An Annotation Method for Sensor Data Streams based on Statistical Patterns

A. Takasu and K. Aihara (Japan)


Information Searches, Engineering Database, Hidden Markov Model


Due to recent advances in sensor technology greater quan tities of sensor data are being generated and circulated. In these circumstances, sensor data stream processing and management technologies have become important research areas. In the development of mechanical and electrical sys tems, sensor stream data are a potential medium for shar ing information among the engineers who are engaged in the various phases in the system development and opera tion. This paper proposes an annotation method for a sen sor data stream that links the information generated in the development and operational phases of a system. The key techniques of the proposed method are sensor pattern con struction using hidden Markov models (HMMs) and an an notation method based on the HMMs constructed. We ap plied the proposed method to the sensor data stream of a supersmall artificial satellite and showed that the proposed method achieved approximately 95% annotation accuracy for long fragments of the sensor data stream.

Important Links:

Go Back