Nonlinear Modeling Techniques Research Articles

Long-term seasonal rainfall forecasting using linear and non-linear modelling approaches: a case study for Western Australia

This paper presents the comparison of the performances between the linear and non-linear modelling techniques in re-generating the patterns of long-term seasonal rainfall in Western Australia. To construct the linear and non-linear models, commonly adopted multiple linear regression (MLR) and artificial neural network (ANN) modelling approaches were applied. Lagged (past) values of the oceanic climate drivers, El Nino Southern Oscillation (ENSO) and Indian Ocean Dipole (IOD) were considered to be the prospective forecasters of seasonal rainfall. The MLR models which were statistically significant and not susceptible to multicollinearity problems were considered as the potential models. The Lavenberg–Marquardt algorithm with Multilayer Perceptron training rule was adopted to construct the non-linear ANN models. The capability of both the MLR and ANN models were evaluated through commonly used statistical parameters. Since rainfall vary not only temporally but also spatially, the analysis were performed on regional scale. The methods were applied to three Western Australian rainfall stations. As expected, in estimating Western Australian spring rainfalls, non-linear ANN models performed much better compared to MLR models in regards to Pearson correlation as well as statistical errors.

Performance monitoring of wind turbines using advanced statistical methods

Estimation of wind power generation for grid interface helps in calculation of the annual energy production, which maintains the balance between electricity production and its consumption. For this purpose, accurate wind speed forecasting plays an important role. In this paper, linear statistical predictive models such as autoregressive integrated moving average (ARIMA), generalized autoregressive score (GAS) model and a GAS model with exogenous variable x (GASX) have been applied for accurate wind speed forecasting. Along with this, a non-linear statistical predictive modelling technique called non-linear GASX (NLGASX) has been proposed and applied to model non-linear time-series data. Furthermore, the proposed NLGASX model is optimized using modelling techniques based on neural networks, namely Sigmoid, TANH, Softmax and RELU. The proposed optimized NLGASX model performs far better as compared with other models. Wind speed is also used as an input to wind power curve model for predicting the wind power. According to the predicted wind power the annual energy has been calculated.

Estimating the global solar radiation in Putrajaya using the Angstrom-Prescott model

Global solar radiation (GSR) studies are essential in enhancing the use of solar PV systems especially for Building Integrated PV system (BIPV). Various studies on GSR had been carried out in Malaysia including Penang, Kuala Lumpur and Kota Bharu at the earlier stage. Afterward, data from the Malaysian Meteorological Department (MET) and the Malaysian National University were used to estimate the monthly average daily global radiation for various locations in Malaysia including Kuala Lumpur, Kuala Lumpur, Petaling Jaya, Bandar Baru Bangi, Kota Baru, Senai, Bayan Lepas, Kuching and Kota Kinabalu. GSR in Putrajaya, a location which has identified to implement Malaysian Building Integrated Photovoltaic (MBIPV) projects has yet to be estimated. The conventional method to obtain the amount of GSR at a location is to install a measuring device like a pyranometer at the site to observe and document its day-to-day recordings. However, this is a time-consuming and costly practice. The models used to estimate the GSR are usually based on astronomical factors, geometrical factors, physical factors and meteorological factors. There are numerous models used to predict GSR which can be categorized based on sunshine, cloud, temperature and other meteorological parameters. Additionally, the global solar energy models can be grouped by its modelling techniques such as linear, nonlinear, artificial intelligence and fuzzy logic modelling techniques. The reviews discovered that the models used to estimate GSR were mostly correlated to sunshine duration (SD), air temperature, relative humidity and geographical parameters like latitude, longitude and altitude. In this paper, the GSR in Putrajaya is estimated from the hourly solar radiation and daily sunshine hours data from the Malaysian Meteorological Department. The data, along with the calculated monthly average daily extraterrestrial radiation on a horizontal surface and monthly average maximum possible daily sunshine is used to plot a scatter graph that is linearly fitted. The gradient and vertical axis cut-off from the linear fit is used to obtain the coefficients in the Angstrom-Prescott (A-P) model. Subsequently, the coefficients were used to estimate the GSR in Putrajaya. In line with the government’s initiative, this study will provide an estimation of the GSR in Putrajaya where the finding will be beneficial to the stakeholders, policy maker, developer and investor and energy authority. The average monthly GSR was obtained for nine out of twelve months with highest at 21.18 MJ/m2 in March and lowest at 18.34 MJ/m2 in June.

