• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.11-19
• /
• 2009

A RAM-based Neural Net(RBNN) which has multi-discriminators is more effective than RBNN with a discriminator. Experience Sensitive Cumulative Neural Network and 3-D Neuro System(3DNS) that accumulate the features point improved the performance of BNN, which were enabled to train additional and repeated patterns and extract a generalized pattern. In recognition process of Neural Net with multi-discriminator, the selection of class was decided by the value of MRD which calculates the accumulated sum of each class. But they had a saturation problem of its memory cells caused by learning volume increment. Therefore, the decision of MRD has a low performance because recognition rate is decreased by saturation. In this paper, we propose the method which improve the MRD ability. The method consists of the optimum MRD and the matching ratio prototype to generalized image, the cumulative filter ratio, the gap of prototype response MRD. We experimented the performance using NIST database of NIST without preprocessor, and compared this model with 3DNS. The proposed MRD method has more performance of recognition rate and more stable system for distortion of input pattern than 3DNS.

• Journal of the Korean Society of Food Culture
• /
• v.25 no.3
• /
• pp.270-284
• /
• 2010

The objective of this study was to familiarize people with the native local food of Chungnam Province by developing its regional food as a culture resource. Native Local Food Search and luxury itemization based on regionally-characterized stories enhances self-perception of the national culture, promotes appropriate local images to the public, and contributes to the local economy by increasing regional tourism. Therefore, this study researched local stories of cultural significance, that is, those connected to the history and originality of Chungnam Province, and developed contents related to Chungnam native local food. Features of the native local food were introduced by a story telling method in order to appeal to the five senses. The story was composed for easy understanding of the value of food, and the brand image of Chungnam was developed based on representative historical stories of the region. In this study, the following were developed as representative images of Chungnam: 'Royal meal table of King Moo-ryung' in Kongju was presented by recomposing the story of King Moo-ryung, a famouns king of the Baekje era; 'Mong-yoo-do-won's rice meal table' was introduced via Mongyoo-do-won's painting by Kyeon An, a famous painter of the Chosun era who was born in Seosan. The 'Royal meal table of King Moo-ryung' was set with food made from local farm products, demonstrating the flavor and elegance of the Baekje era. 'Mong-yoo-do-won's rice meal table' resembled Kyeon An's Mong-yoo-do-won-do, which has a background featuring early spring. The rice table was designed to remind people of a flamboyant painting like a scattered peach blossom leaf in the early spring. To verify the health effectiveness of each rice table, the function of each ingredient was investigated through 'Sik-ryo-chan-yo:a dietary treatment', which was published by Soon-Ui Cheon during the Chosan era. According to the results, most of ingredients are certainly beneficial to health, as was recognized in the early Choson era.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.8
• /
• pp.151-156
• /
• 2019

In recent years, the Korean realistic theme of the film momentum gradually rising. Realistic films do not stick to the business and market, and do not simply cater to the audience's needs for watching movies. They reflect social violence and cruel reality, allowing the audience to observe the structural contradictions in reality and think about the direction when watching movies. At the recent cannes film festival, "parasite" won the top prize palm in cannes by an overwhelming margin, with the highest score of 3.3 issues. Although this film is positioned as a thriller with comedy elements, it presents the opposite life images of Korean classes to the audience in a parasitic way, which not only expands the possibility and artistry of realistic film aesthetics, but also enhances the appreciation of the film and gives play to its own aesthetic value. Focusing on the technical and literary nature of the film, and having a high degree of attention to real life, it is an excellent work that tells about class opposition and thinking about reality. This paper considers and analyzes the content, form and creation method of parasite, and discusses the continuous exploration and attempt of realistic film to image language under the demand of market and system, evolving into new aesthetic expression.

