• Journal of the Korean Wood Science and Technology
• /
• 제24권2호
• /
• pp.46-54
• /
• 1996

This study was carried out to investigate the vacuum drying characteristics of 50mm- and 75mm- thick tree disks of some domestic softwoods for substituting the conventional hardwoods as the materials for wood crafts. Though the elapsed drying times from green to in-use moisture content(MC) were largely shortened by vacuum drying, the tree disks treated by EWS couldn't be dried to in-use MC, and so sapwood stains also were occurred severely. We suggest EWS treatment is undesirable for the species with very high sapwood portion or vacuum drying with hot water circulation heating system. Heart checks were slight, but sapwood checks, which have never been trouble in drying process of tree disks, were severe. For the reasonable explanation it is suggested MC differences between sapwood and heartwood were large and most of tree disks had already no barks before drying test. Ginkgo was vacuum-dried with very slight drying defects such as heart checks, sapwood checks. V-cracks and sapwood stains. In Korean red pine and pitch pine V-cracks were severely occurred. And it was found the special feature that most of these defected tree disks contained several V-cracks within one tree disk. It can be considered as the causes that the region of sapwood was defected by the several checks at the early drying stage because of the steep MC gradient along the radial direction, and then at the later drying stage the drying stresses due to differential shrinkage were concentrated on these brittle spots.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권7호
• /
• pp.259-266
• /
• 2018

본 논문에서는 단어의 순서와 문맥을 고려하는 특징을 추출하여 순환신경망(Recurrent Neural Network)으로 문서를 분류하는 방법을 제안한다. 단어의 의미를 고려한 word2vec 방법으로 문서내의 단어를 벡터로 표현하고, 문맥을 고려하기 위해 doc2vec으로 입력하여 문서의 특징을 추출한다. 문서분류 방법으로 이전 노드의 출력을 다음 노드의 입력으로 포함하는 RNN 분류기를 사용한다. RNN 분류기는 신경망 분류기 중에서도 시퀀스 데이터에 적합하기 때문에 문서 분류에 좋은 성능을 보인다. RNN에서도 그라디언트가 소실되는 문제를 해결해주고 계산속도가 빠른 GRU(Gated Recurrent Unit) 모델을 사용한다. 실험 데이터로 한글 문서 집합 1개와 영어 문서 집합 2개를 사용하였고 실험 결과 GRU 기반 문서 분류기가 CNN 기반 문서 분류기 대비 약 3.5%의 성능 향상을 보였다.

• 한국결정학회지
• /
• 제8권1호
• /
• pp.15-19
• /
• 1997

고온고압용 autoclave에서 $Na_2CO_3$를 광화제로 하여 청색수정 단결정을 수열성장하고, 성장온도와 코발트 함입량과의 관계를 고찰하였다. $5wt.\%$의 $Na_2CO_3$ 수열용액, $343^{\circ}C$의 성장온도, $22^{\circ}C$의 온도구배, 950기압의 조건에서 $100{\times}50{\times}35mm^3$ 크기의 청색수정을 성장하였으며, 성장속도는 0.55 mm/day였다. 가시영역에서의 흡수 스펙트럼을 측정한 결과 545, 570 및 643 nm 근처에서 흡수피크가 관찰되었다. 청색의 농도는 원료내 코발트의 농도와는 무관하며 성장온도와 밀접한 관계가 있음을 확인하였다.

• 한국통신학회논문지
• /
• 제22권8호
• /
• pp.1698-1706
• /
• 1997

본 논문은 2차원 정보, 3차원 정보 그리고 그 밖의 각종 유용한 정보를 취합하여 이를 상호 보완하여 인식하는 멀티미디어 시스템 중의 한 부분으로 이중 3차원 정보를 추출하고 정합 하는 방법을 제안하고자 한다. 우선 거리 영상으로부터 z축 기울기를 이용하여 표면 분류를 행하고 법선 벡터들의 교점을 통해 각 표면들에 대한 특징을 추출한다. 또한 각 표면들로 부터 이루는 각이나 거리등과 같은 특징 관계를 설정한다. 이후 정합 과정을 통해 인식을 수행하게 되는데 정합 과정은 영상인식의 최종 단계로 대단히 중요한 과정중의 하나가 된다. 왜냐하면 멀티미디어 시스템은 각종 정보를 취합하여 정합 과정을 수행해야 하기 때문에 취합한 모든 정보를 보다 보편적이고 효율적으로 정합하는 방법론의 제시가 중요하기 때문이다. 따라서 본 논문에서는 정합 과정 수행에 필요한 보편적 방법론의 제안에 초점을 맞추고자 하며 이중 우선 3차원 물체의 정합과정에 대해 다루고자 한다. 이를 위해 롤이론을 적용하여 유사도를 측정하며 이를 퍼지 관계 행렬을 구성하여 인식을 수행한다. 최종적으로 실험에 의해 본 논문의 유용성을 입증하고자 한다.

