• Smart Media Journal
• /
• v.10 no.1
• /
• pp.32-38
• /
• 2021

Image classification through deep learning on the image from photographs has been a very active research field for the past several years. In this paper, we propose a method of automatically discriminating stone images from domestic source through deep learning, which is to use Python's hash library to scan 300×300 pixel photo images of granites such as Hwangdeungseok, Goheungseok, and Pocheonseok, performing data preprocessing to create learning images by examining duplicate images for each stone, removing duplicate images with the same hash value as a result of the inspection, and deep learning by stone. In addition, to utilize VGGNet, the size of the images for each stone is resized to 224×224 pixels, learned in VGG16 where the ratio of training and verification data for learning is 80% versus 20%. After training of deep learning, the loss function graph and the accuracy graph were generated, and the prediction results of the deep learning model were output for the three kinds of stone images.

• Journal of Information Technology Services
• /
• v.19 no.6
• /
• pp.145-159
• /
• 2020

Because of the recent development of information and communication technology, companies are exposed to various media such as blogs, social media, and YouTube. In particular, exposed news affects the company's reputation. So, while positive news can improve corporate value, negative news can lead to financial losses for the company. In this study, we redefine corporate reputation as social responsibility, vision and leadership, financial performance, products and services through existing literature, and conducted an AHP survey with a total of four components to calculate the weight of each factor. As a result of the calculation, the proportion of financial performance was the highest at 0.41, and products and services, vision and leadership, and social responsibility were the lowest. In addition, in order to measure the reputation of a company, it is classified as a component that defines online news using the LDA technique. In addition, through sentiment analysis, an index for each corporate reputation factor was derived, and the reputation index was calculated by combining it with the AHP analysis result, and Spearman ranking correlation analysis was performed to secure the validity of the research results. Therefore, the significance of this study is that the definition and importance of the constituent factors can contribute to the future planning and development direction of the company, and also contribute to the derivation of the corporate reputation index. This study is significant in that a new analysis methodology that applied AHP analysis results to sentiment analysis was suggested.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.56-62
• /
• 2022

Water reservoir is defined as a storage space to hold and supply filtered water and it's significantly important to manage water level in the water reservoir so as to stabilize water supply by controlling water supply depending on demand. Liquid level sensors have been installed in the water reservoir and the pumps in the booster station facilitated management for optimum water level in the water reservoir. But the incident responses including sensor malfunction and communication breakdown actually count on manager's inspection, which involves risk of accidents. To stabilize draining facility management, this study has come up with AI model that predicts changes in the water level in the water reservoir. Going through simulation in the case of missing data in the water level to verify stability in relation to the field application of the prediction model for water level changes in the reservoir, the comparison of actual change value and predicted value allows to test utility of the model.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.90-101
• /
• 2022

Buses are a popular means of transportation. As such, thorough preparation is needed for passenger safety management. However, the safety system is insufficient because there are accidents such as a death accident occurred when the bus departed without recognizing the elderly approaching to get on in 2018. There is a safety system that prevents pinching accidents through sensors on the back door stairs, but such a system does not prevent accidents that occur in the process of getting on and off like the above accident. If it is possible to predict the intention of bus passengers to get on and off, it will help to develop a safety system to prevent such accidents. However, studies predicting the intention of passengers to get on and off are insufficient. Therefore, in this paper, we propose a 1×1 CNN3D-based getting on and off intention prediction model using skeleton keypoints of passengers extracted from the camera image attached to the bus through UDP-Pose. The proposed model shows approximately 1~2% higher accuracy than the RNN and LSTM models in predicting passenger's getting on and off intentions.

