Motion2Vector

Abstract

With the increasing popularity of consumer wearable devices augmented with sensing capabilities (smart bands, smart watches), there is a significant focus in extracting meaningful information about human behaviour through large scale real-world wearable sensor data. The focus of this work is to develop techniques to detect human activities, utilising a large datasets of wearable data where no ground truth has been produced on the actual activities performed. We propose a deep learning variational auto encoder activity recognition model-Motion2Vector. The model is trained using large

An Unsupervised Method to Recognise Human Activity at Home Using Non-Intrusive Sensors

“…The method was tested against a database generated during experimentation, with five wandering activities and an accuracy of 69% was obtained. In [85], the authors propose the use of an unsupervised method known as the variational autoencoder (VAE) [86]. This method takes care of compressing the input data vector into a representation vector and, in subsequent steps, decompressing it back into an output data vector with the same dimensions, thus exploiting the truly useful information in the input data [87].…”

Perspective Chapter: Recognition of Activities of Daily Living for Elderly People in the Era of Digital Health

“…All referenced datasets are labeled with activities. In recent years, datasets containing no prior labeling of the activities have been studied [13]. Interpreting and using such data imposes significant challenges in developing appropriate ADL recognition techniques.…”

ActivityExplorer: A semi-supervised approach to discover unknown activity classes in HAR systems

“…In this case Gaussian mixture models and clustering are used for unsupervised learning. Other sensing devices have also been explored, such as wearable wrist bands in Bai et al (2019), inertial ring and bracelet in Moschetti et al (2017) or other inertial sensors at different body parts in Trabelsi et al (2013). A combination of different environmental sensors, as well as information about interaction with objects are exploited by Riboni et al (2016) to derive semantic correlations among activities and sensor events.…”