• 공학교육연구
• /
• 제26권4호
• /
• pp.11-21
• /
• 2023

In engineering education, stimulating students' questions and encouraging learning participation are crucial for achieving higher-order thinking abilities. This study aims to investigate the use and effect of an online communication channel in fostering engineering students' questioning abilities. Consequently, in this research, we gauged students' satisfaction with an engineering class that implemented a communication channel, and scrutinized the changes in their perceptions regarding the significance of questions, their engagement in learning, and their academic self-efficacy. In addition, we interviewed the students who participated in the class. The outcomes are as follows: Firstly, student satisfaction improved compared to the previous semester's class where the communication channel was not utilized. Secondly, learners' understanding of the importance of asking questions positively escalated, alongside their actual frequency of posing questions. Thirdly, there was an improvement in learners' active engagement in their studies and their academic self-confidence. The findings of this research suggest that communication channels should be employed to motivate learners to pose questions and involve students in effective learning.

• Educational Technology International
• /
• 제19권1호
• /
• pp.61-91
• /
• 2018

The animated pedagogical agent has been implemented to promote learning outcomes and motivation in multimedia learning. It has been claimed that one of the advantages of using pedagogical agent is persona effect - the personalization or social presence of pedagogical agent can enhance learning engagement and motivation. However, prior research is inconclusive as to whether and how the features of the pedagogical agent have effects on the persona effect. This study investigated whether the similarity between a pedagogical agent and the real instructor in terms of the voice and outlook would improve students' perception of the agent's persona. The study also examined the effect by the size of pedagogical agent on the persona perception. Two experiments were conducted with a total of 115 college students. Experiment 1 indicated a significant main effect of voice on the persona perception. Experiment 2 was conducted to examine whether the size of pedagogical agent would affect the voice effect on the persona perception. The results showed that the instructor-like voice yielded higher persona perception regardless of the pedagogical agent's size. Overall, the study findings indicated that the similarity in voice positively fostered the agent's persona.

• Geomechanics and Engineering
• /
• 제31권3호
• /
• pp.265-279
• /
• 2022

Tunnel convergence prediction is essential for the safe construction and design of tunnels. This study proposes five machine learning models of deep neural network (DNN), K-nearest neighbors (KNN), Gaussian process regression (GPR), support vector regression (SVR), and decision trees (DT) to predict the convergence phenomenon during or shortly after the excavation of tunnels. In this respect, a database including 650 datasets (440 for training, 110 for validation, and 100 for test) was gathered from the previously constructed tunnels. In the database, 12 effective parameters on the tunnel convergence and a target of tunnel wall convergence were considered. Both 5-fold and hold-out cross validation methods were used to analyze the predicted outcomes in the ML models. Finally, the DNN method was proposed as the most robust model. Also, to assess each parameter's contribution to the prediction problem, the backward selection method was used. The results showed that the highest and lowest impact parameters for tunnel convergence are tunnel depth and tunnel width, respectively.

• 전기전자학회논문지
• /
• 제27권4호
• /
• pp.439-449
• /
• 2023

In an era marked by the increasing use of drones and the growing demand for indoor surveillance, the development of a robust application for detecting and tracking both drones and humans within indoor spaces becomes imperative. This study presents an innovative application that uses FMCW radar to detect human and drone motions from the cloud point. At the outset, the DBSCAN (Density-based Spatial Clustering of Applications with Noise) algorithm is utilized to categorize cloud points into distinct groups, each representing the objects present in the tracking area. Notably, this algorithm demonstrates remarkable efficiency, particularly in clustering drone point clouds, achieving an impressive accuracy of up to 92.8%. Subsequently, the clusters are discerned and classified into either humans or drones by employing a deep learning model. A trio of models, including Deep Neural Network (DNN), Residual Network (ResNet), and Long Short-Term Memory (LSTM), are applied, and the outcomes reveal that the ResNet model achieves the highest accuracy. It attains an impressive 98.62% accuracy for identifying drone clusters and a noteworthy 96.75% accuracy for human clusters.

