• Journal of Internet Computing and Services
• /
• v.15 no.6
• /
• pp.117-124
• /
• 2014

Cluttered background is a major obstacle in developing salient object detection and tracking system for mobile device captured natural scene video frames. In this paper we propose a context aware feature vector selection model to provide an efficient noise filtering by machine learning based classifiers. Since the context awareness for feature selection is achieved by searching nearest neighborhoods, known as NP hard problem, we apply a fast approximation method with complexity analysis in details. Separability enhancement in feature vector space by adding the context aware feature subsets is studied rigorously using principal component analysis (PCA). Overall performance enhancement is quantified by the statistical measures in terms of the various machine learning models including MLP, SVM, Naïve Bayesian, CART. Summary of computational costs and performance enhancement is also presented.

• Atmosphere
• /
• v.24 no.4
• /
• pp.491-502
• /
• 2014

As a part of the KIAPS (Korea Institute of Atmospheric Prediction Systems) Package for Observation Processing (KPOP), we have developed the modules for Advanced Microwave Sounding Unit-A (AMSU-A) pre-processing and its bias correction. The KPOP system calculates the airmass bias correction coefficients via the method of multiple linear regression in which the scan-corrected innovation and the thicknesses of 850~300, 200~50, 50~5, and 10~1 hPa are respectively used for dependent and independent variables. Among the four airmass predictors, the multicollinearity has been shown by the Variance Inflation Factor (VIF) that quantifies the severity of multicollinearity in a least square regression. To resolve the multicollinearity, we adopted simple linear regression and Principal Component Regression (PCR) to calculate the airmass bias correction coefficients and compared the results with those from the multiple linear regression. The analysis shows that the order of performances is multiple linear, principal component, and simple linear regressions. For bias correction for the AMSU-A channel 4 which is the most sensitive to the lower troposphere, the multiple linear regression with all four airmass predictors is superior to the simple linear regression with one airmass predictor of 850~300 hPa. The results of PCR with 95% accumulated variances accounted for eigenvalues showed the similar results of the multiple linear regression.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2060-2071
• /
• 1999

The complicate software failure system is defined to the superposition of the points of failure from several component point process. Because the likelihood function is difficulty in computing, we consider Gibbs sampler using iteration sampling based method. For each observed failure epoch, we applied to latent variables that indicates with component of the superposition mode. For model selection, we explored the posterior Bayesian criterion and the sum of relative errors for the comparison simple pattern with superposition model. A numerical example with NHPP simulated data set applies the thinning method proposed by Lewis and Shedler[25] is given, we consider Goel-Okumoto model and Weibull model with GOS, inference of parameter is studied. Using the posterior Bayesian criterion and the sum of relative errors, as we would expect, the superposition model is best on model under diffuse priors.

• Journal of Energy Engineering
• /
• v.6 no.1
• /
• pp.41-51
• /
• 1997

A dynamic mathematical model of a thermal power plant with a single drum-type boiler is described with the base on modular concept. The present process model, which is including full scope of the components and high load changes, is based on physical approach through lumped parameters. The module, which means a component of the power plant and must essentially depict the characteristics of the component well, might be interconnected using pressure nodal method in a arrangement determined by users. With the results of the load changes of 75 MW to 95 MW and 95MW to 75 MW with the rate of 3 MW/min, the applicability of the process model is examined connecting to DCS(Dispersion Control System), which has a real running logic of 100 MW real power plant.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.2
• /
• pp.239-245
• /
• 2020

Recently, BIM (Building Information Modeling) are widely being utilized in Construction industry. However, most structures that have been constructed in the past do not have BIM. For structures without BIM, the use of SfM (Structure from Motion) techniques in the 2D image obtained from the camera allows the generation of 3D model point cloud data and BIM to be established. However, since these generated point cloud data do not contain semantic information, it is necessary to manually classify what elements of the structure. Therefore, in this study, deep learning was applied to automate the process of classifying structural components. In the establishment of deep learning network, Inception-ResNet-v2 of CNN (Convolutional Neural Network) structure was used, and the components of bridge structure were learned through transfer learning. As a result of classifying components using the data collected to verify the developed system, the components of the bridge were classified with an accuracy of 96.13 %.