A Spectral Assignment-Oriented Approach to Improve Interpretability and Accuracy of Proxy Spectral-Based Models

In modeling chemical attributes using hyperspectral data, nonlinear relationships between the predictor and the response are frequent. The common nonlinear modeling techniques improve prediction accuracy but suffer from low interpretability of the models. In this paper, we demonstrate a new multivariate modeling method, denoted as spectral assignment-oriented partial least squares (SAO-PLS), which is designed to provide a nonlinear modeling solution with strong interpretability products. The need for this approach is apparent when a given sample population consists of different spectral features for different levels of the response. Accordingly, the suggested SAO-PLS algorithm segments the data in an optimal location on the response distribution by maximizing the difference in spectral assignments between two clusters. SAO-PLS is applied here to two test cases with different characteristics: 1) an established data set containing airborne hyperspectral data of asphaltic roads, merged with in situ measured dynamic friction values captured using a standardized method and 2) a soil spectral library, spectrally measured with an analytical spectral device spectrometer, to which organic carbon measurements were applied. Our results demonstrate the superiority of SAO-PLS over partial least-squares regression for both model accuracy and interpretability, providing a deeper understanding of the underlying processes.

On the characterization of novel biologically active steroids: Selection of lipophilicity models of newly synthesized steroidal derivatives by classical and non-parametric ranking approaches

In this paper, the guidelines for the interpretation of the results of quantitative structure-retention relationship (QSRR) modeling, comparison and assessment of the established models, as well as the selection of the best and most consistent QSRR model were presented. Various linear and non-linear chemometric regression techniques were used to build QSRR models for chromatographic lipophilicity prediction of a series of triazole, tetrazole, toluenesulfonylhydrazide, nitrile, dinitrile and dione steroid derivatives. Linear regression (LR) and multiple linear regression (MLR) were used as linear techniques, while artificial neural networks (ANNs) were applied as non-linear modeling techniques. Generated models were statistically evaluated applying different approaches for model comparison and ranking. Two non-parametric methods (generalized pair correlation method – GPCM and sum of ranking differences – SRD) were used for model ranking and assessment of the best model for chromatographic lipophilicity prediction using experimentally obtained logk values and row average as a reference ranking. Both, GPCM and SRD, provided highly similar model choice regardless on a different background. These results are in agreement with the classical approach.

Nonlinear characterization of ECGs in patients with Chagas’ disease**Partially supported by Consejo Nacional de Investigaciones Científicas y Tecnológicas, CONICIT under the grant G-97000675 and Vice-Rectorado de Investigación, Universidad Nacional San Agustin de Arequipa-Perú grant contract 15-2017-UNSA.

According to the World-Wide Organization of the Health, the number of people infected with the Tripanosoma Cruzi is considered between 6 and 8 million, causal agent of the Chagas’ disease , and in 550000 the people are expected to be exposed to the affectation risk. When concluding in 1983 a longitudinal epidemiologist study in patients with the disease evaluated every 3 years, the cardiac affectation: chronic Chagasic myocarditis (MCHC) increased from a 17% at the beginning of the study to a 49, 4% after 15 years. Previous studies of the variability of cardiac frequency (HRV) in patients with the Chagas’ disease, show alterations in the spectral indices of the HRV. A nonlinear modeling technique allows the definition of early risk markers in patients with Chagas’s disease and without any evidence of cardiac involvement evaluated by standard diagnostic test (CH1). We analyze ECGs by Holter recordings in patients with ECG alterations (CH2), patients without ECG alterations (CH1) who had positive serological findings for Chagas’ disease and healthy (Control) matched for sex and age. Two ECGs were digitized for each volunteer, one begins at supine position and the other at orthostatic position. The technique applied is based upon quantitative comparison of the evolution from similar ECGs Sub segments, and a measure of the predictability decay rate were calculated for each register. We did find significant differences among Control and CH2 during supine and also standing with high sensibility and specificity in the early detection of cardiac involvement. It is suggested that these alterations are very early autonomic disturbances in patients without ECG alterations (CH1) that could be useful to enhance risk stratification.