• Geomechanics and Engineering
• /
• 제37권3호
• /
• pp.253-262
• /
• 2024

Dynamic properties are pivotal in soil analysis, yet their experimental determination is hampered by complex methodologies and the need for costly equipment. This study aims to predict dynamic soil properties using static properties that are relatively easier to obtain, employing machine learning techniques. The static properties considered include soil cohesion, friction angle, water content, specific gravity, and compressional strength. In contrast, the dynamic properties of interest are the velocities of compressional and shear waves. Data for this study are sourced from 26 boreholes, as detailed in a geotechnical investigation report database, comprising a total of 130 data points. An importance analysis, grounded in the random forest algorithm, is conducted to evaluate the significance of each dynamic property. This analysis informs the prediction of dynamic properties, prioritizing those static properties identified as most influential. The efficacy of these predictions is quantified using the coefficient of determination, which indicated exceptionally high reliability, with values reaching 0.99 in both training and testing phases when all input properties are considered. The conventional method is used for predicting dynamic properties through Standard Penetration Test (SPT) and compared the outcomes with this technique. The error ratio has decreased by approximately 0.95, thereby validating its reliability. This research marks a significant advancement in the indirect estimation of the relationship between static and dynamic soil properties through the application of machine learning techniques.

• Journal of Animal Science and Technology
• /
• 제66권1호
• /
• pp.167-177
• /
• 2024

Iris segmentation is an initial step for identifying the biometrics of animals when establishing a traceability system for livestock. In this study, we propose a deep learning framework for pixel-wise segmentation of bovine iris with a minimized use of annotation labels utilizing the BovineAAEyes80 public dataset. The proposed image segmentation framework encompasses data collection, data preparation, data augmentation selection, training of 15 deep neural network (DNN) models with varying encoder backbones and segmentation decoder DNNs, and evaluation of the models using multiple metrics and graphical segmentation results. This framework aims to provide comprehensive and in-depth information on each model's training and testing outcomes to optimize bovine iris segmentation performance. In the experiment, U-Net with a VGG16 backbone was identified as the optimal combination of encoder and decoder models for the dataset, achieving an accuracy and dice coefficient score of 99.50% and 98.35%, respectively. Notably, the selected model accurately segmented even corrupted images without proper annotation data. This study contributes to the advancement of iris segmentation and the establishment of a reliable DNN training framework.

• 한국콘텐츠학회논문지
• /
• 제22권10호
• /
• pp.765-777
• /
• 2022

본 연구의 목적은 급격히 변화하는 환경 속에서 대학이 경쟁력을 가지기 위해 학습 디지털 트랜스포메이션과 관련된 이론 및 사례를 기반으로 대학에서 활용 가능한 디지털 트랜스포메이션 기반 학습모델을 제시하는 것이다. 이를 위해 기초적인 문헌연구와 사례연구, 전문가 초점집단면접(Focus Group Interview)이 진행되었으며 위 연구방법들을 통해 도출된 학습모델 관련 시사점은 다음과 같다. 국내외에서 관련 분야에 두각을 나타내는 대학들은 빅 데이터를 기반으로 학습분석을 대시보드 구현, 예측 모델 개발, 적응형 학습 지원 등에 활발하게 사용하고 있으며, 첨단 에듀테크를 수업에 적극적으로 도입하여 성과를 내고 있다. 또한 국내 대학이 당면한 현실적인 문제와 애로사항 및 현재 K대학이 당면한 디지털 트랜스포메이션 구현 관련 문제점과 기대 사항들도 확인되었다. 이 시사점들을 바탕으로 본 연구는 K대학의 디지털 트랜스포메이션 기반 학습모델을 개발하였다. 이 모델은 진단, 추천, 학습, 성공의 4개 차원으로 구성되어 있으며 학생이 이 모델을 통해 개인의 성공에 필요한 다양한 학습 과정을 진단 및 추천받아 학습을 진행하고, 학습 성과를 체계적으로 관리해 성공할 수 있도록 한다. 마지막으로 연구결과에 대한 학문적 그리고 실무적 시사점이 논의되었다.

