• 농촌지도와개발
• /
• 제22권4호
• /
• pp.455-464
• /
• 2015

The purposes of this study are to explain and identify the frame of structural relations of learning orientation, self-efficacy, learning transfer and job performance of farmers who participated in the strong and small farms education. This is an experimental research with the data collected from 495 farmers who have taken the farm education. Based on the collected data, the study conducted a structural equation modeling(SEM) to confirm the validity and analyze the structural relations of the suggested model. Using measured and latent variables drew from the analyses, the study set a structural equation model and tested the model by analysis of the structural equation modeling with AMOS 18.0. The results found from the empirical analysis can be summarized as follows. 1) Learning orientation and self-efficacy positively influenced job performance through learning transfer. 2) The hypothesis that learning orientation would have direct impact on job performance was not supported. 3) The strong and small farms education is useful to expand learning transfer and to enhance job performance. So, government policy support has to reinforce learning support on farmers in order to achieve high performance of learning and job management through farm educations.

• 공학교육연구
• /
• 제27권1호
• /
• pp.32-40
• /
• 2024

This study attempted to develop an efficient management plan that allows both workers and organizations to coexist by analyzing the factors that influence the level of organizational immersion of engineering students. Analysis methods included frequency analysis, t-test, pearson correlation analysis, and hierarchical analysis. Firstly, self-esteem and transfer of learning were influential factors on organizational commitment. Second, self-esteem and transfer of learning were influencing factors of self-efficacy. Third, self-efficacy was an influential factor in organizational commitment. Fourth, self-efficacy appeared as a mediating effect on self-esteem and organizational immersion in learning transfer. Therefore, it is necessary to look for various factors that can increase self-efficacy, and to find opportunities for students to be highly immersed in the organization while studying at the same time.

• 대한원격탐사학회지
• /
• 제37권6_1호
• /
• pp.1685-1695
• /
• 2021

우수한 성능을 가지는 딥러닝 모델을 생성하기 위해서는 충분한 양의 학습자료가 필요하다. 하지만, 원격탐사 분야에서 충분한 양의 학습자료를 구축하기 위해서는 많은 시간과 비용을 필요로 한다. 따라서 적은 수의 학습자료를 활용한 딥러닝 모델의 전이학습(transfer learning)의 중요성이 증대되고 있다. 본 연구에서는 사전에 제작된 공개데이터셋을 기반으로 국내 정사영상 및 수치지도를 활용한 전이학습을 통해 국내 다시기 정사영상 내 존재하는 건물객체의 변화에 대한 탐지를 수행하였다. 이를 위하여, 변화탐지를 위한 공개데이터셋을 HRNet-v2 모델을 통하여 선행학습을 수행하고, 국내 정사영상 및 수치지도를 이용한 학습자료에 전이학습을 수행하였다. 전이학습에 대한 영향을 분석하기 위하여 두 곳의 실험지역에 전이 학습된 모델을 포함한 다양한 딥러닝 모델의 결과를 평가한 결과, 전이학습을 활용한 연구가 가장 우수함을 확인하였다. 이를 통하여, 전이학습을 활용해 부족한 양의 학습자료 문제를 해결하고, 다양한 원격탐사 자료에 대하여 효과적으로 변화탐지 기법을 적용할 수 있음을 확인하였다.

• 농촌지도와개발
• /
• 제23권3호
• /
• pp.233-242
• /
• 2016

This study aimed to analyze educational satisfaction and the relationship between learning transfer and learning persistence shown after actual education targeting students who participated in the agricultural education and training. Conclusions based on the study results can be suggested as follows. First, of the factors related to learning persistence, satisfaction of educational contents turned out to be a statistically significant factor with a positive effect in the agricultural education and training. Students participating in the agricultural education and training have a conspicuous object to learn for improving ability which is necessary for and applicable to agriculture. Second, of the three factors related to learning transfer in the agricultural education and training, satisfaction of educational contents, educational facilities and satisfaction of environment turned out to have a positive effect. Third, results show that satisfaction of instructors does not affect both learning persistence and learning transfer. Lastly, in case of education and training for field practice, this study is suggesting the necessity of research by accessing in a concrete and detailed manner such as learning contents, instructors, educational facilities and satisfaction of environment from the comprehensive concept of educational satisfaction in the directivity of study related to satisfaction.

• 문화기술의 융합
• /
• 제9권3호
• /
• pp.845-850
• /
• 2023

본 논문에서는 전이학습을 이용하여 볼베어링의 진동진단을 수행하는 방법을 제안한다. 고장을 진단하기 위해 진동신호를 시간-주파수로 분석할 수 있는 STFT을 CNN의 입력으로 이용하였다. CNN 기반의 딥러닝 인공신경망을 빠르게 학습하고 진단 성능을 높이기 위해 전이학습 기반의 딥러닝 학습 기법을 제안하였다. 전이학습은 VGG 기반의 영상 분류 모델을 이용하여 특징 추출기와 분류기를 선택적으로 학습하였고, 학습에 사용한 데이터 세트는 Case Western Reserve University 대학에서 제공하는 공개된 볼베어링 진동 데이터를 사용하였으며, 성능평가는 기존의 CNN 모델과 비교하는 방법으로 수행하였다. 실험 결과 전이학습이 볼베어링 진동 데이터에서 상태 진단에 유용하다는 것을 증명할 수 있을 뿐만 아니라 이를 통해 다른 산업에서도 전이학습을 사용하여 상태 진단을 개선할 수 있다.

