• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.303-310
• /
• 2007

Named Entity Recognition (NER) is always limited by its lower recall resulting from the asymmetric data distribution where the NONE class dominates the entity classes. This paper presents an approach that exploits non-local information to improve the NER recall. Several kinds of non-local features encoding entity token occurrence, entity boundary and entity class are explored under Conditional Random Fields (CRFs) framework. Experiments on SIGHAN 2006 MSRA (CityU) corpus indicate that non-local features can effectively enhance the recall of the state-of-the-art NER systems. Incorporating the non-local features into the NER systems using local features alone, our best system achieves a 23.56% (25.26%) relative error reduction on the recall and 17.10% (11.36%) relative error reduction on the F1 score; the improved F1 score 89.38% (90.09%) is significantly superior to the best NER system with F1 of 86.51% (89.03%) participated in the closed track.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.3
• /
• pp.217-223
• /
• 2014

With precise sensor position, attitude element, and imaging resolution, a simulated geospatial image can be generated. In this study, a satellite image is simulated using SPOT ortho-image and global elevation data, and the geometric similarity between original and simulated images is analyzed. Using a SPOT panchromatic image and high-density elevation data from a 1/5K digital topographic map data an ortho-image with 10-meter resolution was produced. The simulated image was then generated by exterior orientation parameters and global elevation data (SRTM1, GDEM2). Experimental results showed that (1) the agreement of the image simulation between pixel location from the SRTM1/GDEM2 and high-resolution elevation data is above 99% within one pixel; (2) SRTM1 is closer than GDEM2 to high-resolution elevation data; (3) the location of error occurrence is caused by the elevation difference of topographical objects between high-density elevation data generated from the Digital Terrain Model (DTM) and Digital Surface Model (DSM)-based global elevation data. Error occurrences were typically found at river boundaries, in urban areas, and in forests. In conclusion, this study showed that global elevation data are of practical use in generating simulated images with 10-meter resolution.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.1897-1902
• /
• 2008

The computer system is used in many application domains and any system error in these domains may either cause critical loss or threaten environment or human life. Though examples of these domains can be found in many areas, the system, which is used in domains for carrying passengers including rolling stocks in particular, is expected to show satisfactory operation all the time. The relay control logic, which is used in rolling stocks, is complex in hardware and occupies considerably large volume. Nevertheless, it has been used for a long time, to let the system safely operate even in the occurrence of an error in the computer system. However, the relay control logic circuit is so complex that the analysis of proper circuit operation and interlocking tends to be dependent only on the designer's experiences instead of being systematically performed. Especially, the analysis following a change, addition and deletion of a previous circuit according to the requirements from a source of demand is significantly limited. In this paper, the accuracy of relay control logic is verified by the use of properties of Petri Net model. In addition, how main circuit breaker (MCB) control circuit is modeled and analyzed by the design methodology is shown.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.9
• /
• pp.349-357
• /
• 2003

Because of capacity of the electric power equipment grew larger and the electric power system was complicated, it was required a protocol to process data without the errors in order to supply the high quality and stable electric power. However, HDLC and TCP/IP communication protocol using between Seoul EMS and Kwangju RCC (or between RCC and SCC) is decreasing reliability by the delay of speed and the occurrence of errors. In this paper, we applied ICCP(Inter-Control Center Communication Protocol) communication protocol in order to improve them and implemented an electric power communication system for remote control of the electric power equipment. Also, we modified program for error correction and implemented the system using the most suitable BLT. The errors were more decreased in case of ICCP protocol than HDLC protocol and TCP/IP protocol applied to the electric power communication system.

• Journal of Magnetics
• /
• v.22 no.1
• /
• pp.34-42
• /
• 2017

Material defects in the Steam Generator Tubes (SGT) of sodium cooled fast breeder reactor (PFBR) can lead to leakage of water into sodium. The water and sodium reaction will lead to major accidents. Therefore, the examination of steam generator tubes for the early detection of defects is an important requirement for safety and economic considerations. In this work, the Magnetic Flux Leakage (MFL) based Non Destructive Testing (NDT) technique is used to perform the defect detection process. The rectangular notch defects on the outer surface of steam generator tubes are modeled using COMSOL multiphysics 4.3a software. The obtained MFL images are de-noised to improve the integrity of flaw related information. Grey Level Co-occurrence Matrix (GLCM) features are extracted from MFL images and taken as input parameter to train the neural network. A comparative study on characterization have been carried out using feed-forward back propagation (FFBP) and cascade-forward back propagation (CFBP) algorithms. The results of both algorithms are evaluated with Mean Square Error (MSE) as a prediction performance measure. The average percentage error for length, depth and width are also computed. The result shows that the feed-forward back propagation network model performs better in characterizing the defects.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.12 no.7
• /
• pp.1115-1121
• /
• 2001

