David West

Investigation of Survival Modeling in Supply Chain Financial Distress Analysis

Supply chain risk management has received considerable attention in recent years. Financial model... more Supply chain risk management has received considerable attention in recent years. Financial models that can help predict the probability and timing of supply chain partner failure can bring great benefit to mitigating risks associated with economic instability and financial distress. In this study we compare the predictive bankruptcy classification accuracy of the Cox Proportional Hazards Regression (CPHR) approach to the statistical approaches of Logistic Regression and Discriminant Analysis. Analysis of CPHR versus other models shows competitive results worthy of further consideration.

Download

Identifying process conditions in an urban wastewater treatment plant

International Journal of Operations & Production Management, 2000

ABSTRACT In treating both sewage and storm runoff, wastewater treatment plants are important to m... more ABSTRACT In treating both sewage and storm runoff, wastewater treatment plants are important to maintaining a healthy environment. If the plant operations managers do not respond correctly to plant conditions, environmental damage resulting in the deterioration of human health may be the result. Unfortunately, there are no formal models to help these managers; they rely upon their own intuition to manage the plants. The purpose of this paper is to investigate the effectiveness of various models, originally used for manufacturing, to detect process conditions in wastewater treatment facilities. We compare and contrast the performance of five statistical models and three neural network architectures. The data used in the research is 527 daily measurements of 38 sensor readings of the process state variables of an urban wastewater treatment plant.

Model Selection Strategies for Ensemble Solutions to Bankruptcy Detection

International Conference on Artificial Intelligence, 2005

Considerable research effort has been expended to identify more accurate models for decision supp... more Considerable research effort has been expended to identify more accurate models for decision support systems in financial decision domains including bankruptcy prediction. The focus of this earlier work has been to identify the “single best” prediction model from a collection that includes simple parametric models, nonparametric models that directly estimate data densities, and nonlinear pattern recognition models such as neural networks. Recent theories suggest this work may be misguided in that ensembles of predictors provide more accurate generalization than the reliance on a single model. This paper investigates the role of model diversity in the accuracy of ensemble solutions for bankruptcy detection. We employ twenty two diverse models as base classifiers. The generalization ability of the traditional bagging ensemble is found to be significantly improved by increasing model diversity in the ensemble.

Neural network ensemble strategies for financial decision applications

Computers & Operations Research, 2005

Considerable research e ort has been expended to identify more accurate models for decision suppo... more Considerable research e ort has been expended to identify more accurate models for decision support systems in ÿnancial decision domains including credit scoring and bankruptcy prediction. The focus of this earlier work has been to identify the "single best" prediction model from a collection that includes simple parametric models, nonparametric models that directly estimate data densities, and nonlinear pattern recognition models such as neural networks. Recent theories suggest this work may be misguided in that ensembles of predictors provide more accurate generalization than the reliance on a single model. This paper investigates three recent ensemble strategies: crossvalidation, bagging, and boosting. We employ the multilayer perceptron neural network as a base classiÿer. The generalization ability of the neural network ensemble is found to be superior to the single best model for three real world ÿnancial decision applications.

Download

An empirical analysis of neural network memory structures for basin water quality forecasting

International Journal of Forecasting, 2011

This research investigates the cumulative multi-period forecast accuracy of a diverse set of pote... more This research investigates the cumulative multi-period forecast accuracy of a diverse set of potential forecasting models for basin water quality management. The models are characterized by their short-term (memory by delay or memory by feedback) and long-term (linear or nonlinear) memory structures. The experiments are conducted as a series of forecast cycles, with a rolling origin of a constant fit size. The models are recalibrated with each cycle, and out-of-sample forecasts are generated for a five-period forecast horizon. The results confirm that the JENN and GMNN neural network models are generally more accurate than competitors for cumulative multi-period basin water quality prediction. For example, the JENN and GMNN models reduce the cumulative five-period forecast errors by as much as 50%, relative to exponential smoothing and ARIMA models. These findings are significant in view of the increasing social and economic consequences of basin water quality management, and have the potential for extention to other scientific, medical, and business applications where multi-period predictions of nonlinear time series are critical. c

Download

Control of complex manufacturing processes: a comparison of SPC methods with a radial basis function neural network

Omega, 1999

Manufacturing processes are increasingly subject to tighter control and more frequent monitoring,... more Manufacturing processes are increasingly subject to tighter control and more frequent monitoring, in many cases using real time data collection systems. It is now recognized that complex interactions of auto and cross-correlation exist in data observations from process industries, batch processes, and the traditional parts industry. New control models that capture both multivariate and time series eects are needed to eectively monitor manufacturing processes. In this research, we investigate the ability of radial basis function neural networks to monitor and control complex manufacturing processes that exhibit both auto and cross-correlation. We demonstrate that the radial basis function network is superior to three control models recently proposed for complex manufacturing processes: multivariate Shewhart, multivariate EWMA, and a feed forward neural network with logistic units trained by backpropagation (often called a back-propagation neural network).

