Browsing by Author "Polumetla, Aditya"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Automatic Detection of RWIS Sensor Malfunctions (Phase I)
    (University of Minnesota Center for Transportation Studies, 2009-03) Crouch, Carolyn; Crouch, Donald; Maclin, Richard; Polumetla, Aditya
    The overall goal of this project was to develop computerized procedures that detect Road Weather Information System (RWIS) sensor malfunctions. In this phase of the research we applied two classes of machine learning techniques to data generated by RWIS sensors in order to predict sensor malfunctions and thereby improve accuracy in forecasting temperature, precipitation, and other weather-related data. We built models using machine learning methods that employ data from nearby sensors in order to predict likely values of those sensors that are being monitored. A sensor that deviates noticeably from values inferred from nearby sensors indicates that the sensor has begun to fail. We used both classification and regression algorithms in Phase I. In particular, we used three classification algorithms (namely, J48 decision trees, naïve Bayes, and Bayesian networks) and six regression algorithms (that is, linear regression, least median squares, M5P, multilayer perceptron, radial basis function network, and the conjunctive rule algorithm). We performed a series of experiments to determine which of these models can be used to detect malfunctions in RWIS sensors. We compared the values predicted by the various machine learning methods to the actual values observed at an RWIS sensor to detect sensor malfunctions. This report provides an overview of the nine models used and a classification of the applicability of each model to the detection of RWIS sensor malfunctions.
  • Thumbnail Image
    Item
    Automatic Detection of RWIS Sensor Malfunctions (Phase II)
    (University of Minnesota Center for Transportation Studies, 2009-03) Crouch, Carolyn; Crouch, Donald; Maclin, Richard; Polumetla, Aditya
    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.