Jozef Zurada

A neural network-based system for classification of industrial jobs with respect to risk of low back disorders due to workplace design.

Despite many years of research efforts, the occupational exposure limits of different risk factors for development of low back disorders (LBDs) have not yet been established. One of the main problems in setting such guidelines is the limited understanding of how different risk factors of LBDs interact in causing the injury, as the nature and mechanism of these disorders are relatively unknown phenomena. The task of an industrial ergonomist is complicated because the potential risk factors that may contribute to the onset of LBDs interact in a complex way, and require an analyst to apply elaborate data measurement and collection techniques for a realistic job analysis. This makes it difficult to discriminate well between the jobs that place workers at high or low risk of LBDs. The main objective of this study was to develop an artificial neural network-based diagnostic system which can classify industrial jobs according to the potential risk for low back disorders due to workplace design. Such a system could be useful in hazard analysis and injury prevention due to manual handling of loads in industrial environments. The results show that the developed diagnostic system can successfully classify jobs into the low and high risk categories of LBDs based on lifting task characteristics.

A neuro-fuzzy approach for robot system safety

Robot safety is a critical and largely unsolved problem involving the interaction of man and machine. The paper presents a new approach to robot safety which uses an integrated sensing architecture for monitoring the robot workspace, and a new detection and decision logic for regulating the safe operation of the robot. Sensory information is fused through a trained neural network to produce a map of the hazards. Using this combined map, and information about the robots current position and velocity, a set of fuzzy logic rules has been implemented to regulate robot activity. Simulation results presented in the paper indicate that this method is both effective in detection of potentially hazardous situations and computationally feasible.

Next Generation of Data-Mining Applications

This chapter focuses on the development of an active learning approach to an image mining problem for detectingEgeria densa(a Brazilian waterweed) in digital imagery. An effective way of automatic image classification is to employ learning systems. However, due to a large number of images, it is often impractical to manually create labeled data for supervised learning. On the other hand, classification systems generally require labeled data to carry out learning. In order to strike a balance between the difficulty of obtaining labeled images and the need for labeled data, we explore an active learning approach to image mining. The goal is to minimize the task of expert labeling of images: if labeling is necessary, only those important parts of an image will be presented to experts for labeling. The critical issues are: (1) how to determine what should be presented to experts; (2) how to minimize the number of those parts for labeling; and (3) after a small number of labeled instances are available, how to effectively learn a classifier and apply it to new images. We propose to use ensemble methods for active learning in Egeria detection. Our approach is to use the combined classifications of the ensemble of classifiers to reduce the number of uncertain instances in the image classification process and thus achieve reduced expert involvement in image labeling. We demonstrate the effectiveness of our proposed system via experiments using a real-world application of Egeria detection. Practical concerns in image mining using active learning are also addressed and discussed.Trends in data-mining applications : from research labs to fortune 500 companies. 1. Mining wafer fabrication : framework and challenges. 2. Damage detection employing data-mining techniques. 3. Data projection techniques and their application in sensor array data processing. 4. An application of evolutionary and neural data-mining techniques to customer relationship management. 5. Sales opportunity miner : data mining for automatic evaluation of sales opportunity. 6. A fully distributed framework for cost-sensitive data mining. 7. Application of variable precision rough set approach to care driver assessment. 8. Discovery of patterns in earth science data using data mining. 9. An active learning approach to Egeria densa detection in digital imagery. 10. Experiences in mining data from computer simulations. 11. Statistical modeling of large-scale scientific simulation data. 12. Data mining for gene mapping. 13. Data-mining techniques for microarray data analysis. 14. The use of emerging patterns in the analysis of gene expression profiles for the diagnosis and understanding of diseases. 15. Proteomic data analysis : pattern recognition for medical diagnosis and biomarker discovery. 16. Discovering patterns and reference models in the medical domain of isokinetics. 17. Mining the cystic fibrosis data. 18. On learning strategies for topic-specific web crawling. 19. On analyzing web log data : a parallel sequence-mining algorithm. 20. Interactive methods for taxonomy editing and validation. 21. The use of data-mining techniques in operational crime fighting. 22 .Using data mining for intrusion detection. 23. Mining closed and maximal frequent itemsets. 24. Using fractals in data mining. 25 .Genetic search for logic structures in data.

Could Decision Trees Improve the Classification Accuracy and Interpretability of Loan Granting Decisions

The paper compares the classification performance rate of eight models: logistic regression (LR), neural network (NN), radial basis function neural network (RBFNN), support vector machine (SVM), case-base reasoning (CBR), and three decision trees (DTs). We build models and test their classification accuracy rates on a historical data set provided by a German financial institution. The data set contains 21 financial attributes of 1000 customers. Though at the time of loan application all individuals deemed to the institution to be qualified to obtain a loan, 300 of them defaulted upon a loan and 700 paid it off. To obtain reliable and unbiased error estimates for each of the eight models we apply 10-fold cross-validation and repeat an experiment 10 times. We found that in the overall classification accuracy rates at 0.5 probability cut-off, two of the three DT models significantly outperformed (at alpha=0.05) the other remaining models. We then concentrate our attention on DT models and compare their performance at 0.3 and 0.7 cut-off levels which are more likely to be used by financial institutions. The DT models not only classify better than the other models, but the knowledge they learn in the form of if-then rules is easy to interpret, makes sense, and might be of value to financial institutions which may have to explain the reasons for a loan denial.

