KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Liu, DiHas files: No

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    The dynamics of wetland cover change using a state estimation technique applied to time-series remote sensing imagery
    (2017-12-15)
    Insom, Patcharin
    ;
    Cao, Chunxiang
    ;
    Boonsrimuang, Pisit
    ;
    Torteeka, Peerapong
    ;
    Boonprong, Sornkitja
    Monitoring the dynamics of inundation areas in wetlands over contiguous years is important because it influences wetland ecosystem monitoring. However, because the variable nature of wetlands tends to hamper monitoring change analyses, the potential for misinterpretation increases. The Kalman filter (KF) or extended Kalman filter (EKF), which uses recursive processing based on the former information, can be applied to time-series remote sensing imagery. In the experiment, a periodic triangle function of two modulated parameters is treated as the system model, and Normalized Difference Vegetation Index (NDVI) time-series data are used for the measurement model in the correction processes of the state estimation. A decision metric is computed from the mean and amplitude sequence, which results from the state estimation filter. Consequently, an optimal threshold is calculated using a minimum error thresholding algorithm based on a pre-labelled sample. NDVI time-series data from Poyang Lake, China–derived from 250-m Moderate Resolution Imaging Spectroradiometer satellite data obtained from January 2009 to December 2013–are applied to monitor the dynamics of inundation changes. The results show that the EKF achieves satisfactory results, with 85.52% accuracy in the year 2009, while the KF has an accuracy of 84.16% during that same time.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A Support Vector Machine-Based Particle Filter Method for Improved Flooding Classification
    (2015-09-01)
    Insom, Patcharin
    ;
    Cao, Chunxiang
    ;
    Boonsrimuang, Pisit
    ;
    Liu, Di
    ;
    Saokarn, Apitach
    Support vector machines (SVMs) have been applied to land cover classification, and a number of studies have demonstrated their ability to increase classification accuracy. The high correlation between the data set and SVM training model parameters indicates the high performance of the classification model. To improve the correlation, research has focused on the integration of SVMs and other algorithms for data set selection and SVM training model parameter estimation. This letter proposes a novel method, based on a particle filter (PF), of estimating SVM training model parameters according to an observation system. By treating the SVM training function as the observation system of the PF, the new method automatically updates the SVM training model parameters to values that are more appropriate for the data set and can provide a better classification model than can the original model, wherein the parameters are set by trial and error. Various experiments were conducted using Radarsat-2 synthetic aperture radar data from the 2011 Thailand flood. The proposed method provides superior performance and a more accurate analysis compared with the standard SVM.