Improving Disturbance Storm Time Index Prediction Using Linear and Nonlinear Parametric Models: A Comprehensive Analysis

The earth's magnetosphere is an intricate input-output system, where the inputs are the solar wind parameters and the output measure are the geomagnetic. The disturbance storm time (DST) index is one such quantity measure for the intensity of disturbance in the geomagnetic field due to the magnetic storm. The geomagnetic activities have catastrophic effects on several communication networks and harmful for biological livings. Therefore, it is significant to develop a model for the prediction of disturbance in the geomagnetic field. This paper presents linear as well as nonlinear parametric techniques to model the complex magnetosphere dynamics. Neural network (NN)-based modeling techniques, such as feed-forward NN (FFNN), NN integrated with nonlinear autoregression with exogenous (NARX) inputs, adaptive neuro-fuzzy inference system (ANFIS), and recurrent NN are developed for the prediction of the magnetic storm. Global search algorithms, such as particle swarm optimization and genetic algorithm, also train the developed FFNNs. All the models are trained on 15 years' real-time series data of solar wind parameters and DST index on a frequency of 1 h. The accuracy of the predicted DST index for multiple intensity levels of the magnetic storm using all developed linear and nonlinear modeling techniques is presented, compared, and analyzed thoroughly. The performance of NN integrated with NARX inputs and ANFIS is higher than rest of methods developed in the paper. Both techniques have the capability to predict mild, moderate, and intense magnetic storm with high degree of accuracy. The comparative analysis with state of the art shows the enhanced accuracy and robustness of developed models in this paper.

Automatic large-signal GaAs HEMT modeling for power amplifier design

In this paper, a new nonlinear transistor modeling technique for gallium arsenide high-electron mobility transistor (GaAs HEMT) is proposed. The technique includes an analytical extraction, enhanced by applying nonlinear least squares regression and modified-median method, and a multistage optimization, allowing completely automatic large-signal modeling. Convergence of the technique is proved by a threefold model building procedure followed by the comparison of simulated data like IV-curve and load-pull contours. A 0.15 μm GaAs pHEMT nonlinear model was built and verified with measured IV-curve, multiple bias S-parameters and power characteristics. A good agreement with the measured data proves that the proposed technique enables automatic nonlinear transistor modeling for power MMIC amplifier design.

Mixed-effect non-linear modelling for diameter estimation along the stem of Tectona grandis in mid-western Brazil

This study evaluated the efficiency of taper functions and the application of mixed-effect modelling for diameter estimation along the stems of Tectona grandis. We sampled 266 trees of Tectona grandis, measuring the diameter at relative heights for volume determination, grouping the data according to three form-factor classes. Six taper functions were fitted, selecting the function with better fit performance. Six taper functions were fitted, selecting the function with better fit performance. The selected function was fitted in its basic formulation, and with the mixed non-linear modelling technique in different scenarios, and for the stem stratified in three portions of the total height. The precision and selection of the adjusted models were evaluated regarding the coefficient of determination, standard error of estimate, the Akaike information criterion, bias, quadratic error and absolute bias. According to the statistical criteria used, the model of Kozak was selected for the adjustments. For diameter estimation, the scenario with two coefficients as random effects provided an accuracy increase of 11.91%, and the mixed non-linear modelling better estimated the stem diameter for the stratified stems. In conclusion, the model of Kozak can be used to describe the stem shape of Tectona grandis, and the mixed-effect non-linear model approach was the best technique to estimate diameter along the stem of Tectona grandis.

Accelerated degradation model for C-rate loading of lithium-ion batteries

As Li-ion batteries are used in increasingly diverse applications, their performance and reliability become more critical. Reliability testing of Li-ion batteries involves battery capacity fade monitoring over repeated charging/discharging cycles. Cycling at a nominal charge/discharge current requires an extensive amount of time and resources, and hence a battery qualification process based on battery cycle testing may cause delays in time to market. Discharge C-rate variable can be used for accelerating Li-ion battery cycle testing. This paper develops an accelerated capacity fade model for Li-ion batteries under multiple C-rate loading conditions, to translate the performance and degradation of a battery population at accelerated C-rate conditions to normal C-rate conditions. A nonlinear mixed-effects regression modeling technique is used to take into account the variability of repeated capacity measurements on individual batteries in a population. The model is validated using the experimental data from two battery populations that have been fielded.

