• Journal of Korean Society of Archives and Records Management
• /
• v.22 no.4
• /
• pp.175-196
• /
• 2022

This study aims to determine the research trends in archival preservation through keyword analysis, understand the current research status, and identify the research topics' changes over time. The degree and betweenness centrality analyses were conducted and visualized on 463 "archival preservation studies" articles published from 2000 to 2021 in various academic journals, using NetMiner 4.0. The collected research papers were divided into three time periods according to when they were published: the first period (2000-2007), the second period (2008-2014), and the third period (2015-2021). The subject keywords for the research papers on archival preservation in Korea that have influence and expandability are as follows. Across all periods, these were "electronic records" and "long-term preservation." In addition, if taken separately per period, the "OAIS reference model" and "electronic records" dominated the first and second periods, respectively, while the "records management standard table" and "long-term preservation" both dominated the third period. A conceptual framework and theory-oriented study for archival preservation, such as "digital preservation," "digitalization," and the "OAIS reference model," dominated the first period. During the second period, more research focused on procedures and practical applications related to conservation activities, such as "electronic record," "appraisal," and "DRAMBORA." In contrast, the majority of the research in the third period was on technical implementation according to the changes in the records management environment, such as "data set," "administrative information system," and "social media."

• Korean Chemical Engineering Research
• /
• v.62 no.3
• /
• pp.214-224
• /
• 2024

Valves play an essential role in a chemical plant such as regulating fluid flow and pressure. Therefore, optimal selection of the valve size and type is essential task. Valve size and type have been selected based on theoretical formulas about calculating valve sizing coefficient (Cv). However, this approach has limitations such as requiring expert knowledge and consuming substantial time and costs. Herein, this study developed a model for predicting valve sizes and types using machine learning. We developed models using four algorithms: ANN, Random Forest, XGBoost, and Catboost and model performances were evaluated using NRMSE & R² score for size prediction and F1 score for type prediction. Additionally, a case study was conducted to explore the impact of phases on valve selection, using four datasets: total fluids, liquids, gases, and steam. As a result of the study, for valve size prediction, total fluid, liquid, and gas dataset demonstrated the best performance with Catboost (Based on R², total: 0.99216, liquid: 0.98602, gas: 0.99300. Based on NRMSE, total: 0.04072, liquid: 0.04886, gas: 0.03619) and steam dataset showed the best performance with RandomForest (R²: 0.99028, NRMSE: 0.03493). For valve type prediction, Catboost outperformed all datasets with the highest F1 scores (total: 0.95766, liquids: 0.96264, gases: 0.95770, steam: 1.0000). In Engineering Procurement Construction industry, the proposed fluid-specific machine learning-based model is expected to guide the selection of suitable valves based on given process conditions and facilitate faster decision-making.

• Journal of the Korean Society for information Management
• /
• v.36 no.4
• /
• pp.161-181
• /
• 2019

People begin to recognize sexual orientation or gender identity in adolescence, and adolescents frequently use an accessible and anonymous anonymity knowledge retrieval community to explore sensitive health information about gender. This study attempted to observe their information search behavior based on questions and answers about adolescents' gender identity in the knowledge retrieval community. First, we wanted to examine their information needs and to investigate what factors they preferred to answer by comparing the characteristics of the answers adopted with the non-adopted answers among the answers provided in the questions they shared. To this end, Naver, Korea's representative knowledge search community. In Knowledge-iN, a total of 358 sets of data were analyzed, consisting of responses adopted over three years from January 2016 to December 2018. As a result, adolescents with concerns about gender identity demanded information about definition or confusion about gender identity. In the responses adopted by the users, the factors that gave empathy and positive feelings were higher than those that were not adopted, whereas the negative responses were higher in the unaccepted answers. This study is meaningful in that it analyzes the information needs and information search behaviors of adolescents with no established gender identity, expands the discussion in the information search field, and confirms cognitive and emotional models for information evaluation of health information users. Also, based on the research results, we propose practical implications for effective information services on gender identity that social media should provide to young people.

