EarBit

Bedri, Abdelkareem; Li, Richard; Haynes, Malcolm; Kosaraju, Raj Prateek; Grover, Ishaan; Prioleau, Temiloluwa; Beh, Min Yan; Goel, Mayank; Starner﻿﻿, Thad; Abowd, Gregory D.

doi:10.1145/3130902

Cited by 158 publications

(34 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors determined intake from bites using arm motion, while the present investigation was based on chewing. Bedri et al [11] evaluated eating event detection using a metric called delay, measuring the time from the beginning of an eating event until it was recognised. The average delay reported was 65.4 s. In contrast to the investigation of Bedri et al [11], we also evaluated the timing error at the end of eating events.…”

Section: Discussionmentioning

confidence: 99%

“…Bedri et al [11] evaluated eating event detection using a metric called delay, measuring the time from the beginning of an eating event until it was recognised. The average delay reported was 65.4 s. In contrast to the investigation of Bedri et al [11], we also evaluated the timing error at the end of eating events. Our bottom-up algorithm yielded average start/end timing errors of 2.4 s and 4.3 s.…”

Section: Discussionmentioning

confidence: 99%

“…Bedri et al used an ear-worn system for chewing instance detection. An F1 score of over 80% and accuracy of over 93% was reported [11]. Timing error for eating start was 65.4 s. The authors did not report the timing error at eating ends.…”

Section: Related Workmentioning

confidence: 92%

See 2 more Smart Citations

Retrieval and Timing Performance of Chewing-Based Eating Event Detection in Wearable Sensors

Zhang

Amft

2020

Sensors

View full text Add to dashboard Cite

We present an eating detection algorithm for wearable sensors based on first detecting chewing cycles and subsequently estimating eating phases. We term the corresponding algorithm class as a bottom-up approach. We evaluated the algorithm using electromyographic (EMG) recordings from diet-monitoring eyeglasses in free-living and compared the bottom-up approach against two top-down algorithms. We show that the F1 score was no longer the primary relevant evaluation metric when retrieval rates exceeded approx. 90%. Instead, detection timing errors provided more important insight into detection performance. In 122 hours of free-living EMG data from 10 participants, a total of 44 eating occasions were detected, with a maximum F1 score of 99.2%. Average detection timing errors of the bottom-up algorithm were 2.4 ± 0.4 s and 4.3 ± 0.4 s for the start and end of eating occasions, respectively. Our bottom-up algorithm has the potential to work with different wearable sensors that provide chewing cycle data. We suggest that the research community report timing errors (e.g., using the metrics described in this work).

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Retrieval and Timing Performance of Chewing-Based Eating Event Detection in Wearable Sensors

Zhang

Amft

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The SVM model is evaluated using the accuracy of classification. Accuracy of classification (A) is given by (5).…”

Section: G Svm Classifiermentioning

confidence: 99%

Detection of Oil-Containing Dressing on Salad Leaves Using Multispectral Imaging

Raju

Sazonov

2020

IEEE Access

View full text Add to dashboard Cite

There is a need for non-invasive methods for nutritional analysis of food that can address the drawbacks of current methods such as color photography, which cannot distinguish between energydense and zero calorie foods. This paper discusses a novel, multispectral approach for the identification of oil, particularly in salads, and defines a pseudo-reflectance term. A custom-made multispectral camera was used to collect a novel, publicly shared dataset of images of untreated lettuce leaves or leaves treated with vinegar, oil, or a combination of these. The camera captured image data at 10 wavelengths ∈[380nm,980nm] across the electromagnetic spectrum in the visible and NIR (near-infrared) regions. Imaging was done in a lab environment with the presence of ambient light. Mean spectra were extracted from the regions of interest in the multispectral cube and used to compute pseudo-reflectance. ANOVA (Analysis of Variance) was performed to look for variances in the pseudo-reflectance curves. ANOVA proved that the differences between group means of the four treatment groups (oil, vinegar, oil plus vinegar, control) were statistically significant. Pairs of groups showing the greatest significance were established using a Tukey post hoc test. Sequential Forward Selection (SFS) was used to determine 5 optimal feature wavelengths from the whole feature space (410 nm, 455 nm, 485 nm, 810 nm, and 850 nm). A combination of visible (VIS) and infrared (IR) wavelengths, selected using SFS, showed the greatest potential for discrimination between groups containing oil and groups that do not contain oil with a classification accuracy of 84.20%. The pseudo-reflectance values were statistically proven to be sensitive to the presence of oil as a dressing. This research has demonstrated the feasibility of implementing a multispectral imaging technique for identifying the presence of oil in salads and possibly an energy content detection system. INDEX TERMS Multispectral imaging, energy density, food detection, high calorie detection, dietary assessment.

show abstract

“…This is because gathering and recording of data by the patients place undue burden on them, and the data may not be objective. Current devices to measure the number of chews include a camera that records mouth movements [2]; tooth-embedded sensors [3], EMG [4], and piezoelectric strain gauge sensors [5] attached to the skin surface; microphones that detect chewing noises [6–9]; and accelerometers that recognize the movement of skin caused by chewing [10, 11]. However, these devices were not developed specifically for dietary support of postgastrectomy patients, and each tool has drawbacks when applied to such patients.…”

Section: Introductionmentioning

confidence: 99%

Earable RCC: Development of an Earphone-Type Reliable Chewing-Count Measurement Device

Taniguchi

Kondo²,

Tanaka

et al. 2018

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Gastric cancer patients having undergone gastrectomy are at a high risk of becoming malnourished owing to decreased gastric function. To prevent malnutrition, patients need to thoroughly chew a mouthful of food at least 30 times. For these gastrectomy patients requiring dietary support, we developed a chewing-count measurement device named earable RCC using an earphone-type sensor. Experiments to evaluate the performance of this device were conducted on six healthy volunteers who participated in “gum-chewing tests” and “almond-eating tests.” The precision calculated based on the results was ≥0.958, indicating that the earphone-type chewing-count measurement device could experimentally distinguish chewing from other actions. In addition, the recall calculated from the test results was ≥0.937, showing that the device does not miss chewing actions and can accurately count the number of chews with high probability at the timing of chewing. The experimental results also imply that earphone-type sensors may be used to measure swallowing, occlusal force, and tongue motion. Our future plans include clinical testing of the earphone-type chewing-count measurement device to determine its utility in patients who have undergone gastrectomy. We also intend to expand the application of this device for use in other patients to aid in dementia prevention and dietary support.

show abstract

EarBit

Cited by 158 publications

References 42 publications

Retrieval and Timing Performance of Chewing-Based Eating Event Detection in Wearable Sensors

Retrieval and Timing Performance of Chewing-Based Eating Event Detection in Wearable Sensors

Detection of Oil-Containing Dressing on Salad Leaves Using Multispectral Imaging

Earable RCC: Development of an Earphone-Type Reliable Chewing-Count Measurement Device

Contact Info

Product

Resources

About