• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.115-130
• /
• 2022

Barrage is an interactive method based on video, and the video itself is visualized from the viewer's point of view to play people's emotions, and it already has an advantage in communication by attracting people's attention using stories and plays. Advances in digital and mobile technology have enabled video viewing anytime, anywhere. Due to the nature of the barrage site that relies on the same video content or playback to participate in video sharing through computers or mobile clients, a barrage that can express users' feelings and thoughts will be added, breaking down the limit of content acceptance by a single user. Barrage satisfy users' entertainment needs, and their influence is growing. Gradually, they are heading to offline movie theaters and TV from barrage videos on the Internet. Attempts to function as offline ammunition facilitated technological innovation for media convergence by converging mobile media with PCs and screens. At the same time, the trend of media convergence shown by coal screens is also a trend of overall technological development. A barrage is an extension of human communication skills. The properties of the barrage fit well with the need for experiential marketing (via video). It can provide a visual experience and create an atmosphere of "surrounding and watching" and eliminate loneliness. Barrage itself provides a function to comment on videos, which is a trigger point for the reason, and donation adds to the amount of information in the video, adding to the fun of the video. Through the barrage, sarcastic, teasing, and expressing emotions can bring entertainment experiences, and users can produce and communicate their shooting text while consuming the satisfaction brought by the shooting. At the same time, Barrage attaches great importance to the needs of the masses, is more individual and diversified, and has commercial significance in line with the current development trend of the Internet. As a new interactive method, barrage contains huge potential value. However, the impact of the interactive way of barrage should also be viewed from a dialectical point of view, how to solve the difficulties in the development of barrage. The way to solve the difficulties in the development of barrage is worth studying. This research will analyze the reasons for the development of barrage and the analysis of Chinese barrage websites, the case analysis of barrage videos, the exploration of the characteristics and values of barrage, and the problems in the process of barrage communication. Provide reference for the development of industrial culture.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.627-635
• /
• 2022

As the non-face-to-face situation continues for a long time due to COVID-19, the underlying technologies of the 4th industrial revolution such as IOT, AR, VR, and big data are affecting the metaverse platform overall. Such changes in the external environment such as society and culture can affect the development of academics, and it is very important to systematically organize existing achievements in preparation for changes. The Korea Educational Research Information Service (RISS) collected data including the 'metaverse platform' in the keyword and used the text mining technique, one of the big data analysis. The collected data were analyzed for word cloud frequency, connection strength between keywords, and semantic network analysis to examine the trends of metaverse platform research. As a result of the study, keywords appeared in the order of 'use', 'digital', 'technology', and 'education' in word cloud analysis. As a result of analyzing the connection strength (N-gram) between keywords, 'Edue→Tech' showed the highest connection strength and a total of three clusters of word chain clusters were derived. Detailed research areas were classified into five areas, including 'digital technology'. Considering the analysis results comprehensively, It seems necessary to discover and discuss more active research topics from the long-term perspective of developing a metaverse platform.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.79-86
• /
• 2022

This study aims to analyze the research trends on the civic participation in a smart city and to present implications to policy makers, industry professionals and researchers. As rapid urbanization is defining development trend of modern city, urban problems such as transportation, environment, and energy are spreading and intensifying around the city. Countries around the world are introducing smart cities to solve these urban problems and to achieve sustainable development. Recently, many countries are modifying urban planning from top-down to down-up by actively engaging citizens to participate in the urban construction process directly and indirectly. Although the construction of smart cities is being promoted in Korea to solve urban problems, awareness of smart cities and civic participation are low. In order to overcome this situation, discussions on ideas and methods that can increase civic participation in smart cities are continuously being conducted. Therefore, in this study, by collecting publication containing both 'Smart Cities' and 'Participation (Engagement)' in Scopus DB, the topics of related studies were categorized and research trends were analyzed using topic modeling. Through this study, it is expected that it can be used as evidence to understand the direction of civic participation research in smart cities and to present the direction of related research in the future.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.675-681
• /
• 2021

