A Deep Learning–Based Rotten Food Recognition App for Older Adults: Development and Usability Study

Abstract

Background: Older adults are at greater risk of eating rotten fruits and of suffering food poisoning because cognitive function declines as they age, making it difficult to distinguish rotten fruits. To address this problem, researchers have developed and evaluated a tool detecting rotten food items in various ways. Nevertheless, little is known about how to create such an app to detect rotten food items to support older adults in danger of suffering from health problems from eating rotten food items.Objective: This study aims (1) to create a smartphone app that enables older adults to take a picture of food items with a camera and classifies whether the fruit is rotten or not for older adults, and (2) to evaluate the usability of the app and their perceptions of older adults about the app. Methods:We developed a smartphone app that supports older adults in determining whether the fruits are fresh enough to eat. We used several residual deep networks to check whether the collected fruit photos were fresh fruit. We recruited healthy older adults aged over 65 years (15 males and 11 females) as participants. Then, we evaluated the usability of the app and perceptions of older adults with the app through surveys and interviews. We analyzed survey responses, including an after-scenario questionnaire, as evaluation indicators of the usability of the app and collected qualitative data from interviewees for in-depth analysis of survey responses. Results:The results of this study showed that healthy older adults were satisfied with using an app that determines whether the fruit is fresh by taking a picture of the fruit but would be reluctant to use the paid app. The survey results revealed that participants tended to use the app efficiently to take pictures and determine the freshness of fruits. The qualitative data analysis revealed several categories, such as usability of the app and their perceptions about apps. Conclusions:This study suggests the possibility of developing an app that supports older adults in identifying rotten food items effectively and efficiently. Future work still remains to make the app distinguish the freshness of various food items other than the three kinds of fruits.