Earticle

교통카드 데이터는 다양한 대중교통 통계 지표 산출, 정책 및 평가를 위한 자료로 활용되어 그 활용범위가 상당히 높다. 그러나 교통카드 데이터 내 주요 문제점은 하차 정류장에서 태그 를 안 하고 하차하는 경우가 대부분으로 이는 교통카드 이용자의 불완전한 OD 통행 자료로 활용범위에 있어 한계가 있다. 본 연구는 의사결정 모델 기반 교통카드 데이터 하차 정류장 추정 방법을 적용한 결과 오차 범위 2개 정류장 이하에서 하차 정류장 추정 정확도는 89.7%으 로 분석되었다. 이를 통하여 교통카드 데이터의 불완전성을 해소함으로써 다양한 대중교통 분 석 및 평가 등에 대한 기초 자료로 활용 될 수 있을 것으로 판단된다.

Smartcards are used as the basic data for utilizing the various transportation policies and evaluations, etc. and provided the transportation basic statistics index. However, the main problem of the smartcard data is that the most of users do not take the alighting tag at the stop, so there is a limit to the scope of use for the total O-D trip data because incomplete O-D traffic data of transportation card users. In this study, a decision tree of learning model is estimated for the alighting stop of smartcard users. The model estimation accuracy in range less than 2 stops interval was 89.7% on average. By eliminating the incompleteness alighting stop of smartcard data through this model, it is expected to be used as the basic data for various transportation analyses and evaluations.

2018년부터 기후변화에 따른 폭염과 한파에 의해 사회기반시설에 점증적으로 많은 피해를 미치고 있다. 최근 4년간 기후변화에 따른 영향 중에 냉해에 대한 피해가 매년 증가하여 특정 지역에 국한되었던 피해가 이제는 전국에 걸쳐서 나타나 고 있으며, 이를 최소화하기 위한 각계각층의 전문가들에 의한 노력이 집중되고 있다. 그러나 불연속적으로 측정되는 데이터 들 속에서 지역 특색을 반영하고자 하는 기존 연구들에서는 갑작스럽게 발생하는 이상 저온에 대한 실시간 관측 연구는 쉽지 않은 상황이다. 본 연구에서는 냉해 발생에 영향을 미치는 기상 데이터를 기준으로 냉해 피해가 발생하였던 시점의 기상 패턴 을 탐색한 후 이상저온 발생 시점을 확인할 수 있는 알고리즘 패턴 개발을 하였다. 본 연구의 결과물은 과거의 데이터에 의존 하지 않고 실시간으로 발생하는 데이터에 의한 이상저온이 발생한 시점을 시간 시점에서 확인할 수 있다는 점에서 지역적 기 상 편차를 의식하지 않고 확인이 가능하다는 점에서, 이상저온 발생 시점 데이터를 확보할 수 있다는 점에서 관련 분야에 많 은 도움이 될 것으로 기대할 수 있다.

Since 2018, due to climate change, heat waves and cold waves have caused gradual damage to social infrastructure. Since the damage caused by cold weather has increased every year due to climate change in recent 4 years, the damage that was limited to a specific area is now appearing all over the country, and a lot of efforts are being concentrated from experts in various fields to minimize this. However, it is not easy to study real-time observation of sudden abnormal low temperature in existing studies to reflect local characteristics in discontinuously measured data. In this study, based on the weather-related data that affects the occurrence of cold-weather damage, we developed an algorithm pattern that can identify the time when abnormal cold temperatures occurred after searching for weather patterns at the time of cold-weather damage. The results of this study are expected to be of great help to the related field in that it is possible to confirm the time when the abnormal low temperature occurs due to the data generated in real time without relying on the past data.

