• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.9
• /
• pp.1531-1540
• /
• 2016

In this paper, we propose vehicle license plate recognition system based on Radial Basis Function Neural Networks (RBFNNs) with the use of local binarization functions and canny edge algorithm. In order to detect the area of license plate and also recognize license plate numbers, binary images are generated by using local binarization methods, which consider local brightness, and canny edge detection. The generated binary images provide information related to the size and the position of license plate. Additionally, image warping is used to compensate the distortion of images obtained from the side. After extracting license plate numbers, the dimensionality of number images is reduced through Principal Component Analysis (PCA) and is used as input variables to RBFNNs. Particle Swarm Optimization (PSO) algorithm is used to optimize a number of essential parameters needed to improve the accuracy of RBFNNs. Those optimized parameters include the number of clusters and the fuzzification coefficient used in the FCM algorithm, and the orders of polynomial of networks. Image data sets are obtained by changing the distance between stationary vehicle and camera and then used to evaluate the performance of the proposed system.

• Korean Journal of Soil Science and Fertilizer
• /
• v.50 no.4
• /
• pp.285-292
• /
• 2017

Antibiotics have been used for treating human and animal disease and enhancing growth of cattle, swine, and poultries. However, overused antibiotics can be released into the environment and produce antibiotic resistance genes (ARGs) in the environment. Main objective of this research was to monitor residual of antibiotics in solid matrix such as manure, wastewater sludge, soil and sediment. Total of six antibiotics, Chlortetracycline (CTC), Oxytetracycline (OTC), Tetracycline (TC), Sulfamethazine (SMT), Sulfamethoxazole (SMX), Sulfathiazole (STZ), used for both human and animal was monitored. Result showed that the detection frequency of 6 antibiotics was ordered SMT (100%) > TC = CTC (75%) > OTC (38%) > STZ (13%) > SMZ (0%) and the highest concentration ($309.83{\mu}g\;kg^{-1}$, SMT) was observed in manure. Comparing residual concentration of antibiotics (TC, CTC, and OTC) in soil and sediment, higher concentration was observed in sediment indicating that dissolved forms of antibiotics are released into river and sorbed into sediment particle. In conclusion, monitoring for residual of antibiotics in the environment is necessary and more research should be conducted to verify the source of antibiotic release.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.8
• /
• pp.818-822
• /
• 2008

The purpose of this study is to develop realistic painting simulation in real-time as well as to represent the thickness of the deposited paint on the surface. The Gaussian model is used for a painting deposition model to calculate the thickness of paints. For a painting simulation, rather than implementing particle systems, we propose a new heuristic algorithm for painting process based on a few number of rays. After we find the collision points of the rays with an environment, we compute the painted area using flood-fill searching method on the texture map and visualize paint effects. We analyzed time complexity of our method to verify that our system is suitable for real-time VR applications.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.3
• /
• pp.119-127
• /
• 2020

The detection and recognition of abnormal driving becomes crucial for achieving safety in Intelligent Transportation Systems (ITS). This paper presents a feature extraction method based on spectral data to train a neural network model for driving behavior recognition. The proposed method uses a two stage signal processing approach to derive time-saving and efficient feature vectors. For the first stage, the feature vector set is obtained by calculating variances from each frequency bin containing the power spectrum data. The feature set is further reduced in the second stage where an intersection method is used to select more significant features that are finally applied for training a neural network model. A stream of live signals are fed to the trained model which recognizes the abnormal driving behaviors. The driving behaviors considered in this study are weaving, sudden braking and normal driving. The effectiveness of the proposed method is demonstrated by comparing with existing methods, which are Particle Swarm Optimization (PSO) and Convolution Neural Network (CNN). The experiments show that the proposed approach achieves satisfactory results with less computational complexity.

• Bulletin of the Korean Chemical Society
• /
• v.31 no.8
• /
• pp.2235-2241
• /
• 2010

A reverse-phase HPLC method with detection by mass spectrometry is described for the simultaneous determination of doxifluridine and its two active metabolites, 5-fluorouracil (5-FU) and 5-fluorouridine (5-FUrd), in beagle dog plasma. The optimal chromatographic separation was achieved on a Waters $Xterra^{(R)}$ $C_{18}$ column ($4.6{\times}250\;mm$ i.d., $5\;{\mu}m$ particle size) with a mobile phase of 0.1% formic acid in a mixture of 99% methanol and purified water (99:1, v/v). The developed method was validated in beagle dog plasma with a lowest limit of quantification of $0.05\;{\mu}g/mL$ for both doxifluridine and 5-FU, and $0.2\;{\mu}g/mL$ for 5-FUrd. Doxifluridine and its two metabolites were stable under the analysis conditions, and intra- and inter-day accuracies exceeded 92.87%, with a precision variability ${\leq}11.34%$ for each analyte. Additionally, the method for quantifying doxifluridine and its two metabolites, 5-FU and 5-FUrd, in beagle dog plasma was applied successfully to the analysis of pharmacokinetic samples.

