Abstract. We are developing a personal activity recognition system that is practical, reliable, and can be incorporated into a variety of health-care related applications ranging from personal fitness to elder care. To make our system appealing and useful, we require it to have the following properties: (i) data only from a single body location needed, and it is not required to be from the same point for every user; (ii) should work out of the box across individuals, with personalization only enhancing its recognition abilities; and (iii) should be effective even with a cost-sensitive subset of the sensors and data features. In this paper, we present an approach to building a system that exhibits these properties and provide evidence based on data for 8 different activities collected from 12 different subjects. Our results indicate that the system has an accuracy rate of approximately 90 % while meeting our requirements. We are now developing a fully embedded version of our system based on a cell-phone platform augmented with a Bluetooth-connected sensor board. 1

We present the design, implementation, and deployment of a wearable computing platform for measuring and analyzing human behavior in organizational settings. We propose the use of wearable electronic badges capable of automatically measuring the amount of face-to-face interaction, conversational time, physical proximity to other people, and physical activity levels in order to capture individual and collective patterns of behavior. Our goal is to be able to understand how patterns of behavior shape individuals and organizations. By using on-body sensors in large groups of people for extended periods of time in naturalistic settings, we have been able to identify, measure, and quantify social interactions, group behavior, and organizational dynamics. We deployed this wearable computing platform in a group of 22 employees working in a real organization over a period of one month. Using these automatic measurements, we were able to predict employees ’ self-assessments of job satisfaction and their own perceptions of group interaction quality by combining data collected with our platform and e-mail communication data. In particular, the total amount of communication was predictive of both of these assessments, and betweenness in the social network exhibited a high negative correlation with group interaction satisfaction. We also found that physical proximity and e-mail exchange had a negative correlation of r = −0.55 (p <0.01), which has far-reaching implications for past and future research on social networks.

Sensor networks offer a powerful combination of distributed sensing, computing and communication. They lend themselves to countless applications and, at the same time, offer numerous challenges due to their peculiarities, primarily the stringent energy constraints to which sensing nodes are typically subjected. The distinguishing traits of sensor networks have a direct impact on the hardware design of the nodes at at least four levels: power source, processor, communication hardware, and sensors. Various hardware platforms have already been designed to test the many ideas spawned by the research community and to implement applications to virtually all fields of science and technology. We are convinced that CAS will be able to provide a substantial contribution to the development of this exciting field.

Abstract — In this paper, we combine inertial sensing and sensor network technology to create a pedestrian dead reckoning system. The core of the system is a lightweight sensor-andwireless-embedded device called NavMote that is carried by a pedestrian. The NavMote gathers information about pedestrian motion from an integrated magnetic compass and accelerometers. When the NavMote comes within range of a sensor network (composed of NetMotes), it downloads the compressed data to the network. The network relays the data via a RelayMote to an information center where the data are processed into an estimate of the pedestrian trajectory based on a dead reckoning algorithm. System details including the NavMote hardware/software, sensor network middleware services, and the dead reckoning algorithm are provided. In particular, simple but effective step detection and step length estimation methods are implemented in order to reduce computation, memory, and communication requirements on the Motes. Static and dynamic calibrations of the compass data are crucial to compensate the heading errors. The dead reckoning performance is further enhanced by wireless telemetry and map matching. Extensive testing results show that satisfactory tracking performance with relatively long operational time is achieved. The paper also serves as a brief survey on pedestrian navigation systems, sensors, and techniques. Index Terms — Pedestrian navigation system, dead reckoning, wireless sensor network. I.

The concept of replacing threads with flexible wires and sensors in a fabric to provide an underlying platform for integrating electronic components is known as e-textiles. This concept can be used to design applications involving di#erent types of electronic components including sensors, digital signal processors, microcontrollers, color-changing fibers, and power sources. The adaptability of the textiles to the needs of the individual and the functionality of electronics can be integrated to provide unobtrusive, robust, and inexpensive clothing with novel features. This thesis focuses on the design of e-textiles for acoustic signal processing applications. This research examines challenges encountered when developing e-textile applications involving distributed arrays of microphones. A framework for designing such applications is presented. The design process and the performance analysis of two e-textiles, a large-scale beamforming fabric and a speech-processing vest, are presented.

