AutoDietary: A Wearable Acoustic Sensor System for Food Intake Recognition in Daily Life

Bi, Yin; Lv, Mingsong; Song, Chen; Xu, Wenyao; Guan, Nan; Wang, Yi

doi:10.1109/jsen.2015.2469095

Cited by 115 publications

(85 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[1] compared six wearable microphone locations for recording chewing sounds and observed that the inner ear location provides the highest acoustic signal intensity. [9] presented the AutoDietary system for food type recognition and obtained an 84.9% accuracy in identifying food types between 7 types. Meanwhile, in [30], the authors modified a hearing aid to include two microphones (one in-ear and one for ambient noise), also in an attempt for food type classification.…”

Section: Related Workmentioning

confidence: 99%

EarBit

Bedri

Haynes

et al. 2017

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

151

View full text Add to dashboard Cite

Chronic and widespread diseases such as obesity, diabetes, and hypercholesterolemia require patients to monitor their food intake, and food journaling is currently the most common method for doing so. However, food journaling is subject to self-bias and recall errors, and is poorly adhered to by patients. In this paper, we propose an alternative by introducing EarBit, a wearable system that detects eating moments. We evaluate the performance of inertial, optical, and acoustic sensing modalities and focus on inertial sensing, by virtue of its recognition and usability performance. Using data collected in a simulated home setting with minimum restrictions on participants’ behavior, we build our models and evaluate them with an unconstrained outside-the-lab study. For both studies, we obtained video footage as ground truth for participants activities. Using leave-one-user-out validation, EarBit recognized all the eating episodes in the semi-controlled lab study, and achieved an accuracy of 90.1% and an F1-score of 90.9% in detecting chewing instances. In the unconstrained, outside-the-lab evaluation, EarBit obtained an accuracy of 93% and an F1-score of 80.1% in detecting chewing instances. It also accurately recognized all but one recorded eating episodes. These episodes ranged from a 2 minute snack to a 30 minute meal.

show abstract

Section: Related Workmentioning

confidence: 99%

EarBit

Bedri

Haynes

et al. 2017

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

151

View full text Add to dashboard Cite

show abstract

“…Depending on the studies and approaches, different models and classifiers for event detection will be utilized. We take into account Bi et al [90] and Lopez-Meyer et al [88]. In these systems, the first step is undeniably sound recording with an 8000-Hz sampling rate with an amplifier.…”

Section: Eating Behavior/food Intake Detectionmentioning

confidence: 99%

“…The next step includes framing to produce sound frames for event detection afterward. Bi et al [90] employed the hidden Markov model (HMM) for event detection. This model has long been utilized for sound recognition [138,139].…”

Section: Eating Behavior/food Intake Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Wearable Food Intake Monitoring Technologies: A Comprehensive Review

et al. 2017

Self Cite

View full text Add to dashboard Cite

Wearable devices monitoring food intake through passive sensing is slowly emerging to complement self-reporting of users' caloric intake and eating behaviors. Though the ultimate goal for the passive sensing of eating is to become a reliable gold standard in dietary assessment, it is currently showing promise as a means of validating self-report measures. Continuous food-intake monitoring allows for the validation and refusal of users' reported data in order to obtain more reliable user information, resulting in more effective health intervention services. Recognizing the importance and strength of wearable sensors in food intake monitoring, there has been a variety of approaches proposed and studied in recent years. While existing technologies show promise, many challenges and opportunities discussed in this survey, still remain. This paper presents a meticulous review of the latest sensing platforms and data analytic approaches to solve the challenges of food-intake monitoring, ranging from ear-based chewing and swallowing detection systems that capture eating gestures to wearable cameras that identify food types and caloric content through image processing techniques. This paper focuses on the comparison of different technologies and approaches that relate to user comfort, body location, and applications for medical research. We identify and summarize the forthcoming opportunities and challenges in wearable food intake monitoring technologies.

show abstract

“…To convert image or video to text we need to use NLP and based on the information gathered we need to transfer the specific issue to the respective department [15].…”

Section: Machine Learning (Predictions Phase)mentioning

confidence: 99%

Multiple Architectural Approach for Urban Development Using Wearable IoT Devices: A Combined Machine Learning Approach

Mylavarapu

2018

AIT

View full text Add to dashboard Cite

Machine Learning becomes a part of our life in recent days and everything we do in interlinked with machine learning. As a technocrat, we tried to implement machine learning with Internet of Things (IoT) for better implementation of technology in organizations for security. We designed an sample architecture which will carry the burden of safeguarding the organizational data with IoT using machine learning with an effective manner and in this case we were proposing utilization of cloud computing for better understanding of data storage and retrieval process. Machine learning is used for the prediction models based on which we need to perform high level analysis of data and using IoT we promote authorization mechanism based on which we recognize the appropriate recipient of data and cloud for managing the data services with the three-tier architecture. We present the architecture we are proposing for better utilization of machine learning and IoT with cloud architecture.

show abstract

AutoDietary: A Wearable Acoustic Sensor System for Food Intake Recognition in Daily Life

Cited by 115 publications

References 24 publications

EarBit

EarBit

Wearable Food Intake Monitoring Technologies: A Comprehensive Review

Multiple Architectural Approach for Urban Development Using Wearable IoT Devices: A Combined Machine Learning Approach

Contact Info

Product

Resources

About