• 한국정보통신학회논문지
• /
• 제13권10호
• /
• pp.2163-2170
• /
• 2009

흉부 컴퓨터단층영상에서의 얻어진 폐 영상은 볼륨과 형태 등의 정량적인 정보들로서 진단과 수술 계획 등에 있어서 필연적 정보를 제공한다. 일반적인 영상분할은 이미지를 구성 요소영역이나 목적물에 따라 나누는 방법이다. 그러나 재분할을 하는 단계에서 최종영상은 에너지 최소화를 해결하는 정도에 의존하며, 분할은 응용대상의 관심 영역에서 객체나 물체의 경계에서 정지하게 된다. 가변형 능동모델은 컴퓨터 비젼, 영상처리 분야에서 광범위하게 사용되고 있다. 또한 영역 분할은 현재까지 많은 연구가 되고 있으며, Xu에 의해서 GVF라는 새로운 형태의 외부힘이 제안되고 있다. 본 논문에서 제안하는 알고리듬은 흉부 컴퓨터단층영상에서 실질을 자동 분할하기 위해서 에너지 최소화 방법을 사용하고, 영역분할을 위해 개선된 가변형 능동모델을 제안한다. 알고리듬은 정확한 영역분할을 위해서 기존 방법과 다른 개선된 외부힘을 정의하는 것이다. 임상의 실험은 흉부 컴퓨터단층영상에서 진단에 필요로 하는 폐 실질의 분할이 성공적인 결과를 나타내었다.

• Earthquakes and Structures
• /
• 제17권2호
• /
• pp.143-162
• /
• 2019

Motivated by a simpler and more compact hybrid active tuned mass damper (ATMD) system with wide frequency spacing (i.e., high robustness) but not reducing the effectiveness using the least number of ATMD units, the active tuned tandem mass dampers (ATTMD) have been proposed to attenuate undesirable oscillations of structures under the ground acceleration. Likewise, it is expected that the frequency spacing of the ATTMD is comparable to that of the active multiple tuned mass dampers (AMTMD) or the multiple tuned mass dampers (MTMD). In accordance with the mode generalised system in the specific vibration mode being controlled (simply referred herein to as the structure), the closed-form expression of the dimensionless displacement variances has been derived for the structure with the attached ATTMD. The criterion for the optimum searching may then be determined as minimization of the dimensionless displacement variances. Employing the gradient-based optimization technique, the effects of varying key parameters on the performance of the ATTMD have been scrutinized in order to probe into its superiority. Meanwhile, for the purpose of a systematic comparison, the optimum results of two active tuned mass dampers (two ATMDs), two tuned mass dampers (two TMDs) without the linking damper, and the TTMD are included into consideration. Subsequent to work in the frequency domain, a real-time Simulink implementation of dynamic analysis of the structure with the ATTMD under earthquakes is carried out to verify the findings of effectiveness and stroke in the frequency domain. Results clearly show that the findings in the time domain support the ones in the frequency domain. The whole work demonstrates that ATTMD outperforms two ATMDs, two TMDs, and TTMD. Thereinto, a wide frequency spacing feature of the ATTMD is its highlight, thus deeming it a high robustness control device. Furthermore, the ATTMD system only needs the linking dashpot, thus embodying its simplicity.

• 한국정보통신학회논문지
• /
• 제23권6호
• /
• pp.682-689
• /
• 2019

부분 기반 영상 표현(part-based image representation)에서는 영상의 부분적인 모습을 기저 벡터로 표현하고 기저 벡터의 선형 조합으로 영상을 분해하며, 이 때 기저 벡터의 계수가 곧 물체의 부분적인 특징을 의미하게 된다. 본 논문에는 부분 기반 영상 표현 기법인 비음수 행렬 분해(non-negative matrix factorization, NMF)를 이용하여 얼굴 영상을 표현하고 신경망 기법을 적용하여 가려진 얼굴을 인식하는 얼굴 인식을 제안한다. 표준 비음수 행렬 분해, 투영 경사 비음수 행렬 분해, 직교 비음수 행렬 분해를 이용하여 얼굴 영상을 표현하였고, 각 기법의 성능을 비교하였다. 인식기로는 학습벡터양자화 신경망을 사용하였으며, 인식기에서의 거리 척도로는 유클리디언 거리를 사용하였다. 실험 결과, 전통적인 얼굴 인식 방법에 비하여 제안한 기법이 가려진 얼굴 인식에 보다 강인함을 보인다.

