• International Journal of Advanced Culture Technology
• /
• v.4 no.4
• /
• pp.81-86
• /
• 2016

In this paper, we propose a simple and effective vision-based tracking controller design for autonomous object tracking using multicopter. The multicopter based automatic tracking system usually unstable when the object moved so the tracking process can't define the object position location exactly that means when the object moves, the system can't track object suddenly along to the direction of objects movement. The system will always looking for the object from the first point or its home position. In this paper, PID control used to improve the stability of tracking system, so that the result object tracking became more stable than before, it can be seen from error of tracking. A computer vision and control strategy is applied to detect a diverse set of moving objects on Raspberry Pi based platform and Software defined PID controller design to control Yaw, Throttle, Pitch of the multicopter in real time. Finally based series of experiment results and concluded that the PID control make the tracking system become more stable in real time.

• Journal of Industrial Convergence
• /
• v.17 no.4
• /
• pp.69-75
• /
• 2019

In this study, we developed a world map learning system for elementary education that uses Google Cloud platform STT, Dialog Flow, and fan holograms to recognize the voices of learners and to show and explain three-dimensional images of suitable results as holograms. As a result of the experiments and interviews, it is expected to be helpful for improving the learning effect by inducing students' interest and immersion and is expected to be effectively used for collaborative learning and education for students with disabilities.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.2
• /
• pp.419-426
• /
• 2018

Ecotourism refers to tourism that senses and observes superior natural resources, cultural resources and history around. Today, as the current leisure patterns of the people change, a healing trip to find nature is being activated. In this paper, we propose a platform design and construction for providing ecotourism information. In the proposed platform, first, the image file of the eco-tourism objects taken every day from the image capture device is collected, converted into a video, uploaded to the server, then, when the tourist arrives at the eco-tourism object, It is designed to be able to watch.

• Journal of the Korean Society of Radiology
• /
• v.10 no.8
• /
• pp.637-643
• /
• 2016

Due to the popularity of artificial intelligent, medical image processing using artificial neural network is increasingly attracting the attention of academic and industry researches. Deep learning with a convolutional neural network has been proved to very effective representation of images. However, the training process requires high performance H/W platform. Thus, the realtime learning of a large number of high dimensional samples within low-power devices is a challenging problem. In this paper, we attempt to establish this possibility by presenting a realtime neural network method on Raspberry pi using online sequential extreme learning machine. Our experiments on high-dimensional dataset show that the proposed method records an almost real-time execution.

• Food Science of Animal Resources
• /
• v.33 no.3
• /
• pp.377-389
• /
• 2013

Gamma-amino butyric acid (GABA) is a kind of pharmacological and biological component and its application is wide and useful in Korea specially, becoming aging society in the near feature. GABA is request special dose for the purposed biological effect but the production of concentrated GABA is very difficult due to low concentration of glutamic acid existed in the fermentation broth. To increase GABA concentrate using fermentation technology, high content of glutamic acid is required. For this reason, various strains which have the glutamic acid decarboxylase (GAD) and can convert glutamic acid to GABA, were isolated from various fermented foods. Most of GABA producing strains are lactic acid bacteria isolated from kimchi, especially added monosodium glutamate (MSG) as a taste enhancer. Optimizing the formulation of culture media and the culture condition, GABA conversion yield and amounts were increased. Finally GABA concentration of fermentation broth in batch or fed batch fermentation reached 660 mM or 1000 mM, respectively. Furthermore formulation of culture media for GABA production developed commercially. Many studies about GABA-rich product have been continued, so GABA-rich kimchi, cheese, yogurt, black raspberry juice and tomato juices has been also developed. In Korea many biological effects of GABA are evaluated recently and GABA will be expected to be used in multipurpose.

