• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.111-126
• /
• 2022

Land use and land cover (LULC) mapping is an important factor in geospatial analysis. Although highly precise ground-based LULC monitoring is possible, it is time consuming and costly. Conversely, because the synthetic aperture radar (SAR) sensor is an all-weather sensor with high resolution, it could replace field-based LULC monitoring systems with low cost and less time requirement. Thus, LULC is one of the major areas in SAR applications. We developed a LULC model using only KOMPSAT-5 single co-polarized data and digital elevation model (DEM) data. Twelve HH-polarized images and 18 VV-polarized images were collected, and two HH-polarized images and four VV-polarized images were selected for the model testing. To train the LULC model, we applied the conditional generative adversarial network (cGAN) method. We used U-Net combined with the residual unit (ResUNet) model to generate the cGAN method. When analyzing the training history at 1732 epochs, the ResUNet model showed a maximum overall accuracy (OA) of 93.89 and a Kappa coefficient of 0.91. The model exhibited high performance in the test datasets with an OA greater than 90. The model accurately distinguished water body areas and showed lower accuracy in wetlands than in the other LULC types. The effect of the DEM on the accuracy of LULC was analyzed. When assessing the accuracy with respect to the incidence angle, owing to the radar shadow caused by the side-looking system of the SAR sensor, the OA tended to decrease as the incidence angle increased. This study is the first to use only KOMPSAT-5 single co-polarized data and deep learning methods to demonstrate the possibility of high-performance LULC monitoring. This study contributes to Earth surface monitoring and the development of deep learning approaches using the KOMPSAT-5 data.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.9-18
• /
• 2024

Small streams, despite their rich ecosystems, face challenges in vegetation assessment due to the limitations of traditional, time-consuming methods. This study presents a groundbreaking approach, combining unmanned aerial vehicles(UAVs), convolutional neural networks(CNNs), and the vegetation differential vegetation index (VDVI), to revolutionize both assessment and management of stream vegetation. Focusing on Idong Stream in South Korea (2.7 km long, 2.34 km² basin area)with eight diverse revetment methods, we leveraged high-resolution RGB images captured by UAVs across five dates (July-December). These images trained a ResNeXt101 CNN model, achieving an impressive 89% accuracy in classifying vegetation cover(soil,water, and vegetation). This enabled detailed spatial and temporal analysis of vegetation distribution. Further, VDVI calculations on classified vegetation areas allowed assessment of vegetation vitality. Our key findings showcase the power of this approach:(a) TheCNN model generated highly accurate cover maps, facilitating precise monitoring of vegetation changes overtime and space. (b) August displayed the highest average VDVI(0.24), indicating peak vegetation growth crucial for stabilizing streambanks and resisting flow. (c) Different revetment methods impacted vegetation vitality. Fieldstone sections exhibited initial high vitality followed by decline due to leaf browning. Block-type sections and the control group showed a gradual decline after peak growth. Interestingly, the "H environment block" exhibited minimal change, suggesting potential benefits for specific ecological functions.(d) Despite initial differences, all sections converged in vegetation distribution trends after 15 years due to the influence of surrounding vegetation. This study demonstrates the immense potential of UAV-based remote sensing and CNNs for revolutionizing small-stream vegetation assessment and management. By providing high-resolution, temporally detailed data, this approach offers distinct advantages over traditional methods, ultimately benefiting both the environment and surrounding communities through informed decision-making for improved stream health and ecological conservation.

• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3943-3948
• /
• 2022

Single-photon emission computed tomography is one of the reliable pin-by-pin verification techniques for spent-fuel assemblies. One of the challenges with this technique is to increase the total fuel assembly verification speed while maintaining high verification accuracy. The aim of the present study, therefore, was to develop an artificial intelligence (AI) algorithm-based tomographic image analysis technique for partial-defect verification of fuel assemblies. With the Monte Carlo (MC) simulation technique, a tomographic image dataset consisting of 511 fuel-rod patterns of a 3 × 3 fuel assembly was generated, and with these images, the VGG16, GoogLeNet, and ResNet models were trained. According to an evaluation of these models for different training dataset sizes, the ResNet model showed 100% pattern estimation accuracy. And, based on the different tomographic image qualities, all of the models showed almost 100% pattern estimation accuracy, even for low-quality images with unrecognizable fuel patterns. This study verified that an AI model can be effectively employed for accurate and fast partial-defect verification of fuel assemblies.

