Skip to content
View AayushAswal27's full-sized avatar

Block or report AayushAswal27

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. wattparse wattparse Public

    Splits a building's single electricity meter into per-appliance traces with a seq2point CNN, then flags equipment that ran outside occupancy hours and prices it. Cross-house validated on UK-DALE.

    Python

  2. wind-turbine-predictive-maintenance wind-turbine-predictive-maintenance Public

    Predicts wind turbine failures on real SCADA data (~1.2M rows, 12 fault events). LightGBM + Isolation Forest + LOF fused into a risk score — full fault coverage on unseen turbines, SHAP-explained.

    Jupyter Notebook

  3. AisleGuard AisleGuard Public

    Warehouse safety AI that predicts forklift-pedestrian collisions before they happen. YOLOv11 → BoT-SORT → homography → custom-trained CNN (93% acc, Grad-CAM validated). Streamlit demo.

    Jupyter Notebook

  4. multilingual-rag multilingual-rag Public

    Cross-lingual RAG system for document Q&A in English, Hindi, Bengali & Tamil. Built with LangChain, FAISS, Llama 3.3 70B (Groq) & Streamlit.

    Python

  5. genai-agentic-lab genai-agentic-lab Public

    Building GenAI and agentic systems from scratch — raw implementations before frameworks. Hugging Face → RAG → LLM apps → fine-tuning → agents/LangGraph.

    Jupyter Notebook

  6. pytorch-from-scratch pytorch-from-scratch Public

    Deep learning in PyTorch, notebook by notebook — from tensors and autograd to CNNs, RNNs, LSTMs, transfer learning, and Optuna tuning.

    Jupyter Notebook