• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.1
• /
• pp.49-59
• /
• 2019

Generative adversarial networks(GANs) have received great attention in the machine learning field for their capacity to model high-dimensional and complex data distribution implicitly and generate new data samples from the model distribution. This paper investigates the model training methodology, architecture, and various applications of generative adversarial networks. Experimental evaluation is also conducted for generating synthetic image dataset for defense using two types of GANs. The first one is for military image generation utilizing the deep convolutional generative adversarial networks(DCGAN). The other is for visible-to-infrared image translation utilizing the cycle-consistent generative adversarial networks(CycleGAN). Each model can yield a great diversity of high-fidelity synthetic images compared to training ones. This result opens up the possibility of using inexpensive synthetic images for training neural networks while avoiding the enormous expense of collecting large amounts of hand-annotated real dataset.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.57-63
• /
• 2021

Spoken language understanding, which aims to understand utterance as naturally as human would, are mostly focused on English language. In this paper, we construct a Korean language dataset for spoken language understanding, which is based on a conversational corpus between reservation system and its user. The domain of conversation is limited to restaurant reservation. There are 7 types of slot tags and 5 types of intent tags in 6857 sentences. When a model proposed in English-based research is trained with our dataset, intent classification accuracy decreased a little, while slot filling F1 score decreased significantly.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.293-298
• /
• 2023

The military is facing a continuous decrease in personnel, and in order to cope with potential accidents and challenges in operations, efforts are being made to reduce the direct involvement of personnel by utilizing the latest technologies. Recently, the use of various sensors related to Manned-Unmanned Teaming and artificial intelligence technologies has gained attention, emphasizing the need for flexible utilization methods. In this paper, we propose four dataset construction methods that can be used for effective training of robots that can be deployed in military operations, utilizing not only RGB image data but also data acquired from IR image sensors. Since there is no publicly available dataset that combines RGB and IR image data, we directly acquired the dataset within buildings. The input values were constructed by combining RGB and IR image sensor data, taking into account the field of view, resolution, and channel values of both sensors. We compared the proposed method with conventional RGB image data classification training using the same learning model. By employing the proposed image data fusion method, we observed improved stability in training loss and approximately 3% higher accuracy.

• Korean Journal of Radiology
• /
• v.21 no.8
• /
• pp.987-997
• /
• 2020

Objective: Measurement of the liver and spleen volumes has clinical implications. Although computed tomography (CT) volumetry is considered to be the most reliable noninvasive method for liver and spleen volume measurement, it has limited application in clinical practice due to its time-consuming segmentation process. We aimed to develop and validate a deep learning algorithm (DLA) for fully automated liver and spleen segmentation using portal venous phase CT images in various liver conditions. Materials and Methods: A DLA for liver and spleen segmentation was trained using a development dataset of portal venous CT images from 813 patients. Performance of the DLA was evaluated in two separate test datasets: dataset-1 which included 150 CT examinations in patients with various liver conditions (i.e., healthy liver, fatty liver, chronic liver disease, cirrhosis, and post-hepatectomy) and dataset-2 which included 50 pairs of CT examinations performed at ours and other institutions. The performance of the DLA was evaluated using the dice similarity score (DSS) for segmentation and Bland-Altman 95% limits of agreement (LOA) for measurement of the volumetric indices, which was compared with that of ground truth manual segmentation. Results: In test dataset-1, the DLA achieved a mean DSS of 0.973 and 0.974 for liver and spleen segmentation, respectively, with no significant difference in DSS across different liver conditions (p = 0.60 and 0.26 for the liver and spleen, respectively). For the measurement of volumetric indices, the Bland-Altman 95% LOA was -0.17 ± 3.07% for liver volume and -0.56 ± 3.78% for spleen volume. In test dataset-2, DLA performance using CT images obtained at outside institutions and our institution was comparable for liver (DSS, 0.982 vs. 0.983; p = 0.28) and spleen (DSS, 0.969 vs. 0.968; p = 0.41) segmentation. Conclusion: The DLA enabled highly accurate segmentation and volume measurement of the liver and spleen using portal venous phase CT images of patients with various liver conditions.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.18-21
• /
• 2005