본 연구의 목적은 초등학교 컴퓨터 교과 교육을 위해 테크놀로지 기반 디지털 콘텐츠를 활용한 교수-학습 방 안을 모색해 보는 데 있다. 이에 본 연구에서는 프로젝트 학습에 관한 제이론을 고찰하고 이를 바탕으로 학습 모형을 고안하고 초등학교 교과 교육에 적합한 학습 시스템을 제안하였다. 본 연구의 학습 모형은 초등학교 컴 퓨터 교과의 학습 단계와 내용을 재구성하여 인지적 영역의 지식 및 이해 중심 학습 내용과 기능 중심 영역의 학습 내용 및 절차를 적용하여 구성하였다. 본 연구의 시사점 및 기대 효과를 제시하였다

The purpose of the present study was to explore the application of technology-based digital contents in the teaching and learning process to shed light on computer education in elementary schools. The study designed a learning model in light of the theoretical background with respect to project-based learning and developed a learning system for elementary computer education. The learning model was grounded on the reconstructed learning steps and contents of elementary computer curriculum and was composed of learning contents and procedures on the basis of cognitive areas of knowledge and understanding and functional skills of elementary computer curriculum. The implications and expected effects of the study were presented.

음악은 인류 문화의 중요한 산물로서 다양한 시대와 역사 속에서 전개, 발전하여 온 인문학의 중요한 부분이다. 이러한 맥락에서 음악 교과는 역사․문화적 배경 속에서의 학습을 강조하고 있는데, 구체적인 학습 방법으로 인물학습을 적용해 볼 수 있다. 인물학습은 인물의 생애나 가치관 등을 학습하고, 나아가 인물이 살던 역사․사회적 배경과 관련하여 인물을 고찰할 수 있기 때문이다. 음악 교과에서의 인물학습은 제재곡과 관계된 인물의 삶을 통하여 그가 제재곡을 통해 말하고자 했던 정신적 가치를 발견하고 내면화하는 활동으로 구체화되어야 한다. 이에 본 연구에서는 중학교 학생을 대상으로 국악에서 역사․문화적 가치 이해를 위해 인물학습을 구현하는 방안을 모색해 보았다. 먼저, 음악 교과에서 강조하고 있는 인물학습의 내용 및 방법을 밝히고자 2015 개정 음악과 교육과정을 고찰하였다. 음악과에서 인물학습은 악곡을 중심으로 음악의 역할과 가치에 대한 안목을 키우도록 강조하고 있으며, 악곡의 배경을 파악하여 이해하고 비평하는 활동이 필요함을 알 수 있었다. 이에 음악과의 각 영역에서 인물을 중심으로 음악적 지식을 심화시켜, 악곡에 대한 흥미를 불러일으킬 수 있는 학습경험이 중심이 되는 학습모형을 조직하였다. 이러한 모형에 따라 문묘제례악으로 대표되는 아악의 정비가 우리나라 음악의 형성에 미친 영향과 관련하여 조선 전기 박연의 음악 업적을 학습하도록 적용하였다. 이를 바탕으로 박연이 우리나라의 음악 형성에 미친 영향과 가치를 내면화할 수 있도록 학습 내용을 선정하고 학습 방법을 제시하였다. 본 연구는 음악에 담긴 가치를 내면화하기 위한 방법으로 인물학습을 활용해보고자 하는 고민의 시작이다. 본질적인 음악과의 인물학습 방법에 관한 구체적인 논의는 이후 계속되어야 할 것이다.

