• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.73-76
• /
• 2022

본 논문에서는 메타버스 공간에서 패션 아이템 판매에 있어서 필수적이라 할 수 있는 온라인 가상 피팅 기술을 동작 인식 전용 디바이스가 아닌 일반 스마트폰 카메라를 활용하여 구현하는 기술을 제안한다. 가상 피팅 기술을 구현하기 위해서는 딥러닝 기법을 활용하여 입력 영상을 분석하고, 분석 결과를 토대로 인체의 전체 자세를 추정하며, 인체 사이즈의 근사값을 추출하는 과정들이 수행되어야 하는데, 현재의 스마트폰 컴퓨팅 환경은 이를 수행하기에 충분한 연산 성능을 가지지 못한다는 문제점을 가진다. 본 논문에서는 높은 비용이 요구되는 고부하 연산을 클라우드 서버를 통해 수행하는 서버 기반 프레임워크를 도입하여, 낮은 성능의 스마트폰으로도 고성능 연산이 가능한 서비스 구조를 확보하고 이를 통해 휴대성 높은 증강현실 기반의 가상 피팅 기술을 구현한다. 본 논문의 성과를 통해 메타버스 상거래의 활성화와 메타버스 본연의 의미에 충실한 가상 월드 구축에 기여할 것이라 기대한다.

• Journal of applied mathematics & informatics
• /
• v.41 no.6
• /
• pp.1257-1274
• /
• 2023

Rotating machines heavily rely on an intricate network of interconnected sub-components, with bearing failures accounting for a substantial proportion (40% to 90%) of all such failures. To address this issue, intelligent algorithms have been developed to evaluate vibrational signals and accurately detect faults, thereby reducing the reliance on expert knowledge and lowering maintenance costs. Within the field of machine learning, Artificial Immune Systems (AIS) have exhibited notable potential, with applications ranging from malware detection in computer systems to fault detection in bearings, which is the primary focus of this study. In pursuit of this objective, we propose a novel procedure for detecting novel instances of anomalies in varying operating conditions, utilizing only the signals derived from the healthy state of the analyzed machine. Our approach incorporates AIS augmented by Dynamic Time Warping (DTW). The experimental outcomes demonstrate that the AIS-DTW method yields a considerable improvement in anomaly detection rates (up to 53.83%) compared to the conventional AIS. In summary, our findings indicate that our method represents a significant advancement in enhancing the resilience of AIS-based novelty detection, thereby bolstering the reliability of rotating machines and reducing the need for expertise in bearing fault detection.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.3
• /
• pp.701-707
• /
• 2024

Industry 4.0 has brought about significant changes in the roles of workers through the introduction of innovative technologies. In smart factory environments, workers are required to interact seamlessly with robots and automated systems, often utilizing equipment enhanced by Virtual Reality (VR) and Augmented Reality (AR) technologies. This study aims to systematically analyze recent research literature on monitoring the physical and mental states of workers in Industry 4.0 environments. Relevant literature was collected using the Web of Science database, employing a comprehensive keyword search strategy involving terms related to Industry 4.0 and health monitoring. The initial search yielded 1,708 documents, which were refined to 923 journal articles. The analysis was conducted using VOSviewer, a tool for visualizing bibliometric data. The study identified general trends in the publication years, countries of authors, and research fields. Keywords were clustered into four main areas: 'Industry 4.0', 'Internet of Things', 'Machine Learning', and 'Monitoring'. The findings highlight that research on health monitoring of workers in Industry 4.0 is still emerging, with most studies focusing on using wearable devices to monitor mental and physical stress and risks. This study provides a foundational overview of the current state of research on health monitoring in Industry 4.0, emphasizing the need for continued exploration in this critical area to enhance worker well-being and productivity.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.789-795
• /
• 2020

Many deaths have been reported due to the worldwide pandemic of COVID-19. In order to prevent the further spread of COVID-19, it is necessary to quickly and accurately read images of suspected patients and take appropriate measures. To this end, this paper introduces a deep learning-based COVID-19 chest X-ray reading technique that can assist in image reading by providing medical staff whether a patient is infected. First of all, in order to learn the reading model, a sufficient dataset must be secured, but the currently provided COVID-19 open dataset does not have enough image data to ensure the accuracy of learning. Therefore, we solved the image data number imbalance problem that degrades AI learning performance by using a Stacked Generative Adversarial Network(StackGAN++). Next, the DenseNet-based classification model was trained using the augmented data set to develop the reading model. This classification model is a model for binary classification of normal chest X-ray and COVID-19 chest X-ray, and the performance of the model was evaluated using part of the actual image data as test data. Finally, the reliability of the model was secured by presenting the basis for judging the presence or absence of disease in the input image using Grad-CAM, one of the explainable artificial intelligence called XAI.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.28-36
• /
• 2022

