• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1154-1157
• /
• 2012

축산농가의 경제성과 직결되는 암소 발정기의 조기 탐지는 IT 농 축산 학계에서도 매우 중요한 문제 중 하나이며 반듯이 해결해야만 하는 문제로 알려져 있다. 이를 해결하기 위한 다양한 연구 방법들 중, 본 논문에서는 소리 센서 환경에서의 암소의 발정기 탐지 시스템에 관한 연구를 대상으로 한다. 특히, 발정기 발성음의 특징 벡터 생성에 초점을 맞춘다. 특징은 크게 분별력과 차원이라는 두 가지 기준에 대해 우수해야 한다. 즉, 좋은 특징이란 서로 다른 부류를 잘 분별해 주어야 할 뿐만 아니라, 특징 벡터의 차원이 낮을수록 계산 효율이 좋고 차원의 저주에서 멀어 진다. 본 논문에서는 통계학에 기초한 체계적인 특징 벡터 생성에 관한 알고리즘을 제안하고, 실제 축사에서 녹취한 한우 발정기 발성음을 대상으로 낮은 차원의 특징 벡터 생성 과정을 보인다. 또한 이상상황 탐지기로 잘 알려진 단일 클래스 SVM의 대표 모델인 SVDD를 탐지기로 설정하여 생성된 특징 벡터의 분별력을 실험적으로 검증한다.

• Digital Contents
• /
• no.8 s.99
• /
• pp.56-60
• /
• 2001

인터넷에서 아동을 대상으로 하는 웹사이트들이 이벤트나 광고를 통하여 아동 및 그 법정대리인 등의 개인정보를 지나치게 많이 요구하는 경우가 많고 아동들은 그에 대한 분별력이 적어서 해당 사이트를 빨리 이용하고자 하거나 상품 등을 받고자 하는 욕구에 분별 없이 자신의 개인정보는 물론 가족들, 친구들의 개인정보를 제공하게 된다. 그러나 14세 미만의 아동으로부터 개인정보를 수집하는 경우 법정대리인의 동의를 받도록 하고, 이용 또는 제3자 제공에 대한 동의권, 동의철회권, 열람청구권 및 정정요구권을 부여하고 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.166-172
• /
• 2014

Image classification is an important problem in computer vision. However, it is a very challenging problem due to the variability, ambiguity and scale change that exists in images. In this paper, we propose a method of a hypergraph based modeling can consider the higher-order relationships of semantic attributes of a scene image and apply it to a scene image classification. In order to generate the hypergraph optimized for specific scene category, we propose a novel search method based on a probabilistic subspace method and also propose a method to aggregate the expression values of the member semantic attributes that belongs to the searched subsets based on a linear transformation method via likelihood based estimation. To verify the superiority of the proposed method, we showed that the discrimination power of the feature vector generated by the proposed method is better than existing methods through experiments. And also, in a scene classification experiment, the proposed method shows a competitive classification performance compared with the conventional methods.

• The KIPS Transactions:PartD
• /
• v.19D no.4
• /
• pp.263-270
• /
• 2012

With the current development of high speed Internet and massive database technology, the amount of web documents increases rapidly, and thus, classifying those documents automatically is getting important. In this study, we propose an effective method to extract document features based on Hangeul morpheme and keyword analyses, and to classify non-structured documents automatically by predicting subjects of those documents. To extract document features, first, we select terms using a morpheme analyzer, form the keyword set based on term frequency and subject-discriminating power, and perform the scoring for each keyword using the discriminating power. Then, we generate the classification model by utilizing the commercial software that implements the decision tree, neural network, and SVM(support vector machine). Experimental results show that the proposed feature extraction method has achieved considerable performance, i.e., average precision 0.90 and recall 0.84 in case of the decision tree, in classifying the web documents by subjects.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.8
• /
• pp.94-99
• /
• 1999

It is the hybrid structure of HMM and neural network(NN) that shows high recognition rate in speech recognition algorithms. And it is a method which has majorities of statistical model and neural network model respectively. In this study, we propose a new style of the hybrid structure of semi-continuous HMM(SCHMM) and radial basis function(RBF), which re-estimates weighting coefficients probability affecting observation probability after Baum-Welch estimation. The proposed method takes account of the similarity of basis Auction of RBF's hidden layer and SCHMM's probability density functions so as to discriminate speech signals sensibly through the learned and estimated weighting coefficients of RBF. As simulation results show that the recognition rates of the hybrid structure SCHMM/RBF are higher than those of SCHMM in unlearned speakers' recognition experiment, the proposed method has been proved to be one which has more sensible property in recognition than SCHMM.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.53-60
• /
• 2008

This paper proposes a new multiobjective optimization method for discriminative training of hidden Markov models (HMMs) used as the recognizer for automatic lipreading. While the conventional Baum-Welch algorithm for training HMMs aims at maximizing the probability of the data of a class from the corresponding HMM, we define a new training criterion composed of two minimization objectives and develop a global optimization method of the criterion based on simulated annealing. The result of a speaker-dependent recognition experiment shows that the proposed method improves performance by the relative error reduction rate of about 8% in comparison to the Baum-Welch algorithm.

