• Journal of Environmental Impact Assessment
• /
• v.12 no.4
• /
• pp.271-279
• /
• 2003

Temperature and humidity forecasting have been performed using artificial neural networks model(ANN). We composed ANN with multi-layer perceptron which is 2 input layers, 2 hidden layers and 1 output layer. Back propagation algorithm was used to train the ANN. 6 nodes and 12 nodes in the middle layers were appropriate to the temperature model for training. And 9 nodes and 6 nodes were also appropriate to the humidity model respectively. 90% of the all data was used learning set, and the extra 10% was used to model verification. In the case of temperature, average temperature before 15 minute and humidity at present constituted input layer, and temperature at present constituted out-layer and humidity model was vice versa. The sensitivity analysis revealed that previous value data contributed to forecasting target value than the other variable. Temperature was pseudo-linearly related to the previous 15 minute average value. We confirmed that ANN with multi-layer perceptron could support pollutant dispersion model by computing meterological data at real time.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.26 no.3
• /
• pp.22-31
• /
• 2022

Existing Finocyl grain designs assume configurations and repeat the process of configuration modification and confirmation of the requirements through burn-back analysis. Such a design increases the design fatigue of workers and has a problem of different design completeness depending on capabilities. Therefore, this study devised an optimal design method that applied genetic algorithms to the Burn-back automation analysis program to solve the problem of existing design. For stable search, variable-offset and non-drawable configuration control techniques were developed. The program performance was verified through the searching neutral and double thrust grains.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.06a
• /
• pp.31-32
• /
• 2014

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.10a
• /
• pp.254-259
• /
• 1998

오늘날 컨테이너의 과다한 물동량 증가로 인하여 수작업으로 이루어지는 컨테이너 식별자를 처리하는데 어려움을 겪고 있는 가운데, 이를 자동으로 인식하고 그 결과를 항만 물류 처리 자동화 시스템에 적용하고자 하는 필요성이 대두되고 있다. 이에 본 논문에서는 컨테이너의 인식 처리를 자동화하기 위한 방안으로 컨테이너의 식별자 인식에 신경망 알고리즘의 하나인 Back-propagation을 적용하였으며, BP 알고리즘을 적용하기 위해서 적절한 scaling 비율을 구하고, 학습 DB를 구축하여 기존의 식별자 인식보다 신속하고 정확한 처리가 가능하도록 구현하였다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.12
• /
• pp.116-124
• /
• 2003

According to the convenience and efficiency, IEEE 802.11 WLAN(Wireless LAN) has became rapidly wide-spread on the market. However, QoS support is needed for various multimedia service. In this paper, we consider both MAC method of IEEE 802.11 and IEEE 802.11e and Traffic Category differentiated service by QoS support method. In addition, we study currently existing back-off algorithms in view of comparative analysis. As a result we propose a new back-off algorithm called Collision Rate Based-EDCF. The proposed back-off algorithm confirms the performance by computer simulations in terms of Throughput, and QoS support.

• Journal of electromagnetic engineering and science
• /
• v.9 no.4
• /
• pp.223-228
• /
• 2009

In this paper, a quadrafilar antenna is designed to have a lower profile as an essential part of the size reduction technique and lower back radiation(i.e. higher forward radiation) for the S-band telemetry/telecommand(TM/TC) function of a communication satellite. Particularly, to meet the challenging requirements on the higher isolation between the TM/TC antennas and simultaneously a smaller size, the lowest back radiation and lowest cross-polarization, the optimal physical dimensions of the quadrafilar antenna are found by using the Genetic Algorithm(GA). To prove the validity of the proposed antenna design, its 3D electromagnetic analysis and measured results are compared, showing good agreement.

• Journal of Mechanical Science and Technology
• /
• v.20 no.11
• /
• pp.1873-1880
• /
• 2006

The results of this study suggest the use of a Back Propagation Network (BPN) algorithm for the detection of esophageal erosions or abnormalities - which are the important signs of esophagitis - in the analysis of the color and textural aspects of clinical images obtained by endoscopy. The authors have investigated the optimization of the learning condition by the number of neurons in the hidden layer within the structure of the neural network. By optimizing learning parameters, we learned and have validated esophageal erosion images and/or ulcers functioning as the critical diagnostic criteria for esophagitis and associated abnormalities. Validation was established by using twenty clinical images. The success rates for detection of esophagitis during calibration and during validation were 97.91% and 96.83%, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.52-57
• /
• 1993

Conventional active control algorithm for duct system is developed without considering problems of constrained structure. Therefore it destroys the constrained structures of the weights or parameters. A new LMS algorithm, which does keep the constraints, is proposed for systems with known constrained structure. It is based on error-back propagation. The stability analysis and simulation example are also included.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.21 no.1
• /
• pp.74-80
• /
• 2011

Front-back vibrations of high-speed elevator need to be suppressed as in the case of lateral vibrations. The dynamic model for the front-back vibrations is different from the lateral vibration model since the supporting structure varies. In this study, a dynamic model was derived using the energy method. Based on the free vibration analysis, it was observed that the fundamental frequency for the front-back vibration is slightly lower than the fundamental frequency of the lateral vibration, which means that the active vibration control should be carried out in both directions. The PPF control algorithm was applied to the numerical model under measured rail irregularities. The numerical results show that the active vibration control of elevator front-back vibration is also possible.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5B
• /
• pp.247-256
• /
• 2007

In this paper, we propose Geographical Back-off Routing (Geo-Back Routing) protocol for wireless sensor networks. Geo-Back uses the positions of nodes, a packet's destination and a optimal back-off time to make the packet forwarding decisions using only source and destination's location information without information about neighbor nodes' location or the number of one hop neighbor nodes. Under the frequent topology changes in WSNs, the proposed protocol can find optimal next hop location quickly without broadcast algorithm for update. In our analysis, Geo-Back's scalability and better performance is demonstrated on densely deployed wireless sensor networks.