Optimization of Principal-Component-Analysis-Applied <i>in Situ</i> Spectroscopy Data Using Neural Networks and Genetic Algorithms

Kim, Byungwhan; Kwon, Min Ji

doi:10.1366/000370208783412717

Cited by 20 publications

(7 citation statements)

References 18 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As suggested above, an alternative could be to select PC in the CV procedure based on maximum prediction accuracy. In addition, more sophisticated techniques such as the combination of statistical methods like PCA, neural networks and genetic algorithms could be applied, as has already been tested in other fields [52]. However, a balance between benefits (e.g.…”

Section: Discussionmentioning

confidence: 99%

A comparison of principal component regression and genomic REML for genomic prediction across populations

et al. 2014

View full text Add to dashboard Cite

BackgroundGenomic prediction faces two main statistical problems: multicollinearity and n ≪ p (many fewer observations than predictor variables). Principal component (PC) analysis is a multivariate statistical method that is often used to address these problems. The objective of this study was to compare the performance of PC regression (PCR) for genomic prediction with that of a commonly used REML model with a genomic relationship matrix (GREML) and to investigate the full potential of PCR for genomic prediction.MethodsThe PCR model used either a common or a semi-supervised approach, where PC were selected based either on their eigenvalues (i.e. proportion of variance explained by SNP (single nucleotide polymorphism) genotypes) or on their association with phenotypic variance in the reference population (i.e. the regression sum of squares contribution). Cross-validation within the reference population was used to select the optimum PCR model that minimizes mean squared error. Pre-corrected average daily milk, fat and protein yields of 1609 first lactation Holstein heifers, from Ireland, UK, the Netherlands and Sweden, which were genotyped with 50 k SNPs, were analysed. Each testing subset included animals from only one country, or from only one selection line for the UK.ResultsIn general, accuracies of GREML and PCR were similar but GREML slightly outperformed PCR. Inclusion of genotyping information of validation animals into model training (semi-supervised PCR), did not result in more accurate genomic predictions. The highest achievable PCR accuracies were obtained across a wide range of numbers of PC fitted in the regression (from one to more than 1000), across test populations and traits. Using cross-validation within the reference population to derive the number of PC, yielded substantially lower accuracies than the highest achievable accuracies obtained across all possible numbers of PC.ConclusionsOn average, PCR performed only slightly less well than GREML. When the optimal number of PC was determined based on realized accuracy in the testing population, PCR showed a higher potential in terms of achievable accuracy that was not capitalized when PC selection was based on cross-validation. A standard approach for selecting the optimal set of PC in PCR remains a challenge.Electronic supplementary materialThe online version of this article (doi:10.1186/s12711-014-0060-x) contains supplementary material, which is available to authorized users.

show abstract

Section: Discussionmentioning

confidence: 99%

A comparison of principal component regression and genomic REML for genomic prediction across populations

et al. 2014

View full text Add to dashboard Cite

show abstract

“…예컨대, 소스전력의 감소에 따라 증착률 이 증가되거나 3) , 바이어스의 감소에 따른 굴절률의 증가 4 8) . 공정변수(소 스전력, 압력 등)와 박막특성(증착률, 식각률 등) 간 의 모델링외에, 신경망은 공정 중 수집되는 in-situ 정보와 박막특성간의 모델링, 예컨대 optical emission spectroscopy 데이터와 식각특성간의 모델 9) , 또는 x-ray photoelectron spectroscopy와 같은 박막표면진 단특성과 표면거칠기의 모델링에 10 A + a * E h + bE l 참고문헌…”

Section: 서 론unclassified

Neural Network Modeling of Ion Energy Impact on Surface Roughness of SiN Thin Films

Kim¹,

Lee²

2010

Journal of the Korean institute of surface engineering

View full text Add to dashboard Cite

Surface roughness of deposited or etched film strongly depends on ion bombardment. Relationships between ion bombardment variables and surface roughness are too complicated to model analytically. To overcome this, an empirical neural network model was constructed and applied to a deposition process of silicon nitride (SiN) films. The films were deposited by using a pulsed plasma enhanced chemical vapor deposition system in SiH 4-NH 4 plasma. Radio frequency source power and duty ratio were varied in the range of 200-800 W and 40-100%. A total of 20 experiments were conducted. A non-invasive ion energy analyzer was used to collect ion energy distribution. The diagnostic variables examined include high (or) low ion energy and high (or low) ion energy flux. Mean surface roughness was measured by using atomic force microscopy. A neural network model relating the diagnostic variables to the surface roughness was constructed and its prediction performance was optimized by using a genetic algorithm. The optimized model yielded an improved performance of about 58% over statistical regression model. The model revealed very interesting features useful for optimization of surface roughness. This includes a reduction in surface roughness either by an increase in ion energy flux at lower ion energy or by an increase in higher ion energy at lower ion energy flux.

show abstract

“…Valery et al (1995) developed a process model for dynamic responses, including power draw, grinding charge level, slurry level, and product size distribution for changes in feed rate, size and hardness, and water addition. Principal component analysis (PCA) and factor analysis (FA) for process monitoring and system diagnosis have been proposed for batch processes applications (Nomikos and MacGregor, 1995;Yoon and MacGregor, 2004;Kim and Kwon, 2008). They have been successfully used in the mining industry for analysing ventilation methane emissions and for constructing a prediction model for long-wall mines using artificial neural networks (Karacan, 2008).…”

Section: Introductionmentioning

confidence: 99%

SAG mill system diagnosis using multivariate process variable analysis

Ko¹,

Shang²

2011

Can J Chem Eng

View full text Add to dashboard Cite

Semi-autogenous grinding (SAG) of ore plays a critical role in a mineral processing plant. In SAG operations, abnormal conditions, such as overload or insufficient ore holdup, often result in inefficient production and unstable operation. It is, therefore, essential to monitor the process using effective technology so that abnormal or faulty conditions can be detected and addressed in a timely manner. In this study, investigation is focused on applying multivariate analysis in the monitoring and diagnosing of an industrial SAG operation. The results show that principal component analysis provides an effective methodology for on-line monitoring and diagnosis. The detection and removal of faulty conditions will help to provide stable and cost-efficient operation.Le broyage semi-autogène (BSA) du minerai joue un rôle essentiel dans une usine de traitement des minéraux. Dans les activités de BSA, des conditions anormales, comme une surcharge ou une retenue du minerai insuffisante, mènent souventà une production inefficace et un fonctionnement instable. Il est, par conséquent, essentiel de surveiller le processusà l'aide d'une technologie efficace pour que les conditions anormales soient détectées et abordées de manière opportune. Dans ce document, l'enquête est axée sur l'utilisation d'une analyse multivariée dans le suivi et le diagnostic d'une activité de BSA industrielle. Les résultats indiquent que l'analyse des principaux composants fournit une méthodologie efficace pour le suivi et le diagnostic en ligne. La détection et le retrait de ses conditions anormales aiderontà procurer un fonctionnement stable et economique.

show abstract

Optimization of Principal-Component-Analysis-Applied in Situ Spectroscopy Data Using Neural Networks and Genetic Algorithms

Cited by 20 publications

References 18 publications

A comparison of principal component regression and genomic REML for genomic prediction across populations

A comparison of principal component regression and genomic REML for genomic prediction across populations

Neural Network Modeling of Ion Energy Impact on Surface Roughness of SiN Thin Films

SAG mill system diagnosis using multivariate process variable analysis

Contact Info

Product

Resources

About