With the recent growth of the AI speaker market, the demand for speech synthesis technology that enables natural conversation with users is increasing. Therefore, there is a need for a multi-speaker speech synthesis system that can generate voices of various tones. In order to synthesize natural speech, it is required to train with a large-capacity. high-quality speech DB. However, it is very difficult in terms of recording time and cost to collect a high-quality, large-capacity speech database uttered by many speakers. Therefore, it is necessary to train the speech synthesis system using the speech DB of a very large number of speakers with a small amount of training data for each speaker, and a technique for naturally expressing the tone and rhyme of multiple speakers is required. In this paper, we propose a technology for constructing a speaker encoder by applying the deep learning-based x-vector technique used in speaker recognition technology, and synthesizing a new speaker's tone with a small amount of data through the speaker encoder. In the multi-speaker speech synthesis system, the module for synthesizing mel-spectrogram from input text is composed of Tacotron2, and the vocoder generating synthesized speech consists of WaveNet with mixture of logistic distributions applied. The x-vector extracted from the trained speaker embedding neural networks is added to Tacotron2 as an input to express the desired speaker's tone.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.211-223
• /
• 2022

This study aims to verify the possibility of using the blog mining to collect public opinion in the field of housing policy, thus, it collected blog posts with the keyword 'Happy Housing', extracted the main keywords from them, and analyzed the public's perception through keyword and word cluster analysis. 137,002 blog posts were used as analysis data from May 2013, when social discussion about happy housing spread, to August 2021, and the words derived by dividing the period into three stages in consideration of major housing policies and data collection were analyzed. The results are as follows. In the keyword analysis, overall, the importance of words related to the location, the number, the size, and the conditions for occupancy of Happy Housing is high. In the first stage, government policy implementation, in the second stage, the application process for Happy Housing, and in the third stage, recruitment notices, occupancy qualifications, and rental conditions are found to be highly important. In cluster analysis, project progress, application process, and project area were drawn as main themes at all stages. In particular, policy implementation and implementation plan in the first stage, occupancy qualification and financial support in the second stage, and policy implementation and occupancy qualification in the third stage were drawn as main themes. These results present the possibility of the blog mining as a method of collecting public opinion by sharing policy-related information, reflecting social issues, evaluating whether policies are delivered, and inferring the public's participation in policies.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.325-330
• /
• 2022

This paper conducts the collection and experiment of datasets for deep learning research on sign language such as sign language recognition, sign language translation, and sign language segmentation for Korean sign language. There exist difficulties for deep learning research of sign language. First, it is difficult to recognize sign languages since they contain multiple modalities including hand movements, hand directions, and facial expressions. Second, it is the absence of training data to conduct deep learning research. Currently, KETI dataset is the only known dataset for Korean sign language for deep learning. Sign language datasets for deep learning research are classified into two categories: Isolated sign language and Continuous sign language. Although several foreign sign language datasets have been collected over time. they are also insufficient for deep learning research of sign language. Therefore, we attempted to collect a large-scale Korean sign language dataset and evaluate it using a baseline model named TSPNet which has the performance of SOTA in the field of sign language translation. The collected dataset consists of a total of 11,402 image and text. Our experimental result with the baseline model using the dataset shows BLEU-4 score 3.63, which would be used as a basic performance of a baseline model for Korean sign language dataset. We hope that our experience of collecting Korean sign language dataset helps facilitate further research directions on Korean sign language.