Download

Ensemble strategies for a medical diagnostic decision support system: A breast cancer diagnosis application

European Journal of Operational Research, 2005

The model selection strategy is an important determinant of the performance and acceptance of a m... more The model selection strategy is an important determinant of the performance and acceptance of a medical diagnostic decision support system based on supervised learning algorithms. This research investigates the potential of various selection strategies from a population of 24 classification models to form ensembles in order to increase the accuracy of decision support systems for the early detection and diagnosis

Diversity of ability and cognitive style for group decision processes

Information Sciences, 2009

This research investigates the potential for two forms of error diversity (ability diversity and ... more

Improving diagnostic accuracy using a hierarchical neural network to model decision subtasks

International Journal of Medical Informatics, 2000

Predictive modeling for wastewater applications: Linear and nonlinear approaches

Environmental Modelling & Software, 2009

This study compares the multi-period predictive ability of linear ARIMA models to nonlinear time ... more This study compares the multi-period predictive ability of linear ARIMA models to nonlinear time delay neural network models in water quality applications. Comparisons are made for a variety of artificially generated nonlinear ARIMA data sets that simulate the characteristics of wastewater process variables and watershed variables, as well as two real-world wastewater data sets. While the time delay neural network model was more accurate for the two real-world wastewater data sets, the neural networks were not always more accurate than linear ARIMA for the artificial nonlinear data sets. In some cases of the artificial nonlinear data, where multi-period predictions are made, the linear ARIMA model provides a more accurate result than the time delay neural network. This study suggests that researchers and practitioners should carefully consider the nature and intended use of water quality data if choosing between neural networks and other statistical methods for wastewater process control or watershed environmental quality management.

Download

Overbooking Increases Patient Access at East Carolina University's Student Health Services Clinic

Interfaces, 2009

The health-care clinic presented in this study experienced significant numbers of patients who fa... more The health-care clinic presented in this study experienced significant numbers of patients who failed to arrive for their scheduled appointments (no-shows). The cost of reducing patient access at this clinic because of noshows is estimated to exceed $400,000 annually. An interdisciplinary quality-improvement team developed a novel health-care overbooking model that includes the effects of employee burnout. This model estimates the nonlinear nature of the costs associated with medical-provider burnout caused by overbooked appointments that exceed clinic capacity. Several key East Carolina University clinical staff members had been skeptical about the value of overbooking. The model was instrumental in convincing them that implementing an overbooking process would benefit patients and the organization. The clinic, which subsequently implemented such a process, attributes a savings of $95,000 per semester to the initiative.

Download

Model selection for a medical diagnostic decision support system: a breast cancer detection case

by David West and Vivian West

Artificial Intelligence in Medicine, 2000

There are a number of different quantitative models that can be used in a medical diagnostic deci... more There are a number of different quantitative models that can be used in a medical diagnostic decision support system (MDSS) including parametric methods (linear discriminant analysis or logistic regression), non-parametric models (K nearest neighbor, or kernel density) and several neural network models. The complexity of the diagnostic task is thought to be one of the prime determinants of model selection. Unfortunately, there is no theory available to guide model selection. Practitioners are left to either choose a favorite model or to test a small subset using cross validation methods. This paper illustrates the use of a self-organizing map (SOM) to guide model selection for a breast cancer MDSS. The topological ordering properties of the SOM are used to de®ne targets for an ideal accuracy level similar to a Bayes optimal level. These targets can then be used in model selection, variable reduction, parameter determination, and to assess the adequacy of the clinical measurement system. These ideas are applied to a successful model selection for a real-world breast cancer database. Diagnostic accuracy results are reported for individual models, for ensembles of neural networks, and for stacked predictors.

