• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.3
• /
• pp.197-205
• /
• 2020

Korean language has the characteristics that the pronunciation of phoneme units such as vowels and consonants are fixed and the pronunciation associated with a notation does not change, so that foreign learners can approach rather easily Korean language. However, when one pronounces words, phrases, or sentences, the pronunciation changes in a manner of a wide variation and complexity at the boundaries of syllables, and the association of notation and pronunciation does not hold any more. Consequently, it is very difficult for foreign learners to study Korean standard pronunciations. Despite these difficulties, it is believed that systematic analysis of pronunciation errors for Korean words is possible according to the advantageous observations that the relationship between Korean notations and pronunciations can be described as a set of firm rules without exceptions unlike other languages including English. In this paper, we propose a visualization framework which shows the differences between standard pronunciations and erratic ones as quantitative measures on the computer screen. Previous researches only show color representation and 3D graphics of speech properties, or an animated view of changing shapes of lips and mouth cavity. Moreover, the features used in the analysis are only point data such as the average of a speech range. In this study, we propose a method which can directly use the time-series data instead of using summary or distorted data. This was realized by using the deep learning-based technique which combines Self-organizing map, variational autoencoder model, and Markov model, and we achieved a superior performance enhancement compared to the method using the point-based data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1321-1330
• /
• 2023

This study attempts to address the problem of 3D pose estimation for multiple human objects through a single image generated during the character development process that can be used in augmented reality. In the existing top-down method, all objects in the image are first detected, and then each is reconstructed independently. The problem is that inconsistent results may occur due to overlap or depth order mismatch between the reconstructed objects. The goal of this study is to solve these problems and develop a single network that provides consistent 3D reconstruction of all humans in a scene. Integrating a human body model based on the SMPL parametric system into a top-down framework became an important choice. Through this, two types of collision loss based on distance field and loss that considers depth order were introduced. The first loss prevents overlap between reconstructed people, and the second loss adjusts the depth ordering of people to render occlusion inference and annotated instance segmentation consistently. This method allows depth information to be provided to the network without explicit 3D annotation of the image. Experimental results show that this study's methodology performs better than existing methods on standard 3D pose benchmarks, and the proposed losses enable more consistent reconstruction from natural images.

• Communications of Mathematical Education
• /
• v.38 no.2
• /
• pp.93-120
• /
• 2024

On-line education in mathematics education changed in various aspects before and after COVID-19. This study conducted a systematic literature review of 98 academic papers on on-line education published from 2017 to 2023 in the field of mathematics education before and after COVID19. In particular, this study conducted content analysis to organize on the definitions of various similar terms related to online education. In addition, this study explored research trends on year, research subject, research method, on-line education type, and research topic by the pre-COVID-19, COVID-19, and post-COVID-19 era. Also, a comparative analysis was conducted on literatures on the effects of online education. As a result, first, it was confirmed that there is a need to organize the definitions of terms similar to online education. Also, the implications of identifying the differences and hierarchies between each term can be found. Second, it was confirmed that teachers' expertise for on-line mathematics education was emphasized based on the result of the rapid increase in the number of on-line education studies on teachers since COVID-19. Third, it was confirmed that the number of studies on blended and flipped learning was high in pre-COVID-19, but decreased in the COVID-19 era. Instead, in the COVID-19 era, studies on real-time interactive classes were rapidly active, and even in the post-COVID-19 era, studies on real-time interactive classes still occupied a large proportion. Finally, it was confirmed that the effectiveness of on-line education varies depending on the research background and model. Accordingly, the need to be cautious in interpreting the results of each study on the effectiveness of on-line education was confirmed. Based on these findings, this study presented implications for future research on on-line education in mathematics education.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.749-758
• /
• 2004

In this paper, we propose a new method utilizing only raw corpus without additional human effort for disambiguation of target word selection in English-Korean machine translation. We use two data-driven techniques; one is the Latent Semantic Analysis(LSA) and the other the Probabilistic Latent Semantic Analysis(PLSA). These two techniques can represent complex semantic structures in given contexts like text passages. We construct linguistic semantic knowledge by using the two techniques and use the knowledge for target word selection in English-Korean machine translation. For target word selection, we utilize a grammatical relationship stored in a dictionary. We use k- nearest neighbor learning algorithm for the resolution of data sparseness Problem in target word selection and estimate the distance between instances based on these models. In experiments, we use TREC data of AP news for construction of latent semantic space and Wail Street Journal corpus for evaluation of target word selection. Through the Latent Semantic Analysis methods, the accuracy of target word selection has improved over 10% and PLSA has showed better accuracy than LSA method. finally we have showed the relatedness between the accuracy and two important factors ; one is dimensionality of latent space and k value of k-NT learning by using correlation calculation.

