Pei-Hsi Lee

Pei-Hsi Lee
Chaoyang University of Technology · Department of Information Management

Doctor of Philosophy

About

36
Publications
2,713
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
487
Citations
Citations since 2017
11 Research Items
216 Citations
2017201820192020202120222023010203040
2017201820192020202120222023010203040
2017201820192020202120222023010203040
2017201820192020202120222023010203040

Publications

Publications (36)
Article
In the fiercely competitive broadband internet market in China, the telecom companies are facing a large amount of customer churn. If they can predict the loss of customers and propose a method to prevent it, that will help these telecom companies improve their competitive advantage. This study uses support vector machine (SVM) to predict the loss...
Article
Control charts are widely applied in process control. Life testing is time-consuming and expensive; thus, this testing typically has a termination condition that is based on the assumption of a single failure mode. The lifetimes of unfailed units are known as right-censored data, and conditional expected value (CEV) control charts are effective for...
Article
Most studies on control chart patterns (CCPs) recognition assume that the measured values of process characteristic follow a normal distribution. However, by collecting large-size on-line datasets, it could be found that this assumption may not be tenable. In the present study, a method to combine spectral clustering technique with support vector m...
Article
Coefficient of variation (CV) control charts are widely used to monitor processes in which the mean of process characteristic varies and its standard deviation changes with the mean. However, such charts are generally insensitive to small shifts. In the present paper, a double-sampling (DS) CV chart is proposed to effectively detect the CV shifts....
Article
Lifetime is a crucial quality characteristic of electronic products that must be monitored using control charts. Lifetime may provide right-censored data. A conditional expected value (CEV) x̄ control chart was developed to monitor type I right-censored data. Researchers had always assumed that the censored time is a known constant when designing c...
Article
Tercero-Gomez et al. [Communications in Statistics - Simulation and Computation, 2012, 41(9), pp. 1566–1579] modified the Tukey's chart to improve the insensitivity of signaling mean shifts when the population is skewly distributed. They examine the efficiency for several skewed populations with the modified Tukey's chart (MTCC). The parameters of...
Article
A combination of double sampling and variable sampling interval (DSVSI) charts can increase the efficiency of signaling small shifts. This study proposes joint DSVSI X¯ and s charts and investigates their statistical performance. The proposed approach uses a Markov chain approach to compute the statistical performance, and uses a statistical design...
Article
Statistical process control is the application of statistical methods to the monitoring of process variations. The control chart is a key tool in statistical process control. Tukey's chart is easy to set up and can use a single observation to monitor a process. Using asymmetrical control limits, Tukey's chart can quickly detect positive and negativ...
Article
A combination of double sampling X¯ chart and variable sampling intervals X¯ chart (DSVSI) can successfully reduce the detection time of small mean shift. Before a DSVSI X¯ chart is used, its design parameters should be determined. This study constructs an economic design model of DSVSI X¯ chart for the determination of the design parameters. T...
Article
The Shewhart s chart has been widely used to monitor the standard deviation of a process. However, the main disadvantage of an s chart is its slowness to signal small increases in the variability. In this paper, ideas of adaptive control charts are extended to the Shewhart s chart for improving the efficiency in signalling increases in the standard...
Article
Max chart uses a single chart to control the process mean and variance. It performs with similar efficiency to joint and s charts. This study combined adaptive chart and Max chart to increase the detecting ability. A Markov chain approach was used to develop the statistical indicator and statistical design model of adaptive Max charts. This study d...
Article
This study extended the idea of Carot et al. (20021. Carot , V. , Jabaloyes , J. M. , Carot , T. ( 2002 ). Combined double sampling and variable sampling interval chart . Int. J. Product. Res. 40 ( 9 ): 2175 – 2186 . View all references) to combine double sampling and variable sampling interval s charts (DSVSI s chart) for improving efficiency in d...
Article
Full-text available
Burn-in has been widely used as an effective procedure for screening out failed electronic products during the early-failure period, before shipment to the customers. Environmental stress such as temperature is increasingly being used to effectively shorten the burn-in time, and this method is usually called an accelerated burn-in test. When differ...
Article
Full-text available
