• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.173-181
• /
• 2017

In this paper, we have studied tracking as a training stage of considering the position and the scale of a person given its previous position, scale, as well as next and forward image fraction. Unlike other learning methods, CNN is thereby learning combines both time and spatial features from the image for the two consecutive frames. We introduce multiple path ways in CNN to better fuse local and global information. A creative shift-variant CNN architecture is designed so as to alleviate the drift problem when the distracting objects are similar to the target in cluttered environment. Furthermore, we employ CNNs to estimate the scale through the accurate localization of some key points. These techniques are object-independent so that the proposed method can be applied to track other types of object. The capability of the tracker of handling complex situations is demonstrated in many testing sequences. The accuracy of the SVM classifier using the features learnt by the CNN is equivalent to the accuracy of the CNN. This fact confirms the importance of automatically optimized features. However, the computation time for the classification of a person using the convolutional neural network classifier is less than approximately 1/40 of the SVM computation time, regardless of the type of the used features.

• Journal of the Korea Convergence Society
• /
• v.11 no.9
• /
• pp.7-13
• /
• 2020

With the recent World Health Organization (WHO) Declaration of Pandemic for Coronavirus Disease-19 (COVID-19), COVID-19 is a global concern and many deaths continue. To overcome this, there is an increasing need for sharing information between countries and countermeasures related to COVID-19. However, due to linguistic boundaries, smooth exchange and sharing of information has not been achieved. In this paper, we propose a Neural Machine Translation (NMT) model specialized for the COVID-19 domain. Centering on English, a Transformer based bidirectional model was produced for French, Spanish, German, Italian, Russian, and Chinese. Based on the BLEU score, the experimental results showed significant high performance in all language pairs compared to the commercialization system.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.76-83
• /
• 2023

This study proposes a method to assist webtoon artists in the process of webtoon creation by utilizing a pretrained Text-to-Image model to generate webtoon images from text. The proposed approach involves fine-tuning a pretrained Stable Diffusion model using a webtoon dataset transformed into the desired webtoon style. The fine-tuning process, using LoRA technique, completes in a quick training time of approximately 4.5 hours with 30,000 steps. The generated images exhibit the representation of shapes and backgrounds based on the input text, resulting in the creation of webtoon-like images. Furthermore, the quantitative evaluation using the Inception score shows that the proposed method outperforms DCGAN-based Text-to-Image models. If webtoon artists adopt the proposed Text-to-Image model for webtoon creation, it is expected to significantly reduce the time required for the creative process.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.309-314
• /
• 2023

This study examines the development and limitations of current artificial intelligence (AI) music composition programs. AI music composition programs have progressed significantly owing to deep learning technology. However, they possess limitations pertaining to the creative aspects of music. In this study, we collect, compare, and analyze information on existing AI-based music composition programs and explore their technical orientation, musical concept, and drawbacks to delineate future directions for AI music composition programs. Furthermore, this study emphasizes the importance of developing AI music composition programs that create "personalized" music, aligning with the era of personalization. Ultimately, for AI-based composition programs, it is critical to extensively research how music, as an output, can touch the listeners and implement appropriate changes. By doing so, AI-based music composition programs are expected to form a new structure in and advance the music industry.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.53-59
• /
• 2021

In this paper, we propose a BERGPT-chatbot, a domestic AI chatbot that can alleviate negative emotions based on text input such as 'Replika'. We made BERGPT-chatbot into a chatbot capable of mitigating negative emotions by pipelined two models, KR-BERT and KoGPT2-chatbot. We applied a creative method of giving emotions to unrefined everyday datasets through KR-BERT, and learning additional datasets through KoGPT2-chatbot. The development background of BERGPT-chatbot is as follows. Currently, the number of people with depression is increasing all over the world. This phenomenon is emerging as a more serious problem due to COVID-19, which causes people to increase long-term indoor living or limit interpersonal relationships. Overseas artificial intelligence chatbots aimed at relieving negative emotions or taking care of mental health care, have increased in use due to the pandemic. In Korea, Psychological diagnosis chatbots similar to those of overseas cases are being operated. However, as the domestic chatbot is a system that outputs a button-based answer rather than a text input-based answer, when compared to overseas chatbots, domestic chatbots remain at a low level of diagnosing human psychology. Therefore, we proposed a chatbot that helps mitigating negative emotions through BERGPT-chatbot. Finally, we compared BERGPT-chatbot and KoGPT2-chatbot through 'Perplexity', an internal evaluation metric for evaluating language models, and showed the superity of BERGPT-chatbot.

• Journal of Convergence for Information Technology
• /
• v.8 no.1
• /
• pp.235-242
• /
• 2018

The interest about 4th Industrial Revolution was impressively increased from newspapers, iindustry, government and academic sectors. Especially AI what could be felt by the skin of many peoples, already overpassed the ability of the human's even in creative areas. Namely, now many people start fo feel that the effect of the revolution is just infront of themselves. There were several issues in this trend, the ability of deep learning by machine, the identity of the human, the change of job environment and the concern about the social change etc. Recently many studies have been made about the 4th industrial revolution in many fields like as AI(artificial intelligence), CRISPR, big data and driverless car etc. As many positive effects and pessimistic effects are existed at the same time and many preventing actions are being suggested recently, these opinions will be compared and analyzed and better solutions will be found eventually. Several educational, political, scientific, social and ethical effects and solutions were studied and suggested in this study. Clear implication from the study is that the world we will live from now on is changing faster than ever in the social, industrial, political and educational environment. If it will reform the social systems according to those changes, a society (nation or government) will grasp the chance of its development or take-off, otherwise, it will consume the resources ineffectively and lose the competition as a whole society. But the method of that reform is not that apparent in many aspects as the revolution is progressing currently and its definition should be made whether in industrial or scientific aspect. The person or nation who will define it will have the advantage of leading the future of that business or society.