Jason S. Aronoff

Classification of patient movement events captured with a 6-axis inertial sensor

Patient monitoring is an important part of the overall treatment plan for hospital in-patients. However, monitoring is often time consuming for hospital staff. Staff must either remain in a patients room, check in on the patient with frequent intervals or remotely monitor the patient via video surveillance. Constant monitoring may be disruptive to the patient as he or she attempts to rest. Furthermore, all of these methods may be considered intrusive to the patients privacy and time-consuming for hospital staff which may result in increased medical costs. To mitigate these issues, we propose an alternate method of patient monitoring wherein a high-sensitivity 6-axis accelerometer is attached to the patients hospital bed. Using frequency-series analysis, we can extract relevant patterns for patient movement and train a classifier to identify movement patterns of the patient. Automated monitoring of the patients movement frees up time for hospital staff. The system can be configured to immediately notify staff when certain events are detected, thereby directing resources to where they are needed most. Event identification accuracy of 90% for a 12-class problem space was achieved.

Qualification of security printing features

This paper describes the statistical and hardware processes involved in qualifying two related printing features for their deployment in product (e.g. document and package) security. The first is a multi-colored tiling feature that can also be combined with microtext to provide additional forms of security protection. The color information is authenticated automatically with a variety of handheld, desktop and production scanners. The microtext is authenticated either following magnification or manually by a field inspector. The second security feature can also be tile-based. It involves the use of two inks that provide the same visual color, but differ in their transparency to infrared (IR) wavelengths. One of the inks is effectively transparent to IR wavelengths, allowing emitted IR light to pass through. The other ink is effectively opaque to IR wavelengths. These inks allow the printing of a seemingly uniform, or spot, color over a (truly) uniform IR emitting ink layer. The combination converts a uniform covert ink and a spot color to a variable data region capable of encoding identification sequences with high density. Also, it allows the extension of variable data printing for security to ostensibly static printed regions, affording greater security protection while meeting branding and marketing specifications.