• 제어로봇시스템학회논문지
• /
• 제13권8호
• /
• pp.749-753
• /
• 2007

In this paper, a generalized version of the Motion Silhouette Image(MSI) called the Generic Motion Silhouette Image (GMSI) is proposed for gait recognition. The GMSI is a gray-level image and involves the spatiotemporal information of individual motion. The GMSI not only generalizes the MSI but also reflects a flexible feature of a gait sequence. Along with the GMSI, we use the Principal Component Analysis(PCA) to reduce the dimensionality of the GMSI and the Nearest Neighbor(NN) for classification. We apply the proposed feature to NLPR database and compare it with the conventional MSI. Experimental results show the effectiveness of the GMSI.

• 통합자연과학논문집
• /
• 제5권2호
• /
• pp.120-126
• /
• 2012

This paper describes the algorithm that lowers the dimension, maintains the gesture recognition and significantly reduces the eigenspace configuration time by combining the higher correlation feature information and Principle Component Analysis. Since the suggested method doesn't require a lot of computation than the method using existing geometric information or stereo image, the fact that it is very suitable for building the real-time system has been proved through the experiment. In addition, since the existing point to point method which is a simple distance calculation has many errors, in this paper to improve recognition rate the recognition error could be reduced by using several successive input images as a unit of recognition with K-Nearest Neighbor which is the improved Class to Class method.

• Bulletin of the Korean Chemical Society
• /
• 제17권2호
• /
• pp.192-198
• /
• 1996

We present a theoretical formulation of diffusion process on solid surface based on multidimensional transition state theory (TST). Surface diffusion of single adatom results from hopping processes on corrugated potential surface and is affected by surface vibrations of surface atoms. The rate of rare events such as hopping between lattice sites can be calculated by transition state theory. In order to include the interactions of the adatom with surface vibrations, it is assumed that the coordinates of adatom are coupled to the bath of harmonic oscillators whose frequencies are those of surface phonon modes. When nearest neighbor surface atoms are considered, we can construct Hamiltonians which contain terms for interactions of adatom with surface vibrations for the well minimum and the saddle point configurations, respectively. The escape rate constants, thus the surface diffusion parameters, are obtained by normal mode analysis of the force constant matrix based on the Hamiltonian. The analysis is applied to the diffusion coefficients of W, Ir, Pt and Ta atoms on the bcc(110) plane of W in the zero-coverage limit. The results of the calculations are encouraging considering the limitations of the model considered in the study.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.93-96
• /
• 2022

Natural language processing (NLP) is utilized to understand a natural text. Text analysis systems use natural language algorithms to find the meaning of large amounts of text. Text classification represents a basic task of NLP with a wide range of applications such as topic labeling, sentiment analysis, spam detection, and intent detection. The algorithm can transform user's unstructured thoughts into more structured data. In this work, a text classifier has been developed that uses academic admission and registration texts as input, analyzes its content, and then automatically assigns relevant tags such as admission, graduate school, and registration. In this work, the well-known algorithms support vector machine SVM and K-nearest neighbor (kNN) algorithms are used to develop the above-mentioned classifier. The obtained results showed that the SVM classifier outperformed the kNN classifier with an overall accuracy of 98.9%. in addition, the mean absolute error of SVM was 0.0064 while it was 0.0098 for kNN classifier. Based on the obtained results, the SVM is used to implement the academic text classification in this work.

• Communications for Statistical Applications and Methods
• /
• 제30권3호
• /
• pp.331-341
• /
• 2023

Handling missing values in data analysis is essential in constructing a good prediction model. The easiest way to handle missing values is to use complete case data, but this can lead to information loss within the data and invalid conclusions in data analysis. Imputation is a technique that replaces missing data with alternative values obtained from information in a dataset. Conventional imputation methods include K-nearest-neighbor imputation and multiple imputations. Recent methods include missForest, missRanger, and mixgb ,all which use machine learning algorithms. This paper compares the imputation techniques for datasets with mixed datatypes in various situations, such as data size, missing ratios, and missing mechanisms. To evaluate the performance of each method in mixed datasets, we propose a new imputation performance measure (IPM) that is a unified measurement applicable to numerical and categorical variables. We believe this metric can help find the best imputation method. Finally, we summarize the comparison results with imputation performances and computational times.

