• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.6
• /
• pp.606-611
• /
• 2014

The understanding of another's behavior is a fundamental cognitive ability for primates including humans. Recent neuro-physiological studies suggested that there is a direct matching algorithm from visual observation onto an individual's own motor repertories for interpreting cognitive ability. The mirror neurons are known as core regions and are handled as a functionality of intent recognition on the basis of imitative learning of an observed action which is acquired from visual-information of a goal-directed action. In this paper, we addressed previous works used to model the function and mechanisms of mirror neurons and proposed a computational model of a mirror neuron system which can be used in human-robot interaction environments. The major focus of the computation model is the reproduction of an individual's motor repertory with different embodiments. The model's aim is the design of a continuous process which combines sensory evidence, prior task knowledge and a goal-directed matching of action observation and execution. We also propose a biologically inspired plausible equation model.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.41-49
• /
• 2018

The purpose of this study is to investigate the effect of computer pointing game on the visual perception ability of children with severe intellectual disability. Based on a literature review, we developed a computer pointing game to improve visual perception ability, which consisted of three stages; catching a hamburger, catching a hamburger and a soda, and catching various foods. At each stage, different instructional models were applied by difficulty level of the contents. Experiments were performed among four children with severe intellectual disabilities for three weeks. They belonged to H public school in Kyeonggi, Korea. Their visual perceptions were quantitatively measured four times by utilizing the Korean Developmental Test of Visual Perception tool (K-DTVP-2). For qualitative evaluation, an observation assessment diary was written and analyzed. All four children at the fourth test showed better visual perception ability, compared with the ability at the first test. As a result of the analysis of the observation assessment, they were considered successful in their learning and ordinary life related to visual perception. It can be concluded that the computer pointing game may play a role in helping children with severe intellectual disabilities improve their visual perception ability.

• School Mathematics
• /
• v.5 no.3
• /
• pp.275-295
• /
• 2003

This study intends to understand the practice of elementary school mathematics education, focusing on the teaching and learning methods. To achieve these goals, we reviewed and analysed instructional methods pertaining to both (general) pedagogy and mathematics education. And we designed and implemented a questionnaire survey regarding the elementary school teachers' opinions. Moreover, we observed several mathematics lessons of elementary school to understand better the practice of teaching and learning. From these survey and observation, we learned several important aspects of investigation and development of instructional methods.

• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1195-1202
• /
• 2018

Artificial neural network is widely used for its excellent performance and implementability. However, traditional neural network needs to learn the system from scratch, with the addition of new input data, the variation of the observation environment, or the change in the form of input/output data. To resolve such a problem, the technique of transfer learning has been proposed. Transfer learning constructs a newly developed target system partially updating existing system and hence provides much more efficient learning process. Until now, transfer learning is mainly studied in the field of image processing and is not yet widely employed in acoustic data processing. In this paper, focusing on the scalability of transfer learning, we apply the concept of transfer learning to the problem of guitar chord classification and evaluate its performance. For this purpose, we build a target system of convolutional neutral network (CNN) based 48 guitar chords classification system by applying the concept of transfer learning to a source system of CNN based 24 guitar chords classification system. We show that the system with transfer learning has performance similar to that of conventional system, but it requires only half the learning time.

• Journal of Korean Elementary Science Education
• /
• v.26 no.3
• /
• pp.329-340
• /
• 2007

This study is to find out how well elementary school gardens work as places of observation learning. We compared the tree species planted in elementary school gardens with those which appeared in the science textbooks of the 7th Korean National Curriculum. The number of tree species are 60 throughout all the grades, specifically; 43 in the third grade, 22 in the fifth grade, 16 in the first grade, 15 in the second grade, 8 in the sixth grade, and 5 in the fourth grade, respectively. Their frequency of appearance (hereafter referred to as 'appearance frequency') throughout all the grades is 175, and the maximum frequency is 62 in the third grade. Of particular note is the fact that the appearance frequency in one grade was very high, meaning that a repeat study will not be conducted. The total number of tree species counted in the study was 13,028 and consisted of 167 species in 52 families. Only 23% of the total planted tree species, that is, 38 tree species appeared in the textbooks, so the ratio of the practical usage of school gardens was revealed to be low. In the school gardens, there are only an average of about 16 tree species per school. The fewest number of species in one school was 9 and the most was 22. The native species were 74 and the non-native species were 93. This means that almost all the planted species do not relate to observation learning in the textbooks. The 22 tree species among 60 species in the textbooks were not planted in the gardens. In conclusion, the degree of utilization of almost all the elementary school gardens examined during this investigation was very low.