As port structures are exposed to various extreme external loads such as wind (typhoons), sea waves, or collision with ships; it is important to evaluate the structural safety periodically. To monitor the port structure, especially the rubber fender, a fender segmentation system using a vision sensor and deep learning method has been proposed in this study. For fender segmentation, a new deep learning network that improves the encoder-decoder framework with the receptive field block convolution module inspired by the eccentric function of the human visual system into the DenseNet format has been proposed. In order to train the network, various fender images such as BP, V, cell, cylindrical, and tire-types have been collected, and the images are augmented by applying four augmentation methods such as elastic distortion, horizontal flip, color jitter, and affine transforms. The proposed algorithm has been trained and verified with the collected various types of fender images, and the performance results showed that the system precisely segmented in real time with high IoU rate (84%) and F1 score (90%) in comparison with the conventional segmentation model, VGG16 with U-net. The trained network has been applied to the real images taken at one port in Republic of Korea, and found that the fenders are segmented with high accuracy even with a small dataset.

• Proceedings of the KSPS conference
• /
• 1997.07a
• /
• pp.176-178
• /
• 1997

To make a long story short I made up my mind to experiment with a multimedia approach to my classroom presentations two years ago because my ways of giving instructions bored the pants off me as well as my students. My favorite ways used to be sometimes referred to as classical or traditional ones, heavily dependent on the three elements: teacher's mouth, books, and chalk. Some call it the 'MBC method'. To top it off, I tried audio-visuals such as tape recorders, cassette players, VTR, pictures, and you name it, that could help improve my teaching method. And yet I have been unhappy about the results by a trial and error approach. I was determined to look for a better way that would ensure my satisfaction in the first place. What really turned me on was a multimedia CD ROM title, ELLIS (English Language Learning Instructional Systems) developed by Dr. Frank Otto. This is an integrated system of learning English based on advanced computer technology. Inspired by the utility and potential of such a multimedia system for regular classroom or lab instructions, I designed a simple but practical multimedia language learning laboratory in 1994 for the first time in Korea(perhaps for the first time in the world). It was high time that the conventional type of language laboratory(audio-passive) at Hahnnam be replaced because of wear and tear. Prior to this development, in 1991, I put a first CALL(Computer Assisted Language Learning) laboratory equipped with 35 personal computers(286), where students were encouraged to practise English typing, word processing and study English grammar, English vocabulary, and English composition. The first multimedia language learning laboratory was composed of 1) a multimedia personal computer(486DX2 then, now 586), 2) VGA multipliers that enable simultaneous viewing of the screen at control of the instructor, 3) an amplifIer, 4) loud speakers, 5)student monitors, 6) student tables to seat three students(a monitor for two students is more realistic, though), 7) student chairs, 8) an instructor table, and 9) cables. It was augmented later with an Internet hookup. The beauty of this type of multimedia language learning laboratory is the economy of furnishing and maintaining it. There is no need of darkening the facilities, which is a must when an LCD/beam projector is preferred in the laboratory. It is headset free, which proved to make students exasperated when worn more than- twenty minutes. In the previous semester I taught three different subjects: Freshman English Lab, English Phonetics, and Listening Comprehension Intermediate. I used CD ROM titles like ELLIS, Master Pronunciation, English Tripple Play Plus, English Arcade, Living Books, Q-Steps, English Discoveries, Compton's Encyclopedia. On the other hand, I managed to put all teaching materials into PowerPoint, where letters, photo, graphic, animation, audio, and video files are orderly stored in terms of slides. It takes time for me to prepare my teaching materials via PowerPoint, but it is a wonderful tool for the sake of presentations. And it is worth trying as long as I can entertain my students in such a way. Once everything is put into the computer, I feel relaxed and a bit excited watching my students enjoy my presentations. It appears to be great fun for students because they have never experienced this type of instruction. This is how I freed myself from having to manipulate a cassette tape player, VTR, and write on the board. The student monitors in front of them seem to help them concentrate on what they see, combined with what they hear. All I have to do is to simply click a mouse to give presentations and explanations, when necessary. I use a remote mouse, which prevents me from sitting at the instructor table. Instead, I can walk around in the room and enjoy freer interactions with students. Using this instrument, I can also have my students participate in the presentation. In particular, I invite my students to manipulate the computer using the remote mouse from the student's seat not from the instructor's seat. Every student appears to be fascinated with my multimedia approach to English teaching because of its unique nature as a new teaching tool as we face the 21st century. They all agree that the multimedia way is an interesting and fascinating way of learning to satisfy their needs. Above all, it helps lighten their drudgery in the classroom. They feel other subjects taught by other teachers should be treated in the same fashion. A multimedia approach to education is impossible without the advent of hi-tech computers, of which multi functions are integrated into a unified system, i.e., a personal computer. If you have computer-phobia, make quick friends with it; the sooner, the better. It can be a wonderful assistant to you. It is the Internet that I pay close attention to in conjunction with the multimedia approach to English education. Via e-mail system, I encourage my students to write to me in English. I encourage them to enjoy chatting with people all over the world. I also encourage them to visit the sites where they offer study courses in English conversation, vocabulary, idiomatic expressions, reading, and writing. I help them search any subject they want to via World Wide Web. Some day in the near future it will be the hub of learning for everybody. It will eventually free students from books, teachers, libraries, classrooms, and boredom. I will keep exploring better ways to give satisfying instructions to my students who deserve my entertainment.