• Asia pacific journal of information systems
• /
• v.21 no.1
• /
• pp.103-122
• /
• 2011

Recently, numerous documents have been made available electronically. Internet search engines and digital libraries commonly return query results containing hundreds or even thousands of documents. In this situation, it is virtually impossible for users to examine complete documents to determine whether they might be useful for them. For this reason, some on-line documents are accompanied by a list of keywords specified by the authors in an effort to guide the users by facilitating the filtering process. In this way, a set of keywords is often considered a condensed version of the whole document and therefore plays an important role for document retrieval, Web page retrieval, document clustering, summarization, text mining, and so on. Since many academic journals ask the authors to provide a list of five or six keywords on the first page of an article, keywords are most familiar in the context of journal articles. However, many other types of documents could not benefit from the use of keywords, including Web pages, email messages, news reports, magazine articles, and business papers. Although the potential benefit is large, the implementation itself is the obstacle; manually assigning keywords to all documents is a daunting task, or even impractical in that it is extremely tedious and time-consuming requiring a certain level of domain knowledge. Therefore, it is highly desirable to automate the keyword generation process. There are mainly two approaches to achieving this aim: keyword assignment approach and keyword extraction approach. Both approaches use machine learning methods and require, for training purposes, a set of documents with keywords already attached. In the former approach, there is a given set of vocabulary, and the aim is to match them to the texts. In other words, the keywords assignment approach seeks to select the words from a controlled vocabulary that best describes a document. Although this approach is domain dependent and is not easy to transfer and expand, it can generate implicit keywords that do not appear in a document. On the other hand, in the latter approach, the aim is to extract keywords with respect to their relevance in the text without prior vocabulary. In this approach, automatic keyword generation is treated as a classification task, and keywords are commonly extracted based on supervised learning techniques. Thus, keyword extraction algorithms classify candidate keywords in a document into positive or negative examples. Several systems such as Extractor and Kea were developed using keyword extraction approach. Most indicative words in a document are selected as keywords for that document and as a result, keywords extraction is limited to terms that appear in the document. Therefore, keywords extraction cannot generate implicit keywords that are not included in a document. According to the experiment results of Turney, about 64% to 90% of keywords assigned by the authors can be found in the full text of an article. Inversely, it also means that 10% to 36% of the keywords assigned by the authors do not appear in the article, which cannot be generated through keyword extraction algorithms. Our preliminary experiment result also shows that 37% of keywords assigned by the authors are not included in the full text. This is the reason why we have decided to adopt the keyword assignment approach. In this paper, we propose a new approach for automatic keyword assignment namely IVSM(Inverse Vector Space Model). The model is based on a vector space model. which is a conventional information retrieval model that represents documents and queries by vectors in a multidimensional space. IVSM generates an appropriate keyword set for a specific document by measuring the distance between the document and the keyword sets. The keyword assignment process of IVSM is as follows: (1) calculating the vector length of each keyword set based on each keyword weight; (2) preprocessing and parsing a target document that does not have keywords; (3) calculating the vector length of the target document based on the term frequency; (4) measuring the cosine similarity between each keyword set and the target document; and (5) generating keywords that have high similarity scores. Two keyword generation systems were implemented applying IVSM: IVSM system for Web-based community service and stand-alone IVSM system. Firstly, the IVSM system is implemented in a community service for sharing knowledge and opinions on current trends such as fashion, movies, social problems, and health information. The stand-alone IVSM system is dedicated to generating keywords for academic papers, and, indeed, it has been tested through a number of academic papers including those published by the Korean Association of Shipping and Logistics, the Korea Research Academy of Distribution Information, the Korea Logistics Society, the Korea Logistics Research Association, and the Korea Port Economic Association. We measured the performance of IVSM by the number of matches between the IVSM-generated keywords and the author-assigned keywords. According to our experiment, the precisions of IVSM applied to Web-based community service and academic journals were 0.75 and 0.71, respectively. The performance of both systems is much better than that of baseline systems that generate keywords based on simple probability. Also, IVSM shows comparable performance to Extractor that is a representative system of keyword extraction approach developed by Turney. As electronic documents increase, we expect that IVSM proposed in this paper can be applied to many electronic documents in Web-based community and digital library.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.1-12
• /
• 2020

