• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.29 no.1
• /
• pp.1-8
• /
• 2021

Low level wind shear, which often occurs at Jeju International Airport, is a phenomenon that occurs when the topological location and topographical characteristics of Jeju Island are combined with weather characteristics. Low level wind shears, which are caused by rapid changes in wind direction and wind speed, pose a threat to aircraft safety and also cause abnormal situations, such as aircraft go-around, diversion, and cancellation. Many meteorological studies have been conducted on weather patterns, occurrence periods and frequency of low level wind shears. However, researches related to aircraft operations are limited where here we study the similarities and differences between strong southwest winds and bidirectional tailwind type low level wind shears based on aircraft go-around cases at Jeju International Airport. The results are expected to be used to enhance safety when operating to Jeju International Airport, which includes pilot training that reflects the characteristics generated by wind changes, pilot prior notification, providing pilots with latest trends, and increasing extra fuel.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1114-1121
• /
• 2021

In this paper, we implement a recipe recommendation system using ingredient harmonization analysis based on recipe data. The proposed system receives an image of a food ingredient purchase receipt to recommend ingredients and recipes to the user. Moreover, it performs preprocessing of the receipt images and text extraction using the OCR algorithm. The proposed system can recommend recipes based on the combined data of ingredients. It collects recipe data to calculate the combination for each food ingredient and extracts the food ingredients of the collected recipe as training data. And then, it acquires vector data by learning with a natural language processing algorithm. Moreover, it can recommend recipes based on ingredients with high similarity. Also, the proposed system can recommend recipes using replaceable ingredients to improve the accuracy of the result through preprocessing and postprocessing. For our evaluation, we created a random input dataset to evaluate the proposed recipe recommendation system's performance and calculated the accuracy for each algorithm. As a result of performance evaluation, the accuracy of the Word2Vec algorithm was the highest.

• Journal of the Korean Society of Physical Medicine
• /
• v.17 no.1
• /
• pp.63-74
• /
• 2022

PURPOSE: This study aimed to compare the effects of manual therapy with stabilization exercises to manual therapy alone, on neck pain and body functions in patients with chronic mechanical neck pain. METHODS: Twenty patients with chronic mechanical neck pain were recruited and randomly allocated into two groups. A control group(n = 10) was given the manual therapy alone and an experimental group(n = 10) was given the manual therapy with stabilization exercises. The intervention was carried out 3 days per week for 4 weeks. The cervical resting pain, the most painful motion pain, craniocervical flexor endurance, forward head posture and neck disability index were used to assess participants at baseline and after 4 weeks. RESULTS: A comparison of the parameters before and after the intervention showed that both groups experienced significant improvements in the resting pain, the most painful motion pain, craniocervical flexor endurance, and forward head posture except for the forward head posture in the control group. A comparison of the parameters between the groups did not show a significant difference. CONCLUSION: The results of this study suggest that the combined intervention of manual therapy with stabilization exercise does not seem to be more effective than manual therapy alone for improving neck pain, craniocervical flexor endurance, forward head posture, and the neck disability index in patients with chronic mechanical neck pain.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.644-649
• /
• 2021

Self-Imitation Learning is a simple off-policy actor-critic algorithm that makes an agent find an optimal policy by using past good experiences. In case that Self-Imitation Learning is combined with reinforcement learning algorithms that have actor-critic architecture, it shows performance improvement in various game environments. However, its applications are limited to reinforcement learning algorithms that have actor-critic architecture. In this paper, we propose a method of applying Self-Imitation Learning to Deep Q-Network which is a value-based deep reinforcement learning algorithm and train it in various game environments. We also show that Self-Imitation Learning can be applied to Deep Q-Network to improve the performance of Deep Q-Network by comparing the proposed algorithm and ordinary Deep Q-Network training results.

• Geomechanics and Engineering
• /
• v.30 no.2
• /
• pp.107-121
• /
• 2022

Coal pillar assessment is of broad importance to underground engineering structure, as the pillar failure can lead to enormous disasters. Because of the highly non-linear correlation between the pillar failure and its influential attributes, conventional forecasting techniques cannot generate accurate outcomes. To approximate the complex behavior of coal pillar, this paper elucidates a new idea to forecast the underground coal pillar stability using combined unsupervised-supervised learning. In order to build a database of the study, a total of 90 patterns of pillar cases were collected from authentic engineering structures. A state-of-the art feature depletion method, t-distribution symmetric neighbor embedding (t-SNE) has been employed to reduce significance of actual data features. Consequently, an unsupervised machine learning technique K-mean clustering was followed to reassign the t-SNE dimensionality reduced data in order to compute the relative class of coal pillar cases. Following that, the reassign dataset was divided into two parts: 70 percent for training dataset and 30 percent for testing dataset, respectively. The accuracy of the predicted data was then examined using support vector classifier (SVC) model performance measures such as precision, recall, and f₁-score. As a result, the proposed model can be employed for properly predicting the pillar failure class in a variety of underground rock engineering projects.

