In this paper, a new algorithm denoted as FilterK is proposed for improving the purity of k-means derived physical activity clusters by reducing outlier influence. We applied it to physical activity data obtained with body-worn accelerometers and clustered using k-means. We compared its performance with three existing outlier detection methods: Local Outlier Factor, Isolation Forests and KNN using the ground truth (class labels), average cluster and event purity (ACEP). FilterK provided comparable gains in ACEP (0.581→0.596 compared to 0.580-0.617) whilst removing a lower number of outliers than the other methods (4% total dataset size vs 10% to achieve this ACEP). The main focus of our new outlier detection method is to improve the cluster purities of physical activity accelerometer data, but we also suggest it may be potentially applied to other types of dataset captured by k-means clustering. We demonstrate our method using a k-means model trained on two independent accelerometer datasets (training n=90) and re-applied to an independent dataset (test n=41). Labelled physical activities include lying down, sitting, standing, household chores, walking (laboratory and non-laboratory based), stairs and running. This type of clustering algorithm could be used to assist with identifying optimal physical activity patterns for health.Copyright © 2020 Elsevier Inc. All rights reserved.
Novel benzoate-lipophilic cations selectively induce cell death in human colorectal cancer cell lines.
March 2, 2020
November 6, 2019
September 17, 2020
- ACC 2020The American College of Cardiology decided to cancel ACC.20/WCC due to COVID-19, which was scheduled to take place March 28-30 in Chicago. However, ACC.20/WCC Virtual Meeting continues to release cutting edge science and practice changing updates for cardiovascular professionals on demand and free through June 2020.
- ENDO: 2020ENDO 2020 Annual Conference has been canceled due to COVID-19. Here are highlights of emerging data that has still been released. Keep an eye out for ENDO Online 2020, which will take place from June 8 to 22.