• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.4
• /
• pp.315-324
• /
• 2022

The conventional LESS (LEast-Squares Solution) is calculated under the assumption that there is no errors in independent variables. However, the coordinates of a point, either from traditional ground surveying such as slant distances, horizontal and/or vertical angles, or GNSS (Global Navigation Satellite System) positioning, cannot be determined independently (and the components are correlated each other). Therefore, the TLS (Total Least Squares) adjustment should be applied for all applications related to the coordinates. Many approaches were suggested in order to solve this problem, resulting in equivalent solutions except some restrictions. In this study, we calculated the normal vector of the 3D plane determined by the trace of the VLBI targets based on TLS within GHM (Gauss-Helmert Model). Another numerical test was conducted for the estimation of the Helmert transformation parameters. Since the errors in the horizontal components are very small compared to the radius of the circle, the final estimates are almost identical. However, the estimated variance components are significantly reduced as well as show a different characteristic depending on the target location. The Helmert transformation parameters are estimated more precisely compared to the conventional LESS case. Furthermore, the residuals can be predicted on both reference frames with much smaller magnitude (in absolute sense).

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.419-437
• /
• 2023

As the number of thin filers in Korea surpasses 12 million, there is a growing interest in enhancing the accuracy of assessing their credit default risk to generate additional revenue. Specifically, researchers are actively pursuing the development of default prediction models using machine learning and deep learning algorithms, in contrast to traditional statistical default prediction methods, which struggle to capture nonlinearity. Among these efforts, Graph Neural Network (GNN) architecture is noteworthy for predicting default in situations with limited data on thin filers. This is due to their ability to incorporate network information between borrowers alongside conventional credit-related data. However, prior research employing graph neural networks has faced limitations in effectively handling diverse categorical variables present in credit information. In this study, we introduce the Transformer embedded Graph Convolutional Network (TeGCN), which aims to address these limitations and enable effective default prediction for thin filers. TeGCN combines the TabTransformer, capable of extracting contextual information from categorical variables, with the Graph Convolutional Network, which captures network information between borrowers. Our TeGCN model surpasses the baseline model's performance across both the general borrower dataset and the thin filer dataset. Specially, our model performs outstanding results in thin filer default prediction. This study achieves high default prediction accuracy by a model structure tailored to characteristics of credit information containing numerous categorical variables, especially in the context of thin filers with limited data. Our study can contribute to resolving the financial exclusion issues faced by thin filers and facilitate additional revenue within the financial industry.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.323-338
• /
• 2023

TV advertising with deep analysis of watching pattern of audiences is important to set-top box audience targeting. Applying session-based recommendation model(SBR) to internet commercial, or recommendation based on searching history of user showed its effectiveness in previous studies, but applying SBR to the TV advertising was difficult in South Korea due to data unavailabilities. Also, traditional SBR has limitations for dealing with user preferences, especially in data with user identification information. To tackle with these problems, we first obtain set-top box data from three major broadcasting companies in South Korea(SKB, KT, LGU+) through collaboration with Korea Broadcast Advertising Corporation(KOBACO), and this data contains of watching sequence of 4,847 anonymized users for 6 month respectively. Second, we develop personalized session-based recommendation model to deal with hierarchical data of user-session-item. Experiments conducted on set-top box audience dataset and two other public dataset for validation. In result, our proposed model outperformed baseline model in some criteria.