We propose a social network data collection method that uses wearable social sensors to automatically detect social interactions. This method offers clear advantages over traditional methods since data is automatically collected by electronic sensors rather than humans. We present the design, implementation and deployment of a wearable social sensing platform that can measure and analyze human behavior in a variety of settings and applications. Social sensors are capable of capturing individual and collective patterns of behavior by automatically measuring the amount of face-to-face interaction, conversational dynamics, physical proximity to other people, and physical activity levels. We describe five studies that have been carried out using this platform and discuss other possible application scenarios.

I.A. Emerging personal, social, and urban sensing applications Application context inevitably drives the architecture design choices and the definition of services needed in a network. Over the past decade, the emergence of unanticipated applications of the Internet, such as peer-to-peer file sharing, networked gaming, podcasting, and voice telephony, has contributed to a pressing need to rethink the core Internet infrastructure and its accompanying architectural choices. To truly lay a foundation for tomorrow’s infrastructure, however, requires going beyond simply reacting to applications that have already emerged, to proactively considering the architectural implications of new classes of applications. A key area in this regard involves embedded sensing technology, presently poised to moved beyond scientific, engineering, and industrial domains into broader and more diverse citizen-initiated sensing in personal, social and urban ones. Today, applications are emerging which draw on sensed information about people, objects, and physical spaces. These applications enable new kinds of social exchange: By collecting, processing, sharing, and visualizing this information, they can offer us new and unexpected views of our communities. To achieve their potential, these applications require fundamentally new algorithms and software mechanisms, because physical inputs now become critical. The research

We show how a wearable computing research platform for measuring and analyzing human behavior can be used to understand social systems. Using a wearable sociometric badge capable of automatically measuring the amount of face-to-face interaction, physical proximity to other people, and relative location, we are able to construct a dynamic view of an organization’s social network by viewing interactions as links between actors. Combining this with email data, where e-mail exchanges indicate a social tie, we are able to form a robust view of the social network, using proximity information to remove spurious e-mail exchanges. We attempt to use on-body sensors in large groups of people for extended periods of time in naturalistic settings for the purpose of identifying, measuring, and quantifying social interactions, information flow, and organizational dynamics. We discuss how this system can lead to an automatic intervention system that could optimize the social network in real time by facilitating the addition and removal of links based on objective metrics in a socially natural way. We deployed this research platform in a group of 22 employees working in a real organization over a period of one month, and we found that betweenness in the combined social network had a high negative correlation of r = −0.49 (p <0.05) with perceived group interaction quality.

Sociometric badges are wearable electronic badges capable of automatically measuring the amount of face-to-face interaction, conversational time, prosodic style, physical proximity to other people, and physical activity levels, using social signals derived from vocal features, body motion, and relative location. We present the prior and current state-of-the art in this area of wearable computing and propose several applications that haven’t been fully exploited.

While cameras have the potential to enable many applications in sensor networks, to be effective they first must be externally calibrated. In prior systems, cameras, identified by controllable light sources, utilized angular measurements amongst themselves to determine their relative positions and orientations. However, the typical camera’s narrow field of view makes such systems susceptible to failures in the presence of occlusions or non-ideal configurations. Actuation-assistance helps to overcome such issues by essentially broadening each camera’s view. In this paper we discuss and implement a prototype system that uses actuation to aid in the external calibration of camera networks. We evaluate our system using simulations and a testbed of MicaZ nodes, equipped with Cyclops camera modules mounted on custom pan-tilt platforms. Our results show that actuation-assistance can dramatically reduce node density requirements for localization convergence.