KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Settings

Has files: NoSubject: search.filters.subject.Kernel

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Equatorial Plasma Bubble Detection by Support Vector Machine at Chumphon Station, Thailand
    (2022-01-01)
    Thanakulketsarat, Thananphat
    ;
    Supnithi, Pornchai
    ;
    Myint, Lin Min Min
    ;
    Hozumi, Kornyanat
    Equatorial Plasma Bubble (EPB) is a phenomenon in which depletion of plasma density occurs in the ionosphere particularly in the equatorial region. It can degrade the performances of the navigation system and satellite communication. In this work, we analyze EPB based on the very-high frequency (VHF) radar images at Chumphon station, Thailand. Then an EPB detection system using the support vector machine (SVM) technique is developed, and the accuracies of the systems using different kernels: linear kernel, the polynomial kernel, the radial basic functions kernel (RBF), and the sigmoid kernel are compared. Among the different kernels, we find that the RBF kernel gives the highest accuracy in prediction at 86.67 percent.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Classification of high-resolution NMR spectra based on complex wavelet domain feature selection and kernel-induced random forest
    (2010-12-01)
    Fan, Guangzhe
    ;
    Wang, Zhou
    ;
    Kim, Seoung Bum
    ;
    Temiyasathit, Chivalai
    High-resolution nuclear magnetic resonance (NMR) spectra contain important biomarkers that have potentials for early diagnosis of disease and subsequent monitoring of its progression. Traditional features extraction and analysis methods have been carried out in the original frequency spectrum domain. In this study, we conduct feature selection based on a complex wavelet transform by making use of its energy shift-insensitive property in a multi-resolution signal decomposition. A false discovery rate based multiple testing procedure is employed to identify important metabolite features. Furthermore, a novel kernel-induced random forest algorithm is used for the classification of NMR spectra based on the selected features. Our experiments with real NMR spectra showed that the proposed method leads to significant reduction in misclassification rate. © Springer-Verlag Berlin Heidelberg 2010.