Introduction: Human activity monitoring is a useful tool in medical monitoring, military applications, athletic coaching, and home healthcare. We propose the use of an accelerometer-based system to track crewmember activity during space missions in reduced gravity environments. It is unclear how the partial gravity environment of the Moorn or Mars will affect human locomotion. Here we test a novel analogue of lunar gravity in combination with a custom wireless activity tracking system.

Methods: A noninvasive wireless accelerometer-based sensor system, the activity tracking device (ATD), was developed. The system has two sensor units; one footwear-mounted and the other waist-mounted near the midlower back. Subjects (N=16) were recruited to test the system in the enhanced Zero Gravity Locomotion Simulator (eZLS) at NASA Glenn Research Center. Data were used to develop an artificial neural network for activity recognition.

Results: The eZLS demonstrated the ability to replicate reduced gravity environments. There was a 98% agreement between the ATD and force plate-derived stride times during running (9.7 km x h(-1)) at both 1 g and 1/6 g. A neural network was designed and successfully trained to identify lunar walking, running, hopping, and loping from ATD measurements with 100% accuracy.

Discussion: The eZLS is a suitable tool for examining locomotor activity at simulated lunar gravity. The accelerometer-based ATD system is capable of monitoring human activity and may be suitable for use during remote, long-duration space missions. A neural network has been developed to use data from the ATD to aid in remote activity monitoring.

Download full-text PDF

Source
http://dx.doi.org/10.3357/asem.2825.2011DOI Listing

Publication Analysis

Top Keywords

neural network
12
simulated lunar
8
activity
8
human activity
8
activity monitoring
8
space missions
8
reduced gravity
8
gravity environments
8
lunar gravity
8
activity tracking
8

Similar Publications

Background: Deutetrabenazine is a widely used drug for the treatment of tardive dyskinesia (TD), and post-marketing testing is important. There is a lack of real-world, large-sample safety studies of deutetrabenazine. In this study, a pharmacovigilance analysis of deutetrabenazine was performed based on the FDA Adverse Event Reporting System (FAERS) database to evaluate its relevant safety signals for clinical reference.

View Article and Find Full Text PDF

The early symptoms of hepatocellular carcinoma patients are often subtle and easily overlooked. By the time patients exhibit noticeable symptoms, the disease has typically progressed to middle or late stages, missing optimal treatment opportunities. Therefore, discovering biomarkers is essential for elucidating their functions for the early diagnosis and prevention.

View Article and Find Full Text PDF

Current neural network models of primate vision focus on replicating overall levels of behavioral accuracy, often neglecting perceptual decisions' rich, dynamic nature. Here, we introduce a novel computational framework to model the dynamics of human behavioral choices by learning to align the temporal dynamics of a recurrent neural network (RNN) to human reaction times (RTs). We describe an approximation that allows us to constrain the number of time steps an RNN takes to solve a task with human RTs.

View Article and Find Full Text PDF

Giant cell arteritis (GCA), a systemic vasculitis affecting large and medium-sized arteries, poses significant diagnostic and management challenges, particularly in preventing irreversible complications like vision loss. Recent advancements in artificial intelligence (AI) technologies, including machine learning (ML) and deep learning (DL), offer promising solutions to enhance diagnostic accuracy and optimize treatment strategies for GCA. This systematic review, conducted according to the PRISMA 2020 guidelines, synthesizes existing literature on AI applications in GCA care, with a focus on diagnostic accuracy, treatment outcomes, and predictive modeling.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!