• 한국전기화학회:학술대회논문집
• /
• 2003.11a
• /
• pp.141-151
• /
• 2003

The electrochemical activity of the olivine type $LiMPO_4$ (M=transition metals) cathodes strongly depends on various factors, e.g., the transition metal element M, perturbative doping of the supervalent cations into Li site, composite formation with conductive additives, state of charge/discharge, and particle size and its geometries, etc. This is, therefore, an important issue of interdisciplinary between electrochemistry and solid state science towards practical applications. In order to shed light on this interesting but complicated issue with the transport properties and crystallographic aspects, systematic discussion will be made with the review of our recent publications; (1) first principle derivation of the electronic structures, (2) crystallographic mapping of the selected solid solutions, (3) quantitative elucidation of the electron-lattice interaction, (4) spectroscopic detection of the local environment with Mossbauer and EXAFS, (5) synthetic optimization of the electrode composite, and (6) electrochemical evaluation of the reaction kinetics, particularly on M = Fe, Mn.

• Korean Journal Plant Pathology
• /
• v.14 no.3
• /
• pp.229-239
• /
• 1998

Antibodies were raised against fusion proteins of the N-terminus and a region containing the GDNQ (Gly-Asp-Asn-Gln) polymerase motif of the L (polymerase) protein of sonchus yellow net virus (SYNV). Immunoblot analyses using these antibodies revealed the presence of the L protein in purified SYNV preparations and in nuclear extracts from infected tobacco. The serological analyses and detection in a polyacrylamide gels suggested that the L protein is present in at least a 20 fold lower abundance than the G, N, M1 and M2 proteins, and has size corresponding to a molecular weight of over 200 kDa as predicted from nucleotide sequence data. Electron microscopy with gold-labelled antibodies was used to localize the N, M2, and G proteins of SYNV in thin sections of infected tissue. When sections of SYNV-infected tissue were treated with antisera against total SYNV proteins and N protein, gold label could be detected in both the viroplasms and in virus particles. With the anti-M2 protein antiserum, the gold label was strongly localized in the viroplasms but only limited labelling of the virus particle sonly. Limited labelling of the L protein was observed in the viroplasms and the virus particles, presumably because of the low abundance of L protein in the tissues.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1345-1346
• /
• 2015

본 논문에서는 보행자 및 배경 이미지로부터 HOG-PCA 특징을 추출하고 다항식 기반 RBFNNs(Radial Basis Function Neural Network) 패턴분류기과 최적화 알고리즘을 이용하여 보행자를 검출하는 시스템 설계를 제안한다. 입력 영상으로부터 보행자를 검출하기 위해 전처리 과정에서 HOG(Histogram of oriented gradient) 알고리즘을 통해 특징을 추출한다. 추출된 특징은 고차원이므로 패턴분류기 분류 시 많은 연산과 처리속도가 따른다. 이를 개선하고자 PCA (Principal Components Analysis)을 사용하여 저차원으로의 차원 축소한다. 본 논문에서 제안하는 분류기는 pRBFNNs 패턴분류기의 효율적인 학습을 위해 최적화 알고리즘인 PSO(Particle Swarm Optimization)을 사용하여 구조 및 파라미터를 최적화시켜 모델의 성능을 향상시킨다. 사용된 데이터로는 보행자 검출에 널리 사용되는 INRIA2005_person data set에서 보행자와 배경 영상을 각각 1200장을 학습 데이터, 검증 데이터로 구성하여 분류기를 설계하고 테스트 이미지를 설계된 최적의 분류기를 이용하여 보행자를 검출하고 검출률을 확인한다.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.1
• /
• pp.43-48
• /
• 2020

At present, 24 nuclear power plants are in operation nationwide as the main power source responsible for about 27% of Korea's electricity, and five nuclear power plants are currently under construction. Issues of nuclear safety and reliability have always existed, but after the Fukushima accident, ensuring reliability has become an even more important issue for safety. Compared to other kinds of accidents, the initial response after a nuclear accident is more important than any other accident. Prior to accidents, it is important to be able to predict and judge the accident in advance for the sake of prevention. In this research, non-destructive inspection methods for existing pipe welds include radiographic, ultrasonic, magnetic particle practice, and liquid penetration testing. For this experiment, carbon steel pipes like that of the material used in nuclear pipes were adopted, and specimen welded to the flange (Flange) were manufactured. After testing, the weld specimen were not damaged through the infrared thermography (IRT) experiment. This study attempted to improve the safety of carbon steel pipes through a comparative analysis of finite element analysis.

• KSBB Journal
• /
• v.15 no.2
• /
• pp.214-218
• /
• 2000

A hepatitis B Surface Antigen(HBsAg)-screening kit using immunochromatographic assay(ICA) method was developed by e employing two kinds of antibodies. One is mouse monoclonal anti-HBs for tracer antibody and the other is goat p이yclonal a anti-HBs for capture antibody. This capture antibody was immobilized on the surface of nitroceliulose(NC) membrane and the t tracer antibody was conjugated with g미d particles. When serum sample was added to the sample well, the $\infty$njugates d deposited in a dry state on the surface of glass fiber filter were reconstituted and then combined with HBsAg in serum. In 5 5 min after adding, the assay result was visible through the window, that is, the complexes composed of HBsAg and the c conjugates appeared as maroon line on the lower part of the NC membrane. The detection limit of the ICA kit was 2 ng/ml w when being tested with the reference HBsAg.