• 디지털산업정보학회논문지
• /
• 제11권3호
• /
• pp.179-200
• /
• 2015

Recent national policies National Competency Standards(NCS) to develop teaching-oriented education in the field of industry and learning is taking place. Plan to take advantage of the Internet and multimedia classes, information and communication technology (ICT) for ways to leverage the integration appearing in various forms. The purpose of this study is causal influence on the ARCS motivation theory can determine the basic psychology of human motivation factors and the desires of a typical human nature theory dealing with the psychological needs of interactivity and immersion is learning achievement and learning transfer and to validate the demonstration. By applying information and communication technology sector in the development of learning in information and communication equipment training program modules from a field study conducted at the NCS with a clear empirical and empirical research through the synchronization to the learner and to explore the possibility of generalization.

• 인터넷정보학회논문지
• /
• 제21권5호
• /
• pp.57-65
• /
• 2020

At present, the existing virus recognition systems usually use signature approach to detect malicious executable files, but these methods often fail to detect new and invisible malware. At the same time, some methods try to use more general features to detect malware, and achieve some success. Moreover, machine learning-based approaches are applied to detect malware, which depend on features extracted from malicious codes. However, the different distribution of features oftraining and testing datasets also impacts the effectiveness of the detection models. And the generation oflabeled datasets need to spend a significant amount time, which degrades the performance of the learning method. In this paper, we use transfer learning to detect new and previously unseen malware. We first extract the features of Portable Executable (PE) files, then combine transfer learning training model with KNN approachto detect the new and unseen malware. We also evaluate the detection performance of a classifier in terms of precision, recall, F1, and so on. The experimental results demonstrate that proposed method with high detection rates andcan be anticipated to carry out as well in the real-world environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4816-4834
• /
• 2020

This paper proposes transfer learning and fine-tuning techniques for a deep learning model to detect three distinct brain tumors from Magnetic Resonance Imaging (MRI) scans. In this work, the recent YOLOv4 model trained using a collection of 3064 T1-weighted Contrast-Enhanced (CE)-MRI scans that were pre-processed and labeled for the task. This work trained with the partial 29-layer YOLOv4-Tiny and fine-tuned to work optimally and run efficiently in most platforms with reliable performance. With the help of transfer learning, the model had initial leverage to train faster with pre-trained weights from the COCO dataset, generating a robust set of features required for brain tumor detection. The results yielded the highest mean average precision of 93.14%, a 90.34% precision, 88.58% recall, and 89.45% F1-Score outperforming other previous versions of the YOLO detection models and other studies that used bounding box detections for the same task like Faster R-CNN. As concluded, the YOLOv4-Tiny can work efficiently to detect brain tumors automatically at a rapid phase with the help of proper fine-tuning and transfer learning. This work contributes mainly to assist medical experts in the diagnostic process of brain tumors.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.849-859
• /
• 2021

Prostate cancer (PCa) is a fatal disease that occurs in men. In general, PCa cells are found in the prostate gland. Early diagnosis is the key to prevent the spreading of cancers to other parts of the body. In this case, deep learning-based systems can detect and distinguish histological patterns in microscopy images. The histological grades used for the analysis were benign, grade 3, grade 4, and grade 5. In this study, we attempt to use transfer learning and fine-tuning methods as well as different model architectures to develop and compare the models. We implemented MobileNet, ResNet50, and DenseNet121 models and used three different strategies of freezing layers techniques of fine-tuning, to get various pre-trained weights to improve accuracy. Finally, transfer learning using MobileNet with the half-layer frozen showed the best results among the nine models, and 90% accuracy was obtained on the test data set.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• 컴퓨터교육학회논문지
• /
• 제20권6호
• /
• pp.61-69
• /
• 2017

SW 교육의 목적은 Computational Thinking의 증진에 있다. 특히, 비전공자들의 경우 Computational Thinking을 습득하여 자신의 전공에 적용하여 문제를 해결하는 과정이 필요하다. 본 연구에서는 비전공자 대학생을 대상으로 한 Computational Thinking 교육을 실시한 후, 혼합연구방법론을 통해 Computational Thinking 증진에 영향을 주는 요인이 무엇인지 검증하였다. 또한, Computational Thinking 학습전이 초기과정에서 나타나는 특징을 분석하여 비전공자를 대상으로 한 SW교육의 타당성과 당위성의 근거를 마련하고자 하였다. 연구의 결과로 Computational Thinking 증진에 영향을 주는 요인은 교육만족도, 학습전이 동기, self-CT 효능감으로 나타났다. Computational Thinking 학습전이 초기 과정이 실제 프로그래밍 과정에서 나타나는 Computational Thinking의 개념과 실행의 특징을 보이고 있으므로, 문제해결에서 Computational Thinking을 적용하는 사고과정이 실제 일어나는 것을 확인할 수 있었다. 본 연구에서 나타난 비전공자를 대상으로 한 Computational Thinking 교육의 효과와 전이 과정은 향후 모든 학생들에게 SW교육을 실시해야 하는 타당성과 당위성의 근거가 될 수 있다.

