1994/01/01 by Chris Bishop · 2 citations
Engineering · #Oil and Gas Production Techniques #Reservoir Engineering and Simulation Methods #Water Systems and Optimization #Novelty #Computer science #Novelty detection #Reliability (semiconductor) #Artificial neural network #Key (lock) #Data mining #Pipeline transport #Data validation #Artificial intelligence #Machine learning #Engineering #Database
paper · doi:10.1049/ip-vis:19941330
openalex publication_date 1994/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/05/05
One of the key factors which limits the use of neural networks in many industrial applications has been the difficulty of demonstrating that a trained network will continue to generate reliable outputs once it is in routine use. An important potential source of errors is novel input data; that is, input data which differ significantly from the data used to train the network. The author investigates the relationship between the degree of novelty of input data and the corresponding reliability of the outputs from the network. He describes a quantitative procedure for assessing novelty, and demonstrates its performance by using an application which involves monitoring oil flow in multiphase pipelines.