• Journal of Korea Multimedia Society
• /
• v.10 no.5
• /
• pp.559-568
• /
• 2007

Anchor-person scene detection is of significance for video shot semantic parsing and indexing clues extraction in content-based news video indexing and retrieval system. This paper proposes an efficient algorithm extracting anchor ranges that exist in sports news video for unit structuring of sports news. To detect anchor person scenes, first, anchor person candidate scene is decided by DCT coefficients and motion vector information in the MPEG4 compressed video. Then, from the candidate anchor scenes, image processing method is utilized to classify the news video into anchor-person scenes and non-anchor(sports) scenes. The proposed scheme achieves a mean precision and recall of 98% in the anchor-person scenes detection experiment.

• The KIPS Transactions:PartD
• /
• v.18D no.5
• /
• pp.329-338
• /
• 2011

Terminology recognition system which is a preceding research for text mining, information extraction, information retrieval, semantic web, and question-answering has been intensively studied in limited range of domains, especially in bio-medical domain. We propose a domain independent terminology recognition system based on machine learning method using dictionary, syntactic features, and Web search results, since the previous works revealed limitation on applying their approaches to general domain because their resources were domain specific. We achieved F-score 80.8 and 6.5% improvement after comparing the proposed approach with the related approach, C-value, which has been widely used and is based on local domain frequencies. In the second experiment with various combinations of unithood features, the method combined with NGD(Normalized Google Distance) showed the best performance of 81.8 on F-score. We applied three machine learning methods such as Logistic regression, C4.5, and SVMs, and got the best score from the decision tree method, C4.5.

• ETRI Journal
• /
• v.29 no.2
• /
• pp.179-188
• /
• 2007

We propose a multi-strategic concept-spotting approach for robust spoken language understanding of conversational Korean in a hostile recognition environment such as in-car navigation and telebanking services. Our concept-spotting method adopts a partial semantic understanding strategy within a given specific domain since the method tries to directly extract predefined meaning representation slot values from spoken language inputs. In spite of partial understanding, we can efficiently acquire the necessary information to compose interesting applications because the meaning representation slots are properly designed for specific domain-oriented understanding tasks. We also propose a multi-strategic method based on this concept-spotting approach such as a voting method. We present experiments conducted to verify the feasibility of these methods using a variety of spoken Korean data.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10b
• /
• pp.508-510
• /
• 1998

기존의 절차 지향 프로그램을 이해하고 유지.보수하기 위해서는 많은 비용이 필요하다. 이러한 절차 지향 프로그램에서 객체/클래스를 추출한다면 프로그램을 이해하고 유지.보수하는데 많은 비용을 절감할 수 있을 뿐 아니라, 객체 지향 프로그램으로 변환하는데 많은 도움이 된다. 본 논문에서는 객체/클래스를 추출하기 위한 절차와 구조를 제시하였다. 객체/클래스 추출기는 Clustering Engine, Stochastic Refinement and Decision Engine, Domain Modelling와 Comparison and Intergration Engine의 4부분으로 구성된다. 이러한 과정을 거치면서 기존의 연구 방법과는 다르게 가중치 주는 기준, 다중 객체 후보, 통계적 방법으로의 정재와 결정, 요구사항의 의미적 관점에 기초한 방법을 사용하였다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.126-132
• /
• 2000

This paper presents a facial expression recognition based on Gabor wavelets that uses a fuzzy C-means(FCM) clustering algorithm and neural network. Features of facial expressions are extracted to two steps. In the first step, Gabor wavelet representation can provide edges extraction of major face components using the average value of the image's 2-D Gabor wavelet coefficient histogram. In the next step, we extract sparse features of facial expressions from the extracted edge information using FCM clustering algorithm. The result of facial expression recognition is compared with dimensional values of internal stated derived from semantic ratings of words related to emotion. The dimensional model can recognize not only six facial expressions related to Ekman's basic emotions, but also expressions of various internal states.

