Image processing approach to features extraction in classification of control chart patterns

Lavangnananda, Kittichai; Piyatumrong, Apivadee

doi:10.1109/smcia.2005.1466953

Cited by 13 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The testing data set contained the same number of input vectors as the training set. After testing, the proposed method was done to test with the 600 unknown patterns (100 for each type) which accepted by the reference paper [11,12,13]. The testing results in a confusion matrix (Table II) In the comparisons (Table III), when compares this method with a symbol-sequence histogram ( Figure 6) [10] and neural networks, the proposed method offer better performances than them.…”

Section: The Neural Network Predictions and Discussion Of The Resmentioning

confidence: 99%

Control chart pattern classification using fourier descriptors and neural networks

Phokharatkul

Phaiboon

2011

2011 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC)

View full text Add to dashboard Cite

This paper presents the method of Fourier descriptors and neural networks developed for control chart pattern analysis. The pattern analysis is important to achieve appropriate control and to produce high quality products. This paper also investigates the use of features extracted from Fourier descriptors as the Fourier coefficient components. The Fourier coefficients used to train the neural networks for classifying patterns. Thus, the networks were able to identify the classes. This research concluded the extracted features to improve the performance of the number of Fourier coefficients for neural network training. Experimental results and comparisons based on simulated and unknown data show that the proposed approach performs better than the symbol-sequence histogram with neural network approach.

show abstract

Section: The Neural Network Predictions and Discussion Of The Resmentioning

confidence: 99%

Control chart pattern classification using fourier descriptors and neural networks

Phokharatkul

Phaiboon

2011

2011 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC)

View full text Add to dashboard Cite

show abstract

“…• Extending the above research, Lavangnananda & Piyatumrong [38] added 2 more first order features aimed to better discern between noisy increasing and decreasing behaviour. As well, a further set of second order features obtained from smoothed data was added, bringing the total number of features fed into the neural network to 18.…”

Section: Feature-based Similarity Measures For Clustering and Classifmentioning

confidence: 96%

Evolutionary Synthesis of Stochastic Gene Network Models Using Feature-based Search Spaces

Imada

Ross

2011

New Gener. Comput.

View full text Add to dashboard Cite

A feature-based fitness function is applied in a genetic programming system to synthesize stochastic gene regulatory network models whose behaviour is defined by a time course of protein expression levels. Typically, when targeting time series data, the fitness function is based on a sum-of-errors involving the values of the fluctuating signal. While this approach is successful in many instances, its performance can deteriorate in the presence of noise. This thesis explores a fitness measure determined from a set of statistical features characterizing the time series' sequence of values, rather than the actual values themselves.Through a series of experiments involving symbolic regression with added noise and gene regulatory network models based on the stochastic π-calculus, it is shown to successfully target oscillating and non-oscillating signals. This practical and versatile fitness function offers an alternate approach, worthy of consideration for use in algorithms that evaluate noisy or stochastic behaviour.

show abstract

“…These patterns are generated by GARH (Generalized Autoregressive Conditional Heteroskedasticity Model). These equations are commonly used in all previous researches in this area [9], [10], [11].…”

Section: Control Chart Patternsmentioning

confidence: 99%

“…Preprocessing of CCPs is also popular method to improve classification performance. In recent years, the most popular technique is features extraction such as those used in image processing [10] and [18]. Synergistic of neural networks were also introduce together with features extraction in [19] and [20].…”

Section: Literature Reviewmentioning

confidence: 99%

Systematic study to assess neural networks' capability in classifying control chart patterns

Lavangnananda

Kasikitsakulphol

2010

2010 IEEE International Conference on Intelligent Computing and Intelligent Systems

View full text Add to dashboard Cite

Image processing approach to features extraction in classification of control chart patterns

Cited by 13 publications

References 12 publications

Control chart pattern classification using fourier descriptors and neural networks

Control chart pattern classification using fourier descriptors and neural networks

Evolutionary Synthesis of Stochastic Gene Network Models Using Feature-based Search Spaces

Systematic study to assess neural networks' capability in classifying control chart patterns

Contact Info

Product

Resources

About