Music is an important product of human culture and it is an important part of the humanities that have evolved and developed in various periods and histories. In this context, the music subject emphasizes learning in a historical and cultural context. Figure learning can be applied as a concrete learning method. Because Figure learning can learn the life and the value of the character, and can be considered in relation to the history and social background of the character. In the music subject, Figure learning should be embodied in the activity of discovering and internalizing the spiritual value that he wanted to say through the life of the character related to the music. In this study, I tried to find out how to implement the Figure learning for understanding the historical and cultural values in Korean music for middle school students. First, I tried to clarify the content and method of Figure learning which is emphasized in music subjects, I reviewed the Revised Curriculum of 2015. In the music subjects, Figure learning emphasizes raising to discernment of the role and value of the music, I understood that need to understand and criticize the background of music. Therefore, I made a learning model, that focuses on the learning experience that can intensify the musical knowledge centered on the character and bring about interest in the music. From this model, I applied to learn that encouraged to study the musical achievements of Park-Yeon of the early Chosun Dynasty in relation to the refinement of the Aak represented by Munmyo Jereak on the formation of Korean music. Based on this, I selected learning contents and organized learning method to internalization the influence and value of Korean music formation of Park-Yeon. This study is the beginning of a series of studies aimed at using Figure learning as a way to interiorize the value of music. The specific discussion on how to Figure learning of the music subject should continue to follow.

Purpose: This study aimed to develop a machine learning (ML)-based predictive model for hospitallength of stay incorporating clinical, nursing, and healthcare system factors to optimize hospitalresource allocation, improve patient-centered care, and enhance nursing workflow efficiency. Methods: This retrospective study analyzed a large dataset of inpatient electronic medical records froma private tertiary hospital. The dataset was used to develop predictive models for long-term versusshort-term hospitalization. The modeling process involved several ML algorithms, and their performancewas evaluated using standard statistical metrics. The most significant predictive variables wereidentified through an analysis of their feature importance. Results: Among the tested models, the Random Forest algorithm exhibited the highest predictive accuracy,demonstrating strong performance in predicting hospital length of stay. Key influencing factorsincluded the number of consultations, postoperative recovery time, duration of stay in the intensive careunit, the use of third-generation antibiotics, and the need for infection isolation. Patients requiringventilator care, intensive care unit admission, and specific powerful antibiotics were more likely toexperience prolonged hospitalization. Additionally, nursing-related factors such as fall risk and pressureulcer risk were significantly correlated with an extended hospital stay. Conclusion: This study demonstrates that ML models can effectively predict hospital length of stay,aiding in hospital resource management, nursing workforce allocation, and patient safety interventions. The integration of predictive analytics into healthcare systems can support early risk assessment,personalized discharge planning, and overall hospital efficiency.

Activity recognition in sports is often complex task resulting from the rapid dynamic interaction within players. In this paper, pre-trained VGG-16, deep learning based hockey activity recognition model has been proposed. Own hockey dataset consisting of four main activity includes free hit, goal, penalty corner and long corner was constructed as there are no existing field hockey datasets available. Experimental results indicate that the pre-trained deep learning model generates comparative results on this challenging dataset by tweaking the hyperparameters of this pre-trained model.

Purpose: The purposes of this study were to develop a prediction model for pressure injury using a machine learning algorithm and to integrate it into clinical practice. Methods: This was a retrospective study of tertiary hospitals in Seoul, Korea. It analyzed patients in 12 departments where many pressure injuries occurred, including 8 general wards and 4 intensive care units from January 2018 to May 2022. In total, 182 variables were included in the model development. A pressure injury prediction model was developed using the gradient boosting algorithm, logistic regression, and decision tree methods, and it was compared to the Braden scale. Results: Among the 1,389,660 general ward cases, there were 451 cases of pressure injuries, and among 139,897 intensive care unit cases, there were 297 cases of pressure injuries. Among the tested prediction models, the gradient boosting algorithm showed the highest predictive performance. The area under the receiver operating characteristic curve of the gradient boosting algorithm's pressure injury prediction model in the general ward and intensive care unit was 0.86 (95% confidence interval, 0.83~0.89) and 0.83 (95% confidence interval, 0.79~0.87), respectively. This model was integrated into the electronic health record system to show each patient's probability for pressure injury occurrence, and the risk factors calculated every hour. Conclusion: The prediction model developed using the gradient boosting algorithm exhibited higher performance than the Braden scale. A clinical decision support system that automatically assesses pressure injury risk allows nurses to focus on patients at high risk for pressure injuries without increasing their workload.

