• 전기학회논문지
• /
• 제58권3호
• /
• pp.598-604
• /
• 2009

This paper proposes a vehicle detector with an anisotropic magnetoresistive (AMR) sensor and addresses experimental results to show the detector's performance. The detector consists of an AMR sensor and mechanical and electronic apparatuses. The AMR sensor, composed of four magnetoresistors, senses disturbance of the earth's magnetic field caused by a vehicle moving over the sensor and then produces an output indicative of the moving vehicle. This paper verifies performance of the detector on the basis of experimental results obtained from the field tests carried under the two traffic conditions on local highways in Korea. First, I show the vehicle counting performance on a low speed congested highway by comparing the vehicle counts measured by the detector with the exact counts. Second, both vehicle counts and average speeds calculated from the measured point-occupancy on another continuously free running highway are compared with the reference values obtained from a loop detector which has two independent loop coils, where I have used several performance indices including mean absolute percentage error (MAPE) to show the performance consistency between the two types of detectors.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.186-189
• /
• 2005

In a clinical setting, developing a reliable method for the automated drug infusion system would improve a drug therapy under the unexpected and acute changes of hemodynamics. The conventional proportional-integral-derivative (PID) controller might not be able to achieve maximum performance because of the unexpected change of the intra- and inter-patient variability. The fuzzy PID control and the conventional PID control were tested under the unexpected response of mean arterial blood pressure (MAP) to a vasopressor agent during acute hypotension. Compared with the conventional PID control, the fuzzy PID control performed the robust MAP regulation regardless of the unexpected MAP response (average absolute value of the error between target value and actual MAP: 0.98 vs. 2.93 mmHg in twice response of the expected MAP and 2.59 vs. 9.75 mmHg in three-times response of the expected MAP). The result was due to the adaptive change of the proportional gain in PID parameters.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2004년도 제5회 압연심포지엄 신 시장 개척을 위한 압연기술
• /
• pp.349-358
• /
• 2004

The strip temperature history of finishing mill process is one of the most important factors to stabilize the facilities and to achieve the better product quality including a better prediction of roll force etc. The ultimate goal of this study is to improve scientific understanding of the finishing mill process in the view of heat transfer science. Finishing mill cooling facilities of KwangYang $\#3$ hot rolling are introduced and heat transfer analyses from FET to FDT are particularly focused in this study Three major tasks are successfully achieved as follows: 1) The temperature Prediction Models are developed. 2) The average absolute error is found to be less then 10 Celsius degree (about $8.5^{\circ}C$). 3) Prediction rate (less then $\bar{+}20$) are $10.2\%$ improved $(80.1\;\rightarrow\;90.3\%)$.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.1-6
• /
• 2009

Due to the different camera properties of the multi-view camera system, the color properties of captured images can be inconsistent. This inconsistency makes post-processing such as depth estimation, view synthesis and compression difficult. In this paper, the method to correct the different color properties of multi-view images is proposed. We utilize a gray gradient bar on a display device to extract the color sensitivity property of the camera and calculate a look-up table based on the sensitivity property. The colors in the target image are converted by mapping technique referring to the look-up table. Proposed algorithm shows the good subjective results and reduces the mean absolute error among the color values of multi-view images by 72% on average in experimental results.

• Journal of Biosystems Engineering
• /
• 제24권1호
• /
• pp.67-74
• /
• 1999

A prototype cut-flower sorter was developed and tested for its performance with five varieties of roses. Support plates driven by a chain mechanism transported the roses into an image inspection chamber. Color image processing algorithms were developed to evaluate the length, thickness, and straightness of stem and color, height, and maturity of bud. The average absolute errors of the system for the measurements of stem length, stem thickness, and height of bud were 19.7 mm, 0.5 mm, and 3.8 mm, respectively. The results of classification by the sorter were compared with those of a human inspector for straightness of stem and maturity of bud. The classification error for the straightness of stem was 8.6%, when both direct image and reflected image by a mirror were analyzed. The accuracy in classifying the maturity of bud varied among the varieties, the smallest for‘Nobless’(1.5%) and the largest for‘Rote Rose’(13.5%). The time required to process a rose averaged 2.06 seconds, equivalent to the capacity of 1,600 roses per hour.

• Journal of the Korean Data and Information Science Society
• /
• 제12권2호
• /
• pp.47-55
• /
• 2001

직접(direct) 추정법, 합성(synthetic) 추정법, 복합(composite) 추정법, 베이즈(Bayes) 추정법 등 소지역 추정법들의 효율성을 비교, 분석하고자 '98 경제활동 인구조사에서 경기도의 실제 자료를 이용하여 각 시부지역의 실업자수 추정값의 편의(bias)와 평균제곱 오차(MSE)를 모의실험을 통해 계산하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 D
• /
• pp.1144-1148
• /
• 1997

In this paper, a method for the daily maximum load forecasting which uses a chaotic time series in power system and artificial neural network. We find the characteristics of chaos in power load curve and then determine a optimal embedding dimension and delay time. For the load forecast of one day ahead daily maximum power, we use the time series load data obtained in previous year. By using of embedding dimension and delay time, we construct a strange attractor in pseudo phase plane and the artificial neural network model trained with the attractor mentioned above. The one day ahead forecast errors are about 1.4% for absolute percentage average error.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.578-580
• /
• 1995

In this paper, a method for the daily maximum load forecasting which uses a chaotic time series in power system and artificial neural network. We find the characteristics of chaos in power load curve and then determine a optimal embedding dimension and delay time, For the load forecast of one day ahead daily maximum power, we use the time series load data obtained in previous year. By using of embedding dimension and delay time, we construct a strange attractor in pseudo phase plane and the artificial neural network model trained with the attractor font mentioned above. The one day ahead forecast errors are about 1.4% of absolute percentage average error.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.179-180
• /
• 2007

In this paper, it proposes an efficient iterative stopping rules using absolute mean values for the LLR difference values between the first and second decoder in the present decoding process. It is verifying that the proposal algorithm can be reduced the average number of iterations compared to conventional scheme with a negligible degradation of the error performance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.835-837
• /
• 1996

In this paper, a method for the daily maximum load forecasting which uses a chaotic time series in power system and artificial neural network(Back-propagation) is proposed. We find the characteristics of chaos in power load curve and then determine a optimal embedding dimension and delay time. For the load forecast of one day ahead daily maximum power, we use the time series load data obtained in previous year. By using of embedding dimension and delay time, we construct a strange attractor in pseudo phase plane and the artificial neural network model trained with the attractor mentioned above. The one day ahead forecast errors are about 1.4% for absolute percentage average error.