• 한국IT서비스학회지
• /
• 제21권3호
• /
• pp.63-72
• /
• 2022

The extinction crisis of local cities, caused by a population density increase phenomenon in capital regions, directly causes the increase of vacant houses in local cities. According to population and housing census, Gunsan-si has continuously shown increasing trend of vacant houses during 2015 to 2019. In particular, since Gunsan-si is the city which suffers from doughnut effect and industrial decline, problems regrading to vacant house seems to exacerbate. This study aims to provide a foundation of a system which can predict and deal with the building that has high risk of becoming vacant house through implementing a data driven vacant house prediction machine learning model. Methodologically, this study analyzes three types of machine learning model by differing the data components. First model is trained based on building register, individual declared land value, house price and socioeconomic data and second model is trained with the same data as first model but with additional POI(Point of Interest) data. Finally, third model is trained with same data as the second model but with excluding water usage and electricity usage data. As a result, second model shows the best performance based on F1-score. Random Forest, Gradient Boosting Machine, XGBoost and LightGBM which are tree ensemble series, show the best performance as a whole. Additionally, the complexity of the model can be reduced through eliminating independent variables that have correlation coefficient between the variables and vacant house status lower than the 0.1 based on absolute value. Finally, this study suggests XGBoost and LightGBM based machine learning model, which can handle missing values, as final vacant house prediction model.

• 천문학회보
• /
• 제46권1호
• /
• pp.42.1-42.1
• /
• 2021

In this study, we present a visual explanation of a deep learning solar flare forecast model and its relationship to physical parameters of solar active regions (ARs). For this, we use full-disk magnetograms at 00:00 UT from the Solar and Heliospheric Observatory/Michelson Doppler Imager and the Solar Dynamics Observatory/Helioseismic and Magnetic Imager, physical parameters from the Space-weather HMI Active Region Patch (SHARP), and Geostationary Operational Environmental Satellite X-ray flare data. Our deep learning flare forecast model based on the Convolutional Neural Network (CNN) predicts "Yes" or "No" for the daily occurrence of C-, M-, and X-class flares. We interpret the model using two CNN attribution methods (guided backpropagation and Gradient-weighted Class Activation Mapping [Grad-CAM]) that provide quantitative information on explaining the model. We find that our deep learning flare forecasting model is intimately related to AR physical properties that have also been distinguished in previous studies as holding significant predictive ability. Major results of this study are as follows. First, we successfully apply our deep learning models to the forecast of daily solar flare occurrence with TSS = 0.65, without any preprocessing to extract features from data. Second, using the attribution methods, we find that the polarity inversion line is an important feature for the deep learning flare forecasting model. Third, the ARs with high Grad-CAM values produce more flares than those with low Grad-CAM values. Fourth, nine SHARP parameters such as total unsigned vertical current, total unsigned current helicity, total unsigned flux, and total photospheric magnetic free energy density are well correlated with Grad-CAM values.

• International Journal of Computer Science & Network Security
• /
• 제24권8호
• /
• pp.14-20
• /
• 2024

Traffic sign recognition is an essential feature of intelligent transportation systems and Advanced Driver Assistance Systems (ADAS), which are necessary for improving road safety and advancing the development of autonomous cars. This research investigates the incorporation of the YOLOv9 model into traffic sign recognition systems, utilizing its sophisticated functionalities such as Programmable Gradient Information (PGI) and Generalized Efficient Layer Aggregation Network (GELAN) to tackle enduring difficulties in object detection. We employed a publically accessible dataset obtained from Roboflow, which consisted of 3130 images classified into five distinct categories: speed_40, speed_60, stop, green, and red. The dataset was separated into training (68%), validation (21%), and testing (12%) subsets in a methodical manner to ensure a thorough examination. Our comprehensive trials have shown that YOLOv9 obtains a mean Average Precision (mAP@0.5) of 0.959, suggesting exceptional precision and recall for the majority of traffic sign classes. However, there is still potential for improvement specifically in the red traffic sign class. An analysis was conducted on the distribution of instances among different traffic sign categories and the differences in size within the dataset. This analysis aimed to guarantee that the model would perform well in real-world circumstances. The findings validate that YOLOv9 substantially improves the precision and dependability of traffic sign identification, establishing it as a dependable option for implementation in intelligent transportation systems and ADAS. The incorporation of YOLOv9 in real-world traffic sign recognition and classification tasks demonstrates its promise in making roadways safer and more efficient.