• 한국산업융합학회 논문집
• /
• 제23권3호
• /
• pp.481-489
• /
• 2020

Safety and security during the handling of hazardous materials is a great concern for anyone in the field. One driving point in the security field is the ability to detect the source of the danger and take action against it as quickly as possible. Via the usage of a fully convolutional network, it is possible to create the label map of an input image, indicating what object is occupying the specific area of the image. This research employs the usage of U-net, which was constructed in biomedical field segmentation to segment cells, instead of the original FCN. One of the challenges that this research faces is the availability of ground truth with precise labeling for the dataset. Testing the network after training resulted in some images where the network pronounces even better detail than the expected label map. With better detailed label map, the network might be able to produce better segmentation is something to be studied in further research.

• 지식경영연구
• /
• 제14권4호
• /
• pp.47-74
• /
• 2013

Many organizations require employee's innovative behaviors, since one way for organizations to become more innovative is to capitalize on their employees' ability to innovate. However, employee's frequent conflict not only causes serious damage to organizations, but also blocks the authentic attitude of knowledge creation and has a negative impact on the innovative behaviors of employees. The purpose of this study is to examine the relationships among employee's task conflict and relationship conflict, employee's authentic attitude of knowledges creation, and innovative behaviors of employees in organizations. The result of analysis shows that the influence of task conflict on innovative behaviors is significant. And the influence of task conflict and relationship conflict on employees' authentic attitude of knowledge creation is significant. And the influence of employees' authentic attitude of knowledge creation on innovative behaviors is positively significant. Thus, the study provides researchers and practitioners with a matter of primary interest in knowledge creation as a driving force leading to innovative behaviors of employees, in which the authentic attitude of employees turns out to be an important psychological factor.

• 한국컴퓨터정보학회논문지
• /
• 제11권6호
• /
• pp.237-248
• /
• 2006

정부는 그 동안 공공부문의 문제점으로 지적되어 왔던 낮은 경영성과 저 생산성, 고비용 구조, 낮은 시장 대응력, 조직 운영의 비효율성 등의 문제를 해결하기 위하여 공공부문을 포함하는 정부 혁신을 강력하게 추진하고 있다. 이러한 혁신의 핵심은 체계적인 성과관리에 있다. 지방공기업 역시 경영효율성을 높이고 경쟁력을 강화하기 위해서는 무엇보다도 자율 경영 체제하에서 경영성과를 정확히 측정하고 그에 따른 보상체계를 마련하는 것이 필수적이다. 본 논문에서는 이러한 균형성과표(Balanced Scorecard)에 기반하여 다원화된 평가주체에 부합하는 지방공기업의 성과 지표에 대한 틀을 설계하고 이를 이용하여 실례로 광주광역시환경시설공단에 적용한 사례를 보이고자 한다.

• 한국지능시스템학회논문지
• /
• 제14권3호
• /
• pp.304-309
• /
• 2004

본 논문에서는 편리한 방식으로 착용할 수 있으며 지능을 지니고 있는 시스템을 구현하고자 한다. 인간을 보조하는 역할을 수행함과 동시에 착용할 수 있는 장점을 지닌 시스템의 구현은 다양한 제어기에 적용될 수 있다. 이동 중인 로봇의 상태를 파악하고 인간을 대신하여 명령을 전달해주는 시스템의 구현이 가능해진 것이다. 본 논문에서는 이동 로봇의 주행 정보를 받아들여 충돌 회피 주행에 필요한 속도와 회전각을 판단하여 명령을 전달하는 시스템을 착용 형태의 장치를 이용하여 구현하였다. 웨어러블 장치의 지능을 구현하기 위해 계층적 퍼지 논리와 신경망의 학습 능력을 결합하였다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 춘계학술대회
• /
• pp.923-928
• /
• 2003

This paper presents the motion control of a mobile robot with arc sensor for lattice type welding. Its dynamic equation and motion control method for welding speed and seam tracking are described. The motion control is realized in the view of keeping constant welding speed and precise target line even though the robot is driven along a straight line or comer. The mobile robot is modeled based on Lagrange equation under nonholonomic constraints and the model is represented in state space form. The motion control of the mobile robot is separated into three driving motions of straight locomotion, turning locomotion and torch slider controls. For the torch slider control, the proportional integral derivative (PID) control method is used. For the straight locomotion, a concept of decoupling method between input and output is adopted and for the turning locomotion, the turning speed is controlled according to the angular velocity value at each point of the comer with range of $90^{\circ}$ constrained to the welding speed. The proposed control methods are proved through simulation results and the results have proved that the mobile robot has enough ability to apply the lattice type welding line.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제4권1호
• /
• pp.45-55
• /
• 2000

