VivaKitHuman Activity Recognition from Phone Sensors
Walking, jogging, stairs, sitting, standing or kicking, recognised from 10 seconds of a smartphone's accelerometer and gyroscope (WISDM dataset, 51 people). One model uses hand-crafted features with logistic regression; the other is a 1D CNN (PyTorch) that reads the raw signals. Both are tested on people they have never seen. The demo plots each signal next to its prediction.
Secure checkout by Dodo Payments (UPI, cards). Your personalised download link is e-mailed within 24 hours. One purchase covers one project team of up to 4 students. See terms and refunds.
Our honest results
| 1D CNN macro-F1 - 10 unseen people (2,006 windows) | 0.939 |
| Logistic regression macro-F1 - same people | 0.920 |
| CNN sitting recall (most sitting errors called "standing") | 0.803 |
| Logistic regression, random window split vs split by person | 0.966 vs 0.898 |
Shuffle the windows instead of the people, and every model looks 3-7 points better than it really is. The guide shows why, and why almost all of the CNN's sitting mistakes come from two people. Trains in about 1.5 min on a laptop CPU, so no GPU is needed.
What's included
- Readable source codeSmall, commented modules you can explain line by line in your viva.
- Demo appA local web app to show your examiners - runs offline on your laptop.
- Trained model + reference resultsSo you can compare your own runs fairly.
- Learning guide with viva Q&ABackground, design choices explained, limitations and extension ideas.
- One-click setup & testsWindows setup script and tests that prove it works on your PC.
- Dataset download scriptFetches the public data from its original source, with the citation.
Dataset credit
Weiss, G. (2019). WISDM Smartphone and Smartwatch Activity and Biometrics Dataset [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5HK59 - Creative Commons Attribution 4.0 International
Academic integrity
We sell code and teaching, not finished projects. You must understand, extend and write up the work yourself, acknowledge the kit and cite the dataset. No ready-made reports.