Automatic Detection of Chewing and Swallowing
A series of eating behaviors, including chewing and swallowing, is considered to be crucial to the maintenance of good health. However, most such behaviors occur within the human body, and highly invasive methods such as X-rays and fiberscopes must be utilized to collect accurate behavioral data. A...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/10/3378 |
| _version_ | 1797534289323098112 |
|---|---|
| author | Akihiro Nakamura Takato Saito Daizo Ikeda Ken Ohta Hiroshi Mineno Masafumi Nishimura |
| author_facet | Akihiro Nakamura Takato Saito Daizo Ikeda Ken Ohta Hiroshi Mineno Masafumi Nishimura |
| author_sort | Akihiro Nakamura |
| collection | DOAJ |
| description | A series of eating behaviors, including chewing and swallowing, is considered to be crucial to the maintenance of good health. However, most such behaviors occur within the human body, and highly invasive methods such as X-rays and fiberscopes must be utilized to collect accurate behavioral data. A simpler method of measurement is needed in healthcare and medical fields; hence, the present study concerns the development of a method to automatically recognize a series of eating behaviors from the sounds produced during eating. The automatic detection of left chewing, right chewing, front biting, and swallowing was tested through the deployment of the hybrid CTC/attention model, which uses sound recorded through 2ch microphones under the ear and weak labeled data as training data to detect the balance of chewing and swallowing. N-gram based data augmentation was first performed using weak labeled data to generate many weak labeled eating sounds to augment the training data. The detection performance was improved through the use of the hybrid CTC/attention model, which can learn the context. In addition, the study confirmed a similar detection performance for open and closed foods. |
| first_indexed | 2024-03-10T11:28:28Z |
| format | Article |
| id | doaj.art-1bbbad3fffca4c2087d2173f8801834c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T11:28:28Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1bbbad3fffca4c2087d2173f8801834c2023-11-21T19:27:09ZengMDPI AGSensors1424-82202021-05-012110337810.3390/s21103378Automatic Detection of Chewing and SwallowingAkihiro Nakamura0Takato Saito1Daizo Ikeda2Ken Ohta3Hiroshi Mineno4Masafumi Nishimura5Graduate School of Integrated Science and Technology, Shizuoka University, Hamamatsu 432-8011, JapanNTT DOCOMO, Inc., Tokyo 100-6150, JapanNTT DOCOMO, Inc., Tokyo 100-6150, JapanNTT DOCOMO, Inc., Tokyo 100-6150, JapanGraduate School of Integrated Science and Technology, Shizuoka University, Hamamatsu 432-8011, JapanGraduate School of Integrated Science and Technology, Shizuoka University, Hamamatsu 432-8011, JapanA series of eating behaviors, including chewing and swallowing, is considered to be crucial to the maintenance of good health. However, most such behaviors occur within the human body, and highly invasive methods such as X-rays and fiberscopes must be utilized to collect accurate behavioral data. A simpler method of measurement is needed in healthcare and medical fields; hence, the present study concerns the development of a method to automatically recognize a series of eating behaviors from the sounds produced during eating. The automatic detection of left chewing, right chewing, front biting, and swallowing was tested through the deployment of the hybrid CTC/attention model, which uses sound recorded through 2ch microphones under the ear and weak labeled data as training data to detect the balance of chewing and swallowing. N-gram based data augmentation was first performed using weak labeled data to generate many weak labeled eating sounds to augment the training data. The detection performance was improved through the use of the hybrid CTC/attention model, which can learn the context. In addition, the study confirmed a similar detection performance for open and closed foods.https://www.mdpi.com/1424-8220/21/10/3378chewingswallowingeating behaviorhybrid CTC/attention modeldata augmentation |
| spellingShingle | Akihiro Nakamura Takato Saito Daizo Ikeda Ken Ohta Hiroshi Mineno Masafumi Nishimura Automatic Detection of Chewing and Swallowing Sensors chewing swallowing eating behavior hybrid CTC/attention model data augmentation |
| title | Automatic Detection of Chewing and Swallowing |
| title_full | Automatic Detection of Chewing and Swallowing |
| title_fullStr | Automatic Detection of Chewing and Swallowing |
| title_full_unstemmed | Automatic Detection of Chewing and Swallowing |
| title_short | Automatic Detection of Chewing and Swallowing |
| title_sort | automatic detection of chewing and swallowing |
| topic | chewing swallowing eating behavior hybrid CTC/attention model data augmentation |
| url | https://www.mdpi.com/1424-8220/21/10/3378 |
| work_keys_str_mv | AT akihironakamura automaticdetectionofchewingandswallowing AT takatosaito automaticdetectionofchewingandswallowing AT daizoikeda automaticdetectionofchewingandswallowing AT kenohta automaticdetectionofchewingandswallowing AT hiroshimineno automaticdetectionofchewingandswallowing AT masafuminishimura automaticdetectionofchewingandswallowing |