• Journal of Gastric Cancer
• /
• 제16권4호
• /
• pp.240-246
• /
• 2016

Purpose: It is hypothesized that robotic gastrectomy may surpass laparoscopic gastrectomy after the operators acquire long-term experience and skills in the manipulation of robotic arms. This study aimed to evaluate the long-term learning curve of robotic distal gastrectomy (RDG) for gastric cancer compared with laparoscopic distal gastrectomy (LDG). Materials and Methods: From October 2008 to December 2015, patients who underwent LDG (n=809) were matched to patients who underwent RDG (n=232) at a 1:1 ratio, by using a propensity score matching method after stratification for the operative year. The surgical outcomes, such as trends of operative time, blood loss, and complication rate, were compared between the two groups. Results: The RDG group showed a longer operative time (171.3 minutes vs. 147.6 minutes, P<0.001) but less estimated blood loss (77.6 ml vs. 116.6 ml, P<0.001). The complication rate and postoperative recovery did not differ between the two groups. The RDG group showed a longer operative time and similar estimated blood loss compared with the LDG group after 5 years of experience (operative time: 159.2 minutes vs. 136.0 minutes in 2015, P=0.003; estimated blood loss: 72.9 ml vs. 78.1 ml in 2015, P=0.793). Conclusions: In terms of short-term surgical outcomes, RDG may not surpass LDG after a long-term experience with the technique.

• Journal of Gastric Cancer
• /
• 제15권4호
• /
• pp.270-277
• /
• 2015

Purpose: Minimally invasive gastrectomy (MIG), including laparoscopic distal subtotal gastrectomy (LDG) and robotic distal subtotal gastrectomy (RDG), is performed for gastric cancer, and requires a learning period. However, there are few reports regarding MIG by a beginner surgeon trained in MIG for gastric cancer during surgical residency and fellowship. The aim of this study was to report our initial experience with MIG, LDG, and RDG by a trained beginner surgeon. Materials and Methods: Between January 2014 and February 2015, a total of 36 patients (20 LDGs and 16 RDGs) underwent MIG by a beginner surgeon during the learning period, and 13 underwent open distal subtotal gastrectomy (ODG) by an experienced surgeon in Bundang CHA Medical Center. Demographic characteristics, operative findings, and short-term outcomes were evaluated for the groups. Results: MIG was safely performed without open conversion in all patients and there was no mortality in either group. There was no significant difference between the groups in demographic factors except for body mass index. There were significant differences in extent of lymph node dissection (LND) (D2 LND: ODG 8.3% vs. MIG 55.6%, P=0.004) and mean operative time (ODG 178.8 minutes vs. MIG 254.7 minutes, P<0.001). The serial changes in postoperative hemoglobin level (P=0.464) and white blood cell count (P=0.644) did not show significant differences between the groups. There were no significant differences in morbidity. Conclusions: This study showed that the operative and short-term outcomes of MIG for gastric cancer by a trained beginner surgeon were comparable with those of ODG performed by an experienced surgeon.

• 문화기술의 융합
• /
• 제8권1호
• /
• pp.371-377
• /
• 2022

이 연구는 그간 학습 결과, 교육적 결과물, 객체를 우선시하느라 한국어 어휘 교육에서 다루지 못한 '과정'으로서 주목해야 할 대상과 학습자는 없는지 검토한 후, 신조어의 교육적 가치를 점검하고 이에 대한 자료구축 방안을 제안하는 데 목적을 두었다. '과정' 중에 빠진 사각지대 어휘로는 신조어를, 사각지대 단계의 학습자로는 외국인 학문목적 학습자를 들고, 학문 목적 학습자에게 신조어를 가르치기 위한 학습 자료로 사전을 만들기 위한 전초 작업으로 신조어 '단층적 목록' 만들기를 제안하였다. '단층적 목록'은 신조어를 시기별로 조어, 의미, 문화 등으로 나누어 자료로 구축하는 것이다. 이러한 연구는 그간 한국어 어휘교육에서 구축한 결과물에 '과정'으로 학습으로 할 어휘를 추가하여 한국어 어휘교육을 체계적으로 하는 데 도움을 줄 것이다.