Food intake recognition conception for wearable devices

Päßler, Sebastian; Wolff, Matthias; Fischer, Wolf‐Joachim

doi:10.1145/2007036.2007045

Cited by 13 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently some researchers proposed [8] a 3D-printed behind-the-head framework (Auracle) device to capture the chewing sound based on conduction bone movement and necklace-like device by using throat microphone to capture both chewing and swallowing sound [6], [15]. Päßler & Fischer had used their proposed design in [16] to perform analysis such as analyzing acoustical signal energies and chewing detection based on magnitude squared coherence function(MSC) in [17], food type classification based on hidden Markov model (HMM) in [18], [19] and study on eight different chewing algorithm in [20]. The summary of the acoustical sensor for chewing detection is shown in Table 1, while the wearable sensing design shown in Fig.…”

Section: ) Acousticmentioning

confidence: 99%

“…Researchers typically limit the food type based on its category such as soft; [6], [49] and [22], crunchy; [6], [49] and [50], crispy; [6] and [22], hard; [22], liquid; [22]. While others only state the food type without specifying its category such as in [1], [3], [6], [8], [14], [15], [17], [18], [20], [29], [30], [31], [41], [43], [44], [48], [50] and [51]. Even though most of the in-lab experiment restrict the type of consumed food, however, some of them does provide a variety of food selection and ask the participants to choose according to their preferences [24], [26] and [28].…”

Section: Chewing Datasetmentioning

confidence: 99%

“…ANN is also common to be used in piezoelectric-based sensing, as shown by [26], [37], and [56]. In acoustic-based sensors, the most commonly used classifier is HMM, as used by [18], [20], [15] and [48].…”

Section: B Features Selection and Classificationmentioning

confidence: 99%

“…Overall, the system achieved a recognition performance of 86.6%. In [18] and [19], seven types of food with drink classified with an average accuracy of 63% and 79%, respectively. Päßler et al [19] 14.…”

Section: Food Classificationmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Food Intake Monitoring Based on Chewing Activity: A Survey

Selamat

Ali

2020

IEEE Access

View full text Add to dashboard Cite

Good nutrition is essential for optimal growth, development, and prevention of disease. Due to the importance of nutrition in human life, researchers have been interested in understanding the science of assessing food intake episodes for decades. With the advancement of technology, automated food monitoring tool develops with the help of sensors to address issues related to self-reporting methods. Food monitoring technology is evolving rapidly due to the advancement of sensors; however, automatic monitoring of food intake remains open problems to be solved. For food intake episode detection and monitoring, the sensors used to detect bites, chew, swallow, and hand gestures movement. This survey will be focusing on chewing activity detection during eating episodes. In this survey, a wide range of chewing activity detection explored to outline the sensing design, classification methods, performances, chewing parameters, chewing data analysis as well as the challenges and limitations associated with them.INDEX TERMS Food intake monitoring, automatic food intake detection, chewing sensor, chewing detection, chewing classification, chewing count, chewing data analysis.

show abstract

Section: ) Acousticmentioning

confidence: 99%

Section: Chewing Datasetmentioning

confidence: 99%

Section: B Features Selection and Classificationmentioning

confidence: 99%

Section: Food Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Food Intake Monitoring Based on Chewing Activity: A Survey

Selamat

Ali

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…There are also approaches to make food logging easier, based on the use of mobile photography [20], and Noronha et al use crowdsourcing to analyze nutrition information about photographed meals [25]. Furthermore, Pässler et al propose the utilization of wearable sensors for food intake recognition [28]. The Nutriflect system explores a different novel approach to generate awareness about nutrition without burdening the user with manual data entry by using existing grocery shopping data to provide feedback about food consumption patterns.…”

Section: Ubiquitous Computing and Situated Displaysmentioning

confidence: 99%

Nutriflect

Reitberger

Spreicer

Fitzpatrick

2014

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

A poor nutritional state, as is the case for many people today, can increase risks for cancer, cardiovascular disease and obesity. Technology supported approaches could potentially be used to positively influence food consumption. We present the Nutriflect system, which utilizes users' shopping data to inform them about their long term shopping behavior. In an initial study we conducted structured interviews in grocery stores. Based on the results we implemented a system that visualized a household's collective shopping information via situated displays. The aim was to raise awareness about shopping habits and to enable reflection about nutrition without burdening the users with the manual entry of their eating habits. We evaluated the system in a 4 week field study in 8 households with 21 users. The results indicate that contextually situated displays, showing shopping patterns against personal nutrition goals, can foster a reflective and respectful approach towards better shopping and nutrition.

show abstract

Souveräne digitalrechtliche Entscheidungsfindung hinsichtlich der Datenpreisgabe bei der Nutzung von Wearables

Butting

Conradie

Croll³

et al. 2022

DuD-Fachbeiträge

View full text Add to dashboard Cite

ZusammenfassungWearables unterstützen ihre Nutzer:innen in unterschiedlichen Kontexten. Dabei erzeugen und nutzen sie eine Vielzahl von oft sehr persönlichen (Gesundheits-)Daten, ohne dass Nutzer:innen über die notwendigen Kenntnisse und Erfahrungen verfügen, um reflektierte Entscheidungen über die Nutzung dieser Daten treffen zu können. In der aktuellen Forschung fehlen Konzepte, die einen unreflektierten Datenaustausch vermeiden und reflektierte Entscheidungen unterstützen. In diesem Beitrag diskutieren wir gesellschaftliche Herausforderungen der digitalen Souveränität und zeigen mögliche Wege der Visualisierung persönlicher (Gesundheits-)Daten und der Interaktion mit einem System, das transparente Informationen über die Nutzung von Wearable-Daten liefert. Wir zeigen Möglichkeiten zur Visualisierung rechtlicher und datenschutzrechtlicher Informationen auf und diskutieren unsere Ideen für einen erlebbaren Datenschutz mit Gamifizierungskonzepten. Die Bereitstellung interaktiver und visueller Datenräume kann die Fähigkeit zur eigenständigen Selbstbestimmung für Datenpreisgaben stärken.

show abstract

Food intake recognition conception for wearable devices

Cited by 13 publications

References 10 publications

Automatic Food Intake Monitoring Based on Chewing Activity: A Survey

Automatic Food Intake Monitoring Based on Chewing Activity: A Survey

Nutriflect

Souveräne digitalrechtliche Entscheidungsfindung hinsichtlich der Datenpreisgabe bei der Nutzung von Wearables

Contact Info

Product

Resources

About