Earticle

To realize context aware applications for smart home environments, it is necessary to recognize function or usage of objects as well as categories of them. On conventional research for environment recognition in an indoor environment, most of previous methods are based on shape models. In this paper, we propose a method for recognizing objects focused on the relationship between human actions and functions of objects. Such relationship becomes obvious on human action patterns when he or she handles an object. To estimate object categories by using action patterns, we represent such relationship in Dynamic Bayesian Networks (DBNs). By learning human actions toward objects statistically, objects can be recognized. Finally, we performed experiments and confirmed that objects can be recognized from human actions without shape models.

Since the emergence of the smart-home concept, many devices, interfaces and controllers have become available. However, there is a problem: each component usually performs a single function and there is no synchronization with other components. In order to exploit the great potential of the new technologies that these devices embody, as a base for synchronizing devices, interfaces and intelligent control systems, a universal model is required. The current paper offers a universal, comprehensive model for a smart home. Drawing upon existing protocols and technologies, it illustrates how to integrate different devices, software, and user interfaces to create a smart home. The model emphasizes four principles: A universal model can substantially lead to higher quality and usability of both devices and user interface; Production costs may be significantly reduced if manufacturers adopt a universal standard; The model synchronizes different groups of devices. This makes it possible to program complex scenarios leading to improved and enhanced smart-home utilization; Based on current available communication standards and infrastructure, the model can easily be installed in any house. Proposed smart-home architecture comprises - in addition to appliances and communication interfaces - a central management unit and a built-in database for smart equipment integration, for creating and implementing pre-programmed complex scenarios. The central management unit application and database store an up-to-date list of all connected devices. Any new integrated device is synchronized upon connection and removed when not in use. This is done automatically by sending any shared data (list of properties, commands, optional streaming, etc.) into the database upon initial connection.

The home automation market is characterized by the great number of systems available to the end user. The recent bubble in the building industry made the situation even worse due to the birth of new proprietary systems. The success of the digital home concept depends on the ease of integration between home automation systems and other consumer electronic equipment pre-existing in the home. In this paper the interoperability issue is addressed and the approach followed in the project DomoEsi is presented.