• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.287-290
• /
• 2000

In this paper we have presented approach to automatic the direction feature vectors detection, which detects the ridge line directly in gray scale images. In spite of a greater conceptual complexity, we have shown that our technique has less computational complexity than the complexity of the techniques which require binarization and thinning. Afterwards a various direction feature vectors is changed four direction feature vectors. In this paper used matching method is four direction feature vectors based matching. This four direction feature vectors consist feature patterns in fingerprint images. This feature patterns were used for identification of individuals inputed multilayer Neural Networks(NN) which has capability of excellent pattern identification.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.652-655
• /
• 2017

As maritime information and communication technology has been developing and the demands for various kinds of application services has been increasing nowadays, the multi-band maritime networks combining available multiple radio networks has been introduced. We have previously proposed a multi-band network selection(MNS) system which operates in the middleware layer and selects the best available network seamlessly. In this paper we develop MNS server software, network interfaces, and application program. The functionalities of the MNS system, including updating network status, connecting to heterogeneous networks, and communicating in the best network are also verified via indoor test.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.170-171
• /
• 2022

A ship's maneuvering motion model is important in a computer simulation, especially under the trend of intelligent navigation. This model is usually constructed by the hydrodynamic parameters of the ship which are generated by the principles of hydrodynamics. Ship's motion model is a nonlinear function. By using this function, ships' motion elements can be calculated, then the ship's trajectory can be predicted. Deeping neural networks can construct any linear or non-linear equation theoretically if there have enough and sufficient training data. This study constructs some kinds of deep Networks and trains this network by real ship motion data, and chooses the best one of the networks, uses real data to train it, then uses it to predict the ship's trajectory, getting some conclusions and experiences.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.4
• /
• pp.676-682
• /
• 2018

In wireless sensor networks, we propose an optimization algorithm in order to minimize the consumed energy of nodes for maritime search and rescue. In the marine environment, search and rescue operations are mainly performed on the surveillance side and passively on the rescued side. A self-configurable wireless sensor network can build a system that can send rescue signals in the operations. A simulated annealing algorithm is proposed to minimize the consumed energy of nodes in the networks with many nodes. As the density of nodes becomes higher, the algorithmic computation will increase highly. To search the good result in a proper execution time, the proposed algorithm proposes a new neighborhood generating operation and improves the efficiency of the algorithm. The proposed algorithm was evaluated in terms of the consumed energy of the nodes and algorithm execution time, and the proposed algorithm performed better than other optimization algorithms in the performance results.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.383-384
• /
• 2022

Gas Combustion Unit (GCU) onboard liquefied natural gas carriers handles boil-off to stabilize tank pressure. There are many factors for LNG cargo operators to take into consideration to determine whether to use GCU or not. Gas consumption of main engine and re-liquefied gas through the Partial Re-Liquefaction System (PRS) are good examples of these factors. Human gas operators have decided the operation so far. In this paper, some deep learning neural network models were developed to provide human gas operators with a decision support system. The models consider various factors specially into GCU operation. A deep learning model with Sigmoid activation functions in input layer and hidden layers made the best performance among eight different deep learning models.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.539-544
• /
• 1998

Generally, welding gap is a serious factor of a falling-off in weld quality among various kind of weld defect. Welding gap is created between two work piece in GMAW(Gas Metal Arc Welding) of horizontal fillet weld because surface of workpiece is not flat by cutting process. In these days, there were many attempts to detect welding gap. though we prevalently use the vision sensor or arc sensor in welding process, it is difficult to detect welding gap for improvement of welding quality. But we have a trouble to find relationship between welding gap and many welding parameters due to non-linearity of welding process. As mentioned about the various difficult problem, we can detect welding gap precisely using neural networks which are able to model non-linear function. Also, this paper was proposed real-time monitoring of weld bead shape to find effect of welding gap and to estimate weld quality. Monitoring of weld bead shape examined the correlation of welding parameters with bead eometry using learning ability of neural networks. Finally, the developed system, welding gap detecting system and bead shape monitoring system, is expected to the successful capability of automation of welding process by result of simulation.

• Journal of Advanced Marine Engineering and Technology
• /
• v.36 no.6
• /
• pp.823-829
• /
• 2012

Data communications networks at sea in the future can be modelled by overlapped MANET networks with Broadband Wireless Access carriers. A novel routing scheme (CPLR) is proposed in this paper, which finds out an optimal route by selecting an optimal carrier for each hop in routes based on carrier preferences of each application, and locations of ships as well. As distances between each ships and destination ships are considered in this scheme, routing can be done much faster. Performance is compared with that of the CPR (only Carrier Preference-based Routing Scheme), and it shows some improvements.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2017.11a
• /
• pp.50-53
• /
• 2017

Not only growth of importance to understanding economic trends, but also the prediction to overcome the uncertainty is coming up for long-term maritime recession. This paper discussed about the prediction of BDI with artificial neural networks (ANN). ANN is one of emerging applications that can be the finest solution to the knotty problems that may not easy to achieve by humankind. Proposed a prediction by implementing neural networks that have recurrent architecture which are a Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). And for the reason of comparison, trained Multi Layer Perceptron (MLP) from 2009.04.01 to 2017.07.31. Also made a comparison with conventional statistics, prediction tools; ARIMA. As a result, recurrent net, especially RNN outperformed and also could discover the applicability of LSTM to specific time-series (BDI).

• Journal of Advanced Marine Engineering and Technology
• /
• v.34 no.8
• /
• pp.1145-1152
• /
• 2010

Currently economical communication technologies are needed for high speed data exchange at sea. Wireless environments at sea require some special communication security solutions as well. In this paper, an augmented WiMAX MMR protocol is proposed as a solution of the broadband data communications and security at sea environments fundamentally with no base station.

• Journal of Navigation and Port Research
• /
• v.42 no.5
• /
• pp.341-346
• /
• 2018

Supramax bulk carriers cover a wide range of ocean transportation requirements, from major to minor bulk cargoes. Market forecasting for this segment has posed a challenge to researchers, due to complexity involved, on the demand side of the forecasting model. This paper addresses this issue by using technical indicators as input features, instead of complicated supply-demand variables. Artificial neural networks (ANN), one of the most popular machine-learning tools, were used to replace classical time-series models. Results revealed that ANN outperformed the benchmark binomial logistic regression model, and predicted direction of the spot market with more than 70% accuracy. Results obtained in this paper, can enable chartering desks to make better short-term chartering decisions.