• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.742-762
• /
• 2015

In this study, we propose a distance metric learning approach called discriminant metric learning (DML) for face verification, which addresses a binary-class problem for classifying whether or not two input images are of the same subject. The critical issue for solving this problem is determining the method to be used for measuring the distance between two images. Among various methods, the large margin nearest neighbor (LMNN) method is a state-of-the-art algorithm. However, to compensate the LMNN's entangled data distribution due to high levels of appearance variations in unconstrained environments, DML's goal is to penalize violations of the negative pair distance relationship, i.e., the images with different labels, while being integrated with LMNN to model the distance relation between positive pairs, i.e., the images with the same label. The likelihoods of the input images, estimated using DML and LMNN metrics, are then weighted and combined for further analysis. Additionally, rather than using the k-nearest neighbor (k-NN) classification mechanism, we propose a verification mechanism that measures the correlation of the class label distribution of neighbors to reduce the false negative rate of positive pairs. From the experimental results, we see that DML can modify the relation of negative pairs in the original LMNN space and compensate for LMNN's performance on faces with large variances, such as pose and expression.

• 방송공학회논문지
• /
• 제27권4호
• /
• pp.511-518
• /
• 2022

딥러닝 기반의 지도학습은 다양한 응용 분야에서 비약적인 발전을 이루었다. 그러나 많은 지도 학습 방법들은 학습 및 테스트 데이터가 동일한 분포에서 추출된다는 공통된 가정 하에 이루어진다. 이 제약 조건에서 벗어나는 경우, 학습 도메인에서 훈련된 딥러닝 네트워크는 도메인 간의 분포 차이로 인하여 테스트 도메인에서의 성능이 급격하게 저하될 가능성이 높다. 도메인 적응 기술은 레이블이 풍부한 학습 도메인 (소스 도메인)의 학습된 지식을 기반으로 레이블이 불충분한 테스트 도메인 (타겟 도메인) 에서 성공적인 추론을 할 수 있도록 딥러닝 네트워크를 훈련하는 전이 학습의 한 방법론이다. 특히 비지도 도메인 적응 기술은 타겟 도메인에 레이블이 전혀 없는 이미지 데이터에만 접근할 수 있는 상황을 가정하여 도메인 적응 문제를 다룬다. 본 논문에서는 이러한 비지도 학습 기반의 도메인 적응 기술들에 대해 탐구한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권3호
• /
• pp.522-538
• /
• 2013

Content based image retrieval has become an increasingly important research topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The retrieval systems rely on a key component, the predefined or learned similarity measures over images. We note that, the similarity measures can be potential improved if the data distribution information is exploited using a more sophisticated way. In this paper, we propose a similarity measure learning approach for image retrieval. The similarity measure, so called Fisher kernel, is derived from the probabilistic distribution of images and is the function over observed data, hidden variable and model parameters, where the hidden variables encode high level information which are powerful in discrimination and are failed to be exploited in previous methods. We further propose a discriminative learning method for the similarity measure, i.e., encouraging the learned similarity to take a large value for a pair of images with the same label and to take a small value for a pair of images with distinct labels. The learned similarity measure, fully exploiting the data distribution, is well adapted to dataset and would improve the retrieval system. We evaluate the proposed method on Corel-1000, Corel5k, Caltech101 and MIRFlickr 25,000 databases. The results show the competitive performance of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2527-2545
• /
• 2016

Measuring the similarity of given samples is a key problem of recognition, clustering, retrieval and related applications. A number of works, e.g. kernel method and metric learning, have been contributed to this problem. The challenge of similarity learning is to find a similarity robust to intra-class variance and simultaneously selective to inter-class characteristic. We observed that, the similarity measure can be improved if the data distribution and hidden semantic information are exploited in a more sophisticated way. In this paper, we propose a similarity learning approach for retrieval and recognition. The approach, termed as LDA-FEK, derives free energy kernel (FEK) from Latent Dirichlet Allocation (LDA). First, it trains LDA and constructs kernel using the parameters and variables of the trained model. Then, the unknown kernel parameters are learned by a discriminative learning approach. The main contributions of the proposed method are twofold: (1) the method is computationally efficient and scalable since the parameters in kernel are determined in a staged way; (2) the method exploits data distribution and semantic level hidden information by means of LDA. To evaluate the performance of LDA-FEK, we apply it for image retrieval over two data sets and for text categorization on four popular data sets. The results show the competitive performance of our method.

