Context awareness

About: Context awareness is a research topic. Over the lifetime, 5790 publications have been published within this topic receiving 119944 citations.

Weakly Supervised Recognition of Daily Life Activities with Wearable Sensors

Abstract: This paper considers scalable and unobtrusive activity recognition using on-body sensing for context awareness in wearable computing. Common methods for activity recognition rely on supervised learning requiring substantial amounts of labeled training data. Obtaining accurate and detailed annotations of activities is challenging, preventing the applicability of these approaches in real-world settings. This paper proposes new annotation strategies that substantially reduce the required amount of annotation. We explore two learning schemes for activity recognition that effectively leverage such sparsely labeled data together with more easily obtainable unlabeled data. Experimental results on two public data sets indicate that both approaches obtain results close to fully supervised techniques. The proposed methods are robust to the presence of erroneous labels occurring in real-world annotation data.

Enabling location-aware pervasive computing applications for the elderly

Abstract: The Pervasive Computing Laboratory at the University of Florida is dedicated to creating smart environments and assistants to enable elderly persons to live a longer and a more independent life at home. By achieving this goal, technology will increase the chances of successful aging despite an ailing health care system (e.g. Medicaid). One of the essential services required to maximize the intelligence of a smart environment is an indoor precision tracking system. Such system allows the smart home to make proactive decisions to better serve its occupants by enabling context-awareness instead of being solely reactive to their commands. This paper presents our hands-on experience and lessons learnt from our first phase work to build up a smart home infrastructure for the elderly. We review location tracking technology and describe the rationale behind our choice of the emerging ultrasonic sensor technology. We give an overview of the House of Matilda (an in-laboratory mock up house) and describe our design of a precision in-door tracking system. We also describe an OSGi-based robust framework that abstracts the ultrasonic technology into a standard service to enable the creation of tracking based applications by third party, and to facilitate the collaboration among various devices and other OSGi services. Finally, we describe three pervasive computing applications that use the location-tracking system which we have implemented in Matilda's house.

Where am i: recognizing on-body positions of wearable sensors

Abstract: The paper describes a method that allows us to derive the location of an acceleration sensor placed on the user's body solely based on the sensor's signal The approach described here constitutes a first step in our work towards the use of sensors integrated in standard appliances and accessories carried by the user for complex context recognition It is also motivated by the fact that device location is an important context (eg glasses being worn vs glasses in a jacket pocket) Our method uses a (sensor) location and orientation invariant algorithm to identify time periods where the user is walking and then leverages the specific characteristics of walking motion to determine the location of the body-worn sensor In the paper we outline the relevance of sensor location recognition for appliance based context awareness and then describe the details of the method Finally, we present the results of an experimental study with six subjects and 90 walking sections spread over several hours indicating that reliable recognition is feasible The results are in the low nineties for frame by frame recognition and reach 100% for the more relevant event based case

An investigation of attitudes of students and teachers about participating in a context-aware ubiquitous learning activity

Abstract: In recent years, digital learning has been converting from e-learning to m-learning because of the significant growth of wireless and mobile computing technologies. Students can learn any time and any where with mobile devices. Consequently, context-aware ubiquitous learning (u-learning) is emerging as a new research area. It integrates wireless, mobile and context awareness technologies in order to detect the situation of the learners and provide more seamless adaptive support in the learning process. In this paper, a context-aware u-learning environment is developed for learning about campus vegetation in elementary schools based on an innovative approach by employing repertory grid method in designing learning content. In addition, we probe the feasibility of context-aware u-learning in courses by soliciting feedback from the students and teachers through interviews and questionnaires. The findings reveal that the environment is capable of enhancing students’ motivation and learning effectiveness. Moreover, it is also capable of reducing the teaching load while enabling better control of class order.