• 말소리와 음성과학
• /
• 제1권4호
• /
• pp.47-59
• /
• 2009

The purpose of this paper is to propose an automatic evaluation technique for the prosodic aspect of an English sentence uttered by Korean speakers learning English. The underlying hypothesis is that the consistency of the manual prosody scoring is reflected in an imaginary space of prosody evaluation model constructed out of the three physical properties of the prosody considered in this paper, namely: the fundamental frequency (F0) contour, the intensity contour, and the segmental durations. The evaluation proceeds first by building a prosody evaluation model for the sentence. For the creation of the model, utterances from native speakers of English and Korean learners for the target sentence are manually scored by either native teachers of English or Korean phoneticians in terms of their prosody. Multiple native utterances from the manual scoring are selected as the "model" native utterances against which all the other Korean learners' utterances as well as the model utterances themselves can be semi-automatically evaluated by comparison in terms of the three prosodic aspects [7]. Each learner utterance, when compared to the multiple model native utterances, produces multiple coordinates in a three-dimensional space of prosody evaluation, each axis of which corresponds to the three prosodic aspects. The 3D coordinates from all the comparisons form a prosody evaluation model for the particular sentence and the associated manual scores can display regions of particular scores. The model can then be used as a predictive model against which other Korean utterances of the target sentence can be evaluated. The model from a Korean phonetician appears to support the hypothesis.

• 한국과학교육학회지
• /
• 제28권6호
• /
• pp.527-545
• /
• 2008

본 연구는 과학교육에서 학습동기 요소를 활용한 4E&E순환학습모형을 제안하고자 하였다. 본 모형은 동기설계와 수업설계를 기반으로 하고 있다. 4E&E순환학습모형은 유인(Engage), 탐색(Exlpore), 설명(Explain), 확장(Expand) 등의 4단계로 구성되어 있으며, 각 단계마다 평가(Evaluate)와 feed-back을 통해 순환적으로 진행된다. 그리고 4E&E순환학습 모형은 수업과정 중에 평가와 피드백을 통한 지속적으로 학습에 대한 점검이 이루어지는 특징을 갖고 있어 효과적으로 학습 목표에 도달할 수 있다. 특히, 4E&E순환학습 모형은 학습동기유발전략을 활용하여 수업을 설계하고 실시함으로써 수업에 대한 매력도를 높이고 학습에 집중할 수 있어 과학교육에서 매우 효과적인 모형이라 할 수 있다.

• 공학교육연구
• /
• 제21권1호
• /
• pp.3-13
• /
• 2018

The purpose of this study is to propose a teaching and learning model that can effectively manage convergence education, which is one of the concerns of university education, at the level of course. The pre-collaborative instructional design stage is to prepare the operation of the convergence project course. It shares the common goal and establishes a team of relevant professors to set up the actual convergence project topic and establishes cooperation relationships with industry or community as needed. In the convergence project activity, students will be able to understand the learning objectives, learning activities, evaluation methods, and explain the subject of the convergence project by proceeding with the whole orientation. Students organize teams of interest and conduct learning and design activities on convergence technologies and present their results. In the educational improvement activities, professors will share the lesson process and results and discuss improvements through the improvement seminar. As a result of analyzing the effectiveness of the proposed convergence project based teaching and learning model, the convergence project experience has improved the cooperative self - efficacy for the learners and the results were confirmed that students perceived to achieve the expected learning goal and satisfied with their experience.

• ETRI Journal
• /
• 제46권1호
• /
• pp.48-58
• /
• 2024

This paper presents the development of language tutoring systems for nonnative speakers by leveraging advanced end-to-end automatic speech recognition (ASR) and proficiency evaluation. Given the frequent errors in non-native speech, high-performance spontaneous speech recognition must be applied. Our systems accurately evaluate pronunciation and speaking fluency and provide feedback on errors by relying on precise transcriptions. End-to-end ASR is implemented and enhanced by using diverse non-native speaker speech data for model training. For performance enhancement, we combine semisupervised and transfer learning techniques using labeled and unlabeled speech data. Automatic proficiency evaluation is performed by a model trained to maximize the statistical correlation between the fluency score manually determined by a human expert and a calculated fluency score. We developed an English tutoring system for Korean elementary students called EBS AI Peng-Talk and a Korean tutoring system for foreigners called KSI Korean AI Tutor. Both systems were deployed by South Korean government agencies.

