• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.145-155
• /
• 2015

Noise reduction has been actively studied in the digital image processing and recently, block-based denoising algorithms are widely used. In particular, a low rank approximation employing WNNM(Weighted Nuclear Norm Minimization) and block-based approaches demonstrated the potential for effective noise reduction. However, the algorithm based on low rank a approximation generates the artifacts in the image restoration step. In this paper, we analyzes the image content using the STFT(Short Time Fourier Transform) and proposes an effective method of minimizing the artifacts generated from the conventional algorithm. To evaluate the performance of the proposed scheme, we use the test images containing a wide range of noise levels and compare the results with the state-of-art algorithms.

• Annals of Laboratory Medicine
• /
• v.38 no.6
• /
• pp.495-502
• /
• 2018

Background: Molecular genetic abnormalities are observed in over 90% of chronic myelomonocytic leukemia (CMML) cases. Recently, several studies have demonstrated the negative prognostic impact of ASXL1 mutations in CMML patients. We evaluated the prognostic impact of ASXL1 mutations and compared five CMML prognostic models in Korean patients with CMML. Methods: We analyzed data from 36 of 57 patients diagnosed as having CMML from January 2000 to March 2016. ASXL1 mutation analysis was performed by direct sequencing, and the clinical and laboratory features of patients were compared according to ASXL1 mutation status. Results: ASXL1 mutations were detected in 18 patients (50%). There were no significant differences between the clinical and laboratory characteristics of ASXL1-mutated ($ASXL1^+$) CMML and ASXL1-nonmutated ($ASXL1^-$) CMML patients (all P >0.05). During the median follow-up of 14 months (range, 0-111 months), the overall survival (OS) of $ASXL1^+$ CMML patients was significantly inferior to that of $ASXL1^-$ CMML patients with a median survival of 11 months and 19 months, respectively (log-rank P =0.049). An evaluation of OS according to the prognostic models demonstrated inferior survival in patients with a higher risk category according to the Mayo molecular model (log-rank P =0.001); the other scoring systems did not demonstrate a significant association with survival. Conclusions: We demonstrated that ASXL1 mutations, occurring in half of the Korean CMML patients examined, were associated with inferior survival. ASXL1 mutation status needs to be determined for risk stratification in CMML.

• Korean Journal of Child Education & Care
• /
• v.19 no.3
• /
• pp.183-197
• /
• 2019

Objective: The purpose of this study was to examine the effect of a group program using theraplay on 2-year-olds' prosocial behavior. The changes of prosocial behavior in the process of program were also examined. Methods: Subjects were 12 infants who attended a child care center in W city. Subjects were attached to the experimental or control group. The experimental group participated in 11 group theraplay sessions twice a week. The adaptive social behavior inventory (Hogan et al., 1992) was used for pre and post tests. Wilcoxon rank-sum test was performed to verify the effectiveness of a group theraplay program. Every sessions was video-taped and recorded verbatim. The verbatim were analyzed using the Padgett (2001)'s qualitative data analysis method. Results: Infants who assigned to the experimental group demonstrated significant improvement in prosocial behavior. Their expressive behavior and compliant behavior gradually increased over the sessions. Conclusion/Implications: The present study showed that the use of group program utilizing theraplay was an effective strategy for improving prosocial behavior of 2-year-old infants.

• Journal of Korean Academy of Dental Administration
• /
• v.7 no.1
• /
• pp.29-38
• /
• 2019

The goals of this study were to investigate depression and oral health-related quality of life in the military and public and to identify the factors affecting depression. The respondents were 278 soldiers and 228 general people of similar ages. An independent t-test was used to examine the differences between the two groups in the oral health impact profile and Self-rating Depression Scale. A multivariate logistic regression analysis was performed to examine the factors associated with depression in soldiers and the public. The depression level was significantly higher in the general population than in the military personnel (p<0.001). In contrast, the oral health-related quality of life was better in the general population than in the military, but without a statistical significance (p=0.056). Among soldiers, the military rank was the only factor associated with depression, showing a gradient based on the rank. In the general population, the type of work displayed significant associations with depression. As there are some limitations to investigating the factors affecting depression, comparative analyses of the general population groups with similar soldier groups are rare. This study encourages future investigations of the advancements in mental health and improvement programs for oral health in each group.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.39-46
• /
• 2021

This study is about a method of extracting a summary from a news article in consideration of the importance of each sentence constituting the article. We propose a method of calculating sentence importance by extracting the probabilities of topic sentence, similarity with article title and other sentences, and sentence position as characteristics that affect sentence importance. At this time, a hypothesis is established that the Topic Sentence will have a characteristic distinct from the general sentence, and a deep learning-based classification model is trained to obtain a topic sentence probability value for the input sentence. Also, using the pre-learned ELMo language model, the similarity between sentences is calculated based on the sentence vector value reflecting the context information and extracted as sentence characteristics. The topic sentence classification performance of the LSTM and BERT models was 93% accurate, 96.22% recall, and 89.5% precision, resulting in high analysis results. As a result of calculating the importance of each sentence by combining the extracted sentence characteristics, it was confirmed that the performance of extracting the topic sentence was improved by about 10% compared to the existing TextRank algorithm.