Orthogonal Time Frequency Space (OTFS), characterized by its unique time-frequency orthogonality, has demonstrated significant advantages in overcoming the difficulties caused by time-varying channels in wireless communications. To realize the full capabilities of OTFS, designing an efficient signal detector is crucial. Traditional detectors often fail to perform adequately under complex channel conditions. Therefore, Graph Neural Networks (GNNs), known for their powerful feature representation and generalization capabilities, have been introduced for OTFS signal detection. However, conventional GNN-based detectors do not effectively utilize prior information and edge features. To address this, we propose a Prior Information-Enhanced GNN (PI-EGNN) detector, which improves signal estimation by integrating prior information and fully leveraging edge attributes. Additionally, a linear attention mechanism is introduced to further enhance the overall network performance. Simulation results demonstrate that, compared to state-of-the-art detectors, the proposed PI-EGNN detector shows improved performance.

In this paper, we propose a soft actor?critic (SAC) algorithm with hindsight experience replay (HER), called SACHER, which is a class of deep reinforcement learning (DRL) algorithm. SAC is an off-policy model-free DRL algorithm that outperforms earlier DRL algorithms in terms of exploration and robustness. However, in SAC, maximizing the entropy-augmented objective degrades the optimality of learning outcomes. We propose SACHER to improve the learning performance of SAC. We apply SACHER to the path planning and collision avoidance control of unmanned aerial vehicles (UAVs). We demonstrate the effectiveness of SACHER in terms of the success rate, learning speed, and collision avoidance performance of UAV operation.

In this paper, we propose a new method for generating convolution filters of a convolutional neural network (CNN) model as linear combinations of only a few basis filters that are provided as input features. In our approach, best coefficients of the linear combinations are searched (trained) with the given input basis filters (IBFs) to reconstruct the convolution filter parameters. Since all the convolution filters can be generated by the linear combinations of the IBFs, the size of a CNN model can be compressed if the number of coefficients for the linear combinations is less than that of filter parameters. Our primary goal is to investigate the possibility of expressing filters with a small set of IBFs by linear combinations. The second goal is to compress a model so that it can be beneficial when the model is distributed and stored (particularly downloaded to mobile devices through Wi-Fi).

In this paper, we propose a novel federated learning framework named FedHM that aims to address the challenge of training models on heterogeneous devices with varying architectures. Our approach enables the collaborative training of diverse local models by sharing a fully convolutional network (FCN) architecture that effectively extracts the local-to-global representations. By leveraging the weights with respect to this abstraction as common information across different DNN architectures, FedHM achieves efficient federated learning with minimal computational and communication overhead. We compare FedHM with three federated learning frameworks using two datasets for image classification tasks. Our results show that FedHM achieves high accuracy with considerably lower computational and communication costs compared to the other frameworks.

Recent meta-learning algorithms for few-shot learning are based on episodic training where each episode consists of only a few support and query samples to imitate a target few-shot task. However, due to the limited number of categories and few samples in each category, this framework suffers from over-fitting to both a meta-training dataset and the support set of each episode. It also causes a large variance in the accuracy of each episode, which reduces reliability and confidence in model performance. To address this problem, we propose a novel meta-ensemble learning approach based on a recent ensemble method: a multi-input multi-output (MIMO) configuration. Our approach is simply applied to existing meta-learning algorithms. Multiple subnetworks in a single model simultaneously learn multiple episodes and ensemble the predictions, leveraging the model capacity. We show that meta-ensemble learning achieves significant improvement in generalization. It also improves the performance of meta-learning algorithms on few-shot classification benchmarks.

