• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.65-70
• /
• 2001

We consider a hyper-redundant system that consists of many uniform units. The hyper-redundant system has many degrees of freedom and it can accomplish various tasks. Applysing the reinforcement learning to the hyper-redundant system is very attractive because it is possible to acquire various behaviors for various tasks automatically. In this paper we present a new reinforcement learning algorithm "Q-learning with propagation of motion". The algorithm is designed for the multi-agent systems that have strong connections. The proposed algorithm needs only one small Q-table even for a large scale system. So using the proposed algorithm, it is possible for the hyper-redundant system to learn the effective behavior. In this algorithm, only one leader agent learns the own behavior using its local information and the motion of the leader is propagated to another agents with time delay. The reward of the leader agent is given by using the whole system information. And the effective behavior of the leader is learned and the effective behavior of the system is acquired. We apply the proposed algorithm to a snake-like hyper-redundant robot. The necessary condition of the system to be Markov decision process is discussed. And the computer simulation of learning the locomotion is demonstrated. From the simulation results we find that the task of the locomotion of the robot to the desired point is learned and the winding motion is acquired. We can conclude that our proposed system and our analysis of the condition, that the system is Markov decision process, is valid.

• The Journal of Korean Physical Therapy
• /
• 제31권6호
• /
• pp.333-338
• /
• 2019

Purpose: Although previous studies on the screw-home movement (SHM) for autopsy specimen and walking of living persons conducted, the possibility of acquiring SHM based on inertial measurement units received little attention. This study aimed to investigate the possibility of measuring SHM for the non-weighted bearing using a micro-electro-mechanical system-based wearable motion capture system (MEMSS). Methods: MEMSS and camera-based motion analysis systems were used to obtain kinematic data of the knee joint. The knee joint moved from the flexion position to a fully extended position and then back to the start point. The coefficient of multiple correlation and the difference in the range of motion were used to assess the waveform similarity in the movement measured by two measurement systems. Results: The waveform similarity in the sagittal plane was excellent and the in the transverse plane was good. Significant differences were found in the sagittal plane between the two systems (p<0.05). However, there was no significant difference in the transverse plane between the two systems (p>0.05). Conclusion: The SHM during the passive motion without muscle contraction in the non-weighted bearing appeared in the entire range. We thought that the MEMSS could be easily applied to the acquisition of biomechanical data on the knee related to physical therapy.

• 한국의류학회지
• /
• 제39권3호
• /
• pp.369-378
• /
• 2015

Various forms of wearable bio-signal monitoring systems have been developed recently. Acquisition of stable bio-signal data for health care purposes needs to be unconscious and continuous without hindrance to the users' daily activities. The garment type is a suitable form of a wearable bio-signal monitoring system; however, motion artifacts caused by body movement degrade the signal quality during the measurement of bio-signals. It is crucial to stabilize the electrode position to reduce motion artifacts generated when in motion. The problems with motion artifacts remain unresolved despite their significant effect on bio-signal monitoring. This research creates a foundation for the design of garment-type wearable systems for everyday use by finding a method to reduce motion artifacts through modular design. Two distinct garment-type wearable systems (tee-shirt with a motion artifact-reducing module (MARM) and tee-shirt without a MARM) were designed to compare the effects of modular design on the measurement of heart activity in terms of electrode position displacement, signal quality index value, and morphological quality. The tee-shirt with MARM showed superior properties and yielded higher quality signals than the tee-shirt without MARM. In addition, the tee-shirt with MARM showed a better repeatability of the heart activity signals. Therefore, a garment design with MARM is an efficient way to acquire stable bio-signals while in motion.

