Abstract. In this work, algorithms are developed and evaluated to detect physical activities from data acquired using five small biaxial accelerometers worn simultaneously on different parts of the body. Acceleration data was collected from 20 subjects without researcher supervision or observation. Subjects were asked to perform a sequence of everyday tasks but not told specifically where or how to do them. Mean, energy, frequency-domain entropy, and correlation of acceleration data was calculated and several classifiers using these features were tested. Decision tree classifiers showed the best performance recognizing everyday activities with an overall accuracy rate of 84%. The results show that although some activities are recognized well with subject-independent training data, others appear to require subject-specific training data. The results suggest that multiple accelerometers aid in recognition because conjunctions in acceleration feature values can effectively discriminate many activities. With just two biaxial accelerometers – thigh and wrist – the recognition performance dropped only slightly. This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves. 1

WatchMe is a personal communicator with context awareness in a wristwatch form; it is meant to keep intimate friends and family always connected via awareness cues and text, voice instant message, or synchronous voice connectivity. Sensors worn with the watch track location (via GPS), acceleration, and speech activity; this is classified and conveyed to the other party, where it appears in iconic form on the watch face. When a remote person with whom this information is shared examines it, their face appears on the watch of the person being checked on. The working prototype was used as the focus of interviews to gauge the desirability of such a device.

Abstract. As the proliferation of pervasive and ubiquitous computing devices continues, users will carry more devices. Without the ability for these devices to unobtrusively interact with one another, the user’s attention will be spent on coordinating, rather than using, these devices. We present a method based on a coherence function, a measure of linear correlation in the frequency domain, to reliably analyze walking data recorded by low-cost MEMS accelerometers to determine if two devices are carried by the same person. We use inexpensive accelerometers and show that these sensors perform similarly to more expensive accelerometers for the frequency range of human motion, 0 to 10Hz. We also present results from a large test group illustrating the algorithm’s robustness and its ability to withstand real world time delays, crucial for wireless technologies like Bluetooth and 802.11. We present results that show that our technique is 100 % accurate using a sliding window of 8 seconds of data and the devices are carried in the same location on the body (we also present results for when devices are carried on different parts of the body), is tolerant to

In this paper we describe LiveNet, a flexible wearable platform intended for long-term ambulatory health monitoring with real-time data streaming and context classification. Based on the MIT Wearable Computing Group’s distributed mobile system architecture, LiveNet is a stable, accessible system that combines inexpensive, commodity hardware; a flexible sensor/peripheral interconnection bus; and a powerful, light-weight distributed sensing, classification, and inter-process communications software architecture to facilitate the development of distributed real-time multi-modal and context-aware applications. LiveNet is able to continuously monitor a wide range of physiological signals together with the user's activity and context, to develop a personalized, data-rich health profile of a user over time. We demonstrate the power and functionality of this platform by describing a number of health monitoring applications using the LiveNet system in a variety of clinical studies that are underway. Initial evaluations of these pilot experiments demonstrate the potential of using the LiveNet system for real-world applications in rehabilitation medicine.

Ubiquitous, context-aware computer systems may ultimately enable computer applications that naturally and usefully respond to a user's everyday activity. Although new algorithms that can automatically detect context from wearable and environmental sensor systems show promise, many of the most flexible and robust systems use probabilistic detection algorithms that require extensive libraries of training data with labeled examples. In this paper, we describe the need for such training data and some challenges we have identified when trying to collect it while testing three contextdetection systems for ubiquitous computing and mobile applications. Author Keywords Context-aware, ubiquitous, computing, supervised learning, experience sampling, user interface design ACM Classification Keywords H5.m Information interfaces and presentation (e.g. HCI): Miscellaneous.

www.wearable.ethz.ch 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 (e.g. 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. 1

The proliferation of mobile devices and their tendency to present information proactively has led to an increase in device generated interruptions experienced by users. These interruptions are not confined to a particular physical space and are omnipresent. One possible strategy to lower the perceived burden of these interruptions is to cluster non-time-sensitive interruptions and deliver them during a physical activity transition. Since a user is already “interrupting ” the current activity to engage in a new activity, the user will be more receptive to an interruption at this moment. This work compares the user’s receptivity to an interruption triggered by an activity transition against a randomly generated interruption. A mobile computer system detects an activity transition with the use of wireless accelerometers. The results demonstrate that using this strategy reduces the perceived burden of the interruption.