• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.493-498
• /
• 2004

The objective of the present study is to compare various conventional and recently evolved satellite image-processing techniques and to ascertain the best possible technique that can identify and position of aquaculture farms accurately in and around the Younggwang coastal area. Several conventional techniques performed to extract such information fiom the Landsat-TM imagery do not seem to yield better information about the aquaculture farms, and lead to misclassification. The large errors between the actual and extracted aquaculture farm information are due to existence of spectral confusion and inadequate spatial resolution of the sensor. This leads to possible occurrence of mixture pixels or 'mixels' of the source of errors in the classification techniques. Understanding the confusing and mixture pixel problems requires the development of efficient methods that can enable more reliable extraction of aquaculture farm information. Thus, the more recently evolved methods such as the step-by-step partial spectral end-member extraction and linear spectral unmixing methods are introduced. The farmer one assumes that an end-member, which is often referred to as 'spectrally pure signature' of a target feature, does not appear to be a spectrally pure form, but always mix with the other features at certain proportions. The assumption of the linear spectral unmxing is that the measured reflectance of a pixel is the linear sum of the reflectance of the mixture components that make up that pixel. The classification accuracy of the step-by-step partial end-member extraction improved significantly compared to that obtained from the traditional supervised classifiers. However, this method did not distinguish the aquaculture ponds and non-aquaculture ponds within the region of the aquaculture farming areas. In contrast, the linear spectral unmixing model produced a set of fraction images for the aquaculture, water and soil. Of these, the aquaculture fraction yields good estimates about the proportion of the aquaculture farm in each pixel. The acquired proportion was compared with the values of NDVI and both are positively correlated (R$^2$ =0.91), indicating the reliability of the sub-pixel classification.ixel classification.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.167-173
• /
• 2015

Extraction of Finger-end points is one of the most process for user multi-commands in the Hand-Gesture interface technology. However, most of previous works use the geometric and morphological method for extracting a finger-end points. Therefore, this paper proposes the method of user finger-end points extraction that is motivated a ultrared diffused illumination, which is used for the user commands in the multi-touch display device. Proposed air-mouse is worked by the quantity state and moving direction of extracted finger-end points. Also, our system includes a basic mouse event, as well as the continuous command function for expending a user multi-gesture. In order to evaluate the performance of the our proposed method, after applying to the web browser application as a command device. As a result, the proposed method showed the average 90% success-rate for the various user-commands.

• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.692-695
• /
• 2024

With the recent advancements in artificial intelligence (AI), the performance of deep learning-based audio deepfake technology has significantly improved. This technology has been exploited for criminal activities, leading to various cases of victimization. To prevent such illicit outcomes, this paper proposes a deep learning-based audio deepfake detection model. In this study, we propose CoNSIST, an improved audio deepfake detection model, which incorporates three additional components into the graph-based end-to-end model AASIST: (i) Squeeze and Excitation, (ii) Positional Encoding, and (iii) Reformulated HS-GAL, This incorporation is expected to enable more effective feature extraction, elimination of unnecessary operations, and consideration of more diverse information, thereby improving the performance of the original AASIST. The results of multiple experiments indicate that CoNSIST has enhanced the performance of audio deepfake detection compared to existing models.

• Journal of Korean Academy of Nursing
• /
• v.42 no.4
• /
• pp.453-465
• /
• 2012

Purpose: The study was done to develop a shared decision-making scale for end-of-life patients in Korea. Methods: The process included construction of a conceptual framework, generation of initial items, verification of content validity, selection of secondary items, preliminary study, and extraction of final items. The participants were 388 adults who lived in one of 3 Korean metropolitan cities: Seoul, Daegu, or Busan. Item analysis, factor analysis, criterion related validity, and internal consistency were used to analyze the data. Data collection was done from July to October 2011. Results: Thirty-four items were selected for the final scale, and categorized into 7 factors explaining 61.9% of the total variance. The factors were labeled as sharing information (9 items), constructing system (7 items), explanation as a duty (5 items), autonomy (4 items), capturing time (3 items), participation of family (3 items), and human respect (3 items). The scores for the scale were significantly correlated among shared decision-making scale, terminating life support scale, and dignified dying scale. Cronbach's alpha coefficient for the 34 items was .94. Conclusion: The above findings indicate that the shared decision-making scale has a good validity and reliability when used for end-of-life patients in Korea.

• Journal of the Korea Society of Computer and Information
• /
• v.4 no.4
• /
• pp.34-39
• /
• 1999

In this paper, boundary extraction algorithm is suggested by removing boundary noises efficiently and simplifying object shape in binary image. To remove boundary noises, $2{times}2$ mask boundary extraction algorithm is modified . Proposed method is designed to generate a symmetric path for the parasitic branch noise and to analysis traced features on end point of noise. It can extract more simplified object boundary but preserve original object shape by combining white background color extraction result with foreground extraction result. The usefulness of the proposed method was proved through experiments with various binary images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.662-667
• /
• 2022

Semantic role labeling task(SRL) is to extract predicate and arguments such as agent, patient, place, time. In the previously SRL task studies, a pipeline method extracting linguistic features of sentence has been proposed, but in this method, errors of each extraction work in the pipeline affect semantic role labeling performance. Therefore, methods using End-to-End neural network model have recently been proposed. In this paper, we propose a neural network model using the Biaffine Average Attention model for SRL task. The proposed model consists of a structure that can focus on the entire sentence information regardless of the distance between the predicate in the sentence and the arguments, instead of LSTM model that uses the surrounding information for prediction of a specific token proposed in the previous studies. For evaluation, we used F1 scores to compare two models based BERT model that proposed in existing studies using F1 scores, and found that 76.21% performance was higher than comparison models.

• Information and Communications Magazine
• /
• v.10 no.10
• /
• pp.22-29
• /
• 1993

This paper describes development of a real-time voice recognition dialing system which can recognize around one hundred word vocabularies in speaker independent mode. The voice recognition algorithm is implemented on a DSP board with a telephone interface plugged in an IBM PC AT/486. In the DSP board, procedures for feature extraction, vector quantization(VQ), and end-point detection are performed simultaneously in every 10msec frame interval to satisfy real-time constraints after the word starting point detection. In addition, we optimize the VQ codebook size and the end-point detection procedure to reduce recognition time and memory requirement. The demonstration system is being displayed in MOBILAB of Korea Mobile Telecom at the Taejon EXPO '93.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2005.11a
• /
• pp.177-180
• /
• 2005

MPEG-4 FGS 비트 스트림을 서버측에서는 각 클라이언트의 채널환경에 맞게 적절한 비트율로 추출하여 각 클라이언트에게 전송해야 한다. 부분적인 비트 스트림만으로도 영상 복원이 가능하지만, 같은 비트율에서 전송화질의 극대화를 위해서는 비트 스트림의 추출방법에 대한 연구가 필요하다. 이에 본 논문은 MPEG4 FGS 비디오 스트림을 네트워크 상에서 동적인 통신용량의 변화에 맞춰 적절한 비트율로 추출하는 방법에 대해 제안한다. 제안하는 방법은 같은 비트율에서 전송화질의 극대화를 위해 향상계층의 각 비트 평면(bit-plane)이 손실됐을 때 품질에 미치는 영향을 고려하여 비트율을 줄인다. 이렇게 함으로써 동일한 비트율이 주어진 경우 얻을 수 있는 종단간(end-to-end) 비디오 품질의 향상을 비교 분석하였다.