• Journal of Radiation Protection and Research
• /
• 제46권4호
• /
• pp.204-212
• /
• 2021

Background: Identification of radioisotopes for plastic scintillation detectors is challenging because their spectra have poor energy resolutions and lack photo peaks. To overcome this weakness, many researchers have conducted radioisotope identification studies using machine learning algorithms; however, the effect of data normalization on radioisotope identification has not been addressed yet. Furthermore, studies on machine learning-based radioisotope identifiers for plastic scintillation detectors are limited. Materials and Methods: In this study, machine learning-based radioisotope identifiers were implemented, and their performances according to data normalization methods were compared. Eight classes of radioisotopes consisting of combinations of ²²Na, ⁶⁰Co, and ¹³⁷Cs, and the background, were defined. The training set was generated by the random sampling technique based on probabilistic density functions acquired by experiments and simulations, and test set was acquired by experiments. Support vector machine (SVM), artificial neural network (ANN), and convolutional neural network (CNN) were implemented as radioisotope identifiers with six data normalization methods, and trained using the generated training set. Results and Discussion: The implemented identifiers were evaluated by test sets acquired by experiments with and without gain shifts to confirm the robustness of the identifiers against the gain shift effect. Among the three machine learning-based radioisotope identifiers, prediction accuracy followed the order SVM > ANN > CNN, while the training time followed the order SVM > ANN > CNN. Conclusion: The prediction accuracy for the combined test sets was highest with the SVM. The CNN exhibited a minimum variation in prediction accuracy for each class, even though it had the lowest prediction accuracy for the combined test sets among three identifiers. The SVM exhibited the highest prediction accuracy for the combined test sets, and its training time was the shortest among three identifiers.

• 대한원격탐사학회지
• /
• 제28권4호
• /
• pp.393-407
• /
• 2012

본 연구에서는 광학 원격탐사 영상의 획득 시 태양의 고도 및 방위가 대상 지역의 지형기복과 결합하여 나타나는 영향 및 다수의 시기에 걸쳐 획득한 영상을 비교분석하는 경우 영상 촬영시기의 차이로 인한 태양의 위치변화와 지형기복이 결합하여 나타나는 영향에 대한 보정을 시도하였다. 한라산과 다수의 분석구가 분포하는 제주도를 대상으로 Landsat 7 ETM+ 영상과 ASTER GDEM 지형자료를 사용하여 국지적조도의 모델링 시 커널의 크기를 $3{\times}3$, $5{\times}5$, $7{\times}7$, $9{\times}9$ 화소로 변화시키며 Lambertian 보정기법인 cosine 보정법과 비 Lambertian 보정기법인 c-보정법을 적용하고 보정기법 및 커널 크기에 대한 지형보정 효과를 분석하였다. 개별 영상의 육상지역에 대하여 보정을 수행한 결과 커널의 크기 $7{\times}7$을 적용한 c-보정법을 사용하였을 때에 보정효과가 가장 우수한 것으로 평가되었고, 대상지역을 ISODATA 무감독분류법을 이용하여 선택된 산림지역에 한정하여 지형보정을 수행한 경우에는 커널의 크기 $9{\times}9$를 적용한 c-보정법을 사용하였을 때에 가장 우수한 결과가 도출되었으며 다양한 지표피복이 혼합된 대상지역 대한 보정보다 효과가 큰 것으로 평가되었다. 다시기 영상의 경우 세 시기에 획득된 영상에 대하여 각각 지형보정을 수행한 후 상대적 방사도 보정을 적용하였을 때 지형보정을 수행하지 않은 경우와 비교하여 적외선 파장영역에서는 보다 균질한 반사도로 방사보정이 이루어졌으며 가시광 파장영역에서는 원영상의 반사도 패턴이 잘 보존된 결과가 도출되었다. 이상의 결과로부터 주변 지형으로부터 반사되는 에너지와 불완전한 대기보정으로 인한 잔류 대기영향을 고려하는 c-보정법을 적용하는 경우 cosine 보정법보다 우수한 지형보정 효과가 나타나며 수치표고모델에 내재된 수평과 수직방향 오차 및 위성영상과의 정합오차의 영향을 감소시기키 위하여 국지적 조도의 모델링 시 커널의 크기를 증가시키는 경우 지형보정의 효과가 증대되는 것으로 판단된다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 추계학술대회
• /
• pp.262-267
• /
• 2004

The unloading compliance method is the most commonly used method to evaluate the fracture resistance characteristics of a material. In dynamic loading condition, the direct current potential drop(DCPD) method has been used because the unloading compliance method can not be applied due to the discontinuity of loading. However, even in the dynamic test using DCPD method, there is a problem that the voltage drops sharply on the initiation of crack. For the reason metioned above, the normalization method was suggested on ASTM E 1820 which is revised recently, as a new method to evaluate the dynamic fracture resistance characteristic. The nomalization method can be used to obtain a fracture resistance curve directly from a load-load line displacement. In this study, we obtained two fracture resistance curves from static test of welding part of nuclear piping both by unloading compliance and nomalization method. The two curves were almost same each other, so the adaptability of the nomalization method has been proved. We conducted a dynamic fracture resistance test for the same material. The fracture resistance curve from the dynamic test was obtained by normalization method and compared to that of the static test result.