• Physical Therapy Rehabilitation Science
• /
• v.11 no.1
• /
• pp.78-87
• /
• 2022

Objective: The purpose of this study was to investigate the effect of high-intensity complex exercise program using whole-body vibration (WBV) and respiratory resistance on pain and dysfunction, psychosocial level, balance ability, and pulmonary function in low back pain (LBP) patients with high obesity. Design: A randomized controlled trial Methods: A total of 44 LBP patients withhigh obesity (body mass index, BMI≥30kg/m²) were randomly assigned to an experimental group (n=22) and a control group (n=22). Both groups underwent a lumbar stabilization exercise program. In addition, the experimental group implemented the high-intensity complex exercise program combined with WBV and respiratory resistance. In order to compare the effects depending on the intervention methods, numeric pain rating scale (NRPS), Roland-Morris disability questionnaire (RMDQ), fear-avoidance beliefs questionnaire (FABQ), balance ability, and pulmonary function were used for measurement. Results: Both groups showed significant differences in NRPS, RMDQ, FABQ, balance ability before and after intervention (p<0.05). In addition, the experimental groupshowed significant difference in the amount of change in RMDQ, balance ability and pulmonary function values than the control group (p<0.05). Conclusions: High-intensity complex exercise program using WBV and respiratory resistance has been proven to be an effective and clinically useful method to decrease dysfunction, increase balance ablilty, and pulmonary function for LBP patients with high obesity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3507-3522
• /
• 2022

Model pruning methods have attracted huge attention owing to the increasing demand of deploying models on low-resource devices recently. Most existing methods use the weight norm of filters to represent their importance, and discard the ones with small value directly to achieve the pruning target, which ignores the contribution of the small norm filters. This is not only results in filter contribution waste, but also gives comparable performance to training with the random initialized weights [1]. In this paper, we point out that the small norm filters can harm the performance of the pruned model greatly, if they are discarded directly. Therefore, we propose a novel filter contribution recycle (FCR) method for structured model pruning to resolve the fore-mentioned problem. FCR collects and reassembles contribution from the small norm filters to obtain a mixed contribution collector, and then assigns the reassembled contribution to other filters with higher probability to be preserved. To achieve the target FLOPs, FCR also adopts a weight decay strategy for the small norm filters. To explore the effectiveness of our approach, extensive experiments are conducted on ImageNet2012 and CIFAR-10 datasets, and superior results are reported when comparing with other methods under the same or even more FLOPs reduction. In addition, our method is flexible to be combined with other different pruning criterions.

• Child Health Nursing Research
• /
• v.29 no.1
• /
• pp.24-36
• /
• 2023

Purpose: This systematic literature review and meta-analysis explored extended reality (XR)-based pediatric nursing simulation programs and analyzed their effectiveness. Methods: A literature search was conducted between May 1 and 30, 2022 in the following electronic databases: MEDLINE, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), and CINAHL. The search period was from 2000 to 2022. In total, 6,095 articles were reviewed according to the inclusion and exclusion criteria, and 14 articles were selected for the final content analysis and 10 for the meta-analysis. Data analysis was performed using descriptive statistics and the Comprehensive Meta-Analysis program. Results: XR-based pediatric nursing simulation programs have increased since 2019. Studies using virtual reality with manikins or high-fidelity simulators were the most common, with six studies. The total effect size was statistically significant at 0.84 (95% confidence interval=0.50-1.19, z=4.82, p<.001). Conclusion: Based on the findings, we suggest developing standardized guidelines for the operation of virtual pediatric nursing simulation education and practice. Simultaneously, the application of more sophisticated research designs for effect measurement and the combined applications of various virtual simulation methods are needed to validate the most effective simulation methodology.

• Journal of Information Technology Applications and Management
• /
• v.29 no.3
• /
• pp.43-55
• /
• 2022

In this study, with the goal of developing a deep learning-based product recommendation model for effective matching of influencers and products, a deep learning model with a collaborative filtering model combined with generalized matrix decomposition(GMF), a collaborative filtering model based on multi-layer perceptron (MLP), and neural collaborative filtering and generalized matrix Factorization (NeuMF), a hybrid model combining GMP and MLP was developed and tested. In particular, we utilize one-class problem free boosting (OCF-B) method to solve the one-class problem that occurs when training is performed only on positive cases using implicit feedback in the deep learning-based collaborative filtering recommendation model. In relation to model selection based on overall experimental results, the MLP model showed highest performance with weighted average precision, weighted average recall, and f1 score were 0.85 in the model (n=3,000, term=15). This study is meaningful in practice as it attempted to commercialize a deep learning-based recommendation system where influencer's promotion data is being accumulated, pactical personalized recommendation service is not yet commercially applied yet.

• Journal of East-West Nursing Research
• /
• v.29 no.1
• /
• pp.49-58
• /
• 2023

Purpose: This study aimed to investigate the effects of personality, ego-resilience, and commitment to career choice on the adaptation to college among new nursing students residing in various regions. Methods: The participants were 175 freshmen in nursing departments at 7 universities located in D Metropolitan city. Data were collected through an online questionnaire from June 20, 2022 to July 1, 2022. The collected data were analyzed using descriptive statistics, t-test, one-way ANOVA, Scheffe's test, Pearson's correlation coefficient, and stepwise multiple regression analysis using IBM SPSS/WIN 28.0 software. Results: The average scores of participants were as follows: personality (4.10±0.41), ego-resilience (3.55±0.62), commitment to career choice (3.36±0.59), and adaptation to college (3.63±0.58). The factors influencing college adaptation were ego-resilience, personality, satisfaction with nursing major, and commitment to career choice. The combined explanatory power of these variables for college adaptation was 64.8%. Conclusion: This study highlights the necessity for developing educational programs, training initiatives, and curricular activities to enhance ego-resilience, foster appropriate personality, increase satisfaction with nursing major, and improve commitment to career choice levels among new nursing students residing in various regions.