• ETRI Journal
• /
• v.33 no.2
• /
• pp.259-266
• /
• 2011

We present a new method for an automated markerless system to describe, analyze, and classify human gait motion. The automated system consists of three stages: I) detection and extraction of the moving human body and its contour from image sequences, ii) extraction of gait figures by the joint angles and body points, and iii) analysis of motion parameters and feature extraction for classifying human gait. A sequential set of 2D stick figures is used to represent the human gait motion, and the features based on motion parameters are determined from the sequence of extracted gait figures. Then, a k-nearest neighbor classifier is used to classify the gait patterns. In experiments, this provides an alternative estimate of biomechanical parameters on a large population of subjects, suggesting that the estimate of variance by marker-based techniques appeared generous. This is a very effective and well-defined representation method for analyzing the gait motion. As such, the markerless approach confirms uniqueness of the gait as earlier studies and encourages further development along these lines.

• Journal of the Korean Society for Railway
• /
• v.10 no.3 s.40
• /
• pp.313-318
• /
• 2007

In this study, numerical simulations were carried out to analyze the effect of the smoke extraction system and fire shutters in subway station fires using FDS 4.0. Subway station used in the experiment was 145 m long. Simulation results are validated by comparing with experimental results. Simulation results showed good agreement with experimental results within $10^{\circ}C$. 10 MW polystyrene was used as a fuel in the numerical prediction. Numerical predictions were performed in the center-platform type subway station in case of a kiosk fire. Temperature and CO concentration were lowered by the operation of smoke extraction system. But, the operation of fire shutters had little effect on temperature and CO concentration in the platform level.

• Mass Spectrometry Letters
• /
• v.12 no.4
• /
• pp.186-191
• /
• 2021

A new method for chemical separation of light rare-earth elements (LREEs) using gas-pressurized extraction chromatography (GPEC) is described. GPEC is a microscale column chromatography system that features a constant flow of solvents, which is created by pressurized nitrogen gas. The separation column with a Teflon tubing was packed with LN resin. The proposed GPEC method facilitates production of lesser chemical wastes and faster separation owing to the use of low solvent volume compared to traditional column chromatography. We evaluated the separation of Ba, La, Ce, and Nd using various elution solvents. The column reproducibility of the proposed GPEC system ranged from 2.4% to 4.9% with RSDs of recoveries, and the column-to-column reproducibility ranged from 3.1% to 6.3% with RSDs of recoveries. The proposed technique is robust, and it can be useful for the fast separation of LREEs.

• Journal of Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1042-1045
• /
• 2003

In this paper, we propose the speaker identification system that uses vowel that has speaker's characteristic. System is divided to speech feature extraction part and speaker identification part. Speech feature extraction part extracts speaker's feature. Voiced speech has the characteristic that divides speakers. For vowel extraction, formants are used in voiced speech through frequency analysis. Vowel-a that different formants is extracted in text. Pitch, formant, intensity, log area ratio, LP coefficients, cepstral coefficients are used by method to draw characteristic. The cpestral coefficients that show the best performance in speaker identification among several methods are used. Speaker identification part distinguishes speaker using Neural Network. 12 order cepstral coefficients are used learning input data. Neural Network's structure is MLP and learning algorithm is BP (Backpropagation). Hidden nodes and output nodes are incremented. The nodes in the incremental learning neural network are interconnected via weighted links and each node in a layer is generally connected to each node in the succeeding layer leaving the output node to provide output for the network. Though the vowel extract and incremental learning, the proposed system uses low learning data and reduces learning time and improves identification rate.

• The KIPS Transactions:PartD
• /
• v.18D no.1
• /
• pp.45-56
• /
• 2011

The importance of low-power embedded system is being increased. The studies on low-power system have been performed in issues of hardware architecture and operating system. However because the behaviors of software control the working of hardware devices, the power analysis of software is one of critical issues in energy-efficient embedded system development. This paper proposes a technique to extract tasks from software design models with considering power consumption. We first define the criteria for task extraction, and then propose the way to separate out the task from UML 2.0 design models. Our technique can provide the chance to reduce the power consumption as well as to fulfill the performance requirement in the early phase of software development.

