• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.26-26
• /
• 2023

General circulation models (GCMs) are widely used in hydrological prediction, however their coarse grids make them unsuitable for regional analysis, therefore a downscaling method is required to utilize them in hydrological assessment. As one of the downscaling methods, convolutional neural network (CNN)-based downscaling has been proposed in recent years. The aim of this study is to generate the process of dynamic downscaling using CNNs by applying GCM output as input and RCM output as label data output. Prediction accuracy is compared between different input datasets, and model structures. Several input datasets with key atmospheric variables such as precipitation, temperature, and humidity were tested with two different formats; one is two-dimensional data and the other one is three-dimensional data. And in the model structure, the hyperparameters were tested to check the effect on model accuracy. The results of the experiments on the input dataset showed that the accuracy was higher for the input dataset without precipitation than with precipitation. The results of the experiments on the model structure showed that substantially increasing the number of convolutions resulted in higher accuracy, however increasing the size of the receptive field did not necessarily lead to higher accuracy. Though further investigation is required for the application, this paper can contribute to the development of efficient downscaling method with CNNs.

• Food Science and Preservation
• /
• v.30 no.2
• /
• pp.224-234
• /
• 2023

We analyzed the major quality characteristics of red pepper powders from various regions and predicted these characteristics nondestructively using shortwave infrared hyperspectral imaging (HSI) technology. We conducted partial least squares regression analysis on 70% (n=71) of the acquired hyperspectral data of the red pepper powders to examine the major quality characteristics. R_c² values of ≥0.8 were obtained for the ASTA color value (0.9263) and capsaicinoid content (0.8310). The developed quality prediction model was validated using the remaining 30% (n=35) of the hyperspectral data; the highest accuracy was achieved for the ASTA color value (R_p²=0.8488), and similar validity levels were achieved for the capsaicinoid and moisture contents. To increase the accuracy of the quality prediction model, we conducted spectrum preprocessing using SNV, MSC, SG-1, and SG-2, and the model's accuracy was verified. The results indicated that the accuracy of the model was most significantly improved by the MSC method, and the prediction accuracy for the ASTA color value was the highest for all the spectrum preprocessing methods. Our findings suggest that the quality characteristics of red pepper powders, even powders that do not conform to specific variables such as particle size and moisture content, can be predicted via HSI.

• Journal of Forest and Environmental Science
• /
• v.40 no.1
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• Science of Emotion and Sensibility
• /
• v.16 no.3
• /
• pp.409-416
• /
• 2013

Attention is one of important cognitive functions in human affecting on the selectional concentration of relevant events and ignorance of irrelevant events. The discrimination of attentional and inattentional status is the first step to manage human's attentional capability using computer assisted device. In this paper, we newly combine the non-linear recurrence pattern analysis and spectrum analysis to effectively extract features(total number of 13) from the electroencephalographic signal used in the input to classifiers. The performance of diverse types of attention-inattention classifiers, including supporting vector machine, back-propagation algorithm, linear discrimination, gradient decent, and logistic regression classifiers were evaluated. Among them, the support vector machine classifier shows the best performance with the classification accuracy of 81 %. The use of spectral band feature set alone(accuracy of 76 %) shows better performance than that of non-linear recurrence pattern feature set alone(accuracy of 67 %). The support vector machine classifier with hybrid combination of non-linear and spectral analysis can be used in later designing attention-related devices.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1797-1802
• /
• 2005

In this study, we were developed an accuracy of the proposed two dimensional statical inclinometer what used a position sensitive detector(PSD) by an error analysis. The inclinometer consists of a laser source, a mass, an optic-fiber, and a PSD. The gravity direction on a base platform of the inclinometer is changed by an unknown inclination angle. And a laser spot is moved from the origin to another position of a PSD following a variation of an optical path by the gravity. These processes enable the inclinometer to estimate the inclination angle from distance information of the moving spot. A design methodology on the basis of a sensitivity analysis was applied to improve the measurement performance such as a full measuring range and a resolution. But it still has error factors, so we analyze the uncertainty of the inclinometer to evaluate the systematic errors from alignments, assembly error and so on. The experimental performance evaluation about the design objectives as a measuring range and a resolution was performed. And the validity and the feasibility of the design process were certified by an experimental process. Systematic errors eliminated to improve the accuracy of the inclinometer by the corrected measuring model from the calibration process between the inclination angle and the PSD position instead of the nominal measuring model. The ANOVA(analysis of variance) confirmed the effect of eliminating the systematic errors in the inclinometer. From these methodologies, the proposed inclinometer was able to measure with a high resolution(35.14sec) and a wide range(from $-15^{\circ}\;to\;15^{\circ}$

• International Journal of Highway Engineering
• /
• v.16 no.5
• /
• pp.99-108
• /
• 2014