• Asian Journal of Business Environment
• /
• 제12권1호
• /
• pp.11-16
• /
• 2022

Purpose: This study is aimed to map the provinces in Indonesia based on the education and ICT indicators using several unsupervised learning algorithms. Research design, data, and methodology: The education and ICT indicators such as student-teacher ratio, illiteracy rate, net enrolment ratio, internet access, computer ownership, are used. Several approaches to get deeper understanding on provincial strength and weakness based on these indicators are implemented. The approaches are Ensemble K-Mean and Fuzzy C Means clustering. Results: There are at least three clusters observed in Indonesia the education quality, participation, facilities and ICT Access. Cluster with high education quality and ICT access are consist of DKI Jakarta, Yogyakarta, Riau Islands, East Kalimantan and Bali. These provinces show rapid economic growth. Meanwhile the other cluster consisting of six provinces (NTT, West Kalimantan, Central Sulawesi, West Sulawesi, North Maluku, and Papua) are the cluster with lower education quality and ICT development which impact their economic growth. Conclusions: The provinces in Indonesia are clustered into three group based on the education attainment and ICT indicators. Some provinces can directly implement e-learning; however, more provinces need to improve the education quality and facilities as well as the ICT infrastructure before implementing the e-learning.

• Genomics & Informatics
• /
• 제18권1호
• /
• pp.7.1-7.7
• /
• 2020

In this paper, we present few technical notes about the distance distribution paradigm for Mosaab-metric using 1, 2, and 3 grams feature extraction techniques to analyze composite data points in high dimensional feature spaces. This technical analysis will help the specialist in bioinformatics and biotechnology to deeply explore the biodiversity of influenza virus genome as a composite data point. Various technical examples are presented in this paper, in addition, the integrated statistical learning pipeline to process segmented genomes of influenza virus is illustrated as sequential-parallel computational pipeline.

• 한국산학기술학회논문지
• /
• 제12권10호
• /
• pp.4543-4549
• /
• 2011

본 연구에서는 소프트웨어 제품을 개발하여 테스팅을 하는 과정에서 소프트웨어 관리자들이 소프트웨어 및 검사 도구에 효율적인 학습기법을 이용한 NHPP 소프트웨어 모형에 대하여 연구 하였다. 적용분포는 버르 분포를 적용한 유한고장 NHPP에 기초하였다. 소프트웨어 오류 탐색 기법은 사전에 알지 못하지만 자동적으로 발견되는 에러를 고려한 영향요인과 사전 경험에 의하여 세밀하게 에러를 발견하기 위하여 테스팅 관리자가 설정해놓은 요인인 학습효과의 특성에 대한 문제를 비교 제시 하였다. 그 결과 학습요인이 자동 에러 탐색요인보다 큰 경우가 대체적으로 효율적인 모형임을 확인 할 수 있었다. 본 논문의 수치적인 예에서는 고장 간격 시간 자료를 적용하고 모수추정 방법은 최우추정법을 이용하여 추세분석을 통하여 자료의 효율성을 입증한 후 평균자승오차와 $R^2$(결정계수)를 이용하여 효율적인 모형을 선택 비교하였다.

• Communications for Statistical Applications and Methods
• /
• 제27권2호
• /
• pp.255-268
• /
• 2020

A mixture of multivariate canonical fundamental skew t-distribution (CFUST) has been of interest in various fields. In particular, interest in the unsupervised learning society is noteworthy. However, fitting the model via EM algorithm suffers from significant processing time. The main cause is due to the calculation of many multivariate t-cdfs (cumulative distribution functions) in E-step. In this article, we provide an approximate, but fast calculation method for the in univariate fashion, which is the product of successively conditional univariate t-cdfs with Taylor's first order approximation. By replacing all multivariate t-cdfs in E-step with the proposed approximate versions, we obtain the admissible results of fitting the model, where it gives 85% reduction time for the 5 dimensional skewness case of the Australian Institution Sport data set. For this approach, discussions about rough properties, advantages and limits are also presented.

