Abstract
Sensor devices can be used to measure a large number of attributes in an environment (e.g., a job site, a building, a traffic intersection, and/or other constrained region). These sensors can generate a significant amount of measurement data over time. However, it is challenging to synthesize and process this large amount of data to produce a meaningful understanding of events as they occur. This is particularly true for arbitrary, custom, or otherwise uncommon events which may be of interest only to certain limited users or in certain limited situations.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Bertsch, Fred, "Sensor Network Trained To Understand Arbitrary Labels", Technical Disclosure Commons, (August 29, 2018)
https://www.tdcommons.org/dpubs_series/1477