• The Korean Journal of Ecology
• /
• v.8 no.3
• /
• pp.133-140
• /
• 1985

Aboveground net productions of four stands in the coastal salt marsh of Incheon were estimated with three different methods: first method was to measure peak live standing crop; second to measure both live and dead standing crops; thrid to measure live and dead standing crops and dead disappearance as well. Net productions estimated by the first method were lowest with a difference of 28~50% from those by the third method. Whereas estimates by the second method approximated considerably to those by the third method with a difference of 4~15%. The third method figured out the highest values and seemed to be most appropriate in estimating net production of herbaceous community. Form these results it is known that live standing crop, dead standing crop and dead disappearance respectively accounted for about 60, 30, 10% of net production estimated by the third method. Annual net productions estimated by the third method for Suaeda japonica-Salicornia herbacea, Artemisia scoparia-Limonium tetragonum, Calamagrostis epigeios, and Sonchus brachyotus-Setaria viridis stand were 650, 1, 080, 1, 409 and 1, 126 g.$m^{-2}.yr^{-1}$, respectively.

• Proceedings of the Korean Society for Rock Mechanics Conference
• /
• 2001.10a
• /
• pp.115-120
• /
• 2001

In No. 1 tunnel for Kwnagju urban subway construction, net penetration rate of the shield TBM was analyzed. This tunnel of 540 m length is located in soil layers at starting and in hard rocks such as amphibolite and granitic gneiss at ending with 84 m length. The net penetration rate was dropped down to 2∼11 cm/hr in rock while 50∼80 cm/hr in soil. Theoretical penetration rate is analyzed in conditions of machine and rock in order to compare the actual net penetration rate. The relationships between net penetration rate and thrust force is also investigated in this report.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2003.10b
• /
• pp.133-137
• /
• 2003

In this paper presented the net forging technology of planetary gear after much experiment and analysis, technology of two forging processes after billet being one -time heated, and cold net forging was adopted to ensure the gear forming quality. In the process of die producing, electrical rod NC cutting technology was used .the test and application has proved the net forging gear has reached higher quality and met the requirement of design. The net forging gear technology had been put into production.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.933-935
• /
• 1998

The HMM-Net is an architecture for a neural network that implements a hidden markov model (HMM). The architecture is developed for the purpose of combining the discriminant power of neural networks with the time-domain modeling capability of HMMs. Criteria used for learning HMM-Net classifiers are maximum likelihood(ML) and minimization of mean squared error(MMSE). In this paper we propose an efficient learning method of HMM_Net classifiers using a ML-MMSE hybrid criterion and report the results of an experimental study comparing the performance of HMM_Net classifiers trained by the gradient descent algorithm with the above criteria. Experimental results for the isolated numeric digits from /0/ to /9/ show that the performance of the proposed method is better than the others in the repects of learning and recognition rates.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.137-142
• /
• 2006

상황은 단일 사건에 의해 결정되는 경우도 있지만, 많은 경우 일련의 사건이 특정 시간 제약을 만족하면서 발생할 때 상황이 결정된다. 따라서 상황에 대한 추론은 시간 제약 조건 만족 여부와 함께 사건의 발생을 순서를 확인하는 방법으로 수행될 수 있다. 한편, 어떤 상황은 분명하게 정의되는 것이 아니라 애매한 개념을 사용하여 기술되기 때문에, 퍼지 개념을 이용한 상황 기술과 이에 대한 추론이 필요하다. 한편, 유비쿼터스 환경에서와 같이 여러 대상에 대한 상황을 유추하여 서비스를 제공해야 하는 경우에, 대상 간에 동일한 상황이 발생할 수 있기 때문에 이에 대한 고려가 필요하다. 이러한 상황 추론을 위해서 이 논문에서는 Fuzzy Colored Timed Petri net 모델이라는 상황 추론 모델에 대해서 제안한다. 제안한 모델은 Timed Petri net 성질을 이용하여 일련의 사건 발생을 모델링하고, Colored Petri net의 성질을 이용하여 다수 대상에 대한 상황 추론을 허용하며, fuzzy 토큰 개념을 이용하여 애매한 개념을 사용하여 정의된 상황에 대한 추론을 가능하게 한다.

