• Journal of Sensor Science and Technology
• /
• v.25 no.6
• /
• pp.431-434
• /
• 2016

Currently, the radial basis function network (RBFN) and various other neural networks are employed to classify gases using chemical sensors arrays, and their performance is steadily improving. In particular, the identification performance of the RBFN algorithm is being improved by optimizing parameters such as the center, width, and weight, and improved algorithms such as the radial basis function network-stochastic gradient (RBFN-SG) and radial basis function network-normalized stochastic gradient (RBFN-NSG) have been announced. In this study, we optimized the number of centers, which is one of the parameters of the RBFN-NSG algorithm, and observed the change in the identification performance. For the experiment, repeated measurement data of 8 samples were used, and the elbow method was applied to determine the optimal number of centers for each sample of input data. The experiment was carried out in two cases(the only one center per sample and the optimal number of centers obtained by elbow method), and the experimental results were compared using the mean square error (MSE). From the results of the experiments, we observed that the case having an optimal number of centers, obtained using the elbow method, showed a better identification performance than that without any optimization.

• Korean Journal of Remote Sensing
• /
• v.24 no.1
• /
• pp.65-78
• /
• 2008

This study compares the relative accuracy and consistency of four split-window land surface temperature (LST) algorithms (Becker and Li, Kerr et ai., Price, Ulivieri et al.) using 24 sets of Terra (Aqua)/Moderate Resolution Imaging Spectroradiometer (MODIS) data, observed ground grass temperature and air temperature over South Korea. The effective spectral emissivities of two thermal infrared bands have been retrieved by vegetation coverage method using the normalized difference vegetation index. The intercomparison results among the four LST algorithms show that the three algorithms (Becker-Li, Price, and Ulivieri et al.) show very similar performances. The LST estimated by the Becker and Li's algorithm is the highest, whereas that by the Kerr et al.'s algorithm is the lowest without regard to the geographic locations and seasons. The performance of four LST algorithms is significantly better during cold season (night) than warm season (day). And the LST derived from Terra/MODIS is closer to the observed LST than that of Aqua/MODIS. In general, the performances of Becker-Li and Ulivieri et al algorithms are systematically better than the others without regard to the day/night, seasons, and satellites. And the root mean square error and bias of Ulivieri et al. algorithm are consistently less than that of Becker-Li for the four seasons.

• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1266-1276
• /
• 2021

The mask parameters of a coded aperture are critical design features when optimizing the performance of a gamma-ray camera. In this paper, experiments and Monte Carlo simulations were performed to derive the minimum detectable activity (MDA) when one seeks a real-time imaging capability. First, the impact of the thickness of the modified uniformly redundant array (MURA) mask on the image quality is quantified, and the imaging of point, line, and surface radiation sources is demonstrated using both cross-correlation (CC) and maximum likelihood expectation maximization (MLEM) methods. Second, the minimum detectable activity is also derived for real-time imaging by altering the factors used in the image quality assessment, consisting of the peak-to-noise ratio (PSNR), the normalized mean square error (NMSE), the spatial resolution (full width at half maximum; FWHM), and the structural similarity (SSIM), all evaluated as a function of energy and mask thickness. Sufficiently sharp images were reconstructed when the mask thickness was approximately 2 cm for a source energy between 30 keV and 1.5 MeV and the minimum detectable activity for real-time imaging was 23.7 MBq at 1 m distance for a 1 s collection time.

• Current Optics and Photonics
• /
• v.5 no.6
• /
• pp.606-616
• /
• 2021

A photonic integrated interferometric imaging system possesses the characteristics of small-scale, low weight, low power consumption, and better image quality. It has potential application for replacing conventional large space telescopes. In this paper, the principle of photonic integrated interferometric imaging is investigated. A novel lenslet array arrangement and lenslet pairing approach are proposed, which are helpful in improving spatial frequency coverage. For the novel lenslet array arrangement, two short interference arms were evenly distributed between two adjacent long interference arms. Each lenslet in the array would be paired twice through the novel lenslet pairing approach. Moreover, the image reconstruction model for optical interferometric imaging based on compressed sensing was established. Image simulation results show that the peak signal to noise ratio (PSNR) of the reconstructed image based on compressive sensing is about 10 dB higher than that of the direct restored image. Meanwhile, the normalized mean square error (NMSE) of the direct restored image is approximately 0.38 higher than that of the reconstructed image. Structural similarity index measure (SSIM) of the reconstructed image based on compressed sensing is about 0.33 higher than that of the direct restored image. The increased spatial frequency coverage and image reconstruction approach jointly contribute to better image quality of the photonic integrated interferometric imaging system.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.9
• /
• pp.41-48
• /
• 2008

