• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.952-959
• /
• 2018

Clustering is one of the most fundamental algorithms in machine learning. The performance of clustering is affected by the distribution of data, and when there are more data or more dimensions, the performance is degraded. For this reason, we use a stacked auto encoder, one of the deep learning algorithms, to reduce the dimension of data which generate a feature vector that best represents the input data. We use k-means, which is a famous algorithm, as a clustering. Sine the feature vector which reduced dimensions are also multi dimensional, we use the Euclidean distance as well as the cosine similarity to increase the performance which calculating the similarity between the center of the cluster and the data as a vector. A deep clustering networks combining a stacked auto encoder and k-means re-trains the networks when the k-means result changes. When re-training the networks, the loss function of the stacked auto encoder and the loss function of the k-means are combined to improve the performance and the stability of the network. Experiments of benchmark image ad document dataset empirically validated the power of the proposed algorithm.

• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1415-1422
• /
• 2019

배경 제거는 동영상에서 변화를 감지하는 컴퓨터 비전 및 이미지 처리의 주요 작업이다. 최상의 성능을 가지는 배경 제거 방법은 일반적인 컴퓨팅 환경에서 실시간으로 사용할 수 없을 만큼 계산량이 많다. 제안하는 알고리즘은 널리 사용되는 MOG 기반의 배경 제거 알고리즘을 이미지 크기 조정 알고리즘으로 개선했다. 제안된 이미지 크기 조정 알고리즘은 계산량을 대폭 감소시키고 지역 정보를 활용하도록 설계해 카메라 잡음에 강력하다. 제안된 알고리즘의 실험결과는 최신 배경 제거 방법에 근접하는 분류능력과 13배 이상 빠른 처리 속도를 가진다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5143-5158
• /
• 2018

Improving the intrusion detection system (IDS) is a pressing need for cyber security world. With the growth of computer networks, there are constantly daily new attacks. Machine Learning (ML) is one of the most important fields which have great contribution to address the intrusion detection issues. One of these issues relates to the imbalance of the diverse classes of network traffic. Accuracy paradox is a result of training ML algorithm with imbalanced classes. Most of the previous efforts concern improving the overall accuracy of these models which is truly important. However, even they improved the total accuracy of the system; it fell in the accuracy paradox. The seriousness of the threat caused by the minor classes and the pitfalls of the previous efforts to address this issue is the motive for this work. In this paper, we consolidated stratified sampling, cost function and weighted Support Vector Machine (WSVM) method to address the accuracy paradox of ID problem. This model achieved good results of total accuracy and superior results in the small classes like the User-To-Remote and Remote-To-Local attacks using the improved version of the benchmark dataset KDDCup99 which is called NSL-KDD.

• 전기학회논문지
• /
• 제64권7호
• /
• pp.1064-1073
• /
• 2015

In this study, we introduce the pedestrian detection system by using the feature of HOG-PCA and RBFNNs pattern classifier. HOG(Histogram of Oriented Gradient) feature is extracted from input image to identify and recognize a object. And a dimension is reduced for improving performance as well as processing speed by using PCA which is a typical dimensional reduction algorithm. So, the feature of HOG-PCA through the dimensional reduction by using PCA leads to the improvement of the detection rate. FCM clustering algorithm is used instead of gaussian function to apply the characteristic of input data as well and connection weight is used by polynomial expression such as constant, linear, quadratic and modified quadratic. Finally, INRIA person database known as one of the benchmark dataset used for pedestrian detection is applied for the performance evaluation of the proposed classifier. The experimental result of the proposed classifier are compared with those studied by Dalal.

• 로봇학회논문지
• /
• 제11권4호
• /
• pp.300-309
• /
• 2016

This paper proposes a method for motion estimation of consecutive cameras using 3-D straight lines. The motion estimation algorithm uses two non-parallel 3-D line correspondences to quickly establish an initial guess for the relative pose of adjacent frames, which requires less correspondences than that of current approaches requiring three correspondences when using 3-D points or 3-D planes. The estimated motion is further refined by a nonlinear optimization technique with inlier correspondences for higher accuracy. Since there is no dominant line representation in 3-D space, we simulate two line representations, which can be thought as mainly adopted methods in the field, and verify one as the best choice from the simulation results. We also propose a simple but effective 3-D line fitting algorithm considering the fact that the variance arises in the projective directions thus can be reduced to 2-D fitting problem. We provide experimental results of the proposed motion estimation system comparing with state-of-the-art algorithms using an open benchmark dataset.