• Journal of Intelligence and Information Systems
• /
• v.15 no.3
• /
• pp.53-65
• /
• 2009

The part-of-speech determination is necessary for resolving the part-of-speech ambiguity in English-Korean machine translation. The part-of-speech ambiguity causes high parsing complexity and makes the accurate translation difficult. In order to solve the problem, the resolution of the part-of-speech ambiguity must be performed after the lexical analysis and before the parsing. This paper proposes the CatAmRes model, which resolves the part-of-speech ambiguity, and compares the performance with that of other part-of-speech tagging methods. CatAmRes model determines the part-of-speech using the probability distribution from Bayesian network training and the statistical information, which are based on the Penn Treebank corpus. The proposed CatAmRes model consists of Calculator and POSDeterminer. Calculator calculates the degree of appropriateness of the partof-speech, and POSDeterminer determines the part-of-speech of the word based on the calculated values. In the experiment, we measure the performance using sentences from WSJ, Brown, IBM corpus.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.1-8
• /
• 2018

Recently, the convolutional neural network shows high performance in many computer vision tasks. However, convolutional neural networks require enormous amount of operation, so it is difficult to adopt them in the embedded environments. To solve this problem, many studies are performed on the ASIC or FPGA implementation, where an efficient representation method is required. The fixed-point representation is adequate for the ASIC or FPGA implementation but causes a performance degradation. This paper proposes a separate optimization of representations for the convolutional layers and the batch normalization layers. With the proposed method, the required bit width for the convolutional layers is reduced from 16 bits to 10 bits for the ResNet-50 neural network. Since the computation amount of the convolutional layers occupies the most of the entire computation, the bit width reduction in the convolutional layers enables the efficient implementation of the convolutional neural networks.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.219-219
• /
• 2015

Hwacheon Reservoir is one of the reservoirs, which are located on the North Han River in South Korea. Construction of this reservoir was started in 1939 and completed in 1944. At the upstream of this reservoir there are Peace Reservoir, which is located in South Korea and Imnam Reservoir, which is located in North Korea. After construction of Imnam Reservoir, inflow regularity of Hwacheon Reservoir was changed and inflow of Hwacheon Reservoir also, was decreased. Peace Reservoir is used to decrease flood and damage at downstream due to unexpected release from Imnam Reservoir. This reservoir also, has a special role to regulate inflow of Hwacheon Reservoir. Hwacheon Reservoir has an important role for hydropower generation and flood control. Capacity and maximum discharge capacity of Hwacheon Reservoir are 1018 million $m^3$ and $9500m^3/s$, respectively. This reservoir has four generators to produce power and it is one of the important reservoirs for hydropower generation in South Korea. Due to the important role of this reservoir in generating power, maximization of hydropower generation of this reservoir is important and necessary. For this purpose, HEC-ResPRM model was applied in this study. HEC-ResPRM is a useful and applicable model to operate reservoirs and it gives optimal value for release to maximize power by minimizing penalty functions. In this study, after running the model, amount of release was optimized and hydropower generation was maximized by allocating more water for hydropower release instead of spillway release. Also, the model increased release in dry period from October to June to prevent high amount of release in flood season from July to September.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.44-49
• /
• 2021

Recently, due to COVID-19, studies have been popularly worked to apply neural network to mask wearing automatic detection system. For applying neural networks, the 1-stage detection or 2-stage detection methods are used, and if data are not sufficiently collected, the pretrained neural network models are studied by applying fine-tuning techniques. In this paper, the system is consisted of 2-stage detection method that contain MTCNN model for face recognition and ResNet model for mask detection. The mask detector was experimented by applying five ResNet models to improve accuracy and fps in various environments. Training data used 17,217 images that collected using web crawler, and for inference, we used 1,913 images and two one-minute videos respectively. The experiment showed a high accuracy of 96.39% for images and 92.98% for video, and the speed of inference for video was 10.78fps.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2022