• The KIPS Transactions:PartD
• /
• v.14D no.6
• /
• pp.573-584
• /
• 2007

As multimedia information recently increases fast, various types of retrieval of multimedia data are becoming issues of great importance. For the efficient multimedia data processing, semantics based retrieval techniques are required that can extract the meaning contents of multimedia data. Existing retrieval methods of multimedia data are annotation-based retrieval, feature-based retrieval and annotation and feature integration based retrieval. These systems take annotator a lot of efforts and time and we should perform complicated calculation for feature extraction. In addition. created data have shortcomings that we should go through static search that do not change. Also, user-friendly and semantic searching techniques are not supported. This paper proposes to develop S-MARS(Semantic Metadata-based Multimedia Annotation and Retrieval System) which can represent and extract multimedia data efficiently using MPEG-7. The system provides a graphical user interface for annotating, searching, and browsing multimedia data. It is implemented on the basis of the semantic metadata model to represent multimedia information. The semantic metadata about multimedia data is organized on the basis of multimedia description schema using XML schema that basically comply with the MPEG-7 standard. In conclusion. the proposed scheme can be easily implemented on any multimedia platforms supporting XML technology. It can be utilized to enable efficient semantic metadata sharing between systems, and it will contribute to improving the retrieval correctness and the user's satisfaction on embedding based multimedia retrieval algorithm method.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.21-30
• /
• 2009

Semantic web uses ontology languages such as RDF, RDFS, and OWL to define the metadata on the web. There have been many researching efforts in the semantic web technologies based on an agent for extracting triple and relation about concept of ontology. But the extraction of relation and triple about the concept of ontology based on an agent ends up writing a limited query statement as characteristics of an agent. As for this, there is the less of flexibility when extracting triple and relation about the other concept of ontology. We are need a query tool for flexible information retrieval of ontology that is can access the standard ontology and can be used standard query language. In this paper, we propose a SPARQL query tool that is can access the OWL ontology via HTTP protocol and it can be used to make a query. Query result can be output to the soap message. These operations can be support the web service.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.51-65
• /
• 2024

Accurate electrical load forecasting is important to the effective operation of power systems in smart grids. With the recent development in machine learning, artificial intelligence-based models for predicting power demand are being actively researched. However, since existing models get input variables as numerical features, the accuracy of the forecasting model may decrease because they do not reflect the semantic relationship between these features. In this paper, we propose a scheme for short-term load forecasting by using features extracted through the large language models for input data. We firstly convert input variables into a sentence-like prompt format. Then, we use the large language model with frozen weights to derive the embedding vectors that represent the features of the prompt. These vectors are used to train the forecasting model. Experimental results show that the proposed scheme outperformed models based on numerical data, and by visualizing the attention weights in the large language models on the prompts, we identified the information that significantly influences predictions.

• Journal of KIISE:Software and Applications
• /
• v.31 no.11
• /
• pp.1455-1473
• /
• 2004

This paper suggests a technique, TELOR(Technique of Object Extraction Based on Legacy System Interface for Improvement of Object Reusability) for reuse and reengineering by analyzing the Legacy System interface to distill the meaningful information from them and disassemble them into object units which are to be integrated into the next generation systems. The TELOR method consists of a 4 steps procedure: 1) the interface use case analysis step, 2) the interface object dividing step, 3) the object structure modeling step, and 4) the object model integration step. In step 1, the interface structure and information about the interaction between the user and the Legacy System are obtained. In step 2, the interface information is divided into semantic fields. In step 3, studies and models the structural and collaborative relationship among interface objects. Finally, in step 4, object model integration step, integrates the models and improves the integrated model at a higher level. The objects integration model created through TELOR provides a more efficient understanding of the Legacy System and how to apply it to next generation systems.

• Journal of Internet Computing and Services
• /
• v.12 no.5
• /
• pp.73-85
• /
• 2011

Lots of valuable textual information is used to extract relations between named entities from literature. Composite kernel approach is proposed in this paper. The composite kernel approach calculates similarities based on the following information:(1) Phrase structure in convolution parse tree kernel that has shown encouraging results. (2) Predicate-argument structure patterns. In other words, the approach deals with syntactic structure as well as semantic structure using a reciprocal method. The proposed approach was evaluated using various types of test collections and it showed the better performance compared with those of previous approach using only information from syntactic structures. In addition, it showed the better performance than those of the state of the art approach.