• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.922-934
• /
• 2020

The talent trading platform is a platform that brokers transactions such as program coding, media content production (video, music, presentation materials, etc.), design, learning, and repair. Existing talent trading platforms provide a server-client model-based service, which incurs server operating costs and arbitration labor costs for transactions, which has a disadvantage that users bear high service fees. This paper proposes a method to reduce server and database operation costs by uploading transaction information to blocks through the system as a distributed app (dApp) based on the Ethereum platform. In addition, it proposes a method to lower transaction fees by reducing the labor cost of transaction arbitrators through smart contracts. Compare and analyze the cost processing procedure and transaction fee size of the blockchain-based talent trading platform and the existing talent trading platform.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.116-123
• /
• 2021

Due to the rapid growth of the online fashion market and the resulting expansion of online choices, there is a problem that the seller cannot directly respond to a large number of consumers individually, although consumers are increasingly demanding for more personalized recommendation services. Images are being tagged as a way to meet consumer's personalization needs, but when people tagging, tagging is very subjective for each person, and artificial intelligence tagging has very limited words and does not meet the needs of users. To solve this problem, we designed an algorithm that recognizes the shape, attribute, and emotional information of the product included in the image with AI, and codes this information to represent all the information that the image has with a combination of codes. Through this algorithm, it became possible by acquiring a variety of information possessed by the image in real time, such as the sensibility of the fashion image and the TPO information expressed by the fashion image, which was not possible until now. Based on this information, it is possible to go beyond the stage of analyzing the tastes of consumers and make hyper-personalized clothing recommendations that combine the tastes of consumers with information about trends and TPOs.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1224-1230
• /
• 2020

Since the spread of smart phones, interest in wearable devices has increased and diversified, and is closely related to the lives of users, and has been used as a method for providing personalized services. In this paper, we propose a method to detect the user's behavior by applying information from a 3-axis acceleration sensor and a 3-axis gyro sensor embedded in a smartphone to a convolutional neural network. Human behavior differs according to the size and range of motion, starting and ending time, including the duration of the signal data constituting the motion. Therefore, there is a performance problem for accuracy when applied to a convolutional neural network as it is. Therefore, we proposed a Time-Division Feature Fusion Convolutional Neural Network (TDFFCNN) that learns the characteristics of the sensor data segmented over time. The proposed method outperformed other classifiers such as SVM, IBk, convolutional neural network, and long-term memory circulatory neural network.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.39-46
• /
• 2021

This study is about a method of extracting a summary from a news article in consideration of the importance of each sentence constituting the article. We propose a method of calculating sentence importance by extracting the probabilities of topic sentence, similarity with article title and other sentences, and sentence position as characteristics that affect sentence importance. At this time, a hypothesis is established that the Topic Sentence will have a characteristic distinct from the general sentence, and a deep learning-based classification model is trained to obtain a topic sentence probability value for the input sentence. Also, using the pre-learned ELMo language model, the similarity between sentences is calculated based on the sentence vector value reflecting the context information and extracted as sentence characteristics. The topic sentence classification performance of the LSTM and BERT models was 93% accurate, 96.22% recall, and 89.5% precision, resulting in high analysis results. As a result of calculating the importance of each sentence by combining the extracted sentence characteristics, it was confirmed that the performance of extracting the topic sentence was improved by about 10% compared to the existing TextRank algorithm.

• Journal of Korean Library and Information Science Society
• /
• v.52 no.2
• /
• pp.127-144
• /
• 2021

The purpose of this study is to redefine the competencies of teacher librarians and to derive implications for training and re-educating teacher librarians by analyzing the priorities of competencies. A questionnaire survey targeting teacher librarians based on analytic hierarchy process has been conducted. The results indicate that in terms of the upper-level areas of competencies, it was found that they prioritized teacher librarians' competencies in the following order: information specialists, teachers, administrators, and cooperative leaders. Analysis of the lower levels of competency indicates that the priorities of the required competencies are listed in the following order: collection development, management and preservation, teaching and learning, media production, information service, library cooperative instruction, library assisted instruction, content curation. Therefore, being able to provide information resources by developing a collection of books to support the educational process in school libraries was found to be a critical competency. It seems necessary to cultivate the capacity to manage online and offline collections and produce and provide various teaching media and services by utilizing school library resources. It seems to give implications for the education of teacher librarians.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.63-74
• /
• 2022

