Format

Send to

Choose Destination
Sensors (Basel). 2019 Jan 25;19(3). pii: E501. doi: 10.3390/s19030501.

A Semi-Automatic Annotation Approach for Human Activity Recognition.

Author information

1
Associação Fraunhofer Portugal Research, Rua Alfredo Allen 455/461, 4200-135 Porto, Portugal. p.bota@campus.fct.unl.pt.
2
Associação Fraunhofer Portugal Research, Rua Alfredo Allen 455/461, 4200-135 Porto, Portugal. joana.silva@fraunhofer.pt.
3
Associação Fraunhofer Portugal Research, Rua Alfredo Allen 455/461, 4200-135 Porto, Portugal. duarte.folgado@fraunhofer.pt.
4
Associação Fraunhofer Portugal Research, Rua Alfredo Allen 455/461, 4200-135 Porto, Portugal. hugo.gamboa@fraunhofer.pt.
5
Laboratório de Instrumentação, Engenharia Biomédica e Física da Radiação (LIBPhys-UNL), Departamento de Física, Faculdade de Ciências e Tecnologia, FCT, Universidade Nova de Lisboa, 2829-516 Caparica, Portugal. hugo.gamboa@fraunhofer.pt.

Abstract

Modern smartphones and wearables often contain multiple embedded sensors which generate significant amounts of data. This information can be used for body monitoring-based areas such as healthcare, indoor location, user-adaptive recommendations and transportation. The development of Human Activity Recognition (HAR) algorithms involves the collection of a large amount of labelled data which should be annotated by an expert. However, the data annotation process on large datasets is expensive, time consuming and difficult to obtain. The development of a HAR approach which requires low annotation effort and still maintains adequate performance is a relevant challenge. We introduce a Semi-Supervised Active Learning (SSAL) based on Self-Training (ST) approach for Human Activity Recognition to partially automate the annotation process, reducing the annotation effort and the required volume of annotated data to obtain a high performance classifier. Our approach uses a criterion to select the most relevant samples for annotation by the expert and propagate their label to the most confident samples. We present a comprehensive study comparing supervised and unsupervised methods with our approach on two datasets composed of daily living activities. The results showed that it is possible to reduce the required annotated data by more than 89% while still maintaining an accurate model performance.

KEYWORDS:

active learning; human activity recognition; machine learning; self-training; semi-supervised learning; time series

PMID:
30691040
PMCID:
PMC6387461
DOI:
10.3390/s19030501
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center