• Journal of Korean Society of Forest Science
• /
• v.101 no.3
• /
• pp.381-386
• /
• 2012

This study was carried out to clarify the turbidity change on three stands (Castanea crenata, Pinus densiflora and Plantation Land) by rainfall characteristics in small watershed. The change of turbidity showed in order of plantation land, Castanea stand and Pinus stand. The linear equations models between turbidity and rainfall intensity were able to account for 91% in Castanea stand, 80% in Pinus stand and 71% in plantation land. The linear equations models between turbidity and duration of rainfall were able to account for about 0-1% in three stands. The linear equations models between turbidity and preceding dry days were able to account for about 30% in three stands. The linear equations models between turbidity and accumulative rainfall were able to account for about 6-22% in three stands. The results indicates that soil runoff by land use and development of forest area could be applied to the mitigation measures such as afforestation and erosion check dam for erosion control and water quality management in small watershed.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.1 no.3
• /
• pp.189-196
• /
• 2013

In order for efficient recycling and eco-friendly treatment of construction waste, there is a need to apply a building separation and dismantling technique early on in the stage of waste generation. This study was conducted to analyze the relevant domestic circumstances and propose the applicable range of buildings in order to introduce a building separation and dismantling system to Korea. For this purpose, related policies and systems implemented overseas and the current situation of buildings were examined, and the workability of separation and dismantling of buildings according to their uses was compared. Also, the economic impact of the separation and dismantling system was examined and a survey was conducted, seeking the opinions of the relevant companies regarding the need for the system and the selection criteria for eligible buildings. Based on the results, it was determined that it would be impossible to apply the separation and dismantling system to all buildings in Korea, considering the current technical power and economic situation, and that the system should be introduced in phases, according to the building classification determined based on floor area and use, as the cost may vary depending on a number of variables including the level of difficulty and field conditions.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2018.06a
• /
• pp.42.2-42.2
• /
• 2018

신도시 및 대규모 도시 개발이 진행됨에 따라 안정적이고 효율적인 전력 공급을 위해 다수의 지상 배전함이 설치되고 있으며, 이에 따라 불법 광고물 및 스티커의 부착으로 인한 문제가 발생하고 있다. 이를 해결하기 위하여 여러 기관 및 산업체에서는 부착 방지용 코팅 도료 및 시트에 대하여 다양한 연구개발을 진행하고 있으며, 현장에 적용 된 다수의 제품이 존재한다. 하지만 현재 대부분의 제품들은 약 1년 정도의 시간이 지나면 부착 방지 기능을 상실하며, 도료와 기판 또는 시트와 기판 사이의 박리가 일어나 도시의 미관을 더욱 해치는 결과를 초래하고 있다. 이러한 원인으로는 부착력(Peel resistance, N/cm)을 측정하는 기존의 제시된 방법(KS T 1028, Peel test)으로는 정확한 측정이 어렵기 때문에 제품 선별에 어려움이 있다. 일반 기판의 경우 규격에서 요구하는 각도($90^{\circ}$, $180^{\circ}$)가 잘 유지되어 정밀한 부착력 측정이 가능하지만, 저점착 기능성 코팅소재(Anti-adhesion coating)의 경우 부착 자체가 어렵기 때문에 요구 각도를 유지하기 어려워 정밀한 측정을 할 수 없다. 이러한 문제점들을 해결하고자 압입자(Probe)를 이용한 새로운 평가 장치와 방법(Tack test)을 개발 및 제시하였다. 평가 지표로는 최대 점착력(Adhesive force, N), 최대 점착력일 때 점착제가 늘어난 총 길이(Extension of adhesive, mm), 탈착 에너지(Energy, J)가 있으며, 인가하는 힘(N)이 커질수록, 탈착 속도(Velocity)가 빨라질수록 평가 지표 모두 값이 상승하는 경향성을 보인다. 각 시험방법(Peel test, Tack test)에 대한 테이프류 점착제와 기판과의 결합이 끊어지는(Debonding, 탈착) 메커니즘(Mechanism)은 점착제 기공(Cavity)의 형성, 결합이 끊어지는 힘(Debonding force, N), 힘의 평형(Force balance)로 설명 가능하며, 상호간의 관계성을 도출한다. 이와 같은 평가 지표를 활용하여 저점착 기능성 코팅소재에 대해 정밀한 평가를 하는 것으로, 향후 개발될 다양한 제품에 대한 성능 분별력을 높이고, 현장에 적용 될 제품들의 성능을 끌어 올려 기존에 발생한 다양한 문제점들을 해결 할 수 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.8
• /
• pp.1433-1445
• /
• 1994

In this paper, an coherent optical correlator system based on the off-axis projection synthetic discriminant funtion (OA-pSDF) was analyzed and implemented optically. The filter was synthesized by combining conventional pSDF with single reference plane wave multiplexing. Synthesized pSDF were transformed to binary phase only filters (BPOFs) and fabricated as computer generated holograms(CGHs), which was used in the real time optical correlator system instead of using expensive spatial light modulators(SLMs). From the characteristic test, it was found that OA-pSDF showed distortion invariance and good performances in discrminating subset images. The proposed OA-pSDF BPOF could overcome the limitations of conventional BPOFs : that is distortion variance such as acale and rotation, especially out of plane variance.