In this paper, we analyzed the performance of GFSK system that presence fading effect in indoor radio communication environments and impulsive electromagnetic noise from electronic equipments then we applied the Truncated Type- II Hybrid ARQ scheme to make satisfied in data transmission service. As a result, the system was influenced by fading and impulsive electromagnetic noise. Especially, the system was much degraded by high occurrence frequency and amplitude of impulsive electromagnetic noise than fading which has direct frequency. By adopting the Truncated Type-II hybrid ARQ technique we can also obtained the performance improvement in the low signal power(20 dB) arid over 24 dB in strong impulsive electromagnetic noise environment which is occurred error floor and terribly influenced by the system.

• Computers and Concrete
• /
• v.20 no.6
• /
• pp.719-729
• /
• 2017

A considerable research is available on the seismic response of Reinforced Concrete (RC) shear wall-frame buildings, but the studies on the reliability of such buildings, with the consideration of human error, are limited. In the present study, a detailed procedure for reliability assessment of RC shear wall-frame building subjected to earthquake loading against serviceability limit state is presented. Monte Carlo simulation was used for the reliability assessment. The procedure was implemented on a 10-story RC building to demonstrate that the shear walls improve the reliability substantially. The annual and life-time failure probabilities of the studied building were estimated by employing the information of the annual probability of earthquake occurrence and the design life of the building. A simple risk-based cost assessment procedure that relates both the structural life-time failure probability and the target reliability with the total cost of the building was then presented. The structural failure probability (i.e., the probability of exceeding the allowable drift) considering human errors was also studied. It was observed that human error in the estimation of total load and/or concrete strength changes the reliability sharply.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.6
• /
• pp.345-354
• /
• 2018

It is conservative to say that lots of research is performed as measures to use UAV for application to the rapid spatial information and its application is faced with settlement stage to some extent. In addition, Korea Land and Geospatial Informatix Corporation autonomously produces work regulation which is applied to every kind of orders and National Geographic Information Institute (2018) has notified public surveying work instructions about unmanned aerial device for the rapid spatial information construction. The results acquired by UAV are comprised of contents about accuracy improvements for the orthophoto when reviewing pertinent regulations. The results acquired by UAV are comprised of contents about accuracy improvements for the orthophoto when reviewing pertinent regulations. As a result, it is known that error amount has been sharply increased from 400m separation distance, and this study proposes that cross flight is able to reduce irregular error occurrence as measures to acquire stable results.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.3
• /
• pp.183-190
• /
• 2021

Tomographic particle image velocimetry (PIV) is a widely used method that measures a three-dimensional (3D) flow field by reconstructing camera images into voxel images. In 3D measurements, the setting and calibration of the camera's mapping function significantly impact the obtained results. In this study, a camera self-calibration technique is applied to tomographic PIV to reduce the occurrence of errors arising from such functions. The measured 3D particles are superimposed on the image to create a disparity map. Camera self-calibration is performed by reflecting the error of the disparity map to the center value of the particles. Vortex ring synthetic images are generated and the developed algorithm is applied. The optimal result is obtained by applying self-calibration once when the center error is less than 1 pixel and by applying self-calibration 2-3 times when it was more than 1 pixel; the maximum recovery ratio is 96%. Further self-correlation did not improve the results. The algorithm is evaluated by performing an actual rotational flow experiment, and the optimal result was obtained when self-calibration was applied once, as shown in the virtual image result. Therefore, the developed algorithm is expected to be utilized for the performance improvement of 3D flow measurements.

• Journal of Navigation and Port Research
• /
• v.42 no.3
• /
• pp.159-166
• /
• 2018

The identification of behavioral errors by seafarers that have caused marine accidents may provide important clues for the reduction or prevention of marine accidents. The purpose of this study is to identify the behavioral errors of seafarers by the type of marine accident using the theory of Skill-, Rule-, and Knowledge-Based Behavior (SRKBB). In order to identify behavioral errors, we collected the information related to 1,744 cases of maritime accidents over a 9 year period (2008 ~ 2016). The behavior errors of the seafarers who caused the marine accidents were classified as SBBE (Skill-Based Behavioral Error), RBBE (Rule-Based Behavioral Error), and KBBE (Knowledge-Based Behavioral Error). After analyzing the frequency of behavioral errors according to the type of marine accident, results showed SBBE had the highest frequency of errors, followed by RBBE. Additionally, the frequency of occurrence of accidents such as stranding, overturning, and sinking was high in KBBE. This study showed it is possible to identify behavioral errors of seafarers according to the type of marine accidents.