Nonlinear sigma model approach to many-body quantum chaos: Regularized and unregularized out-of-time-ordered correlators

The out-of-time-ordered correlators (OTOCs) have been proposed and widely used recently as a tool to define and describe many-body quantum chaos. Here, we develop the Keldysh non-linear sigma model technique to calculate these correlators in interacting disordered metals. In particular, we focus on the regularized and unregularized OTOCs, defined as $Tr[\sqrt{\rho} A(t) \sqrt{\rho} A^\dagger(t)]$ and $Tr[\rho A(t)A^\dagger(t)]$ respectively (where $A(t)$ is the anti-commutator of fermion field operators and $\rho$ is the thermal density matrix). The calculation of the rate of OTOCs' exponential growth is reminiscent to that of the dephasing rate in interacting metals, but here it involves two replicas of the system (two "worlds"). The intra-world contributions reproduce the dephasing (that would correspond to a decay of the correlator), while the inter-world terms provide a term of the opposite sign that exceeds dephasing. Consequently, both regularized and unregularized OTOCs grow exponentially in time, but surprisingly we find that the corresponding many-body Lyapunov exponents are different. For the regularized correlator, we reproduce an earlier perturbation theory result for the Lyapunov exponent that satisfies the Maldacena-Shenker-Stanford bound. However, the Lyapunov exponent of the unregularized correlator parametrically exceeds the bound. We argue that the latter is not a reliable indicator of many body quantum chaos as it contains additional contributions from elastic scattering events due to virtual processes that should not contribute to many-body chaos. These results bring up an important general question of the physical meaning of the OTOCs often used in calculations and proofs. We briefly discuss possible connections of the OTOCs to observables in quantum interference effects and level statistics via a many-body analogue of the Bohigas-Giannoni-Schmit conjecture.

Abstract 16592: A Next-Generation Artificial Intelligence-Based Integrated Genetic-Epigenetic Prediction of 5-Year Risk for Coronary Heart Disease

Coronary heart disease (CHD) is a leading cause of death in the US. CHD associated morbidity and mortality can be reduced if those at risk can be identified well in advance, to put in place prevention interventions prior to an acute coronary event. Limitations of current approaches call for additional efforts to improve risk predictions. We recently developed a Precision Medicine tool capable of predicting 5-year risk, that can also guide personalized prevention interventions and monitor changes in risk over time. It was developed using an application of AI, machine learning, in the Framingham Heart Study to mine integrated genetic-epigenetic biosignatures that capture the complex interplay between our genome and the environment in conferring risk for CHD. The training and test sets consisted of 1180 (19/695 females and 23/485 males developed symptomatic CHD within 5-years) and 524 (8/293 females and 12/231 males developed symptomatic CHD within 5-years) individuals, respectively, of Northern European ancestry. Non-linear data mining and modeling techniques were employed on the training set to identify prediction signatures from genome-wide SNP and DNA methylation (DNAm) data. We identified 14 DNAm and 10 SNPs from the training set (training bootstrap average sensitivity and specificity of 0.61 and 0.71, respectively) that predicted the 5-year risk in the test set with a sensitivity and specificity of 0.60 and 0.69, respectively. Performance was compared to that of the Framingham Risk Score (FRS) and the ASCVD Risk Estimator. The sensitivity and specificity in the test set were 0.05 and 0.99 for FRS, and 0.38 and 0.85 for ASCVD. Even with a small number of incident cases, our tool performed with superior sensitivity, which is vital because, while a false positive would result in additional testing, a false negative can be detrimental. Unlike genetics, because DNAm is dynamic, it can be mapped to actionable risk factors to guide personalized interventions and over time, re-assess risk and continuously monitor heart health. We demonstrate translational feasibility of this tool via next-gen digital PCR assays. Additional efforts are ongoing to optimize, validate and extend our tool to further improve performance in larger, more ethnically diverse cohorts.

Modeling Electronic Power Converters in Smart DC Microgrids—An Overview

Electronic power converters (EPCs) are the key elements of the smart dc microgrid architectures. In order to enhance the controllability of the system, most of the elements are envisioned to be connected to the different buses through EPCs. Therefore, power flow, stability, and dynamic response in the microgrid are function of the behavior of the EPCs and their control loops. Besides, dc microgrids constitute a new paradigm in power distribution systems due to the high variability of their operating conditions, owing to the intermittent behavior of the renewable sources and customer energy consumption. Furthermore, in order to deal with this variability, the power converters can modify their operation mode, adding complexity to the dynamic and stability analysis of the system. This paper gives an overview of the various analytical and blackbox modeling strategies applied to smart dc micro/nanogrids. Different linear and nonlinear modeling techniques are reviewed describing their capabilities, but also their limitations. Finally, differences among blackbox models will be highlighted by means of illustrative examples.

