Bibliographic Details
| Title: |
Image and dataset based nutrition estimation for hospitalized patients using AI. |
| Authors: |
Sathana, V.1 (AUTHOR) nusathana@gmail.com, Sathya, M.1 (AUTHOR) jmssathya2000@gmail.com, Swathi, R.1 (AUTHOR) swathiboopathi1360@gmail.com, Swetha, J.1 (AUTHOR) swethajegatheesan@gmail.com, Vaishnavi, S.1 (AUTHOR) vaishu09052001@gmail.com |
| Source: |
AIP Conference Proceedings. 2023, Vol. 2822 Issue 1, p1-8. 8p. |
| Subject Terms: |
*HOSPITAL patients, *MACHINE learning, *IMAGE recognition (Computer vision), *IMAGE processing, *DATABASES, *NUTRITION, *FEEDING tubes, *SPORTS nutrition, *FOOD consumption |
| Abstract: |
The food nutrition intake calculator detects the nutrition level of the hospitalized patient's food. The objective of the system is to predict the images of the food which the patients will take in hospital. It detects the nutrient level whether it is a higher level or a lower level of the nutrient. In this process, the food intake images of what the patients have eaten in the hospital. Here the images were predicted by the image processing method. In image processing, classification of the images done by SVM algorithm. In addition, Gaussian Smoothing algorithm, which is used to detect outline of the image. The prediction of the food's nutrition level is measured by grams. The food information collected from the hospital are stored in the database. After that patient intake food image is compared with database. Then the result of the image processing method will be converted into the dataset. The result of the dataset is classified by the Few shot learning algorithm. It also shows the recovery details of the patient. In future, there is a need to improve more processes for food nutrition intake. Nonetheless, the trouble lies in the way that the modern comment prerequisites characteristically limit the quality and the size of the food pictures information base for a supplement consumption appraisal. [ABSTRACT FROM AUTHOR] |
|
Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Academic Search Complete |