• Journal of information and communication convergence engineering
• /
• v.18 no.3
• /
• pp.167-175
• /
• 2020

The net income per unit area from crop production could be the most critical consideration for agricultural producers during cultivation planning. This paper proposes a scheme for predicting the net income per unit area based on machine learning and related calculations. This scheme predicts rice production and operation costs by applying climate and price index data. The rice price is also predicted by applying rice production and operation cost data. Finally, these predicted results are employed to calculate the predicted net income, which is compared with the actual net income. Consequently, the proposed scheme shows a meaningful degree of conformity, which indicates the potential of machine learning for predicting various aspects of agricultural production.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.60.1-60.1
• /
• 2017

In this study we apply Convolution Neural Network(CNN) to solar flare occurrence prediction with various parameter options using the 00:00 UT MDI images from 1996 to 2010 (total 4962 images). We assume that only X, M and C class flares correspond to "flare occurrence" and the others to "non-flare". We have attempted to look for the best options for the models with two CNN pre-trained models (AlexNet and GoogLeNet), by modifying training images and changing hyper parameters. Our major results from this study are as follows. First, the flare occurrence predictions are relatively good with about 80 % accuracies. Second, both flare prediction models based on AlexNet and GoogLeNet have similar results but AlexNet is faster than GoogLeNet. Third, modifying the training images to reduce the projection effect is not effective. Fourth, skill scores of our flare occurrence model are mostly better than those of the previous models.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.6
• /
• pp.972-981
• /
• 1990

Many researchers have been interested in whether complex computational problems can be solved by the neural net or not. Especially, problems of early vision are integrated by Tikhonov's regularization theory. Regularization technique can be realized in resistive net. In this paper, we suggest the resistive net with upper and lower thresholder to be able to compute shape from shading and to solve its discontinuous problem. We simulate three algorithms-Horn's algorithm, resistive net and up-low thrwsholding net -with respect to three cases-fully boundary, boundary losing partly and noisy image. As being able to cope with crease and discontinuous parts, we get the good 3D shape from shading.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.400-405
• /
• 1990

This paper deals with the design technique of the controller for the discrete system control using Extended Safe Petri Net which is deduced from Petri Net as its subclass with a specific constraint and which is introduced to develop the design and analysis for the discrete systems. First, we propose a construction matrix suitable for the discrete systems that represent the marking flows which are the dynamic behavior of the discrete systems. Next, we develop a method that can design the controller for the discrete system control by analyzing the proposed construction matrix into the incidence matrix of Extended Safe Petri Net. Finally, the validity of the proposed method is shown by using the incidence matrix and matrix equation of Extended Safe Petri Net model.

• Proceedings of the KIPE Conference
• /
• 2006.06a
• /
• pp.308-310
• /
• 2006

DeviceNet은 Rockwell/Allen-Bradley에서 개발된 응용계층으로 CAN(controller area network)을 기반으로 한 저가의 통신 링크이며 단순한 산업용 디바이스(sensors, actuators)와 상위 디바이스(controller)를 연결하는 하위 레벨의 네트워크이다. 본 논문에서는 2대의 전동기를 마스터, 슬레이브 형식으로 실시간 동특성을 만족할 수 있는 동기제어 알고리즘을 개발하고 이를 DeviceNet을 이용하여 실시간으로 제어할수 있는 복수 전동기 구동시스템을 구현하고자 한다. DeviceNet 마스터는 Hilscher사(社)의 DeviceNet Card(CIF50-DNM)를 PC에 장착되어 구현하고 슬레이브는 Atmel사(社)의 AVR칩(AT90CAN128)을 이용하여 설계하였다.