Estimating normal and abnormal activities using smartphones.

Stud Health Technol Inform

Technological Educational Institute of Crete, Biomedical Informatics and eHealth Laboratory, Estavromenos, 71004, Heraklion, Crete, Greece.

Published: February 2018

The main objective of this study is to propose a computational pipeline for the recognition of normal and abnormal activities based on smartphone accelerometer data. Methods and techniques that have been previously evaluated are further evolved and applied for the recognition of a large set of separate activities as well as a sequence of activities simulating a common scenario of daily living as a more realistic approach. For these purposes, the MobiAct dataset which encompass a set of normal activities of daily living (ADLs) and abnormal activities (falls) was used. The results show a classification accuracy of 99% for the recognition of separate ADLs, while a reduction of 5% is observed for the recognition of the scenarios.

Download full-text PDF

Source

Publication Analysis

Top Keywords

abnormal activities
12
normal abnormal
8
daily living
8
activities
6
estimating normal
4
activities smartphones
4
smartphones main
4
main objective
4
objective study
4
study propose
4

Similar Publications

Background: Recent research has revealed the potential value of machine learning (ML) models in improving prognostic prediction for patients with trauma. ML can enhance predictions and identify which factors contribute the most to posttraumatic mortality. However, no studies have explored the risk factors, complications, and risk prediction of preoperative and postoperative traumatic coagulopathy (PPTIC) in patients with trauma.

View Article and Find Full Text PDF

Attenuated cardiac autonomic function in patients with long-COVID with impaired orthostatic hemodynamics.

Clin Auton Res

January 2025

Department of Cardiac Sciences, Libin Cardiovascular Institute, University of Calgary, GAC70 HRIC Building, 3280 Hospital Dr NW, Calgary, AB, T2N 4Z6, Canada.

Purpose: Long-coronavirus disease (long-COVID) is associated with initial orthostatic hypotension and postural orthostatic tachycardia syndrome. Whether altered autonomic tone underlies these abnormalities is unknown. We compared autonomic function between patients with long-COVID and healthy controls, and within patients with long-COVID with different orthostatic hemodynamic phenotypes.

View Article and Find Full Text PDF

Aims: This study aimed to explore the brain activity characteristics of individuals with Internet Gaming Disorder (IGD) during mobile gameplay, focusing on neural responses to positive and negative game events. The findings may enhance our understanding of the neural mechanisms underlying IGD.

Methods: Functional near-infrared spectroscopy (fNIRS) was employed to measure hemodynamic responses (HbO/HbR) in the prefrontal cortex of both IGD participants and recreational gaming users (RGU), during solo and multiplayer mobile gameplay.

View Article and Find Full Text PDF

Synergistic photodynamic/photothermal therapy (PDT/PTT) can be used to target cancer cells by locally generating singlet oxygen species or increasing temperature under laser irradiation. This approach offers higher tumor ablation efficiency, lower therapeutic dose requirements, and reduced side effects compared to single treatment approaches. However, the therapeutic efficiency of PDT/PTT is still limited by the low oxygen levels within the solid tumors caused by abnormal vasculature and altered cancer cell metabolism.

View Article and Find Full Text PDF

The insular cortex (IC) processes various sensory information, including nociception, from the trigeminal region. Repetitive nociceptive inputs from the orofacial area induce plastic changes in the IC. Parvalbumin-immunopositive neurons (PVNs) project to excitatory neurons (pyramidal neurons [PNs]), whose inputs strongly suppress the activities of PNs.

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!