• Smart Structures and Systems
• /
• v.30 no.5
• /
• pp.521-535
• /
• 2022

Efficient management of deteriorating civil infrastructure is one of the most important research topics in many developed countries. In particular, the remote displacement measurement of bridges using linear variable differential transformers, global positioning systems, laser Doppler vibrometers, and computer vision technologies has been attempted extensively. This paper proposes a remote displacement measurement system using closed-circuit televisions (CCTVs) and a computer-vision-based method for in-situ bridge bearings having relatively large displacement due to temperature change in long term. The hardware of the system is composed of a reference target for displacement measurement, a CCTV to capture target images, a gateway to transmit images via a mobile network, and a central server to store and process transmitted images. The usage of CCTV capable of night vision capture and wireless data communication enable long-term 24-hour monitoring on wide range of bridge area. The computer vision algorithm to estimate displacement from the images involves image preprocessing for enhancing the circular features of the target, circular Hough transformation for detecting circles on the target in the whole field-of-view (FOV), and homography transformation for converting the movement of the target in the images into an actual expansion displacement. The simple target design and robust circle detection algorithm help to measure displacement using target images where the targets are far apart from each other. The proposed system is installed at the Tancheon Overpass located in Seoul, and field experiments are performed to evaluate the accuracy of circle detection and displacement measurements. The circle detection accuracy is evaluated using 28,542 images captured from 71 CCTVs installed at the testbed, and only 48 images (0.168%) fail to detect the circles on the target because of subpar imaging conditions. The accuracy of displacement measurement is evaluated using images captured for 17 days from three CCTVs; the average and root-mean-square errors are 0.10 and 0.131 mm, respectively, compared with a similar displacement measurement. The long-term operation of the system, as evaluated using 8-month data, shows high accuracy and stability of the proposed system.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.339-346
• /
• 2023

The uncertainties of microstructural features affect the properties of materials. Numerous pores that are randomly distributed in materials make it difficult to predict the properties of the materials. The distribution of pores in cementitious materials has a great influence on their mechanical properties. Existing studies focus on analyzing the statistical relationship between pore distribution and material responses, and the correlation between them is not yet fully determined. In this study, the mechanical response of cementitious materials is predicted through an image-based data approach using a convolutional neural network (CNN), and the correlation between pore distribution and material response is analyzed. The dataset for machine learning consists of high-resolution micro-CT images and the properties (tensile strength) of cementitious materials. The microstructures are characterized, and the mechanical properties are evaluated through 2D direct tension simulations using the phase-field fracture model. The attributes of input images are analyzed to identify the spot with the greatest influence on the prediction of material response through CNN. The correlation between pore distribution characteristics and material response is analyzed by comparing the active regions during the CNN process and the pore distribution.

• Journal of The Korean Astronomical Society
• /
• v.56 no.2
• /
• pp.213-224
• /
• 2023

Type II solar radio bursts show frequency drifts from high to low over time. They have been known as a signature of coronal shock associated with Coronal Mass Ejections (CMEs) and/or flares, which cause an abrupt change in the space environment near the Earth (space weather). Therefore, early detection of type II bursts is important for forecasting of space weather. In this study, we develop a deep-learning (DL) model for the automatic detection of type II bursts. For this purpose, we adopted a 1-D Convolution Neutral Network (CNN) as it is well-suited for processing spatiotemporal information within the applied data set. We utilized a total of 286 radio burst spectrum images obtained by Hiraiso Radio Spectrograph (HiRAS) from 1991 and 2012, along with 231 spectrum images without the bursts from 2009 to 2015, to recognizes type II bursts. The burst types were labeled manually according to their spectra features in an answer table. Subsequently, we applied the 1-D CNN technique to the spectrum images using two filter windows with different size along time axis. To develop the DL model, we randomly selected 412 spectrum images (80%) for training and validation. The train history shows that both train and validation losses drop rapidly, while train and validation accuracies increased within approximately 100 epoches. For evaluation of the model's performance, we used 105 test images (20%) and employed a contingence table. It is found that false alarm ratio (FAR) and critical success index (CSI) were 0.14 and 0.83, respectively. Furthermore, we confirmed above result by adopting five-fold cross-validation method, in which we re-sampled five groups randomly. The estimated mean FAR and CSI of the five groups were 0.05 and 0.87, respectively. For experimental purposes, we applied our proposed model to 85 HiRAS type II radio bursts listed in the NGDC catalogue from 2009 to 2016 and 184 quiet (no bursts) spectrum images before and after the type II bursts. As a result, our model successfully detected 79 events (93%) of type II events. This results demonstrates, for the first time, that the 1-D CNN algorithm is useful for detecting type II bursts.

