A multidevice and multimodal dataset for human energy expenditure estimation using wearable devices

In recent years, there has been a growing interest in using wearable devices for human energy expenditure (HEE) estimation. However, most of the existing datasets for HEE estimation are either single-device or single-modality. In this paper, we present a multidevice and multimodal dataset for HEE estimation using wearable devices. The dataset was collected from 10 subjects over a period of 7 days. Each subject wore four devices: two chest-mounted devices (one with an accelerometer and one with a heart rate sensor), a thigh-mounted device with an accelerometer, and a wrist-mounted device with a photoplethysmogram (PPG) sensor. The data from all four devices were synchronized and collected at 10 Hz. In addition, the subjects were also asked to perform four activities (walking, running, cycling, and sitting) at different speeds, intensities, and durations. The ground truth HEE for each activity was measured using the indirect calorimetry method.

The dataset consists of four files: (1) a README file that provides an overview of the dataset; (2) a file containing the raw data from all four devices; (3) a file containing the ground truth HEE values for each activity; and (4) a file containing the activity labels for each data record. The dataset is available for download at https://doi.org/10.5281/zenodo.3780891.

A multidevice and multimodal dataset for human energy expenditure estimation using wearable devices

In recent years, there has been an increasing interest in using wearable devices for energy expenditure estimation. The accuracy of these estimates is often limited by the lack of data regarding the individual’s physical activity and energy expenditure. In this paper, we present a multidevice and multimodal dataset for human energy expenditure estimation. The dataset was collected using four different wearable devices: an activity monitor, a heart rate monitor, a GPS device, and a body temperature sensor. The data was collected over a period of two weeks and includes a variety of activities, such as walking, running, and cycling. The objective of this dataset is to provide a resource for research on energy expenditure estimation using wearable devices. The dataset is available for download at: https://data.mendeley.com/datasets/rscbjbr9sj/1.

A new multidevice and multimodal dataset for human energy expenditure estimation using wearable devices has been released. The dataset, called PAMAP2 and collected by the University of Applied Sciences Upper Austria, includes measurements from nine different devices worn by 24 participants during 12 activities.

This is the second version of the PAMAP dataset, which was originally released in 2008 and has been widely used in research on energy expenditure estimation. The new version includes data from newer devices and provides moreactivity and device diversity, making it more applicable to real-world settings.

PAMAP2 is already being used in a number of studies, including one that is investigating the use of different devices and algorithms for energy expenditure estimation in children. This study is important because, while research on energy expenditure estimation using wearable devices has increased in recent years, most of the existing studies have been conducted in adults.

The PAMAP2 dataset provides a valuable resource for researchers working on energy expenditure estimation and will enable further progress in this area of research.