• Korean Linguistics
• /
• v.63
• /
• pp.103-132
• /
• 2014

This study compares various speech rates of Korean learners with those of native Korean. Speech data were collected from 34 native Koreans and 33 Korean learners (19 Chinese and 14 Japanese). Each participant recorded a 9 syllabled Korean sentence at three different speech rate types. A total of 603 speech samples were analyzed by speech rate types (normal, slow, and fast), native languages (Korean, Chinese, Japanese), and learners' proficiency levels (beginner, intermediate, and advanced). We found that learners' L1 background plays a role in categorizing different speech rates in the L2 (Korean), and also that the leaners' proficiency correlates with the increase of speaking rate regardless of speech rate categories. More importantly, faster speech rate values found in the advanced level of learners do not necessarily match to the native speakers' speech rate categories. This means that learning speech rate categories can be more complex than we think of proficiency or fluency. That is, speech rate categories may not be acquired automatically during the course of second language learning, and implicit or explicit exposures to various rate types are necessary for second language learners to acquire a high level of communicative skills including speech rate variation. This paper discusses several pedagogical implications in terms of teaching pronunciation to second language learners.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.127-132
• /
• 2021

This paper applies a machine learning model to forecasting freight rates in dry bulk and tanker markets with wavelet decomposition and empirical mode decomposition because they can refect both information scattered in the time and frequency domain. The decomposition with wavelet is outperformed for the dry bulk market, and EMD is the more proper model in the tanker market. This result provides market players with a practical short-term forecasting method. This study contributes to expanding a variety of predictive methodologies for one of the highly volatile markets. Furthermore, the proposed model is expected to improve the quality of decision-making in spot freight trading, which is the most frequent transaction in the shipping industry.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3914-3924
• /
• 2024

The release source term of radioactivity becomes a critical foundation for emergency response and accident consequence assessment after a nuclear accident Rapidly and accurately inverting the source term remains an urgent scientific challenge. Today source term inversion based on meteorological data and gamma dose rate measurements is a common method. But gamma dose rate actually includes all nuclides information, and the composition of radioactive nuclides is generally uncertain. This paper introduces a novel nuclear accident source term inversion model, which is Improve Snow Ablation Optimizer-Sensitivity Analysis Pruning Extreme Learning Machine (ISAO-SAELM) model. The model inverts the release rates of 11 radioactive nuclides (I-131, Xe-133, Cs-137, Kr-88, Sr-91, Te-132, Mo-99, Ba-140, La-140, Ce-144, Sb-129). It does not require the use of the physical field of the reactor to obtain prior information and establish a dispersion model. And the robustness is validated through noise analysis test. The mean absolute errors of the release rates of 11 nuclides are 15.52 %, 15.28 %, 15.70 %, 14.99 %, 14.85 %, 15.61 %, 15.96 %, 15.42 %, 15.84 %, 15.13 %, 17.72 %, which show the significant superiority of ISAO-SAELM. ISAO-SAELM model not only achieves notable advancements in accuracy but also receives validation in terms of practicality and feasibility.

• Journal of Korea Water Resources Association
• /
• v.55 no.8
• /
• pp.565-575
• /
• 2022

Recently, in the field of water resource engineering, interest in predicting time series water levels and flow rates using deep learning technology that has rapidly developed along with the Fourth Industrial Revolution is increasing. In addition, although water-level and flow-rate prediction have been performed using the Long Short-Term Memory (LSTM) model and Gated Recurrent Unit (GRU) model that can predict time-series data, the accuracy of flow-rate prediction in rivers with rapid temporal fluctuations was predicted to be very low compared to that of water-level prediction. In this study, the Paldang Bridge Station of the Han River, which has a large flow-rate fluctuation and little influence from tidal waves in the estuary, was selected. In addition, time-series data with large flow fluctuations were selected to collect water-level and flow-rate data for 2 years and 7 months, which are relatively short in data length, to be used as training and prediction data for the LSTM and GRU models. When learning time-series water levels with very high time fluctuation in two models, the predicted water-level results in both models secured appropriate accuracy compared to observation water levels, but when training rapidly temporal fluctuation flow rates directly in two models, the predicted flow rates deteriorated significantly. Therefore, in this study, in order to accurately predict the rapidly changing flow rate, the water-level data predicted by the two models could be used as input data for the rating curve to significantly improve the prediction accuracy of the flow rates. Finally, the results of this study are expected to be sufficiently used as the data of flood warning system in urban rivers where the observation length of hydrological data is not relatively long and the flow-rate changes rapidly.