• Korean Journal of Head & Neck Oncology
• /
• v.37 no.2
• /
• pp.25-31
• /
• 2021

Background/Objectives: Although thyroid lobectomy recently is considered as sufficient for low-risk papillary thyroid carcinoma (PTC), completion thyroidectomy is required due to the insufficiency of the preoperative evaluation. The aim of this study was to investigate recurrence rate and disease free survival depending on the gross extrathyroidal extension (gETE) or the number of metastatic lymph node identified in patients with PTC. Materials & Methods: We assessed 3373 patients with PTC who underwent lobectomy at Seoul St. Mary's Hospital (Seoul, Korea) between January 2009 and December 2014. Clinicopathological characteristics and long-term surgical outcomes were retrospectively analyzed through complete chart reviews. The mean follow-up duration was 97.1 ± 21.4 months. Results: The rate of recurrence was higher in gETE group (1.8% vs. 6.0%, p=0.004), leading to decreased disease free survival in Kaplan-Meier analysis (log-rank p<0.001). N1 group (n=1389) was analyzed into two groups whether the number of positive nodes is more than 5 or less. For the group of the more metastatic nodes, the recurrence rate higher compared to the other group (3.0% vs. 9.3%, p<0.001). DFS was longer in the group that had lesser metastatic nodes (log-rank p<0.001). However, in terms of N1 group over 1cm (n=492), No statistical difference was observed according to the number of positive lymph nodes (4.5% vs. 9.1%, p=0.092) Conclusion: When it comes to node positive PTC, Despite the number of positive lymph nodes was over 5, follow-up with no further surgery can be an option.

• Journal of the Korea Convergence Society
• /
• v.13 no.4
• /
• pp.321-329
• /
• 2022

This study analyzes how companies of prospector type with inherent risks from new products and R&D costs affect audit hours, and further analyzes how they affect rank-specific audit hours. Samples were empirically analyzed using samples from 2018 to 2019 for KOSPI-listed and KOSDAQ-listed companies. As a result of the analysis, first, it was found that auditors were aware of the inherent risks of companies of prospector type and were striving to improve audit quality. Second, it was found that the corresponding degree of risk differs depending on the position and role in the audit team, so higher efforts were made in core positions with high risk levels. The results of this study are meaningful in verifying how the type of Business Strategies affects the audit efforts and resource input of auditors who are external parties, not internal factors such as financial reporting quality or tax avoidance. It also has important implications that a company's Business Strategies can be an significant factor to consider in preparing policies and systems for improving audit quality.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.176-182
• /
• 2023

With about 80% of the global economy expected to shift to the global market by 2030, exports of reverse direct purchase products, in which foreign consumers purchase products from online shopping malls in Korea, are growing 55% annually. As of 2021, sales of reverse direct purchases in South Korea increased 50.6% from the previous year, surpassing 40 million. In order for domestic SMEs(Small and medium sized enterprises) to enter overseas markets, it is important to come up with export strategies based on various market analysis information, but for domestic small and medium-sized sellers, entry barriers are high, such as lack of information on overseas markets and difficulty in selecting local preferred products and determining competitive sales prices. This study develops an AI-based product recommendation and sales price estimation model to collect and analyze global shopping malls and product trends to provide marketing information that presents promising and appropriate product sales prices to small and medium-sized sellers who have difficulty collecting global market information. The product recommendation model is based on the LTR (Learning To Rank) methodology. As a result of comparing performance with nDCG, the Pair-wise-based XGBoost-LambdaMART Model was measured to be excellent. The sales price estimation model uses a regression algorithm. According to the R-Squared value, the Light Gradient Boosting Machine performs best in this model.

• Journal of Korean Academy of Nursing
• /
• v.52 no.1
• /
• pp.36-51
• /
• 2022

Purpose: The purpose of this study was to examine the effects of electroencephalogram (EEG) biofeedback training for emotion regulation and brain homeostasis on anxiety about COVID-19 infection, impulsivity, anger rumination, meta-mood, and self-regulation ability of late adolescents in the prolonged COVID-19 pandemic situation. Methods: A non-equivalent control group pretest-posttest design was used. The participants included 55 late adolescents in the experimental and control groups. The variables were evaluated using quantitative EEG at pre-post time points in the experimental group. The experimental groups received 10 sessions using the three-band protocol for five weeks. The collected data were analyzed using the Shapiro-Wilk test, Wilcoxon rank sum test, Wilcoxon signed-rank test, t-test and paired t-test using the SAS 9.3 program. The collected EEG data used a frequency series power spectrum analysis method through fast Fourier transform. Results: Significant differences in emotion regulation between the two groups were observed in the anxiety about COVID-19 infection (W = 585.50, p = .002), mood repair of meta-mood (W = 889.50, p = .024), self-regulation ability (t = - 5.02, p < .001), self-regulation mode (t = - 4.74, p < .001), and volitional inhibition mode (t = - 2.61, p = .012). Neurofeedback training for brain homeostasis was effected on enhanced sensory-motor rhythm (S = 177.00, p < .001) and inhibited theta (S = - 166.00, p < .001). Conclusion: The results demonstrate the potential of EEG biofeedback training as an independent nursing intervention that can markedly improve anxiety, mood-repair, and self-regulation ability for emotional distress during the COVID-19 pandemic.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.113-124
• /
• 2023

With the advent of 5G and B5G (Beyond 5G) networks, network virtualization technology that can overcome the limitations of existing networks is attracting attention. The purpose of network virtualization is to provide solutions for efficient network resource utilization and various services. Existing heuristic-based VNE (Virtual Network Embedding) techniques have been studied, but the flexibility is limited. Therefore, in this paper, we propose a GNN-based network slicing classification scheme to meet various service requirements and a RL-based VNE scheme for optimal resource allocation. The proposed method performs optimal VNE using an Actor-Critic network. Finally, to evaluate the performance of the proposed technique, we compare it with Node Rank, MCST-VNE, and GCN-VNE techniques. Through performance analysis, it was shown that the GNN and RL-based VNE techniques are better than the existing techniques in terms of acceptance rate and resource efficiency.