• Korean Journal of Remote Sensing
• /
• v.39 no.6_2
• /
• pp.1577-1589
• /
• 2023

Recently, the necessity of predicting changes for monitoring ocean is widely recognized. In this study, we performed a time series prediction of remote-sensing reflectance (Rrs), which can indicate changes in the ocean, using Geostationary Ocean Color Imager (GOCI) data. Using GOCI-I data, we trained a multi-scale Convolutional Long-Short-Term-Memory (ConvLSTM) which is proposed in this study. Validation was conducted using GOCI-II data acquired at different periods from GOCI-I. We compared model performance with the existing ConvLSTM models. The results showed that the proposed model, which considers both spatial and temporal features, outperformed other models in predicting temporal trends of Rrs. We checked the temporal trends of Rrs learned by the model through long-term prediction results. Consequently, we anticipate that it would be available in periodic change detection.

• Journal of Korea Water Resources Association
• /
• v.56 no.2
• /
• pp.75-89
• /
• 2023

As the Mekong River basin is a nationally shared river, it is difficult to collect precipitation data, and the quantitative and qualitative quality of the data sets differs from country to country, which may increase the uncertainty of hydrological analysis results. Recently, with the development of remote sensing technology, it has become easier to obtain grid-based precipitation products(GPPs), and various hydrological analysis studies have been conducted in unmeasured or large watersheds using GPPs. In this study, rainfall-runoff simulation in the Mekong River basin was conducted using the SWAT model, which is a quasi-distribution model with three satellite GPPs (TRMM, GSMaP, PERSIANN-CDR) and two GPPs (APHRODITE, GPCC). Four water level stations, Luang Prabang, Pakse, Stung Treng, and Kratie, which are major outlets of the main Mekong River, were selected, and the parameters of the SWAT model were calibrated using APHRODITE as an observation value for the period from 2001 to 2011 and runoff simulations were verified for the period form 2012 to 2013. In addition, using the ConvAE, a convolutional neural network model, spatio-temporal correction of original satellite precipitation products was performed, and rainfall-runoff performances were compared before and after correction of satellite precipitation products. The original satellite precipitation products and GPCC showed a quantitatively under- or over-estimated or spatially very different pattern compared to APHPRODITE, whereas, in the case of satellite precipitation prodcuts corrected using ConvAE, spatial correlation was dramatically improved. In the case of runoff simulation, the runoff simulation results using the satellite precipitation products corrected by ConvAE for all the outlets have significantly improved accuracy than the runoff results using original satellite precipitation products. Therefore, the bias correction technique using the ConvAE technique presented in this study can be applied in various hydrological analysis for large watersheds where rain guage network is not dense.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2782-2804
• /
• 2024

The integration of artificial intelligence technology with medicine has rapidly evolved, with increasing demands for quality of life. However, falls remain a significant risk leading to severe injuries and fatalities, especially among the elderly. Therefore, the development and application of computer vision-based fall detection technologies have become increasingly important. In this paper, firstly, the keypoint detection algorithm ViTPose++ is used to obtain the coordinates of human body keypoints from the camera images. Human skeletal feature maps are generated from this keypoint coordinate information. Meanwhile, human dense feature maps are produced based on the DensePose algorithm. Then, these two types of feature maps are confused as dual-channel inputs for the model. The convolutional gated recurrent unit is introduced to extract the frame-to-frame relevance in the process of falling. To further integrate features across three dimensions (spatio-temporal-channel), a dual-channel fall detection algorithm based on video streams is proposed by combining the Convolutional Block Attention Module (CBAM) with the ConvGRU. Finally, experiments on the public UR Fall Detection Dataset demonstrate that the improved ConvGRU-CBAM achieves an F1 score of 92.86% and an AUC of 95.34%.

• The Korean Journal of Physiology and Pharmacology
• /
• v.20 no.5
• /
• pp.507-514
• /
• 2016

Although 3D-complex fractionated atrial electrogram (CFAE) mapping is useful in radiofrequency catheter ablation for persistent atrial fibrillation (AF), the directions and configuration of the bipolar electrodes may affect the electrogram. This study aimed to compare the spatial reproducibility of CFAE by changing the catheter orientations and electrode distance in an in -silico left atrium (LA). We conducted this study by importing the heart CT image of a patient with AF into a 3D-homogeneous human LA model. Electrogram morphology, CFAE-cycle lengths (CLs) were compared for 16 different orientations of a virtual bipolar conventional catheter (conv-cath: size 3.5 mm, inter-electrode distance 4.75 mm). Additionally, the spatial correlations of CFAE-CLs and the percentage of consistent sites with CFAE-CL<120 ms were analyzed. The results from the conv-cath were compared with that obtained using a mini catheter (mini-cath: size 1 mm, inter-electrode distance 2.5 mm). Depending on the catheter orientation, the electrogram morphology and CFAE-CLs varied (conv-cath: $11.5{\pm}0.7%$ variation, mini-cath: $7.1{\pm}1.2%$ variation), however the mini-cath produced less variation of CFAE-CL than conv-cath (p<0.001). There were moderate spatial correlations among CFAE-CL measured at 16 orientations (conv-cath: $r=0.3055{\pm}0.2194$ vs. mini-cath: $0.6074{\pm}0.0733$, p<0.001). Additionally, the ratio of consistent CFAE sites was higher for mini catheter than conventional one ($38.3{\pm}4.6%$ vs. $22.3{\pm}1.4%$, p<0.05). Electrograms and CFAE distribution are affected by catheter orientation and electrode configuration in the in-silico LA model. However, there was moderate spatial consistency of CFAE areas, and narrowly spaced bipolar catheters were less influenced by catheter direction than conventional catheters.