The aim of this study is to present a graphical method in order to evaluate stages in shrinkage cracking. Firstly, the distribution of crack openings is established by sorting the openings of individual cracks in the soil cracking system. Secondly, it is normalized in a range of 0 to 1 to obtain the normalized crack opening distribution. Thirdly, three S-shape curve models introduced by Brooks and Corey(1964), Fredlund and Xing(1994) and van Genuchten(1980) are chosen to fit the normalized crack opening distribution using a curve fitting method. The accuracy of fitting which is described through fitting parameters by the van Genuchten equation is much higher than that by the Brooks and Corey equation and slightly higher than that by the Fredlund and Xing equation; thus the van Genuchten model is used. Finally, the stages of shrinkage cracking are graphically evaluated by drawing three separate straight lines corresponding to three linear parts of the fitted normalized crack opening distribution. The proposed method is tested with different sample thicknesses. The measured data are fitted by the selected model with the fairly high regression coefficient and small root mean square error. The results show graphically that shrinkage cracking comprises three stages; namely, primary, secondary and residual stages. Subsequently, the ranges of evaluated crack opening for each of these stages are presented.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.673-686
• /
• 2022

Deep learning algorithms for Structural Health Monitoring (SHM) have been extracting the interest of researchers and engineers. These algorithms commonly used loss functions and evaluation indices like the mean square error (MSE) which were not originally designed for SHM problems. An updated loss function which was specifically constructed for deep-learning-based structural damage detection problems has been proposed in this study. By tuning the coefficients of the loss function, the weights for damage localization and quantification can be adapted to the real situation and the deep learning network can avoid unnecessary iterations on damage localization and focus on the damage severity identification. To prove efficiency of the proposed method, structural damage detection using convolutional neural networks (CNNs) was conducted on a truss bridge model. Results showed that the validation curve with the updated loss function converged faster than the traditional MSE. Data augmentation was conducted to improve the anti-noise ability of the proposed method. For reducing the training time, the normalized modal strain energy change (NMSEC) was extracted, and the principal component analysis (PCA) was adopted for dimension reduction. The results showed that the training time was reduced by 90% and the damage identification accuracy could also have a slight increase. Furthermore, the effect of different modes and elements on the training dataset was also analyzed. The proposed method could greatly improve the performance for structural damage detection on both the training time and detection accuracy.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.19 no.2
• /
• pp.93-101
• /
• 2015

Purpose In SPECT image, scatter count is the cause of quantitative count error and image quality degradation. Thus, a wide range of scatter correction(SC) methods have been studied and this study is to evaluate the accuracy of CT based SC(CTSC) used in SPECT/CT as the comparison with existing energy window based SC(EWSC). Materials and Methods SPECT/CT images were obtained after filling air in order to acquire a reference image without the influence of scatter count inside the Triple line insert phantom setting hot rod(74.0 MBq) in the middle and each SPECT/CT image was obtained each separately after filling water instead of air in order to derive the influence of scatter count under the same conditions. In both conditions, Astonish(iterative : 4 subset : 16) reconstruction method and CT attenuation correction were commonly applied and three types of SC methods such as non-scatter correction(NSC), EWSC, CTSC were used in images filled with image. For EWSC, 9 sub-energy windows were set additionally in addition to main(=peak) energy window(140 keV, 20%) and then, images were acquired at the same time and five types of EWSC including DPW(dual photo-peak window)10%, DEW(dual energy window)20%, TEW(triple energy window)10%, TEW5.0%, TEW2.5% were used. Under the condition without fluctuations in primary count, total count was measured by drawing volume of interest (VOI) in the images of the two conditions and then, the ratio of scatter count of total counts was calculated as percent scatter fraction(%SF) and the count error with image filled with water was evaluated with percent normalized mean-square error(%NMSE) based on the image filled with air. Results Based on the image filled with air, %SF of images filled with water to which each SC method was applied is NSC 37.44, DPW 27.41, DEW 21.84, TEW10% 19.60, TEW5% 17.02, TEW2.5% 14.68, CTSC 5.57 and the most scattering counts were removed in CTSC and %NMSE is NSC 35.80, DPW 14.28, DEW 7.81, TEW10% 5.94, TEW5% 4.21, TEW2.5% 2.96, CTSC 0.35 and the error in CTSC was found to be the lowest. Conclusion In SPECT/CT images, the application of each scatter correction method used in the experiment could improve the quantitative count error caused by the influence of scatter count. In particular, CTSC showed the lowest %NMSE(=0.35) compared to existing EWSC methods, enabling relatively accurate scatter correction.

