We describe a wireless wearable system that was developed to provide quantitative gait analysis outside the confines of the traditional motion laboratory. The sensor suite includes three orthogonal accelerometers, three orthogonal gyroscopes, four force sensors, two bidirectional bend sensors, two dynamic pressure sensors, as well as electric field height sensors. The "GaitShoe" was built to be worn in any shoe, without interfering with gait and was designed to collect data unobtrusively, in any environment, and over long periods. The calibrated sensor outputs were analyzed and validated with results obtained simultaneously from the Massachusetts General Hospital, Biomotion Laboratory. The GaitShoe proved highly capable of detecting heel-strike and toe-off, as well as estimating foot orientation and position, inter alia.

This paper presents a framework for power-efficient detection in embedded sensor systems. State detection is structured as a decision tree classifier that dynamically orders the activation and adjusts the sampling rate of the sensors (termed groggy wakeup), such that only the data necessary to determine the system state is collected at any given time. This classifier can be tuned to trade-off accuracy and power in a structured, parameterized fashion. An embedded instantiation of these classifiers, including real-time sensor control, is described. An application based on a wearable gait monitor provides quantitative support for this framework. The decision tree classifiers achieved roughly identical detection accuracies to those obtained using support vector machines while drawing three times less power. Both simulation and real-time operation of the classifiers demonstrate that our multi-tiered classifier determines states as accurately as a single-trigger (binary) wakeup system while drawing as little as half as much power and with only a negligible increase in latency.

We have designed and constructed a modular platform for use in compact wireless sensing. This platform is based around a series of circuit boards (or panes), each of which instantiates a specific sensing modality - e.g. inertial sensing, tactile sensing or ambient sensing. As opposed to similar architectures, this system treats the sensor panes as discrete design objects that have data collection as their primary purpose. The main goals achieved by this design are ease of prototyping (and revision) and encapsulation of design knowledge. We describe a number of different projects instantiated with this system. Key among them are a wearable gait measurement system which exploited the modularity of the system, a novel musical controller which benefited from the design encapsulation and a study of dynamically low-power sensor nodes based on the structure of the panes (i.e. multiple sensors for a single modality). Several other applications are discussed. Lessons learned in the areas of software design, sensor placement and mechanical stability are commented on.