• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 추계학술대회
• /
• pp.91-94
• /
• 2021

As deep learning technologies becoming developed, realistic fake videos synthesized by deep learning models called "Deepfake" videos became even more difficult to distinguish from original videos. As fake news or Deepfake blackmailing are causing confusion and serious problems, this paper suggests a novel model detecting Deepfake videos. We chose Residual Convolutional Neural Network (Resnet50) as an extraction model and Long Short-Term Memory (LSTM) which is a form of Recurrent Neural Network (RNN) as a classification model. We adopted cosine similarity with hinge loss to train our extraction model in embedding the features of Deepfake and original video. The result in this paper demonstrates that temporal features in the videos are essential for detecting Deepfake videos.

• 공업화학
• /
• 제29권4호
• /
• pp.446-451
• /
• 2018

플라보노이드성분 함량이 높은 밀싹을 이용하여 유효성분을 추출하고, 중심합성계획모델을 이용하여 추출공정을 최적화하였다. 중심합성계획모델의 반응치로는 추출수율과 플라보노이드성분 함량을 설정하고, 독립변수인 추출시간, 주정/초순수 부피비, 추출온도에 따른 주효과도와 교호효과도를 해석하였다. 추출수율의 경우 추출시간과 추출온도가 상대적으로 큰 영향을 미쳤으며, 플라보노이드성분 함량의 경우에는 추출시간의 영향이 가장 크게 나타났다. 추출수율과 플라보노이드성분 함량을 모두 고려한 결과 최적추출조건은 추출시간(2.44 h), 주정/초순수의 부피비(50.00 vol%), 추출온도($54.41^{\circ}C$)이었으며, 이때 추출수율은 30.14 wt%, 플라보노이드성분 함량은 $35.37{\mu}g\;QE/mL\;dw$이었다. 이 조건의 실제 실험결과 추출수율(29.92 wt%), 플라보노이드성분 함량($35.32{\mu}g\;QE/mL\;dw$)으로 오차율은 각각 0.39%, 0.74%이었다. 이는 두 개의 반응치를 동시에 분석하는 다중분석 종합분석임에도 높은 정확도를 나타낸 것으로 본 연구에서의 최적화과정 신뢰도가 우수한 것으로 사료된다.

• 제어로봇시스템학회논문지
• /
• 제11권12호
• /
• pp.1062-1067
• /
• 2005

This paper discusses a skeleton feature extraction method for ubiquitous robot system. The skeleton features are used to analyze human motion and pose estimation. In different conventional feature extraction environment, the ubiquitous robot system requires more robust feature extraction method because it has internal vibration and low image quality. The new hybrid silhouette extraction method and adaptive skeleton model are proposed to overcome this constrained environment. The skin color is used to extract more sophisticated feature points. Finally, the experimental results show the superiority of the proposed method.

• 한국정보기술학회 영문논문지
• /
• 제10권1호
• /
• pp.45-56
• /
• 2020

Despite extensive research, performance enhancement of keyphrase (KP) extraction remains a challenging problem in modern informatics. Recently, deep learning-based supervised approaches have exhibited state-of-the-art accuracies with respect to this problem, and several of the previously proposed methods utilize Bidirectional Encoder Representations from Transformers (BERT)-based language models. However, few studies have investigated the effective application of BERT-based fine-tuning techniques to the problem of KP extraction. In this paper, we consider the aforementioned problem in the context of scientific articles by investigating the fine-tuning characteristics of two distinct BERT models - BERT (i.e., base BERT model by Google) and SciBERT (i.e., a BERT model trained on scientific text). Three different datasets (WWW, KDD, and Inspec) comprising data obtained from the computer science domain are used to compare the results obtained by fine-tuning BERT and SciBERT in terms of KP extraction.

• 한국터널지하공간학회 논문집
• /
• 제8권1호
• /
• pp.53-63
• /
• 2006

본 연구는 프라우드 상사와 등온기체모델을 적용한 축소모형실험을 실시하여, 터널화재시 연기의 거동과 부분배연설비의 배연효율을 분석함으로써 방재설비의 운영방안을 제시하고자 하였다. 실험 결과 터널 화재시 입계유속 이상의 제연 풍량이 유지 될 경우 부분 배연 갤러리의 배연효율은 그룹댐퍼와 균일댐퍼 모두 거의 유사하였다. 또한, 터널내 차량이 정체시 화재가 발생할 경우, 화재초기에는 화원 앞 뒤에 위치해있는 부분 배연 갤러리만을 열어 연키의 성총회률유지하면서 연층을 배연시키고 제트팬은 가동시키지 않고 이후 승객이 모두 대피할 수 있는 충분한 시간이 지난 후 제트팬을 함께 가동시켜 터널 내의 연기를 배출하도록 하며 교통 소통이 원활한 경우에는 터널의 제연설비를 가몽하여 연기의 후방전파를 차단하고 통시에 부분배연 설비를 가동할 것을 제안하였다.