• Journal of the Korean earth science society
• /
• v.43 no.3
• /
• pp.430-445
• /
• 2022

The purpose of this study was to explore the learning effects in elementary school students who participated in a geological field trip conducted under the theme 'minerals and rocks', focusing on novelty space. A total of 10 sixth-grade students participated in this program held at a public elementary school in Seoul as part of after-school club activities. Students observed mineral and rock samples in a classroom and outdoor learning environment. The authors collected activity papers (texts, drawing), researchers' participation notes, video and audio recordings containing the study participants' activities, and post-interview data To analyze the learning effects in the cognitive domain of students, the observation analysis framework for rock classification of Remmen and Frøyland (2020) and the rock description analysis framework of Oh (2020) were used. Additionally, to explore the learning effects of psychological and geographic areas, students' drawings, texts, discourses, and interview data were inductively analyzed. The results showed that the students demonstrated 'everyday' and 'transitional' observations in the classroom learning environment, while in the outdoor learning environment (school playground, community-based activities), they demonstrated 'transitional' and 'scientific' observations. Moreover, as the scientific observation stage progressed, more types of descriptive words for rocks were used. In terms of psychological and geographic aspects, students showed their selection of places to explore familiar outdoor learning environments, positive perceptions of outdoor learning, and aesthetic appreciation. Finally, this study not only discussed novelty space as a tool for analyzing students' learning effects but also suggested the need for an academic approach considering new learning environments, such as learning through virtual field trips.

• Journal of Korean Elementary Science Education
• /
• v.35 no.2
• /
• pp.253-264
• /
• 2016

The purpose of this study was to investigate implications of self-directed learning experiments in elementary science education through understanding elementary school students' awareness of their experiences in self-directed learning experiments. Twenty students joined the school science club voluntarily and conducted self-directed learning experiments. We collected data through observation of the experiments, interviews, and questionnaires. The students who participated in the club showed high satisfaction with self-directed learning experiments. The participants were aware that their scientific interest and knowledge, and the confidence in conducting experiments were increased. The students felt positive about the inquiry process of conducting self-directed learning experiments with their own subjects. They also felt a sense of achievement in attempting their experiments in defiance of several failures. The participants realized that the self-directed inquires led to increased declarative and procedural knowledge of science. The students stated that they had some difficulties in coping with the different results contrary to expectations and preparing laboratory materials and instruments. Nonetheless, they showed the promotion of their scientific literacy during overcoming those difficulties. We suggest that self-directed learning experiments can be a more effective way in science learning to make students experience the nature of science than existing school experiments. This can be implemented through a creative experience activities such as science clubs.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.1
• /
• pp.44-51
• /
• 2003

Knowledge acquisition is a bottleneck in knowledge-based system implementation. Decision tree induction is a useful machine learning approach for extracting classification knowledge from a set of training examples. Many real-world data contain fuzziness due to observation error, uncertainty, subjective judgement, and so on. To cope with this problem of real-world data, there have been some works on fuzzy classification rule learning. This paper makes a survey for the kinds of fuzzy classification rules. In addition, it presents a fuzzy classification rule learning method based on decision tree induction, and shows some experiment results for the method.

• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.614-618
• /
• 2016

As information on the internet and the data from smart devices are growing, the amount of stream data is also increasing in the real world. The stream data, which is a potentially large data, requires online learnable models and algorithms. In this paper, we propose a novel class of models: predictive convolutional neural networks to be able to perform online learning. These models are designed to deal with longer patterns as the layers become higher due to layering convolutional operations: detection and max-pooling on the time axis. As a preliminary check of the concept, we chose two-month gathered GPS data sequence as an observation sequence. On learning them with the proposed method, we compared the original sequence and the regenerated sequence from the abstract information of the models. The result shows that the models can encode long-range patterns, and can generate a raw observation sequence within a low error.

• Journal of Korean Society of Water and Wastewater
• /
• v.34 no.1
• /
• pp.35-43
• /
• 2020

Turbidity has various effects on the water quality and ecosystem of a river. High turbidity during floods increases the operation cost of a drinking water supply system. Thus, the management of turbidity is essential for providing safe water to the public. There have been various efforts to estimate turbidity in river systems for proper management and early warning of high turbidity in the water supply process. Advanced data analysis technology using machine learning has been increasingly used in water quality management processes. Artificial neural networks(ANNs) is one of the first algorithms applied, where the overfitting of a model to observed data and vanishing gradient in the backpropagation process limit the wide application of ANNs in practice. In recent years, deep learning, which overcomes the limitations of ANNs, has been applied in water quality management. LSTM(Long-Short Term Memory) is one of novel deep learning algorithms that is widely used in the analysis of time series data. In this study, LSTM is used for the prediction of high turbidity(>30 NTU) in a river from the relationship of turbidity to discharge, which enables early warning of high turbidity in a drinking water supply system. The model showed 0.98, 0.99, 0.98 and 0.99 for precision, recall, F1-score and accuracy respectively, for the prediction of high turbidity in a river with 2 hour frequency data. The sensitivity of the model to the observation intervals of data is also compared with time periods of 2 hour, 8 hour, 1 day and 2 days. The model shows higher precision with shorter observation intervals, which underscores the importance of collecting high frequency data for better management of water resources in the future.