensorFlow/Keras project for binary classification of brain MRI images. It includes data preprocessing, CNN training, evaluation scripts, single-image prediction, and a Gradio demo.
A bioacoustics pipeline for identifying mosquito species from raw .wav audio, combining log-mel spectrogram CNNs, Bi-GRU attention, and pretrained audio embeddings.
An n8n, VAPI, Python, and REST API workflow for creating and confirming events through voice-based interaction.
A Python bot that listens for Telegram messages and publishes them to Twitter/X, including authentication, media handling, and retry logic.
| Area | Technologies |
|---|---|
| Languages | Python, Java |
| ML / DL | TensorFlow, Keras, PyTorch, Scikit-learn, NumPy, Pandas, Librosa, OpenCV |
| Automation & APIs | n8n, VAPI, Telegram Bot API, Twitter/X API, REST APIs |
| Development | Git, GitHub, Google Colab, Jupyter Notebook |
- Email: adityasushilgupta04@gmail.com
- LinkedIn: linkedin.com/in/aditya-gp