Automatic Detection of RWIS Sensor Malfunctions (Phase II)
Loading...
View/Download File
Persistent link to this item
Statistics
View StatisticsJournal Title
Journal ISSN
Volume Title
Title
Automatic Detection of RWIS Sensor Malfunctions (Phase II)
Published Date
2009-03
Publisher
University of Minnesota Center for Transportation Studies
Type
Report
Abstract
The overall goal of this project (Phases I & II) was to develop computerized procedures that detect Road Weather Information System (RWIS) sensor malfunctions. In the first phase of the research we applied three classification algorithms and six regression algorithms to data generated by RWIS sensors in order to predict malfunctions. In this phase we investigate the use of Hidden Markov models as predictors of sensor values.
The Hidden Markov model (HMM) is a technique used to model a sequence of temporal events. For example, suppose we have the sequence of values produced by a given sensor over a fixed time period. An HMM can be used to produce this sequence and then to determine the probability of occurrence of another sequence of values, such as that produced by the given sensor for a subsequent time period. If the actual values produced by the sensor deviate from the predicted sequence then a malfunction may have occurred.
This report provides an overview of the Hidden Markov model and three algorithms, namely, the Forward- Backward algorithms, the Baum-Welch algorithm, and the Viterbi algorithm, that were used in our development of Hidden Markov models to predict sensor values. We performed a series of experiments to evaluate the use of HMMs as predictors of temperature and precipitation sensor values.
Keywords
Description
Related to
Replaces
License
Collections
Series/Report Number
Funding information
Isbn identifier
Doi identifier
Previously Published Citation
Suggested citation
Crouch, Carolyn; Crouch, Donald; Maclin, Richard; Polumetla, Aditya. (2009). Automatic Detection of RWIS Sensor Malfunctions (Phase II). Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/97646.
Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.