• Journal of the Korean Society of Radiology
• /
• v.81 no.5
• /
• pp.1164-1174
• /
• 2020

Purpose To evaluate a deep learning model to predict recurrence of thyroid tumor using preoperative ultrasonography (US). Materials and Methods We included representative images from 229 US-based patients (male:female = 42:187; mean age, 49.6 years) who had been diagnosed with thyroid cancer on preoperative US and subsequently underwent thyroid surgery. After selecting each representative transverse or longitudinal US image, we created a data set from the resulting database of 898 images after augmentation. The Python 2.7.6 and Keras 2.1.5 framework for neural networks were used for deep learning with a convolutional neural network. We compared the clinical and histological features between patients with and without recurrence. The predictive performance of the deep learning model between groups was evaluated using receiver operating characteristic (ROC) analysis, and the area under the ROC curve served as a summary of the prognostic performance of the deep learning model to predict recurrent thyroid cancer. Results Tumor recurrence was noted in 49 (21.4%) among the 229 patients. Tumor size and multifocality varied significantly between the groups with and without recurrence (p < 0.05). The overall mean area under the curve (AUC) value of the deep learning model for prediction of recurrent thyroid cancer was 0.9 ± 0.06. The mean AUC value was 0.87 ± 0.03 in macrocarcinoma and 0.79 ± 0.16 in microcarcinoma. Conclusion A deep learning model for analysis of US images of thyroid cancer showed the possibility of predicting recurrence of thyroid cancer.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.1
• /
• pp.97-107
• /
• 2024

Despite the rapid advancement in image recognition technology, achieving perfect digitization of tabular documents and handwritten documents still challenges. The purpose of this study is to improve the accuracy of digitizing the logbook by correcting errors by utilizing associated rules considered during logbook entries. Through this, it is expected to enhance the accuracy and reliability of data extracted from logbook through OCR programs. This model is to improve the accuracy of digitizing the logbook of the training ship "Saenuri" at the Mokpo Maritime University by correcting errors identified after Optical Character Recognition (OCR) program recognition. The model identified and corrected errors by utilizing associated rules considered during logbook entries. To evaluate the effect of model, the data before and after correction were divided by features, and comparisons were made between the same sailing number and the same feature. Using this model, approximately 10.6% of errors out of the total estimated error rate of about 11.8% were identified, and 56 out of 123 errors were corrected. A limitation of this study is that it only focuses on information from Dist.Run to Stand Course sections of the logbook, which contain navigational information. Future research will aim to correct more information from the logbook, including weather information, to overcome this limitation.

• Economic and Environmental Geology
• /
• v.50 no.6
• /
• pp.477-486
• /
• 2017

In this study, we analyze precise seabed geomorphology and conditions for comparing the nearshore areas of the Dongdo(East Island) and the Seodo(West Island) using detailed bathymetry data and seafloor backscattering images, in Dokdo, the East Sea. We have been obtained the detailed bathymetry data and the seafloor backscattering data. The survey range is about $250m{\times}250m$ including land of islets to the nearshore areas of the southern part of the Dongdo and the Seodo. As a result of bathymetry survey, the southern area of the Dongdo(~50 m) is deeper than the Seodo(~30 m) in the water depth. The survey areas are consist of extended bedrocks from land of the Dongdo and the Seodo. The underwater rock region of the Seodo is larger than the Dongdo. In spite of similar extended rocks features from islets, there are some distinctive seabed characteristics between the southern nearshore areas of the Dongdo and the Seodo. The Talus-shaped seafloor environment formed by gravel and underwater rocks originating from the land of the Dongdo is up to about 15 m depth. And the boundary line of between extended bedrocks and seabottom is unclear in the southern nearshore of the Dongdo. On the other hand, the southern coast of the Seodo is characterized by relatively large scale underwater rocks and evenly distributed sediments, which clearly distinguish the boundary of between extended bedrocks and seafloor. This is because the tuff layers exposed to the coastal cliffs of the Dongdo are weak against weathering and erosion. It is considered that there are more influences of the clastic sediments carried from the land of the Dongdo compared with the Seodo. Particularly, the land of the Dongdo has been undergoing construction activities. And also a highly unstable ground such as faults, joints and cracks appears in the Dongdo. In previous study, there are dissimilar features of the massive tuff breccia formations of the Dongdo and the Seodo. These conditions are thought to have influenced the different seabed characteristics in the southern nearshore areas of the Dongdo and the Seodo.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.31 no.6 s.165
• /
• pp.837-847
• /
• 2007

1,098 pieces of photographs($1995{\sim}2002$) of men's suit style have been classified according to fashion images in order to examine features and change aspects with statistical analysis. The findings of examining features of the trend by year with test of homogeneity, correspondence analysis, biplots, correlation analysis and regression analysis are as follows: (a) there are significant differences on fashion images as the trend by yew with test of homogeneity, (b) there are remarkable differences on the fashion trend by year with correspondence analysis and biplots. (c) There are significant correlations for appearance among fashion images by its frequency through correlation analysis, and (d) it is assumed that fashion images are going to be gradually outstanding according to regression analysis.