• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.2
• /
• pp.398-405
• /
• 2006

We propose a pattern classification model using a selective perception ability of human beings. Generally, human beings recognize an object by putting a selective concentration on it in the region of interest. Much better classification and recognition could be possible by adapting this phenomenon in pattern classification. First, the pattern classification model creates some reference cluster patterns in a usual way. Then it generates an SPM(Selective Perception Map) that reflects the mutual relation of the reference cluster patterns. In the recognition phase, the model applies the SPM as a weight for calculating the distance between an input pattern and the reference patterns. Our experiments show that the proposed classifier with the SPM acquired the better results than other approaches in pattern classification.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.833-835
• /
• 2002

In this paper, we propose multi-resolutional representation of B-rep solid models using the selective Boolean operations on non-manifold geometric models. Since the union and subtraction operations of the selective Boolean operations are commutative, the integrity of the model is guaranteed for reordering design features. A multi-resolution representation is established using a non-manifold merged set model and a feature modeling tree reordered according to some criterion of level of detail (LOD). Then, a solid model for a specified LOD can be extracted from this multi-resolution model using the selective Boolean operations.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.123-136
• /
• 2005

We propose a recognition system for superimposed patterns based on selective attention model and SVM which produces better performance than artificial neural network. The proposed selective attention model includes attention layer prior to SVM which affects SVM's input parameters. It also behaves as selective filter. The philosophy behind selective attention model is to find the stopping criteria to stop training and also defines the confidence measure of the selective attention's outcome. Support vector represents the other surrounding sample vectors. The support vector closest to the initial input vector in consideration is chosen. Minimal euclidean distance between the modified input vector based on selective attention and the chosen support vector defines the stopping criteria. It is difficult to define the confidence measure of selective attention if we apply common selective attention model, A new way of doffing the confidence measure can be set under the constraint that each modified input pixel does not cross over the boundary of original input pixel, thus the range of applicable information get increased. This method uses the following information; the Euclidean distance between an input pattern and modified pattern, the output of SVM, the support vector output of hidden neuron that is the closest to the initial input pattern. For the recognition experiment, 45 different combinations of USPS digit data are used. Better recognition performance is seen when selective attention is applied along with SVM than SVM only. Also, the proposed selective attention shows better performance than common selective attention.

• Korean Journal of Computational Design and Engineering
• /
• v.5 no.4
• /
• pp.293-300
• /
• 2000

The non-manifold geometric modeling technique is to improve design process and to Integrate design, analysis, and manufacturing by handling mixture of wireframe model, surface model, and solid model in a single data structure. For the non-manifold geometric modeling, Euler operators and other high level modeling methods are necessary. Boolean operation is one of the representative modeling method for the non-manifold geometric modeling. This thesis studies Boolean operations of non-manifold model with the data structure of selective storage. The data structure of selective storage is improved non-manifold data structure in that existing non-manifold data structures using ordered topological representation method always store non-manifold information even if edges and vortices are in the manifold situation. To implement Boolean operations for non-manifold model, intersection algorithm for topological cells of three different dimensions, merging and selection algorithm for three dimensional model, and Open Inventor(tm), a 3D toolkit from SGI, are used.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.11a
• /
• pp.78-81
• /
• 2010

In this paper, we propose an efficient and effective selective protection scheme to SVC that exploit the propagation of protection effect by protecting significant frames that can give the maximum visual quality degradation. We model SVC dependency coding structure as a directed acyclic graph which is characterized with an estimated visual quality value as the attribute at each node. The estimated visual quality is calculated by using our model based on the proportions of intra- and inter-predicted MBs, amounts of residual, and estimated visual quality of reference frames. The proposed selective protection scheme traverses the graph to find optimal protection paths that can give maximum visual quality degradation. Experimental results show that the proposed selective protection scheme reduces the required number of frames to be protected by 46.02% compared to the whole protection scheme and 27.56% compared to the layered protection scheme.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.7A
• /
• pp.628-638
• /
• 2005

The analysis of maximum diversity order and coding gain for multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems over time-and frequency-selective (or doubly-selective) channels is addressed in this paper. A novel channel time-space correlation function is developed given the spatially correlated doubly-selective Rayleigh fading channel model. Based on this channel-model assumption, the upper-bound of pairwise error probability (PEP) for MIMO-OFDM systems is derived under the maximum likelihood (ML) detection. For a certain space-frequency code, we quantify the maximum diversity order and deduce the expression of coding gain. In this wort the impact of channel time selectivity is especially studied and a new definition of time diversity is illustrated correspondingly

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.29-37
• /
• 2021

In this paper, we propose a deep learning-based retinal vessel segmentation model for handling multi-scale information of fundus images. we integrate the selective kernel convolution into U-Net-based convolutional neural network. The proposed model extracts and segment features information with various shapes and sizes of retinal blood vessels, which is important information for diagnosing eye-related diseases from fundus images. The proposed model consists of standard convolutions and selective kernel convolutions. While the standard convolutional layer extracts information through the same size kernel size, The selective kernel convolution extracts information from branches with various kernel sizes and combines them by adaptively adjusting them through split-attention. To evaluate the performance of the proposed model, we used the DRIVE and CHASE DB1 datasets and the proposed model showed F1 score of 82.91% and 81.71% on both datasets respectively, confirming that the proposed model is effective in segmenting retinal blood vessels.

• Journal of Korean Society on Water Environment
• /
• v.23 no.2
• /
• pp.228-235
• /
• 2007

For efficient turbid water withdrawal in the Imha reservoir, a selective withdrawal facility was recently installed and operated during summer season of year 2006. In this research, CE-QUAL-W2 model was utilized to assess the efficiency of the selective withdrawal facility, in comparison with the original surface withdrawal, on turbid water management. Model calibration was carried out using data observed at four automatic monitoring stations in the reservoir. It was found that the model appropriately simulated, with the RMSE less than 5.2 NTU, the observed vertical and horizontal distributions of water temperature and turbidity as well as the location of maximum turbid water at each monitoring station. The analysis results showed that selective withdrawal is more effective in removing high turbid water than surface withdrawal as selective withdrawal contributed to reducing $35Mm^3$ of high turbidity water (> 100 NTU) in the reservoir by increasing outflows of high turbid water. Therefore, effective management of turbid water in the reservoir can be achieved by changing locations of intake depending on turbid water distribution conditions. The results of this study will provide some basic information for establishing better operation strategies to cope with turbid water problems.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.26 no.3
• /
• pp.53-63
• /
• 2001

An efficient mobility management for mobile stations plays an important role in mobile communication network. This paper studies the mobility management scheme that combines a distance-based registration(DBR) and a selective paging (SP). We introduce an analytical model based on 2-dimensional random walk mobility model and evaluate the performance of the proposed mobility management scheme using the model to determine the optimal size of location area that results in the minimum signaling traffic on radio channels. Numerical results are provided to demonstrate the performance of the proposed mobility management scheme under various circumstances. These results can be used effectively in design and evaluation of registration methods considering the system circumstances.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.28 no.3
• /
• pp.67-79
• /
• 2003

An efficient mobility management for mobile stations plays an important role in mobile communication networks. Even though many a mobility management schemes have been proposed, most of mobile communication networks adopt the mobility scheme based on zone-based registration. This paper studies the mobility management scheme that combines zone-based registration and 2-step selective paging. We assume cell by cell registration area, not ring by ring registration area of previous studies, and set up a new mobility model based on 2-dimensional random walk model considering the characteristic of zone-based registration to evaluate its performance exactly. We provide numerical results using proposed model to demonstrate the performance of zone-based registration and 2-step selective paging under various circumstances.