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.748-756
• /
• 2022

Thanks to the competition of AlphaGo and Sedol Lee, machine learning has received world-wide attention and huge investments. The performance improvement of computing devices greatly contributed to big data processing and the development of neural networks. Artificial intelligence not only imitates human beings in many fields, but also seems to be better than human capabilities. Although humans' creation is still considered to be better and higher, several artificial intelligences continue to challenge human creativity. The quality of some creative outcomes by AI is as good as the real ones produced by human beings. Sometimes they are not distinguishable, because the neural network has the competence to learn the common features contained in big data and copy them. In order to confirm whether artificial intelligence can express the inherent characteristics of different arts, this paper proposes a new neural network model called Humming. It is an experimental model that combines vgg16, which extracts image features, and DeepJ's architecture, which excels in creating various genres of music. A dataset produced by our experiment shows meaningful and valid results. Different results, however, are produced when the amount of data is increased. The neural network produced a similar pattern of music even though it was a different classification of images, which was not what we were aiming for. However, these new attempts may have explicit significance as a starting point for feature transfer that will be further studied.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.105-111
• /
• 2023

Currently, most of content restoration using artificial intelligence learning is 2D learning. However, 3D form of artificial intelligence learning is in an incomplete state due to the disadvantage of requiring a lot of computation and learning speed from the existing 2 axes (X, Y) to 3 axes (X, Y, Z). The purpose of this paper is to secure a data-set for artificial intelligence learning by analyzing and 3D modeling the stone pagodas of ourinari by era based on the two-dimensional information (image) of cultural assets. In addition, we analyzed the differences and characteristics of towers in each era in Korea, and proposed a feature modeling method suitable for artificial intelligence learning. Restoration of cultural properties relies on a variety of materials, expert techniques and historical archives. By recording and managing the information necessary for the restoration of cultural properties through this study, it is expected that it will be used as an important documentary heritage for restoring and maintaining Korean traditional pagodas in the future.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.25-30
• /
• 2022

With the recent development of device performance such as smartphones, cameras, and video cameras, it has become possible to obtain human biometric information from images and photos. A German hacker group obtained human iris information from high-definition photos and revealed hacking into iris scanners on smartphones. As high-quality images and photos can be obtained with such advanced devices, the need for a suitable security system is also emerging. Therefore, in this paper, we propose a method of automatically masking human iris information in images and photos using Haar Cascades and Blur models from openCV. It is a technology that automatically masks iris information by recognizing a person's eye in a photo or video and provides the result. If this technology is used in devices and applications such as smartphones and zoom, it is expected to provide better security services to users.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.24-31
• /
• 2023

Meta-learning is metacognition that instantly distinguishes between knowing and unknown. It is a learning method that adapts and solves new problems by self-learning with a small amount of data.A few-shot learning method is a type of meta-learning method that accurately predicts query data even with a very small support set. In this study, we propose a method to solve the limitations of the prototype created with the mean-point vector of each class. For this purpose, we use the few-shot learning method that created the prototype used in the few-shot learning method as the median prototype. For quantitative evaluation, a handwriting recognition dataset and mini-Imagenet dataset were used and compared with the existing method. Through the experimental results, it was confirmed that the performance was improved compared to the existing method.

• Smart Media Journal
• /
• v.12 no.5
• /
• pp.81-87
• /
• 2023

In this paper, accidents in high-voltage overhead distribution lines, which provide stable power supply in the power system, cause inconvenience in life and disruption of production of companies. 22.9 [kV] high-voltage overhead power distribution lines aim to improve reliability and stability, such as damage caused by rain, snow, wind, etc., or electric shock prevention. Therefore, in order to prevent wire disconnection accidents due to deterioration of electrical conductivity or tensile strength due to corrosion of overhead distribution lines, it is necessary to prevent unexpected accidents in the future through regular inspection and repair. In order to diagnose deterioration due to corrosion of distribution lines, a diagnostic system (measuring instrument) is installed on the wires to monitor the condition of the wires. The manager on the ground receives the measured data through ZigBee wireless communication, controls the diagnosis system through the diagnosis system program, and grasps the condition of the overhead distribution line through the measured data and photographed photos, and predicts the life of the wire along with the visual inspection method. developed a program.