The rapid proliferation of wireless networks provides a ubiquitous channel for delivering instructional materials at the convenience of the user. By delivering content through portable devices linked to the Internet, the full spectrum of multimedia capabilities is available for engaging the user's interest. This capability encompasses not only text but images, video, speech generation and voice recognition. Moreover, the incorporation of machine learning capabilities at the source provides the ability to tailor the material to the general level of expertise of the user as well as the immediate needs of the moment: for instance, a request for information regarding a particular city might be covered by a leisurely presentation if solicited from the home, but more tersely if the user happens to be driving a car. This paper presents system architecture to support mobile instruction in conjunction with knowledge-based tutoring capabilities. For concreteress, the general concepts are examined in the context of a system for mathematics education on the Web.

• Journal of Mechanical Science and Technology
• /
• 제16권1호
• /
• pp.83-93
• /
• 2002

This paper presents a motion control method and its simulation results of a mobile robot for a lattice type welding. Its dynamic equation and motion control methods for welding speed and seam tracking are described. The motion control is realized in the view of keeping constant welding speed and precise target line even though the robot is driven for following straight line or curve. The mobile robot is modeled based on Lagrange equation under nonholonomic constraints and the model is represented in state space form. The motion control of the mobile robot is separated into three driving motions of straight locomotion, turning locomotion and torch slider control. For the torch slider control, the proportional-integral-derivative (PID) control method is used. For the straight locomotion, a concept of decoupling method between input and output is adopted and for the turning locomotion, the turning speed is controlled according to the angular velocity value at each point of the corner with range of 90$^{\circ}$ constrained to the welding speed. The proposed control methods are proved through simulation results and these results have proved that the mobile robot has enough ability to apply the lattice type welding line.

• 한국ITS학회 논문지
• /
• 제15권4호
• /
• pp.153-160
• /
• 2016

영상취득 장치를 이용한 지능화된 감시 장치의 개발 기술 또한 발전하고 있다. 비교적 고속으로 움직이는 객체를 탐지해야 하는 분야에서 무엇보다 중요한 것은 배경영상 갱신에 대한 부하를 효과적으로 줄여서 실시간적으로 갱신할 수 있어야 하는데 현재 범용 컴퓨터 능력으로는 질감 등을 특징으로 추출하는 방법 등은 대부분 연산처리의 부하 때문에 적용상의 한계가 있다. 본 논문에서는 적어도 초당 30프레임의 카메라 영상에서 주행 중인 자동차와 같이 고속으로 움직이는 객체를 탐지하는 응용영역에서 실시간으로 배경 영상을 갱신하는 알고리즘을 제시하고, 실제 입력영상에서 객체 영역을 추출하는 시험을 통해 성능을 분석하였다.

• 제어로봇시스템학회논문지
• /
• 제17권6호
• /
• pp.521-525
• /
• 2011

Lane marking detection is one of important issues in the field of autonomous mobile robot. Especially, in urban environment, like pavement roads of downtown or tour tracks of Science Park, which have continuous patterns on the surface of the road, the lane marking detection becomes more important ability. Although there were many researches about lane detection and lane tracing, many of them used vision sensors mainly to detect lane marking. In this paper, we obtain 2 dimensional library data of 'Intensity' and 'Distance' using one laser rangefinder only. We design a simple classifier and filtering algorithm for the lane detection which uses only one LRF (Laser Range Finder). Allowing extended usage of LRF, this research provides more functionality not only in range finding but also in lane detecting to mobile robots. This work will be technically helpful for robot developers to design more simple and efficient autonomous driving system using LRF.

• 전기학회논문지P
• /
• 제67권2호
• /
• pp.75-81
• /
• 2018

In this paper for developing and implementing the car driver's front lane attention enhancement developed system using the car camera. The developed system automatically alarm the car driver when front cars make the dangerous situation. We use Raspberry Pi camera module V2 as car camera module, Raspberry Pi 3 board as hardware main board of implementing embedded system and develop the application library module which can be operated on the Raspberry situation. The application library module widely consist of two part, front car recognition part and dangerous situation distinguish part. Our developed system satisfy the performance test of the target system at the software test certification laboratory of TTA(Telecommunication Technology Association). We test four items as attentive car recognition ability at day and night, system performance, response time. We get the performance of developed system based on the four goal. The car driver's front lane attention enhancement system in this paper will be widely used at the ADAS(Advanced Driving Assistance System) because of the better performance and function.