• 한국철도학회논문집
• /
• 제19권3호
• /
• pp.314-323
• /
• 2016

직류 전철변전소의 가선전압은 전동차들의 회생제동 및 역행가속패턴에 따라 급격히 상승 또는 하강하는 특성을 갖는다. 가선전압 순시 변동폭을 최소로 유지함으로써, 전철변전소와 전동차들의 에너지 효율을 개선시키기 위한 다양한 연구들이 이루어지고 있다. 본 논문은 직류전철 변전소의 가선전압의 급격한 변동특성을 모델링하고 선형인공 신경망 알고리즘을 이용한 가선전압 회로모델의 파라메터 추정 방법을 제안하며, 최소자승법을 이용한 추정방법과의 비교를 통해 이 방법의 타당성을 입증한다. 가선전압 및 피더전류들의 누적 측정값을 사용하여 일괄처리 최소자승법으로 RC 병렬회로의 파라메터들을 추정한 결과를 제시하며, 실시간 가선전압 및 피더전류 측정값을 이용하여 오차역 전파방식으로 학습되는 선형인공신경망 기법 추정 결과를 분석한다.

• Industrial Engineering and Management Systems
• /
• 제1권1호
• /
• pp.64-72
• /
• 2002

In the field of plant maintenance, data that are gathered by sensors on multiple machines are handled and analyzed. Online or pseudo online data handling is required on such fields. When the data occurrence speed exceeds the data handling speed, multiple data should be handled at a time (batch data handling or pseudo online data handling). If l amount of data are received at one time following N amount of data, how to estimate the new parameters effectively is a great concern. A new simplified calculation method, which calculates the N data's weights, is introduced. Numerical examples show that this new method has a fairly god estimation accuracy and the calculation time is less than 1/10 compared with the case when the whole data are re-calculated. Even under the restriction calculation ability in the apparatus is limited, this proposed method makes the failure detection of equipments possible in early stages with a few new coming data. This method would be applicable in many data handling fields.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권9호
• /
• pp.389-401
• /
• 2002

To complement the conventional fusion methodologies of state fusion and measurement fusion, a time-propagated measurement fusion methodology is proposed. Various aspects of common process noise are investigated regarding information preservation. Based on time-propagated measurement fusion methodology, four compression filters are derived. The derived compression filters are efficient in asynchronous sensor fusion and fault detection since they maintain correct statistical information. A new batch Kalman recursion is proposed to show the optimality under the time-propagated measurement fusion methodology. A simple simulation result evaluates estimation efficiency and characteristic.

• Communications for Statistical Applications and Methods
• /
• 제26권6호
• /
• pp.591-610
• /
• 2019

Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.

• 한국음향학회지
• /
• 제17권2호
• /
• pp.84-89
• /
• 1998

본 논문에서는 임의의 단어를 인식하기 위하여 음성학적으로 최적화된 (phonetically-optimized word) 음성 데이터베이스를 사용하여 훈련된 가변어휘 고립단위 음 성인식기의 실제 인식기 사용 환경에서의 성능을 평가하였다. 이를 위하여, 훈련 데이터베이 스에서와 상이한 환경에서 수집된 음성학적으로 균형 잡힌(phonetically-balanced word) 고 립 단어 음성을 테스트 데이터로 사용하였다. 테스트 데이터는 일반적인 사무실에서 작동하 는 노트북 PC에서 내장 마이크를 사용하여 녹음되었다. 이렇게 녹음된 음성을 사용하여 고 립단어 인식기의 인식률을 측정하였다. 이 인식기는 최대 사후(maximum a posteriori) 추정 알고리듬을 사용하여 화자의 변화에 적응하였다. 컴퓨터 모의실험 결과에 의하면 화자 적응 을 하지 않은 기본 시스템은 깨끗한 음성에 대하여 81.3%에서 사무실 환경 음성에 대하여 69.8%로 인식률이 저하되었다. 사무실 환경 음성에 대하여, 비교사 점진(unsupervised incremental) 모드에서 최대 사후 추정 화자 적응 알고리듬을 적용하였을 경우에는 화자적 응을 하지 않은 경우에 비하여 9%의 에러를 감소시키며, 50단어의 적응 단어를 사용하여 교사 묶음(supervised batch) 모드에서 최대 사후 추정 화자 적응 알고리듬을 적용하였을 경우에는 16%의 에러를 감소시켰다.

