• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제9권4호
• /
• pp.145-152
• /
• 2020

기계독해는(Machine reading comprehension) 사용자 질의와 관련된 문서를 기계가 이해한 후 정답을 추론하는 인공지능 자연어처리 태스크를 말하며, 이러한 기계독해는 챗봇과 같은 자동상담 서비스에 활용될 수 있다. 최근 자연어처리 분야에서 가장 높은 성능을 보이고 있는 BERT 언어모델은 대용량의 데이터를 pre-training 한 후에 각 자연어처리 태스크에 대해 fine-tuning하여 학습된 모델로 추론함으로써 문제를 해결하는 방식이다. 본 논문에서는 BERT기반 특허상담 기계독해 태스크를 위해 특허상담 데이터 셋을 구축하고 그 구축 방법을 소개하며, patent 코퍼스를 pre-training한 Patent-BERT 모델과 특허상담 모델학습에 적합한 언어처리 알고리즘을 추가함으로써 특허상담 기계독해 태스크의 성능을 향상시킬 수 있는 방안을 제안한다. 본 논문에서 제안한 방법을 사용하여 특허상담 질의에 대한 정답 결정에서 성능이 향상됨을 보였다.

• Journal of Ginseng Research
• /
• 제34권2호
• /
• pp.93-97
• /
• 2010

To enhance the functionalities of ginseng, an acid impregnation pre-treatment was applied during red ginseng processing. Acetic, ascorbic, citric, malic, lactic, and oxalic acid were used for the acid impregnation treatment, and total and crude saponin concentrations and ginsenoside patterns were evaluated. Total and crude saponin contents of red ginseng pre-treated by acetic, ascorbic, and citric acid were similar to those of red ginseng without pre-treatment, whereas lactic, malic, and oxalic acid pre-treatment caused a reduction of total and crude saponin in red ginseng. From the high performance liquid chromatography analysis of ginsenosides, increased $Rg_3$ density was shown in red ginseng pre-treated by acetic, ascorbic, and citric acid impregnation. In the case of lactic, malic, and oxalic acid pre-treatment, increased $Rg_1$ density was observed in red ginseng. Increased $Rg_1$ and $Rg_3$ contents due to acid impregnation during red ginseng processing may contribute to improving bioactive functionalities of red ginseng.

• The Korean Journal of Physiology and Pharmacology
• /
• 제23권2호
• /
• pp.131-139
• /
• 2019

Manually reviewing electroencephalograms (EEGs) is labor-intensive and demands automated seizure detection systems. To construct an efficient and robust event detector for experimental seizures from continuous EEG monitoring, we combined spectral analysis and deep neural networks. A deep neural network was trained to discriminate periodograms of 5-sec EEG segments from annotated convulsive seizures and the pre- and post-EEG segments. To use the entire EEG for training, a second network was trained with non-seizure EEGs that were misclassified as seizures by the first network. By sequentially applying the dual deep neural networks and simple pre- and post-processing, our autodetector identified all seizure events in 4,272 h of test EEG traces, with only 6 false positive events, corresponding to 100% sensitivity and 98% positive predictive value. Moreover, with pre-processing to reduce the computational burden, scanning and classifying 8,977 h of training and test EEG datasets took only 2.28 h with a personal computer. These results demonstrate that combining a basic feature extractor with dual deep neural networks and rule-based pre- and post-processing can detect convulsive seizures with great accuracy and low computational burden, highlighting the feasibility of our automated seizure detection algorithm.

• International Journal of Computer Science & Network Security
• /
• 제21권3호
• /
• pp.177-184
• /
• 2021

All over the world, people are affected by many chronic diseases and medical practitioners are working hard to find out the symptoms and remedies for the diseases. Many researchers focus on the feature detection of the disease and trying to get a better health recommendation system. It is necessary to detect the features automatically to provide the most relevant solution for the disease. This research gives the framework of Health Recommendation System (HRS) for identification of relevant and non-redundant features in the dataset for prediction and recommendation of diseases. This system consists of three phases such as Pre-processing, Feature Selection and Performance evaluation. It supports for handling of missing and noisy data using the proposed Imputation of missing data and noise detection based Pre-processing algorithm (IMDNDP). The selection of features from the pre-processed dataset is performed by proposed ensemble-based feature selection using an expert's knowledge (EFS-EK). It is very difficult to detect and monitor the diseases manually and also needs the expertise in the field so that process becomes time consuming. Finally, the prediction and recommendation can be done using Support Vector Machine (SVM) and rule-based approaches.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2001년도 하계학술대회 논문집
• /
• pp.319-322
• /
• 2001

The proposed system was composed of pre-processor which was executing binary/high-pass filtering and post-processor which ranged from statistic data to prediction. In post-processor work, step one was filter process of image, step two was image recognition, and step three was destruction degree/time prediction. After these processing, we could predict image of the last destruction timestamp. This research was produced variation value according to growth of tree pattern. This result showed improved correction, when this research was applied image Processing. Pre-processing step of original image had good result binary work after high pass- filter execution. In the case of using partial discharge of the image, our research could predict the last destruction timestamp. By means of experimental data, this Prediction system was acquired ${\pm}$3.2% error range.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.532-535
• /
• 2005

