Engineering Management and Systems Engineering

Non-reactive gas-phase pollutants such as benzene diffuse into indoor furnishings and leave behind a unique materialphase concentration profile that serves as a record of the past gas-phase indoor concentrations. The inverse problem to be solved is the diffusion equation in a slab such as vinyl flooring. Using knowledge of the present material-phase concentration profile in the slab, we seek to determine the historical material-phase concentration at the surface exposed to indoor air, and hence the historical gas-phase concentration, which can be used directly to determine exposure. The problem as posed has a unique solution that may be solved using a variety of approaches. We use a trained artificial neural network (ANN) to derive solutions for hypothetical exposure scenarios. The ANN results show that it is possible to estimate the intensity and timing of past exposures from the material-phase concentration profile in a building material. The overall method is limited by (1) the resolution of techniques for measuring spatial material-phase concentration profiles, (2) how far back in time we seek to determine exposure and (3) the representational power of the ANN solution. For example, we estimate that this technique can estimate exposure to phenol up to 0.5 y in the past from analyses of vinyl flooring. r

In recent years, the opening of worldwide markets to many products has forced manufacturing companies to compete on a global basis. This high level of competition amongst manufacturers has led to rapid developments in the areas of computer integrated manufacturing, flexible manufacturing, agile manufacturing, and intelligent manufacturing. These developments have in turn generated a need for intelligent sensing and decision making systems capable of automatically performing many tasks traditionally executed by human beings. Visual inspection is one such task, and there is a need for effective automated visual inspection systems in today's competitive manufacturing environments. The following will discuss the advantages of implementing an intelligent visual inspection system based on natural human vision. Results from current models will also be presented,

The ISO 9000 quality management system has been widely accepted and adapted as a national standard by most industrial countries. Despite its high popularity and the urgent demand from customers to implement ISO 9000, some major concerns for those organizations that are seeking registration to ISO 9000 include the expensive cost and the lengthy time to implement.

It has been widely accepted by many studies that non-linearity exists in the financial markets and that neural networks can be effectively used to uncover this relationship. Unfortunately, many of these studies fail to consider alternative forecasting techniques, the relevance of input variables, or the performance of the models when using different trading strategies. This paper introduces an information gain technique used in machine learning for data mining to evaluate the predictive relationships of numerous financial and economic variables. Neural network models for level estimation and classification are then examined for their ability to provide an effective forecast of future values. A cross-validation technique is also employed to improve the generalization ability of several models. The results show that the trading strategies guided by the classification models generate higher risk-adjusted profits than the buy-and-hold strategy, as well as those guided by the level-estimation based forecasts of the neural network and linear regression models. q Expert Systems with Applications 29 927-940 www.elsevier.com/locate/eswa 0957-4174/$ -see front matter q

It has been long recognized that trading volume provides valuable information for understanding stock price movement. As such, equivolume charting was developed to consider how stocks appear to move in a volume frame of reference as opposed to a time frame of reference. Two technical indicators, namely the volume adjusted moving average (VAMA) and the ease of movement (EMV) indicator, are developed from equivolume charting. This paper explores the profitability of stock trading by using a neural network model developed to assist the trading decisions of the VAMA and EMV. The generalized regression neural network (GRNN) is chosen and utilized on past S&P 500 index data. For the VAMA, the GRNN is used to predict the future stock prices, as well as the future width size of the equivolume boxes typically utilized on an equivolume chart, for calculating the future value of the VAMA. For the EMV, the GRNN is also used to predict the future value of the EMV. The idea is to further exploit the equivolume potential by using a forecasting system to predict the future equivolume measurements, allowing investors to enter or exit trades earlier. The results show that the stock trading using the neural network with the VAMA and EMV outperforms the results of stock trading generated from the VAMA and EMV without neural network assistance, the simple moving averages (MA) in isolation, and the buy-and-hold trading strategy.