• 산업진흥연구
• /
• 제2권2호
• /
• pp.31-44
• /
• 2017

본 연구는 조직구성원인 인식하는 조직 내 커뮤니케이션 유형과 학습전이 풍토 간의 영향관계를 알아보기 위한 연구로 독립변인으로 설정한 조직 내 커뮤니케이션 유형은 상사와 커뮤니케이션, 매체 질 커뮤니케이션, 동료와 커뮤니케이션, 조직 전망 커뮤니케이션의 4개 변수로 제시하였으며, 종속변인인 학습전이풍토는 상사지원, 동료지원, 전이기회, 조직보상 인식의 4개 하위변수로 구성하였다. 본 연구목적을 달성하기 위해 2015년 중소기업 핵심직무역량 교육과정에 참여한 후 3개월 이상 경과한 참가자 150명을 대상으로 통계상 무의미한 설문을 제외 한 116부를 최종 활용하였다. 한편, 수집된 자료는 SPSS 20.0의 통계패키지 프로그램을 사용하여 빈도순석, 요인분석(Factor Analysis), 신뢰도 검증, 기술통계분석, 단순 다중회귀분석을 통해 연구가설을 검증하였다. 본 연구 결과 첫째, 조직 내 커뮤니케이션 유형과 학습전이 풍토인 상사의 지원 간의 영향관계에서 조직 내 커뮤니케이션 유형의 상사와 커뮤니케이션, 매체의 질 커뮤니케이션, 동료와 커뮤니케이션, 조직전망에 대한 커뮤니케이션은 모두 상사의 지원에 정(+)의 유의한 영향관계를 나타내었다. 둘째, 조직 내 커뮤니케이션 유형은 학습전이 풍토의 동요의 지원에는 모두 영향을 미치지 않는 것으로 나타났다. 셋째, 조직 내 커뮤니케이션 유형과 학습전이 풍토의 전이기화 간의 영향관계에서는 동료와 커뮤니케이션을 제외한 상사와 커뮤니케이션, 매체의 질 커뮤니케이션, 조직전망에 대한 커뮤니케이션이 전이기회에 정(+)의 영향관계를 나타내었다. 마지막으로 조직 내 커뮤니케이션 유형과 학습전이 풍토의 조직보상 인식에 대한 영향관계에서는 상사와 커뮤니케이션과 조직전망에 대한 커뮤니케이션이 정(+)의 영향관계를 나타냈다.

• ETRI Journal
• /
• 제46권2호
• /
• pp.263-276
• /
• 2024

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

• 한국컴퓨터정보학회논문지
• /
• 제28권11호
• /
• pp.1-11
• /
• 2023

유방암은 전 세계적으로 여성들 대다수에게 가장 두려워하는 질환이다. 오늘날 데이터의 증가와 컴퓨팅 기술의 향상으로 머신러닝(machine learning)의 효율성이 증대되어 암 검출 및 진단 등에 중요한 역할을 하고 있다. 딥러닝(deep learning)은 인공신경망(artificial neural network, ANN)을 기반으로 하는 머신러닝 기술의 한 분야로 최근 여러 분야에서 성능이 급속도로 개선되어 활용 범위가 확대되고 있다. 본 연구에서는 유방암 분류를 위해 전이학습(transfer learning) 기반 DNN(Deep Neural Network)과 SVM(support vector machine)의 구조를 결합한 DNN-SVM Hybrid 모형을 제안한다. 전이학습 기반 제안된 모형은 적은 학습 데이터에도 효과적이고, 학습 속도도 빠르며, 단일모형, 즉 DNN과 SVM이 가지는 장점을 모두 활용 가능토록 결합함으로써 모형 성능이 개선되었다. 제안된 DNN-SVM Hybrid 모형의 성능평가를 위해 UCI 머신러닝 저장소에서 제공하는 WOBC와 WDBC 유방암 자료를 가지고 성능실험 결과, 제안된 모형은 여러 가지 성능 척도 면에서 단일모형인 로지스틱회귀 모형, DNN, SVM 그리고 앙상블 모형인 랜덤 포레스트보다 우수함을 보였다.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제3권1호
• /
• pp.57-68
• /
• 1999

In this paper, we investigate the comparative effectiveness of two kinds of instructional methods in transfer of mathematics learning: one based on the situated cognition, i.e. situated learning (SL) and the other based on traditional learning (TL). Both classes (of grade 2) studied addition and subtraction of 3-digit numbers. After that, they completed two written tests (Written Test 1 included computation problems, Written Test 2 included computation problems and story problems) and a real situation test. As a result, no significant differences were found between the two groups' performance on computation skill in Written Tests 1 and 2. But the SL group performed significantly better on the performance of story problem and real situation test than TL group. This result indicated that the SL made improvement in transfer of mathematics learning. As a result of interviews with 12 children of the SL group were able to use contextual resources in solving real situation as well as story problems.