Dataset Information

Segmenting accelerometer data from daily life with unsupervised machine learning.

ABSTRACT:

Purpose

Accelerometers are increasingly used to obtain valuable descriptors of physical activity for health research. The cut-points approach to segment accelerometer data is widely used in physical activity research but requires resource expensive calibration studies and does not make it easy to explore the information that can be gained for a variety of raw data metrics. To address these limitations, we present a data-driven approach for segmenting and clustering the accelerometer data using unsupervised machine learning.

Methods

The data used came from five hundred fourteen-year-old participants from the Millennium cohort study who wore an accelerometer (GENEActiv) on their wrist on one weekday and one weekend day. A Hidden Semi-Markov Model (HSMM), configured to identify a maximum of ten behavioral states from five second averaged acceleration with and without addition of x, y, and z-angles, was used for segmenting and clustering of the data. A cut-points approach was used as comparison.

Results

Time spent in behavioral states with or without angle metrics constituted eight and five principal components to reach 95% explained variance, respectively; in comparison four components were identified with the cut-points approach. In the HSMM with acceleration and angle as input, the distributions for acceleration in the states showed similar groupings as the cut-points categories, while more variety was seen in the distribution of angles.

Conclusion

Our unsupervised classification approach learns a construct of human behavior based on the data it observes, without the need for resource expensive calibration studies, has the ability to combine multiple data metrics, and offers a higher dimensional description of physical behavior. States are interpretable from the distributions of observations and by their duration.

SUBMITTER: van Kuppevelt D

PROVIDER: S-EPMC6326431 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Segmenting accelerometer data from daily life with unsupervised machine learning.

van Kuppevelt Dafne D Heywood Joe J Hamer Mark M Sabia Séverine S Fitzsimons Emla E van Hees Vincent V

PloS one 20190109 1

<h4>Purpose</h4>Accelerometers are increasingly used to obtain valuable descriptors of physical activity for health research. The cut-points approach to segment accelerometer data is widely used in physical activity research but requires resource expensive calibration studies and does not make it easy to explore the information that can be gained for a variety of raw data metrics. To address these limitations, we present a data-driven approach for segmenting and clustering the accelerometer data ...[more]

PMID: 30625153

Similar Datasets

Project description:Physical activity levels are related through algorithms to the energetic demand, with no information regarding the integrity of the multiple physiological systems involved in the energetic supply. Longitudinal analysis of the oxygen uptake (V?o2) by wearable sensors in realistic settings might permit development of a practical tool for the study of the longitudinal aerobic system dynamics (i.e., V?o2 kinetics). This study evaluated aerobic system dynamics based on predicted V?o2 data obtained from wearable sensors during unsupervised activities of daily living (?ADL). Thirteen healthy men performed a laboratory-controlled moderate exercise protocol and were monitored for ?6 h/day for 4 days (?ADL data). Variables derived from hip accelerometer (ACCHIP), heart rate monitor, and respiratory bands during ?ADL were extracted and processed by a validated random forest regression model to predict V?o2. The aerobic system analysis was based on the frequency-domain analysis of ACCHIP and predicted V?o2 data obtained during ?ADL. Optimal samples for frequency domain analysis (constrained to ?0.01 Hz) were selected when ACCHIP was higher than 0.05 g at a given frequency (i.e., participants were active). The temporal characteristics of predicted V?o2 data during ?ADL correlated with the temporal characteristics of measured V?o2 data during laboratory-controlled protocol ([Formula: see text]?=?0.82, P < 0.001, n?=?13). In conclusion, aerobic system dynamics can be investigated during unsupervised activities of daily living by wearable sensors. Although speculative, these algorithms have the potential to be incorporated into wearable systems for early detection of changes in health status in realistic environments by detecting changes in aerobic response dynamics. NEW & NOTEWORTHY The early detection of subclinical aerobic system impairments might be indicative of impaired physiological reserves that impact the capacity for physical activity. This study is the first to use wearable sensors in unsupervised activities of daily living in combination with novel machine learning algorithms to investigate the aerobic system dynamics with the potential to contribute to models of functional health status and guide future individualized health care in the normal population.

Project description:Machine learning (ML) methods have great potential to transform chemical discovery by accelerating the exploration of chemical space and drawing scientific insights from data. However, modern chemical reaction ML models, such as those based on graph neural networks (GNNs), must be trained on a large amount of labelled data in order to avoid overfitting the data and thus possessing low accuracy and transferability. In this work, we propose a strategy to leverage unlabelled data to learn accurate ML models for small labelled chemical reaction data. We focus on an old and prominent problem-classifying reactions into distinct families-and build a GNN model for this task. We first pretrain the model on unlabelled reaction data using unsupervised contrastive learning and then fine-tune it on a small number of labelled reactions. The contrastive pretraining learns by making the representations of two augmented versions of a reaction similar to each other but distinct from other reactions. We propose chemically consistent reaction augmentation methods that protect the reaction center and find they are the key for the model to extract relevant information from unlabelled data to aid the reaction classification task. The transfer learned model outperforms a supervised model trained from scratch by a large margin. Further, it consistently performs better than models based on traditional rule-driven reaction fingerprints, which have long been the default choice for small datasets, as well as those based on reaction fingerprints derived from masked language modelling. In addition to reaction classification, the effectiveness of the strategy is tested on regression datasets; the learned GNN-based reaction fingerprints can also be used to navigate the chemical reaction space, which we demonstrate by querying for similar reactions. The strategy can be readily applied to other predictive reaction problems to uncover the power of unlabelled data for learning better models with a limited supply of labels.

Project description:IntroductionSchizophrenia and Major Depressive Disorder (MDD) are highly burdensome mental disorders, with significant cost to both individuals and society. Despite these disorders representing distinct clinical categories, they are each heterogenous in their symptom profiles, with considerable transdiagnostic features. Although movement and sleep abnormalities exist in both disorders, little is known of the precise nature of these changes longitudinally. Passively-collected longitudinal data from wearable sensors is well suited to characterize naturalistic features which may cross traditional diagnostic categories (e.g., highlighting behavioral markers not captured by self-report information).MethodsThe present analyses utilized raw minute-level actigraphy data from three diagnostic groups: individuals with schizophrenia (N = 23), individuals with depression (N = 22), and controls (N = 32), respectively, to interrogate naturalistic behavioral differences between groups. Subjects' week-long actigraphy data was processed without diagnostic labels via unsupervised machine learning clustering methods, in order to investigate the natural bounds of psychopathology. Further, actigraphic data was analyzed across time to determine timepoints influential in model outcomes.ResultsWe find distinct actigraphic phenotypes, which differ between diagnostic groups, suggesting that unsupervised clustering of naturalistic data aligns with existing diagnostic constructs. Further, we found statistically significant inter-group differences, with depressed persons showing the highest behavioral variability.LimitationsHowever, diagnostic group differences only consider biobehavioral trends captured by raw actigraphy information.ConclusionsPassively-collected movement information combined with unsupervised deep learning algorithms shows promise in identifying naturalistic phenotypes in individuals with mental health disorders, specifically in discriminating between MDD and schizophrenia.

Dataset Information

Segmenting accelerometer data from daily life with unsupervised machine learning.

Purpose

Methods

Results

Conclusion

Publications

Segmenting accelerometer data from daily life with unsupervised machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets