• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.383-385
• /
• 2011

본 논문에서는 동영상을 대상으로 하는 기존의 시각주의 시스템의 성능을 향상시킨 새로운 시스템에 대하여 설명한다. 제안하는 시스템은 기존의 시스템이 가지고 있던 한계점인 서로 반대되는 특징을 가지는 색상에서 하나의 특징만을 고정적으로 선택하던 것을 극복하여, 서로 반대되는 특징 중 현저함이 더 높은 색상 특징을 선택하여 입력 들어오는 영상에 적응적인 현저함 추출을 하였다. 도한 시간 현저함 정보를 추가적으로 고려할 수 있도록 하여 동영상에 대한 처리도 가능하도록 하였고, 성능 평가 시 인간을 대상으로 한 설문 조사 실험을 추가하여 보다 인간의 시각 인식과 유사한 시스템임을 증명하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.133-138
• /
• 2008

In this paper, we propose a novel anchor shot detection system, named to MASD (Multi-phase Anchor Shot Detection), which is a core step of the preprocessing process for the news video analysis. The proposed system is composed of four modules and operates sequentially: 1) skin color detection module for reducing the candidate face regions; 2) face detection module for finding the key-frames with a facial data; 3) vector representation module for the key-frame images using a non-negative matrix factorization; 4) one class SVM module for determining the anchor shots using a support vector data description. Besides the qualitative analysis, our experiments validate that the proposed system shows not only the comparable accuracy to the recently developed methods, but also more faster detection rate than those of others.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.16-17
• /
• 2015

본 논문에서는 실내 환경 중 TV 시청환경에서 마이크로폰 어레이를 이용하여 다양한 다중 음원 방향을 추정하는 기법을 제안한다. 제안된 기법은 기존의 하나의 음원에 특화되어 있는 GCC-PHAT 기반의 방법을 GCC-PHAT 버퍼와 NMF를 도입하여 다중음원의 방향 추정을 가능하게 만들었다. 제안된 기법의 성능을 평가하기 위해서 실 거주 환경에서 발생하는 소음원과 TV 소리 방향 추정 결과에 대한 실측치와 추정치 간의 오차인 절대 평균오차를 측정하였으며, 실험 결과 제안한 기법이 기존의 방법인 GCC-PHAT보다 우수한 추정 성능을 보임을 확인하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2155-2160
• /
• 2014

In this paper, we proposes a new document summarization method using the extracted semantic feature which the semantic feature is extracted by distributed parallel processing based Hadoop. The proposed method can well represent the inherent structure of documents using the semantic feature by the non-negative matrix factorization (NMF). In addition, it can summarize the big data document using Hadoop. The experimental results demonstrate that the proposed method can summarize the big data document which a single computer can not summarize those.

• 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.

• Advances in concrete construction
• /
• v.10 no.4
• /
• pp.319-332
• /
• 2020

The impacts of reinforcing concrete matrix with steel fibers, polypropylene fibers and recycled plastic fibers using different volume fractions of 0.15%, 0.5%, 1.5% and 2.5% on the compressive and tensile characteristics are experimentally investigated in the current research. Also, flexural behavior of plain concrete (PC) beams, shear performance of reinforced concrete (RC) beams and compressive characteristics of both PC and RC columns reinforced with recycled plastic fibers were studied. The experimental results showed that the steel fibers improved the splitting tensile strength of concrete higher than both the polypropylene fibers and recycled plastic fibers. The end-hooked steel fibers had a positive effect on the compressive strength of concrete while, the polypropylene fibers, the recycled plastic fibers and the rounded steel fibers had a negative impact. Compressive strength of end-hooked steel fiber specimen with volume fraction of 2.5% exhibited the highest value among all tested samples of 32.48 MPa, 21.83% higher than the control specimen. The ultimate load, stiffness, ductility and failure patterns of PC and RC beams in addition to PC and RC columns strengthened with recycled plastic fibers enhanced remarkably compared to non-strengthened elements. The maximum ultimate load and stiffness of RC column reinforced with recycled plastic fibers with 1.5% volume fraction improved by 21 and 15%, respectively compared to non-reinforced RC column.

• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.179-186
• /
• 2009

This paper proposes a target speech extraction which restores speech signal of a target speaker form noisy convolutive mixture of speech and an interference source. We assume that the target speaker is known and his/her utterances are available in the training time. Incorporating the additional information extracted from the training utterances into the separation, we combine convolutive blind source separation(CBSS) and non-negative decomposition techniques, e.g., probabilistic latent variable model. The nonnegative decomposition is used to learn a set of bases from the spectrogram of the training utterances, where the bases represent the spectral information corresponding to the target speaker. Based on the learned spectral bases, our method provides two postprocessing steps for CBSS. Channel selection step finds a desirable output channel from CBSS, which dominantly contains the target speech. Reconstruct step recovers the original spectrogram of the target speech from the selected output channel so that the remained interference source and background noise are suppressed. Experimental results show that our method substantially improves the separation results of CBSS and, as a result, successfully recovers the target speech.

• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.481-488
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization) and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architectureII, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortions.

• Mass Spectrometry Letters
• /
• v.2 no.2
• /
• pp.49-52
• /
• 2011

Competitive binding of $C_{60}$ and $C_{70}$ to meso-substituted porphyrins was studied by mass spectrometry (MS). Electrospray ionization MS was employed to acquire the mass spectra of 1 : 1 porphyrin-fullerene complexes formed in a mixture of mesosubstituted porphyrin and fullerite to determine the ratio of complexes between $C_{60}$ and $C_{70}$. Matrix-free laser desorption ionization MS was used to obtain the mass spectra of fullerite to measure the mole fraction of $C_{60}$ and $C_{70}$. The binding constant ratio ($K_{70}$/$K_{60}$) was determined from the mass spectral data. The difference in standard Gibbs free energy change, ${\Delta}({\Delta}G^o)_{70-60}$, for the competitive binding of $C_{60}$ and $C_{70}$ was calculated from $K_{70}$/$K_{60}$. Of the five porphyrins, tetraphenyl, tetra(4-pyridyl), tetra(4-carboxyphenyl), tetra(3,5-di-tert-butylphenyl), and tetra(pentafluorophenyl) porphyrins, the first three non-bulky porphyrins yield negative values of ${\Delta}({\Delta}G^o)_{70-60}$, whereas the other two bulky porphyrins result in positive values of ${\Delta}({\Delta}G^o)_{70-60}$. This result indicates that $C_{70}$ binding to porphyrin is thermodynamically favored over $C_{60}$ binding in non-bulky porphyrins, but disfavored in bulky ones. It also suggests that the binding mode of $C_{70}$is different between non-bulky and bulky porphyrins, which is in line with previous experimental findings of the "side-on" binding to non-bulky porphyrins and the $C_{60}$-like "end-on" binding to bulky porphyrins.

• Corrosion Science and Technology
• /
• v.18 no.5
• /
• pp.206-211
• /
• 2019

Silicon carbide (SiC) thin films become superhard when they have microstructures of nanocolumnar crystalline grains (NCCG) with an intergranular amorphous SiC matrix. We investigated the role of ion bombardment and deposition temperature in forming the NCCG in SiC thin films. A direct-current (DC) unbalanced magnetron sputtering method was used with pure Ar as sputtering gas to deposit the SiC thin films at fixed target power of 200 W and chamber pressure of 0.4 Pa. The Ar ion bombardment of the deposited films was conducted by applying a negative DC bias voltage 0-100 V to the substrate during deposition. The deposition temperature was varied between room temperature and $450^{\circ}C$. Above a critical bias voltage of -80 V, the NCCG formed, whereas, below it, the SiC films were amorphous. Additionally, a minimum thermal energy (corresponding to a deposition temperature of $450^{\circ}C$ in this study) was required for the NCCG formation. Transmission electron microscopy, Raman spectroscopy, and glancing angle X-ray diffraction analysis (GAXRD) were conducted to probe the samples' structural characteristics. Of those methods, Raman spectroscopy was a particularly efficient non-destructive tool to analyze the formation of the SiC NCCG in the film, whereas GAXRD was insufficiently sensitive.