This paper discusses a hybrid prediction model that combines differential evolutionbased fuzzy clustering with a fuzzy inference neural network for performing an index level forecast. In the first phase of the proposed model, stepwise regression analysis is implemented to determine the combination of inputs that have the strongest forecasting ability. Next, the selected variables are grouped by means of a differential evolution-based fuzzy clustering method, allowing the extraction rules to be determined. For the final stage, a fuzzy inference neural network is implemented to predict the market prices by using the extraction rules from the previous stage.

The ART1 neural network algorithm has been implemented in the past for the classifying and grouping of similar vectors from a machine-part matrix. Recently, a new ARTI paradigm which involves reordering of the input vectors with a modified procedure for storing a group's representation vectors has proven successful in both speed and functionally compared to previous techniques. This new paradigm is now adapted and implemented on a neuro-computer utilising 256 processors, allowing the neural network to take advantage of its inherent parallelism. Tremendous improvements in the speed of the machine-part matrix optimization result from the parallel implementation. Comparisons with the previous serial algorithm are made and suggestions for possible parallel implementation within a manufacturing environment are discussed.

The Black-Scholes (BS) model is the standard approach used for pricing financial options. However, although being theoretically strong, option prices valued by the model often differ from the prices observed in the financial markets. This paper applies a hybrid neural network which preprocesses financial input data for improving the estimation of option market prices. This model is comprised of two parts. The first part is a neural network developed to estimate volatility. The second part is an additional neural network developed to value the difference between the BS model results and the actual market option prices. The resulting option price is then a summation between the BS model and the network response. The hybrid system with a neural network for estimating volatility provides better performance in terms of pricing accuracy than either the BS model with historical volatility (HV), or the BS model with volatility valued by the neural network.

The following research implements a differential evolution-based fuzzy-type clustering method with a fuzzy inference neural network after input preprocessing with regression analysis in order to predict future interest rates, particularly 3-month T-bill rates. The empirical results of the proposed model is compared against nonparametric models, such as locally weighted regression and least squares support vector machines, along with two linear benchmark models, the autoregressive model and the random walk model. The root mean square error is reported for comparison.

This study focuses on various trader behaviors that affect market dynamics. In particular, the effects of a covering mechanism, learning mechanism and bias mechanism are analyzed through agent-based financial market model. An XCS classifier system is used to model trader learning mechanism. A trader model is proposed to formulate a trader decision model that combines bias mechanisms with learning mechanisms. The results reveal that biased traders survive under evolving markets and affect price dynamics. The model contributes to understanding the market behavior and potential sources of deviation from efficient market equilibrium.

There has been a growing interest in applying neural networks and technical analysis indicators for predicting future stock behavior. However, previous studies have not practically evaluated the predictive power of technical indicators by employing neural networks as a decision maker to uncover the underlying nonlinear pattern of these indicators. The objective of this paper is to investigate if using these indicators as the input variables to a neural network will provide more accurate stock trend predictions, and whether they will yield higher trading pro¢ts than the traditional technical indicators. Three neural networks are examined in the study to predict the short-term trend signals of three stocks across different market industries. The overall results indicate that the proportion of correct predictions and the pro¢tability of stock trading guided by these neural networks are higher than those guided by their benchmarks.

Investing in options has many advantages : they provide increased cost efficiency; they have the potential to deliver higher percentage returns due to increased leverage; and they offer a number of hedging and strategic alternatives. It is, therefore, worthwhile to investigate the option trading strategies that offer high payoffs. This paper provides a performance evaluation of models used in the pricing of options for a bull spread options strategy. The strategy is highly profitable when the price of the underlying primitive reaches the second out-of-themoney strike price before the expiration date of the options, but no further. The challenge lies in choosing the optimal out-of-the-money option strike price. The option exercise price, past primitive price jumps, and primitive volatility shifts are the important factors that are to be analyzed. Since the understanding of the primitive volatility is important, this thesis investigates the forecasting ability of Feed Forward Neural Networks (FNN) using back propagation learning and Recurrent Neural Networks (RNN) models, using implied volatility forecasts obtained from a Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model. The performance of the three models is studied and compared using the data from the S&P 500, DJIA, NYSE, and NASDAQ indexes. The resultsshown by the volatility forecasts indicate that RNN is a better forecasting tool. These results are further used to evaluate the performance of RNN and GARCH models in forecasting the sell option strike price in a bull call spread strategy. The trading profitability of these models is tested using SPY, DIA and SIRI options over a 1 month, 3month and 6 month trading horizon.