• Journal of Korea Water Resources Association
• /
• v.56 no.11
• /
• pp.765-774
• /
• 2023

Due to climatechange, precipitation variability has increased, leading to more frequentoccurrences of droughts and floods. To establish measures for managing waterresources in response to the increasing uncertainties of climate conditions, itis necessary to understand the variability of natural river discharge and theimpact of reservoir operation modeling considering dam inflow and artificialwater supply. In this study, an integrated rainfall-runoff and reservoiroperation modeling was applied to analyze the water supply reliability andflood risk for a multipurpose dam catchment under climate change conditions. Therainfall-runoff model employed was the modèle du Génie Rural à 4 paramètresJournalier (GR4J) model, and the reservoir operation model used was an R-basedmodel with the structure of HEC-Ressim. Applying the climate change scenariosuntil 2100 to the established integrated model, the changes in water supplyreliability and flood risk of the Happcheon Dam were quantitatively analyzed.The results of the water supply reliability analysis showed that under SSP2-4.5conditions, the water supply reliability was higher than that under SSP5-8.5conditions. Particularly, in the far-future period, the range of flood risk widened,and both SSP2-4.5 and SSP5-8.5 scenarios showed the highest median flood riskvalues. While precipitation and runoff were expected to increase by less than10%, dam-released flood discharge was projected to surge by over 120% comparedto the baseline

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.31-49
• /
• 2023

With the growth of the food-catering industry, consumer preferences and the number of dine-in restaurants are gradually increasing. Thus, personalized recommendation services are required to select a restaurant suitable for consumer preferences. Previous studies have used questionnaires and star-rating approaches, which do not effectively depict consumer preferences. Online reviews are the most essential sources of information in this regard. However, previous studies have aggregated online reviews into long documents, and traditional machine-learning methods have been applied to these to extract semantic representations; however, such approaches fail to consider the surrounding word or context. Therefore, this study proposes a novel review textual-based restaurant recommendation model (RT-RRM) that uses deep learning to effectively extract consumer preferences from online reviews. The proposed model concatenates consumer-restaurant interactions with the extracted high-level semantic representations and predicts consumer preferences accurately and effectively. Experiments on real-world datasets show that the proposed model exhibits excellent recommendation performance compared with several baseline models.

• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.67-76
• /
• 2024

Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.

• Progress in Medical Physics
• /
• v.26 no.3
• /
• pp.119-126
• /
• 2015

The purpose of this study is to analyze motion-induced dose error generated by each tumor motion parameters of irregular tumor motion in helical tomotherapy. To understand the effect of the irregular tumor motion, a simple analytical model was simulated. Moving cases that has tumor motion were divided into a slightly irregular tumor motion case, a large irregular tumor motion case and a patient case. The slightly irregular tumor motion case was simulated with a variability of 10% in the tumor motion parameters of amplitude (amplitude case), period (period case), and baseline (baseline case), while the large irregular tumor motion case was simulated with a variability of 40%. In the phase case, the initial phase of the tumor motion was divided into end inhale, mid exhale, end exhale, and mid inhale; the simulated dose profiles for each case were compared. The patient case was also investigated to verify the motion-induced dose error in 'clinical-like' conditions. According to the simulation process, the dose profile was calculated. The moving case was compared with the static case that has no tumor motion. In the amplitude, period, baseline cases, the results show that the motion-induced dose error in the large irregular tumor motion case was larger than that in the slightly irregular tumor motion case or regular tumor motion case. Because the offset effect was inversely proportion to irregularity of tumor motion, offset effect was smaller in the large irregular tumor motion case than the slightly irregular tumor motion case or regular tumor motion case. In the phase case, the larger dose discrepancy was observed in the irregular tumor motion case than regular tumor motion case. A larger motion-induced dose error was also observed in the patient case than in the regular tumor motion case. This study analyzed motion-induced dose error as a function of each tumor motion parameters of irregular tumor motion during helical tomotherapy. The analysis showed that variability control of irregular tumor motion is important. We believe that the variability of irregular tumor motion can be reduced by using abdominal compression and respiratory training.

