• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.3
• /
• pp.1390-1403
• /
• 2016

Facial expression recognition (FER) plays a very significant role in computer vision, pattern recognition, and image processing applications such as human computer interaction as it provides sufficient information about emotions of people. For video-based facial expression recognition, depth cameras can be better candidates over RGB cameras as a person's face cannot be easily recognized from distance-based depth videos hence depth cameras also resolve some privacy issues that can arise using RGB faces. A good FER system is very much reliant on the extraction of robust features as well as recognition engine. In this work, an efficient novel approach is proposed to recognize some facial expressions from time-sequential depth videos. First of all, efficient Local Binary Pattern (LBP) features are obtained from the time-sequential depth faces that are further classified by Generalized Discriminant Analysis (GDA) to make the features more robust and finally, the LBP-GDA features are fed into Hidden Markov Models (HMMs) to train and recognize different facial expressions successfully. The depth information-based proposed facial expression recognition approach is compared to the conventional approaches such as Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Linear Discriminant Analysis (LDA) where the proposed one outperforms others by obtaining better recognition rates.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.11a
• /
• pp.479-484
• /
• 2002

In this paper consisted of three steps for the research The first, The Database of Biological Resource Information are constructing for species Information and Content Information of based XML. The second, The item of defined from the analysts and must be considered for national GSD(Global Species Database), Supply and Contracture of Input System of based Component for the Efficient Local Information Database. The third Information Service and Interoperability are using the GRM(Global Road Map) of based DADI. These are able to accomplish to Contracture for Database and Service structure of Biological Resources Information.

• ETRI Journal
• /
• v.37 no.3
• /
• pp.541-550
• /
• 2015

In this paper, we propose a classification-based approach for hybridizing statistical machine translation and rulebased machine translation. Both the training dataset used in the learning of our proposed classifier and our feature extraction method affect the hybridization quality. To create one such training dataset, a previous approach used auto-evaluation metrics to determine from a set of component machine translation (MT) systems which gave the more accurate translation (by a comparative method). Once this had been determined, the most accurate translation was then labelled in such a way so as to indicate the MT system from which it came. In this previous approach, when the metric evaluation scores were low, there existed a high level of uncertainty as to which of the component MT systems was actually producing the better translation. To relax such uncertainty or error in classification, we propose an alternative approach to such labeling; that is, a cut-off method. In our experiments, using the aforementioned cut-off method in our proposed classifier, we managed to achieve a translation accuracy of 81.5% - a 5.0% improvement over existing methods.

• Proceedings of the KIPE Conference
• /
• 2008.10a
• /
• pp.124-126
• /
• 2008

Grid Connected inverter is produced current to deliver power to grid. To provide low THD current, LCL filters is effective to filter high frequency component of current output from inverter. To provide sinusoidal waveform, there are many researchers have been proposed several controllers for grid-connected inverter controllers. Synchronous Reference Frame (SRF)-based controller is the most popular methods. SRF-based controller is capable for reducing both of zero-steady state error and phase delay. But SRF based controller is contained cross-coupling components, which generate some difficulties to analyze. In this paper, SRF based controller is analyzed. By applying decoupling control, cross-coupling component is eliminated and single phase model of the system is obtained. Through this single phase model, gain controller is designed. To reduce steady state error, proportional gain is set as high as possible, but it may produce instability. To compromise between a minimum steady state error and stability, the single phase model is evaluate through Root Locus and Bode diagram. PSIM simulation is used to verify the analysis.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.6
• /
• pp.875-882
• /
• 2010

Nowadays, the global market requires a variety of products and shorter life cycle to fulfill the diverse demands of customers. To survive in the turbulent and competitive markets, automobile assembly companies must design and implement manufacturing systems that respond rapidly to market demands. In this paper, methods for reconfiguring system based on modular concept is proposed using AR(Augmented reality) technologies. First, the relationship matrixes between change drivers and system components are generated to divide existing manufacturing system to each module. And, new change drivers are selected based on required function in new system. Through the modification of relationship matrix, the concept design of new system is proposed and implemented in AR environment. Finally, according to proposed methods and procedure in this paper, the existing cockpit assembly system is reconfigured to spare tire assembly system as a case study. As the use of the modular-based reconfiguration method in AR environment, the time and cost for reconfiguring manufacturing system will be reduced dramatically.