The binary adaptive resonance (ART1) neural network algorithm has been successfully implemented in the past for the classifying and grouping of similar vectors from a machine-part matrix. A modi®ed ART1 paradigm which reorders the input vectors, along with a modi®ed procedure for storing a group's representation vectors, has proven successful in both speed and functionality in comparison to former techniques. This paradigm has been adapted and implemented on a neuro-computer utilizing 256 processors which allows the computer to take advantage of the inherent parallelism of the ART1 algorithm. The parallel implementation results in tremendous improvements in the speed of the machine-part matrix optimization. The machine-part matrix was initially limited to 65,536 elements (256 6 256) which is a consequence of the maximum number of processors within the parallel computer. The restructuring and modi®cation of the parallel implementation has allowed the number of matrix elements to increase well beyond their previous limits. Comparisons of the modi®ed structure with both the serial algorithm and the initial parallel implementation are made. The advantages of using a neural network approach in this case are discussed.

It has been widely accepted that predicting stock returns is not a simple task since many market factors are involved and their structural relationships are not perfectly linear. Recently, a promising data mining technique in machine learning has been proposed to uncover the predictive relationships of numerous ÿnancial and economic variables. Inspired by the fact that the determinant between these variables and their interrelationships over stock returns changes over time, we explore this issue further by using data mining to uncover the recent relevant variables with the greatest predictive ability. The objective is to examine whether using the recent relevant variables leads to additional improvements in stock return forecasting. Given evidence of non-linearity in the ÿnancial market, the resulting variables are then provided to neural networks, including probabilistic and feed-forward neural networks, for predicting the directions of future excess stock return. The results show that redeveloped neural network models that use the recent relevant variables generate higher proÿts with lower risks than the buy-and-hold strategy, conventional linear regression, and the random walk model, as well as the neural network models that use constant relevant variables.

This paper presents the use of an intelligent hybrid stock trading system that integrates neural networks, fuzzy logic, and genetic algorithms techniques to increase the efficiency of stock trading when using a volume adjusted moving average (VAMA), a technical indicator developed from equivolume charting. For this research, a neuro-fuzzy-based genetic algorithm (NF-GA) system utilizing a VAMA membership function is introduced. The results show that the intelligent hybrid system takes advantage of the synergy among these different techniques to intelligently generate more optimal trading decisions for the VAMA, allowing investors to make better stock trading decisions.

An approach to estimate the indirect economic loss due to damaged bridges within the highway system from an earthquake event is presented. The indirect cost considered refers to the increased highway transportation cost only. The study zone covers the St. Louis metropolitan area and its surrounding suburban regions. An earthquake scenario centered in St. Louis, with a magnitude 7.0 is used. The direct earthquake loss was primarily damage to bridges, which causes an increase in travel time and distance within the transportation network. This information is then used as input for the indirect loss model. The indirect loss is examined from an economic perspective. The results reveal that the indirect loss is significant when compared to the direct loss resulting from bridge damage. From the study results, a transportation network planner can prepare an appropriate preventive action plan ͑such as choosing alternative routes for potential damaged links, as well as reinforcing possible high damage bridges͒ to reduce the potential losses before the earthquake occurs.

Stock market forecasting research offers many challenges and opportunities, with the forecasting of individual stocks or indexes focusing on forecasting either the level (value) of future market prices, or the direction of market price movement. A three-stage stock market prediction system is introduced in this article. In the first phase, Multiple Regression Analysis is applied to define the economic and financial variables which have a strong relationship with the output. In the second phase, Differential Evolution-based type-2 Fuzzy Clustering is implemented to create a prediction model. For the third phase, a Fuzzy type-2 Neural Network is used to perform the reasoning for future stock price prediction. The results of the network simulation show that the suggested model outperforms traditional models for forecasting stock market prices.