We used Fisher linear discriminant analysis (LDA), static neural networks (NN), and focused time delay neural networks (TDNN) for gesture recognition. Gestures were collected in form of acceleration signals along three axes from six participants. A sports watch containing a 3-axis accelerometer, was worn by the users, who performed four gestures. Each gesture was performed for ten seconds, at the speed of one gesture per second. User-dependent and userindependent k-fold cross validations were carried out to measure the classifier performance. Using first and second order statistical descriptors of acceleration signals from validation datasets, LDA and NN classifiers were able to recognize the gestures at an average rate of 86% and 97% (user-dependent) and 89% and 85% (user-independent), respectively. TDNNs proved to be the best, achieving near perfect classification rates both for user-dependent and userindependent scenarios, while operating directly on the acceleration signals alleviating the need for explicit feature extraction.

No abstract

An embedded telemetry unit for bone strain monitoring is presented. The telemetry unit is designed using commercially available components to lower design time and manufacturing costs. The unit can read up to eight strain gauges and measures 2.4 cm × 1.3 cm × 0.7 cm. The unit is powered from a small Li-polymer battery that can be recharged wirelessly through tissue, making it suitable for implanted applications. The average current consumption of the telemetry unit is 1.9 mA while transmitting at a rate of 75 kps and at a sampling rate of 20 Hz. The telemetry unit also features a power-down mode to minimize its power consumption when it is not in use. The telemetry unit operates in the 915-MHz ISM radio band. The unit was tested in an ex vivo setting with an ulna bone from a mouse and in a simulated in vivo setting with a phantom tissue. Bone strain data collected ex vivo shows that the telemetry unit can measure strain with an accuracy comparable to a more expensive benchtop data acquisition system.

No abstract

No abstract