• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.389-396
• /
• 2024

Generative AI has recently been utilized across all fields, achieving expert-level advancements in deep data analysis. However, identifying regional names in scientific literature remains a challenge due to insufficient training data and limited AI application. This study developed a standardized dataset for effectively classifying regional names using address data from Korean institution-affiliated authors listed in the Web of Science. It tested and evaluated the applicability of machine learning and deep learning models in real-world problems. The BERT model showed superior performance, with a precision of 98.41%, recall of 98.2%, and F1 score of 98.31% for metropolitan areas, and a precision of 91.79%, recall of 88.32%, and F1 score of 89.54% for city classifications. These findings offer a valuable data foundation for future research on regional R&D status, researcher mobility, collaboration status, and so on.

• Journal of Advanced Navigation Technology
• /
• v.27 no.6
• /
• pp.776-781
• /
• 2023

K-UAM will be commercialized through maturity after 2035. Since the Urban Air Mobility (UAM) corridor will be used vertically separating the existing helicopter corridor, the corridor usage is expected to increase. Therefore, a system for monitoring corridors is also needed. In recent years, object detection algorithms have developed significantly. Object detection algorithms are largely divided into one-stage model and two-stage model. In real-time detection, the two-stage model is not suitable for being too slow. One-stage models also had problems with accuracy, but they have improved performance through version upgrades. Among them, YOLO-V5 improved small image object detection performance through Mosaic. Therefore, YOLO-V5 is the most suitable algorithm for systems that require real-time monitoring of wide corridors. Therefore, this paper trains YOLO-V5 and analyzes whether it is ultimately suitable for corridor monitoring.K-uam will be commercialized through maturity after 2035.

• Proceedings of the KSEEG Conference
• /
• 2002.06a
• /
• pp.81-100
• /
• 2002

While most of regulatory communities in abroad recognize ' 'natural attenuation " to include degradation, dispersion, dilution, sorption (including precipitation and transformation), and volatilization as governing Processes, regulators prefer "degradation" because this mechanism destroys the contaminant of concern. Unfortunately, true degradation only applies to organic contaminants and short- lived radionuclides, and leaves most metals and long-lived radionuclides. The natural attenuation Processes may reduce the potential risk Posed by site contaminants in three ways: (i)contaminants could be converted to a less toxic form througy destructive processes such as biodegradation or abiotic transformations; (ii) potential exposure levels may be reduced by lowering concentrations (dilution and dispersion); and (iii) contaminant mobility and bioavailability may be reduced by sorption to geomedia. In this review, authors will focus will focul on "sorption" among the natural attenuation processes of hazardous inorganic contaminants including radionuclides. Note though that sorption and transformation processes of inorganic contaminants in the natural setting could be influenced by biotic activities but our discussion would limit only to geochemical reactions involved in the natural attenuation. All of the geochemical reactions have been studied in-depth by numerous researchers for many years to understand "retardation" process of contaminants in the geomedia. The most common approach for estimating retardation is the determination of distrubution coefficiendts ($K_{d}$) of contaminants using parametric or mechanistic models. As typocally used in fate and contaminant transport calculations such as predictive models of the natural attenuation, the $K_{d}$ is defined as the ratio of the contaminant concentration in the surrounding aqueous solution when the system is at equilibrium. Unfortunately, generic or default $K_{d}$ values can result in significant error when used to predict contaminant migration rate and to select a site remediation alternative. Thus, to input the best $K_{d}$ value in the contaminant transport model, it is essential that important geochemical processes affecting the transport should be identified and understood. Precipitation/dissolution and adsorption/desorption are considered the most important geochemical processes affecting the interaction of inorganic and radionuclide contaminants with geomedia at the near and far field, respectively. Most of contaminants to be discussed in this presentation are relatively immobile, i.e., have very high $K_{d}$ values under natural geochemical environments. Unfortunately, the obvious containment in a source area may not be good enough to qualify as monitored natural attenuation site unless owner demonstrate the efficacy if institutional controls that were put in place to protect potential receptors. In this view, natural attenuation as a remedial alternative for some of sites contaminated by hazardous-inorganic components is regulatory and public acceptance issues rather than scientific issue.