• Korean Journal of Soil Science and Fertilizer
• /
• v.50 no.2
• /
• pp.115-126
• /
• 2017

There is an increasing concern over arsenic (As) contamination in rice. This study was conducted to develope a prediction model for As uptake by rice based on the physico-chemical properties of soil. Soil and brown rice samples were collected from 46 sites in paddy fields near three different areas of closed mines and industrial complexes. Total As concentration, soil pH, Al oxide, available phosphorus (avail-P), organic matter (OM) content, and clay content in the soil samples were determined. Also, 1.0 N HCl, 1.0 M $NH_4NO_3$, 0.01 M $Ca(NO_3)_2$, and Mehlich 3 extractable-As in the soils were measured as phytoavailable As concentration in soil. Total As concentration in brown rice samples was also determined. Relationships among As concentrations in brown rice, total As concentrations in soils, and selected soil properties were as follows: As concentration in brown rice was negatively correlated with soil pH value, where as it was positively correlated with Al oxide concentration, avail-P concentration, and OM content in soil. In addition, the concentration of As in brown rice was statistically correlated only with 1.0 N HCl-extractable As in soil. Also, using multiple stepwise regression analysis, a modelling equation was created to predict As concentration in brown rice as affected by selected soil properties including soil As concentration. Prediction of As uptake by rice was delineated by the model [As in brown rice = 0.352 + $0.00109^*$ HCl extractable As in soil + $0.00002^*$ Al oxide + $0.0097^*$ OM + $0.00061^*$ avail-P - $0.0332^*$ soil pH] ($R=0.714^{***}$). The concentrations of As in brown rice estimated by the modelling equation were statistically acceptable because normalized mean error (NME) and normalized root mean square error (NRMSE) values were -0.055 and 0.2229, respectively, when compared with measured As concentration in the plant.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_2
• /
• pp.1317-1328
• /
• 2021

This study analyzes the early satellite mission marine fog detection results from Geostationary Ocean Color Imager-II (GOCI-II). We investigate optical characteristics of the GOCI-II spectral bands for marine fog between October 2020 and March 2021 during the overlapping mission period of Geostationary Ocean Color Imager (GOCI) and GOCI-II. For Rayleigh-corrected reflection (R_rc) at 412 nm band available for the input of the GOCI-II marine fog algorithm, the inter-comparison between GOCI and GOCI-II data showed a small Root Mean Square Error (RMSE) value (0.01) with a high correlation coefficient (0.988). Another input variable, Normalized Localization Standard (NLSD), also shows a reasonable correlation (0.798) between the GOCI and GOCI-II data with a small RMSE value (0.007). We also found distinctive optical characteristics between marine fog and clouds by the GOCI-II observations, showing the narrower distribution of all bands' R_rc values centered at high values for cloud compared to marine fog. The GOCI-II marine fog detection distribution for actual cases is similar to the GOCI but more detailed due to the improved spatial resolution from 500 m to 250 m. The validation with the automated synoptic observing system (ASOS) visibility data confirms the initial reliability of the GOCI-II marine fog detection. Also, it is expected to improve the performance of the GOCI-II marine fog detection algorithm by adding sufficient samples to verify stable performance, improving the post-processing process by replacing real-time available cloud input data and reducing false alarm by adding aerosol information.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.3
• /
• pp.223-235
• /
• 2020

In this study, we propose an approach for calibrating the elevation of a DEM (Digital Elevation Model), one of the key data in realizing unmanned aerial vehicle image-based precision agriculture. First of all, radiometric correction is performed on the orthophoto, and then ExG (Excess Green) is generated. The non-vegetation area is extracted based on the threshold value estimated by applying the Otsu method to ExG. Subsequently, the elevation of the DEM corresponding to the location of the non-vegetation area is extracted as EIFs (Elevation Invariant Features), which is data for elevation correction. The normalized Z-score is estimated based on the difference between the extracted EIFs to eliminate the outliers. Then, by constructing a linear regression model and correcting the elevation of the DEM, high-quality DEM is produced without GCPs (Ground Control Points). To verify the proposed method using a total of 10 DEMs, the maximum/minimum value, average/standard deviation before and after elevation correction were compared and analyzed. In addition, as a result of estimating the RMSE (Root Mean Square Error) by selecting the checkpoints, an average RMSE was derivsed as 0.35m. Comprehensively, it was confirmed that a high-quality DEM could be produced without GCPs.