• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.42-50
• /
• 2023

The development of technology has achieved digital innovation throughout the media industry, including production techniques and editing technologies, and has brought diversity in the form of consumer viewing through the OTT service and streaming era. The convergence of big data and deep learning networks automatically generated text in format such as news articles, novels, and scripts, but there were insufficient studies that reflected the author's intention and generated story with contextually smooth. In this paper, we describe the flow of pictures in the storyboard with image caption generation techniques, and the automatic generation of story-tailored scenarios through language models. Image caption using CNN and Attention Mechanism, we generate sentences describing pictures on the storyboard, and input the generated sentences into the artificial intelligence natural language processing model KoGPT-2 in order to automatically generate scenarios that meet the planning intention. Through this paper, the author's intention and story customized scenarios are created in large quantities to alleviate the pain of content creation, and artificial intelligence participates in the overall process of digital content production to activate media intelligence.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.515-528
• /
• 2003

Component Based Software Development has been recognized as a new software development paradigm, and received much attention among researchers. However, it requires software architecture based development to assure component reusability and efficient software development. This paper proposes the Component Based 4+1 View Model of software architecture to support component based software development. It is redefined on the basis of the existing 4+1 view model of software architecture developed by Kruchten. Also, we describe the elements of the view model in detail with UML. This architecture constructs the foundation of component based software such as increasing the understanding of software and providing the information about how the components interact with each other. It can be done by exposing the context for the use of software components to each views.

• The Journal of Society for e-Business Studies
• /
• v.27 no.2
• /
• pp.175-192
• /
• 2022

Artificial intelligence-based natural language processing technology is playing an important role in helping users write English-language documents. For academic documents in particular, the English proofreading services should reflect the academic characteristics using formal style and technical terms. But the services usually does not because they are based on general English sentences. In addition, since existing studies are mainly for improving the grammatical completeness, there is a limit of fluency improvement. This study proposes an automatic academic English editing methodology to deliver the clear meaning of sentences based on the use of technical terms. The proposed methodology consists of two phases: misspell correction and fluency improvement. In the first phase, appropriate corrective words are provided according to the input typo and contexts. In the second phase, the fluency of the sentence is improved based on the automatic post-editing model of the bidirectional recurrent neural network that can learn from the pair of the original sentence and the edited sentence. Experiments were performed with actual English editing data, and the superiority of the proposed methodology was verified.

• The KIPS Transactions:PartD
• /
• v.12D no.3 s.99
• /
• pp.439-446
• /
• 2005

XML is the standard that can manage systematically WWW documents and increase retrieval efficiency. Because XML documents have the information of contents and that of structure in single document, users can get more suitable retrieval result by retrieving the information of content as well as that of logical structure. In this paper, we will propose a method to calculate the weights of XML tags so that the information of XML tag is used to index decision. A proposed method creates term vector and weight vector for XML tags, and calculates weight of tag by reflecting user's retrieval behavior (user's query). And it decides the weights of index terms of XML document by reflecting the weights of tags. And we will perform an evaluation of proposed method by comparison with existing researches using weights of paragraphs.

• Journal for History of Mathematics
• /
• v.24 no.2
• /
• pp.1-15
• /
• 2011

Approximation is a very useful approach in mathematics research. It was the same in traditional Chinese and Chosun mathematics. This study derived five characteristics from approximation approaches which were found in Chinese and Chosun mathematical books: improvement of approximate values, common and inevitable use of approximate values, recognition of approximate values and their reasons, comparison of their exactness, application of approximate principles. Through these characteristics, we can infer what Chinese and Chosun mathematicians recognized approximate values and how they manipulated them. They took approximate approaches by necessity or for the sake of convenience in mathematical study and its applications. Also, they tried to improve the degree of exactness of approximate values and use the inverse calculations to check them.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.71-78
• /
• 2009

For more effective index extraction and index weight determination, studies of extracting indices are carried out by using document content as well as structure. However, most of studies are concentrating in calculating the importance of context rather than that of XML tag. These conventional studies determine its importance from the aspect of common sense rather than verifying that through an objective experiment. This paper, for the automatic indexing by using the tag information of XML document that has taken its place as the standard for web document management, classifies major tags of constructing a paper according to its importance and calculates the term weight extracted from the tag of low weight. By using the weight obtained, this paper proposes a method of calculating the final weight while updating the term weight extracted from the tag of high weight. In order to determine more objective weight, this paper tests the tag that user considers as important and reflects it in calculating the weight by classifying its importance according to the result. Then by comparing with the search performance while using the index weight calculated by applying a method of determining existing tag importance, it verifies effectiveness of the index weight calculated by applying the method proposed in this paper.

• 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.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.493-503
• /
• 2014

A hierarchical classification scheme, which can reduce the spectral ambiguity and also reflect crop cultivation patterns from past land-cover maps, is presented for the purpose of the early production of crop classification maps in large-scale crop areas. Specifically, the effects of mixed pixels are minimized not only by applying a hierarchical classification approach based on different spectral characteristics from crop growth cycles, but also by considering temporal contextual information derived from past crop cultivation patterns. The applicability of the presented classification scheme was evaluated by a case study of Iowa State in USA with time-series MODIS 250 m Normalized Difference Vegetation Index(NDVI) data sets and past Cropland Data Layers(CDLs). Corn and soybean, which are major crop types in the study area and also display spectral similarity, could be properly classified by applying different classification stages and accounting for past crop cultivation patterns. The classification result by the presented scheme showed increases of minimum 7.68%p and maximum 20.96%p in overall accuracy, compared with one based on purely spectral information. In addition, the combination of temporal contextual information during classification was less affected by the number of NDVI data sets and the best overall accuracy of 86.63% was achieved. Thus, it is expected that this classification scheme can be effectively used for the early production of large-area crop classification maps in major feed-grain importing countries.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.6
• /
• pp.277-281
• /
• 2006

This paper presents a method for the automatic recognition of pitch accents over syllables. The method that we propose is based on the time-delay recursive neural network (TDRNN). which is a neural network classifier with two different representation of dynamic context: the delayed input nodes allow the representation of an explicit trajectory F0(t) along time. while the recursive nodes provide long-term context information that reflects the characteristics of pitch accentuation in spoken English. We apply the TDRNN to pitch accent recognition in two forms: in the normal TDRNN. all of the prosodic features (pitch. energy, duration) are used as an entire set in a single TDRNN. while in the distributed TDRNN. the network consists of several TDRNNs each taking a single prosodic feature as the input. The final output of the distributed TDRNN is weighted sum of the output of individual TDRNN. We used the Boston Radio News Corpus (BRNC) for the experiments on the speaker-independent pitch accent recognition. π 1e experimental results show that the distributed TDRNN exhibits an average recognition accuracy of 83.64% over both pitch events and non-events.

• Journal of KIISE:Databases
• /
• v.33 no.7
• /
• pp.727-740
• /
• 2006

Schema matching is important as a prerequisite to the transformation of XML documents. This paper presents a schema matching method for the transformation of XML documents. The proposed method consists of two steps: preliminary matching relationships between leaf nodes in the two XML schemas are computed based on proposed ontology and leaf node similarity, and final matchings are extracted based on a proposed path similarity. Particularly, for a sophisticated schema matching, the proposed ontology is incrementally updated by users' feedback. furthermore, since the ontology can describe various relationships between concepts, the proposed method can compute complex matchings as well as simple matchings. Experimental results with schemas used in various domains show that the proposed method is superior to previous works, resulting in a precision of 97% and a recall of 83 % on the average. Furthermore, the dynamic ontology increased by 9 percent overall.