# Detecting Unseen Falls from Wearable Devices using Channel-wise Ensemble of Autoencoders

arXiv: https://arxiv.org/abs/1610.03761 · HTML: https://mlsanity.com/paper/1610.03761/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2016.

## Built on by (most cited first, 5 of 5)

- [Cross-domain Activity Recognition via Substructural Optimal Transport](https://mlsanity.com/paper/2102.03353/) (2021)
- [Machine Learning for the Detection and Identification of Internet of Things (IoT) Devices: A Survey](https://mlsanity.com/paper/2101.10181/) (2021)
- [Detecting Disengagement in Virtual Learning as an Anomaly using Temporal Convolutional Network Autoencoder](https://mlsanity.com/paper/2211.06870/) (2022)
- [MAISON -- Multimodal AI-based Sensor platform for Older Individuals](https://mlsanity.com/paper/2211.03615/) (2022)
- [Triple Spectral Fusion for Sensor-based Human Activity Recognition](https://mlsanity.com/paper/2605.02743/) (2026)

## Abstract (arXiv)

A fall is an abnormal activity that occurs rarely, so it is hard to collect real data for falls. It is, therefore, difficult to use supervised learning methods to automatically detect falls. Another challenge in using machine learning methods to automatically detect falls is the choice of engineered features. In this paper, we propose to use an ensemble of autoencoders to extract features from different channels of wearable sensor data trained only on normal activities. We show that the traditional approach of choosing a threshold as the maximum of the reconstruction error on the training normal data is not the right way to identify unseen falls. We propose two methods for automatic tightening of reconstruction error from only the normal activities for better identification of unseen falls. We present our results on two activity recognition datasets and show the efficacy of our proposed method against traditional autoencoder models and two standard one-class classification methods.