Non-small cell lung cancer (NSCLC) accounts for a high proportion of 85% among all lung cancer and has a significantly higher mortality rate (22.7%) compared to other cancers. Therefore, it is very important to predict the prognosis after surgery in patients with non-small cell lung cancer. In this study, the types of preoperative chest CT image patches for non-small cell lung cancer patients with tumor as a region of interest are diversified into five types according to tumor-related information, and performance of single classifier model, ensemble classifier model with soft-voting method, and ensemble classifier model using 3 input channels for combination of three different patches using pre-trained ResNet and EfficientNet CNN networks are analyzed through misclassification cases and Grad-CAM visualization. As a result of the experiment, the ResNet152 single model and the EfficientNet-b7 single model trained on the peritumoral patch showed accuracy of 87.93% and 81.03%, respectively. In addition, ResNet152 ensemble model using the image, peritumoral, and shape-focused intratumoral patches which were placed in each input channels showed stable performance with an accuracy of 87.93%. Also, EfficientNet-b7 ensemble classifier model with soft-voting method using the image and peritumoral patches showed accuracy of 84.48%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.399-401
• /
• 2022

A definitive diagnosis to classify the breast malignancy status may be achieved by microscopic analysis using surgical open biopsy. However, this procedure requires experts in the specializing of histopathological image analysis directing to time-consuming and high cost. To overcome these issues, deep learning is considered practically efficient to categorize breast cancer into benign and malignant from histopathological images in order to assist pathologists. This study presents a pre-trained convolutional neural network model architecture with a 100% fine-tuning scheme and Adagrad optimizer to classify the breast cancer histopathological images into benign and malignant using a 40× magnification BreaKHis dataset. The pre-trained architecture was constructed using the InceptionResNetV2 model to generate a modified InceptionResNetV2 by substituting the last layer with dense and dropout layers. The results by demonstrating training loss of 0.25%, training accuracy of 99.96%, validation loss of 3.10%, validation accuracy of 99.41%, test loss of 8.46%, and test accuracy of 98.75% indicated that the modified InceptionResNetV2 model is reliable to predict the breast malignancy type from histopathological images. Future works are necessary to focus on k-fold cross-validation, optimizer, model, hyperparameter optimization, and classification on 100×, 200×, and 400× magnification.

• Imaging Science in Dentistry
• /
• v.43 no.3
• /
• pp.171-177
• /
• 2013

Purpose: The purpose of this study was to compare the efficacy of two imaging modes in a cone beam computed tomography (CBCT) system in detecting root fracture in endodontically-treated teeth with fiber posts or screw posts by selecting two fields of view. Materials and Methods: In this study, 78 endodontically-treated single canal premolars were included. A post space was created in all of them. Then the teeth were randomly set in one of 6 artificial dental arches. In 39 of the 78 teeth set in the 6 dental arches, a root fracture was intentionally created. Next, a fiber post and a screw post were cemented into 26 teeth having equal the root fractures. High resolution (HiRes) and standard zoom images were provided by a CBCT device. Upon considering the reconstructed images, two observers in agreement with each other confirmed the presence or absence of root fracture. A McNemar test was used for comparing the results of the two modes. Results: The frequency of making a correct diagnosis using the HiRes zoom imaging mode was 71.8% and in standard zoom was 59%. The overall sensitivity and specificity in diagnosing root fracture in the HiRes mode were 71.79% and 46.15% and in the standard zoom modes were 58.97% and 33.33%, respectively. Conclusion: There were no significant differences between the diagnostic values of the two imaging modes used in the diagnosis of root fracture or in the presence of root canal restorations. In both modes, the most true-positive results were reported in the post space group.