This research aimed to establish near infrared(NIR)spectroscopy models for identification ofsyrup types in which the maple syrup was discriminated from other syrup types.Thirty syruptypes were used in this research;th...This research aimed to establish near infrared(NIR)spectroscopy models for identification ofsyrup types in which the maple syrup was discriminated from other syrup types.Thirty syruptypes were used in this research;the NIR spectra of each type were recorded with 10 replicates.The repeatability and reproducibility of NIR scamning were perfomed,and the absorbance atG940cn-1 was used for calculation,.Principal component analysis was used to group the syruptype.Identification models were developed by soft independent modeling by,class analogy(SIMCA)and partial least-squares diseriminant analysis(PLS.DA),The SiMCA models of alsyrup types exhibited accuracy percentage of 93.3-100%for identifying syrup types,whereasmaple syrup discrimination models showed percentage of accuracy between 83.2%and 100%.The PLS-DA technique gave the accuracy of syrup types classification bet ween 96.6%and 100%and presented ability on discrimination of maple syrup form other types of syrup with accuracyof 100%.The finding presented the potential of NIR spectroscopy for the syrup typeidentification.展开更多
Support Vector Machine (SVM) is a very specific type of learning algorithms characterized by the capacity control of the decision function, the use of the kernel functions and the sparsity of the solution. In this pap...Support Vector Machine (SVM) is a very specific type of learning algorithms characterized by the capacity control of the decision function, the use of the kernel functions and the sparsity of the solution. In this paper, we investigate the predictability of financial movement direction with SVM by forecasting the weekly movement direction of NIKKEI 225 index. To evaluate the forecasting ability of SVM, we compare the perfor-mance with those of Linear Discriminant Analysis, Quadratic Discriminant Analysis and Elman Backpropagation Neural Networks. The experiment results show that SVM outperforms other classification methods. Furthermore, we propose a combining model by integrating SVM with other classification methods. The combining model performs the best among the forecasting methods.展开更多
文摘This research aimed to establish near infrared(NIR)spectroscopy models for identification ofsyrup types in which the maple syrup was discriminated from other syrup types.Thirty syruptypes were used in this research;the NIR spectra of each type were recorded with 10 replicates.The repeatability and reproducibility of NIR scamning were perfomed,and the absorbance atG940cn-1 was used for calculation,.Principal component analysis was used to group the syruptype.Identification models were developed by soft independent modeling by,class analogy(SIMCA)and partial least-squares diseriminant analysis(PLS.DA),The SiMCA models of alsyrup types exhibited accuracy percentage of 93.3-100%for identifying syrup types,whereasmaple syrup discrimination models showed percentage of accuracy between 83.2%and 100%.The PLS-DA technique gave the accuracy of syrup types classification bet ween 96.6%and 100%and presented ability on discrimination of maple syrup form other types of syrup with accuracyof 100%.The finding presented the potential of NIR spectroscopy for the syrup typeidentification.
基金This work is partially supported by Ministry of Education, Culture, Sports, Science and Technology of Japan, National Natural Science Foundation of China, Chinese Acedemy of Sciences, Key Laboratory of Management, Decision and Information Systems
文摘Support Vector Machine (SVM) is a very specific type of learning algorithms characterized by the capacity control of the decision function, the use of the kernel functions and the sparsity of the solution. In this paper, we investigate the predictability of financial movement direction with SVM by forecasting the weekly movement direction of NIKKEI 225 index. To evaluate the forecasting ability of SVM, we compare the perfor-mance with those of Linear Discriminant Analysis, Quadratic Discriminant Analysis and Elman Backpropagation Neural Networks. The experiment results show that SVM outperforms other classification methods. Furthermore, we propose a combining model by integrating SVM with other classification methods. The combining model performs the best among the forecasting methods.