Purpose: This study aimed to develop a predictive model for the early identification of patients at risk of sepsis, using routinely available clinical information and laboratory test results collected during the initial phase of patient care. Methods: This retrospective analysis included electronic medical records of 22,400 adult patients who presented with suspected infection to a tertiary care university hospital in Korea between January 2013 and May 2024. Patients were classified according to Systemic Inflammatory Response Syndrome (score ≥ 2) or Quick Sequential Organ Failure Assessment (score ≥ 2), in combination with sepsis-related International Classification of Diseases, 10th revision codes. Four different machine learning models were trained and validated using five-fold cross-validation. In addition, Shapley additive explanations analysis was performed to interpret the contribution and clinical relevance of key predictive variables. Results: Among the evaluated models, CatBoost demonstrated the strongest predictive performance. Notably, platelet distribution width, alveolar?arterial oxygen difference, procalcitonin, and the arterial/alveolar oxygen ratio consistently emerged as major predictors. Importantly, several variables that did not reach statistical significance in univariate analysis nevertheless contributed substantially to overall model performance, highlighting the importance of complex, multidimensional interactions among clinical factors. Conclusion: These findings indicate that a model based on simple, routinely collected clinical data can achieve high predictive accuracy and strong generalizability. Such a tool may support early clinical decision-making by multidisciplinary teams, including nurses, across diverse real-world care settings. Further prospective studies are warranted to validate its clinical utility and to assess its potential effects on patient outcomes.

Federated learning (FL) enables distributed model training while preserving privacy, but frequent updates from many devices create substantial communication challenges. Over-the-air computation (AirComp) offers a solution by aggregating updates directly over wireless channels through signal superposition, reducing overhead. However, AirComp can increase the mean squared error (MSE) of aggregated signals, affecting model accuracy. This paper introduces a beamforming optimization framework for AirComp in FL systems, jointly optimizing base station beamforming and device transmission scaling to minimize MSE. Two algorithms are developed: a high-performance convex method (Miso-CVX) and a lower-complexity subgradient method (Miso-Subgradient), both balancing signal misalignment and noise. Extensive simulations show improved aggregation accuracy, convergence speed, and robustness to channel variations.

Objective To present new classification methods of knee osteoarthritis (KOA) using machine learning and compare its performance with conventional statistical methods as classification techniques using machine learning have recently been developed. Methods A total of 84 KOA patients and 97 normal participants were recruited. KOA patients were clustered into three groups according to the Kellgren-Lawrence (K-L) grading system. All subjects completed gait trials under the same experimental conditions. Machine learning-based classification using the support vector machine (SVM) classifier was performed to classify KOA patients and the severity of KOA. Logistic regression analysis was also performed to compare the results in classifying KOA patients with machine learning method. Results In the classification between KOA patients and normal subjects, the accuracy of classification was higher in machine learning method than in logistic regression analysis. In the classification of KOA severity, accuracy was enhanced through the feature selection process in the machine learning method. The most significant gait feature for classification was flexion and extension of the knee in the swing phase in the machine learning method. Conclusion The machine learning method is thought to be a new approach to complement conventional logistic regression analysis in the classification of KOA patients. It can be clinically used for diagnosis and gait correction of KOA patients.

Background: A critical features of Alzheimer’s disease (AD) is cognitive dysfunction, which partly arises from decreased in acetylcholine levels. AD afftected brains are characterized by extensive oxidative stress, which is thought to be primarily induced by the amyloid beta (Aβ) peptide. In a previous study, Cinnamomum loureiroi tincture inhibited acetylcholinesterase (AchE) activity. That study identified AChE inhibitor in the C. loureiroi extract. Furthermore, the C. loureiroi extract enhanced memory in a trimethyltin (TMT)-induced model of cognitive dysfunction, as assessed via two behavioral tests. Rosa laevigata extract protected against oxidative stress-induced cytotoxicity. Administrating R. laevigata extracts to mice significantly reversed Aβ-induced learning and memory impairment, as shown in behavioral tests. Methods and Results: We conducted behavioral to examine the synergistic effects of C. loureiroi and R. laevigata extracts in inhibiting AChE and counteracting TMT-induced learning and memory losses. We also performed biochemical assays. The biochemical results showed a relationship between increased oxidative stress and cholinergic neurons damage in TMT-treated mice. Conclusions: A diet containing C. loureiroi and R. laevigata extracts ameliorated learning and memory impairments in the Y-maze and passive avoidance tests, and exerted synergistic inhibitory effect against AChE and lipid peroxidation.