• 한국치위생학회지
• /
• 제17권2호
• /
• pp.235-245
• /
• 2017

Objectives: The purpose of this study was to investigate how wisdom tooth extraction is perceived, and to correct erroneous perceptions thereby establishing proper awareness. Methods: We conducted a survey on how wisdom tooth extraction was perceived among adults in 20 households in Seoul and Gyeonggi province starting in December, 2016. Results: A review of the factors influencing the perception of wisdom tooth extraction showed that the regression model was statistically significant and the model had an explanatory power of 8.3%. It was also found that those in their 20s or younger had saw a lower level of perceived oral health, and a higher level in perception in wisdom tooth extraction. Moreover, students, housewives, and professions showed a lower perception of wisdom tooth extraction. Conclusions: It is necessary to have an education program for adults aged 60 or older who have few opportunities for oral health education.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2011년도 한국컴퓨터종합학술대회논문집 Vol.38 No.1(A)
• /
• pp.255-258
• /
• 2011

An application of Gammatone auditory filterbank for emotion recognition from speech is described in this paper. Gammatone filterbank is a bank of Gammatone filters which are used as a preprocessing stage before applying feature extraction methods to get the most relevant features for emotion recognition from speech. In the feature extraction step, the energy value of output signal of each filter is computed and combined with other of all filters to produce a feature vector for the learning step. A feature vector is estimated in a short time period of input speech signal to take the advantage of dependence on time domain. Finally, in the learning step, Hidden Markov Model (HMM) is used to create a model for each emotion class and recognize a particular input emotional speech. In the experiment, feature extraction based on Gammatone filterbank (GTF) shows the better outcomes in comparison with features based on Mel-Frequency Cepstral Coefficient (MFCC) which is a well-known feature extraction for speech recognition as well as emotion recognition from speech.

• 자원리싸이클링
• /
• 제9권1호
• /
• pp.21-26
• /
• 2000

고탄소페로망간을 중.저탄소페로망간으로 제조하는 AOD공정의 Bag filter에 포집된 분진은 약 90%가 $Mn_3O_4$인 망간산화물이다. 분진의 입도는 5$\mu\textrm{m}$이하이고, 입자들은 직경이 10nm정도인 미립자들의 응집체로서 구형이다. 분진에서 망간을 질산으로 침출할 때의 최대침출율은 약 67%이며,비정질의 $MnO_2$가 잔류한다. 침출속도는 온도가 증가함에 따라 빨라지고 고농도의 질산에서는 늦어졌다. 침출속도를 여러 침출모델에 적용한 결과는 pore diffusion model에 일치하였다.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.III
• /
• pp.715-721
• /
• 2000

In this research, rule and neuro net based boundary extraction algorithm was developed. Extracting boundary of the interest, lean tissue, is essential for the quality evaluation of the beef based on color machine vision. Major quality features of the beef are size, marveling state of the lean tissue, color of the fat, and thickness of back fat. To evaluate the beef quality, extracting of loin parts from the sectional image of beef rib is crucial and the first step. Since its boundary is not clear and very difficult to trace, neural network model was developed to isolate loin parts from the entire image input. At the stage of training network, normalized color image data was used. Model reference of boundary was determined by binary feature extraction algorithm using R(red) channel. And 100 sub-images(selected from maximum extended boundary rectangle 11${\times}$11 masks) were used as training data set. Each mask has information on the curvature of boundary. The basic rule in boundary extraction is the adaptation of the known curvature of the boundary. The structured model reference and neural net based boundary extraction algorithm was developed and implemented to the beef image and results were analyzed.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(2)
• /
• pp.47-50
• /
• 2000

DC Gummel-Poon SPICE model parameter extraction program has been implemented. This program extracts the parameters from measured data using Levenberg-Marquardt algorithm. Measured data consist of forward and reverse Gummel plot, forward and reverse output characteristics and RE and RC measurements.