• KEPCO Journal on Electric Power and Energy
• /
• 제5권3호
• /
• pp.173-179
• /
• 2019

심랭식 공기분리공정은 공기를 액화시켜 질소와 산소, 아르곤 등 다양한 산업가스를 생산하며, 가스생산조건(순도, 종류)에 따라 공정 또한 달라진다. 그 중 SNG 플랜트 공급용 공기분리공정은 99.5% 이상의 초고순도 산소 생산을 요구하기 때문에 공정의 효율이 타 공기분리공정에 비해 떨어지며, 공정효율을 낮추는 요인에는 공기압축에 의한 소모동력이 대표적이다. 본 연구에서는 SNG 플랜트에 적용하는 공기분리공정의 에너지 효율 향상을 위하여 소모동력과 관련된 공기 압축 설비의 민감도 분석을 수행하였다. 민감도 분석을 위해 ASPEN PLUS를 이용해 공기분리공정을 모사하였다. 모사 결과, 99.5% 이상의 산소 18.21 kg/s를 생산하였으며, 33.26 MW의 동력이 소모되었다. 모사된 공정 중 공기압축설비는 주 압축기 1대와 2대의 재 압축기가 있으며, 2대의 재압축기에서의 공기압축비 변화에 따른 고압질소, 저압산소, 저압질소의 유량과 순도에 대한 영향과 공정 내 소모동력 변화에 대해 분석하였다. 분석 결과, 99.5% 산소, 99% 질소(고압), 90% 질소(저압)를 생산하기 위한 최적의 운전조건은 재압축비가 각각 0.48, 0.50가 되었으며, 재압축비 조정 후 $0.507kWh/O_2kg$에서 $0.473kWh/O_2kg$으로 소모동력도 약 7%가량 줄었음을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.647-650
• /
• 2005

In this paper, a low voltage SRAM using double boosting scheme is described. A low supply voltage deteriorates the static noise margin (SNM) and the cell read-out current. For read/write operation, a selected word line and cell VDD bias are boosted in a different level using double boosting scheme. This increases not only the static noise margin but also the cell readout current at a low supply voltage. A low voltage SRAM with 32K ${\times}$ 8bit implemented in a 0.18um CMOS technology shows an access time of 26.1ns at 0.8V supply voltage.

• ETRI Journal
• /
• 제32권5호
• /
• pp.766-773
• /
• 2010

Support vector machine (SVM) active learning plays a key role in the interactive content-based image retrieval (CBIR) community. However, the regular SVM active learning is challenged by what we call "the small example problem" and "the asymmetric distribution problem." This paper attempts to integrate the merits of semi-supervised learning, ensemble learning, and active learning into the interactive CBIR. Concretely, unlabeled images are exploited to facilitate boosting by helping augment the diversity among base SVM classifiers, and then the learned ensemble model is used to identify the most informative images for active learning. In particular, a bias-weighting mechanism is developed to guide the ensemble model to pay more attention on positive images than negative images. Experiments on 5000 Corel images show that the proposed method yields better retrieval performance by an amount of 0.16 in mean average precision compared to regular SVM active learning, which is more effective than some existing improved variants of SVM active learning.

• The Journal of the Acoustical Society of Korea
• /
• 제22권3E호
• /
• pp.124-132
• /
• 2003

We propose a new method for speech/non-speech classifiers based on concepts of the adaptive boosting (AdaBoost) algorithm in order to detect speech for robust speech recognition. The method uses a combination of simple base classifiers through the AdaBoost algorithm and a set of optimized speech features combined with spectral subtraction. The key benefits of this method are the simple implementation, low computational complexity and the avoidance of the over-fitting problem. We checked the validity of the method by comparing its performance with the speech/non-speech classifier used in a standard voice activity detector. For speech recognition purpose, additional performance improvements were achieved by the adoption of new features including speech band energies and MFCC-based spectral distortion. For the same false alarm rate, the method reduced 20-50% of miss errors.

