A data-driven method for detecting and diagnosing causes of water quality contamination in a dataset with a high rate of missing values.
Raymond Houé NgounaRomy RatolojanaharyKamal MedjaherFabien DauriacMathieu SebiloJean Junca-BouriéPublished in: Eng. Appl. Artif. Intell. (2020)
Keyphrases
- missing values
- high rate
- water quality
- low rate
- imputation methods
- missing data
- false alarms
- data imputation
- water treatment
- incomplete data
- missing data imputation
- measured data
- water resources
- incomplete data sets
- missing information
- high dimensional data
- learning algorithm
- detection rate
- false positives
- semi supervised
- computational cost
- feature space
- missing attribute values
- neural network
- data sets