• Earthquakes and Structures
• /
• 제9권3호
• /
• pp.673-698
• /
• 2015

This paper investigates inelastic seismic demands of the normal component of near-fault pulse-like ground motions, which differ considerably from those of far-fault ground motions and also parallel component of near-fault ones. The results are utilized to improve the nonlinear static procedure (NSP) called Displacement Coefficient Method (DCM). 96 near-fault and 20 far-fault ground motions and the responses of various single degree of freedom (SDOF) systems constitute the dataset. Nonlinear Dynamic Analysis (NDA) is utilized as the benchmark for comparison with nonlinear static analysis results. Considerable influences of different faulting mechanisms are observed on inelastic seismic demands. The demands are functions of the strength ratio and also the pulse period to structural period ratio. Simple mathematical expressions are developed to consider the effects of near-fault motion and fault type on nonlinear responses. Modifications are presented for the DCM by introducing a near-fault modification factor, $C_N$. In locations, where the fault type is known, the modifications proposed in this paper help to obtain a more precise estimate of seismic demands in structures.

• 전기학회논문지
• /
• 제61권1호
• /
• pp.135-142
• /
• 2012

In this paper, we proposed a new architecture called radial basis function-based polynomial neural networks classifier that consists of heterogeneous neural networks such as radial basis function neural networks and polynomial neural networks. The underlying architecture of the proposed model equals to polynomial neural networks(PNNs) while polynomial neurons in PNNs are composed of Fuzzy-c means-based radial basis function neural networks(FCM-based RBFNNs) instead of the conventional polynomial function. We consider PNNs to find the optimal local models and use RBFNNs to cover the high dimensionality problems. Also, in the hidden layer of RBFNNs, FCM algorithm is used to produce some clusters based on the similarity of given dataset. The proposed model depends on some parameters such as the number of input variables in PNNs, the number of clusters and fuzzification coefficient in FCM and polynomial type in RBFNNs. A multiobjective particle swarm optimization using crowding distance (MoPSO-CD) is exploited in order to carry out both structural and parametric optimization of the proposed networks. MoPSO is introduced for not only the performance of model but also complexity and interpretability. The usefulness of the proposed model as a classifier is evaluated with the aid of some benchmark datasets such as iris and liver.

• 한국멀티미디어학회논문지
• /
• 제19권9호
• /
• pp.1647-1658
• /
• 2016

RGB+D database has been widely used in object recognition, object tracking, robot control, to name a few. While rapid advance of active depth sensing technologies allows for the widespread of indoor RGB+D databases, there are only few outdoor RGB+D databases largely due to an inherent limitation of active depth cameras. In this paper, we propose a novel method used to build outdoor RGB+D databases. Instead of using active depth cameras such as Kinect or LIDAR, we acquire a pair of stereo image using high-resolution stereo camera and then obtain a depth map by applying stereo matching algorithm. To deal with estimation errors that inevitably exist in the depth map obtained from stereo matching methods, we develop an approach that estimates confidence of depth maps based on unsupervised learning. Unlike existing confidence estimation approaches, we explicitly consider a spatial correlation that may exist in the confidence map. Specifically, we focus on refining confidence feature with the assumption that the confidence feature and resultant confidence map are smoothly-varying in spatial domain and are highly correlated to each other. Experimental result shows that the proposed method outperforms existing confidence measure based approaches in various benchmark dataset.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.1-6
• /
• 2022

Exploration has always been an instinct of humans, and underwater life is as fascinating as it seems. So, for studying flora and fauna below water, there is a need for high-quality images. However, the underwater images tend to be of impaired quality due to various factors, which calls for improved and enhanced underwater images. There are various Histogram Equalization (HE) based techniques which could aid in solving these issues. Classifying the HE methods broadly, there is Global Histogram Equalization (GHE), Mean Brightness Preserving HE (MBPHE), Bin Modified HE (BMHE), and Local HE (LHE). Each of these HE extensions have their own pros and cons and thus, by considering them we have considered BBHE, CLAHE, BPDHE, BPDFHE, and DSIHE enhancement algorithms, which are based on Mean Brightness Preserving HE and Local HE, for this study. The performance is evaluated with non-reference performance measures like Entropy, UCIQE, UICM, and UIQM. In this study, we apply the enhancement algorithms on 300 images from the UIEB benchmark dataset and then apply the techniques of cascading fusion on the best-performing algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권4호
• /
• pp.1110-1127
• /
• 2022

To improve the training efficiency and generalization performance of a support vector machine (SVM) in a large-scale set, an optimal SVM learning method based on adaptive sparse sampling and the granularity shift factor is presented. The proposed method combines sampling optimization with learner optimization. First, an adaptive sparse sampling method based on the potential function density clustering is designed to adaptively obtain sparse sampling samples, which can achieve a reduction in the training sample set and effectively approximate the spatial structure distribution of the original sample set. A granularity shift factor method is then constructed to optimize the SVM decision hyperplane, which fully considers the neighborhood information of each granularity region in the sparse sampling set. Experiments on an artificial dataset and three benchmark datasets show that the proposed method can achieve a relatively higher training efficiency, as well as ensure a good generalization performance of the learner. Finally, the effectiveness of the proposed method is verified.