mdhabibi/LIME-for-Time-Series
LIME for TimeSeries enhances AI transparency by providing LIME-based interpretability tools for time series models. It offers insights into model predictions, fostering trust and understanding in complex AI systems.
This tool helps healthcare professionals and researchers understand why an AI model classifies an electrocardiogram (ECG) as normal or abnormal. You input ECG signals, and it shows you which specific segments of the ECG signal were most influential in the model's diagnosis. It's designed for medical practitioners and researchers who need to trust and verify AI predictions for cardiac conditions.
No commits in the last 6 months.
Use this if you need to know exactly which parts of an ECG signal led an AI model to a particular cardiovascular diagnosis, enhancing trust and clinical adoption.
Not ideal if you are looking for a tool to train a new ECG classification model from scratch without needing to interpret its internal workings.
Stars
15
Forks
3
Language
Jupyter Notebook
License
GPL-3.0
Last pushed
Mar 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mdhabibi/LIME-for-Time-Series"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...