WTNN: Weibull-Tailored Neural Networks for survival analysis
By: Gabrielle Rives, Olivier Lopez, Nicolas Bousquet
The Weibull distribution is a commonly adopted choice for modeling the survival of systems subject to maintenance over time. When only proxy indicators and censored observations are available, it becomes necessary to express the distribution's parameters as functions of time-dependent covariates. Deep neural networks provide the flexibility needed to learn complex relationships between these covariates and operational lifetime, thereby extending the capabilities of traditional regression-based models. Motivated by the analysis of a fleet of military vehicles operating in highly variable and demanding environments, as well as by the limitations observed in existing methodologies, this paper introduces WTNN, a new neural network-based modeling framework specifically designed for Weibull survival studies. The proposed architecture is specifically designed to incorporate qualitative prior knowledge regarding the most influential covariates, in a manner consistent with the shape and structure of the Weibull distribution. Through numerical experiments, we show that this approach can be reliably trained on proxy and right-censored data, and is capable of producing robust and interpretable survival predictions that can improve existing approaches.
Similar Papers
Modeling Complex Life Systems: Bayesian Inference for Weibull Failure Times Using Adaptive MCMC
Methodology
Predicts how long things will last, even when uncertain.
Estimated Phase II Weibull control chart for monitoring times between events
Applications
Finds problems in how things are made.
Survival Analysis as Imprecise Classification with Trainable Kernels
Machine Learning (CS)
Helps predict when things will happen, even with missing info.