• The Journal of the Korea Contents Association
• /
• v.22 no.3
• /
• pp.197-211
• /
• 2022

This study examines the structural relationship between parents' positive parenting attitudes, negative parenting attitudes, emotional problems, and academic helplessness. To this end, the data of 2,590 first-year middle school students in the Korean Children and Youth Panel Survey 2018 were used to understand the structural relationship between variables. For this study, the correlation between variables was examined with SPSS 21.0, and the structural relationship between variables was identified with AMOS 21.0. The research results are as follows. First, it was found that the positive parenting attitude and negative parenting attitude of parents had a significant effect on academic helplessness. Second, parents' positive and negative parenting attitudes had a significant effect on emotional problems. Third, emotional problems had a significant positive effect on academic ability. Fourth, emotional problems were partially mediated between parents' positive parenting attitudes, negative parenting attitudes, and academic helplessness. In other words, the emotions of adolescents affected by their parents' parenting attitudes affect their learning. Through this study, it is meaningful to confirm that emotional problems can be treated as factors that influence studies, not simply limited to factors influenced by other factors.

• Journal of Korean Elementary Science Education
• /
• v.42 no.1
• /
• pp.1-16
• /
• 2023

This study investigated the level of academic passion for pre-service elementary teachers' science pedagogical content knowledge (PCK) and the factors that influence the passion. To this end, 182 first to fourth grade students in advanced non-science majors who were taking science-related courses in the second semester were selected, and two tests were then administered to evaluate their academic passions for science subject matter knowledge and science pedagogical knowledge. Individual in-depth interviews were also conducted with some of the participants. It was found that the factors such as "importance" and "harmonious passion" for learning science subject matter knowledge and science pedagogical knowledge were found at a high level. On the other hand, the factors such as "like" and "investment of time and energy" were slightly higher than normal, and the factor such as "obsessive passion" was slightly lower than normal. The differences in academic passion for science subject matter knowledge and science pedagogical knowledge were greater according to the high school track than the grade. The pre-service elementary teachers selected more often the factors such as "individual interests", "high school track", "contents of science-related courses at the university of education", "characteristics of professor in charge of science-related courses at the university of education", and "experience in teaching practicum" as the factors that influenced their academic passion for science subject matter knowledge and science pedagogical knowledge. However, there was a slight difference in the selection ratio depending on the high school track.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.15-30
• /
• 2023

Recently, various services using artificial intelligence(AI) are emerging in the media field as well However, most of the video editing, which involves finding an editing point and attaching the video, is carried out in a passive manner, requiring a lot of time and human resources. Therefore, this study proposes a methodology that can detect the edit points of video according to whether person in video are spoken by using Video Swin Transformer. First, facial keypoints are detected through face alignment. To this end, the proposed structure first detects facial keypoints through face alignment. Through this process, the temporal and spatial changes of the face are reflected from the input video data. And, through the Video Swin Transformer-based model proposed in this study, the behavior of the person in the video is classified. Specifically, after combining the feature map generated through Video Swin Transformer from video data and the facial keypoints detected through Face Alignment, utterance is classified through convolution layers. In conclusion, the performance of the image editing point detection model using facial keypoints proposed in this paper improved from 87.46% to 89.17% compared to the model without facial keypoints.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.284-290
• /
• 2024

Speech emotion recognition (SER) is a technique that is used to analyze the speaker's voice patterns, including vibration, intensity, and tone, to determine their emotional state. There has been an increase in interest in artificial intelligence (AI) techniques, which are now widely used in medicine, education, industry, and the military. Nevertheless, existing researchers have attained impressive results by utilizing acted-out speech from skilled actors in a controlled environment for various scenarios. In particular, there is a mismatch between acted and spontaneous speech since acted speech includes more explicit emotional expressions than spontaneous speech. For this reason, spontaneous speech-emotion recognition remains a challenging task. This paper aims to conduct emotion recognition and improve performance using spontaneous speech data. To this end, we implement deep learning-based speech emotion recognition using the VGG (Visual Geometry Group) after converting 1-dimensional audio signals into a 2-dimensional spectrogram image. The experimental evaluations are performed on the Korean spontaneous emotional speech database from AI-Hub, consisting of 7 emotions, i.e., joy, love, anger, fear, sadness, surprise, and neutral. As a result, we achieved an average accuracy of 83.5% and 73.0% for adults and young people using a time-frequency 2-dimension spectrogram, respectively. In conclusion, our findings demonstrated that the suggested framework outperformed current state-of-the-art techniques for spontaneous speech and showed a promising performance despite the difficulty in quantifying spontaneous speech emotional expression.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.67-74
• /
• 2024

