• 충청수학회지
• /
• 제23권4호
• /
• pp.893-902
• /
• 2010

In this article we study self-dual codes of length 6 over ${\mathbb{Z}}_m$. A classification of such codes for $m{\leq}24$ is given. Main tool for the classification is the new double cosets decomposition method given in the recent article of the author.

• 대한토목학회논문집
• /
• 제30권1D호
• /
• pp.45-51
• /
• 2010

차종별 교통량 자료는 도로의 운영, 제어, 유지관리 계획 수립 및 과적차량 단속에도 매우 중요한 자료이다. 본 논문에서는 축검지 센서를 차량 진행방향에 대해서 경사지게 설치하고 이를 통해서 얻어지는 자료를 활용하여 차종분류 알고리즘을 개발하였다. 새로운 개발한 차종분류 알고리즘에서는 2축 차량에서 후륜 차량바퀴의 복륜 여부를 새로운 분류변수로 설정하였다. 분석대상이 차량은 1,878대로 CCTV를 활용하여 기록했으며 인력식 조사를 통하여 복륜여부와 차종을 구분하였다. 계측된 차량바퀴 접지면의 대각선 길이 성분의 크기를 입력 자료로 활용한 판별분석을 통하여 후륜바퀴가 복륜인지 단륜인지를 구분하였다. 복륜 여부만을 이용하여 차종분류를 했을 때, 차종분류의 정확도는 1종에 속하는 차량의 경우는 96.92%, 3종에 속하는 차량에서는 82.91% 그리고 4종에 속하는 차량에서는 79.13%에 이르는 것으로 분석되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2078-2093
• /
• 2019

Visual smoke recognition is a challenging task due to large variations in shape, texture and color of smoke. To improve performance, we propose a novel smoke recognition method by combining dual-encoded features that are extracted from both spatial and Curvelet domains. A Curvelet transform is used to filter an image to generate fifty sub-images of Curvelet coefficients. Then we extract Local Binary Pattern (LBP) maps from these coefficient maps and aggregate histograms of these LBP maps to produce a histogram map. Afterwards, we encode the histogram map again to generate Dual-encoded Local Binary Patterns (Dual-LBP). Histograms of Dual-LBPs from Curvelet domain and Completed Local Binary Patterns (CLBP) from spatial domain are concatenated to form the feature for smoke recognition. Finally, we adopt Gaussian Kernel Optimization (GKO) algorithm to search the optimal kernel parameters of Support Vector Machine (SVM) for further improvement of classification accuracy. Experimental results demonstrate that our method can extract effective and reasonable features of smoke images, and achieve good classification accuracy.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1248-1259
• /
• 2016

Classification methods based on dual energy X-ray absorptiometry, ultrasonic waves, and quantitative computed tomography have been proposed. Also, a classification method based on machine learning with bone mineral density and structural indicators extracted from the CT images has been proposed. We propose a method which enhances the performance of existing classification method based on bone mineral density and structural indicators by extending structural indicators and using principal component analysis. Experimental result shows that the proposed method in this paper improves the correctness of osteoporosis classification 2.8% with extended structural indicators only and 4.8% with both extended structural indicators and principal component analysis. In addition, this paper proposes a method of automatic phantom analysis needed to convert the CT values to BMD values. While existing method requires manual operation to mark the bone region within the phantom, the proposed method detects the bone region automatically by detecting circles in the CT image. The proposed method and the existing method gave the same conversion formula for converting CT value to bone mineral density.

• 정보보호학회논문지
• /
• 제28권1호
• /
• pp.85-93
• /
• 2018

생체 정보를 이용한 사용자 인증은 차세대 인증 방법으로서 기존의 인증 시스템에서 급진적으로 사용되고 있는 인증 방법이다. 대부분의 생체 인증 시스템은 수집된 생체 정보가 가지는 노이즈로 인한 문제, 데이터의 품질에 대한 문제, 인식률의 한계 등 많은 문제점들을 가지고 있다. 이를 해결하기 위한 방법으로 본 논문에서는 비선형적인 실제 데이터를 정확하게 처리하기 위해 비선형기법인 Dual QML을 사용하고, 또한 정확한 영역을 추출하여 인증의 정확도를 증가시키는 전처리 과정을 추가로 제안하여 정확도 증가뿐만 아니라 성능을 향상시키는 방법을 제안하고자 한다. 앞서 발표된 Dual QML은 생체 정보로 얼굴, 장문, 귀를 사용하였다. 본 논문은 앞선 Dual QML 실험에 사용하지 않은 홍채를 생체 정보로 사용하여 홍채 인식을 위한 방법으로도 Dual QML이 우수하다는 것을 보이고자 한다. 마지막으로 실험을 통해 이에 대한 실증을 보이고자 한다.