• 대한공간정보학회지
• /
• 제22권3호
• /
• pp.99-105
• /
• 2014

교통사고는 화재와 더불어 도시지역에서 발생하는 인위적 재해 중 가장 높은 비중을 차지하고 있어서 보다 과학적인 원인분석과 더불어 다양한 예방대책수립이 필요하다. 본 연구에서는 지방중소도시인 진주시를 대상으로 2013년 발생한 교통사고 데이터를 교통사고 발생 원인별 분석, 발생 시간 및 계절적 특성분석 등 위치정보와 연계하여 시공간적 분포특성을 분석하고 토지이용계획에 따른 도시공간개발 특성과 연계함으로서 교통사고와의 공간적 상관성을 분석하였다. 그 결과 사고유형별 사고 분포특성을 보면 측면직각추돌(차 대 차), 횡단중사고(차 대 사람)가 밀도분석과 최근린분석에서 가장 군집도가 높았으며, 중심상업지역과 고밀도 주거지역, 공업지역을 연결하는 도로상에서 가장 많이 발생하는 특성을 보였다. 또한 피해상황에서는 인적피해가, 기상상태에서는 맑은 날이, 노면상태는 건조할 때가, 도로형태는 삼지교차로 일 때가 가장 높은 군집도를 보여주었다.

• 한국산림과학회지
• /
• 제101권4호
• /
• pp.547-557
• /
• 2012

본 연구는 강원대학교 학술림을 대상으로 현장조사자료와 Landsat TM-5 위성영상 정보를 이용하여 k-NN기법을 통해 산림바이오매스를 추정하는 것을 목적으로 하였다. 임상 층화 및 최소수평 참조거리(HRA)와 공간필터링의 조건변화에 따른 최적의 참조표본점 개수(k)를 검토하였으며, 이에 따른 산림바이오매스량 추정과 정확도를 비교 분석하였다. 침엽수는 $5{\times}5$ 필터링을 적용한 HRA 4 km와 k=8를 적용하였을 때 최소의 RMSE를 나타냈으며, 편차는 1.8 t/ha으로 과대추정되었다. 한편, 잣나무와 활엽수는 필터링을 적용하지 않은 HRA 4km의 k=8과 HRA 10 km의 k=6을 적용하였을 때 최소의 RMSE가 나타났으며, 편차는 각각 -1.6 t/ha, -5.2 t/ha로 과소추정되었다. k-NN기법에 의하여 추정된 총 바이오매스량은 799천t이며, ha당 평균 산림바이오매스량은 237 t/ha로서 표본점자료를 이용한 추정치보다 약 1 t/ha 높게 나타났다.

• Journal of Information Science Theory and Practice
• /
• 제9권2호
• /
• pp.47-65
• /
• 2021

This study aims to identify specific topics, trends, and structural characteristics of scholarly communication research, based on 1,435 articles published from 1970 to 2018 in the Scopus database through Latent Dirichlet Allocation topic modeling, serial analysis, and network analysis. Topic modeling, time series analysis, and network analysis were used to analyze specific topics, trends, and structures, respectively. The results were summarized into three sets as follows. First, the specific topics of scholarly communication research were nineteen in number, including research resource management and research data, and their research proportion is even. Second, as a result of the time series analysis, there are three upward trending topics: Topic 6: Open Access Publishing, Topic 7: Green Open Access, Topic 19: Informal Communication, and two downward trending topics: Topic 11: Researcher Network and Topic 12: Electronic Journal. Third, the network analysis results indicated that high mean profile association topics were related to the institution, and topics with high triangle betweenness centrality, such as Topic 14: Research Resource Management, shared the citation context. Also, through cluster analysis using parallel nearest neighbor clustering, six clusters connected with different concepts were identified.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.1189-1192
• /
• 2005

본 논문에서는 스케치 연산자를 적용하여 견실한 얼굴인식 방법을 제안한다. 제안된 방법은 인식 대상의 중요한 특성인 에지(edge), 벨리(valley) 및 질감(texture) 성분을 효과적으로 표현하기 위한 방법으로써, BDIP(block difference of inverse probabilities)를 사용하여 얼굴의 특징을 스케치 영상과 같이 나타내는 얼굴 영상을 획득한다. 그리고, BDIP 처리된 얼굴 영상은 입력 데이터의 차원 축소 및 얼굴 특징 벡터의 추출을 위해 PCA(Principal Component Analysis)를 수행한 후, Nearest Neighbor 분류기를 통해 인식을 수행한다. 제안된 방법의 성능을 평가하기 위하여, 일반적으로 많이 사용되는 HE(Histogram equalization)을 사용한 얼굴 인식 방법과의 비교를 수행한다. 실험결과, 본 논문에서 제안한 방법이 고유값이 적은 경우에 가장 높은 인식률을 나타내는 것을 알 수 있었다.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.402-410
• /
• 2017

For many years, researchers in face description area have been representing and recognizing faces based on different methods that include subspace discriminant analysis, statistical learning and non-statistics based approach etc. But still automatic face recognition remains an interesting but challenging problem. This paper presents a novel and efficient face image representation method based on Optimized Local Ternary Pattern (OLTP) texture features. The face image is divided into several regions from which the OLTP texture feature distributions are extracted and concatenated into a feature vector that can act as face descriptor. The recognition is performed using nearest neighbor classification method with Chi-square distance as a similarity measure. Extensive experimental results on Yale B, ORL and AR face databases show that OLTP consistently performs much better than other well recognized texture models for face recognition.