• Journal of the Korean Society of Radiology
• /
• v.84 no.1
• /
• pp.240-252
• /
• 2023

Purpose To assess the effect of deep learning image reconstruction (DLIR) for head CT in pediatric patients. Materials and Methods We collected 126 pediatric head CT images, which were reconstructed using filtered back projection, iterative reconstruction using adaptive statistical iterative reconstruction (ASiR)-V, and all three levels of DLIR (TrueFidelity; GE Healthcare). Each image set group was divided into four subgroups according to the patients' ages. Clinical and dose-related data were reviewed. Quantitative parameters, including the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), and qualitative parameters, including noise, gray matter-white matter (GM-WM) differentiation, sharpness, artifact, acceptability, and unfamiliar texture change were evaluated and compared. Results The SNR and CNR of each level in each age group increased among strength levels of DLIR. High-level DLIR showed a significantly improved SNR and CNR (p < 0.05). Sequential reduction of noise, improvement of GM-WM differentiation, and improvement of sharpness was noted among strength levels of DLIR. Those of high-level DLIR showed a similar value as that with ASiR-V. Artifact and acceptability did not show a significant difference among the adapted levels of DLIR. Conclusion Adaptation of high-level DLIR for the pediatric head CT can significantly reduce image noise. Modification is needed while processing artifacts.

• Korean Journal of Applied Biomechanics
• /
• v.12 no.2
• /
• pp.1-16
• /
• 2002

The purposes of this study were to investigate the effects of strength training on the change of ground reaction force for the children with trisomy 21 Down syndrome. The subjects of this study were consisted of eight elementary school students with Down syndrome who participated in the strength training. The strength training was administered by six items such as squat, leg curl, leg extension, toe raise, sit-ups, and hyperextension. For strengthening muscle, each group also was treated by walking for 8 weeks, three times a week, 10-15RM, 3sets, which was based on the principle of progressive overload. For inquiring the effect of strength training, the ground reaction force variables were measured in two phases : before-training and 8 week-after training. The gait of each subject was acquisition using 2 AMTI force platforms set at 100 frequency. The results of this study were as follows: The pattern of vertical, antero-posterior and medio-lateral forces, trajectory of net COP and the timing ratio of reaching the each events were shown variously. So, it is not easy to explain these variables clearly. As the result of strength training, these variables were changed. However, the results of within subjects differ greatly, there was no difference statistically.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.5 no.2 s.17
• /
• pp.9-16
• /
• 2005

This paper presents the use of an Artificial Neural Network (ANN) as a viable means of forecasting Inundation Damage Area (IDA) in many watersheds. In order to develop the forecasting model with various environmental factors, we selected 108 watershed areas in South Korea and collected 49 damage data sets from 1990 to 2000, of which each set is composed of 27 parameters including the IDA, rainfall amount, and land use. After successful training processes of the ANN, a good agreement (R=0.92) is obtained (under present conditions) between the measured values of the IDA and those predicted by the developed ANN using the remaining 26 data sets as input parameters. The results indicate that the inundation damage is affected by not only meteorological information such as the rainfall amount, but also various environmental characteristics of the watersheds. So, the ANN proves its present ability to predict the IDA caused by an event of complex factors in a specific watershed area using accumulated temporal-spatial information, and it also shows a potential capability to handle complex non-linear dynamic phenomena of environmental changes. In this light, the ANN can be further harnessed to estimate the importance of certain input parameters to an output (e.g., the IDA in this study), quantify the significance of parameters involved in pre-existing models, and contribute to the presumption, selection, and calibration of input parameters of conventional models.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.497-504
• /
• 2020

