• MALSORI
• /
• no.51
• /
• pp.99-115
• /
• 2004

In this parer, we propose LM adaptation for broadcast news recognition. We collect information of recent articles from the internet on real time, make a recent small size LM, and then interpolate recent LM with a existing LM composed of existing large broadcast news corpus. We performed interpolation experiments to get the best type of articles from recent corpus because collected recent corpus is composed of articles which are related with test set, and which are unrelated. When we made an adapted LM using recent LM with similar articles to test set through Tf-Idf method and existing LM, we got the best result that ERR of pseudo-morpheme based recognition performance has 17.2 % improvement and the number of OOV has reduction from 70 to 27.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.210-210
• /
• 2000

In this paper, we have investigated the properties of multi-layer perceptron (MLP) for odour patterns classification and concentration estimation simultaneously. When the MLP may be has a fast convergence speed with small error and excellent mapping ability for classification, it can be possible to use for classification and concentration prediction of volatile chemicals simultaneously. However, the conventional MLP, which is back-Propagation of error based on the steepest descent method, was difficult to use for odour classification and concentration estimation simultaneously, because it is slow to converge and may fall into the local minimum. We adapted the Levenberg-Marquardt(LM) algorithm [4,5] having advantages both the steepest descent method and Gauss-Newton method instead of the conventional steepest descent method for the simultaneous classification and concentration estimation of odours. And, We designed the artificial odour sensing system(Electronic Nose) and applied LM-BP algorithm for classification and concentration prediction of VOC gases.

• Journal of Environmental Impact Assessment
• /
• v.22 no.2
• /
• pp.125-134
• /
• 2013

Plant virus coat (CP) gene-mediated protection is one of the best known approaches to protect against virus resistant transgenic plants. Transgenic N. benthamiana plants containing the CP gene of Zucchini green mottle mosaic virus (ZGMMV) were used for the environmental risk assessment of the living modified (LM) plants with plant virus resistance. The most optimal co-infection method of both ZGMMV and CMV (Cucumber mosaic virus) on Non-LM and CP-expressing LM tobacco plants was established and co-infection of CMV and ZGMMV was confirmed by polymerase chain reaction (PCR). To address the effects of LM tobacco plants on the mutation of the virus, in-vitro transcripts of CP and Replicase (Rep) derived from CMV and/or ZGMMV were inoculated onto Non-LM or LM tobacco plants. Mutation frequency of CP and Rep from CMV and ZGMMV was examined through six serial passages in Non-LM and LM tobacco plants. Little actual frequency of mutation was estimated, probably due to the limited number of transgenic plants tested in this study. However, it does not suggest environmental safety of these CP-mediated LM plants. Further study at a larger scale is needed to evaluate the environmental risk associated with the CP-expressing LM plants.

• Journal of Microbiology and Biotechnology
• /
• v.21 no.12
• /
• pp.1336-1344
• /
• 2011

This study details and examines a novel ligation-mediated polymerase chain reaction (LM-PCR) method. Named the LM-PCR/Shifter, it relies on the use of a Class IIS restriction enzyme giving restriction fragments with different 4-base, 5' overhangs, this being the Shifter, and the ligation of appropriate oligonucleotide adapters. A sequence of 4-base, 5' overhangs of the adapter and a 4-base sequence of the 3' end of the primer(s) determine a subset of the genomic restriction fragments, which are amplified by PCR. The method permits the differentiation of bacterial species strains on the basis of the different DNA band patterns obtained after electrophoresis in polyacrylamide gels stained with ethidium bromide and visualized in UV light. The usefulness of the LM-PCR/Shifter method for genotyping is analyzed by a comparison with the restriction endonuclease analysis of chromosomal DNA by the pulsed-field gel electrophoresis (REA-PFGE) and PCR melting profile (PCR MP) methods for isolates of clinical origin. The clustering of the LM-PCR/Shifter fingerprinting data matched those of the REA-PFGE and PCR MP methods. We found that the LM-PCR/Shifter is rapid, and offers good discriminatory power and excellent reproducibility, making it a method that may be effectively applied in epidemiological studies.

• Korean Journal of Soil Science and Fertilizer
• /
• v.44 no.3
• /
• pp.353-360
• /
• 2011

