• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.119-126
• /
• 2023

In this paper, a new model was presented to objectively evaluate the defense ability of defenders in Korean professional baseball. In the proposed model, using Korean professional baseball game data from 2016 to 2019, a representative defender was selected for each team and defensive position to evaluate defensive ability. In order to evaluate the defense ability, a method of calculating the defense range for each position and dividing the calculated defense area was proposed. The defensive range for each position was calculated using the Convex Hull algorithm based on the point at which the defenders in the same position threw out the ball. The out conversion score and victory contribution score for both infielders and outfielders were calculated as basic scores using the defensive range for each position. In addition, double kill points for infielders and extra base points for outfielders were calculated separately and added together.

• Informatization Policy
• /
• v.30 no.3
• /
• pp.69-91
• /
• 2023

The impact of technological advancements on employment is a matter of ongoing debate, with discussions on the effects of AI technology development on employment being particularly scarce. This study employs the natural language processing technique (SBERT) and patents to calculate an occupation-based AI exposure score and to analyze employment trends by group. It proposes a method for calculating the AI exposure score based on the similarity between Korean patent information and US job descriptions and linking SOC(U.S.) and KSCO(Korea). The analysis of domestic AI patent applications and regional employment data in the KOSIS Database since 2013 reveals a K-shaped polarization pattern in Korean employment trends among groups with above and below average levels of AI exposure.

• Journal of Preventive Medicine and Public Health
• /
• v.57 no.2
• /
• pp.120-127
• /
• 2024

Objectives: The coronavirus disease 2019 (COVID-19) pandemic led to increased mortality rates. To assess this impact, this ecological study aimed to estimate the excess death counts in southern Iran. Methods: The study obtained weekly death counts by linking the National Death Registry and Medical Care Monitoring Center repositories. The P-score was initially estimated using a simple method that involved calculating the difference between the observed and expected death counts. The interrupted time series analysis was then used to calculate the mean relative risk (RR) of death during the first year of the pandemic. Results: Our study found that there were 5571 excess deaths from all causes (P-score=33.29%) during the first year of the COVID-19 pandemic, with 48.03% of these deaths directly related to COVID-19. The pandemic was found to increase the risk of death from all causes (RR, 1.26; 95% confidence interval [CI], 1.19 to 1.33), as well as in specific age groups such as those aged 35-49 (RR, 1.21; 95% CI, 1.12 to 1.32), 50-64 (RR, 1.38; 95% CI, 1.28 to 1.49), and ≥65 (RR, 1.29; 95% CI, 1.12 to 1.32) years old. Furthermore, there was an increased risk of death from cardiovascular diseases (RR, 1.17; 95% CI, 1.11 to 1.22). Conclusions: There was a 26% increase in the death count in southern Iran during the COVID-19 pandemic. More than half of these excess deaths were not directly related to COVID-19, but rather other causes, with cardiovascular diseases being a major contributor.

• Journal of The Korean Society of Integrative Medicine
• /
• v.12 no.1
• /
• pp.97-108
• /
• 2024

Purpose : In this study, we aimed to determine the impact of the COVID-19 pandemic on nursing students' adjustment to college life by focusing on their empathic ability, perceived stress, and resilience. Methods : We applied a descriptive survey research design, which included a self-report questionnaire. The participants comprised 307 nursing students in B city. The data were analyzed by calculating the percentages, means, standard deviations, t-tests, ANOVA, Scheffé test, Pearson's correlation coefficients, and hierarchical regression using SPSS 23.0. Results : The participants' empathic ability score was 3.30±.42, perceived stress score 1.85±.49, resilience score 3.44±.64, and adjustment to college life score 3.25±.52. Adjustment to college life was positively correlated with resilience (r=.43, p<.001) but negatively correlated with perceived stress (r=.27, p<.001). Factors affecting adjustment to college life include, among general characteristics in Model 1, in descending order, major satisfaction-satisfied (β=.54, p<.001), interpersonal conflict: never (β=.26, p=.018), health status: healthy (β=.25, p=.002), character: positive (β=.21, p=.006), character: optimistic (β=.19, p=.015), parents' economic power: high (β=.15, p=.047), and gender: male (β=.11, p=.016). Model 1 was statistically significant (F=11.67, p<.001), and the explanatory power was 41 %. In Model 2, empathic ability, perceived stress, and resilience were added as independent variables. When including the dependent variables, the factors that most influenced adjustment to college life were perceived stress (β=-.37, p<.001), major satisfaction-satisfied (β=.36, p<.001), health status-healthy (β=.25, p<.001), gender-male (β=.10, p=.015), and resilience (β=.10, p=.029). Model 2 was statistically significant (F=17.65, p<.001), and the explanatory power was 56 %. Conclusion : We found that gender, major satisfaction, health status, perceived stress, and resilience affected adjustment to college life among nursing students who had experienced the COVID-19 pandemic. To increase their ability to adjust to college life, a gender-specific intervention program should be developed that can improve the students' health status, major satisfaction and resilience, and reduce their perceived stress.