• Korean Chemical Engineering Research
• /
• v.58 no.3
• /
• pp.381-389
• /
• 2020

This study analyzed the optimal electricity cost of a 100% renewable energy source (RES) based system. Especially energy storage system (EES) and supplementary biopower system as well as photovoltaic (PV) and wind power component were included in the proposed RES-based system to overcome the intermittence of RESs and to efficiently balance energy supply and demand. To comparatively analyze the levelized cost of electricity (LCOE) of different RES-based systems, six scenarios were developed according to the involved RESs: PV, wind, PV/wind, PV/biopower, wind/biopower, and PV/wind/biopower systems. We then applied the proposed systems to build a 100% RES-based system in Jeju Island, Korea. As a result, the single component based system, PV and wind power system of 0.18 and 0.28 $/kWh, respectively, cannot compete with the economics of existing electricity grid. However, the optimal LCOE of the hybrid system where PV and wind power are used as main supply options and biopower as supplementary option was identified to be 0.08 $/kWh, which can compete with the economics of an existing electricity grid.

• Journal of the Korean Electrochemical Society
• /
• v.7 no.4
• /
• pp.206-210
• /
• 2004

All array of carbon paste-based electrodes was prepared by screen printing the carbon paste modified with metal oxides $(TiO_2,\;RuO_2,\;PbO_2,\;Ni(OH)_2)$ and Prussian blue (PB). An electronic tongue system was assembled with the carbon-paste electrode array, and applied to discriminate the tastes of various commercial beverages and foods by measuring the chronoamperometric responses to the samples diluted in 0.1M carbonate buffer (pH 9.6). The results were analyzed with principal component analysis(PCA) method and plotted on two dimensional PCA coordinate; it was apparent that the amperometric electronic tongue system could discriminate the types of various foods and beverages.

• Spatial Information Research
• /
• v.15 no.3
• /
• pp.301-310
• /
• 2007

There are 21,000 National Surveying Control Points (NSCP) made of stone for precise surveying nationwide. NSCPs that provide location information are usually buried at the top of a mountain for view points that cannot be used by the public. Recently, according to the growing ubiquitous computing generation, location-based information has become very important and a service that can be easily accessed by the public is needed. In this research, a new type of reference point for a location information service is proposed. It is an Intelligent Reference Point (IRP) equipped with RFID tags and a two-dimensional bar-code system. The IRP system is composed of an electronic tag component, a tag identification component, and an IRP service component. We designed the IRP receiver identifying RFID tag and two-dimensional barcode was designed using a PDA, digital camera, and an RFID receiver. Also designed was IRP input data and input information. Furthermore, the operation software was developed in a PDA for identifying IRP and using IRP the service, and the IRP positioning method was developed using a GIS spatial analysis.

• The KIPS Transactions:PartD
• /
• v.9D no.1
• /
• pp.75-80
• /
• 2002

Putnam develops SLIM (Software LIfecycle Management) model based upon the assumption that the manpower utilization during software project development is followed by a Rayleigh distribution. To obtain the manpower distribution, we have to be estimate the total development effort and difficulty ratio parameter. We need a way to accurately estimate these parameters early in the requirements and specification phase before investment decisions have to be made. Statistical tests show that system attributes are highly correlation (redundant) so that Putnam discards one and get a parameter estimator from the other attributes. But, different statistical method has different system attributes and presents different performance. To select the principle system attributes, this paper uses the principle component analysis (PCA) instead of Putnam's method. The PCA's results improve a 9.85 percent performance more than the Putnam's result. Also, this model seems to be simple and easily realize.

• Journal of the Korea Society for Simulation
• /
• v.26 no.3
• /
• pp.23-34
• /
• 2017

This paper is to study the simulation model of depot maintenance system that analyzes logistics supportability such as component availability and cost of target equipment. A depot maintenance system could repair or maintain multiple components simultaneously. The key performance indicators of this system are component availability, repair cycle time, and maintenance cost. The simulation model is based on the engine maintenance process of army aviation depot. This study combines the NOLH(Nearly Orthogonal Latin Hypercube) experimental design method, to composes 33 scenarios, with a multiple regression analysis to find out major factors that influence on key performance indicators. This study is significant in providing a cost-effectiveness analysis on depot maintenance system that is capable of maintaining multiple components at the same time.