Initial public offering (IPO) has a legal framework for investor protection, and because there are various quantitative evaluation factors, objective analysis is possible, and various studies have been conducted. In addition, crowdfunding also has several devices to prevent indiscriminate funding as the legal system for investor protection. On the other hand, the blockchain-based cryptocurrency white paper (ICO), which has recently been in the spotlight, has ambiguous legal means and standards to protect investors and lacks quantitative evaluation methods to evaluate ICOs objectively. Therefore, this study collects online-published ICO white papers to detect fraud in ICOs, performs ICO fraud predictions based on BERT, a text embedding technique, and compares them with existing Random Forest machine learning techniques, and shows the possibility on fraud detection. Finally, this study is expected to contribute to the study of ICO fraud detection based on quantitative methods by presenting the possibility of using a quantitative approach using unstructured data to identify frauds in ICOs.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.26-37
• /
• 2022

In this paper, images are automatically acquired to control the initial disease of strawberries among facility cultivation crops, and disease analysis is performed using the EfficientNet model to inform farmers of disease status, and disease diagnosis service is proposed by experts. It is possible to obtain an image of the strawberry growth stage and quickly receive expert feedback after transmitting the disease diagnosis analysis results to farmers applications using the learned EfficientNet model. As a data set, farmers who are actually operating facility cultivation were recruited and images were acquired using the system, and the problem of lack of data was solved by using the draft image taken with a cell phone. Experimental results show that the accuracy of EfficientNet B0 to B7 is similar, so we adopt B0 with the fastest inference speed. For performance improvement, Fine-tuning was performed using a pre-trained model with ImageNet, and rapid performance improvement was confirmed from 100 Epoch. The proposed service is expected to increase production by quickly detecting initial diseases.

• The Journal of the Korea Contents Association
• /
• v.22 no.7
• /
• pp.548-562
• /
• 2022

This study was conducted to diagnose the issues of AI ethics in global content and to discuss what kind of discourse is needed to strengthen human identity. To this end, the study selected Netflix original content "The Social Dilemma" for analysis and adopted narrative analysis as the research method. The analysis results confirmed that "Social Dilemma" showed the structure of a traditional current affairs documentary and mainly used experts and statistical data to develop the story. It also reinforced core content claims by enumerating domestic and foreign cases such as the 2021 Myanmar massacre and the spread of fake news. In addition, the relationship between the characters clearly revealed the binary opposition between developers and media companies as well as users and advertisers. For the solution to the problem, strong regulations on businesses and the suspension of social media use were reached. However, "The Social Dilemma" merely pointed out the misuse of AI technology and had a narrative that ignored human identity and social relationships. Such results raise the need for creating contents that emphasize the importance of human sociality, relationships, and learning ability in the age of AI.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.31-38
• /
• 2022

In the document extraction summary study, various methods for selecting important sentences based on the relationship between sentences were proposed. In the Korean document summary using the summation similarity of sentences, the summation similarity of the sentences was regarded as the amount of sentence information, and the summary sentences were extracted by selecting important sentences based on this. However, the problem is that it does not take into account the various importance that each sentence contributes to the entire document. Therefore, in this study, we propose a document extraction summary method that provides a summary by selecting important sentences based on the amount of quantitative and semantic information in the sentence. As a result, the extracted sentence agreement was 58.56% and the ROUGE-L score was 34, which was superior to the method using only the combined similarity. Compared to the deep learning-based method, the extraction method is lighter, but the performance is similar. Through this, it was confirmed that the method of compressing information based on semantic similarity between sentences is an important approach in document extraction summary. In addition, based on the quickly extracted summary, the document generation summary step can be effectively performed.