• Smart Media Journal
• /
• v.11 no.10
• /
• pp.65-75
• /
• 2022

Deep learning is used as a creative tool that could overcome the limitations of existing analysis models and generate various types of results such as text, image, and music. In this paper, we propose a method necessary to preprocess audio data using the Niko's MIDI Pack sound source file as a data set and to generate music using Bi-LSTM. Based on the generated root note, the hidden layers are composed of multi-layers to create a new note suitable for the musical composition, and an attention mechanism is applied to the output gate of the decoder to apply the weight of the factors that affect the data input from the encoder. Setting variables such as loss function and optimization method are applied as parameters for improving the LSTM model. The proposed model is a multi-channel Bi-LSTM with attention that applies notes pitch generated from separating treble clef and bass clef, length of notes, rests, length of rests, and chords to improve the efficiency and prediction of MIDI deep learning process. The results of the learning generate a sound that matches the development of music scale distinct from noise, and we are aiming to contribute to generating a harmonistic stable music.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.9
• /
• pp.381-386
• /
• 2023

Many existing test case generation researchers extract test cases from models. However, research on generating test cases from natural language requirements is required in practice. For this purpose, the combination of natural language analysis and requirements engineering is very necessary. However, Requirements analysis written in Korean is difficult due to the diverse meaning of sentence expressions. We research test case generation through natural language requirement definition analysis, C3Tree model, cause-effect graph, and decision table steps as one of the test case generation methods from Korean natural requirements. As an intermediate step, this paper generates test cases from C3Tree model-based decision tables using meta-modeling. This method has the advantage of being able to easily maintain the model-to-model and model-to-text transformation processes by modifying only the transformation rules. If an existing model is modified or a new model is added, only the model transformation rules can be maintained without changing the program algorithm. As a result of the evaluation, all combinations for the decision table were automatically generated as test cases.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.371-380
• /
• 2023

Relation extraction is to extract relationships between named entities from text. Traditionally, relation extraction methods only extract relations between predetermined subject and object entities. However, in end-to-end relation extraction, all possible relations must be extracted by considering the positions of the subject and object for each pair of entities, and so this method uses time and resources inefficiently. To alleviate this problem, this paper proposes a method that sets directions based on the positions of the subject and object, and extracts relations according to the directions. The proposed method utilizes existing relation extraction data to generate direction labels indicating the direction in which the subject points to the object in the sentence, adds entity position tokens and entity type to sentences to predict the directions using a pre-trained language model (KLUE-RoBERTa-base, RoBERTa-base), and generates representations of subject and object entities through probabilistic crossover operation. Then, we make use of these representations to extract relations. Experimental results show that the proposed model performs about 3 ~ 4%p better than a method for predicting integrated labels. In addition, when learning Korean and English data using the proposed model, the performance was 1.7%p higher in English than in Korean due to the number of data and language disorder and the values of the parameters that produce the best performance were different. By excluding the number of directional cases, the proposed model can reduce the waste of resources in end-to-end relation extraction.

• Journal of the Korean Society of Earth Science Education
• /
• v.16 no.2
• /
• pp.261-275
• /
• 2023

The purpose of this study was to analyze the conceptual understanding of carbon neutrality among secondary school science pre-service teachers, as well as to identify gaze patterns in visual materials. For this study, gaze tracking data of 20 pre-service secondary school science teachers were analyzed. Through this, the levels of conceptual understanding of carbon neutrality were categorized for the participants, and differences in gaze patterns were analyzed based on the degree of conceptual understanding of carbon neutrality. The research findings are as follows. First, as a result of performing modeling activities to predict carbon emissions and removals until 2100 using the concept of '2050 carbon neutrality,' 50% of the participants held a conception that carbon emissions would continue to increase. Additionally, 25% of the participants did not properly understand the causal relationship between net carbon dioxide emissions and cumulative concentrations. Second, the gaze movements of the participants regarding visual materials related to carbon neutrality were significantly influenced by the information presented in the text area, and in the case of graphs, the focus was mainly on the data area. Moreover, when visual data with the same function and category were arranged, participants showed the most interest in materials explaining concepts or visual data placed on the left side. This implies a preference for specific positions or orders. Participants with lower levels of conceptual understanding and inadequate grasp of causal relationships among elements exhibited notably reduced concentration and overall gaze flow. These findings suggest that conceptual understanding of carbon neutrality including climate change and natural disaster significantly influences interest in and engagement with visual materials.