In order to develop the application method of pig compost (PC) and liquid manure (LM) for whole crop barley cultivation, experiments were conducted at Munpo series (coarse loamy, mixed, nonacid, mesic family of Typic Fluvaquents) soil in Gyehwa-reclaimed land, six plots, a LM applied rate as N% ; non-application, chemical fertilizer (CF)100, 100, 50+50, 50+CF50 and (PC30+LM40)+LM50 as basal and additional fertilizer. $NO_3^-$-N content in soil was decreased as along with the growth of plant, highest in LM100% as basal fertilization at early growth stage and highest in (PC30%+LM40%)+LM40% and CF100% at last growth stage. Amount of $NO_3^-$-N and $NH_4^+$-N in soil was high in (PC30%+LM40%)+LM40% and CF100% of top soil but in subsoil significant difference was little in all treatment. Amount of OM, $A_V.P_2O_5$, T-N, exchangeable Ca and Na in soil was higher (PC30%+LM40%)+LM40% than non-application after harvest. Amount of nutrient uptake in plant was higher in CF100% and split application of LM than LM 100% application. Nitrogen utilization rate was in the order of CF100% >LM50%+LM50%=LM50%+CF50%>(PC30%+LM40%)+LM40% >LM100%. The yield of whole crop barley in (PC30%+LM40%)+LM40% and CF100% was 3.2 times more than in non-application ($309kg\;10a^{-1}$). Feed values such as crude protein and TDN was increased 1.0% ~ 1.4% in LM as split application than basal 100% treatment. Accordingly, in order to increase yield of a whole crop barley with application PC+LM in reclaimed land treat split application rather than to treat LM 100% into the land.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.55 no.2
• /
• pp.89-97
• /
• 2006

Interior permanent magnet synchronous motor(IPMSM) has become a popular choice in electric vehicle applications, due to their excellent power to weight ratio. The paper is proposed maximum torque control of IPMSM drive using learning mechanism-fuzzy neural network(LM-FNN) controller and artificial neural network(ANN). The control method is applicable over the entire speed range and considered the limits of the inverter's current and voltage rated value. For each control mode, a condition that determines the optimal d-axis current $i_{d}$ for maximum torque operation is derived. This paper considers the design and implementation of novel technique of high performance speed control for IPMSM using LM-FNN controller and ANN controller. The hybrid combination of neural network and fuzzy control will produce a powerful representation flexibility and numerical processing capability. Also, this paper is proposed speed control of IPMSM using LM-FNN and estimation of speed using ANN controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The proposed control algorithm is applied to IPMSM drive system controlled LM-FNN and ANN controller, the operating characteristics controlled by maximum torque control are examined in detail. Also, this paper is proposed the analysis results to verify the effectiveness of the LM-FNN and ANN controller.

• Journal of Plant Biotechnology
• /
• v.44 no.1
• /
• pp.97-106
• /
• 2017

Living modified crops are genetically modified living organisms and are widely used in biotechnical research and desired goods. As the reliance on LM products, concerns about safety of LMOs have been continuously increased in South Korea. We established the detection methods for unintentional released LMOs in environmental conditions. To detect six LM event genes of 1 canola, 1 maize and 4 soybeans, PCR conditions were based upon consideration of the Joint Research Centre information. Genomic DNAs were isolated from LM samples and PCR analysis were performed using each event-specific primer pair. Event-specific genes of all events were efficiently recognized by our methods. To investigate the insertion site of LM genes in each genome, we verified PCR product sequence by DNA sequencing. These results suggest that the LM event-specific gene amplification can be efficiently developed. In addition, our detection method is fit for monitoring and post-management of LM crops in the environment.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.191-201
• /
• 2005

In this paper, we propose a method to calculate camera motion parameter, which is based on efficient invariant features irrelevant to the camera veiwpoint. As feature information in previous research is variant to camera viewpoint. information content is increased, therefore, extraction of accurate features is difficult. LM(Levenberg-Marquardt) method for camera extrinsic parameter converges on the goat value exactly, but it has also drawback to take long time because of minimization process by small step size. Therefore, in this paper, we propose the extracting method of invariant features to camera viewpoint and two-stage calculation method of camera motion parameter which enhances accuracy and convergent degree by using camera motion parameter by 2D homography to the initial value of LM method. The proposed method are composed of features extraction stage, matching stage and calculation stage of motion parameter. In the experiments, we compare and analyse the proposed method with existing methods by using various indoor images to demonstrate the superiority of the proposed algorithm.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1302-1308
• /
• 2019

This paper presents an approach for classifying image made by acquired position data from a 2D Lidar sensor with a convolutional neural network (CNN). Lidar sensor has been widely used for unmanned devices owing to advantages in term of data accuracy, robustness against geometry distortion and light variations. A CNN algorithm consists of one or more convolutional and pooling layers and has shown a satisfactory performance for image classification. In this paper, different types of CNN architectures based on training methods, Gradient Descent(GD) and Levenberg-arquardt(LM), are implemented. The LM method has two types based on the frequency of approximating Hessian matrix, one of the factors to update training parameters. Simulation results of the LM algorithms show better classification performance of the image data than that of the GD algorithm. In addition, the LM algorithm with more frequent Hessian matrix approximation shows a smaller error than the other type of LM algorithm.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1011-1012
• /
• 2007

The paper is proposed maximum torque control of SynRM drive using learning mechanism-fuzzy neural network(LM-FNN) controlle. The control method is applicable over the entire speed range and considered the limits of the inverter's current and voltage rated value. For each control mode, a condition that determines the optimal d-axis current ${^{i}}_d$ for maximum torque operation is derived. The proposed control algorithm is applied to SynRM drive system controlled LM-FNN controller, the operating characteristics controlled by maximum torque control are examined in detail. Also, this paper is proposed the analysis results to verify the effectiveness of the LM-FNN controller.