• 한국지능시스템학회논문지
• /
• 제10권4호
• /
• pp.374-378
• /
• 2000

in information retrieval, lack of positive examples is a main cause of poor performance. In this case most learning algorithms may not characteristics in the data to low recall. To solve the problem of unbalanced data, we propose a boosting method that uses linear perceptrons as weak learnrs. The perceptrons are trained on local data sets. The proposed algorithm is applied to text filtering problem for which only a small portion of positive examples is available. In the experiment on category crude of the Reuters-21578 document set, the boosting method achieved the recall of 80.8%, which is 37.2% improvement over multilayer with comparable precision.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 추계학술대회 논문집
• /
• pp.667-669
• /
• 2014

Development of 3 cylinder turbo charger engine is increasing due to engine down-sizing, cost reduction and emission regulations. However, 3 cylinder engine makes higher Exhaust manifold gas pressure(P3) pulsation than 4 cylinder engine and it generate boosting air with high pulsation. The mechanical waste-gate turbocharger just controlled by the boosting air has higher movement because of this high pulsation boosting air. This causes high vibrations to wasted gate and accelerate wear of the linkage system. So we need to understand out of the exhaust gas pressure pulsation changed by turbocharger compressor pressure(P2) Pulsation. In this study, we discuss how to prevent to abnormal movement of the turbo actuator by stabilized P2 Pulsation.

• Journal of the Korean Data and Information Science Society
• /
• 제27권1호
• /
• pp.255-264
• /
• 2016

Classification is a predictive modeling for a categorical target variable. Various classification ensemble methods, which predict with better accuracy by combining multiple classifiers, became a powerful machine learning and data mining paradigm. Well-known methodologies of classification ensemble are boosting, bagging and random forest. In this article, we assume that decision trees are used as classifiers in the ensemble. Further, we hypothesized that tree size affects classification accuracy. To study how the tree size in uences accuracy, we performed experiments using twenty-eight data sets. Then we compare the performances of ensemble algorithms; bagging, double-bagging, boosting and random forest, with different tree sizes in the experiment.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 추계종합학술대회
• /
• pp.462-466
• /
• 2002

본 논문에서는 8Bit MPU를 이용한 신경자극 치료장치가 설계되었다. 개발되고 있는 시스템은 저전력 MPU와 전압 boosting회로, 과전류 감시 및 이상전류 보정회로, 펄스의 상태를 알려주는 LED display 및 BUTTO과 펄스를 우리 몸에 전달시켜주는 Pad로 이루어져있다. 입력된 9V의 전압은 전압 boosting회로를 통해 120V까지 승압된다. 펄스는 단상 직사각형파, 대칭성 이상파, 교대 대칭성 이상파등의 형태로 우리 몸에 입력되어 근육의 수축과 이완을 시켜주는 알고리즘을 적용하였다.

• 산업기술연구
• /
• 제31권A호
• /
• pp.103-107
• /
• 2011

In this paper, a method is proposed to improve power factor and the input current THD in LED driver circuit. The researched circuit consists of a valley-fill circuit and boosting inductor and a Buck converter. Valley-fill circuit is a passive PFC and simplified structure, the buck converter is operated with current feedback. The switching frequency is 50KHz in LED driver circuit and LED forward current is constant. A valley-fill type PFC circuit for LED driver(15Watt) has been implemented, and the validity of proposed method is shown by is simulation and experimental result.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.872-875
• /
• 2009

In a bankruptcy prediction model, the accuracy is one of crucial performance measures due to its significant economic impacts. Ensemble is one of widely used methods for improving the performance of classification and prediction models. Two popular ensemble methods, Bagging and Boosting, have been applied with great success to various machine learning problems using mostly decision trees as base classifiers. In this paper, we analyze the performance of boosted neural networks for improving the performance of traditional neural networks on bankruptcy prediction tasks. Experimental results on Korean firms indicated that the boosted neural networks showed the improved performance over traditional neural networks.