• The Journal of the Korea Contents Association
• /
• v.18 no.5
• /
• pp.265-279
• /
• 2018

This study conducted an experiment using data mining techniques to develop prediction models of worker job turnover. The experiment used data from the '2015 Graduate Occupational Mobility Survey' by the Korea Employment Information Service. We developed the prediction models using a decision tree, Bayes net, and artificial neural network. We found that the decision tree-based prediction model reported the best accuracy. We also found that the six influential factors affecting employees' turnover intention are type of working time, job status, full-time or not full-time, regular working hours per week, regular working days per week, and personal development opportunities. From the decision tree-based prediction model, we derived 12 rules of employee turnover for all job types. Using the derived rules, we proposed helpful directions for enhancing workers' job tenure. In addition, we analyzed the influential factors affecting employees' job turnover intention according to four job types and derived rules for each: office (ten rules), culture and art (nine rules), construction (four rules), and information technology (six rules). Using the derived rules, we proposed customized directions for improving the job tenure for each group.

• Journal of the Korean GEO-environmental Society
• /
• v.19 no.10
• /
• pp.21-26
• /
• 2018

Soil-water characteristic curve, which is called soil retention curve, is required to explore water flows in unsaturated soils, relative permeability of water in multi-phase fluids flow, and change to stiffness and volume of soils. Thus, the understanding of soil-water characteristic curves of soils help us explore the behavior of soils inclduing fluids. Biopolymers are environmental-friendly materials, which can be completely degraded by microbes and have been believed not to affect the nature. Thus, various biopolymers such as deacetylated power, polyethylene oxide, xanthan gum, alginic acid sodium salt, and polyacrylic acid have been studies for the application to soil remediation, soil improvement, and enhanced oil recovery. PAA (polyacrylic acid) is one of biopolymers, which have shown a great effect in enhanced oil recovery as well as soil remediation because of the improvement of water-flood performance by mobility control. The study on soil-water characteristic curves of sandy soils containing PAA (polyacrylic acid) has been conducted through experimentations and theoretical models. The results show that both capillary entry pressure and residual water saturation dramatically increase according to the increased concentration of PAA (polyacrylic acid). Also, soil-water characteristic curves by theoretical models are quite well consistent with the results by experimental studies. Thus, soil-water characteristic curves of sandy soils containing biopolymers such as PAA (polyacrylic acid) can be estimated using fitting parameters for the theoretical model.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.2
• /
• pp.397-405
• /
• 2015

In the past, expressways focused on mobility. However, the paradigm of expressways fuction today has been changed from fast expressways to safe expressways as people's quality of living and consciousness level heightened. In 2012, 3,550 traffic accidents occurred on expressways and 371 people died. The fatality rate of traffic accidents on expressways is almost twice that on general national roads. This study developed accident forecast models (safety performance functions) based on the number of traffic accidents and traffic volumes on six major lines on expressways. It is difficult to forecast safety performance functions for each expressway line because the lines and the scales of expressways are different from each other; therefore, integrated safety performance functions of six lines were determined first, and the coefficients, which can correct the traffic accidents on each line, were calculated. It is believed that this study will contribute in the safer management of expressways by being used as basic information in the establishment of traffic safety strategies for each expressway line in prevention of traffic accidents. Moreover, more studies would be required in the future, which would suggest reliable accident forecasts by calculating correction coefficients by line through integrated models by groups dependent on the characteristics of each line.

