• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1213-1214
• /
• 2023

현재 국내외 CCTV 구축량 증가로 사생활 침해와 높은 설치 비용등이 문제점으로 제기되고 있다. 따라서 본 연구는 Early Fusion을 적용한 위급상황 음향 분류 모델을 제안한다. 음향 데이터에 STFT(Short Time Fourier Transform), Spectrogram, Mel-Spectrogram을 적용해 특징 벡터를 추출하고 3차원으로 Early Fusion하여 ResNet, DenseNet, EfficientNetV2으로 학습한다. 실험 결과 Early Fusion 방법이 가장 좋은 결과를 보였고 DenseNet, EfficientNetV2가 Accuracy, F1-Score 모두 0.972의 성능을 보였다.

• Journal of Internet Computing and Services
• /
• v.6 no.6
• /
• pp.57-69
• /
• 2005

This paper proposes a minimal workflow model as a feasible solution to the workflow process rediscovery problem. The minimal workflow model can be represented by the minimal workflow net. The process model is represented by ICN(Information Control Net) Modeling method, ICN can configure activity dependent net applying proper algorithm according to activity dependency among activities which configure the ICN, The proposed model is possible to develop with the application of minimal workflow net and with the application of the algorithm related to activity dependent net properties, Hence, it can solve the process rediscovery problem and can also be helpful on process improvement.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.19-26
• /
• 2020

Steel production requires high-quality surfaces with minimal defects. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. To meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. In this paper, we proposed a ShuffleDefectNet defect detection system based on deep learning. The proposed defect detection system exceeds state-of-the-art performance for defect detection on the Northeastern University (NEU) dataset obtaining a mean average accuracy of 99.75%. We train the best performing detection with different amounts of training data and observe the performance of detection. We notice that accuracy and speed improve significantly when use the overall architecture of ShuffleDefectNet.

• Proceedings of the Materials Research Society of Korea Conference
• /
• 2009.11a
• /
• pp.17.2-17.2
• /
• 2009

Al Foam 소재는 다공질 금속으로써 저밀도 및 우수한 충격에너지 흡수능으로 최근 새로운 기능성 재료로 부상하여 세계 각국에서 연구개발이 활발하게 진행되고있다. 특히 이러한 Al Foam재를 자동차용 부품의 충격흡수재로사용할 경우 뛰어난 충격흡수능으로 인해 고안전 차량 부품 개발에 획기적인 기술 적용이 기대된다. 그러나, 종래 Al Foam재를 기계부품 등에 삽입할 경우 발포금속을 제조하여 부품 형상에 따라 가공하여 삽입하였으나 이는 공정 중 추가적인 기계 가공 및 비용이 들며 이에 따라생산성이 떨어지는 단점이 있었다. 따라서 본 연구논문에서는 차량용 충격흡수 부품 제작에있어 추가적인 가공 및 공정 수를 줄일 수 있는 Y-프로세스라는 주조공법을 적용하여 Net 형상 Al Foam재를 제작하였다. Y-프로세스는 Al Foam 금속 용탕이 주형에 투하되었을 때 Net 형상의 주형을 용탕 내 삽입하여 금속 용탕의 발포 및 응고시 Net 형상을따라 발포 및 응고가 되도록 하여 Net 형상의 Al Foam이삽입된 부품을 만드는 공법을 말한다. Y-프로세스로제조된 Al Foam재는 주형 내 완전히 충진되지는 못하였으나 주형내 충진된 Al Foam재의 상하부 셀크기가 비교적 균일한 모습을 나타내어 향후 공정제어를 통해 우수한 품질의 Net 형상 Al Foam 제조가 가능함을 알 수있었다.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.42 no.1
• /
• pp.83-88
• /
• 2009

The purpose of this paper is to obtain the fundamental data on the catch fluctuation in the pound set net according to the tide age from the catch recorded from the year 1997 to 2004 in the coastal waters of Guideok, Jeju. Total catch by the pound set net had a little connection with the tide age. During increasing tide, total catch were reduced slightly from the neap tide to the high tide while there seemed to be a little sign of rise in the total catch until decreasing tide. But in the relation between the catches and the tide age, the level of the correlation coefficient chosen at $p{\le}0.05$ was not significant. Therefore, the catch of the pound set net seemed not to be influenced by the tide age. In addition, CPUE at the high tide was higher than that at the neap tide. When the catch per operating frequency was graded in the order under 50 kg, 50-100 kg and 100-200 kg, the frequency rate by the pound set net was 38%, 19% and 19%, respectively.