• Science of Emotion and Sensibility
• /
• v.20 no.3
• /
• pp.119-130
• /
• 2017

The purpose of the study is discovering the effects of virtual competitors on user in AR (Augment Reality) home training system. Specifically, the current research examined their effects on immersion, perceived competition, and leaning motivation. The paper tested three unexplored relationship. First, introducing virtual competitors in home training system will enhance user's immersion. Second, presenting virtual competitors in home training system will increase user's perceived competition. Third, virtual competitors in home training system will raise user's learning motivation. For empirical analysis, we developed home training system, which could check and give feedback automatically, based on user's posture. Using this AR home training system, the study empirically shows how and why virtual competitors affect users. The results give implications not only on service design; but also on the idea that virtual other could affect user's behavior.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.5
• /
• pp.345-349
• /
• 2009

Social bookmarking systems are a typical web 2.0 service based on folksonomy, providing the platform for storing and sharing bookmarking information. Spammers in social bookmarking systems denote the users who abuse the system for their own interests in an improper way. They can make the entire resources in social bookmarking systems useless by posting lots of wrong information. Hence, it is important to detect spammers as early as possible and protect social bookmarking systems from their attack. In this paper, we applied a diverse set of machine learning approaches, i.e., decision tables, decision trees (ID3), $na{\ddot{i}}ve$ Bayes classifiers, TAN (tree-augment $na{\ddot{i}}ve$ Bayes) classifiers, and artificial neural networks to this task. In our experiments, $na{\ddot{i}}ve$ Bayes classifiers performed significantly better than other methods with respect to the AUC (area under the ROC curve) score as veil as the model building time. Plausible explanations for this result are as follows. First, $na{\ddot{i}}ve$> Bayes classifiers art known to usually perform better than decision trees in terms of the AUC score. Second, the spammer detection problem in our experiments is likely to be linearly separable.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.59-66
• /
• 2021

Humans mainly recognize surrounding objects using visual and auditory information among the five senses (sight, hearing, smell, touch, taste). Major research related to the latest object recognition mainly focuses on analysis using image sensor information. In this paper, after emitting various chirp audio signals into the observation space, collecting echoes through a 2-channel receiving sensor, converting them into spectral images, an object recognition experiment in 3D space was conducted using an image learning algorithm based on deep learning. Through this experiment, the experiment was conducted in a situation where there is noise and echo generated in a general indoor environment, not in the ideal condition of an anechoic room, and the object recognition through echo was able to estimate the position of the object with 83% accuracy. In addition, it was possible to obtain visual information through sound through learning of 3D sound by mapping the inference result to the observation space and the 3D sound spatial signal and outputting it as sound. This means that the use of various echo information along with image information is required for object recognition research, and it is thought that this technology can be used for augmented reality through 3D sound.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.19-27
• /
• 2022

In general, the performance of ML(Machine Learning) application is determined by various factors such as the type of ML model, the size of model (number of parameters), hyperparameters setting during the training, and training data. In particular, the recognition accuracy of ML may be deteriorated or experienced overfitting problem if the amount of dada used for training is insufficient. Existing studies focusing on image recognition have widely used open datasets for training and evaluating the proposed ML models. However, for specific applications where the sensor used, the target of recognition, and the recognition situation are different, it is necessary to build the dataset manually. In this case, the performance of ML largely depends on the quantity and quality of the data. In this paper, training data used for motion recognition application is augmented using the kernel density estimation algorithm which is a type of non-parametric estimation method. We then compare and analyze the recognition accuracy of a ML application by varying the number of original data, kernel types and augmentation rate used for data augmentation. Finally experimental results show that the recognition accuracy is improved by up to 14.31% when using the narrow bandwidth Tophat kernel.