| ชื่อเรื่อง | : | Prediction of brix values of intact peaches with least squares-support vector machine regression models |
| นักวิจัย | : | Mukarev, Mihail. , Walsh, Kerry B. |
| คำค้น | : | Sucrose. , Strategic basic research. , 820211 Stone Fruit. , 070307 Crop and Pasture Post Harvest Technologies (incl. Transportation and Storage). , Peach. , Near infrared spectroscopy. , Fruit , Near infrared spectroscopy -- Partial least squares -- Least squares support vector machines -- Optimization -- LS-SVM -- Parameters -- Pruning -- Regression model -- Non-linear |
| หน่วยงาน | : | Central Queensland University, Australia |
| ผู้ร่วมงาน | : | - |
| ปีพิมพ์ | : | 2555 |
| อ้างอิง | : | http://hdl.cqu.edu.au/10018/927241 |
| ที่มา | : | Mukarev, M & Walsh, K 2012, 'Prediction of brix values of intact peaches with least squares-support vector machine regression models', Journal of Near Infrared Spectroscopy, vol. 20, online 18 October. http://dx.doi.org/10.1255/jnirs.1026 |
| ความเชี่ยวชาญ | : | - |
| ความสัมพันธ์ | : | Journal of near infrared spectroscopy. United Kingdom : N I R Publications, 2012. Vol 20, (2012), p. 1-26 26 pages Refereed 0022-2968 1751-6552 (online) , ACQUIRE [electronic resource] : Central Queensland University Institutional Repository. |
| ขอบเขตของเนื้อหา | : | - |
| บทคัดย่อ/คำอธิบาย | : | Second derivative of interactance spectra (731 – 926 nm) of intact peaches and Brix values of extracted juice were used to develop a LS-SVM regression (based on a RBF kernel) and a PLS regression model. An iterative approach was taken with the LS-SVM regression, involving a grid search with application of a gradient based optimization method using a validation set for tuning of hyperparameters, followed by pruning of the LS-SVM model with the optimized hyperparameters. The grid search approach led to five-fold faster and better determination of hyperparameters. Less than 45% of the initial 1430 calibration samples were kept in the models. In prediction of an independent test set with 120 samples, the pruned LS-SVM models performed better than the PLS model (RMSEP decreased by 9 to 14 %). |
| บรรณานุกรม | : |
Mukarev, Mihail. , Walsh, Kerry B. . (2555). Prediction of brix values of intact peaches with least squares-support vector machine regression models.
กรุงเทพมหานคร : Central Queensland University, Australia. Mukarev, Mihail. , Walsh, Kerry B. . 2555. "Prediction of brix values of intact peaches with least squares-support vector machine regression models".
กรุงเทพมหานคร : Central Queensland University, Australia. Mukarev, Mihail. , Walsh, Kerry B. . "Prediction of brix values of intact peaches with least squares-support vector machine regression models."
กรุงเทพมหานคร : Central Queensland University, Australia, 2555. Print. Mukarev, Mihail. , Walsh, Kerry B. . Prediction of brix values of intact peaches with least squares-support vector machine regression models. กรุงเทพมหานคร : Central Queensland University, Australia; 2555.
|
ridm@nrct.go.th ระบบคลังข้อมูลงานวิจัยไทย รายการโปรดที่คุณเลือกไว้
