Efficient Deep Clustering of Human Activities and How to Improve Evaluation

by   Louis Mahon, et al.

There has been much recent research on human activity re­cog­ni­tion (HAR), due to the proliferation of wearable sensors in watches and phones, and the advances of deep learning methods, which avoid the need to manually extract features from raw sensor signals. A significant disadvantage of deep learning applied to HAR is the need for manually labelled training data, which is especially difficult to obtain for HAR datasets. Progress is starting to be made in the unsupervised setting, in the form of deep HAR clustering models, which can assign labels to data without having been given any labels to train on, but there are problems with evaluating deep HAR clustering models, which makes assessing the field and devising new methods difficult. In this paper, we highlight several distinct problems with how deep HAR clustering models are evaluated, describing these problems in detail and conducting careful experiments to explicate the effect that they can have on results. We then discuss solutions to these problems, and suggest standard evaluation settings for future deep HAR clustering models. Additionally, we present a new deep clustering model for HAR. When tested under our proposed settings, our model performs better than (or on par with) existing models, while also being more efficient and better able to scale to more complex datasets by avoiding the need for an autoencoder.


page 1

page 2

page 3

page 4


Unsupervised Deep Learning-based clustering for Human Activity Recognition

One of the main problems in applying deep learning techniques to recogni...

Unsupervised Embedding Learning for Human Activity Recognition Using Wearable Sensor Data

The embedded sensors in widely used smartphones and other wearable devic...

Clustering with Deep Learning: Taxonomy and New Methods

Clustering is a fundamental machine learning method. The quality of its ...

Towards Deep Clustering of Human Activities from Wearables

Our ability to exploit low-cost wearable sensing modalities for critical...

A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions

Clustering is a fundamental machine learning task which has been widely ...

Improving Deep Image Clustering With Spatial Transformer Layers

Image clustering is an important but challenging task in machine learnin...

Deep learning based Auto Tuning for Database Management System

The management of database system configurations is a challenging task, ...

Please sign up or login with your details

Forgot password? Click here to reset