• Annual Conference on Human and Language Technology
• /
• 1995.10a
• /
• pp.164-168
• /
• 1995

SEJONG-NET은 시각 문자패턴의 인식 과정을 설명 할 수 있는 적절한 패러다임을 제공하기 위해 척추동물의 시신경계 구조와 기능을 모방하여 만든 문자인식 모형이다. 초기에는 온라인 한글 인식을 위하여 설계되었으며, 이후 다양한 문자 집합이나 오프라인 한글 문자를 위한 모뎀들이 개발되었다. 현재까지 개발된 여러 SEJONG-NET 모델이 가지고 있는 문제점은 정직성이라고 할 수 있다. 즉, 설계 초기에 고려한 인식 대상 문자 집합과 문자 패턴에 대해서만 인식이 가능하고, 변형된 패턴을 기존의 패턴으로 근사화하여 해석하거나 새로운 패턴에 대하여 그것을 추가 학습하는 것이 불가능하다. 따라서 본 논문은 SEJONG-NET의 이러한 제약점을 해결하여 한글 인식 문제에 일반적으로 적용될 수 있도록 개선하는 것을 목적으로 한다. 이를 위해 상위층에서는 인간이 가지고 있는 문자에 대한 구조적인 지식을 표현하고 학습을 통해 추가적으로 습득할 수 있는 형태로 구현하였고, 하위층에서는 상위층에서 쓰이는 구조적인 지식을 표현하는데 적합한 특징을 추출해 낼 수 있도록 구현하였다. 특히 하위층에서는 인간의 초기 시각 피질에서 감지되는 특징들을 추출하도록 구현하여 사용되는 특징이 일반성을 가질 수 있도록 하였다. 이러한 방법을 기반으로 하여 본 논문에서는 변형된 패턴에 대한 적응 학습 능력을 가지며 인지과학적인 사실에 보다 충실하도록 개선된, 온라인 한글 인식을 위한 SEJONG-NET 모델을 제안한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.5
• /
• pp.728-733
• /
• 2018

Deep learning has been actively studied for predicting protein secondary structure based only on the sequence information of the amino acids constituting the protein. In this paper, we compared the performances of the convolutional neural networks of various structures to predict the protein secondary structure. To investigate the optimal depth of the layer of neural network for the prediction of protein secondary structure, the performance according to the number of layers was investigated. We also applied the structure of GoogLeNet and ResNet which constitute building blocks of many image classification methods. These methods extract various features from input data, and smooth the gradient transmission in the learning process even using the deep layer. These architectures of convolutional neural networks were modified to suit the characteristics of protein data to improve performance.

• Journal of the Korean Society for Advanced Composite Structures
• /
• v.6 no.3
• /
• pp.8-13
• /
• 2015

This study investigates the application of a synthetic resine based net-hose system to sustain vegetated embankment slope reinforcement. The net-hose system is designated to improve water supply to the vegetation that can suffer the lack of water in case of extreme drying condition or rock slope where water supply is relatively insufficient to ensure the growth of vegetation. A series of laboratory tests were conducted to check the structural adequacy and effectiveness of net-hose system. The results indicated that the model slope equipped with net-hose system seemed to provide better water supply resulting in more vegetated areas and higher matric suction due to active water uptake capacity, which might be contributed to greater shear strength of slope surface. A limited numerical analysis was conducted to verify the effect of water uptake on vegetated root system that generally yields better slope stability.

• Journal of Bio-Environment Control
• /
• v.5 no.2
• /
• pp.167-173
• /
• 1996

Laser distance meter and x-y robot employed in the extraction of three dimensional image recognition of muskmelon net and recognized the characteristics of that. All data measured transmitted to the PC/AT in the computer room and programmed with Visual Basic(Microsoft). Alteration of the concentration and application time of nutrient solution modified the net height and width of hydroponically grown muskmelon. Net height and width which are the characteristics of muskmelon depended on the concentration of nutrient solution used. Decreasing with the concentration of nutrient solution lowered the occupying ratio of net and also observed the tendency of widening of muskmelon net.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.9 no.3
• /
• pp.76-81
• /
• 2006

The reinforcement of soil shear strength by nylon net as substitute materials simulating a fine root system was evaluated by soil strength parameters(apparent cohesion(c) and internal friction angle(tan${\phi}$), using simple shear tester which clearly depicts shear deformation and controls soil suction. And the results of shear test by using bamboo as a substitute materials simulating a main root system and using nylon net as a substitute materials simulating a fine root system were compared. The reinforcement of soil strength by nylon net are expressed by apparent cohesion more than internal friction angle. In addition the increment of apparent cohesion by nylon net reached a peak in suction 60 $cmH_2O$. Different from with bamboo, the possibility of the change on internal friction angle(tan${\phi}$) caused by the soil water condition was shown in shear strain 20% condition. These results show that the mechanism of reinforcement by substitute materials simulating root system may be different in the condition of various soil water content.