• Proceedings of the KIEE Conference
• /
• 2001.10a
• /
• pp.122-124
• /
• 2001

In this paper, the influence of electrical parameters such as the turn-on and turn-off angle on the torque and force characteristics is investigated for the reduction of the torque ripple which is main source of vibration and noise in switched reluctance motor (SRM). The four different types of the turn-on angle are set to the section of rising inductance profile respectively. The optimum turn-on angle is proposed for the acquisition of the flat current shape minimizing the torque ripple. 2D finite element method (FEM) considering the iron saturation and the actual switching circuit of the SRM drive is applied for the dynamic analysis. The simulation results of phase current and torque are also compared to the experimental results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.449-452
• /
• 2023

The rapid development of the Internet has led to a significant increase in multimedia content in social networks. How to better analyze and improve video classification models has become an important task. Deep learning models have typical "black box" characteristics. The model requires explainable analysis. This article uses two classification models: ConvLSTM and VGG16+LSTM models. And combined with the explainable method of LRP, generate visualized explainable results. Finally, based on the experimental results, the accuracy of the classification model is: ConvLSTM: 75.94%, VGG16+LSTM: 92.50%. We conducted explainable analysis on the VGG16+LSTM model combined with the LRP method. We found VGG16+LSTM classification model tends to use the frames biased towards the latter half of the video and the last frame as the basis for classification.

• The korean journal of orthodontics
• /
• v.48 no.5
• /
• pp.292-303
• /
• 2018

Objective: Biplanar imaging systems allow for simultaneous acquisition of lateral and frontal cephalograms. The purpose of this study was to compare measurements recorded on three-dimensional (3D) cephalograms constructed from two-dimensional conventional radiographs and biplanar radiographs generated using a new biplanar imaging system with those recorded on cone-beam computed tomography (CBCT)-generated cephalograms in order to evaluate the accuracy of the 3D cephalograms generated using the biplanar imaging system. Methods: Three sets of lateral and frontal radiographs of 15 human dry skulls with prominent facial asymmetry were obtained using conventional radiography, the biplanar imaging system, and CBCT. To minimize errors in the construction of 3D cephalograms, fiducial markers were attached to anatomical landmarks prior to the acquisition of radiographs. Using the 3D $Ceph^{TM}$ program, 3D cephalograms were constructed from the images obtained using the biplanar imaging system (3D $ceph_{biplanar}$), conventional radiography (3D $ceph_{conv}$), and CBCT (3D $ceph_{cbct}$). A total of 34 measurements were obtained compared among the three image sets using paired t-tests and Bland-Altman plotting. Results: There were no statistically significant differences between the 3D $ceph_{biplanar}$ and 3D $ceph_{cbct}$ measurements. In addition, with the exception of one measurement, there were no significant differences between the 3D $ceph_{cbct}$ and 3D $ceph_{conv}$ measurements. However, the values obtained from 3D $ceph_{conv}$ showed larger deviations than those obtained from 3D $ceph_{biplanar}$. Conclusions: The results of this study suggest that the new biplanar imaging system enables the construction of accurate 3D cephalograms and could be a useful alternative to conventional radiography.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.134-142
• /
• 2019

As the development of internet of energy (IoE) technologies and spread of various electronic devices have diversified patterns of energy consumption, the reliability of demand prediction has decreased, causing problems in optimization of power generation and stabilization of power supply. In this study, we propose a deep learning method, 1-Dimention-Convolution and Bidirectional Long Short-Term Memory (1D-ConvBLSTM), that combines a convolution neural network (CNN) and a Bidirectional Long Short-Term Memory(BLSTM) for highly reliable demand forecasting by effectively extracting the energy consumption pattern. In experimental results, the demand is predicted with the proposed deep learning method for various number of learning iterations and feature maps, and it is verified that the test data is predicted with a small number of iterations.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.35-42
• /
• 2021

In this paper, we propose a deep learning-based person re-identification method using a three-dimensional RGB-Depth Xtion2 camera considering joint coordinates and dynamic features(velocity, acceleration). The main idea of the proposed identification methodology is to easily extract gait data such as joint coordinates, dynamic features with an RGB-D camera and automatically identify gait patterns through a self-designed one-dimensional convolutional neural network classifier(1D-ConvNet). The accuracy was measured based on the F1 Score, and the influence was measured by comparing the accuracy with the classifier model (JC) that did not consider dynamic characteristics. As a result, our proposed classifier model in the case of considering the dynamic characteristics(JCSpeed) showed about 8% higher F1-Score than JC.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.85-92
• /
• 2022

In this paper, we propose a technique that can express low-resolution hair and fur simulations in high-resolution without noise using ConvNet and geometric images of strands in the form of lines. Pairs between low-resolution and high-resolution data can be obtained through physics-based simulation, and a low-resolution-high-resolution data pair is established using the obtained data. The data used for training is used by converting the position of the hair strands into a geometric image. The hair and fur network proposed in this paper is used for an image synthesizer that upscales a low-resolution image to a high-resolution image. If the high-resolution geometry image obtained as a result of the test is converted back to high-resolution hair, it is possible to express the elastic movement of hair, which is difficult to express with a single mapping function. As for the performance of the synthesis result, it showed faster performance than the traditional physics-based simulation, and it can be easily executed without knowing complex numerical analysis.