In the medical field, numerical imbalance of data due to differences in disease prevalence is a common problem. It reduces the performance of a artificial intelligence network, leading to difficulties in learning a network with good performance. Recently, generative adversarial network (GAN) technology has been introduced as a way to address this problem, and its ability has been demonstrated by successful applications in various fields. However, it is still difficult to achieve good results in solving problems with performance degraded by numerical imbalances because the image resolution of the previous studies is not yet good enough and the structure in the image is modeled locally. In this paper, we propose a multi-scale conditional generative adversarial network based on attention mechanism, which can produce high resolution images to solve the numerical imbalance problem of chest X-ray image data. The network was able to produce images for various diseases by controlling condition variables with only one network. It's efficient and effective in that the network don't need to be learned independently for all disease classes and solves the problem of long distance dependency in image generation with self-attention mechanism.

• Journal of the Korean earth science society
• /
• v.40 no.3
• /
• pp.300-312
• /
• 2019

The purpose of this study is to develop an astronomical observing education program that enables high school students to inquire the distance of astronomical bodies based on the research methods (observing open clusters and exploring collected big data) using small telescopes and DSLR cameras. After analyzing the 2015 revised science curriculum, we developed science club activity materials and teacher-student learning contents suitable for high school earth science education. A panel of six teachers and researchers of earth science education and astronomy, participated in developing the educational materials. The validity of the program was verified through establishing the agreement among the panels after in-depth discussions and clarifications. The program, developed with 10 lessons in total, showed high satisfactory content validity (CVI, .89) and conformity of school class (Likert's 5 point scales, 4.17). The feedback of the panels and the Delphi analysis continued to improve the quality of the program. The pilot testing result with high school students (N=9) showed that the students' satisfaction rate was high as 4.48. Using the astronomical observational education program of this study is expected to contribute in improving the convergence educational activity, interest, curiosity, and inquiry ability of students in the universe and the astronomical bodies.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.621-628
• /
• 2021

This paper proposes a method to calibrate a thermal camera with three different perspectives. In particular, the intrinsic parameters of the camera and re-projection errors were provided to quantify the accuracy of the calibration result. Three lenses of the camera capture the same image, but they are not overlapped, and the image resolution is worse than the one captured by the RGB camera. In computer vision, camera calibration is one of the most important and fundamental tasks to calculate the distance between camera (s) and a target object or the three-dimensional (3D) coordinates of a point in a 3D object. Once calibration is complete, the intrinsic and the extrinsic parameters of the camera(s) are provided. The intrinsic parameters are composed of the focal length, skewness factor, and principal points, and the extrinsic parameters are composed of the relative rotation and translation of the camera(s). This study estimated the intrinsic parameters of thermal cameras that have three lenses of different perspectives. In particular, image enhancement based on a deep learning algorithm was carried out to improve the quality of the calibration results. Experimental results are provided to substantiate the proposed method.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.697-702
• /
• 2023

Recently, with the introduction of drones, a core technology of the 4th industrial revolution, various convergence education using drones is being conducted in school education sites. In particular, drone theory and practice education is being conducted in connection with free semester classes and career exploration. The drone convergence education program has higher learner satisfaction than simple demonstration and practice education, and the learning effect is high due to direct practical experience. However, since practical education is being conducted for a large number of learners, it is impossible to restrict and control the flight of a large number of drones in a limited place. In this paper, we propose a monitoring system that allows the instructor to monitor multiple drones in real time and learners to recognize collisions between drones in advance when multiple drones are operated, focusing on education operated in schools. The communication module used in the experiment was equipped with GPS in Murata LoRa, and the server and client were configured to enable monitoring based on the location data received in real time. The performance of the proposed system was evaluated in an open space, and it was confirmed that the communication signal was good up to a distance of about 120m. In other words, it was confirmed that 25 educational drones can be controlled within a range of 240m and the instructor can monitor them.