Hassen Taleb

On fuzzy and probabilistic control charts

In this article, different procedures of constructing control charts for linguistic data, based on fuzzy and probability theory, are discussed. Three sets of membership functions, with different degrees of fuzziness, are proposed for fuzzy approaches. A comparison between fuzzy and probability approaches, based on the Average Run Length and samples under control, is conducted for real data. Contrary to the conclusions of Raz and Wang (1990b) the choice of degree of fuzziness affected the sensitivity of control charts.

Monitoring the Coefficient of Variation Using Control Charts with Run Rules

Abstract Monitoring the coefficient of variation (CV) is a successful approach to Statistical Process Control when the process mean and standard deviation are not constant. In recent years the CV has been investigated by many researchers as the monitored statistic for several control charts. Viewed under this perspective, this paper presents a new efficient method to monitor the CV by means of Run Rules (RR) type charts. Tables are provided to show the statistical run length properties of Shewhart- y , RR2,3 -y , RR3,4 -y and RR4,5 -y control charts for several combinations of in control CV values y0 , sample size n and shift size r. Indeed, comparative studies have been performed to find the best control chart for each combination. An example illustrates the use of these charts on real data gathered from a metal sintering process.

Monitoring the Coefficient of Variation Using a Variable Sampling Interval Control Chart

The coefficient of variation (CV) is a quality characteristic that has several applications in applied statistics and is receiving increasing attention in quality control. Few papers have proposed control charts that monitor this normalized measure of dispersion. In this paper, an adaptive Shewhart control chart implementing a variable sampling interval (VSI) strategy is proposed to monitor the CV. Tables are provided for the statistical properties of the VSI CV chart, and a comparison is performed with a Fixed Sampling Rate Shewhart chart for the CV. An example illustrates the use of these charts on real data gathered from a casting process. Copyright

Multivariate Fuzzy Multinomial Control Charts

Abstract Two approaches for constructing control charts to monitor multivariate attribute processes when data set is presented in linguistic form are suggested. Two monitoring statistics T2f and W2 are developed based on fuzzy and probability theories. The first is similar to the Hotelling’s T2 statistic and is based on representative values of fuzzy sets. The distribution of W2 statistic, being a linear combination of dependent chi-square variables, is derived using Satterthwaite’s approximation. Resulting multivariate control charts are compared based on the average run length (ARL). A numerical example is given to illustrate the application of the proposed multivariate control charts and the interpretation of out-of-control signals.

One-Sided Shewhart-type Charts for Monitoring the Coefficient of Variation in Short Production Runs

Abstract Monitoring the coefficient of variation is an effective approach to Statistical Process Control when the process mean and standard deviation are not constant but their ratio is constant. Until now, research has not investigated the monitoring of the coefficient of variation for short production runs. Viewed under this perspective, this paper proposes a new method to monitor the coefficient of variation for a finite horizon production by means of one-sided Shewhart-type charts. Tables are provided for the statistical properties of the proposed charts when the shift size is deterministic. Two illustrative examples are given in order to illustrate the use of these charts on real data.

Automatic detection of lesions in lung regions that are segmented using spatial relations

This article presents a novel approach for the automatic detection of lesions and selection of features on chest radiographs. We have illustrated the importance of accurate segmentation, which is based on spatial relationships between the lung structures, as a preprocessing step in a Computer Aided Diagnosis (CAD) scheme. Then, three suitable combinations of features have been identified using the forward stepwise selection method from the original images and their transformed ones. Experimental results show that our segmentation approach and the suppression of skeletal structures improve the detection accuracy. The selected features can describe efficiently different kinds of chest lesions.

One-Sided Run Rules Control Charts for Monitoring the Coefficient of Variation in Short Production Runs

This paper proposes a new efficient method to monitor the coefficient of variation (CV) in a short production run context by means of one-sided run rules type charts. Plotting points on run rules control charts is a stochastic process modelled in this paper by using Markov chains to get their main statistical properties. Proofs concerning the computation of the truncated run length properties are given. Tables summarising the main numerical results for several combinations of in-control CV values, sample sizes and shift sizes are provided. Moreover, a comparison analysis has been performed to show that implementing one-sided run rules type charts is the best decision most of the time. Finally, an example illustrates the use of these charts on real data. [Received 25 May 2014; Revised 17 November 2015; Accepted 28 March 2016]

A Hybrid Fuzzy-SVM classifier for automated lung diseases diagnosis

Abstract A novel scheme for lesions classification in chest radiographs is presented in this paper. Features are extracted from detected lesions from lung regions which are segmented automatically. Then, we needed to eliminate redundant variables from the subset extracted because they affect the performance of the classification. We used Stepwise Forward Selection and Principal Components Analysis. Then, we obtained two subsets of features. We finally experimented the Stepwise/FCM/SVM classification and the PCA/FCM/SVM one. The ROC curves show that the hybrid PCA/FCM/SVM has relatively better accuracy and remarkable higher efficiency. Experimental results suggest that this approach may be helpful to radiologists for reading chest images.