Tukey's chart uses a single observation to monitor the process mean, and it is suitable for monitoring of destructive testing data. Tukey's chart adopts symmetrical control limits to monitor process and it is insensitive to signal mean shifts when the monitoring variable follows a skew distribution. This study proposes Tukey's chart with asymmetric...
Article
This study performs a model to evaluate the river water quality monitoring system. The standard River Pollution Index which includes dissolved oxygen (DO), biochemical oxygen demand (BOD5), suspended solids (SS), and ammonia nitrogen (NH3-N) is collected from years 2006 to 2010 for monitoring of river water quality. Furthermore, control chart techn...
Article
The Shewhart R control chart (R chart) has been widely used to monitor process variance. However, the main disadvantage of an R chart is its slowness to signal small increases on the variability. In this paper, ideas of adaptive control charts are extended to the Shewhart R chart for improving efficiency in signaling increases on the variance. A Ma...
Conference Paper
The product quality will be growth as operational time and experience increase after a production process introduces a new technology. A growth curve can forecast the quality growth. This study applies a logistic growth curve to constructs an evaluation method of quality growth for larger-the-better characteristic. The parameter estimation method o...
Article
In semiconductor processes, many data of process were obtained by the destructive testing methods, which will incur high inspection cost. Double Sampling (DS) s charts can quickly detect the shifts of process standard deviation and effectively reduce sample size. In this study, DS s charts were designed based on a statistical viewpoint, and their p...
Article
A combination of double sampling the [image omitted] chart and the variable sampling interval of the [image omitted] chart (DSVSI [image omitted] chart) increases the sensitivity in the small shift detection. A usual assumption of control charts is that the process observations are normally distributed. However, this assumption may not be true for...
Article
Double sampling X¯ control chart (DS) which is a Shewhart-type chart can reduce sample size and detect small process shift fast. In process monitoring of real industry, observations may be interdependent and correlated, and an original DS design will occur high cost for the wrong determination of the process state. In this study, an economic design...
Conference Paper
Double sampling X control chart (DS) which is a Shewhart-type chart can reduce sample size and detect small process shift fast. In real industries, process observations may be interdependent and correlated, and the statistical performance of DS X chart for the correlated data need to be re-evaluated. This article constructs the calculations of stat...
Article
The double sampling (DS) chart can reduce the sample size when monitoring the process mean. In this study, Duncan's cost model was modified by adding the statistical constraints to develop the design model of DS chart for the optimization of design parameters--sample size, control limit coefficient, warning limit coefficient and sampling interval....
Article
In this study, the performances of double sampling (DS) chart under non normality are presented and compared with Shewhart chart and VP chart. The comparison result shows the DS chart has performance as good as the VP chart, but it is more effective than the Shewhart chart in detecting small process mean shifts.
Article
The significant features of Tukey's control chart include characteristics such as: easy setup, use of single observation to monitor process, and suitability to monitor destructive testing processes. The control limit width and sampling interval should be determined before Tukey's control chart can be used. In this study, Duncan's cost function is m...
Article
Burn-in has been widely used as an effective procedure for screening out failures in the early operating period the electronic product, before it is shipped to the customers. Increasing the environmental stress such as temperat can effectively shorten the burn-in time, and this method is usually called accelerated burn-in test. When differ stress l...
Article
The mixed-Weibull distribution is widely used to analyze the burn-in time. Kececioglu had presented its parameter estimation method with application of Weibull probability plot (WPP) such a graphic analysis method. However his method is not easy to estimate parameters when the data loses the failure mode information. A self-organizing map neural ne...
Article
A Tukey's control chart was designed to monitor single observation data. Its easy control-limits setting and simple statistical concept are the most important advantages. In this study, we setup the Tukey's control chart based on known probability distribution and construct its average run length calculator. ARL performance of the Tukey's control c...
Article
Full-text available
Back-propagation network (BPN) has the advantage of simulating a nonlinear system that is difficult to describe by a physical model. This study introduces a back-propagation network methodology to estimate the accelerated life reliability. The environmental stresses and failure times are chosen as the input variables. An optimum prediction system i...

Network

Cited By