Schiavone Giuseppina, Lamichhane Bishal, Van Hoof Chris
Wearable Health Solutions, Holst Centre, High Tech Campus 31, 5656 AE Eindhoven, Netherlands.
Biomed Res Int. 2017;2017:4593956. doi: 10.1155/2017/4593956. Epub 2017 Jan 4.
A novel methodology, the double layer methodology (DLM), for modeling an individual's lifestyle and its relationships with health indicators is presented. The DLM is applied to model behavioral routines emerging from self-reports of daily diet and activities, annotated by 21 healthy subjects over 2 weeks. Unsupervised clustering on the first layer of the DLM separated our population into two groups. Using eigendecomposition techniques on the second layer of the DLM, we could find activity and diet routines, predict behaviors in a portion of the day (with an accuracy of 88% for diet and 66% for activity), determine between day and between individual similarities, and detect individual's belonging to a group based on behavior (with an accuracy up to 64%). We found that clustering based on health indicators was mapped back into activity behaviors, but not into diet behaviors. In addition, we showed the limitations of eigendecomposition for lifestyle applications, in particular when applied to noisy and sparse behavioral data such as dietary information. Finally, we proposed the use of the DLM for supporting adaptive and personalized recommender systems for stimulating behavior change.
本文提出了一种用于对个体生活方式及其与健康指标的关系进行建模的新方法，即双层方法（DLM）。DLM应用于对21名健康受试者在两周内自我报告的日常饮食和活动中出现的行为习惯进行建模。DLM第一层的无监督聚类将我们的人群分为两组。通过在DLM第二层使用特征分解技术，我们可以找到活动和饮食习惯，预测一天中部分时间的行为（饮食预测准确率为88%，活动预测准确率为66%），确定日与日之间以及个体之间的相似性，并根据行为检测个体所属的组（准确率高达64%）。我们发现，基于健康指标的聚类可以映射回活动行为，但不能映射到饮食行为。此外，我们展示了特征分解在生活方式应用中的局限性，特别是在应用于如饮食信息等嘈杂和稀疏的行为数据时。最后，我们提出使用DLM来支持适应性和个性化推荐系统，以促进行为改变。
