• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.107-109
• /
• 2003

Optical sensor-based land cover categories produce spectral signature confusion along with degraded classification accuracy. In the classification tasks, the goal of fusing data from different sensors is to reduce the classification error rate obtained by single source classification. This paper describes the result of land cover/land use classification derived from solely of Landsat TM (TM) and multisensor image fusion between JERS 1 SAR (JERS) and TM data. The best radar data manipulation is fused with TM through various techniques. Classification results are relatively good. The highest Kappa Coefficient is derived from classification using principal component analysis-high pass filtering (PCA+HPF) technique with the Overall Accuracy significantly high.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.5
• /
• pp.1347-1354
• /
• 1994

This paper deals with the experimental research, including measurement and analysis and field survey, on the causes of occurring noise defective gear boxes in hoist production plant in order to reduce the fraction of their occurrence. In this reserch following investigations are performed : measurement and gear-boxes, examination of each machining process of production, measurement and analysis of dimensional accuracy of each part, comparative vibration test with exchanging inaccurate parts. From these investigations, it is found that the machining accuracy of pinion gear tooth thickness is the most sensitive factor of noise problem. By maintaining the tooth thickness error within 0.05 mm tolerance in the gear cutting process, the fraction of noise defective gear-boxes are greatly reduced to less than 2%, where the usual rate of it has been 20-50%.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.8 no.1
• /
• pp.45-51
• /
• 1999

Thermal expansion of the ball screw can directly affect the accuracy of positioning along the travel axis in the semi-closed loop type CNC Lathe. In this paper, use of MACRO variables can make the thermal displacement of the ball screw estimated. Also, the estimated displacements of the ball screw are controlled by calculating the interval of pitch error rate in the Numerical Control(NC). Under the constant operating conditions, the thermal expansion of the ball screw was measured to confirm the effectiveness of the compensation method in the CNC Lathe. By using this method the results show that the thermal displacement of the ball screw could be reduced to 20% compared with ordinary method.

• Journal of Multimedia Information System
• /
• v.7 no.3
• /
• pp.205-214
• /
• 2020

Crime has become one of the major problems in modern society. Even though visual surveillances through closed-circuit television (CCTV) is extensively used for solving crime, the number of crimes has not decreased. This is because there is insufficient workforce for performing 24-hour surveillance. In addition, CCTV surveillance by humans is not efficient for detecting dangerous situations owing to accuracy issues. In this paper, we propose the autonomous detection of dangerous situations in CCTV scenes using a deep learning model with relational inference. The main feature of the proposed method is that it can simultaneously perform object detection and relational inference to determine the danger of the situations captured by CCTV. This enables us to efficiently classify dangerous situations by inferring the relationship between detected objects (i.e., distance and position). Experimental results demonstrate that the proposed method outperforms existing methods in terms of the accuracy of image classification and the false alarm rate even when object detection accuracy is low.

• International Journal of Contents
• /
• v.9 no.1
• /
• pp.38-41
• /
• 2013

The clamp meter maintains electric safety as a non-invasive method while measuring the absolute value of tube current with it has been recently developed for an X-ray high-tension cable. Especially this can show high accuracy at short X-ray exposure time. Considering such a condition, this study is to evaluate the feasibility of a clamp meter in measuring X-ray tube current by taking the measurements and comparing with those of the Dynalyzer III which has been considered as a standard measuring device. From measuring the tube current accuracy depending on changes in tube voltage and exposure time, the clamp meter showed higher accuracy rate which was -1.3~4.2% difference. Thus clamp meter can be used for clinical radiologists who are not familiar electric circuit to manage X-ray devices easily and correctly in the future.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.363-366
• /
• 2003

The hard turning is a turning operation performed in high strength alloy steels (HRC>30) in order to reach surface roughness close to those obtained in grinding. This is possible because of availability of improved tool materials (polycrystalline cubic boron nitride. PCBN), ad more rigid machine tools. According to many previous work of hard turning mechanism, the maximum temperature of cutting can be raised up to 100$0^{\circ}C$. As the heat generation rate is very high, the thermal displacement of tool holder cannot be negligible. Therefore, the aim of this paper is to analyze effects of high heat generation at CBN tool tip to the thermal displacement of a tool holder in hard turning and finally geometric accuracy. The thermal behavior of a CBN tool holder is investigated by numerical simulation and experiment, and the result shows thermal elongation of microns order is possible during hard turning process.

