• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1713-1716
• /
• 2012

최근 우리 사회에는 여성과 아동을 대상으로 하는 강력범죄들이 많이 발생하고 있어 개인 위치확인 및 안전에 대한 서비스들이 최근 재조명을 받고 있다. 하지만 서비스가 시작된 기간에 비해 아직도 높은 단말기 가격대와 월 사용료, 그리고 위험상황에서의 사용성은 상대적으로 미약한 발전을 이루었다. 그나마 스마트폰이 많이 보급되어 해당 서비스들의 가격이 조금씩 인하되고, GPS를 활용한 위치정보의 정확도를 개선하는 등 많은 노력을 기울이고 있지만 그 효과는 미비하다. 따라서 본 논문에서는 스마트폰의 다양한 센서를 이용하여, 스마트폰을 꺼낼 수 없는 위험상황에서 사용자가 위험상황에서 특정 이벤트를 발생시켜, 인지된 상태정보를 전송하는 방식을 분석하고, 이를 기반으로 앞으로 개인 안전에 대한 서비스가 발전할 방향을 제시하고자 한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.4
• /
• pp.118-124
• /
• 2017

In this study, a numerical simulation was performed using commercial code Fluent(v.17.1). The underground Combined Cycle Power Plant (CCPP) was simplified to analyze the methane gas leakage with the crack size and position. In addition, extensive numerical simulations were carried out for different crack sizes from 10 mm to 20 mm. The crack position is the gas leakage, which is assumed to be near the pipe elbow and the gas turbine. A total of 4 cases were compared and analyzed. To analyze the gas leakage, the concept of the Lower Flammable Limit (LFL) was applied. The leakage distance was defined in the longitudinal direction, and the transverse direction was estimated and quantitatively analyzed. As a result, the leakage distance in the longitudinal direction varies by 52.3 % depending on the crack size at the same crack position. Moreover, the maximum difference was 34.8 % according to the crack position when the crack sizes are identical. As jet flow impacts on the obstacle and changes its direction, the recirculation flows are formed. These results are expected to provide useful data to optimize the location and number of gas detections in confined spaces, such as underground CCPP.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.619-622
• /
• 2012

본 연구에서는 키넥트(Kinect) 센서를 통해 수화 동작에서 손의 좌표와 이동방향을 추출하여 속성으로 하고, 데이터 마이닝의 분류 기법을 통해 수화를 인식하여 그 결과를 한글 텍스트로 번역해주는 소프트웨어를 개발한다. 제안 방법의 1단계에서는 0.05초 단위로 추출한 손의 좌표만을 속성으로 한다. 2단계에서는 개개인의 특성 및 화면상의 위치와 같은 요소에 따라 좌표 값이 달라지기 때문에, 손의 움직임에서 변위를 추출하여 손이 움직이는 방향을 속성으로 한다. 하지만 비슷한 방향으로 움직이는 수화가 있을 경우 수화의 구분이 어려우므로 3단계에서는 손의 좌표, 방향 두 가지를 분류하는 속성으로 사용한다. 향후 연구 방향은 수화의 중요한 요소인 손의 위치를 속성으로 추가시키고, 데이터 마이닝의 부스팅(Boosting) 기법을 적용하여 인식률을 높이는 것이다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.25 no.4
• /
• pp.287-292
• /
• 2012

In this study, Multi-Channel Magnetic Flux Leakage(MFL) sensor - based inspection system was applied to monitor the condition of cables. This inspection system measures magnetic flux to detect the local faults(LF) of steel cable. To verify the feasibility of the proposed damage detection technique, an 8-channel MFL sensor head prototype was designed and fabricated. A steel cable bunch specimen with several types of damage was fabricated and scanned by the MFL sensor head to measure the magnetic flux density of the specimen. To interpret the condition of the steel cable, magnetic flux signals were used to determine the locations of the flaws and the level of damage. Measured signals from the damaged specimen were compared with thresholds set for objective decision making. In addition, the magnetic flux density values measured from every channel were summed to focus on the detection of axial location. And, sum of flux density were displayed with threshold. Finally, the results were compared with information on actual inflicted damages to confirm the accuracy and effectiveness of the proposed cable monitoring method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.6
• /
• pp.516-523
• /
• 2001

This paper introduces a indirect rotor position and speed estimation algorithm for the SRM(switched reluctance motor) sensorless control based on the sliding mode observer and evolutionary programming The information of position and speed is generally provided by encoder or resolve. However, the position sensor not only adds complexity, cost and size to the whole drive system, but also causes limitation for industrial applications. In this paper, in order to eliminate the position sensor, indirect position sensing, indirect position sensing method using sliding mode observer is used for SRM drives. But if sliding mode observer parameters are selected to be large, the corresponding rapid changes of estimated position and velocity result in chattering phenomenon. Therefore in order to reduce the chattering, this observer parameters are optimized by evolutionary programming. And PID controller is also optimized to track precisely for the SRM using evolutionary programming.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.3
• /
• pp.173-178
• /
• 2024