• Journal of Korean Society of Transportation
• /
• v.34 no.2
• /
• pp.107-122
• /
• 2016

This study aims to develop a framework to estimate mobile source emissions with the macroscopic travel demand model including enhanced estimates of intra-zonal travel emissions using Space Syntax analysis. It is acknowledged that "the land-use and transportation interaction model explains the influence of urban structure on accessibility and mobility pattern". Based upon this theory, the estimation model of intra-zonal travel emissions is presented with the models of total travel distance, total travel demand, and average travel speed of intra-zonal trips. Thess statistical models include several spatial indices derived from the Space Syntax analysis. It explains that urban spatial structure is a critical factor for intra-zonal travel emissions, which is lower in compact zone with smaller portion of land area, lower sprawl indicator, and more grid-type of road network. Also the suggested framework is applied in the evaluation of the effectiveness of bicycle lane project in Suwon, Korea. The estimated emissions including intra-zonal travel is as double as the results only with inter-zonal demands, which shows better performance of the suggested framework for more realistic outcomes. This framework is applicable to the estimation of mobile source emissions in nation-wide and the assessment of transportation-environment policies in regional level.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.1-25
• /
• 2022

After the first Covid-19 confirmed case occurred in Korea in January 2020, interest in personal transportation such as public bicycles not public transportation such as buses and subways, increased. The demand for 'Ddareungi', a public bicycle operated by the Seoul Metropolitan Government, has also increased. In this study, a demand prediction model of a GRU(Gated Recurrent Unit) was presented based on the rental history of public bicycles by time zone(2019~2021) in Seoul. The usefulness of the GRU method presented in this study was verified based on the rental history of Around Exit 1 of Yeouido, Yeongdengpo-gu, Seoul. In particular, it was compared and analyzed with multiple linear regression models and recurrent neural network models under the same conditions. In addition, when developing the model, in addition to weather factors, the Seoul living population was used as a variable and verified. MAE and RMSE were used as performance indicators for the model, and through this, the usefulness of the GRU model proposed in this study was presented. As a result of this study, the proposed GRU model showed higher prediction accuracy than the traditional multi-linear regression model and the LSTM model and Conv-LSTM model, which have recently been in the spotlight. Also the GRU model was faster than the LSTM model and the Conv-LSTM model. Through this study, it will be possible to help solve the problem of relocation in the future by predicting the demand for public bicycles in Seoul more quickly and accurately.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• The korean journal of orthodontics
• /
• v.21 no.2 s.34
• /
• pp.259-272
• /
• 1991

Orthodontic traction has been suggested as the treatment of choice for intrusive luxation injuries. Prior research has shown orthodontic forces to be ineffective in the presence of ankylosis or in cases with zero mobility following the injury. If orthodontic traction is to be effective, it must be initiated prior to the onset of ankylosis. The purpose of this study was to describe the effects of intrusive luxation at various times following the injury, and to determine the time of the onset of ankylosis, and to examine what effect immediate partial luxation has on the onset of ankylosis. Eight young mongrel dogs were utilized for this study. Intrusive luxation was produced with an axial impact using a gravity hammer and a specially designed holding device on 4 teeth (2 max. and 2 man. first premolars) in each dog. The teeth were intruded approximately 3-4mm in an axial direction. One maxillary and one mandibular premolars were partially luxated with the other two teeth being untouched. Pre and posttrauma tooth position was documented with plaster models and radiographs taken with an individualized X-ray jig. Dogs were sacrificed immediately following the injury and at 1, 2, 4, 7, 10, 14 and 21 days respectively. Tetracycline was administered as a vital bone marker 24 hours before sacrifice. Block sections of the tooth and alveolus were prepared for decalcified and non decalcified histologic sections. The effects of traumatic intrusion were analyzed by means of model casts, radiographs, tetracycline bone marking and histologic preparations. The results obtained were as follows: 1. The animal sacrificed immediately following the injury displayed alveolar fractures, torn periodontal ligaments, and areas of direct tooth-bone contact. 2. The odontoblastic layer of the pulp was disorganized as early as 24 hours after the injury. 3. Bony remodeling was noted at 4 days along with active surface resorption. 4. Ankylosis was first seen 7 days after the injury. 5. Osteogenesis in the dentin (thick tetracycline bands) was observed 7 days after the injury. 6. There was no progressive root resorption and ankylosis where the periodontal ligament has been healed. 7. The Luxated group showed significantly more root resolution and ankylosis than the Nonluxated group with increased observation periods. The results suggest that ankylosis may occur within the first week following the injury, and hence orthodontic traction should be initiated as soon after the injury as possible.