• 센서학회지
• /
• 제25권4호
• /
• pp.291-296
• /
• 2016

The ideal chemical sensor must show the similar result under the same condition for accurate measurement of gases regardless of time. However, the actual responses of chemical sensors have been shown the lacks of repeatability and reproducibility because of the drift which has been caused by aging and pollution of the sensor and the environment change such as temperature and humidity. If the problems are not properly taken into considerations, the stability and reliability of the system using chemical sensors would be decreased. In this paper, we analyzed the sensor's drift and applied the three different compensation methods(DWT( Discrete Wavelets Transform), Baseline Manipulation, Internal Normalization) for reducing the effects of the drift in order to improve the stability and the reliability of short term of the chemical sensors. And in order to compare the results of the methods, the standard deviation was used as a criterion. The sensor drift was analyzed by a trend line graph. We applied the three methods to the successive data measured for three days and compared the results. As a result of comparison, the standard deviation of DWT showed lowest value. (Before compensation: 7.1219, DWT: 1.3644, Baseline Manipulation: 2.5209, Internal Normalization: 3.1425).

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 춘계학술대회
• /
• pp.385-388
• /
• 2013

본 논문에서는 MPEG-7의 EHD(Edge Histogram Descriptor)를 이용한 이미지 매칭기법의 취약점을 보이고 이미지 정규화를 이용해 이를 개선하는 방법을 제안한다. EHD 알고리즘은 edge의 기울기 분포를 수집하여 같은 분포를 가지는 이미지를 매칭하는 기법에 사용한다. 하지만 EHD는 매칭하고자 하는 객체의 회전과 왜곡의 변화에 민감하여 오인식률이 높다. 따라서 이미지를 정규화 하여 매칭하고자 하는 이미지 내의 객체의 edge 정보를 보다 정확하게 추출하여 매칭 성능을 개선한다. 실험을 통해 왜곡과 회전으로 정규화한 EHD 알고리즘을 비교 및 분석하여 기존의 방법에 비해 크기와 회전의 변화에 강인함을 보인다.

• 말소리와 음성과학
• /
• 제3권3호
• /
• pp.69-75
• /
• 2011

This paper investigates phrase positional effects on the timing of F0 (pitch) peaks in Tokyo Japanese disyllabic words with varying accent type (HL or LH) and phrase position (final or non final). The F0 peak timing was normalized by the total word duration ('normalized H timing'). The normalized H timing was significantly affected by accent type and phrase position. The H timing was later in the LH accent type than in the HL accent type, and in non final positions than in final positions. In addition, to examine the validity of the quantitative results, different models of phrase position effects were compared by measuring H timing in two approaches: normalization versus relative distance measures. For the normalization measures, the H timing was measured as the time of the F0 peak divided by the total word duration or by the duration of the tone bearing syllable. For the relative distance measures, the H timing was measured as the distance in milliseconds from the end of the word or from the end of the associated syllable. The best model was the normalization by the total word duration, rather than by the duration of the tone bearing syllable. This means that phrase positional effects on the timing of F0 peaks in Japanese disyllabic words are best modeled in terms of proportion of the total word duration.

• 한국컴퓨터정보학회논문지
• /
• 제13권1호
• /
• pp.75-80
• /
• 2008

본 논문에서는 프레임들의 차이값으로부터 카메라 브레이크에 의해 발생하는 큰 변화의 폭을 갖는 경계지점을 추출하는 전역적 결정트리를 이용하여 샷 경계를 검출하는 방법을 제시한다. 먼저 지적 $X^2$ 히스토그램과 정규화를 통하여 프레임 간 차이값을 계산하고, 다음으로 차이값간의 거리를 정규화를 통하여 계산한다. 계산된 차이값간의 거리를 바탕으로 전역적 임계치 거리를 계산하여 인접한 두 프레임들에 대한 거리값과 전역적 임계치 거리를 비교하여 샷 경계를 검출한다. 본 논문에서 제시한 전역적 결정트리를 이용하여 객체나 카메라의 움직임과 플래시 라이트와 같은 갑작스런 장면 변화를 쉽게 검출할 수 있다.

• Journal of Biosystems Engineering
• /
• 제35권6호
• /
• pp.450-457
• /
• 2010

Although cherry tomato is one of major vegetables consumed in fresh vegetable market, the quality grading method is mostly dependant on size measurement using drum shape sorting machines. Using Visible/Near-infrared spectroscopy, apparatus to be able to acquire transmittance spectrum data was made and used to estimate firmness, sugar content, and acidity of cherry tomatoes grown at hydroponic and soil culture. Partial least square (PLS) models were performed to predict firmness, sugar content, and acidity for the acquired transmittance spectra. To enhance accuracy of the PLS models, several preprocessing methods were carried out, such as normalization, multiplicative scatter correction (MSC), standard normal variate (SNV), and derivatives, etc. The coefficient of determination ($R^2_p$) and standard error of prediction (SEP) for the prediction of firmness, sugar, and acidity of cherry tomatoes from green to red ripening stages were 0.859 and 1.899 kgf, with a preprocessing of normalization, 0.790 and $0.434^{\circ}Brix$ with a preprocessing of the 1st derivative of Savitzky Golay, and 0.518 and 0.229% with a preprocessing normalization, respectively.

• 기술사
• /
• 제31권1호
• /
• pp.38-45
• /
• 1998

• 인지과학
• /
• 제7권2호
• /
• pp.39-56
• /
• 1996