Dataset Information

A Public Domain Dataset for Real-Life Human Activity Recognition Using Smartphone Sensors.

ABSTRACT: In recent years, human activity recognition has become a hot topic inside the scientific community. The reason to be under the spotlight is its direct application in multiple domains, like healthcare or fitness. Additionally, the current worldwide use of smartphones makes it particularly easy to get this kind of data from people in a non-intrusive and cheaper way, without the need for other wearables. In this paper, we introduce our orientation-independent, placement-independent and subject-independent human activity recognition dataset. The information in this dataset is the measurements from the accelerometer, gyroscope, magnetometer, and GPS of the smartphone. Additionally, each measure is associated with one of the four possible registered activities: inactive, active, walking and driving. This work also proposes asupport vector machine (SVM) model to perform some preliminary experiments on the dataset. Considering that this dataset was taken from smartphones in their actual use, unlike other datasets, the development of a good model on such data is an open problem and a challenge for researchers. By doing so, we would be able to close the gap between the model and a real-life application.

SUBMITTER: Garcia-Gonzalez D

PROVIDER: S-EPMC7218897 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Public Domain Dataset for Real-Life Human Activity Recognition Using Smartphone Sensors.

Garcia-Gonzalez Daniel D Rivero Daniel D Fernandez-Blanco Enrique E Luaces Miguel R MR

Sensors (Basel, Switzerland) 20200413 8

In recent years, human activity recognition has become a hot topic inside the scientific community. The reason to be under the spotlight is its direct application in multiple domains, like healthcare or fitness. Additionally, the current worldwide use of smartphones makes it particularly easy to get this kind of data from people in a non-intrusive and cheaper way, without the need for other wearables. In this paper, we introduce our orientation-independent, placement-independent and subject-inde ...[more]

PMID: 32295028

Similar Datasets

Project description:The data were collected to test the hypothesis that problematic smartphone use, defined as the risk of smartphone addiction, is positively related to the type/purpose of device use (hedonic, meaning pleasure/gratification) and perceived stress, while it is negatively related to life satisfaction. The data were collected online between October 2020 and January 2021, using Qualtrics online research platform. The participants were aged 18 years or over, had a good command of the English language. They were recruited by posting the survey link on popular social media platforms, such as Facebook, LinkedIn, and Twitter, as well as by using applications such as WhatsApp and Instagram. Participation was voluntary, anonymous, and without material compensation. In addition to demographic questions (age, gender, level of education), respondents completed three questionnaires, including the Smartphone Application-Based Addiction Questionnaire (SABAS), Satisfaction with Life Scale (SWLS), Perceived Stress Scale (PSS), and answered two questions about the proportion of time they use their smartphone to access the Internet and the proportion of time they use smartphone for hedonic purposes. In the course of the data analysis, our aim was to predict the risk of smartphone addiction by the type or purpose of smartphone use, perceived stress, life satisfaction, age, and gender. The reuse potential of the data lies in the possibility to examine the relationships between the hedonic use of smartphones and other variables in the dataset. Researchers could also examine differences of gender or education level in the specific components of smartphone addiction, since each item of the SABAS represents a distinct component in the 'Components model' of addiction [4]. Furthermore, since we have data on Internet access via a tablet, laptop, and desktop computer, it is possible to analyse the relationships of the dependent variables with these paths of accessing the Internet.

Dataset Information

A Public Domain Dataset for Real-Life Human Activity Recognition Using Smartphone Sensors.

Publications

A Public Domain Dataset for Real-Life Human Activity Recognition Using Smartphone Sensors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets