دورية أكاديمية
SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning.
| العنوان: | SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning. |
|---|---|
| المؤلفون: | Mauldin TR; Department of Computer Science, Texas State University, San Marcos, TX 78666, USA. trm119@txstate.edu., Canby ME; Department of Computer Science, Rice University, Houston, TX 77005, USA. marc.canby@gmail.com., Metsis V; Department of Computer Science, Texas State University, San Marcos, TX 78666, USA. vmetsis@txstate.edu., Ngu AHH; Department of Computer Science, Texas State University, San Marcos, TX 78666, USA. angu@txstate.edu., Rivera CC; Department of Computer Science, University of Puerto Rico, San Juan 00927, Puerto Rico. coralys.cubero@upr.edu. |
| المصدر: | Sensors (Basel, Switzerland) [Sensors (Basel)] 2018 Oct 09; Vol. 18 (10). Date of Electronic Publication: 2018 Oct 09. |
| 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: PubMed not MEDLINE |
| أسماء مطبوعة: | Original Publication: Basel, Switzerland : MDPI, c2000- |
| مستخلص: | This paper presents SmartFall, an Android app that uses accelerometer data collected from a commodity-based smartwatch Internet of Things (IoT) device to detect falls. The smartwatch is paired with a smartphone that runs the SmartFall application, which performs the computation necessary for the prediction of falls in real time without incurring latency in communicating with a cloud server, while also preserving data privacy. We experimented with both traditional (Support Vector Machine and Naive Bayes) and non-traditional (Deep Learning) machine learning algorithms for the creation of fall detection models using three different fall datasets (Smartwatch, Notch, Farseeing). Our results show that a Deep Learning model for fall detection generally outperforms more traditional models across the three datasets. This is attributed to the Deep Learning model's ability to automatically learn subtle features from the raw accelerometer data that are not available to Naive Bayes and Support Vector Machine, which are restricted to learning from a small set of extracted features manually specified. Furthermore, the Deep Learning model exhibits a better ability to generalize to new users when predicting falls, an important quality of any model that is to be successful in the real world. We also present a three-layer open IoT system architecture used in SmartFall, which can be easily adapted for the collection and analysis of other sensor data modalities (e.g., heart rate, skin temperature, walking patterns) that enables remote monitoring of a subject's wellbeing. |
| References: | Sensors (Basel). 2018 Apr 10;18(4):null. (PMID: 29642638) Sensors (Basel). 2014 Apr 22;14(4):7181-208. (PMID: 24759116) J Physiol. 1968 Mar;195(1):215-43. (PMID: 4966457) Eur Rev Aging Phys Act. 2016 Oct 30;13:8. (PMID: 27807468) Comput Methods Programs Biomed. 2014 Dec;117(3):489-501. (PMID: 25308505) Sensors (Basel). 2017 Jan 20;17(1):. (PMID: 28117691) Med Eng Phys. 2008 Jan;30(1):84-90. (PMID: 17222579) Sensors (Basel). 2016 Jul 25;16(8):. (PMID: 27463719) Sensors (Basel). 2018 Apr 26;18(5):null. (PMID: 29701721) Sensors (Basel). 2012;12(9):12301-16. (PMID: 23112713) J Geriatr Phys Ther. 2014 Oct-Dec;37(4):178-96. (PMID: 24406708) Sensors (Basel). 2017 Jun 16;17(6):. (PMID: 28621709) Sensors (Basel). 2014 Mar 21;14(3):5687-701. (PMID: 24662406) |
| معلومات مُعتمدة: | CNS1358939 National Science Foundation; CRI1305302 National Science Foundation |
| فهرسة مساهمة: | Keywords: IoT application; IoT architecture; deep learning; fall detection; recurrent neural network; smart health; smartwatch |
| تواريخ الأحداث: | Date Created: 20181012 Date Completed: 20181011 Latest Revision: 20181114 |
| رمز التحديث: | 20221213 |
| مُعرف محوري في PubMed: | PMC6210545 |
| DOI: | 10.3390/s18103363 |
| PMID: | 30304768 |
| قاعدة البيانات: | MEDLINE |
Full Text Finder كن أول من يترك تعليقا!