• Korean Journal of Environment and Ecology
• /
• v.25 no.3
• /
• pp.365-377
• /
• 2011

This study aims at classifying and interpreting on the second forest vegetation located in Mt. Duryun affiliated to the ecotone in southern part of Korea, and foreseeing vegetation change based on component species and dominant species on canopy. The second forest vegetation is classified into 3 community units as Quercus serrata-Quercus variabilis community, Dendropanax morbiferus-Quercus acuta community and Chamaecyparis obtusa plantation. This research is also expatiated on the relationship between the distribution of communities and the environmental conditions. Quercus serrata-Quercus variabilis community will be succession horizontally and gradually from the part where Quercus variabilis is dominated relatively at first to the other part in the community, according to the component species of deciduous broad-leaved forest in the warm-temperate zone and evergreen broad-leaved forest as Camellietea japonicae.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.23 no.11
• /
• pp.1288-1296
• /
• 2012

A candidate hybrid satellite and terrestrial network architecture, MSS/ATC(Mobile Satellite Service/Ancillary Terrestrial Component), is proposed for utilizing efficiently the exist MSS bands. Studies on the adjacent channel interference from the existing terrestrial mobile services and MSS/ATC itself are important to allocate a new ATC service frequency in MSS band. In this paper, we have analyzed the minimum permission power of terrestrial base station and the capacity loss with parameters of ACIR, number of MS(mobile Station) and MES(Mobile Earth Station) in uplink, and also, the capacity performance based on 1 beam and 1 cell assumption for MSS/ATC in downlink. The ACIR requirements are estimated in two MSS/ATC frequency allocation scenarios for 5 MHz and 10 MHz guard band to share spectrum with adjacent systems, and according to these ACIR requirements the service coverage and the receiver filter for ATC system should be designed in near future.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.10 no.3
• /
• pp.221-228
• /
• 2016

In this paper, we introduce our simulation software for EEG signal accuracy improvement. Users can check and train own EEG signal accuracy using our simulation software. Subjects were shown emotional imagination condition with landscape photography and logical imagination condition with a mathematical problem to subject. We use that EEG signal data, and apply Independent Component Analysis algorithm for noise removal. So we can have beta waves(${\beta}$, 14-30Hz) data through Band Pass Filter. We extract feature using Root Mean Square algorithm and That features are classified through Support Vector Machine. The classification result is 78.21% before EEG signal accuracy improvement training. but after successive training, the result is 91.67%. So user can improve own EEG signal accuracy using our simulation software. And we are expecting efficient use of BCI system based EEG signal.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.809-826
• /
• 2018

The entropy evaluation method for noise sources is one of the evaluation methods for the random number generator that is the essential element of modern cryptographic systems and cryptographic modules. The primary entropy evaluation methods outside of the country are more suitable to apply to hardware noise sources than software noise sources, and there is a difficulty in quantitative evaluation of entropy by software noise source. In this paper, we propose an entropy evaluation method that is suitable for software noise sources, considering characteristics of software noise sources. We select time-dependent noise sources that are software noise sources of Windows OS, and the heuristic analysis and experimental analysis are performed considering the characteristics of each time-dependent noise source. Based on these analyses, we propose an entropy harvest method from the noise source and the min-entropy estimation method as the entropy evaluation method for time-dependent noise sources. We also show how to use our entropy evaluation method in the Conditioning Component described in SP 800-90B of NIST(USA).

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.149-158
• /
• 2004

This study proposes a method for segmentation and recognition of traffic signs using shape information and edge image in real image. It first segments traffic sign candidate regions by connected component algorithm from binary images, obtained by utilizing the RGB color ratio of each pixel in the image, and then extracts actual traffic signs based on their symmetries on X- and Y-axes. Histogram equalization is performed for unsegmented candidate regions caused by low contrast in the image. In the recognition stage, it utilizes shape information including projection profiles on X- and Y-axes, moment, and the number of crossings and distance which concentric circular patterns and 8-directional rays from region center intersects with edges of traffic signs. It finally performs recognition by measuring similarity with the templates in the database. It will be shown from several experimental results that the system is robust to environmental factors, such as light and weather condition.