• 산업기술연구
• /
• 제16권
• /
• pp.51-60
• /
• 1996

This research was performed for the fundamental data using a advanced treatment process of piggery wastewater. Characteristics of influent wastewater was divided with various methods in fixed biofilm batch reasctor. Fractons of organic were divided into readily biodegradable soluble COD(Ss), slowly biodegradable COD(Xs), nonbiodegradable soluble COD($S_I$), and nonbiodegradable suspended COD($X_I$). Experimental results were summerized as following : i) biodegradable organics fraction in piggery wastewater was about 88.1 percent, and fraction of readily biodegradable soluble COD was about 66.1 percent. ii) Fractions of nonbiodegradable soluble COD was 11~12 percent, and soluble inert COD by metabolism was producted about 6~8 percent. iii) Active biomass fraction of attached biofilm was about 54.7 percent, and substrate utilization rate and maximum specific growth rate of heterotrophs were $8.315d^{-1}$ and $3.823d^{-1}$, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.779-782
• /
• 1990

Recently batch type cold rolling processes have been replaced by continuous annealing type processes for cold rolled sheets of mild steel and high strength steel in order to obtain higher productivity, labor saving. In the continuous annealing line, it is very important to maintain the target steel strip temperature at the exit side of each furnace. The automation system of continuous annealing line is based on a hierachical composition. This paper shows how to preset the set value of furnace temperature control for the heating section in a continuous annealing line. Saying in other words, this paper presents the development of an adaptive control approach to control the exit strip temperature in the continuous annealing line. There are three parts in this approach; one is a process modelling and another is recursive parameter estimation and the other is a design of temperature controller.

• Genomics & Informatics
• /
• 제9권4호
• /
• pp.189-193
• /
• 2011

Simple sequence repeats (SSRs) are ubiquitous short tandem duplications found within eukaryotic genomes. Their length variability and abundance throughout the genome has led them to be widely used as molecular markers for crop-breeding programs, facilitating the use of marker-assisted selection as well as estimation of genetic population structure. Here, we report a software application, "SSR-Primer Generator " for SSR discovery, SSR-primer design, and homology-based search of in silico amplicons from a DNA sequence dataset. On submission of multiple FASTA-format DNA sequences, those analyses are batch processed in a Java runtime environment (JRE) platform, in a pipeline, and the resulting data are visualized in HTML tabular format. This application will be a useful tool for reducing the time and costs associated with the development and application of SSR markers.

• International Journal of Railway
• /
• 제6권2호
• /
• pp.45-52
• /
• 2013

Railway construction needs vast soil investigation for its infrastructure foundation designs along the planned railway path to identify the design parameters for stability and serviceability checks. The soil investigation data are usually classified and grouped to decide design input parameters per each construction section and budget estimates. Deterministic design method which most civil engineer and practitioner are familiar with has a clear limitation in construction/maintenance budget control, and occasionally produced overdesigned or unsafe design problems. Instead of using a batch type analysis with predetermined input parameters, data population collected from site soil investigation and design load condition can be statistically estimated for the mean and variance to present the feature of data distribution and optimized with a best fitting probability function. Probabilistic approach using entire feature of design input data enables to predict the worst, best and most probable cases based on identified ranges of soil and load data, which will help railway designer select construction method to save the time and cost. This paper introduces two Monte Carlo simulations actually applied on estimation of retaining wall external stability and long term settlement of organic soil in soil investigation area for a recent high speed railway project.

• 한국환경과학회지
• /
• 제28권10호
• /
• pp.899-905
• /
• 2019

Recently, an innovative method for wastewater treatment and nutrient removal was developed by combining the sequence batch reactor and membrane bioreactor to overcome pollution caused by shipboard sewage. This system is a modified form of the activated sludge process and involves repeated cycles of mixing and aeration. In the present study, the bacterial diversity and dominant microbial community in this wastewater treatment system were studied using the MACROGEN next generation sequencing technique. A high diversity of bacteria was observed in anaerobic and aerobic bioreactors, with approximately 486 species. Microbial diversity and the presence of beneficial species are crucial for an effective biological shipboard wastewater treatment system. The Arcobacter genus was dominant in the anaerobic tank, which mainly contained Arcobacter lanthieri (8.24%), followed by Acinetobacter jahnsonii (5.81%). However, the dominant bacterial species in the aerobic bioreactor were Terrimonas lutea (7.24%) and Rubrivivax gelatinosus (4.95%).