No abstract

Recent developments of information technologies are leading the advent of the era of ubiquitous healthcare, which means healthcare services at any time and at any places. The ubiquitous healthcare service needs a wearable system for more continual measurement of biological signals of a user, which gives information of the user from wearable sensors. In this paper, we propose a wearable context aware system for ubiquitous healthcare, and its systematic design process of a ubiquitous healthcare service. Some wearable sensor systems are introduced with Zigbee communication. We develop a context aware framework to send information from wearable sensors to healthcare service entities as a middleware to solve the interoperability problem between sensor makers and healthcare service providers. And, we propose a systematic process of design of ubiquitous healthcare services with the context aware framework. In order to show the feasibility of the proposed system, some application examples are given, which are applied to remote monitoring, and a self check service.

No abstract

For video understanding, namely analyzing who did what in a video, actions along with objects are primary elements. Most studies on actions have handled recognition problems for a well-trimmed video and focused on enhancing their classification performance. However, action detection, including localization as well as recognition, is required because, in general, actions intersect in time and space. In addition, most studies have not considered extensibility for a newly added action that has been previously trained. Therefore, proposed in this paper is an extensible hierarchical method for detecting generic actions, which combine object movements and spatial relations between two objects, and inherited actions, which are determined by the related objects through an ontology and rule based methodology. The hierarchical design of the method enables it to detect any interactive actions based on the spatial relations between two objects. The method using object information achieves an F-measure of 90.27%. Moreover, this paper describes the extensibility of the method for a new action contained in a video from a video domain that is different from the dataset used.

No abstract