Classifying the risk of work related low back disorders due to manual material handling tasks

Work related low back disorders (LBDs) due to manual lifting tasks (MLTs) have long been recognized as one of the main occupational disabling injury that affects the quality of life of the industrial working population in the U.S. There have been a number of intensive research efforts devoted to understanding the phenomena of LBDs and building classification models that could effectively distinguish between high risk and low risk MLTs that contribute to LBDs. As of today, however, such models and the occupational exposure limits of different risk factors causing LBDs as well as the guidelines preventing them have not yet been fully proposed. One of the first efforts to comprehend the nature and phenomenon of LBDs was undertaken by Marras et al. (1993). They created a seminal data set and used it to build logistic regression (LR) models to identify significant variables and classify MLTs into high risk and low risk with respect to LBDs. Since then a number of studies have used the same data set to build and test various classifiers to detect the likelihood of LBDs due to manual material handling jobs. This paper summarizes and critiques the previous studies. It also employs this data set to build and test seven classification models, two of which have not been applied in this context yet. The parameters of the models have been calibrated for the best performance, and the models were constructed and validated on the full set and the reduced set of features. Though the performances of our best models are better than those reported in National Institute for Occupational Health and Safety (NIOHS) Guides and two of our previous studies, they are generally less optimistic than those reported in several other studies; this paper proposes a systematic and more reliable approach to creating and validating classifiers to distinguish between low and high risk MLTs that contribute to LBDs.

Effective RNS scaling algorithm with the Chinese remainder theorem decomposition

A novel scaling technique in the residue number system (RNS) is proposed. In this technique, the main computational effort is made in the precomputing phase. The remainder calculations are performed by the modulo and binary adders. The scaling requires one look-up cycle and time for modulo addition of the n+2 operands. In the proposed approach there are restrictions neither on the form and the size nor on the number of moduli of the RNS. The scaling factor K can be integer or real, and it must fulfill merely a weak condition K > n, where n is the number of moduli. The absolute scaling error by using the correction scheme does not exceed 1.5.<<ETX>>

Investigation of Artificial Neural Networks for Classifying Levels of Financial Distress of Firms: The Case of an Unbalanced Training Sample

Accurateprediction of financial distress of firms is crucial to bank lending officers, financial analysts, and stockholders as all of them have a vested interest in monitoring the firms’ financial performance. Most of the previous studies concerning predicting financial distress were performed for a dichotomous state such as nonbankrupt versus bankrupt or no going concern opinion versus going concern opinion. Many studies used well-balanced samples. Much less than one-half of firms become distressed and firms generally progress through different levels of financial distress before bankruptcy. Therefore, this study investigates the usefulness of artificial neural networks in classifying several levels of distress for unbalanced but somewhat realistic training samples. The chapter also compares the classification ability of neural networks and logistic regression through extensive computer simulation of several experiments. Results from these experiments indicate that analysis with two cascaded neural networks produce the best classification results. One network separates healthy from distressed firms only, the other network classifies those firms identified as distressed into one of three distressed states.

Applications of fuzzy-based linguistic patterns for the assessment of computer screen design quality

The main objective of this study was to develop a modeling framework which would unify different aspects of computer screen design and result in a quantitative criterion for an optimized computer screen format. The fuzzy set‐based linguistic design patterns were utilized as a tool to build this model. The linguistic patterns are based on categories of expressions related closely to natural language and truth values, which are close to a human designers intuition. The proposed framework is capable of assessing the quality of computer screen design based on existing knowledge in human‐computer interface domain using the fuzzy‐based linguistic pattern approach. Exemplary patterns for an optimal screen density, information grouping, and some aspects of screen layout are presented, along with a sequence of calculations based on the exemplary screen format. This study showed that it is possible to achieve a rational and relatively easy to interpret assessment of different screen designs in the form of the degr...

Analyzing Massive Data Sets: An Adaptive Fuzzy Neural Approach for Prediction, with a Real Estate Illustration

Drawing useful predictions from vast accumulations of data is becoming critical to the success of an enterprise. Organizations’ databases grow exponentially from transactions with external stakeholders in addition to their own internal activities. An important organizational computing issue is that, as they grow, the databases become potentially more valuable and also more difficult to analyze. One example is predicting the value of residential real estate based on past comparable sales transactions. This is critical to several important sectors of the US economy including the mortgage finance industry and local governments that collect property taxes. The common methodology for dealing with such property valuation is based on multiple regression, although this methodology has been found to be deficient. Data mining methods have been proposed and tested as an alternative, but the results are very mixed. This article introduces a novel approach for improving predictions using an adaptive, neuro-fuzzy inference model, and illustrates its application to real estate property price prediction through the use of comparable properties. Although neuro-fuzzy–based approaches have been found to be effective for classification and estimation in many fields, there is very little existing work that investigates their potential in a real estate context. In addition, this article addresses several common problems in existing studies, such as small sample size, lack of rigorous data sampling, and poor model validation and testing. Our model is tested with real sales data from the assessment office in a large US city. The results show that the neuro-fuzzy model is superior in all of the test scenarios. The article also discusses and refines a unique technique to defining comparable properties to improve accuracy. Test results show very promising potential for this technique in mass appraisal in real estate and similar contexts when used with the neuro-fuzzy model.

A comparison of the ability of neural networks and logit regression models to predict levels of financial distress

In this study we compared the classification accuracy rates of neural networks to those from ordinal logit models for a multi-state response variable. The results indicate that with the multi-state response variable, neural networks produce higher overall classification rates than ordinal logit models, but do not more accurately classify distressed firms. As a result, we can not clearly state that neural networks are superior to regression when predicting more than one level of financial distress.