A Framework to Improve Energy Efficient Behaviour at Home through Activity and Context Monitoring.
A Framework to Improve Energy Efficient Behaviour at Home through Activity and Context Monitoring.
复制标题
DOI：
10.3390/s17081749
复制
发表时间：
2017-07-31
期刊：
影响因子：
--
通讯作者：
Corchado JM
中科院分区：
文献类型：
--
作者：
García Ó;Prieto J;Alonso RS;Corchado JM
实时定位系统被认为是开发提供定制服务的应用程序的最合适的技术之一。这些系统为我们提供了定位和跟踪用户的能力，除其他功能外，它们还有助于识别行为模式和习惯。此外，实施促进家庭节能的政策是一项复杂的任务，涉及使用这种类型的系统。虽然在这一领域有多个提案，但实施联合收割机技术并使用社会计算来影响用户行为的框架尚未在能源方面实现任何显著的节省。在这项工作中，CAFCLA框架（上下文感知框架协作学习应用程序）被用来开发一个推荐系统的家庭用户。所提出的系统集成了实时定位系统和无线传感器网络，使得有可能开发的应用程序，在社会计算的保护伞下工作。实验用例的实施有助于有效使用能源，节省了17%。此外，所进行的案例研究指出，从长远来看，有可能养成良好的能源消费习惯。这要归功于系统的真实的时间和历史定位、跟踪和上下文数据，基于这些数据生成定制的建议。
Real-time Localization Systems have been postulated as one of the most appropriated technologies for the development of applications that provide customized services. These systems provide us with the ability to locate and trace users and, among other features, they help identify behavioural patterns and habits. Moreover, the implementation of policies that will foster energy saving in homes is a complex task that involves the use of this type of systems. Although there are multiple proposals in this area, the implementation of frameworks that combine technologies and use Social Computing to influence user behaviour have not yet reached any significant savings in terms of energy. In this work, the CAFCLA framework (Context-Aware Framework for Collaborative Learning Applications) is used to develop a recommendation system for home users. The proposed system integrates a Real-Time Localization System and Wireless Sensor Networks, making it possible to develop applications that work under the umbrella of Social Computing. The implementation of an experimental use case aided efficient energy use, achieving savings of 17%. Moreover, the conducted case study pointed to the possibility of attaining good energy consumption habits in the long term. This can be done thanks to the system’s real time and historical localization, tracking and contextual data, based on which customized recommendations are generated.
登录
查看更多内容
DOI：
10.4018/978-1-4666-7284-0.ch012
发表时间：
2015-01-01
期刊：
RECENT ADVANCES IN AMBIENT INTELLIGENCE AND CONTEXT-AWARE COMPUTING
影响因子：
--
作者：
Garcia, Oscar;Tapia, Dante I.;Corchado, Juan M.
通讯作者：
Corchado, Juan M.
影响因子：
7.4
作者：
Aerts, D.;Minnen, J.;Descamps, F.
通讯作者：
Descamps, F.
影响因子：
8.7
作者：
Anda, Martin;Temmen, Justin
通讯作者：
Temmen, Justin
影响因子：
6.7
作者：
Feng, Xiaohang;Yan, Da;Hong, Tianzhen
通讯作者：
Hong, Tianzhen
DOI：
10.3390/s17030643
发表时间：
2017-03-21
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Blanco-Novoa Ó;Fernández-Caramés TM;Fraga-Lamas P;Castedo L
通讯作者：
Castedo L