Constructing speaker embeddings in speaker verification is an important issue. In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. In this case, the effect of low-level layers is not well represented in the speaker embedding encoding. In this study, we propose Masked Cross Self-Attentive Encoding (MCSAE) using ResNet. It focuses on training the features of both high-level and low-level layers. Based on multi-layer aggregation, the output features of each residual layer are used for the MCSAE. In the MCSAE, the interdependence of each input features is trained by cross self-attention module. A random masking regularization module is also applied to prevent overfitting problem. The MCSAE enhances the weight of frames representing the speaker information. Then, the output features are concatenated and encoded in the speaker embedding. Therefore, a more informative speaker embedding is encoded by using the MCSAE. The experimental results showed an equal error rate of 2.63 % using the VoxCeleb1 evaluation dataset. It improved performance compared with the previous self-attentive encoding and state-of-the-art methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.15-23
• /
• 2017

The person Re-identification is the most challenging part of computer vision due to the significant changes in human pose and background clutter with occlusions. The picture from non-overlapping cameras enhance the difficulty to distinguish some person from the other. To reach a better performance match, most methods use feature selection and distance metrics separately to get discriminative representations and proper distance to describe the similarity between person and kind of ignoring some significant features. This situation has encouraged us to consider a novel method to deal with this problem. In this paper, we proposed an enhanced recurrent neural network with three-tier hierarchical network for person re-identification. Specifically, the proposed recurrent neural network (RNN) model contain an iterative expectation maximum (EM) algorithm and three-tier Hierarchical network to jointly learn both the discriminative features and metrics distance. The iterative EM algorithm can fully use of the feature extraction ability of convolutional neural network (CNN) which is in series before the RNN. By unsupervised learning, the EM framework can change the labels of the patches and train larger datasets. Through the three-tier hierarchical network, the convolutional neural network, recurrent network and pooling layer can jointly be a feature extractor to better train the network. The experimental result shows that comparing with other researchers' approaches in this field, this method also can get a competitive accuracy. The influence of different component of this method will be analyzed and evaluated in the future research.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.669-681
• /
• 2023

Studies have tried to apply remote sensing technology, a non-destructive survey method, instead of the existing destructive survey, which requires relatively large labor input and a long time to estimate chlorophyll content, which is an important indicator for evaluating the growth of fruit trees. This study was conducted to non-destructively evaluate the chlorophyll content of pear tree leaves using unmanned aerial vehicle-based hyperspectral imagery for two years(2021, 2022). The reflectance of the single bands of the pear tree canopy extracted through image processing was band rationed to minimize unstable radiation effects depending on time changes. The estimation (calibration and validation) models were developed using machine learning algorithms of elastic-net, k-nearest neighbors(KNN), and support vector machine with band ratios as input variables. By comparing the performance of estimation models based on full band ratios, key band ratios that are advantageous for reducing computational costs and improving reproducibility were selected. As a result, for all machine learning models, when calibration of coefficient of determination (R²)≥0.67, root mean squared error (RMSE)≤1.22 ㎍/cm², relative error (RE)≤17.9% and validation of R²≥0.56, RMSE≤1.41 ㎍/cm², RE≤20.7% using full band ratios were compared, four key band ratios were selected. There was relatively no significant difference in validation performance between machine learning models. Therefore, the KNN model with the highest calibration performance was used as the standard, and its key band ratios were 710/714, 718/722, 754/758, and 758/762 nm. The performance of calibration showed R²=0.80, RMSE=0.94 ㎍/cm², RE=13.9%, and validation showed R²=0.57, RMSE=1.40 ㎍/cm², RE=20.5%. Although the performance results based on validation were not sufficient to estimate the chlorophyll content of pear tree leaves, it is meaningful that key band ratios were selected as a standard for future research. To improve estimation performance, it is necessary to continuously secure additional datasets and improve the estimation model by reproducing it in actual orchards. In future research, it is necessary to continuously secure additional datasets to improve estimation performance, verify the reliability of the selected key band ratios, and upgrade the estimation model to be reproducible in actual orchards.