Download

Model selection for medical diagnosis decision support systems

Decision Support Systems, 2004

... With the widespread use of electronic data capture and automation of medical records, medical... more

Model selection for medical diagnosis decision support systems

Decision Support Systems, 2004

... With the widespread use of electronic data capture and automation of medical records, medical... more

The comparative ability of self-organizing neural networks to define cluster structure

by Paul Mangiameli and David West

Omega, 1995

Download

Model selection for medical diagnosis decision support systems

by Paul Mangiameli, Rohit Rampal, and David West

Decision Support Systems, 2004

In this paper, we examine the model section decision for a medical diagnostic decision support sy... more In this paper, we examine the model section decision for a medical diagnostic decision support system (MDSS). Our purpose in doing this is to understand how model selection affects the accuracy of the decision support system. We explore two related research questions: (1) Do ensembles of models, acting as a single decision maker, perform more accurately than single models; and (2) How does model diversity affect the accuracy of the ensembles? Specifically, we compare 23 single models and bootstrap aggregating (i.e., bagging) models for their predictive abilities across five diverse medical data sets. We are able to reach important conclusions about our research objectives. Ensembles are more accurate than single models in their predictive ability. The best ensemble model achieves an error level significantly lower than the error of the best single model for four of the five medical applications analyzed. The magnitude of the error reduction ranges from 6.4% to 17.5%. Also, when designing an ensemble for an MDSS, the decision to diversify the model selection should be guided by the relationship between model instability and generalization error for the population of models under consideration. D

Download

Ensemble strategies for a medical diagnostic decision support system: A breast cancer diagnosis application

by Paul Mangiameli, Vivian West, Rohit Rampal, and David West

European Journal of Operational Research, 2005

The model selection strategy is an important determinant of the performance and acceptance of a m... more The model selection strategy is an important determinant of the performance and acceptance of a medical diagnostic decision support system based on supervised learning algorithms. This research investigates the potential of various selection strategies from a population of 24 classification models to form ensembles in order to increase the accuracy of decision support systems for the early detection and diagnosis of breast cancer. Our results suggest that ensembles formed from a diverse collection of models are generally more accurate than either pure-bagging ensembles (formed from a single model) or the selection of a ''single best model.'' We find that effective ensembles are formed from a small and selective subset of the population of available models with potential candidates identified by a multicriteria process that considers the properties of model generalization error, model instability, and the independence of model decisions relative to other ensemble members.

Download

Identifying process conditions in an urban wastewater treatment plant

by Paul Mangiameli and David West

International Journal of Operations & Production Management

In treating both sewage and storm runoff, wastewater treatment plants are important to maintainin... more In treating both sewage and storm runoff, wastewater treatment plants are important to maintaining a healthy environment. If the plant operations managers do not respond correctly to plant conditions, environmental damage resulting in the deterioration of human health may be the result. Unfortunately, there are no formal models to help these managers; they rely upon their own intuition to manage the plants. The purpose of this paper is to investigate the effectiveness of various models, originally used for manufacturing, to detect process conditions in wastewater treatment facilities. We compare and contrast the performance of five statistical models and three neural network architectures. The data used in the research is 527 daily measurements of 38 sensor readings of the process state variables of an urban wastewater treatment plant.

Control of complex manufacturing processes: a comparison of SPC methods with a radial basis function neural network

by Paul Mangiameli and David West

Omega, 1999

Manufacturing processes are increasingly subject to tighter control and more frequent monitoring,... more Manufacturing processes are increasingly subject to tighter control and more frequent monitoring, in many cases using real time data collection systems. It is now recognized that complex interactions of auto and cross-correlation exist in data observations from process industries, batch processes, and the traditional parts industry. New control models that capture both multivariate and time series eects are needed to eectively monitor manufacturing processes. In this research, we investigate the ability of radial basis function neural networks to monitor and control complex manufacturing processes that exhibit both auto and cross-correlation. We demonstrate that the radial basis function network is superior to three control models recently proposed for complex manufacturing processes: multivariate Shewhart, multivariate EWMA, and a feed forward neural network with logistic units trained by backpropagation (often called a back-propagation neural network). #

Download

Identifying process conditions in an urban wastewater treatment plant

by Paul Mangiameli and David West

International Journal of Operations & Production Management, 2000

ABSTRACT In treating both sewage and storm runoff, wastewater treatment plants are important to m... more ABSTRACT In treating both sewage and storm runoff, wastewater treatment plants are important to maintaining a healthy environment. If the plant operations managers do not respond correctly to plant conditions, environmental damage resulting in the deterioration of human health may be the result. Unfortunately, there are no formal models to help these managers; they rely upon their own intuition to manage the plants. The purpose of this paper is to investigate the effectiveness of various models, originally used for manufacturing, to detect process conditions in wastewater treatment facilities. We compare and contrast the performance of five statistical models and three neural network architectures. The data used in the research is 527 daily measurements of 38 sensor readings of the process state variables of an urban wastewater treatment plant.

Uploads

Papers by David West

Log In