• Journal of Korean Neurosurgical Society
• /
• v.66 no.1
• /
• pp.53-62
• /
• 2023

Objective : Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability. Methods : A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm's diagnostic performance. Results : In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anterior-posterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor. Conclusion : The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.205-217
• /
• 2018

Deep learning using convolutional neural networks (CNNs) is being studied in various fields of image recognition and these studies show excellent performance. In this paper, we compare the performance of CNN architectures, KCR-AlexNet and KCR-GoogLeNet. The experimental data used in this paper is obtained from PHD08, a large-scale Korean character database. It has 2,187 samples of each Korean character with 2,350 Korean character classes for a total of 5,139,450 data samples. In the training results, KCR-AlexNet showed an accuracy of over 98% for the top-1 test and KCR-GoogLeNet showed an accuracy of over 99% for the top-1 test after the final training iteration. We made an additional Korean character dataset with fonts that were not in PHD08 to compare the classification success rate with commercial optical character recognition (OCR) programs and ensure the objectivity of the experiment. While the commercial OCR programs showed 66.95% to 83.16% classification success rates, KCR-AlexNet and KCR-GoogLeNet showed average classification success rates of 90.12% and 89.14%, respectively, which are higher than the commercial OCR programs' rates. Considering the time factor, KCR-AlexNet was faster than KCR-GoogLeNet when they were trained using PHD08; otherwise, KCR-GoogLeNet had a faster classification speed.

• Education of Primary School Mathematics
• /
• v.25 no.3
• /
• pp.213-232
• /
• 2022

With the importance of number line in learning fractions, this study investigated how 4th grade students understand fractions and its operations in number line. The questionnaire consisted 22 items which were related to representing fractions, comparing the size of fractions, and operating addition and subtraction of fractions. Both structured number line and sub-structured number line were presented in the items. As results of the study, the overall success rates were not high and even some items showed higher incorrect answer rates than the success rates. Also, the students showed a difficulty in solving non-structured number line tasks. It was also noticeable that students showed several types of incorrect answers, which means that students had incomplete understanding of both fractions and number line. This paper is expected to shed light on elementary students' understanding of fractions and number line and to provide implications of how to deal with number line in teaching and learning fractions in the elementary school.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.569-575
• /
• 2021

Deep learning shows differences in prediction performance depending on data quality and model. This study uses various input data and multiple deep learning models to build an optimal deep learning model for predicting solar radiation, which has the most influence on power generation prediction. did. As the input data, the weather data of the Korea Meteorological Administration and the clairvoyant meteorological image were used by segmenting the image of the Korea Meteorological Agency. , comparative evaluation, and predicting solar radiation by constructing multiple deep learning models connecting the models with the best error rate in each model. As an experimental result, the RMSE of model A, which is a multiple deep learning model, was 0.0637, the RMSE of model B was 0.07062, and the RMSE of model C was 0.06052, so the error rate of model A and model C was better than that of a single model. In this study, the model that connected two or more models through experiments showed improved prediction rates and stable learning results.

• Education of Primary School Mathematics
• /
• v.14 no.3
• /
• pp.237-259
• /
• 2011

Mathematics learning disabilities is a specific learning disorder affecting the normal acquisition of arithmetic and spatial skills. Reported prevalence rates range from 5 to 10 percent and show high rates of comorbid disabilities, such as dyslexia and ADHD. In this study, the characteristics and the causes of this disorder has been examined. The core cause of mathematics learning disabilities is not clear yet: it can come from general cognitive problems, or disorder of innate intuitive number module could be the cause. Recently, researchers try to subdivide mathematics learning disabilities as (1) semantic/memory type, (2) procedural/skill type, (3) visuospatial type, and (4) reasoning type. Each subtype is related to specific brain areas subserving mathematical cognition. Based on these findings, the author has performed a basic research to develop grade specific diagnostic tests: number processing test and math word problems for lower grades and comprehensive math knowledge tests for the upper grades. The results should help teachers to find out prior knowledge, specific weaknesses of students, and plan personalized intervention program. The author suggest diagnostic tests are organized into 6 components. They are number sense, conceptual knowledge, arithmetic facts retrieval, procedural skills, mathematical reasoning/word problem solving, and visuospatial perception tests. This grouping will also help the examiner to figure out the processing time for each component.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.119-128
• /
• 2002

This paper proposes an efficient recognition method of car license plate from the car images by using both the dynamical thresholding and the neural network with enhanced learning algorithm. The car license plate is extracted by the dynamical thresholding based on the structural features and the density rates. Each characters and numbers from the p]ate is also extracted by the contour tracking algorithm. The enhanced neural network is proposed for recognizing them, which has the algorithm of combining the modified ART1 and the supervised learning method. The proposed method has applied to the real-world car images. The simulation results show that the proposed method has better the extraction rates than the methods with information of the gray brightness and the RGB, respectively. And the proposed method has better recognition performance than the conventional backpropagation neural network.