PURPOSES : The travel times of expressway buses have been estimated using the travel time data between entrance tollgates and exit tollgates, which are produced by the Toll Collections System (TCS). However, the travel time data from TCS has a few critical problems. For example, the travel time data include the travel times of trucks as well as those of buses. Therefore, the travel time estimation of expressway buses using TCS data may be implicitly and explicitly incorrect. The goal of this study is to improve the accuracy of the expressway bus travel time estimation using DSRC-based travel time by identifying the appropriate analysis period of input data. METHODS : All expressway buses are equipped with the Hi-Pass transponders so that the travel times of only expressway buses can be extracted now using DSRC. Thus, this study analyzed the operational characteristics as well as travel time patterns of the expressway buses operating between Seoul and Dajeon. And then, this study determined the most appropriate analysis period of input data for the expressway bus travel time estimation model in order to improve the accuracy of the model. RESULTS : As a result of feasibility analysis according to the analysis period, overall MAPE values were found to be similar. However, the MAPE values of the cases using similar volume patterns outperformed other cases. CONCLUSIONS : The best input period was that of the case which uses the travel time pattern of the days whose total expressway traffic volumes are similar to that of one day before the day during which the travel times of expressway buses must be estimated.

• Journal of Astronomy and Space Sciences
• /
• v.25 no.4
• /
• pp.445-458
• /
• 2008

Image chain analysis of synthetic aperture radar (SAR) satellite is one of the primary activities for satellite design because SAR image quality depends on spacecraft bus performance as well as SAR payload. Especially, satellite pointing and stability error make worst effect on the original SAR image quality which is implemented by SAR payload design. In this research, Image chain analysis S/W was developed in order to analyze the SAR image quality degradation due to satellite pointing and stability error. This S/W consists of orbit model, attitude control model, SAR payload model, clutter model, and SAR processor. SAR raw data, which includes total 25 point targets in the scene of $5km{\times}5km$ swath width, was generated and then processed for analysis. High resolution mode (spotlight), of which resolution is 1m, was applied. The results of image chain analysis show that radiometric accuracy is the most degraded due to the pointing error. Therefore, the successful design of attitude control subsystem in spacecraft bus for enhancing the pointing accuracy is most important for image quality.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.40 no.8
• /
• pp.695-702
• /
• 2012

In this study, Multi-fidelity analysis is performed to improve the accuracy of analysis result during conceptual design stage. Multidisciplinary Design Optimization(MDO) method is also considered to satisfy the total system requirements. Low-fidelity analysis codes which are based on empirical equations are developed and validated for analyzing the Unmanned Aerial Vehicle(UAV) which have unconventional configurations. Analysis codes consist of initial sizing, aerodynamics, propulsion, mission, weight, performance, and stability modules. Design synthesis program which is composed of those modules is developed. To improve the accuracy of the design method for UAV, Vortex Lattice Method is used for the strategy of MFA. Multi-Disciplinary Feasible(MDF) method is used for MDO technique. To demonstrate the validity of presented method, the optimization results of both methods are compared. According to those results, the presented method is demonstrated to be applicable to improve the accuracy of the analyses during conceptual design stage.

• Journal of Korean Society for Geospatial Information Science
• /
• v.11 no.2 s.25
• /
• pp.47-52
• /
• 2003

Change detection and analysis is a powerful application of remote sensing, in that the spectral resolution of multi-band sensors can be used to advantage in monitoring both significant and subtle land cover changes over time. In this study, the LANDSAT TM data was used to detect the change areas affected by flood from a heavy rainfall. The study area is the Nakdong River located in the Korea peninsular. Among the several change detection techniques, change vector analysis(CVA), principle component analysis(PCA) and image difference approach are utilized in this paper. CVA uses any number of spectral bands from multi-date satellite data to produce change image that yield information of the magnitude and direction of differences pixel values. And accuracy assessment was carried out with a change image produced from three techniques. In result, CVA was found to be the most accurate for detecting areas affected by flood. CVA with the overall accuracy and Kappa coefficient of 97.27 percent and 94.45 percent, respectively.

• The Journal of Korean Academy of Prosthodontics
• /
• v.57 no.2
• /
• pp.102-109
• /
• 2019

Purpose: The purpose of this study was to evaluate the accuracy of three types of intraoral scanners and the accuracy of the single abutment and bridge abutment model. Materials and methods: In this study, a single abutment, and a bridge abutment with missing first molar was fabricated and set as the reference model. The reference model was scanned with an industrial three-dimensional scanner and set as reference scan data. The reference model was scanned five times using the three intraoral scanners (CS3600, CS3500, and EZIS PO). This was set as the evaluation scan data. In the three-dimensional analysis (Geomagic control X), the divided abutment region was selected and analyzed to verify the scan accuracy of the abutment. Statistical analysis was performed using SPSS software (${\alpha}=.05$). The accuracy of intraoral scanners was compared using the Kruskal-Wallis test and post-test was performed using the Pairwise test. The accuracy difference between the single abutment model and the bridge abutment model was analyzed by the Mann-Whitney U test. Results: The accuracy according to the intraoral scanner was significantly different (P < .05). The trueness of the single abutment model and the bridge abutment model showed a statistically significant difference and showed better trueness in the single abutment (P < .05). There was no significant difference in the precision (P = .616). Conclusion: As a result of comparing the accuracy of single and bridge abutments, the error of abutment scan increased with increasing scan area, and the accuracy of bridge abutment model was clinically acceptable in three types of intraoral scanners.