• Composites Research
• /
• 제32권5호
• /
• pp.216-221
• /
• 2019

Piecewise Integrated Composite (PIC) 보는 하중 유형에 따라 구간을 나누어, 각 구간마다 하중 유형에 강한 복합재료의 적층 순서를 배열한 보이다. 본 연구에서는 보의 거동을 고려하여 PIC 보의 구간을 머신 러닝을 통해 나누어 기존에 제시되었던 PIC 보에 비해 우수한 굽힘 특성을 갖게 하는 것이 목적이다. FE 모델의 240개 요소가 참조점으로 선택되었다. 선행 유한요소해석은 머신 러닝의 학습데이터 생성을 위하여 규칙적으로 분포된 참조점에서 3축 특성 값(Triaxiality)으로 나타냈다. 3축 특성 값은 인장, 압축 그리고 전단의 하중유형을 나타낸다. 머신 러닝 모델은 하이퍼파라미터(Hyperparameter)와 학습데이터로 구성되었으며, 하이퍼파라미터 튜닝을 통해 적절한 하중 충실도를 도출하였지만, 거동이 큰 보의 옆면에서는 적절하지 않은 하중 충실도가 도출되었다. 이를 해결하기 위하여 고르게 배치한 참조점을 보의 거동에 따라 배치하여 학습 데이터를 얻었고, 머신 러닝 모델이 생성되었다. 앞서 생성된 머신 러닝 모델을 통하여 보가 매핑 되었고, PIC 보에 대하여 유한요소 해석을 진행한 결과, 기존에 제시되었던 PIC 보에 비해 최대하중과 흡수 에너지가 커지는 특성이 나타났다.

• 유통과학연구
• /
• 제15권12호
• /
• pp.95-102
• /
• 2017

Purpose - This study aims to develop diagnostic indices for managerial performance of agro-food distribution corporations. In particular, weights of diagnostic indices were estimated using the AHP method. Management diagnosis on agro-food distribution corporations is expected to increase their competitiveness in the domestic market as well as in international markets. Research design, data, and methodology - It develops weights or importance of the diagnostic indices based upon the survey of 21 experts in food distribution management. The survey was carried out using e-mail. Management diagnostic indices were developed based upon four BSC(Balanced Scorecard) perspectives of finance, learning/growth/leadership, customer, and internal process/technology. Results - Diagnostic indices on financial perspective consist on profitability, productivity, growth, stability and activity. Learning and leadership perspective indices consist of management will, CEO leadership, level of learning, innovation, and level of management information system. Customer perspective indices are branding, customer and channel management and internal process/technology indices consist of fourteen sub-indices representing technologies, efficiency, and dynamics. It was estimated that the weight of financial perspective index was 0.3, internal process/technology perspective index 0.248, customer category index 0.247, and learning, growth and leadership perspective index 0.205. This study also estimates weights of sub-indices for managerial diagnosis by four different perspectives. Estimated weight of profitability (0.085) is the greatest among financial perspective indices, followed by stability (0.072), growth (0.053), productivity (0.051), and activity (0.038). While estimated weights of leadership, capability, and information indices are 0.100, 0.061, and 0.044 respectively, weights of marketing, customer management, and quality and service indices are 0.104, 0.093, and 0.051, respectively. Among internal process/technology perspective, estimated weights of efficiency, technology, and innovation indices are 0.106, 0.088, and 0.054, respectively. Conclusions - The diagnostic indices for managerial performance of agro-food distribution corporations would be utilized by agro-food distribution corporations themselves, extension service institutions, and consultants. It is also expected that central and local governments use diagnostic indices developed in this study for the purpose of evaluating the effects of governmental support programs for agro-food distribution corporations. Futhermore researchers and consultants would modify diagnostic indices developed in this study, reflecting characteristics and situation of types of agro-food distribution corporations.