YutoTerashima

YutoTerashima / hms-harmful-brain-activity-classification

Public

Kaggle Silver Medal solution archive for HMS harmful brain activity EEG classification.

deep-learning eeg kaggle medical-ai pytorch
29
0
100% credibility
Found May 04, 2026 at 27 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Jupyter Notebook
AI Summary

Reproducible archive of a Kaggle Silver Medal solution that classifies harmful brain activity patterns like seizures from EEG data using blended image and waveform analysis models.

How It Works

1
🔍 Discover the Prize-Winning Project

You stumble upon this GitHub collection celebrating a Silver Medal win for spotting dangerous brain patterns in hospital EEG scans.

2
📦 Prepare Your Workspace

You easily set up the tools on your computer so everything runs smoothly without hassle.

3
📥 Gather Brain Scan Data

You bring in the special EEG recordings from the competition after accepting the patient privacy rules.

4
Pick Quick Peek or Deep Dive
🚀
Quick Test

See sample predictions right away to feel the magic.

🎓
Full Training

Let three smart pattern-spotters learn from the scans.

5
🧠 Models Spot Hidden Patterns

Watch as the tools transform wavy brain signals into clear pictures of risks like seizures.

6
🔗 Mix the Best Guesses

Combine smart outputs from different views for super-reliable results.

🏆 Celebrate Your Insights

Enjoy ready reports, predictions, and the full story of top-tier brain analysis success.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 27 to 29 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is hms-harmful-brain-activity-classification?

This GitHub repo archives a Kaggle silver medal solution for the HMS harmful brain activity classification challenge, tackling EEG classification of harmful brain patterns like seizures and generalized periodic discharges in hospital patients. Developers get a Python package with PyTorch models blending spectrogram CNNs and raw EEG sequence models into calibrated predictions for the six-class problem. Install via pip, download Kaggle datasets through CLI scripts, run smoke tests on CPU, or train full ensembles on GPU for reproducible results matching the 123rd-place leaderboard score.

Why is it gaining traction?

It stands out as a polished kaggle github repo beyond raw notebooks, offering editable YAML configs, CLI entrypoints for training individual models or blending submissions, and auto-generated reports on CV folds and sanity checks. The smoke mode lets you validate pipelines instantly without Kaggle login or datasets, ideal for quick kaggle github clone reviews. With kaggle github integration via API downloads and pytest coverage, it bridges competition hacks to production-ready baselines faster than typical bronze silver gold medal dumps.

Who should use this?

Kaggle competitors dissecting top EEG solutions for hms-harmful-brain-activity-classification kaggle baselines. Neuro ML researchers needing reproducible brain activity classification pipelines with raw EEG and spectrogram handling. Devs building kaggle github datasets workflows or prototyping medical AI with PyTorch on hospital-grade eeg data.

Verdict

Grab it if you're into Kaggle silver medal archives—docs, configs, and tests are solid for reproduction, despite 18 stars and 1.0% credibility score signaling early maturity. Low adoption means watch for community forks, but it's a constructive starting point for EEG classification extensions.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.