دورية أكاديمية
أعرض في EDS

Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition.

التفاصيل البيبلوغرافية
العنوان: Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition.
المؤلفون: Cherian J; Department of Computer Science & Engineering, Texas A&M University, College Station, TX 77843, USA., Ray S; Department of Computer Science & Engineering, Texas A&M University, College Station, TX 77843, USA., Taele P; Department of Computer Science & Engineering, Texas A&M University, College Station, TX 77843, USA., Koh JI; Department of Computer Science & Engineering, Texas A&M University, College Station, TX 77843, USA., Hammond T; Department of Computer Science & Engineering, Texas A&M University, College Station, TX 77843, USA.
المصدر: Sensors (Basel, Switzerland) [Sensors (Basel)] 2024 Jun 16; Vol. 24 (12). Date of Electronic Publication: 2024 Jun 16.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: MEDLINE
أسماء مطبوعة: Original Publication: Basel, Switzerland : MDPI, c2000-
مواضيع طبية MeSH: Activities of Daily Living* , Machine Learning* , Human Activities*, Humans ; Algorithms ; Walking/physiology ; Pattern Recognition, Automated/methods
مستخلص: Monitoring activities of daily living (ADLs) plays an important role in measuring and responding to a person's ability to manage their basic physical needs. Effective recognition systems for monitoring ADLs must successfully recognize naturalistic activities that also realistically occur at infrequent intervals. However, existing systems primarily focus on either recognizing more separable, controlled activity types or are trained on balanced datasets where activities occur more frequently. In our work, we investigate the challenges associated with applying machine learning to an imbalanced dataset collected from a fully in-the-wild environment. This analysis shows that the combination of preprocessing techniques to increase recall and postprocessing techniques to increase precision can result in more desirable models for tasks such as ADL monitoring. In a user-independent evaluation using in-the-wild data, these techniques resulted in a model that achieved an event-based F1-score of over 0.9 for brushing teeth, combing hair, walking, and washing hands. This work tackles fundamental challenges in machine learning that will need to be addressed in order for these systems to be deployed and reliably work in the real world.
References: Appl Psychophysiol Biofeedback. 2012 Sep;37(3):205-15. (PMID: 22488204)
IEEE J Biomed Health Inform. 2018 May;22(3):686-696. (PMID: 28410113)
IEEE Trans Syst Man Cybern B Cybern. 2009 Apr;39(2):539-50. (PMID: 19095540)
NCHS Data Brief. 2021 Sep;(404):1-8. (PMID: 34570695)
IUI. 2019 Mar;2019:80-85. (PMID: 31032488)
Sensors (Basel). 2022 Feb 11;22(4):. (PMID: 35214275)
Sensors (Basel). 2020 Sep 08;20(18):. (PMID: 32911780)
Smart Health (Amst). 2021 Mar;19:100171. (PMID: 33521225)
IEEE Sens J. 2016 Feb;16(4):1054-1061. (PMID: 36452935)
Sensors (Basel). 2019 Jul 21;19(14):. (PMID: 31330919)
Neural Netw. 2015 Oct;70:39-52. (PMID: 26210983)
Am J Public Health. 1982 Dec;72(12):1373-9. (PMID: 6814269)
Med Phys. 2017 Mar;44(3):832-846. (PMID: 28079249)
Sensors (Basel). 2016 Jan 18;16(1):. (PMID: 26797612)
J Am Geriatr Soc. 1983 Dec;31(12):721-7. (PMID: 6418786)
Proc ACM Int Conf Ubiquitous Comput. 2015 Sep;2015:1029-1040. (PMID: 29520397)
معلومات مُعتمدة: 1952236 National Science Foundation
فهرسة مساهمة: Keywords: activities of daily living; class imbalance; human activity recognition; in-the-wild; postprocessing; preprocessing; smartwatch
تواريخ الأحداث: Date Created: 20240627 Date Completed: 20240627 Latest Revision: 20240629
رمز التحديث: 20240629
مُعرف محوري في PubMed: PMC11207638
DOI: 10.3390/s24123898
PMID: 38931682
قاعدة البيانات: MEDLINE
الوصف
تدمد:1424-8220
DOI:10.3390/s24123898