• Journal of Electrical Engineering and Technology
• /
• 제13권6호
• /
• pp.2511-2520
• /
• 2018

In this study, Multi-Radial Basis Function Support Vector Machine (Multi-RBF SVM) classifier is introduced based on a composite kernel function. In the proposed multi-RBF support vector machine classifier, the input space is divided into several local subsets considered for extremely nonlinear classification tasks. Each local subset is expressed as nonlinear classification subspace and mapped into feature space by using kernel function. The composite kernel function employs the dual RBF structure. By capturing the nonlinear distribution knowledge of local subsets, the training data is mapped into higher feature space, then Multi-SVM classifier is realized by using the composite kernel function through optimization procedure similar to conventional SVM classifier. The original training data set is partitioned by using some unsupervised learning methods such as clustering methods. In this study, three types of clustering method are considered such as Affinity propagation (AP), Hard C-Mean (HCM) and Iterative Self-Organizing Data Analysis Technique Algorithm (ISODATA). Experimental results on benchmark machine learning datasets show that the proposed method improves the classification performance efficiently.

• 대한방사선기술학회지:방사선기술과학
• /
• 제42권1호
• /
• pp.9-17
• /
• 2019

Although digital mammography is a representative method for breast cancer detection. It has a limitation in detecting and classifying breast tumor due to superimposed structures. Machine learning, which is a part of artificial intelligence fields, is a method for analysing a large amount of data using complex algorithms, recognizing patterns and making prediction. In this study, we proposed a technique to improve the diagnostic accuracy of energy-selective mammography by training data using the machine learning algorithm and using dual-energy measurements. A dual-energy images obtained from a photon-counting detector were used for the input data of machine learning algorithms, and we analyzed the accuracy of predicted tumor thickness for verifying the machine learning algorithms. The results showed that the classification accuracy of tumor thickness was above 95% and was improved with an increase of imput data. Therefore, we expect that the diagnostic accuracy of energy-selective mammography can be improved by using machine learning.

• Korean Journal of Mathematics
• /
• 제28권2호
• /
• pp.285-294
• /
• 2020

We study the complementary information set codes (for short, CIS codes) over 𝔽₄. They are strongly connected to correlation-immune functions over 𝔽₄. Also the class of CIS codes includes the self-dual codes. We find a construction method of CIS codes over 𝔽₄ and a criterion for checking equivalence of CIS codes over 𝔽₄. We complete the classification of all inequivalent CIS codes of length up to 8 over 𝔽₄.

• 한국멀티미디어학회논문지
• /
• 제23권4호
• /
• pp.525-538
• /
• 2020

A practical animal face classification system that classifies animals in image and video data is considered as a pivotal topic in machine learning. In this research, we are proposing a novel method of fully connected dual Deep Convolutional Neural Network (DCNN), which extracts and analyzes image features on a large scale. With the inclusion of the state of the art Batch Normalization layer and Exponential Linear Unit (ELU) layer, our proposed DCNN has gained the capability of analyzing a large amount of dataset as well as extracting more features than before. For this research, we have built our dataset containing ten thousand animal faces of ten animal classes and a dual DCNN. The significance of our network is that it has four sets of convolutional functions that work laterally with each other. We used a relatively small amount of batch size and a large number of iteration to mitigate overfitting during the training session. We have also used image augmentation to vary the shapes of the training images for the better learning process. The results demonstrate that, with an accuracy rate of 92.0%, the proposed DCNN outruns its counterparts while causing less computing costs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2607-2627
• /
• 2017

Nonnegative matrix factorization (NMF) has received considerable attention due to its effectiveness of reducing high dimensional data and importance of producing a parts-based image representation. Most of existing NMF variants attempt to address the assertion that the observed data distribute on a nonlinear low-dimensional manifold. However, recent research results showed that not only the observed data but also the features lie on the low-dimensional manifolds. In addition, a few hard priori label information is available and thus helps to uncover the intrinsic geometrical and discriminative structures of the data space. Motivated by the two aspects above mentioned, we propose a novel algorithm to enhance the effectiveness of image representation, called Dual graph-regularized Constrained Nonnegative Matrix Factorization (DCNMF). The underlying philosophy of the proposed method is that it not only considers the geometric structures of the data manifold and the feature manifold simultaneously, but also mines valuable information from a few known labeled examples. These schemes will improve the performance of image representation and thus enhance the effectiveness of image classification. Extensive experiments on common benchmarks demonstrated that DCNMF has its superiority in image classification compared with state-of-the-art methods.