• ETRI Journal
• /
• 제32권6호
• /
• pp.881-890
• /
• 2010

Conventional fire detection systems use physical sensors to detect fire. Chemical properties of particles in the air are acquired by sensors and are used by conventional fire detection systems to raise an alarm. However, this can also cause false alarms; for example, a person smoking in a room may trigger a typical fire alarm system. In order to manage false alarms of conventional fire detection systems, a computer vision-based fire detection algorithm is proposed in this paper. The proposed fire detection algorithm consists of two main parts: fire color modeling and motion detection. The algorithm can be used in parallel with conventional fire detection systems to reduce false alarms. It can also be deployed as a stand-alone system to detect fire by using video frames acquired through a video acquisition device. A novel fire color model is developed in CIE $L^*a^*b^*$ color space to identify fire pixels. The proposed fire color model is tested with ten diverse video sequences including different types of fire. The experimental results are quite encouraging in terms of correctly classifying fire pixels according to color information only. The overall fire detection system's performance is tested over a benchmark fire video database, and its performance is compared with the state-of-the-art fire detection method.

• 재활복지공학회논문지
• /
• 제5권1호
• /
• pp.111-115
• /
• 2011

본 논문에서는 신체의 움직임을 측정하는 시스템에 있어서 여러 개의 분산형 시스템 간의 시간 동기화 방법을 제안한다. 분산형 시스템을 고려하는 이유는 피험자의 신체로부터 여러 가지 정보를 수집함에 있어서 하나의 집중된 시스템을 설계하게 되면 각 센서 시스템으로 배선이 연결되어야 하고 이는 피험자에게 크나큰 불편함을 주게 되기 때문이다. 제안된 동기화 방법은 단순한 키 스위치를 사용하고 스위치에 연결된 디지털 포트를 추가로 읽어 들이는 방식으로서 하드웨어가 매우 간단하여 잘 알려진 유비쿼터스 센서 네트워크 방식에 비해 추가적인 전력을 소모하지 않는다. 소프트웨어적으로는 데이터를 측정 후 오프라인 처리 방법을 사용하여 두 시스템간의 샘플링 시간 차이를 구하고 시간을 스케일링하여 보정하는 방식이다. 제안된 방법의 타당성을 실험을 통해 보인다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권4호
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• 한국IT서비스학회지
• /
• 제10권1호
• /
• pp.65-72
• /
• 2011

In this paper, we consist of three dimensional acceleration sensor as a small-sized sensor module to acquire base technologies that need to estimate exhibition audience' moving distance. and that we developed algorism and device that can calculate acceleration in gravity direction with attaching it to people's body part without regard to three dimensional direction. By making use of the sensor module, we have to process the data that let it quantitatively process possible to measure people's walk and movement by computer system. We normalized sensor output data in the process of change from sensor module to acquisition of data, rectangular coordinates and single scalar acceleration value in gravity direction. Printed out sensor data attaching sensor module to people's body part is used for motion pattern detection after normalization, Motion sensor devised mode change algorism because it print data of other pattern according to attached position of body. For algorism design, we collected data occurring during walking about subject and we also defined occurring problem domain after analyzing the data. We settle defined problem domain and that we simulated the walking number measuring instrument with highly efficient in restricted environment.

• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.1-5
• /
• 2021

Sleep apnea refers to a condition in which a person does not breathe during sleep, and is a dangerous symptom that blocks oxygen supply in the body, causing various complications, and the elderly and infants can die if severe. In this paper, we present an algorithm that classifies sleep breathing by analyzing the intensity of breathing with images alone in preparation for the risk of sleep apnea. Only the chest of the person being measured is set to the Region of Interest (ROI) to determine the breathing strength by the differential image within the corresponding ROI area. The adult was selected as the target of the measurement and the breathing strength was measured accurately, and the difference in breathing intensity was also distinguished using depth information. Two videos of sleeping babies also show that even microscopic breathing motions smaller than adults can be detected, which is also expected to help prevent infant death syndrome (SIDS).

• Investigative Magnetic Resonance Imaging
• /
• 제16권1호
• /
• pp.55-66
• /
• 2012

