boniolp/dCAM

[SIGMOD 2022] Python code for "Dimension-wise Class Activation Map for Multivariate Time Series Classification"

32
/ 100
Emerging

This project helps data scientists and researchers understand why their machine learning models classify multivariate time series data the way they do. It takes multivariate time series data and a trained classification model as input, then produces a "Dimension-wise Class Activation Map" (dCAM). This map highlights the specific time points and data dimensions that most influenced the model's decision, making complex classifications more transparent.

No commits in the last 6 months.

Use this if you need to explain the decisions of a convolutional neural network (CNN) or similar model classifying multivariate time series, pinpointing exactly which parts of the data drove a particular classification.

Not ideal if your data is not time-series based, or if you are looking for explanations for models other than those commonly used for time series classification (like CNNs).

time-series-analysis explainable-ai predictive-modeling pattern-recognition data-interpretation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

19

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/boniolp/dCAM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.