• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.630-633
• /
• 2022

속성기반 감성 분석은 텍스트 내에 존재하는 속성에 대해 세분화된 감성 분석을 수행하는 과제를 말한다. 세분화된 감성분석을 정확하게 수행하기 위해서는 텍스트에 존재하는 감성 표현과 그것이 수식하는 대상에 대한 정보가 반드시 필요하다. 그리고 순서대로 두 가지 정보는 이후 정보를 텍스트에서 추출하기 위해 중요한 단서가 된다. 따라서 본 논문에서는 KorBERT와 Bi-LSTM을 이용한 단계적 특징을 활용한 다중 작업 학습 모델을 사용하여 한국어 감성 분석 말뭉치의 감성 표현과 대상을 추출하는 작업을 수행하였다. 제안한 모델을 한국어 감성 분석 말뭉치로 학습 및 평가한 결과, 감성 표현 추출 작업의 출력을 추가적인 특성으로 전달하여 대상 추출 작업의 성능을 향상시킬 수 있음을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.715-716
• /
• 2009

인터넷의 발전은 대량의 정보를 양산하였고, 이러한 대량의 정보 집합 내에서는 비슷한 정보가 재활용 되거나 반복되는 정보중복문제를 가지고 있다. 중복되는 정보들로부터 사용자에게 원하는 정보를 신속히 검색할 수 있도록 하는 정보 요약에 대한 필요성은 점차 증가하고 있다. 본 논문은 비음수 행렬 인수분해(NMF, non-negative matrix factorization)에 의한 문서의 의미특징을 이용하여 주제기반의 다중문서를 요약하는 새로운 방법을 제안한다. 본 논문에서는 다중문서가 포함하고 있는 문서들 간의 고유구조를 문서요약에 이용하여서 요약의 질을 높일 수 있고, 주제와 문장 간의 유사성과 다양성 고려하여서 쉽게 과잉정보를 제거하여 문장을 요약할 수 있는 장점을 갖는다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.641-642
• /
• 2022

단일 데이터로부터의 이동 객체에 대한 행동 인식 연구는 데이터 수집 과정에서 발생하는 노이즈의 영향을 크게 받는다. 본 논문은 영상 데이터와 센서 데이터를 이용하여 다중 융합 네트워크 기반 이동 객체 행동 인식 방법을 제안한다. 영상으로부터 객체가 감지된 영역의 추출과 센서 데이터의 이상치 제거 및 결측치 보간을 통해 전처리된 데이터들을 융합하여 시퀀스를 생성한다. 생성된 시퀀스는 CNN(Convolutional Neural Networks)과 LSTM(Long Short Term Memory)기반 다중 융합 네트워크 모델을 통해 시계열에 따른 행동 특징들을 추출하고, 깊은 FC(Fully Connected) 계층을 통해 특징들을 융합하여 행동을 예측한다. 본 연구에서 제시된 방법은 사람을 포함한 동물, 로봇 등의 다양한 객체에 적용될 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.953-955
• /
• 2016

본 논문은 다중 회귀 분석을 이용하여 3축 가속도센서기반의 활동량을 추정하는 방법을 제안한다. 본 연구를 위해 총 59명의 피 실험자가 자체 제작한 활동량계를 착용한 뒤 트레드밀에서 일정한 속도로 걷는/뛰는 동작을 수행한 신호를 수집하였다. 수집한 3축 가속도 신호의 에너지 값에서 사전에 정의한 특징들을 산출한다. 그 다음 각 특징별로 선형, 지수, 로지스틱 회귀 분석을 적용하여 적합도가 높은 특징을 선정한다. 마지막으로 산출된 회귀식들을 사용하여 다중 회귀 분석 방법으로 활동량을 추정한다. 호흡가스 대사 분석기(K4B2)를 착용한 뒤 동일한 방법으로 실험을 수행 하고 제안한 방법과 정확도를 비교한 결과 제안한 방법의 정확도는 86.38 %로 산출되었다. 이는 기존의 Kim 외 3인의 연구결과[1]보다 2.70 %, Actical의 정확도보다 4.31 % 높은 수치이다.