• 공학교육연구
• /
• 제12권3호
• /
• pp.3-12
• /
• 2009

최근의 공학설계교육의 발달은 공학교육에 많은 영향을 주고 있다. 그러나 이와 관련한 대부분의 연구는 시스템개발이나 과정개발과 관련된 분야에 집중되어 있어, 학습 효과와 학습결과 학습자들이 프로젝트를 수행하는 과정에 얼마나 학습전이가 이루어 졌는지에 대한 연구는 전무하다. 본 연구는 대학의 공학설계교육의 결과로 발생하는 학습의 정도와 학습전이간의 관계를 규명하려는데 있다. 본래 학습전이는 기업교육을 통하여 학습자들이 획득한 지식과 기술을 직무 상황에서 효과적으로 또는 지속적으로 자신의 현 직무에 적용하는 정도를 말한다. 연구결과 학습자 특성과 교육과정설계 특성은 학습에 유의미한 결과를 나타냈으며, 학습자 특성에 따른 전이효과 역시 유효한 결과를 가져왔으며, 학습이 전이에 영향을 미치는 것으로 나타났다.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제8권2호
• /
• pp.351-358
• /
• 2018

강화 학습은 변화하는 환경에서의 최적의 보상을 얻을 수 있는 행동을 결정하기 위한 정책을 얻는 기계 학습 기법이다. 하지만 기존에 연구되어 온 강화 학습은 불확실하고 연속적인 실제 환경에서 최적의 행동을 얻기 위해 발생되는 높은 계산 복잡도 문제와 학습된 결과를 얻기 위해서는 많은 시간이 소요 된다는 문제점을 가지고 있다. 앞에서 언급한 문제를 해결하기 위해, 높은 계산 복잡도 문제를 해결을 위해서는 강화 학습을 구성하는 가치 함수와 정책을 독립적으로 구성하는 AC(actor-critic) 기법이 제안되었다. 그리고 빠른 학습 결과를 얻기 위해 기 학습된 지식을 새로운 환경에서 이용하여 기존 학습보다 빠르게 학습 결과를 얻을 수 있는 전이 학습(transfer learning) 기법이 제안되었다. 본 논문에서는 기존에 연구되어 왔던 기계 학습 기법의 향상 기법인 AC 기법과 전이 학습 기법에 대해 소개하고, 이를 무선 액세스 네트워크 환경에서 기지국 상태 조정을 위해 적용되고 있는 사례를 소개한다.

• Educational Technology International
• /
• 제16권2호
• /
• pp.183-200
• /
• 2015

This study investigated the effect of learning achievements and cognitive load according to different types of presenting learning materials and epistemological beliefs (EB). Learning achievements in this study were composed by retention and transfer of ill-structured problem. A total of 80 college students participated in the study. Prior to the learning, students were guided to fill out a questionnaire regarding epistemological beliefs and a prior knowledge test. The students of each group studied with a different type of reading material: full text (FT), full text including key questions (KeyFT) and full text including a concept map (CmFT). After a session of study was finished, they were asked to complete the posttest: retention and transfer. The results showed that there was a significant difference in transfer achievements. CmFT outperformed higher scores than the other types. There was no significant difference in retention among the groups. It is strongly believed that the types of presenting learning materials may have affected the understanding of ill-structured problem solving skills. Students with sophisticated EB showed higher achievements on retention and transfer than naive-EB and mixed-EB. Even though the data showed decrease of the cognitive load on the type of materials and EB, there were no significant differences on the cognitive load. We should consider a positive effect of types of presenting learning materials and EB enhancing capabilities of solving ill-structured problems in real life.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.209-216
• /
• 2019

Over the past decade, researchers were able to solve complex medical problems as well as acquire deeper understanding of entire issue due to the availability of machine learning techniques, particularly predictive algorithms and automatic recognition of patterns in medical imaging. In this study, a technique called transfer learning has been utilized to classify Magnetic Resonance (MR) images by a pre-trained Convolutional Neural Network (CNN). Rather than training an entire model from scratch, transfer learning approach uses the CNN model by fine-tuning them, to classify MR images into Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal control (NC). The performance of this method has been evaluated over Alzheimer's Disease Neuroimaging (ADNI) dataset by changing the learning rate of the model. Moreover, in this study, in order to demonstrate the transfer learning approach we utilize different pre-trained deep learning models such as GoogLeNet, VGG-16, AlexNet and ResNet-18, and compare their efficiency to classify AD. The overall classification accuracy resulted by GoogLeNet for training and testing was 99.84% and 98.25% respectively, which was exceptionally more than other models training and testing accuracies.

• 산업경영시스템학회지
• /
• 제44권3호
• /
• pp.33-38
• /
• 2021

Recently, transfer learning techniques with a base convolutional neural network (CNN) model have widely gained acceptance in early detection and classification of crop diseases to increase agricultural productivity with reducing disease spread. The transfer learning techniques based classifiers generally achieve over 90% of classification accuracy for crop diseases using dataset of crop leaf images (e.g., PlantVillage dataset), but they have ability to classify only the pre-trained diseases. This paper provides with an evaluation scheme on selecting an effective base CNN model for crop disease transfer learning with regard to the accuracy of trained target crops as well as of untrained target crops. First, we present transfer learning models called CDC (crop disease classification) architecture including widely used base (pre-trained) CNN models. We evaluate each performance of seven base CNN models for four untrained crops. The results of performance evaluation show that the DenseNet201 is one of the best base CNN models.