Gietzelt Matthias, Wolf Klaus-Hendrik, Haux Reinhold
Peter L. Reichertz Institute for Medical Informatics, University of Braunschweig - Institute of Technology and Hannover Medical School, Germany.
Stud Health Technol Inform. 2011;169:460-4.
Due to the progress in technology, it is possible to capture continuous sensor data pervasively and ubiquitously. In the area of health-enabling and ambient assisted technologies we are faced with the problem of analyzing these data in order to improve or at least maintain the health status of patients. But due to the interdisciplinarity of this field every discipline makes use of their own analyzing methods. In fact, the choice of a certain analyzing method often solely depends on the set of methods known to the data analyst. It would be an advantage if the data analyst would know about all available analyzing methods and their advantages and disadvantages when applied to the manifold of data. In this paper we propose a nomenclature that structures existing analyzing methods and assists in the choice of a certain method that fits to a given measurement context and a given problem.
由于技术的进步,现在有可能普遍且无处不在地捕获连续的传感器数据。在健康促进和环境辅助技术领域,我们面临着分析这些数据以改善或至少维持患者健康状况的问题。但由于该领域的跨学科性质,每个学科都使用自己的分析方法。实际上,特定分析方法的选择通常仅取决于数据分析师所熟知的方法集。如果数据分析师了解所有可用的分析方法及其在应用于多种数据时的优缺点,那将是一个优势。在本文中,我们提出了一种命名法,该命名法对现有的分析方法进行了结构化,并有助于选择适合给定测量环境和给定问题的特定方法。