A nonlinear resonant mass sensor with enhanced sensitivity and resolution incorporating compressed bistable beam

A new piezoelectric actuated nonlinear mass sensor is proposed by using the snap-through phenomenon of a compressed bistable beam to enhance the sensitivity and resolution, which can be used to weigh or detect threshold mass by tracking the bifurcation frequency shift. According to the nonlinear finite element modeling technique, the nonlinear dynamic response of the combined nonlinear structure is numerically calculated, which shows that the bifurcation point can be accurately identified by the sharp and great amplitude change regardless of the damping effect, thus providing an effective way for tracking the bifurcation frequency. Hence, the nonlinear sensitivity depicted by the bifurcation frequency shift per unit mass can reach 3.3 times the sensitivity of linear mass sensors having the same size. Also, as a mass switch, the response amplitude jumps sharply when the added mass is greater than or equal to the threshold value, which is dependent on the excitation frequency. Meanwhile, the influences of the beam compression and excitation voltage on the sensitivity and minimum detectable mass were obtained for sensor optimization. For concept validation, a macro-sized nonlinear mass sensor was fabricated with the geometric size of 58.0 mm long and 4.0 mm wide, and the experimental results show that the sensitivity is around 575.0 Hz/g compared with the simulated sensitivity of 542.0 Hz/g. For a mass switch, the minimum threshold mass is 0.2 mg. The fair agreement between the simulation and experiments adequately validated the proposed nonlinear bistable mass sensor.

A nonlinear FE analysis to model progressive fatigue damage of cross-ply laminates under pin-loaded conditions

Involving several damages and failure mechanisms result in a rather complex fatigue process of composite materials. Inhomogeneity, anisotropy and nonlinear nature of composite materials require advanced nonlinear modeling techniques of strength and fatigue. In this paper, a progressive fatigue damage model is proposed by considering the nonlinearity effects of in-plane shear stress/strain relationship. To this aim, fatigue failure criteria and material property degradations rules are derived based on material nonlinearity. The mathematical model is applied through a UMAT subroutine code developed in ABAQUS commercial software. To validate the model, life predictions are compared with the available experimental results of coupon specimen and pin-loaded carbon/epoxy cross-ply laminates. The presented finite element nonlinear progressive fatigue damage model improved the life prediction for both geometries. For coupon specimen and pin-loaded simulations, the present model reduced the average error of life predictions by 80% and 50%, respectively compared to the conventional linear models. From results of the pin-loaded model, the nonlinear assumption predicts a shorter life at high external loads due to higher stress in the fiber direction of on-axis plies as critical elements of the laminate; however, at lower external loads, both linear and nonlinear models predict similar stress state and life.

Multiway principal polynomial analysis for semiconductor manufacturing process fault detection

In semiconductor industry, the etching process is a highly sophisticated nonlinear process, which significantly affects the wafer quality. Fault detection technique has been investigated as a promising tool to reduce the fault wafers and increase overall equipment effectiveness. However, traditional fault detection models are not adequate enough to describe the etching process due to the high complexity and non-linearity of wafer processing process. In this study, a novel fault detection technique called multiway principal polynomial analysis (MPPA) is proposed. MPPA is a nonlinear modeling technique which learns a low-dimensional representation from process data based on a sequence of principal polynomials. Compared to linear methods, MPPA is more flexible and efficient in tackling process nonlinearity. Furthermore, MPPA has the desirable properties of invertibility, volume-preservation, and straightforward out-of-sample extension, thus making it interpretable and easier to implement in real application. To verify the effectiveness of the proposed MPPA, it was applied to a nonlinear numerical example and the real-world operation data of a semiconductor manufacturing process. The application results demonstrated that the proposed MPPA method outperforms the conventional MPCA, FD-kNN, and PC-kNN in the fault detection performance.

Evaluation of Rotation Capacity of I-shaped Welded Steel Plate Girders

Flexural ductility in steel sections is required to accommodate inelastic force redistribution. It is used to evaluate available inelastic performances of structures. Various factors that influence ductility of the section are compactness, material properties, and lateral support configuration close to plastic hinge region. This paper attempts to evaluate inelastic rotation response of hybrid and homogeneous I-sections considering the influence of above factors. An experimentally verified nonlinear finite element modeling technique is employed to carry out parametric studies to evaluate the extent of influence of the above parameters on rotation response. An attention is given to the interaction between local and lateral buckling and their influence on inelastic rotation for the members subjected to constant moment loading. Regression analysis of the database parametric studies resulted into an equation for evaluation of rotation capacity of I-shaped steel plate girders. The equation is validated by applying it to selected experiments conducted by various researchers. Results of the proposed equation are compared with the rotation capacity prediction equations by others. Statistical analysis of validation study shows that the proposed equation provides refined results as compared to available equations. A flowchart and solved example for the demonstration of the use of proposed equation along with stable length equations are presented.