• 한국방사선학회논문지
• /
• 제16권5호
• /
• pp.595-602
• /
• 2022

본 연구는 딥러닝을 이용한 흉부 X선 폐렴 영상에 대하여 정확하고 효율적인 의료영상의 자동진단을 위해서 가장 효율적인 학습률을 제시하고자 하였다. Inception V3 딥러닝 모델에 학습률을 0.1, 0.01, 0.001, 0.0001로 각각 설정한 후 3회 딥러닝 모델링을 수행하였다. 그리고 검증 모델링의 평균 정확도 및 손실 함수 값, Test 모델링의 Metric을 성능평가 지표로 설정하여 딥러닝 모델링의 수행 결과로 획득한 결과값의 3회 평균값으로 성능을 비교 평가하였다. 딥러닝 검증 모델링 성능평가 및 Test 모델링 Metric에 대한 성능평가의 결과, 학습률 0.001을 적용한 모델링이 가장 높은 정확도와 우수한 성능을 나타내었다. 이러한 이유로 본 논문에서는 딥러닝 모델을 이용한 흉부 X선 영상에 대한 폐렴 유무 분류 시 학습률을 0.001로 적용할 것을 권고한다. 그리고 본 논문에서 제시하는 학습률의 적용을 통한 딥러닝 모델링 시 흉부 X선 영상에 대한 폐렴 유무 분류에 대한 인력의 보조적인 역할을 수행할 수 있을 거라고 판단하였다. 향후 딥러닝을 이용한 폐렴 유무 진단 분류 연구가 계속해서 진행될 시, 본 논문의 논문 연구 내용은 기초자료로 활용될 수 있다고 여겨지며 나아가 인공지능을 활용한 의료영상 분류에 있어 효율적인 학습률 선택에 도움이 될 것으로 기대된다.

• 한국ITS학회 논문지
• /
• 제19권3호
• /
• pp.28-37
• /
• 2020

본 연구는 공공자전거의 대여량을 예측하는 딥러닝 모형을 개발하였다. 이를 위하여 공공자전거 대여량 자료, 기상 자료, 그리고 지하철 이용량 자료를 수집하였다. 지수평활 모형, ARIMA 모형과 LSTM기반의 딥러닝 모형을 구축한 후 MSE와 MAE 평가 지표를 사용하여 예측 오차를 비교·평가하였다. 평가 결과, 지수평활 모형으로 MSE 348.74, MAE 14.15 값이 산출되었다. ARIMA 모형으로 MSE 170.10, MAE 9.30 값을 얻었다. 그리고 딥러닝 모형으로 MSE 120.22, MAE 6.76 값이 산출되었다. 지수평활 모형의 값과 비교하여 ARIMA 모형의 MSE는 51%, MAE는 34% 감소하였다. 그리고 딥러닝 모형의 MSE는 66%, MAE는 52% 감소하여 딥러닝 모형의 오차가 가장 적은 것으로 파악되었다. 이러한 결과로부터 공공자전거 대여량 예측 분야에서 딥러닝 모형의 적용시 예측 오차를 크게 감소시킬 수 있을 것으로 판단된다.

