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

10/12/2016
by   Shehroz S. Khan, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2015

Detecting Falls with X-Factor Hidden Markov Models

Identification of falls while performing normal activities of daily livi...
research
08/30/2018

DeepFall -- Non-invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders

Human falls rarely occur; however, detecting falls is very important fro...
research
05/09/2019

Wearable Sensor Data Based Human Activity Recognition using Machine Learning: A new approach

Recent years have witnessed the rapid development of human activity reco...
research
04/20/2023

Fruit Picker Activity Recognition with Wearable Sensors and Machine Learning

In this paper we present a novel application of detecting fruit picker a...
research
03/08/2022

Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition

Sensor-based human activity recognition (HAR) is a paramount technology ...
research
02/25/2023

A Preliminary Study on Pattern Reconstruction for Optimal Storage of Wearable Sensor Data

Efficient querying and retrieval of healthcare data is posing a critical...
research
08/24/2020

Unsupervised Multi-Modal Representation Learning for Affective Computing with Multi-Corpus Wearable Data

With recent developments in smart technologies, there has been a growing...

Please sign up or login with your details

Forgot password? Click here to reset