• Journal of KIISE:Software and Applications
• /
• v.35 no.4
• /
• pp.255-264
• /
• 2008

This paper proposes a novel method using K-means and Non-negative matrix factorization (NMF) for topic -based multi-document summarization. NMF decomposes weighted term by sentence matrix into two sparse non-negative matrices: semantic feature matrix and semantic variable matrix. Obtained semantic features are comprehensible intuitively. Weighted similarity between topic and semantic features can prevent meaningless sentences that are similar to a topic from being selected. K-means clustering removes noises from sentences so that biased semantics of documents are not reflected to summaries. Besides, coherence of document summaries can be enhanced by arranging selected sentences in the order of their ranks. The experimental results show that the proposed method achieves better performance than other methods.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.4
• /
• pp.93-100
• /
• 2005

In this paper, we describe biometric watermarking techniques for secure user verification on the remote, multimodal biometric system employing both fingerprint and face information, and compare their effects on verification accuracy quantitatively. To hide biometric data with watermarking techniques, we first consider possible two scenarios. In the scenario 1, we use a fingerprint image as a cover work and hide facial features into it. On the contrary, we hide fingerprint features into a facial image in the Scenario 2. Based on the experimental results, we confirm that the Scenario 2 is superior to the Scenario 1 in terms of the verification accuracy of the watermarking image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.9
• /
• pp.1878-1883
• /
• 2012

Generally, in the underwater target recognition, feature vectors are extracted from the target signal utilizing spatial information according to target shape/material characteristics. And, various signal processing techniques have been studied to extract feature vectors which is less sensitive to the location of the receiver. In this paper, we analyzed the characteristics of synthesized underwater objects using canonical correlation analysis method which is relatively less sensitive to the location of receiver. Canonical correlation analysis is applied to two consecutive backscattered sonar returns at different aspect angles to analyze the correlation characteristics in multi-aspect environment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.5
• /
• pp.133-138
• /
• 2010

We present a new multimodal biometric authentication method, which performs both feature-level fusion and decision-level fusion. After generating support vector machines for new features made by integrating face and voice features, the final decision for authentication is made by integrating decisions of face SVM classifier, voice SVM classifier and integrated features SVM clssifier. We justify our proposal by comparing our method with traditional one by experiments with XM2VTS multimodal database. The experiments show that our multilevel fusion algorithm gives higher recognition rate than the existing schemes.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.499-506
• /
• 2004

The copper foil surface inspection system is necessary for the factory automation and product quality. The developed system is composed of the high speed line scan camera, the image capture board and the processing computer. For the system resource utilization and real-time processing, multi-threaded architecture is introduced. There are one image capture thread, 2 or more defect detection threads, and one defect communication thread. To process the high-speed input image data, the I/O overlap is used through the double buffering. The defect is first detected by the predetermined threshold. To cope with the light irregularity, the compensation process is applied. After defect detection, defect type is classified with the defect width, eigenvalue ratio of the defect covariance matrix and gray level of defect. In experiment, for high-speed input image data, real-time processing is possible with multi -threaded architecture, and the 89.4% of the total 141 defects correctly classified.

• Korean Journal of Remote Sensing
• /
• v.29 no.5
• /
• pp.569-579
• /
• 2013

In this study, land-cover classification was implemented using features extracted from multi-temporal SAR data through 3D wavelet transform and the applicability of the 3D wavelet transform as a feature extraction approach was evaluated. The feature extraction stage based on 3D wavelet transform was first carried out before the classification and the extracted features were used as input for land-cover classification. For a comparison purpose, original image data without the feature extraction stage and Principal Component Analysis (PCA) based features were also classified. Multi-temporal Radarsat-1 data acquired at Dangjin, Korea was used for this experiment and five land-cover classes including paddy fields, dry fields, forest, water, and built up areas were considered for classification. According to the discrimination capability analysis, the characteristics of dry field and forest were similar, so it was very difficult to distinguish these two classes. When using wavelet-based features, classification accuracy was generally improved except built-up class. Especially the improvement of accuracy for dry field and forest classes was achieved. This improvement may be attributed to the wavelet transform procedure decomposing multi-temporal data not only temporally but also spatially. This experiment result shows that 3D wavelet transform would be an effective tool for feature extraction from multi-temporal data although this procedure should be tested to other sensors or other areas through extensive experiments.