• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.206-211
• /
• 2009

This paper presents a methodology to 1-day-forecast stock index using the automatic feature extraction method based on the neural network with weighted fuzzy membership functions (NEWFM). The distributed non-overlap area measurement method selects the minimized number of input features by automatically removing the worst input features one by one. CPP$_{n,m}$(Current Price Position of the day n: a percentage of the difference between the price of the day n and the moving average from the day n-1 to the day n-m) and the 2 wavelet transformed coefficients from the recent 32 days of CPP$_{n,m}$ are selected as minimized features using bounded sum of weighted fuzzy membership functions (BSWFMs). For the data sets, from 1989 to 1998, the proposed method shows that the forecast rate is 60.93%.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.2
• /
• pp.101-107
• /
• 2014

This study is proposed the novel PPG sensor device and the signal processing method to replace the acceleration sensor that is used to reject motion artifacts contained in photoplethysmography(PPG). The proposed method is to reject motion artifacts by an adaptive filter based on the estimated motion artifact by using a blue LED light. To evaluate the performance of the proposed method experimentally, We did design a novel sensor consisted of blue/red LEDs and photo-sensor and implemented, and then rejected the motion artifacts by using an adaptive filter and the implemented sensor. In the results of the experiments, it is shown that the proposed sensor device and signal processing can reconstruct the PPG signal despite the occurrence of motion artifacts, and also that the SNR was 4.5 times of moving average filter. According to the experimental results, the proposed method can be applied to design a low-cost device.

• Journal of Industrial Convergence
• /
• v.18 no.3
• /
• pp.53-61
• /
• 2020

Travel speed is an important parameter for measuring road traffic and incident detection system. In this paper I suggests a model developed for estimating reliable and accurate average roadway link travel speeds using image processing sensor. This method extracts the vehicles from the video image from CCTV, tracks the moving vehicles using deep neural network, and extracts traffic information such as link travel speeds and volume. The algorithm estimates link travel speeds using a robust data-fusion procedure to provide accurate link travel speeds and traffic information to the public. In the field tests, the new model performed better than existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.2 s.314
• /
• pp.19-26
• /
• 2007

In the sigma filter, there is a specialized neighbours distribution scheme in which the sigma value is computed from local statistics. It is designed to modify a standard average filter to preserve edges. However this filter is vulnerable to details-enhancement and conventional sigma approaches have been focused on denoising, not enhancing the characteristic area. This paper proposes an adaptive image enhancement algorithm using local statistics and functional synthesis which are utilized for adaptive realization of the enhancement, so that not only image noise may be smoothed but also details may be enhanced. For the local adaptation, parameters are estimated and weighted at each moving window that satisfy the criteria. The experimental results illuminates the effectiveness of the proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.2
• /
• pp.95-99
• /
• 2002

The Loose Part Monitoring System(LPMS) has been designed to detect. locate and evaluate detached or loosened parts and foreign objects in the reactor coolant system. In this paper, at first, we presents an application of the back propagation neural network. At the preprocessing step, the moving window average filter is adopted to reject the reject the low frequency background noise components. And then, extracting the acoustic signature such as Starting point of impact signal. Rising time. Half period. and Global time, they are used as the inputs to neural network . Secondly, we applied the neural network algorithm to LPMS in order to estimate the mass of loose parts. We trained the impact test data of YGN3 using the backpropagation method. The input parameter for training is Rising clime. Half Period amplitude. The result shored that the neural network would be applied to LPMS. Also, applying the neural network to thin practical false alarm data during startup and impact test signal at nuclear power plant, the false alarms are reduced effectively.

• Journal of Environmental Health Sciences
• /
• v.38 no.5
• /
• pp.393-397
• /
• 2012

Objectives: The objectives of this study were to measure passengers' exposure to ultrafine particles (UFP) and to determine effects of fuel, operating condition and position of seat. Method: UFP exposures in front and back seats of the Elephant vehicle in Seoul Grand Park were simultaneously measured by a condensation particle counter (P-Trak model 8525, TSI). The measurements were conducted 7 times with diesel-powered vehicle and 3 times with electricity vehicle in one day. The vehicle stopped at 3 locations along with 2.2 km of driving route. Results: UFP concentration in diesel-powered vehicle was significantly higher than electricity vehicle. At front seat of diesel-powered vehicle, average UFP exposure during stopping was significantly higher than during moving. When diesel-powered vehicle moved, UFP exposure in back seat was significantly higher than in front seat. Conclusions: Passengers in the diesel-powered Elephant vehicle could be exposed to high level of UFP. The UFP exposure was associated with operation condition and position of seat.

