발간년도 : [2022]
| 논문정보 |
|
| 논문명(한글) |
[Vol.17, No.5] Body Fat Classification Model Using Body Size Data and K-means Clustering Algorithm |
|
| 논문투고자 |
Taejun Lee, Wenchao Jia, Sunghwan Kim, Hoekyung Jung |
|
| 논문내용 |
Recently, various cases of applying machine learning in the healthcare field are increasing. Functions such as electrocardiogram and body composition analysis are provided through wearable devices such as smart watches, and deep learning technology is applied to these functions. Through this, rational decision-making and standardized processes are derived, which is being used in research and construction of healthcare services tailored to individuals. In addition to existing medical records and medical insurance information, data collected through various channels such as public data, social media data, and genetic data disclosed by the government are being utilized. In order to apply this data to the model, human intervention is required, such as classifying to data. In this paper, we propose a model that classifying the average body fat percentage by group according to gender and age by receiving human body size data such as chest circumference and waist circumference as input. For the data, the human body size data provided by National Institute of Technology and Standards was used, and since this data is difficult to apply to the classification model, it was converted into data to which a clustering algorithm was applied. Classification is performed by applying to a CNN(Convolutional Neural Network) model. Through this, it is thought that it can be utilized in various application cases such as personalized body shape management service and obesity analysis. |
|
| 첨부논문 |
|
|
|
|
|
자료실 > 논문지 
