The first three authors contributed equally to the paper and their names are in alphabetical order. The authors are grateful to Patrik Floréen and the anonymous reviewers for commenting on the paper.Abstract-We present BeTelGeuse, an extensible data collection platform for mobile devices. BeTelGeuse supports collecting data from various sources, and it also automatically infers higher level context from sensor data. In this article we introduce the architecture and current features of BeTelGeuse. We also evaluate the impact BeTelGeuse has on the performance of a mobile phone, and present case studies of situations where we have used BeTelGeuse.
We introduce a grocery retrieval system that maps shopping lists written in natural language into actual products in a grocery store. We have developed the system using nine months of shopping basket data from a large Finnish supermarket. To evaluate the system, we used 70 real shopping lists gathered from customers of the supermarket. Our system achieves over 80% precision for products at rank one, and the precision is around 70% for products at rank 5.
We propose a grid-based GSM positioning algorithm that can be deployed entirely on mobile devices. The algorithm uses Gaussian distributions to model signal intensity variations within each grid cell. Position estimates are calculated by combining a probabilistic centroid algorithm with particle filtering. In addition to presenting the positioning algorithm, we describe methods that can be used to create, update and maintain radio maps on a mobile device. We have implemented the positioning algorithm on Nokia S60 and Nokia N900 devices and we evaluate the algorithm using a combination of offline and real world tests. The results indicate that the accuracy of our method is comparable to state-of-the-art methods, while at the same time having significantly smaller storage requirements.
In ubiquitous computing, activity-related data is typically gathered using customized sensing equipment that give physiological measurements. Unfortunately, such systems are often proprietary or expensive to obtain. Recently, the decrease in the prices of Bluetooth chips has made Bluetooth sensors a viable alternative. In previous research, various systems for gathering data from Bluetooth sensors have been proposed, but they are usually limited to a specific set of sensors or to a specific runtime platform. To address these shortcomings, we have developed BeTelGeuse, a tool for Bluetooth data gathering. BeTelGeuse turns a standard mobile device such as a cellular phone into a relay node which gathers data from a body area network over Bluetooth, and forwards it to a remote server over a mobile data service such as GPRS.
Current mobile phones provide GSM cell information and many devices also support GPS or WiFi-based location information. A problem with raw location data is that it does not provide semantic information, which makes it hard to integrate location-awareness into applications. Moreover, to understand what kind of location information is important to users, researchers currently need to perform time consuming user studies. In this paper we introduce SerPens, a tool that enables gathering semantically enriched location information on personal devices. The main novelty of SerPens is that it enables users to share and gather semantic information in a collaborative fashion. The label information is tied to a taxonomy and is accessible to applications. SerPens has been developed on top of BeTelGeuse, a Bluetooth-based data gathering tool for J2ME compatible devices.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.