• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.2
• /
• pp.150-154
• /
• 2006

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition are determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.1
• /
• pp.52-57
• /
• 2005

In the foe of global competition, the requirements for the continuously increasing productivity, flexibility and quality(dimensional accuracy, mechanical properties and surface properties) have imposed a mai or change on steel manufacturing industries. Indeed, one of the keys to achieve this goal is the automation of the steel-making process using AI(Artificial Intelligence) techniques. The automation of hot rolling process requires the developments of several mathematical models for simulation and quantitative description of the industrial operations involved. In this paper, an on-line training neural network for both long-term teaming and short-term teaming was developed in order to improve the prediction of rolling force in hot rolling mill. This analysis shows that the predicted rolling force is very closed to the actual rolling force, and the thickness error of the strip is considerably reduced.

• Journal of Korean Elementary Science Education
• /
• v.37 no.1
• /
• pp.66-79
• /
• 2018

The purpose of this study is to explore how pre-service elementary teachers perceive and use smart learning environments. For this purpose, 23 pre-service elementary teachers who took theory and practice in a science education course were asked to develop lesson materials using smart tools and make a self-report questionnaire. These data were categorized in an instructional, exploratory, and interactive approach, depending on how they guided students to access knowledge and information. As a result of the study, pre-service teachers perceived the smart tools as the exploratory and interactive learning tools to be used for students to actively search for and interact with data and knowledge. But in developing lesson materials, they usually used the smart tools for resource sharing and communication in the instructional manner. In conclusion, the gap between their perception of smart tools and lesson materials, and the educational implications will be discussed.

• Journal for History of Mathematics
• /
• v.28 no.4
• /
• pp.191-204
• /
• 2015

The reason of the confusion of learners about the logic concepts such as implication, necessary condition and sufficient condition can be analyzed from the point of view of history of logic, discrepancy between ordinary language and formal logic, and reification which occurs in the process of cognition of discursive object and also indicates the necessity of a research. This study analysed the difficulties related to study and implication concept and attempted to the reflection of textbook and curriculum. Not that ordinary language makes the introduction of formal language easier, but that this study discussed the possibilities ordinary language intervenes the learning of formal language. This study additionally intended to understand learning difficulties of concrete subjects, abstract subjects and the gap between primary object and discursive object by understanding the process of sagging, encapsulating and reifying.

• ETRI Journal
• /
• v.29 no.5
• /
• pp.700-702
• /
• 2007

We present a relevance feedback approach based on multi-class support vector machine (SVM) learning and cluster-merging which can significantly improve the retrieval performance in region-based image retrieval. Semantically relevant images may exhibit various visual characteristics and may be scattered in several classes in the feature space due to the semantic gap between low-level features and high-level semantics in the user's mind. To find the semantic classes through relevance feedback, the proposed method reduces the burden of completely re-clustering the classes at iterations and classifies multiple classes. Experimental results show that the proposed method is more effective and efficient than the two-class SVM and multi-class relevance feedback methods.

• Asia Pacific Journal of Corpus Research
• /
• v.2 no.1
• /
• pp.1-11
• /
• 2021

Recently, corpus assisted vocabulary instruction has been attracting a lot of interest. Most studies have focused on understanding language learners' receptive vocabulary knowledge. Limited attention has been paid to learners' productive competence. To fill this gap, this study attended to learners' productive lexical development in terms of form, meaning and use respectively. This study introduced EFL learners to the corpus-based language pedagogy to learn COVID-19 theme-based vocabulary. To investigate the gains and views of 33 EFL first-year college students, a sentence completion task and a questionnaire were developed. Learners' productive performances in the three lexical knowledge aspects (i.e., form, meaning and use) were particularly targeted. The results revealed that the students achieved significant gains in all aspects regardless of their proficiency level. In particular, the less proficient students achieved greater knowledge retention compared with their highly proficient counterparts. Meanwhile, students showed positive attitudes towards the corpus-based approach to vocabulary learning.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.1
• /
• pp.269-274
• /
• 2023

In this paper, we proposed a new UNet 3+ model for medical image segmentation. The proposed ensemble(E) UNet 3+ model consists of UNet 3+s of varying depths into one unified architecture. UNet 3+s of varying depths have same encoder, but have their own decoders. They can bridge semantic gap between encoder and decoder nodes of UNet 3+. Deep supervision was used for learning on a total of 8 nodes of the E-UNet 3+ to improve performance. The proposed E-UNet 3+ model shows better segmentation results than those of the UNet 3+. As a result of the simulation, the E-UNet 3+ model using deep supervision was the best with loss function values of 0.8904 and 0.8562 for training and validation data. For the test data, the UNet 3+ model using deep supervision was the best with a value of 0.7406. Qualitative comparison of the simulation results shows the results of the proposed model are better than those of existing UNet 3+.

• Journal of information and communication convergence engineering
• /
• v.22 no.1
• /
• pp.56-63
• /
• 2024

Despite the rapid strides in content-based image retrieval, a notable disparity persists between the visual features of images and the semantic features discerned by humans. Hence, image retrieval based on the association of semantic similarities recognized by humans with visual similarities is a difficult task for most image-retrieval systems. Our study endeavors to bridge this gap by refining image semantics, aligning them more closely with human perception. Deep learning techniques are used to semantically classify images and retrieve those that are semantically similar to personalized images. Moreover, we introduce a keyword-based image retrieval, enabling automatic labeling of images in mobile environments. The proposed approach can improve the performance of a mobile device with limited resources and bandwidth by performing retrieval based on the visual features and keywords of the image on the mobile device.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.9
• /
• pp.697-706
• /
• 2020

The relationship between education and work is of the greatest concern to individuals and society because they are the key drivers of growth and development. In the context of Industry 4.0, labor and educators are facing the challenges of big changes in the workplace. How to prepare undergraduate students for the world of employment has become the most important mission of higher education providers. This paper explored the competency gap in the labor market in Vietnam from the perspective of employees who have been dissatisfied with the current status. First, a qualitative method with the Delphi technique was applied to confirm this consensus in an employees' competency model. Then, the satisfaction level for each competency criterion was explored by applying the advance quantitative method, namely, best non-fuzzy performance approach. Lifelong learning was ranked first, followed by creativity and innovation, foreign languages, expertise and digitalization, adaptability, and finally, organizing and managing ability. Critical thinking and problem-solving were perceived to have the biggest gap. The order of competency satisfaction is useful in explaining the mismatch between education quality and labor market demand. The findings provide valuable guidelines for education managers who seek to bridge the competency gap and improve education quality.

• Journal of Digital Policy
• /
• v.3 no.1
• /
• pp.11-20
• /
• 2024

The intelligent information society is expected to drastically change our lives. The purpose of this content is to derive tasks in the field of media education for the elderly for the realization of digital inclusion in an intelligent information society. To this end, the vision, goals, strategies, and tasks of the intelligent information society were examined through the 6th National Informatization Basic Plan(2018~2022) and the 2022 Education Informatization White Paper(2022). In addition, the current status of the digital gap among the elderly classified as vulnerable groups was identified through the results of the 2022 Digital Information Gap Survey. In order to ease the digital information gap between the elderly in the intelligent information society, it is believed that the development of intelligent media education services using intelligent information technology, provision of media education services for the elderly through learning online service channels, and support for digital intelligent media education for the elderly are necessary.