Time-to-event analysis is important in a wide range of applications from clinical prognosis to risk modeling for credit scoring and insurance. In risk modeling, it is sometimes required to make a simultaneous assessment of the hazard arising from two or more mutually exclusive factors. This paper applies to an existing neural network model for competing risks (PLANNCR), a Bayesian regularization with the standard approximation of the evidence to implement automatic relevance determination (PLANNCR-ARD). The theoretical framework for the model is described and its application is illustrated with reference to local and distal recurrence of breast cancer, using the data set of Veronesi (1995).

Explicit finite element (FE) and multi-body dynamics (MBD) models have been developed to evaluate total knee replacement (TKR) mechanics as a complement to experimental methods. In conjunction with these models, probabilistic methods have been implemented to predict performance bounds and identify important parameters, subject to uncertainty in component alignment and experimental conditions. Probabilistic methods, such as advanced mean value (AMV) and response surface method (RSM), provide an efficient alternative to the gold standard Monte Carlo simulation technique (MCST). The objective of the current study was to benchmark models from three platforms (two FE and one MBD) using various probabilistic methods by predicting the influence of alignment variability and experimental parameters on TKR mechanics in simulated gait. Predicted kinematics envelopes were on average about 2.6 mm for tibial anterior–posterior translation, 2.9° for tibial internal–external rotation and 1.9 MPa for tibial peak contact pressure for the various platforms and methods. Based on this good agreement with the MCST, the efficient probabilistic techniques may prove useful in the fast evaluation of new implant designs, including considerations of uncertainty, e.g. misalignment.

The purpose of this paper is to explore both an extended and a reduced set of input parameters of the Finite Element (FE) model of the human lower limb with a Total Knee Replacement (TKR) implant. The most influential parameters in determining the size and the shape of the performance envelopes of eight kinematics and peak contact pressure output variables of the tibio-femoral joint and the patello-femoral joint are sought. The lower limb FE model, which includes bones, TKR implant, soft tissues and applied forces of realistic size, is used in the context of the stair ascent simulation. Two probabilistic methods are used together with the FE model to generate the performance envelopes and to explore the sensitivities of the input parameters of the FE model: the Monte Carlo simulation and the Response Surface Method (RSM). A total of four probabilistic FE analyses assess how the uncertainties in an extended set of 77 input variables and a reduced set of 22 input variables obtained from the RSM/sensitivity analyses affect the performance envelopes. It is shown that the FE model with the reduced set of variables is able to replicate the full FE model. The differences between the Monte Carlo envelopes of performance obtained with the FE model with the full set of variables and the FE model with the reduced set of variables were on average over all output measures under 1.67 mm for translations, 1.75° for rotations and under 2 MPa for peak contact pressures. The differences between the RSM and the Monte Carlo envelopes of performances obtained with the reduced set of input variables were, on average, over all output measures under 0.75 mm for translations, 1.26° for rotations and 2.39 MPa for peak contact pressures. While saving computational time with the reduced set of variables, the findings are especially of high importance to the orthopedic surgeons who would like to know the most important parameters that can influence the performance of the TKR for a given human activity.

This paper presents an efficient and effective Decision Support System (DSS) for operational monitoring and control of water distribution systems based on a three layer General Fuzzy Min-Max Neural Network (GFMMNN) and graph theory. The operational monitoring and control involves detection of pipe leakages. The training data for the GFMMNN is obtained through simulation of leakages in a water network for a given operational period. The training data generation scheme includes a simulator algorithm based on loop corrective flows equations, a Least Squares (LS) loop flows state estimator and a Confidence Limit Analysis (CLA) algorithm for uncertainty quantification entitled Error Maximization (EM) algorithm. These three numerical algorithms for modeling and simulation of water networks are based on loop corrective flows equations and graph theory. It is shown that the detection of leakages based on the training and testing of the GFMMNN with patterns of variation of nodal consumptions with or without confidence limits is computational superior to the training based on patterns of nodal heads and pipe flows state estimates with or without confidence limits and to the original recognition system trained with patterns of data obtained with the LS nodal heads state estimator.