The impact of the interannual climatic variability on the vegetation sensitively appears in the timing of phenological events such as green-up, mature, and senescence. Therefore, an accurate and temporally high-resolution NDVI dataset will be required for analysis on the interannual variability of the climate-vegetation relationship. We constructed a daily 8km NDVI dataset over Eurasia based on the 8km tiled data of Pathfinder A VHRR Land (PAL) Global daily product. Cloud contamination was successfully reduced by Temporal Window Operation (TWO), which is a method to find optimized upper envelop line of the NDVI seasonal change. Based on the daily NDVI time series from 1982 to 2000, an accurate (daily) interannual change of the phenological events will be analyzed.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.52 no.10
• /
• pp.571-576
• /
• 2003

XML Web Service based on internet can cause problems on transmission speed and data error. Also system analysis results simulated by several different research groups can hardly have reliability because of error data that come from improperly managed files. In order to solve this problems, algorithm sever using XML Web Service is shared on the internet so widely that various application programs based on basic analysis module with a united IO can be developed. And also XML Dataset DB is interacted with XML Web Service, which prevents propagation of error data. It causes to improve reliabilityon the load flow analysis result and solve the problems on data error or transmission speed that can possibly come from internet.

• Journal of Biomedical Engineering Research
• /
• v.41 no.1
• /
• pp.28-34
• /
• 2020

In this paper, we introduce motion artifact reduction algorithm for interleaved MRI using an advanced 3D approximation algorithm. The motion artifact framework of this paper is data corrected by post-processing with a new 3-D approximation algorithm which uses data structure for each voxel. In this study, we simulate and evaluate our algorithm using Shepp-Logan phantom and T1-MRI template for both scattered dataset and uniform dataset. We generated motion artifact using random generated motion parameters for the interleaved MRI. In simulation, we use image coregistration by SPM12 (https://www.fil.ion.ucl.ac.uk/spm/) to estimate the motion parameters. The motion artifact correction is done with using full dataset with estimated motion parameters, as well as use only one half of the full data which is the case when the half volume is corrupted by severe movement. We evaluate using numerical metrics and visualize error images.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1133-1141
• /
• 2019

Most of the previous studies for bark recognition have focused on the extraction of LBP-like statistical features. Deep learning approach was not well studied because of the difficulty of acquiring large volume of bark image dataset. To overcome the bark dataset problem, this study utilizes the MobileNet which was trained with the ImageNet dataset. This study proposes two approaches. One is to extract features by the pixel-wise convolution and classify the features with SVM. The other is to tune the weights of the MobileNet by flexibly freezing layers. The experimental results with two public bark datasets, BarkTex and Trunk12, show that the proposed methods are effective in bark recognition. Especially the results of the flexible tunning method outperform state-of-the-art methods. In addition, it can be applied to mobile devices because the MobileNet is compact compared to other deep learning models.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.1-6
• /
• 2022

Scene change detection is an important topic because of the wide and growing range of its applications. Streaming services from many providers are increasing their capacity which causes the industry growth. The method for the scene change detection is described here and compared with the State-of-the-Art methods over the Open Video Scene Detection (OVSD) - an open dataset of Creative Commons licensed videos freely available for download and use to evaluate video scene detection algorithms. The proposed method is based on scene analysis using threshold values and smooth scene changes. A comparison of the presented method was conducted in this research. The obtained results demonstrated the high efficiency of the scene cut localization method proposed by authors, because its efficiency measured in terms of precision, recall, accuracy, and F-metrics score exceeds the best previously known results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3658-3679
• /
• 2022

Classification of persons wearing and not wearing face masks in images has emerged as a new computer vision problem during the COVID-19 pandemic. In order to address this problem and scale up the research in this domain, in this paper a hybrid technique by employing ResNet-101 and multi-layer perceptron (MLP) classifier has been proposed. The proposed technique is tested and validated on a self-created face masks classification dataset and a standard dataset. On self-created dataset, the proposed technique achieved a classification accuracy of 97.3%. To embrace the proposed technique, six other state-of-the-art CNN feature extractors with six other classical machine learning classifiers have been tested and compared with the proposed technique. The proposed technique achieved better classification accuracy and 1-6% higher precision, recall, and F1 score as compared to other tested deep feature extractors and machine learning classifiers.