• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.29 no.1
• /
• pp.147-152
• /
• 2005

This paper proposes an evaluates a new approach to detect ships as targets from Radarsat-1 SAR (Synthetic Aperture Radar) imagery in the vicinity of Korean peninsula. To be more specific, a labeling technique and morphological filtering in conjunction with some other methods are employed to automatically detect the ships. From the test, the ships are revealed to be detected. For ground truth data, information from a radar system is used, which allows assessing accuracy of the approach. The results showed that the proposed approach has the high potential in automatically detecting the ships.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.08a
• /
• pp.29-36
• /
• 2004

The paper describes recent experimental results on the development of Digital Magnetic Compass (DMC), which can provide smart automatic correction functions to the magnetic interferences. The design methodology of magnetic sensing circuit with ring-core fluxgate sensor is represented. The performance results of the sensing circuits are discussed with error analysis by polynomial regressions. As test results, the sensing circuit filtered only the second harmonic signal that is proportional to the direction of earth's magnetic field, and it leads to the obtainment of bearing information. In addition, the total residual errors of DMC can be analyzed by the adoption of polynomial regressions. It shown that the possibility of high precise DMC, in the future.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2011.11a
• /
• pp.133-134
• /
• 2011

While researches related with construction automation have dramatically increased, a Robot-based Automatic Construction system (RCA system) has developed for high-rise buildings in Korea. At the aspect that wide adoption of the RCA system is dependent on economic efficiency comparing with a conventional method, feasibility study on the RCA system should be implemented. However, due to practical limitations, the RCA system has tested to a seven story building. Based on the test results, this study implements a cost/benefits analysis to a simulated forty story building in order to derive more reliable data on the RCA system's practicability.

• Proceedings of the KIEE Conference
• /
• 2000.11a
• /
• pp.119-121
• /
• 2000

The possibility of a remote on-line determination of the maximum load rates that are basically set at generation plants is investigated in automatic generation control (AGC) system. Energy management system (EMS) generates a test input to a remote power plant to get the samples of the generator output. Then from the samples it can be attempted to determine an approximate value of the load rate limit set by the operator. It is shown in computer simulation that in actual power plants the limit can be approximately determined from the input-output characteristics of the plants for a unit-step input.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1428-1430
• /
• 1999

The New Distribution Automation System(NDAS) was composed of several equipments, computer system, communication system, feeder remote unit, switches and so on. In this paper, we introduce the conception of hardware and software design about Central Control System, the communication method and protocol in Feeder Remote Unit, the Automatic Switch, the operating software, consideration factors in the feeder automation(FA) and the system configuration of NDAS in power distribution test center.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1027-1028
• /
• 2008

In this paper, we proposed image-processing technique for automatic real-time fire and smoke detection in tunnel fire environment. To minimize false detection of fire in tunnel we used motion information of video sequence. And this makes it possible to detect exact position of event in early stage with detection, test, and verification procedures. In addition, by comparing false detection elimination results of each step, we have proved the validity and efficiency of proposed algorithm.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1047-1048
• /
• 2008

The objective of this paper is to build a decision method of the shape quality for the stainless steel and ensure reducibility of working-load for next rolling process. The criterion of the shape quality is derived from the customer needs, and Automatic Shape Decision System is implemented in SPM (Skin Pass Mill). The methods of shape decision are based on curve fitting and frequency analysis and so on. The Field Test with concerned customers is successful. The performance of right decision is 99% and the claims from the customer have been largely reduced.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.3
• /
• pp.50-59
• /
• 1993

There is basic problem with the current evaluation method for character recognition systems. The current method evaluates the average recognition rate by applying the test data to the target system. The average recognition rate tells no more than and no less than the overall performance and it depends on the data. In this paper we propose a testing method which will analyze the target system and point out its strong points and weak points. This can be made possible through using the data which are generated cy distorting the standard character images according to a carefully controlled manner. This paper will describe how to automatically generate such distorted images. Also we will show the method is actually effective and useful by applying it to evaluating existing recognition algorithms.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.69-77
• /
• 1993

Automatic image recognition system is essential for a better man-to machine interaction. Because of the noise and deformation due to the sensor operation, it is not simple to build an image recognition system even for the fixed images. In this paper neural network which has been reported to be adequate for pattern recognition task is applied to the fixed and variational(rotation, size, position variation for the fixed image)recognition with a hope that the problems of conventional pattern recognition techniques are overcome. At fixed image recognition system. ART model is trained with face images obtained by camera. When recognizing an matching score. In the test when wigilance level 0.6 - 0.8 the system has achievel 100% correct face recognition rate. In the variational image recognition system, 65 invariant moment features sets are taken from thirteen persons. 39 data are taken to train multi-layer perceptron and other 26 data used for testing. The result shows 92.5% recognition rate.

• ETRI Journal
• /
• v.38 no.3
• /
• pp.487-493
• /
• 2016

Two new methods are proposed for an unsupervised adaptation of a language model (LM) with a single sentence for automatic transcription tasks. At the training phase, training documents are clustered by a method known as Latent Dirichlet allocation (LDA), and then a domain-specific LM is trained for each cluster. At the test phase, an adapted LM is presented as a linear mixture of the now trained domain-specific LMs. Unlike previous adaptation methods, the proposed methods fully utilize a trained LDA model for the estimation of weight values, which are then to be assigned to the now trained domain-specific LMs; therefore, the clustering and weight-estimation algorithms of the trained LDA model are reliable. For the continuous speech recognition benchmark tests, the proposed methods outperform other unsupervised LM adaptation methods based on latent semantic analysis, non-negative matrix factorization, and LDA with n-gram counting.