• Journal of the Optical Society of Korea
• /
• v.20 no.3
• /
• pp.381-388
• /
• 2016

The performance of a staring infrared imaging system can be characterized based on estimating the modulation transfer function (MTF). The slant edge method is a widely used MTF estimation method, which can effectively solve the aliasing problem caused by the discrete undersampling of the infrared focal plane array. However, the traditional slant edge method has some limitations such as the low precision of the edge angle extraction and using the approximate function to fit the edge spread function (ESF), which affects the accuracy of the MTF estimation. In this paper, we propose a modified slant edge method, including an edge angle extraction method that can improve the precision of the edge angle extraction and an ESF fitting algorithm which is based on the transfer function model of the imaging system, to enhance the accuracy of the MTF estimation. This modified slant edge method presents higher estimation accuracy and better immunity to noise and edge angle than other traditional methods, which is demonstrated by the simulation and application experiments operated in our study.

• Science of Emotion and Sensibility
• /
• v.7 no.2
• /
• pp.133-140
• /
• 2004

A large number of indices are produced from human sensibility ergonomic data, which are accumulated by the project "Study on the Development of Web-Based Database System of Human Sensibility and its Support". Since the research in this field will be increased rapidly, it is necessary to automate the index processing of human sensibility ergonomic data. From the similarity between indexation and summarization, we propose the automation of this process. In this paper, we study on extraction of keywords, information types and expression features that are considered as basic elements of following techniques for automatic summarization: classification of documents, extraction of information types and linguistic features. This study can be applied to automatic summarization system and knowledge management system in the domain of human sensibility ergonomics.rgonomics.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.10
• /
• pp.1787-1793
• /
• 2008

Fingerprint Recognition System is made up of Off-line treatment and On-line treatment; the one is registering all the information of there trieving features which are retrieved in the digitalized fingerprint getting out of the analog fingerprint through the fingerprint acquisition device and the other is the treatment making the decision whether the users are approved to be accessed to the system or not with matching them with the fingerprint features which are retrieved and database from the input fingerprint when the users are approaching the system to use. In this paper, we propose a new data structure, called Union and Division, for processing binarized digital fingerprint image efficiently. We present a minutiae extraction algorithm that is using Union and Division and consists of binarization, noise removal, minutiae extraction stages.

• Membrane and Water Treatment
• /
• v.4 no.1
• /
• pp.11-25
• /
• 2013

Emulsion liquid membrane (ELM) process suffers from emulsion instability problem. So far, emulsion produced by mechanical methods such as stirrer and homogenizer has big size and high emulsion breakage. This paper discussed the application of emulsion produced by sonicator to extract cadmium in a batch ELM system. The emulsions consist of N,N-Dioctyl-1-octanamine (trioctylamine/TOA), nitrogen trihydride (ammonia/NH4OH), sorbitan monooleate (Span 80), and kerosene as carrier, stripping solution, emulsifying agent, and organic diluent, respectively. Effects of comprehensive parameters on extraction efficiency of Cd(II) such as emulsification time, extraction time, stirring speed, surfactant concentration, initial feed phase concentration, carrier concentration, volume ratio of the emulsion to feed phase, and pH of initial feed phase were evaluated. The results showed that extraction efficiencies of Cd(II) greater than 98% could be obtained under the following conditions: 15 minutes of emulsification time, 4 wt.% of Span 80 concentration, 4 wt.% of TOA concentration, 15 minutes of extraction time, 250 rpm of stirring speed, 100 ppm of initial feed concentration, volume ratio of emulsion to feed phase of 1:5, and initial feed pH of 1.53.