목적 : 자기공명영상(MRI) 획득시 피험자의 머리 움직임은 영상의 품질에 영향을 줄 수 있다. 영상 왜곡의 발생 원인이 되는 피험자의 움직임을 감지하기 위한 3차원 광학 추적 시스템을 제작하였다. 대상 및 방법 : 시스템은 두 대의 CCD 카메라 및 적외선 조명, 구형 반사 마커, 프레임 그래버(frame grabber)와 데스크탑 컴퓨터로 구성되었다. 두 대의 카메라를 이용하여 마커의 움직임을 관측하는 스테레오 비전 시스템을 제작하고, 카메라의 내부/외부 매개변수를 측정하는 캘리브레이션(calibration)과 측정된 매개변수를 이용하여 3차원 움직임 정보를 계산하는 삼각측량(triangulation)기법을 적용하였다. 캘리브레이션 보드와 피험자용 안경을 제작하여 움직임 추적의 정확도와 실제 MRI 영상 촬영 동안의 움직임 검출의 유효성을 평가하였다. 결과 : 반사 마커가 부착된 안경을 쓴 피험자들이 MRI 영상 촬영 동안 머리를 규칙적으로 움직였을 때, 시스템은 MRI의 고자장 환경 내에서도 영상에 영향을 주지 않고 피험자들의 움직임을 잘 감지했다. 결론 : 제작한 스테레오 비전 시스템은피험자의 머리 움직임을 잘 감지하였고, 실시간 알림 기능을 통해 피험자의 움직임을 중지할 수 있도록 알려줌으로써 MRI 영상에 영향을 주는 것을 최소화할 수 있다.

• 한국의학물리학회지:의학물리
• /
• 제24권1호
• /
• pp.76-83
• /
• 2013

진단 및 치료분야에서 호흡 움직임이 미치는 영향에 대한 연구는 외부 움직임을 관찰하여 실시되었으나, 이러한 외부 움직임은 내부 장기의 실제 움직임을 반영하지 못한다. 이에 본 연구에서는 개의 흉부 내 비침습적 이식이 가능한 인공 폐결절을 제작하여 동물실험에 대한 적용가능성을 확인하고 PET 영상 획득 및 방사선조사 시 움직임의 영향을 평가하고자하였다. 인공폐결절은 8 Fr 일회용 위장용 영양공급튜브를 개조하여 제작하였다. 제작된 결절모델은 마취된 개 4마리에 기관을 경유하여 기관지에 삽입한 뒤 방사선투시장치를 이용하여 위치를 확인하였다. PET 촬영용 인공폐결절은 내강에 $^{18}F$-FDG를 주입한 뒤 호흡운동 모사체에 장착하여 정지 상태, 10 rpm과 15 rpm의 종축 왕복운동간 PET 촬영을 실시하였다. 방사선조사용 인공폐결절은 유리선량계를 이식한 뒤 PET 촬영 시와 동일한 호흡운동 모사체에 장착하여 정지 상태, 10 rpm과 15 rpm의 종축 왕복운동간 1 Gy 선량을 조사하였다. 인공폐결절은 방사선투시장치 영상에서 실험동물의 후엽 근위부 세기관지에 이식되며 호흡에 따라 결절의 위치가 변화함을 확인하였다. PET 영상에서의 인공폐결절은 모사된 호흡 움직임에 따라 움직임에 의한 인공산물을 나타내었으며, 호흡동조게이트 시 SNR은 7.21로 기준영상의 SNR 10.15에 비해 감소하였으나 프로파일상 게이트영상의 영상계수는 정적영상에 비해 기준영상과 유사하여 PET 영상의 질을 개선함을 확인하였다. 방사선조사 실험간 인공폐결절 내 삽입된 유리선량계에 조사된 조사선량은 정지 상태와 10 rpm의 종축 왕복운동에서 0.91 Gy로 차이를 보이지 않았으나, 15 rpm의 종축 왕복운동에서 0.90 Gy로 오차범위 내 감소를 나타내었으며, 이온 전리함을 통한 조사선량 검출에서도 근소한 감소를 나타내었다. 본 실험에서 제작된 인공폐결절은 실험동물의 후엽 근위부 세기관지에 높은 재현성을 보이며 방사선투시 영상에서 폐의 내부 움직임을 반영하였다. PET 영상 내 움직임에 의한 인공산물이 관찰되며, 방사선 조사연구에서는 호흡운동이 미약한 영상 흐림을 일으킴을 확인하였다. 따라서 본 인공폐결절은 진단 및 치료분야에서 실험동물을 이용한 움직임 기반 진단 및 치료 평가에 유용한 도구로 사용될 것으로 기대된다.