• Journal of the Korean Data and Information Science Society
• /
• 제23권3호
• /
• pp.579-585
• /
• 2012

Many different semi-supervised learning algorithms have been proposed for use wit unlabeled data. However, most of them focus on classification problems. In this paper we propose a semi-supervised regression algorithm called the semi-supervised local constant estimator (SSLCE), based on the local constant estimator (LCE), and reveal the asymptotic properties of SSLCE. We also show that the SSLCE has a faster convergence rate than that of the LCE when a well chosen weighting factor is employed. Our experiment with synthetic data shows that the SSLCE can improve performance with unlabeled data, and we recommend its use with the proper size of unlabeled data.

• 상하수도학회지
• /
• 제16권6호
• /
• pp.710-716
• /
• 2002

A General Pipe Break Prediction Model that incorporates linear and exponential models in its form is developed. The model is capable of fitting pipe break trends that have linear, exponential or in between of linear and exponential trend by using a weighting factor. The weighting factor is adjusted to obtain a best model that minimizes the sum of squared errors of the model. The model essentially plots a best curve (or a line) passing through "cumulative number of pipe breaks" versus "break times since installation of a pipe" data points. Therefore, it prevents over-predicting future number of pipe breaks compared to the conventional exponential model. The optimal replacement time equation is derived by using the Threshold Break Rate equation by Loganathan et al. (2002).

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2015년도 추계학술대회 논문집
• /
• pp.209-210
• /
• 2015

This paper presents a new model predictive control method without the effect of a weighting factor in order to reduce common-mode voltage (CMV) for a three-phase voltage source inverter (VSI). By utilizing two active states with same dwell time during a sampling period instead of one state used in conventional method, the proposed method can reduce the CMV of VSI without the weighting factor. Simulation is carried out to verify the effectiveness of the proposed predictive control method with the aid of PSIM software.

• 인지과학
• /
• 제13권1호
• /
• pp.1-11
• /
• 2002

본 논문에서는 먼저 Anchor Text의 단어들이 키워드로 적합한지 TFIDF를 이용하여 테스트하였다. 그 결과는 가중치가 높아서 키워드로 적합한 단어가 있었는가 하면. 아예 문서에 나오지도 않는 단어가 있어 키워드로 적합하지 않은 단어도 있었다. 이를 해결하기 위하여 새로운 키워드 추출 방법을 제시하였다. 본 논문에서는 적합하지 않은 키워드를 제거함으로써 새로운 키워드를 만들어 내고 TFIDF값을 각 키워드의 가중치로 이용하여 Ranking이 가능하게 하였다. 이렇게 추출된 키워드는 기존의 방법보다 정확도가 높아졌음 증명했다.

• 전자공학회논문지 IE
• /
• 제49권2호
• /
• pp.40-45
• /
• 2012

본 논문은 전력용 변압기의 최적화된 온도제어를 위하여 부하율을 이용하여 권선최고점온도를 예측하고 냉각장치를 제어하는 방법을 제안하였다. 전력용 변압기의 최적화된 온도제어를 위하여, 하중함수를 사용하여 부하전류에 따른 부하율과 권선온도, 외기온도, 오일온도 등을 바탕으로 권선최고점온도를 예측하는 상관관계식을 제시한다. 또한, 이를 전력용변압기에 적용하여 제어한 결과를 제시한다.

• 유체기계공업학회:학술대회논문집
• /
• 유체기계공업학회 2005년도 연구개발 발표회 논문집
• /
• pp.185-190
• /
• 2005

This work presents a numerical procedure to optimize the elliptic-shaped pin fin arrays to enhance turbulent heat transfer. The response surface method is used as an optimization technique with Reynolds-averaged Navier Stokes analysis of flow and heat transfer. Shear stress transport (SST) turbulence model is used as a turbulence closure. Computational results for average heat transfer rate show a reasonable agreement with the experimental data. Four variables including major axis length, minor axis length, pitch and the pin fin length nondimensionalized by duct height are chosen as design variables. The objective function is defined as a linear combination of heat transfer and friction-loss related terms with weighting factor. D-optimal design is used to reduce the data points, and, with only 28 points, reliable response surface is obtained. Optimum shapes of the pin-fin arrays have been obtained in the range from 0.0 to 0.1 of weighting factor.

• 한국정밀공학회지
• /
• 제25권2호
• /
• pp.72-79
• /
• 2008

In the redundant actuation system which has more actuators than a system's mobility, there are various method to determine actuated torques because those are not determined uniquely. This paper presents a torque distribution method using weighted-pseudoinverse to optimize the maximum torque of various actuated inputs of the redundant system. The various weighting factor of weighted-pseudoinverse is studied to reduce maximum actuated torque. This method is experimentally applied to 3RRR parallel robot, which shows that presented method can efficiently reduce the maximum actuated torque.

• 한국멀티미디어학회논문지
• /
• 제19권5호
• /
• pp.924-931
• /
• 2016

In this paper, Various network adaptive MAC scheduling technique is proposed to effectively overcome limits of narrow bandwidth and low transmission speed in underwater. UPFC(Underwater Packet Flow Control) is a technique to reduce both the number of transmission and transmission time using three types (Normal, Blocked, Parallel) of data transmission. In this technique, the load information, in which a transmission node have, is transmitted to destination node using marginal bit in reserved header. Then the transmitted information is referred to determine weighting factor. According to the weighting factor, scheduling is dynamically changed adaptively. The performance of UPFC is analyzed and flow control technique which can be applied to Cluster Based Network and Ad Hoc network as well.

• 한국안전학회지
• /
• 제28권4호
• /
• pp.72-80
• /
• 2013

Accident prevention plan it a construction site should be analyzed and made with risk evaluation and management, from recent year, in Korea. Accidents occurred in construction site are related to all parties such as owner, main and subcontractor, labour. But analyzing some relationship between main and subcontractor is very important to estimate what risk between then are existed in a site. There are some different aspects concerning with risk management between them. Everywork has its own risk in there, This is the reason why everywork which are made by subcontractor himself should be evaluated for risk level. And main contractor should provide for subcontractor to prevent each risk at the work, all the time.

• 농촌계획
• /
• 제10권3호
• /
• pp.41-51
• /
• 2004

This study aims to develop a potential evaluation method for urban spatial expansion using remote sensing (RS) and geographic information system (GIS). A multi-criteria evaluation method with several criteria and their weighting values was introduced to evaluate the score and quantification of the potential surface around the existing cities. The six criteria with one geographic factor, slope, and five accessibility factors, time distance from center of the city, national road, interchange of expressway, a big city, and station, were defined for the potential. RS techniques were applied for classification of the actual urban expansion maps between two periods, and GIS functions were used for score of accessibility criteria with a distance decay function from geographic, road and several point maps, which was developed in this study. The new methodology was applied to a test area, Suwon, between 1986 and 1996. In order to optimize the six weighting values, this study made new findings to search the optimal combination of the weighting values from new methodology, weighted scenario method for intensity order (WSM), combined with intensity order and AHP method, including a trial and error method for sensitivity analysis to make the intensity order. The optimal combination of the weighting values by the new method generated the optimal potential surface, considering spatial trend of urban expansion in the test area.