Using Neural Networks to Create New Indices and Classification Schemes

  • Brion, Gail (PI)
  • Lingireddy, Srinivasa (CoI)

Grants and Contracts Details


Objectives: To reduce the risk of waterborne disease by creating new indices and classification schemes based upon advanced fuzzy logic based computing techniques. The hypothesis we will prove meeting this objective is IIShifts in indicator and indigenous bacterial populations can be reliably mathematically related by neural network models to the presence, concentration, age, and source of microbial pathogens. " Ap~roac~: Creation of a robust, multi-year, multi season, multiparameter database of water quality at a sIngle Intake on the Kentucky River that contains new indices relative to the age and source of fecal material. This database will also contain measures of potential pathogens and related or suggested indices. Conventional statistical analysis and advanced neural network analysis will be applied to the resultant database to uncover: . Relationships between pathogen presence and indices, both new and conventional. . Predictive models that take into account watershed characteristics such as rainfall, seasonality, and flow patterns. . Classification schemes that indicate the predominant sources, and relative ages, of fecal contamination under varying conditions. In concert with this data collection and modeling effort will be laboratory scale survival studies to elucidate the relationships between pathogens and indices survival in natural waters. The information from the survival studies will provide decay models to be linked with the neural network modeling efforts for river water quality data to accurately track source and age of pollution. Special attention will be paid to the survival of pathogens relative to the new bacterial ratio indices that have been identified by the investigators over the last years. The relative densities and ratios of bacterial populations have already been used by the PIs to train neural network models to classify fecal source (human sewage versus runoff) and age of fecal materials in runoff. What is needed now is a single, long-term, controlled study of the ecology and survival of mixed bacterial populations and their relationship with pathogens. By understanding how these populations shift with time, and by using the power of neural network modeling to illuminate these this newly discovered bacterial ratio, interrelationships, new types of indices and classification schemes can be developed that can be tailored to capture the individuality of watersheds resulting in the prevention of disease.
Effective start/end date7/1/026/30/06


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.