EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Toward Concurrent Identification of Human Activities with a Single Unifying Neural Network Classification: First Step

Andrew Smith iD, Musa Azeem, Chrisogonas O Odhiambo, Pamela J Wright iD, Hanim E Diktas iD, Spencer Upton, Corby K Martin iD, Brett Froeliger, Cynthia F Corbett iD, Homayoun Valafar iD

Sensors · 2024

DOI: 10.3390/s24144542 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Andrew Smith und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA. Hauptthemen laut MEDLINE: Neural Networks, Computer, Human Activities, Wearable Electronic Devices. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, NIGMS NIH HHS, NIDDK NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The characterization of human behavior in real-world contexts is critical for developing a comprehensive model of human health. Recent technological advancements have enabled wearables and sensors to passively and unobtrusively record and presumably quantify human behavior. Better understanding human activities in unobtrusive and passive ways is an indispensable tool in understanding the relationship between behavioral determinants of health and diseases. Adult individuals (N = 60) emulated the behaviors of smoking, exercising, eating, and medication (pill) taking in a laboratory setting while equipped with smartwatches that captured accelerometer data. The collected data underwent expert annotation and was used to train a deep neural network integrating convolutional and long short-term memory architectures to effectively segment time series into discrete activities. An average macro-F1 score of at least 85.1 resulted from a rigorous leave-one-subject-out cross-validation procedure conducted across participants. The score indicates the method’s high performance and potential for real-world applications, such as identifying health behaviors and informing strategies to influence health. Collectively, we demonstrated the potential of AI and its contributing role to healthcare during the early phases of diagnosis, prognosis, and/or intervention. From predictive analytics to personalized treatment plans, AI has the potential to assist healthcare professionals in making informed decisions, leading to more efficient and tailored patient care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerHuman ActivitiesWearable Electronic DevicesHumansAdultMaleFemaleAccelerometryExercise

Stichwörter der Autor:innen

bite detectioncontext-aware environmentsecological momentary assessmenthuman activity recognitionmachine learningneural networkssmart healthcarewearable sensors

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA.
  • Advancing Chronic Care Outcomes through Research and iNnovation (ACORN) Center, Department of Biobehavioral Health & Nursing Science, College of Nursing, University of South Carolina, Columbia, SC 29208, USA.
  • Pennington Biomedical Research Center, Louisiana State University System, Baton Rouge, LA 70808, USA.
  • Department of Psychiatry, Psychological Sciences, and Cognitive Neuroscience Systems Core Facility, University of Missouri, Columbia, MO 65211, USA.

ORCID-Profile: Andrew Smith, Pamela J Wright, Hanim E Diktas, Corby K Martin, Cynthia F Corbett, Homayoun Valafar

Förderung

  • NIH HHS
  • NIGMS NIH HHS
  • NIDDK NIH HHS
  • NIDA NIH HHS
  • NIGMS
  • NORC Center
  • National Institute of General Medical Sciences
  • NIH/NIDA

Zitieren

APA

Smith, A., Azeem, M., Odhiambo, C. O., Wright, P. J., Diktas, H. E., Upton, S., Martin, C. K., Froeliger, B., Corbett, C. F., & Valafar, H. (2024). Toward Concurrent Identification of Human Activities with a Single Unifying Neural Network Classification: First Step. Sensors. https://doi.org/10.3390/s24144542

Vancouver

Smith A, Azeem M, Odhiambo CO, Wright PJ, Diktas HE, Upton S, et al. Toward Concurrent Identification of Human Activities with a Single Unifying Neural Network Classification: First Step. Sensors. 2024. doi:10.3390/s24144542

BibTeX
@article{Smith2024,
  author = {Smith, Andrew and Azeem, Musa and Odhiambo, Chrisogonas O and Wright, Pamela J and Diktas, Hanim E and Upton, Spencer and Martin, Corby K and Froeliger, Brett and Corbett, Cynthia F and Valafar, Homayoun},
  title = {Toward Concurrent Identification of Human Activities with a Single Unifying Neural Network Classification: First Step},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24144542}
}
Kostenlos starten →