• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Bioinformatics and Biomedicine >Machine Learning to Predict Overeating from Macronutrient Composition
【24h】

Machine Learning to Predict Overeating from Macronutrient Composition

机译：机器学习可预测大量营养素的暴饮暴食

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper investigates nutritional deficiencies as a possible cause of overeating and obesity. Existing medical research suggests such a connection. Data obtained from public calorie logs were used to create decision tree models and random forest classifiers that can predict instances of overeating based on macronutrient composition at varying overeating thresholds. Macronutrient composition was defined as the percentage of carbohydrate, protein, and fat calorie intake out of the total calorie intake. Our research indicates that macronutrient composition has a large role in predicting overeating lapses and could be used in current calorie-tracking applications to help users lose weight and adhere to healthy nutritional guidelines.
机译：本文调查了营养不足是暴饮暴食和肥胖的可能原因。现有医学研究表明了这种联系。从公共卡路里记录中获得的数据被用于创建决策树模型和随机森林分类器，这些分类器可以根据不同的暴饮暴食阈值下的大量营养成分来预测暴饮暴食的情况。常量营养素的组成定义为碳水化合物，蛋白质和脂肪卡路里摄入量占总卡路里摄入量的百分比。我们的研究表明，大量营养素成分在预测暴饮暴食中起很大作用，可用于当前的卡路里追踪应用中，以帮助用户减轻体重并遵守健康的营养指南。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号