• Food Science and Biotechnology
• /
• v.16 no.2
• /
• pp.270-274
• /
• 2007

To characterize the polysaccharides which exist as soluble forms in fruit wines, crude polysaccharides were isolated from red, white, raspberry, wild grape, and pear wine, respectively. Among them, the crude polysaccharide (RW-0) in red wine showed the highest yield and considerable amounts of thiobarbituric acid (TBA)-positive materials. The pectic polysaccharide RW-2 was purified to homogeneity from RW-0 by subsequent size-exclusion chromatography using Sephadex G-75 and its structure was characterized. RW-2 consisted of 14 different monosaccharides which included rarely observed sugars in general polysaccharides, such as 2-O-methyl-fucose, 2-O-methyl-xylose, apiose (Api), 3-C-carboxy-5-deoxy-L-xylose (aceric acid, AceA), 3-deoxy-D-manno-2-octulosonic acid (Kdo), and 3-deoxy-D-lyxo-2-heptulosaric acid (Dha). Methylation analysis indicated that RW-2 comprised at least 20 different glycosyl linkages such as 3,4-linked fucose, 2,3,4-linked rhamnose, 3'-linked apiose, and 2,3,3'-linked apiose, being characteristic in rhamnogalacturonan II (RG-II). High performance size-exclusion chromatography indicated that RW-2 mainly comprised RG-II of higher molecular weight (12,000), and that the changes of molecular weight to apparent 7,000 under less than pH 2.0 were observed. These analyses indicated that the higher molecular weight polysaccharide in RW-2 was mainly present as a RG-II dimer.

• Atmosphere
• /
• v.28 no.3
• /
• pp.317-324
• /
• 2018

In this study, we review the ground-based whole-sky camera (WSC), which is developed to continuously capture day and night cloud images using the illumination data from a precision Lightmeter with a high temporal resolution. The WSC is combined with a precision Lightmeter developed in IYA (International Year of Astronomy) for analysis of an artificial light pollution at night and a DSLR camera equipped with a fish-eye lens widely applied in observational astronomy. The WSC is designed to adjust the shutter speed and ISO of the equipped camera according to illumination data in order to stably capture cloud images. And Raspberry Pi is applied to control automatically the related process of taking cloud and sky images every minute under various conditions depending on illumination data from Lightmeter for 24 hours. In addition, it is utilized to post-process and store the cloud images and to upload the data to web page in real time. Finally, we check the technical possibility of the method to observe the cloud distribution (cover, type, height) quantitatively and objectively by the optical system, through analysis of the captured cloud images from the developed device.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1034-1036
• /
• 2017

최근 가구별 라이프스타일의 변화로 외식 소비문화가 증가하면서 간편하면서도 건강한 음식인 회전초밥을 찾는 수요도 늘어나고 있다. 하지만 기존 회전초밥 가게는 레일 위의 초밥을 일일이 직접 확인하고 만들어야하는 번거로움이 있어 판매량 및 초밥 현황 파악에 정확성이 낮으며, 소비자는 초밥의 신선도가 떨어져도 알 방법 없다. 본 논문은 이러한 문제들의 해결책으로 라즈베리파이를 이용한 초밥 관리 시스템을 제안한다. 이 시스템의 첫 번째 기능은 회전하는 레일에 부착된 파이카메라로 영상처리를 하여 불필요한 인력 없이 한눈에 레일 위의 초밥을 확인한다. 두 번째 기능은 RFID 태그로 시간을 체크하여 최대한의 신선도를 유지하면서 고객에게 상품을 제공한다. 세 번째 기능은 카메라와 RFID로 판매량을 파악하고 웹에서 조회 가능하게 한다. 즉, 이 시스템은 실시간으로 판매량과 초밥 공급을 확인할 수 있도록 하고, 더욱 신선한 상품을 제공하여 상품의 질적 향상과 일의 효율성을 높일 수 있도록 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1231-1234
• /
• 2017

이 논문은 실내 환경을 개선하기 위한 창문 자동제어 시스템을 제안한다. 현대인들은 하루에 약 70% 이상을 실내에서 생활하고 있다. 이로 인해 실내 환경의 질이 매우 중요한 요소로 부각되면서 사람들의 관심이 크게 증가하고 있다. 이 논문에서는 아두이노, 라즈베리 파이 및 다양한 센서를 이용하여 실내 환경을 적정수준으로 유지하고 개선할 수 있는 창문 자동제어 시스템을 제안한다. 제안 시스템 구현을 위해 온습도 센서, 미세먼지 센서, 공기 질 센서, 모터 등을 이용한다. 또한 3D프린팅을 이용하여 제작한 프로토타입을 보인다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.6
• /
• pp.1093-1098
• /
• 2017

In this study, we designed the system that helps drivers check all information about parking space at the entrance and find out whether the places is available or not, because the system has 'Image recognition function' which can even recognize car number plates exactly. Besides, we place the webcam close to the car number plate, so that car number can be identified more quickly. Finally, since we set the webcam high, the system keeps us from parking wrong places by displaying on the screen.