• Journal of Chest Surgery
• /
• v.28 no.1
• /
• pp.37-41
• /
• 1995

To determine the role of mediastinoscopy in the preoperative staging of the primary lung cancer, we studied 23 patients from January 1993 to December 1993 and compared the results of mediastinoscopy and computed tomographic scanning with the findings at thoracotomy. Mediastinoscopy was performed in 14 patients when they had larger than 10mm mediastinal nodes at computed tomographic scanning. Six of them were found to have metastatic nodes. Nine patients, who had negative computed tomographic scanning and negative mediastinoscopic results,underwent thoracotomy. One of them was found to have a metastatic mediastinal lymph node. When results from both series of patients were compared, the sensitivity and specificity of computed tomographic scanning showed 83.3% and 47.1% respectively with an accuracy of 56.5%. The results of mediastinoscopy showed that the sensitivity was 85.7%, the specificity was 100% and the accuracy was 95.7%.Because of the low accuracy rate of computed tomographic scanning, a more routine use of mediastinoscopy seems to be justified.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.10B
• /
• pp.1813-1820
• /
• 2000

In this paper we proposed an efficient multiresolution motion estimation(MRME) algorithm using half-pixel accuracy motion estimation (HPAME) and characteristics of motion vectors in the baseband. Conventional MRME method needs exact motion vectors in the baseband because those are used as initial motion vectors in higher frequency subbands. Therefore the proposed method uses HPAME to estimate the motion vectors exactly in the baseband. Based on the characteristics of these motion vectors the motion vectors in the higher frequency subbands are selectively estimatied. That is motion vectors in the higher frequency subbands are estimated only for the blocks which have the half-pixel accuracy motion vectors in the baseband. In the proposed method by using HPAME in the baseband and selective motion estimation in the higher frequency subbands we can obtain reconstructed image with the similar quality with the conventional method though we reduce the computational complexity and the bit rate considerably.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.3
• /
• pp.107-113
• /
• 2011

An OFDMA(Orthogonal Frequency Division Multiple Access) includes a MIMO(Multi-Input Multi-Output) scheme for improving spectral efficiency and data throughput. Recognizing that the performance of MIMO system is heavily dependent upon the accuracy of channel estimation, we propose a novel channel estimation for the MIMO scheme based on OFDMA. Conventional interpolation-based channel estimation suffers from poor estimation error at specific subcarriers. Proposed scheme makes use of a planar interpolation instead of linear interpolation for those subcarriers of bad accuracy. Simulation results show that the proposed scheme improves the performance of MIMO system by improving the accuracy in channel estimation especially for the adverse subcarrier positions. It is observed that the proposed scheme outperforms the conventional method by about 2dB in terms of both mean squared error and overall bit error rate with a reasonable computational complexity.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.9
• /
• pp.37-43
• /
• 2016

This paper introduces a method for video shot group detection needed for efficient management and summary of video. The proposed method detects shots based on low-level visual properties and performs temporal and spatial clustering based on visual similarity of neighboring shots. Shot groups created from temporal clustering are further clustered into small groups with respect to visual similarity. A set of representative shot frames are selected from each cluster of the smaller groups representing a scene. Shots excluded from temporal clustering are also clustered into groups from which representative shot frames are selected. A number of video clips are collected and applied to the method for accuracy of shot group detection. We achieved 91% of accuracy of the method for shot group detection. The number of representative shot frames is reduced to 1/3 of the total shot frames. The experiment also shows the inverse relationship between accuracy and compression rate.