Skip to main content
NCBI home page
NIHPA Author Manuscripts logoLink to NIHPA Author Manuscripts
. Author manuscript; available in PMC: 2017 Jan 1.
Published in final edited form as: Gerontechnology. 2016;15(Suppl):88s.

Accuracy and stability testing of a ‘smart dresser’ for persons with dementia

DF Mahoney 1, W Burleson 1, J Rowe 1, EL Mahoney 1
PMCID: PMC5199139  NIHMSID: NIHMS831843  PMID: 28050165

Purpose

To report the accuracy and stability testing results for a prototype assistive dressing technology designed for persons with dementia to enable them to dress with more privacy and less dependency on caregivers1. Smart-home technologies have been critiqued for not disclosing performance characteristics to the marketplace2, 3. Transparency is necessary to inform potential users as to the state-of-the-art to ensure realistic expectations and user safety4.

Method

A 110 day device run-in pilot study. The system operated 24/7 in a community based studio sized unit using the local Wi-Fi network. A 69 yr old male tester documented usability issues. Automatic log reports were generated daily by the system, validated and annotated by the project manager. A content analysis of the user and log reports was conducted. Descriptive statistics describe the quantitative findings.

Results & Discussion

The alpha prototype (Figure 1) performed very favorably. It functioned error free for the majority of the trial (75% of days) with stable performance for 95.5% of days (Figure 2). Thirty-seven correctable error events occurred during 28 of the 110 days and as shown in Figure 3 resulted in 4 categories of errors: hardware (0.9%), network (3.6%), usability (4.5%), and re-initialization (24.5%). In Phase 2, the run-in will continue for a total of six months to uncover any long-term usage issues. Lessons learned will inform quality improvements to further optimize system performance.

Figure 1.

Figure 1

Open in a new tab

DRESS©Mahoney & Burleson Alpha System, smart dresser system components: dresser, iPad, motion sensor, iPods, caregiver mobile device, fiducial barcodes, and wrist sensor

Figure 2.

Figure 2

Open in a new tab

©Mahoney & Burleson. System Accuracy and Stability (as a % of 110 day trial)

Figure 3.

Figure 3

Open in a new tab

©. Mahoney & Burleson Type and Rate of Errors (% of 110 days)

References

  • 1.Mahoney DF, Burleson W, Lozano C, Ravishankar V, Mahoney EL. Prototype development of a responsive emotive sensing system (DRESS) to aid older persons with dementia to dress independently. Gerontechnology. 2015;13(3):345–358. doi: 10.4017/gt.2015.13.3.005.00. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 2.Garfinkel S. Smart home devices need to get a lot smarter. MIT Technology. Review June 30, 2014: www.technologyreview.com/s/528696/smart-home-devices-need-to-get-a-lot-smarter/; retrieved March 10, 2016.
  • 3.Lee JM, Kim Y, Welk GJ. Validity of consumer-based physical activity monitors. Medicine and Science in Sports and Exercise. 2014;46(9):1840–1848. doi: 10.1249/MSS.0000000000000287. [DOI] [PubMed] [Google Scholar]
  • 4.Wolf JA, Moreau JF, Akilov O, Patton T, English JC, Ho J, Ferris LK. Diagnostic inaccuracy of smart phone applications for melanoma detection. JAMA Dermatology. 2013;149(4):422. doi: 10.1001/jamadermatol.2013.2382. [DOI] [PMC free article] [PubMed] [Google Scholar]

RESOURCES