As the population and income levels rise, meat consumption steadily increases annually. However, the number of farms and farmers producing meat decrease during the same period, reducing meat sufficiency. Information and Communications Technology (ICT) has begun to be applied to reduce labor and production costs of livestock farms and improve productivity. This technology can be used for rapid pregnancy diagnosis of sows; the location and size of the gestation sacs of sows are directly related to the productivity of the farm. In this study, a system proposes to determine the number of gestation sacs of sows from ultrasound images. The system used the YOLOv7-E6E model, changing the activation function from sigmoid-weighted linear unit (SiLU) to a multi-activation function (SiLU + Mish). Also, the upsampling method was modified from nearest to bicubic to improve performance. The model trained with the original model using the original data achieved mean average precision of 86.3%. When the proposed multi-activation function, upsampling, and AutoAugment were applied, the performance improved by 0.3%, 0.9%, and 0.9%, respectively. When all three proposed methods were simultaneously applied, a significant performance improvement of 3.5% to 89.8% was achieved.

본 연구는 교수자가 개발한 교수·학습모형(이하: SCIVFeRE 모형)이 간호대학생의 핵심간호술 문제해결 능력, 자기 주도 학습능력, 수행 자신감에 미치는 효과를 검증하기 위하여 실시한 단일군 전·후 설계(One group pretest-post test design)이다. 졸업을 앞둔 예비간호사들을 대상으로 핵심실무 능력 인증제를 위한 사전프로그램으로 개발되었다. 내용은 18개의 핵심 간호술과 임상 사례를 접목한 복합 시나리오 6개의 핵심 간호술을 해결하는 것으로 총 연구 기간은 2023년 1월 20일부터 2023년 12월 31일간이었다. 연구에 참여한 대상자는 졸업을 앞둔 예비간호사(4학년) 218명으로 서술적 분석과 짝 비교 검정을 이용하여 분석하였다. 연구 결과, 학생들의 핵심 간호술 문제해결 능력, 자기주도 학습 능력, 수행 자신감은 통계적 으로 유의한 값을 보였으며, 본 교수·학습모형은 간호대학생의 핵심 간호술 수행능력향상에 효과적인 것으로 나타났다.

This study is a single group pretest, post-test design conducted to verify the effect of the teaching-learning model developed by the instructor on the core nursing problem-solving ability, self-directed learning ability, and performance confidence of nursing students. It is to solve 18 core nursing skills and 6 core nursing skills in a complex scenario that combines clinical cases for prospective nurses who are about to graduate. The study period was from January 20, 2023, to December 31, 2023. The subjects of the study were 218 prospective nurses (fourth grade) who were about to graduate, and were analyzed using descriptive analysis and pair comparison tests. As a result of the study, students' ability to solve core nursing problems, self-directed learning ability, and performance confidence showed statistically significant values, and this teaching-learning model was found to be effective in improving nursing students' ability to perform core nursing skills.

This study explores how multidimensional immersion learning could affect EFL undergraduates’ self-regulated learning (SRL) by enhancing their inner speech. As the inner voice can be related to learners’ self-reflection and self-awareness of their existences, this study focuses on inner voice as a key for linguistic proficiency development in the immersion class. Twenty-two participants expressed their inner thoughts in the target language through a topic-based argumentation concerning real-life issues. Using the digital technology of Prezi and Voki, they organized their contents, and provided self-assessments of pronunciation and accents. Regression analysis suggested achievement as a crucial element to activate SRL and language proficiency. Multidimensional immersion learning can cultivate communication skills, providing various experiences and motivation.