Comparing Sampling Strategies for Tackling Imbalanced Data in Human Activity Recognition

Alharbi, Fayez; Ouarbya, Lahcen and Ward, Jamie A. 2022. Comparing Sampling Strategies for Tackling Imbalanced Data in Human Activity Recognition. Sensors, 22(4), 1373. ISSN 1424-8220 [Article]

[img]
Preview
Text
sensors-22-01373.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview

Abstract or Description

Human activity recognition (HAR) using wearable sensors is an increasingly active research topic in machine learning, aided in part by the ready availability of detailed motion capture data from smartphones, fitness trackers, and smartwatches. The goal of HAR is to use such devices to assist users in their daily lives in application areas such as healthcare, physical therapy, and fitness. One of the main challenges for HAR, particularly when using supervised learning methods, is obtaining balanced data for algorithm optimisation and testing. As people perform some activities more than others (e.g., walk more than run), HAR datasets are typically imbalanced. The lack of dataset representation from minority classes hinders the ability of HAR classifiers to sufficiently capture new instances of those activities. We introduce three novel hybrid sampling strategies to generate more diverse synthetic samples to overcome the class imbalance problem. The first strategy, which we call the distance-based method (DBM), combines Synthetic Minority Oversampling Techniques (SMOTE) with Random_SMOTE, both of which are built around the k-nearest neighbors (KNN). The second technique, referred to as the noise detection-based method (NDBM), combines SMOTE Tomek links (SMOTE_Tomeklinks) and the modified synthetic minority oversampling technique (MSMOTE). The third approach, which we call the cluster-based method (CBM), combines Cluster-Based Synthetic Oversampling (CBSO) and Proximity Weighted Synthetic Oversampling Technique (ProWSyn). We compare the performance of the proposed hybrid methods to the individual constituent methods and baseline using accelerometer data from three commonly used benchmark datasets. We show that DBM, NDBM, and CBM reduce the impact of class imbalance and enhance F1 scores by a range of 9–20 percentage point compared to their constituent sampling methods. CBM performs significantly better than the others under a Friedman test, however, DBM has lower computational requirements.

Item Type:

Article

Identification Number (DOI):

https://doi.org/10.3390/s22041373

Additional Information:

Jamie A. Ward is funded by a Leverhulme supported APEX award from The British Academy, Royal Academy of Engineering and Royal Society (R156910)

Keywords:

activity recognition; wearable sensors; imbalanced activities; sampling methods

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
27 January 2022Accepted
11 February 2022Published

Item ID:

31457

Date Deposited:

11 Feb 2022 16:39

Last Modified:

11 Feb 2022 16:40

Peer Reviewed:

Yes, this version has been peer-reviewed.

URI:

https://research.gold.ac.uk/id/eprint/31457

View statistics for this item...

Edit Record Edit Record (login required)