These days, many image processing techniques have been studied for effective image compression. Among those, 2D image filtering is widely used for 2D image processing. The 2D image filtering can be implemented by performing ID linear filtering separately in the direction of horizontal and vertical. Efficiency of image compression depends on what filtering method is used. Generally, circular convolution is widely used in the 2D image filtering for image processing. However it doesn't consider correlations at the region of image boundary, therefore filtering can not be performed effectively. To solve this problem. I proposed new convolution technique using Symmetric-Mirroring convolution, satisfying the 'alias-free' and 'error-free' requirement in the reconstructed image. This method could provide more effective performance than former compression methods. Because it used very high correlative data when performed at the boundary region. In this paper, pre-processing filtering in H.264 codec was adopted to analyze efficiency of proposed filtering technique, and the simulator developed by Matlab language was used to examine the performance of the proposed method.

• 한국기계가공학회지
• /
• 제11권2호
• /
• pp.98-104
• /
• 2012

In this paper, precision processing is carried out for the pre hardened steel(HRC 54), which is one of injection mould materials. Processing characteristics are estimated according to the number of tool cutting blade and roundness is observed by the 3-Dimensional measuring machine. The surface roughness affected by the wire electric discharge machining are measured. Cutting component force of STAVOX is the highest in condition of 2F processing because load per a blade of cutting tool is high. Especially, the difference in Fz is over 20N by cutting load. The slower spindle rotation speed and tool feed rate are, the better cutting component force is. The roundness of hole processed in condition of 4F is good because feed rate is able to be fast. When rotation speed is increased, the surface roughness is decreased. The surface roughness acquired in condition of 2F processing is higher about 50% than 4F processing.

• Smart Structures and Systems
• /
• 제15권1호
• /
• pp.209-225
• /
• 2015

Compared to ambient vibration testing, impact testing has the merit to extract not only structural modal parameters but also structural flexibility. Therefore, structural deflections under any static load can be predicted from the identified results of the impact test data. In this article, a signal processing procedure for structural flexibility identification is first presented. Especially, practical issues in applying the proposed procedure for structural flexibility identification are investigated, which include sensitivity analyses of three pre-defined parameters required in the data pre-processing stage to investigate how they affect the accuracy of the identified structural flexibility. Finally, multiple-reference impact test data of a three-span reinforced concrete T-beam bridge are simulated by the FE analysis, and they are used as a benchmark structure to investigate the practical issues in the proposed signal processing procedure for structural flexibility identification.

• 폴리머
• /
• 제37권3호
• /
• pp.362-372
• /
• 2013

새로운 방법에 의하여 제조된 셀룰로오스-NMMO pre-dope를 이용한 셀룰로오스 섬유 및 필름 제조를 위한 압출가공 시 열분해 및 기계적 분해에 따른 셀룰로오스의 분자량 및 알파 셀룰로오스 함량 변화에 대하여 고찰하였다. 고속분쇄에 의해 제조된 pre-dope를 압출기에 통과시켜 용액으로 제조할 때 가공온도, 셀룰로오스의 농도 및 체제시간에 따라 셀룰로오스의 분자량 및 알파 셀룰로오스 함량 변화가 다양하게 나타났다. 셀룰로오스의 분자량과 알파 셀룰로오스 함량은 셀룰로오스의 농도가 낮을수록 온도가 높을수록 감소하였다. 셀룰로오스 농도 15% 및 짧은 체제시간 영역에서 알파 셀룰로오스 함량은 높은 전단으로 인해 온도가 높을수록 가장 큰 변화를 보였다. 다양한 가공조건으로부터 알파 셀룰로오스 함량변화 거동은 분자량 변화와 다른 거동을 보였으며 셀룰로오스 용액 제조를 위한 압출가공조건이 중요 요인임을 알 수 있었다.

• 한국지리정보학회지
• /
• 제6권2호
• /
• pp.65-79
• /
• 2003

본 연구에서는 지리정보시스템(GIS)을 사용하여 Visual MODFLOW 지하수 유동 모델링 툴에 필요한 입력 인자(자료)를 과학적으로 만들어줄 뿐만 아니라, 모델링을 위해 입력된 인자들과 모델링 후 생성된 결과물들을 DB화하고 이를 체계적으로 관리할 수 있도록 하는 Visual MODFLOW 지하수 유동 모델링을 위한 GIS 기반 전 후처리기를 개발하였다. 이 전 후처리기의 모듈로서 가장 특징적인 것은 모델구역 내에서 관정 주변에 상대적으로 조밀하게 즉, 셀의 크기가 다양한 그리드를 GIS ArcView에서 자동 또는 반자동으로 형성하는 툴을 개발하였다는 것이다. 모델링 구역 내에서 다양한 경계조건(boundary condition)을 반영한 DXF 생성을 위한 툴 개발도 들 수 있다. 아울러 2차원인 ArcView를 이용하여 3차원 수리지질구조를 생성하고, MODFLOW 프로그램의 입출력 자료형태와 동일한 위상구조를 유지한 채 전 후처리하도록 한 것은 이 연구의 가장 큰 성과이다.