In this paper, we present a study aimed at analyzing how different rainfall measurement methods affect the performance of reservoir water level predictions. This work is particularly timely given the increasing emphasis on climate change and the sustainable management of water resources. To this end, we have employed rainfall data from ASOS, AWS, and Thiessen Network-based measures provided by the KMA Weather Data Service to train our neural network models for reservoir yield predictions. Our analysis, which encompasses 34 reservoirs in Jeollabuk-do Province, examines how each method contributes to enhancing prediction accuracy. The results reveal that models using rainfall data based on the Thiessen Network's area rainfall ratio yield the highest accuracy. This can be attributed to the method's accounting for precise distances between observation stations, offering a more accurate reflection of the actual rainfall across different regions. These findings underscore the importance of precise regional rainfall data in predicting reservoir yields. Additionally, the paper underscores the significance of meticulous rainfall measurement and data analysis, and discusses the prediction model's potential applications in agriculture, urban planning, and flood management.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of The Korean Association of Information Education
• /
• v.24 no.4
• /
• pp.369-378
• /
• 2020

This paper examines inquiries generated in three different online educational programs in Korea at the secondary educational level. Data covers 12,023 inquiries recorded during the first semester of 2019 and the compared groups among three programs are divided by four criteria: its type, period, inquirer, and the way of response. Statistical comparisons using Chi-square test suggest that there are significant differences in frequency rates of inquiries among three programs. First, 'Program A' has more inquiries by student themselves, mostly in the middle of the semester about the contents. Second, inquiries are more frequent for 'Program B' by the coordinating teachers about system-related or evaluation-related questions, either at the beginning or the end of the semester. Third, in the case of 'Program C', parents of health-impaired students are the main inquirers who ask admin-related questions at the beginning of the semester. With respect to the way of response to inquiries, more than 95% of inquiries are answered immediately for all three programs. These quantitative findings are also supported qualitatively, by face-to-face interviews with operators of the three programs. Results of this paper can be used for educational practitioners and experts when they design and operate the customized online educational programs with different purposes and different target-students in the future.

• Korean Journal of Cognitive Science
• /
• v.23 no.4
• /
• pp.425-455
• /
• 2012

Multi-dimensional verbal short-term memory mechanisms are largely divided into the phonological channel and the lexical-semantic channel. The former is called phonological short-term memory and the latter is called semantic short-term memory. Phonological short-term memory is further segmented into the phonological input buffer and the phonological output buffer. In this study, the language performance of each of three patients with similar levels of conduction aphasia was analyzed in terms of multi-dimensional verbal short-term memory. To this end, three patients with conduction aphasia were instructed to perform four different aspects of language tasks that are spontaneous speaking, repetition, spontaneous writing, and dictation in both word and sentence level. Moreover, the patients' phonological memories and semantic short-term memories were evaluated using digit span tests and verbal learning tests. As a result, the three subjects exhibited various types of performances and error responses in the four aspects of language tests, and the short-term memory tests also did not produce identical results. The language performance of three patients with conduction aphasia can be explained according to whether the defects occurred in the semantic short-term memory, phonological input buffer and/or phonological output buffer. In this study, the relations between language and multi-dimensional verbal short-term memory were discussed based on the results of language tests and short-term memory tests in patients with conduction aphasia.

• Journal of Educational Research in Mathematics
• /
• v.27 no.2
• /
• pp.291-312
• /
• 2017

According to the current research of educational assessment, formative assessment which focuses on improving students' learning has been emphasized. Consequently, integration between instruction and assessment is crucial and various assessment strategies are required. In order to use different assessment strategies in classrooms, teachers should experience strategies and reflect their strengths and weaknesses. In this study, pre-service elementary teachers experienced six assessment strategies (feedback, providing assessment standard, providing exemplary cases, self assessment, peer assessment, and written assessment), and their perceptions toward each strategy were investigated. During one semester, pre-service teachers experienced each of them and they answered questionnaire at the end of the semester. From the results, it is found that pre-service teachers presented different strategies that were most helpful in their cognitive and affective domain according to their perception of assessment. The results imply that different assessment strategies should be applied in instruction and teachers should extend their perception of assessment purposes.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.406-414
• /
• 2019

The purpose of this study was to investigate how educational experience (teaching experience, experience participating in the Teacher Learning Community, curriculum training experience, and innovative experience working in school) of elementary school teachers affects the recognition and execution of curriculum and textbooks. For this purpose, the results of a questionnaire survey for elementary school teachers were analyzed by performing T-tests, One-Way ANOVA, correlation analysis, and regression analysis. The results were as follows. First, according to the teacher's educational experience, there were statistically significant differences in the recognition and execution of curriculum reorganization, and the recognition and dependence on textbooks. Second, there were statistically significant correlations among such variables as recognition and implementation of curriculum reorganization, and the recognition and dependence on textbooks. Third, the teacher's educational experience had a significant impact on curriculum reorganization and the dependence on textbooks. Curriculum restructuring in elementary schools is not an end in itself. What is also needed is to find and implement the best class plans for promoting the .meaningful growth and development of elementary school students. This study suggests that the dependence on textbooks should be lowered and the curriculum should be actively reorganized, and teachers should develop their expertise based on extensive educational experience.