• Journal of Environmental Science International
• /
• v.13 no.7
• /
• pp.703-710
• /
• 2004

Petroleum refineries have been considered as an important emission source for atmospheric volatile hazardous air pollutants(HAPs). The emission source includes petroleum refinery processes and process equipment. The control strategy for volatile HAPs requires emission estimations of these pollutants. However, systematic methods of volatile HAPs emission from petroleum refineries have not yet been established. Accordingly, present study surveyed the estimation method of volatile HAPs emitted from the petroleum refinery processes and process equipment. The emission estimation methods for the petroleum refinery processes are applied for 11 petroleum refining facilities: fluidized catalytic cracking, thermal cracking, moving bed catalytic cracking, compressed engine, blowdown system, vacuum distilled column condensator, natural gas or distilled boiler, natural gas or distilled heater, oil boiler, oil heater and flare. Four emission estimation methods applied for the petroleum refinery process equipment are as follows: average emission factor approach, screening ranges approach, EPA correlation approach and unit-specific correlation approach. The process equipment for which emission factors are available are valves, pump seals, connectors, flanges and open-ended lines.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.769-780
• /
• 2015

Smoothing a digital curve by averaging its connected points is widely employed to minimize sharp changes of the curve that are generally introduced by noise. An appropriate degree of smoothing is critical since the area or features of the original shape can be distorted at a higher degree while the noise is insufficiently removed at a lower degree. In this paper, we provide a mathematical relationship between the parameters, such as the number of iterations, average distance between neighboring points, weighting factors for averaging and the moving distance of the point on the curve after smoothing. Based on these findings, we propose to control the smoothed curve such that its deviation is bounded particular error level as well as to significantly expedite smoothing for a pixel-based digital curve.

• Environmental Engineering Research
• /
• v.20 no.3
• /
• pp.268-276
• /
• 2015

Solid waste production increases due to population and consumption increments. Landfill is the ultimate destination for all kinds of municipal solid waste; and is the most convenient waste disposal method in developing countries. To minimize investment and operational costs and society's opposition towards locating landfills nearby, proper landfill sizing and siting are essential. In this study, solid waste forecasting using Autoregressive Integrating Moving Average (ARIMA) was integrated with government future plans and waste composition to estimate the required landfill area for the state of Selangor, Malaysia. Landfill siting criteria were then prioritized based on expert's preferences. To minimize ambiguity and the uncertainty of the criteria prioritizing process, the expert's preferences were treated using integrated Median Ranked Sample Set (MRSS) and Analytic Hierarchy Process (AHP) models. The results show that the required landfill area is 342 hectares and the environmental criteria are the most important; with a priority equal to 48%.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.38 no.5
• /
• pp.64-73
• /
• 1996

When typhoon occurs, the meteorological conditions get worse and can cause a large damage from storm and flood . This damage, however, can be minimized if a precise analysis of the runoff characteristics by typhoon tracks is used in the flood contorl This paper aims at the analysis of storm occurrence and runoff characteristics by typhoon tracks in Nakdong river basin. Therefore, the data of 14 typhoons which invaded Nakdong river basin during the period from 1975 to 1991 were collected, analyzed, and studied. The major results of this study are as followings; 1) The frequency of the typhoon occurrence here in Korea was affected by the storms three times a year on the average. The highest-recorded frequency was during the months of July to September. 2) The survey of the track characteristics depending on the forms of the storm in the Nakdong river basin showed that typhoon storm advanced from the south of the basin to the north, while the frontal type storm was most likely to advanced from the west to the north. 3) Typhoon tracks are classified into three categories, 6 predictors with high correlation coefficient are finally selected, and stepwise multiple regression method are used to establish typhoon strom forecasting models. 4) The riview on the directions of progress of the storm made it clear that the storm moving downstream from upstream of the basin could develop into peak discharge for ca short time and lead to more flood damage than in any other direction.