Quantifying Eating Behavior With a Smart Plate in Patients With Arm Impairment After Stroke

Mertes, Gert; Chen, Wei; Hallez, Hans; Jia, Jie; Vanrumste, Bart

doi:10.1109/bhi.2019.8834466

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of classifying the dish correctly is crucial for the application as it provides the input for the look-up of the nutritional information. Moreover, the application facilitates nutritional monitoring for patients with critical health ailments like diabetes and also for older people [21]. We emulate the application on the Raspberry Pi by passing a batch of images collected from the application as an input for inference.…”

Section: A Application and Datasetmentioning

confidence: 99%

Context Aware Adaptive ML Inference in Mobile-Cloud Applications

Dolui

Michiels

Hughes

et al. 2022

2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)

Self Cite

View full text Add to dashboard Cite

With the emergence of mobile devices having enough resources to execute real-time ML inference, deployment opportunities arise on mobile devices while keeping privacy-sensitive data close to the source and reducing server load. Moreover, offloading inference to a cloud server facilitates deployment of neural network-based applications on resource-constrained devices. Depending on the application goals and execution context of the application, the optimal deployment on either cloud server or mobile device varies during the lifetime of an application. In this paper, we propose a context-aware middleware that enables optimization of deployed application software to satisfy the application's functional goals in accordance with changing execution context and environmental conditions. We facilitate system design through the abstraction of deployed software components as states and make use of finite state machines and contextual triggers to model the reconfiguration of the system. We evaluate our framework using a real-world nutritional monitoring application via food image recognition deployed in a two-tier mobile and cloud architecture. We compare the proposed solution with various static deployments of the application and show that our approach can react to changing application goals at run-time in order to reduce server load and thereby increase scalability.

show abstract

Section: A Application and Datasetmentioning

confidence: 99%

Context Aware Adaptive ML Inference in Mobile-Cloud Applications

Dolui

Michiels

Hughes

et al. 2022

2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite the recent advancements in smart devices for tracking eating behavior, including the wristband [24], ear sensors [25], smart fork [26], smart utensils [27], smart plate [28], smart tray [29], and wearable cameras [30], the video recordings of eating episodes remain the least intrusive and most scalable approach. Video recordings are able not only to reproduce wearables functionalities (e.g., eating rate, number of bites) but also to expand them towards more complex eating behavior events (e.g., emotion detection for eating behavior, social interactions at the table, or parent-child interaction [31]).…”

Section: Introductionmentioning

confidence: 99%

Capturing Eating Behavior from Video Analysis: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

Current methods to detect eating behavior events (i.e., bites, chews, and swallows) lack objective measurements, standard procedures, and automation. The video recordings of eating episodes provide a non-invasive and scalable source for automation. Here, we reviewed the current methods to automatically detect eating behavior events from video recordings. According to PRISMA guidelines, publications from 2010–2021 in PubMed, Scopus, ScienceDirect, and Google Scholar were screened through title and abstract, leading to the identification of 277 publications. We screened the full text of 52 publications and included 13 for analysis. We classified the methods in five distinct categories based on their similarities and analyzed their accuracy. Facial landmarks can count bites, chews, and food liking automatically (accuracy: 90%, 60%, 25%). Deep neural networks can detect bites and gesture intake (accuracy: 91%, 86%). The active appearance model can detect chewing (accuracy: 93%), and optical flow can count chews (accuracy: 88%). Video fluoroscopy can track swallows but is currently not suitable beyond clinical settings. The optimal method for automated counts of bites and chews is facial landmarks, although further improvements are required. Future methods should accurately predict bites, chews, and swallows using inexpensive hardware and limited computational capacity. Automatic eating behavior analysis will allow the study of eating behavior and real-time interventions to promote healthy eating behaviors.

show abstract

Quantifying Eating Behavior With a Smart Plate in Patients With Arm Impairment After Stroke

Cited by 2 publications

References 17 publications

Context Aware Adaptive ML Inference in Mobile-Cloud Applications

Context Aware Adaptive ML Inference in Mobile-Cloud Applications

Capturing Eating Behavior from Video Analysis: A Systematic Review

Contact Info

Product

Resources

About