论文标题
一种基于物联网的新型框架，用于使用机器学习技术进行非侵入性人类卫生监测
A Novel IoT-based Framework for Non-Invasive Human Hygiene Monitoring using Machine Learning Techniques
论文作者
论文摘要
人们的个人卫生习惯在日常生活方式中照顾身体和健康的状况有很多。保持良好的卫生习惯不仅减少了患疾病的机会，而且还可以降低在社区内传播疾病的风险。鉴于当前的大流行，诸如洗手或定期淋浴之类的日常习惯在人们中至关重要，特别是对于独自生活在家里或辅助生活设施中的老年人。本文提出了一个新颖的非侵入性框架，用于使用我们采用机器学习技术的振动传感器来监测人卫生。该方法基于地球通传感器，数字化器和实用外壳中具有成本效益的计算机板的组合。监测日常卫生常规可能有助于医疗保健专业人员积极主动，而不是反应性，以识别和控制社区内潜在暴发的传播。实验结果表明，在不同卫生习惯的分类中，应用支持向量机（SVM）进行二进制分类的精度约为95％。此外，基于树的分类器（随机福雷斯特和决策树）都可以实现最高精度（100％）优于其他模型，这意味着可以使用振动和非侵入性传感器对卫生事件进行分类以监测卫生活动。
People's personal hygiene habits speak volumes about the condition of taking care of their bodies and health in daily lifestyle. Maintaining good hygiene practices not only reduces the chances of contracting a disease but could also reduce the risk of spreading illness within the community. Given the current pandemic, daily habits such as washing hands or taking regular showers have taken primary importance among people, especially for the elderly population living alone at home or in an assisted living facility. This paper presents a novel and non-invasive framework for monitoring human hygiene using vibration sensors where we adopt Machine Learning techniques. The approach is based on a combination of a geophone sensor, a digitizer, and a cost-efficient computer board in a practical enclosure. Monitoring daily hygiene routines may help healthcare professionals be proactive rather than reactive in identifying and controlling the spread of potential outbreaks within the community. The experimental result indicates that applying a Support Vector Machine (SVM) for binary classification exhibits a promising accuracy of ~95% in the classification of different hygiene habits. Furthermore, both tree-based classifier (Random Forrest and Decision Tree) outperforms other models by achieving the highest accuracy (100%), which means that classifying hygiene events using vibration and non-invasive sensors is possible for monitoring hygiene activity.