• The Journal of Korean Academy of Prosthodontics
• /
• v.46 no.2
• /
• pp.169-174
• /
• 2008

Statement of problem: Changes of the marginal bone around dental implants have significance not only for the functional maintenance but also for the esthetic success of the implant. It was proposed that bone-retention elements such as microthreads at the coronal part of implant might help maintain the marginal bone level. Purpose: This study was designed to evaluate the effect of microthread configuration within the marginal coronal portion of the implant fixture at the marginal bone changes after loading around two different external hex implants. Material and methods: Twenty-four patients were included and randomly assigned to treatment with $Br{{\aa}}nemark$ system implants (Group 1, rough-surfaced implants, n=20) and Oneplant system implants (Group 2, rough-surfaced neck with microthreads, n=20). Clinical and radiographic examinations were conducted at baseline (implant loading) and 1 year postloading. Data analysis was performed by the SAS statistical package version 9.1.3 (SAS Institute, Cary, NC, USA) and the final model was calculated by the MIXED procedure (three-level ANCOVA) for marginal bone change of each test group at baseline and 1 year follow-up. Results: Comparing to baseline, significant differences were noted in marginal bone level changes for the 2 groups at 1 year follow-up (P<0.05). Group 1 had a mean crestal bone level changes of $0.83{\pm}0.31mm$; Group 2 had a mean crestal bone level changes of $0.44{\pm}0.36mm$. Rough-surfaced with microthreads implants showed significantly less marginal bone loss than rough surfaced neck without microthread implants. Conclusion: A rough surface with microthreads at the implant was beneficial design to maintain the marginal bone level against functional loading.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.1 no.2
• /
• pp.1-15
• /
• 1997

This paper presents substructural identification methods for the assessment of local damages in complex and large structural systems. For this purpose, an auto-regressive and moving average with stochastic input (ARMAX) model is derived for a substructure to process the measurement data impaired by noises. Using the substructural methods, the number of unknown parameters for each identification can be significantly reduced, hence the convergence and accuracy of estimation can be improved. Secondly, the damage index is defined as the ratio of the current stiffness to the baseline value at each element for the damage assessment. The indirect estimation method was performed using the estimated results from the identification of the system matrices from the substructural identification. To demonstrate the proposed techniques, several simulation and experimental example analyses are carried out for structural models of a 2-span truss structure, a 3-span continuous beam model and 3-story building model. The results indicate that the present substructural identification method and damage estimation methods are effective and efficient for local damage estimation of complex structures.

• IMMUNE NETWORK
• /
• v.2 no.3
• /
• pp.158-165
• /
• 2002

Background: Toluene diisocyanate (TDI) can cause contact allergy and occupational asthma, but the mechanism underlying sensitization to this chemical compound remains controversal. Also the correlation of mast cell with contact hypersensitivity (CHS) and the role of mast cell in the TDI-induced CHS is unknown. This issue was investigated by administrating TDI on the skin of genetically mast cell-deficient WBB6F1/$J-Kit^{W}/Kit^{W-v}$ ($W/W^{V}$) and congenic normal WBB6F1/J-Kit+/+ (+/+) mice. Methods: To development of animal model of TDI-induced CHS and to investigate the correlation of mast cell with CHS and the role of mast cell in the TDI-induced CHS, $W/W^V$ and +/+ mice were sensitized with TDI on the back skin at day 1 and day 8, and then challenged with 1% TDI on the ear at day 15. At 1, 2, 4, 8, and 24 hours after 1% TDI challenge, the ear thicknesses were measured. It was investigated the histologic changes of dermis in the ear of $W/W^V$ and +/+ mice at 24 hours after 1% TDI challenge. Results: TDI induced a significant ear swelling response in $W/W^V$ and +/+ mice. TDI induced the significant infiltrations of polymorphonuclear leukocytes and eosinophils in $W/W^V$ and +/+ mice, but not of mast cells in normal mice. And TDI increased a characteristic extent of mast cell degranulation in normal mice. There were no significant differences in the ear swelling and the infiltrations of polymorphonuclear leukocytes and eosinophils of normal versus $W/W^V$ mice, either at baseline or after TDI-induced CHS. Conclusion: From the above results, TDI can be used as a murine CHS model, and the mast cells may not be essential in TDI-induced CHS.