• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.2
• /
• pp.105-112
• /
• 2014

The International Maritime Organization has determined that more than 80% of maritime accidents are caused by human error. A variety of methods have been considered to reduce maritime accidents caused by such human error. Navigators operate by observing surrounding maritime situations and analyzing information using various navigational devices. This study proposes a system to ensure safe navigation by assisting navigators through the delivery of maritime safety information (MSI) between land and sea. In the future, supplementing the system through long-term on-the-ship tests is necessary by defining MSI in relation to maritime service portfolio regions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.394-399
• /
• 2005

현재 선박에서 항해사에게 항로정보를 제공하는 장비는 ECDIS와 GPS 플로터가 많이 사용되고 있으나 자동항로생성 및 항로설명기능이 없어 숙련된. 항해사만 사용할 구 있는 문제가 있으며, 특히 종이해도의 대체 시스템인 ECDIS에 사용되는 ENC를 이용한 자동항로생성 및 항로 설명에 관한 연구는 없는 실정이다. ENC는 IHO에서 정의한 S-52, S-57 표준포멧을 기반으로 제작된다. 본 논문에서는 ENC의 해도데이터와 GPS의 위치데이터, Anemometer의 풍향$\cdot$풍속데이터, 조류데이터를 이용하여 현 위치에서 목적지까지의 최적항로를 설계하여 안내해주는 통합형 항해가이딩시스템(INGS)을 구축하여 그 유효성을 확인하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.5
• /
• pp.139-146
• /
• 2008

Wireless sensor network-related application system can perform functions such as environmental pollution monitoring, building control, home automation in future. In this paper, we present wireless sensor network based system for subway station in order to reduce the damage of the people and the subway station due to fire. Sensor nodes in this system can sense temperature, illumination, smoke, and human body in real time and detect the accident in the subway station. These real-time sensing and wireless networking minimize casualties and damage to property.

• Proceedings of the SAREK Conference
• /
• 2007.06a
• /
• pp.103-103
• /
• 2007

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.49-52
• /
• 2011

• Journal of the Korea Institute of Building Construction
• /
• v.4 no.3
• /
• pp.125-131
• /
• 2004

Nowadays, it seems we are in the high time of construction design because development of construction technology widen the option of construction exterior closing materials and deepen the high-tech construction method with all various materials. When we see the flow of construction market, the mainstream is the high-rise intelligent building, which makes the best use of the small midtown area efficently. Therefore, Alum curtain wall is becoming the main material of exterior construction, the concept of which is changing from just a simple window frame to an outer wall which has comprehensive function and capability. As we think of the importance of Curtain wall as a comprehensive outer wall, We should do thorough technical examination and verification at the stage of construction design and plan of carrying out construction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.7
• /
• pp.1479-1484
• /
• 2005

This paper represents an intelligent sensor controller of mobile robot for object recognition in an indoor hon environment. A range finder sensor module has been developed by using optic PSD (Position Sensitive Detector) sensor way at a low Vice. While PSD sensor is cost effective and light weighting, it has switching noise and white noise. To remove these noises, we propose a heuristic filter. For line-based map building. also we prorosed advanced Hough transformation and navigation algorithm. Some experiments were illustrated for the validity of the developed system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.330-336
• /
• 2005

Existing Bayesian update method using ultrasonic sensors only for mobile robot map building has a problem of the quality of map being degraded in the wall with irregularity, which is caused by the wide beam distribution. For improving this problem, an infrared sensors aided map building method is presented in this paper. Information of obstacle at each region in ultrasonic sensor beam is acquired using the infrared sensors and the information is used to get the confidence of ultrasonic sensor information via fuzzy inference system and genetic algorithm. Combining the resulting confidence with the result of Bayesian update method, an improve map is constructed. The proposed method showed good results in the simulations and experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.191-194
• /
• 2005

This paper represents an intelligent sensor controller of mobile robot for object recognition in an indoor known environment. A range finder sensor module has been developed by using optic PSD (Position Sensitive Detector) sensor array at a low price. While PSD sensor is cost effective and light weighting, it has switching noise and while noise. To remove these noises, we propose a heuristic filter. For line-based map building, also we proposed advanced Hough transformation and navigation algorism. Some experiments were illustrated for the validity of the developed system.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.30-33
• /
• 2001

The number of hidden neurons of the feed-forward neural networks is generally decided on the basis of experience. The method usually results in the lack or redundancy of hidden neurons, and causes the shortage of capacity for storing information of learning overmuch. This research proposes a new method for optimizing the number of hidden neurons bases on information entropy, Firstly, an initial neural network with enough hidden neurons should be trained by a set of training samples. Second, the activation values of hidden neurons should be calculated by inputting the training samples that can be identified correctly by the trained neural network. Third, all kinds of partitions should be tried and its information gain should be calculated, and then a decision-tree correctly dividing the whole sample space can be constructed. Finally, the important and related hidden neurons that are included in the tree can be found by searching the whole tree, and other redundant hidden neurons can be deleted. Thus, the number of hidden neurons can be decided. In the case of building a neural network with the best number of hidden units for tea quality evaluation, the proposed method is applied. And the result shows that the method is effective