• Korean Journal of Agricultural Science
• /
• v.49 no.4
• /
• pp.837-845
• /
• 2022

In this study, tomato maturity was estimated based on deep learning for a harvesting robot. Tomato images were obtained using a RGB camera installed on a monitoring robot, which was developed previously, and the samples were cropped to 128 × 128 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the mean-variance loss was used to learn implicitly the distribution of the data features by class. In the test stage, the tomato maturity was estimated as a continuous index, which has a range of 0 to 1, by calculating the expected class value. The results show that the F1-score of the classification was approximately 0.94, and the performance was similar to that of a deep learning-based classification task in the agriculture field. In addition, it was possible to estimate the distribution in each maturity stage. From the results, it was found that our approach can not only classify the discrete maturation stages of the tomatoes but also can estimate the continuous maturity.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.707-720
• /
• 2021

To improve the accuracy of the recommendation system, multi-criteria recommendation systems have been widely researched. However, it is highly complicated to extract the preferred features of users and items from the data. To this end, subjective indicators, which indicate a user's priorities for personalized recommendations, should be derived. In this study, we propose a method for generating recommendation candidates by predicting multi-criteria ratings from reviews and using them to derive user priorities. Using a deep learning model based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), multi-criteria prediction ratings were derived from reviews. These ratings were then aggregated to form a linear regression model to predict the overall rating. This model not only predicts the overall rating but also uses the training weights from the layers of the model as the user's priority. Based on this, a new score matrix for recommendation is derived by calculating the similarity between the user and the item according to the criteria, and an item suitable for the user is proposed. The experiment was conducted by collecting the actual "TripAdvisor" dataset. For performance evaluation, the proposed method was compared with a general recommendation system based on singular value decomposition. The results of the experiments demonstrate the high performance of the proposed method.

• Journal of Korean Neurosurgical Society
• /
• v.60 no.5
• /
• pp.540-549
• /
• 2017

Objective : To evaluate the diagnostic value of computed tomography-myelography (CTM) compared to that of magnetic resonance imaging (MRI) in patients with lumbar radiculopathy. Methods : The study included 91 patients presenting with radicular leg pain caused by herniated nucleus pulposus or lateral recess stenosis in the lumbar spine. The degree of nerve root compression on MRI and CTM was classified into four grades. The results of each imaging modality as assessed by two different observers were compared. Visual analog scale score for pain and electromyography result were the clinical parameters used to evaluate the relationships between clinical features and nerve root compression grades on both MRI and CTM. These relationships were quantified by calculating the receiver-operating characteristic curves, and the degree of relationship was compared between MRI and CTM. Results : McNemar's test revealed that the two diagnostic modalities did not show diagnostic concurrence (p<0.0001). Electromyography results did not correlate with grades on either MRI or CTM. The visual analog pain scale score results were correlated better with changes of the grades on CTM than those on MRI (p=0.0007). Conclusion : The present study demonstrates that CTM could better define the pathology of degenerative lumbar spine diseases with radiculopathy than MRI. CTM can be considered as a useful confirmative diagnostic tool when the exact cause of radicular pain in a patient with lumbar radiculopathy cannot be identified by using MRI. However, the invasiveness and potential complications of CTM are still considered to be pending questions to settle.

• Journal of Korea Multimedia Society
• /
• v.23 no.5
• /
• pp.625-632
• /
• 2020

In the diagnosis of lung cancer, the tumor size is measured by the longest diameter of the tumor in the entire slice of the CT. In order to accurately estimate the size of the tumor, it is better to measure the volume, but there are some limitations in calculating the volume in the clinic. In this study, we propose an algorithm to segment lung cancer by applying a custom loss function that combines focal loss and dice loss to a U-Net model that shows high performance in segmentation problems in chest CT images. The combination of values of the various parameters in custom loss function was compared to the results of the model learned. The purposed loss function showed F1 score of 88.77%, precision of 87.31%, recall of 90.30% and average precision of 0.827 at α=0.25, γ=4, β=0.7. The performance of the proposed custom loss function showed good performance in lung cancer segmentation.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.561-568
• /
• 2022

Most deep learning-based video object segmentation methods perform the segmentation with past prediction information stored in external memory. In general, the more past information is stored in the memory, the better results can be obtained by accumulating evidence for various changes in the objects of interest. However, all information cannot be stored in the memory due to hardware limitations, resulting in performance degradation. In this paper, we propose a method of storing new information in the external memory without additional memory allocation. Specifically, after calculating the attention score between the existing memory and the information to be newly stored, new information is added to the corresponding memory according to each score. In this way, the method works robustly because the attention mechanism reflects the object changes well without using additional memory. In addition, the update rate is adaptively determined according to the accumulated number of matches in the memory so that the frequently updated samples store more information to maintain reliable information.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.28 no.2
• /
• pp.113-119
• /
• 2024

Existing reinforced concrete buildings with seismically deficient column details affect the overall behavior depending on the failure type of column. This study aims to develop and validate a machine learning-based prediction model for the column failure modes (shear, flexure-shear, and flexure failure modes). For this purpose, artificial neural network (ANN), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) models were used, considering previously collected experimental data. Using four machine learning methodologies, we developed a classification learning model that can predict the column failure modes in terms of the input variables using concrete compressive strength, steel yield strength, axial load ratio, height-to-dept aspect ratio, longitudinal reinforcement ratio, and transverse reinforcement ratio. The performance of each machine learning model was compared and verified by calculating accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model represents the highest average value of the classification model performance measurements among the considered learning methods, and it can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with simple column details.