An Attempt to Use Non-Linear Regression Modelling Technique in Long-Term Seasonal Rainfall Forecasting for Australian Capital Territory

The objective of this research is the assessment of the efficiency of a non-linear regression technique in predicting long-term seasonal rainfall. The non-linear models were developed using the lagged (past) values of the climate drivers, which have a significant correlation with rainfall. More specifically, the capabilities of SEIO (South-eastern Indian Ocean) and ENSO (El Nino Southern Oscillation) were assessed in reproducing the rainfall characteristics using the non-linear regression approach. The non-linear models developed were tested using the individual data sets, which were not used during the calibration of the models. The models were assessed using the commonly used statistical parameters, such as Pearson correlations (R), root mean square error (RMSE), mean absolute error (MAE) and index of agreement (d). Three rainfall stations located in the Australian Capital Territory (ACT) were selected as a case study. The analysis suggests that the predictors which has the highest correlation with the predictands do not necessarily produce the least errors in rainfall forecasting. The non-linear regression was able to predict seasonal rainfall with correlation coefficients varying from 0.71 to 0.91. The outcomes of the analysis will help the watershed management authorities to adopt efficient modelling technique by predicting long-term seasonal rainfall.

Probabilistic seismic vulnerability analysis of corroded reinforced concrete frames including spatial variability of pitting corrosion

A probabilistic framework for seismic vulnerability analysis of corroded Reinforced Concrete (RC) frame structures is developed. An advanced nonlinear finite element modelling technique is used to accurately simulate the nonlinear behaviour of prototype corroded RC frames over their service life. Different sources of uncertainties including modelling uncertainties, geometrical uncertainties and spatial variability of pitting corrosion are considered through Monte Carlo simulation and using Latin Hypercube Sampling (LHS) technique. A set of new seismic damage limit states (SDLS) are defined accounting for multiple failure modes of the corrosion damaged frames by means of pushover analyses. The influence of corrosion on nonlinear dynamic behaviour of corroded RC frames is investigated through Incremental Dynamic Analysis (IDA) of proposed frame structures under 44 far-field ground motions. The impact of considering corrosion damaged SDLS, spatial variability of pitting corrosion, and record-to-record variability on seismic vulnerability of RC frames are explored and discussed in detail. It is concluded that disregarding the influence of corrosion on SDLS significantly underestimates the probability of failure of corroded RC frames. The analyses results show that spatial variability of pitting corrosion does not have a significant impact on global nonlinear behaviour and seismic vulnerability/reliability of corroded RC frames.

A New Fuzzy Modeling Framework for Integrated Risk Prognosis and Therapy of Bladder Cancer Patients

This paper presents a new fuzzy modeling approach for analyzing censored survival data and finding risk groups of patients diagnosed with bladder cancer. The proposed framework involves a new procedure for integrating the frameworks of interval type-2 fuzzy logic and Cox modeling intrinsically. The output of this synergistic framework is a score/prognostics index which is indicative of the patient's level of mortality risk. A threshold value is selected whereby patients with risk scores that are greater than this threshold are classed as high-risk patients and vice versa. Unlike in the case of black-box type modeling approaches, the paper shows that interpretability and transparency are maintained using the proposed fuzzy modeling framework. Two datasets are used to test the modeling accuracy of the elicited models. The first is an artificial dataset which has similar characteristics as in a typical survival data. The second relates to real-life bladder cancer data from which one requires a model that identifies the low-risk and high-risk patients and then recommends risk management decisions based on, predicted risk level, patient history and characteristics, disease pathology, and event times. The performance of the proposed framework is compared with the traditional Cox model, logistic regression as well as a nonlinear survival data modeling technique based on neural networks. This is the first time an attempt has been made to exploit the transparency advantages of fuzzy models and the principled statistical framework of the Cox model in order to identify risk groups and recommend risk management decisions from complex survival datasets. In both the artificial data and real data, the proposed modeling framework, although minimalistic, shows better generalization performances than the previously reported models against which the results were compared.