This study presents a technique for assessing the dimensional quality of assembly parts in Prefabricated Steel Structures (PSS) using a stereo vision sensor. The stereo vision system captures images and point cloud data of the assembly area, followed by applying image processing algorithms such as fuzzy-based edge detection and Hough transform-based circular bolt hole detection to identify bolt hole locations. The 3D center positions of each bolt hole are determined by correlating 3D real-world position information from depth images with the extracted bolt hole positions. Principal Component Analysis (PCA) is then employed to calculate coordinate axes for precise measurement of distances between bolt holes, even when the sensor and structure orientations differ. Bolt holes are sorted based on their 2D positions, and the distances between sorted bolt holes are calculated to assess the assembly part's dimensional quality. Comparison with actual drawing data confirms measurement accuracy with an absolute error of 1mm and a relative error within 4% based on median criteria.

• Journal of Korean Society for Geospatial Information Science
• /
• v.3 no.2 s.6
• /
• pp.213-220
• /
• 1995

Map Matching is the method for correcting the current position from dead reckoning in Car Navigation System. In this paper, we proposed the new map matching algorithm that can correct the positioning error caused by sensors and digital map data around the cross road area. To do this, first we set the error boundary of the cross road area by combining the relative error of moving distance and the absolute error of road length, second, we find out the starting point of turning within the determined error boundary of the cross point area, third, we compare the turning angle of the car to the angle of each possible road, and the last, we decide the matched road. We used wheel sensor as a speed sensor and used optical fiber gyro as a directional sensor, and assembled the sensors to the notebook computer. We testified our algorithm by driving the Daejeon area-which is a part of south Korea-as a test area. And we proved the efficiency by doing that.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.76-79
• /
• 2010

lately, vehicle blackbox increasing importance and usability Is needed accuracy and variety of information. because, blackbox help to analyze the exact cause of the accident and use as objective evidence in vehicle-related crime. In the paper, to overcome the limitations of the existing black box, use various sensors and vehicle information blackbox store current state of the vehicle with OBD-II protocol using vehicle state information and store exact current location and direction information of the vehicle with Gyro sensor and GPS and use global time of GPS for synchronization of information. In addition, blackbox back the information up with wifi. because, when blackbox damaged, dirvers were able to verify the information.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.23-26
• /
• 2008

본 논문에서는 로봇의 지능적 행위를 구현하기 위하여 인공지능의 몇 가지 기법을 휴머노이드 로봇에 적용하고 이를 테스트 도메인에서 실험하는 연구결과를 기술하였다. 본 연구에서 적용한 기법들은, 인공지능의 계획기법에 기반한 로봇의 계획생성, A^* 알고리즘을 적용한 길 찾기, 외부 센서 값에 기반한 장애물회피 및 로봇의 자기 위치인식, 그리고 원하는 물체를 파악하기 위해 템플릿 매칭을 이용한 영상인식 등 네 가지 방향으로 접근하였다. 전반적으로 로봇의 실험은, 웹 페이지로부터 사용자의 쇼핑 목록을 입력 받아, 인공지능의 계획기법에 기반하여 서버에서 이에 대한 실행계획을 만들고 난 후, 로봇이 서버로부터 TCP/IP 기반의 소켓 통신을 통하여 세부 실행계획을 전달받아 임무를 수행하게 된다. 또한 이러한 임무를 수행하기 위해서는 로봇자신의 현재위치에 대한 정보 및 목표물에 대한 위치인식이 요구되며, 이를 위해서 사전에 주어진 맵의 좌표를 찾아가는 방법을 사용하였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.4
• /
• pp.341-351
• /
• 2008

Communication in wireless sensor networks comprising a plurality of sensor nodes located in an ad hoc environment is unidirectional in that data gathered by sensor nodes are transmitted to a sink node and not vice versa. In those networks, it is not possible for a server or a gateway to send commands to the sensor nodes to determine whether some previously received data are valid when the data indicate unusual conditions, which makes it difficult to make appropriate reactions to the unusual situations. This paper proposes and implements a TDMA-based sensor network communication protocol named BiWSLP(Bidirectional Wireless Sensor Line Protocol) supporting bidirectional communication capability. The BiWSLP is an extension of the WSLP, a unidirectional sensor network communication protocol based on the TDMA protocol. To test the feasibility of the proposed BiWSLP, we construct a virtual bridge management system capable of sending commands to sensor nodes as well as collecting data from the sensor nodes. Based on the test results of the virtual bridge management system, we show the applicability and advantages of the BiWSLP in terms of energy efficiency and bidirectional communication capability.