| Abstract: | 體脂肪含量是人體健康指標之一，測量體脂肪可以幫助我們了解體脂肪和疾病的預防。屍體解剖法是量測身體脂肪最準確的方法，在活人身上執行量測似乎是不切實際的。此外，水中秤重法、同位素稀釋法、生物阻抗分析法等雖具有準確性，但大多是操作程序繁瑣或是價格昂貴。為此，美國陸軍、YMCA等組織各自發展量測模型。世界衛生組織建議以簡單容易操作量測的BMI來代替身體脂肪含量。但BMI最為人所詬病的是並未考慮人體脂肪在身體的分佈及特定部的堆積問題，因此準確度亦有待商確。本研究想透過複迴歸分析、類神經網路與遺傳神演算神經網路模型，藉由人體參數(年齡、體重、身高、頸圍、胸圍、腹圍、臀圍等)的輸入，來建構一個更精確的預測模型。本研究使用美國猶他州楊百翰大學人體效能研究中心(Human Performance Research Center, Brigham Young University, Provo) Dr. A. Garth Fisher所提供252筆男性的身體各量測指標的資料。實驗預測結果以遺傳演算神經網路模型(RMSE 4.0854) > 類神經網路5變數模型(RMSE 4.3330) > 類神經網路12變數模型(RMSE 4.3783) > 複迴歸12變數模型(RMSE 4.3981) > 複迴歸5變數模型(RMSE 4.4620) > YMCA體脂肪模型(RMSE 4.7757) > US Army體脂肪模型(RMSE 7.7336)。
Body fat mass is one of the health indicators. Measuring it is helpful to understand the relationship between body fat and diseases. Although, cadaver dissection provides the most accurate method to assess the value. But, it is not appropriate for the people who are living.
Additionally, some accurate methods, such as underwater weighting, isotope dilution, bioelectrical impedance analysis , are complicated and costly incredibly. Therefore, Young Men''s Christian Association (YMCA) and the United States army tried to develop instruments for gauging body fat.
Furthermore, World Health Organization (WHO) suggested that using body mass index (BMI) instead of body fat. However, evaluating BMI is not considered distribution of human body fat tissue component and specific region. It is doubtful about the accuracy.
The purpose of this study is constructing a more precise predict model by multiple regression analysis, artificial neural network, genetic algorithm neural network, the parameters are age, weight, height, neck circumference, chest circumference, abdomen circumference, hip circumference, and so on. 252 males’ body measurement indicators were database which were collected by Dr. A. Garth Fisher who was in Human Performance Research Center , Brigham Young University , Provo.
The result is genetic algorithm neural network RMSE: Root Mean Square Error (RMSE 4.0854) > artificial neural network 5 variables model (RMSE 4.3330) > artificial neural network 12 variables model (RMSE 4.3783) > multiple regression analysis 12 variables model (RMSE 4.3981) > multiple regression analysis 5 variables model (RMSE 4.4620) > YMCA body fat model (RMSE 4.7757) > US Army body fat Model (RMSE 7.7336)。 |
