• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.67-76
• /
• 2019

In this paper, we propose an efficient object classification method based on semantic segmentation for multi-labeled image data. In addition to various pixel unit information and processing techniques such as color information, contour, contrast, and saturation included in image data, a detailed region in which each object is located is extracted as a meaningful unit and the experiment is conducted to reflect the result in the inference. We use a neural network that has been proven to perform well in image classification to understand which object is located where image data containing various class objects are located. Based on these researches, we aim to provide artificial intelligence services that can classify real-time detailed areas of complex images containing various objects in the future.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.1
• /
• pp.51-58
• /
• 2019

This study focused on violent act, such as verbal offensive and other acts of violence such as cyber bullying, personal information infringement. Online bullying is seriously taking place online, as juvenile violence is seriously debated due to recent school violence. In particular, it is necessary to seek countermeasures by considering the nature of cyber violence in cyberspace, particularly when stalking victims in cyberspace have died from stalking. The study examines the problem of defamation and defamation of character and tries to identify problems. Measures were taken to enact cyber defamation laws. To this end, the Commission analyzed cases of defamation and defamation of character and considered legal precedents. The study intends to study cyber defamation and defamation of character. First, I want to differentiate between cyber libel and defamation of character. Second, I intend to raise the need for cyber defamation of cybercrime and consider the offence of contempt for the criminal justice system. Third, seek ways to protect against cyber defamation and defamation of character.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.1
• /
• pp.371-376
• /
• 2019

Creative thinking appears even before it is expressed in language, and its existence is revealed through emotion, intuition, image and body feeling before logic or linguistics rules work. In this study, Lego is intended to present experimental child interactive content that is applied with a computer vision based on image processing techniques. In the case of infants, the main purpose of this content is the development of hand muscles and the ability to implement imagination. The purpose of the analysis algorithm of the OpenCV library and the image processing using the 'VVVV' that is implemented as a 'Node' in the midst of perceptual changes in image processing technology that are representative of object recognition, and the objective is to use a webcam to film, recognize, derive results that match the analysis and produce interactive content that is completed by the user participating. Research shows what Lego children have made, and children can create things themselves and develop creativity. Furthermore, we expect to be able to infer a diverse and individualistic person's thinking based on more data.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.134-139
• /
• 2021

This paper discusses the types and functions of English subordinate clauses, whether English subordinate clauses (SC) are headed by a Complementizer (CP) or headed by a lexical (but not functional) Preposition (PP). Furthermore, unlike the standard classification, the current paper provides a finer-grained analysis and classification of English SCs. The traditional or prescriptive view on the functions of English SCs includes Noun SC such as complement clauses, Adjectival SC including relative clauses, and Adverbial SCs that cover a garden variety of subordinators. Added to the existing classification of subordination in English is what I notate as Verbless subordinate clause (V-less SC). Of these 4 different types of subordinate clauses with different functions, properties, and distributions, Subjectless Verbless subordinate clause is further divided into Smallest small clause (SSC) which accounts for English subordination mechanism more uniformly and consistently with respect to their clausal architecture, especially when the subordinate clause is neither PP nor CP.

• 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.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.353-358
• /
• 2021

This study provides the syntactic analysis for the agreement attraction by proposing three types of syntactic subject-verb agreement. Because subject-verb number agreement codifies the link between a predicate and its subject, it must be the purely syntactic processes of the head-to-head agreement or the feature percolation, where relevant agreement features percolate upward or downward through the hierarchical syntactic structure. The agreement errors are not affected by linear proximity or minimal interference, but instead are affected by the hierarchical relationship between an agreement target and a local attractor. The data in this paper includes the complex noun phrases with a modifier PP or a relative clause CP. Here, the [+PL] feature is suggested to be a local attractor for subject-verb agreement errors as a strong feature. Therefore, speakers tend to erroneously produce plural agreement for a singular subject in a main clause due to a plural NP in a modifier PP or plural agreement for a singular subject in a relative clause due to plural main subject.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.487-495
• /
• 2021

The purpose of this study is to make it easier, more fun and more convenient to learn a foreign language through the development of an efficient audio contents platform that utilizes each person's native language ability. In order to achieve the goal to produce audio contents centering on the native language used in real life. Contents that are created without much effort in daily life could be used as precious contents for foreign language learners to learn the natural use of the language. Currently, most of the online foreign language learning platforms have problems with the contents depletion and the low practicality of contents. Accordingly, I am expecting this platform improves the existing shortcomings, giving foreign language learners the opportunity to learn a foreign language more realistically and at the same time giving native speakers an opportunity to generate additional revenue by utilizing their spare time.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.383-395
• /
• 2021

The diversity of urban landscapes is established by dynamic characteristics such as language, color, and their movement, which are the building environment, street patterns, and people. With the increase of foreign migrants in Korea, new guidelines are needed in terms of local community administration and land policy. Administrative, sociological, and geographical studies have been conducted on the steadily increasing number of foreign migrants since the 2000s, but it is difficult to establish for making safe and healthy communities through which different cultures and lifestyles of each country and ethnic group undergo some integration with the existing host society. There are limitations in identifying the lack of statistical data and the representation of a minority proportion of foreign residents. In order to analyze the core elements of the integrated strategy of the local community, the residential behavior and spatial characteristics of foreign migrants must first be identified.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1355-1362
• /
• 2021

Recently, not only congenital hearing impairment, but also the number of people with hearing impairment due to acquired factors is increasing. The environment in which sign language can be learned is poor. Therefore, this study intends to present a sign language (sign language number/sign language text) evaluation system as a sign language learning assistance tool for sign language learners. Therefore, in this paper, sign language is captured as an image using OpenCV and Convolutional Neural Network (CNN). In addition, we study a system that recognizes sign language behavior using MediaPipe, converts the meaning of sign language into text-type data, and provides it to users. Through this, self-directed learning is possible so that learners who learn sign language can judge whether they are correct dez. Therefore, we develop a sign language learning assistance system that helps us learn sign language. The purpose is to propose a sign language learning assistance system as a way to support sign language learning, the main language of communication for the hearing impaired.

• Journal of Industrial Convergence
• /
• v.19 no.6
• /
• pp.177-186
• /
• 2021

This review aims to propose a model that can reinterpret the abnormal and functional connections between cognitive processes and emotional regulations based on the neurocognitive networks for a comprehensive understanding of pathologic processes and treatment approach of depression and anxiety disorder. Through the processes of rebuilding the network model for depression and anxiety disorder, it was confirmed that depression can be said to be 'over-immersion in self-referencing' due to hyper-activation of default mode network (DMN), and anxiety disorders to be 'disconnection with self-referencing' due to hypo-activation of DMN. The attempts to link up between abnormal activation and pathological function of DMN which is thought to be involved in self-referential processing associated with self-consciousness and projection among neurocognitive networks may be another starting point that can afford to be suggestive in integrated interpretation and therapeutic approach to depression and anxiety disorder.