• 한국항행학회논문지
• /
• 제25권6호
• /
• pp.569-575
• /
• 2021

딥러닝은 데이터의 품질과 모델에 따라 예측 성능에 차이를 보인다. 본 연구는 발전량 예측에 가장 영향을 주는 일사량 예측을 위한 최적의 딥러닝 모델을 구축하기 위해 다양한 입력 데이터와 다중 딥러닝 모델을 사용하였다. 입력 데이터는 기상청의 기상 데이터와 천리안 기상영상을 기상청 지역의 영상을 분할하여 사용하였다, 본 연구는 기본적인 딥러닝 모델인 DNN, LSTM, CNN 모델에 대해 중간층의 깊이와 노드를 변경하여 일사량을 예측하여, 비교 평가하였다, 또한, 각 모델에서 가장 좋은 오차율을 가진 모델을 연결한 다증 딥러닝 모델을 구축하여 일사량을 예측하였다. 실험 결과로서 다중 딥러닝 모델인 모델 A의 RMSE는 0.0637이며, 모델 B의 RMSE는 0.07062이며, 모델 C의 RMSE는 0.06052로서 단일 모델보다 모델 A 그리고 모델 C의 오차율이 좋았다. 본 연구는 실험을 통해 두 개 이상의 모델을 연결한 모델이 향상된 예측률과 안정된 학습 결과를 보였다.

• 소성∙가공
• /
• 제31권4호
• /
• pp.229-239
• /
• 2022

Convolution Neural Network(CNN) is a class of deep learning algorithms and can be used for image analysis. In particular, it has excellent performance in finding the pattern of images. Therefore, CNN is commonly applied for recognizing, learning and classifying images. In this study, the surface defect classification performance of Al 6061 extruded material using CNN-based algorithms were compared and evaluated. First, the data collection criteria were suggested and a total of 2,024 datasets were prepared. And they were randomly classified into 1,417 learning data and 607 evaluation data. After that, the size and quality of the training data set were improved using data augmentation techniques to increase the performance of deep learning. The CNN-based algorithms used in this study were VGGNet-16, VGGNet-19, ResNet-50 and DenseNet-121. The evaluation of the defect classification performance was made by comparing the accuracy, loss, and learning speed using verification data. The DenseNet-121 algorithm showed better performance than other algorithms with an accuracy of 99.13% and a loss value of 0.037. This was due to the structural characteristics of the DenseNet model, and the information loss was reduced by acquiring information from all previous layers for image identification in this algorithm. Based on the above results, the possibility of machine vision application of CNN-based model for the surface defect classification of Al extruded materials was also discussed.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2006년도 학술발표회 논문집
• /
• pp.354-359
• /
• 2006

The analysis of large-scale water resources systems is often complicated by the presence of multiple reservoirs and diversions, the uncertainty of unregulated inflows and demands, and conflicting objectives. Reinforcement learning is presented herein as a new approach to solving the challenging problem of stochastic optimization of multi-reservoir systems. The Q-Learning method, one of the reinforcement learning algorithms, is used for generating integrated monthly operation rules for the Keum River basin in Korea. The Q-Learning model is evaluated by comparing with implicit stochastic dynamic programming and sampling stochastic dynamic programming approaches. Evaluation of the stochastic basin-wide operational models considered several options relating to the choice of hydrologic state and discount factors as well as various stochastic dynamic programming models. The performance of Q-Learning model outperforms the other models in handling of uncertainty of inflows.

• Educational Technology International
• /
• 제7권2호
• /
• pp.23-44
• /
• 2006

As the educational paradigm has shifted from the traditional knowledge oriented instruction learning to the knowledge product oriented instructional learning, the development of student's creativity becomes one of the most important educational goals, because the ability that can produce the knowledge creatively is required in the digital information knowledge based society. The purpose of this study is to make a basic direction and strategy for the instructional design to develop an on and off line blended instructional design which will help a learning community to be a more collaborative and creative learning community. This research has investigated the concept and the characteristics of collaborative creativity and creative problem solving as the theoretical basis of the design. After that, on the basis of the theories connected with the collaborative creativity theory, the direction and the strategies for the development of collaborative creativity was designed. The design was applied into the real learning community and finally proved the effectiveness of the learning model for the development of the collaborative creativity by the quantitative evaluation.