• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2992-2994
• /
• 2000

In cope with insufficient agricultural labor and requirement of high quality product Hydroponics is a really good method. It makes the high density agriculture possible and all the growing environments controllable. So its research is so much progressing to maximize the quantity and quality of farm products. Furthermore, the big progress, in the research of a future agriculture. is systematically conducted for the automatic controlled system. In this paper, a practical automatic control cultivation system is implemented. To automatically control and optimize the very nonlinear and time-varying growth of farm products, a hybrid strategy(FECA: Fuzzy Expertized Control Algorithm) is proposed which serially combines a fuzzy expert system with the fuzzy logic control. The fuzzy expert system (FMES: Fuzzy Model-based Expert System) is intended to overcome the non-linearity of the growth of farm products. The part of fuzzy controller is incorporated to solve the time-variance of the growth of farm products. Finally. the efficiency and the effectiveness of the implemented agricultural automation system is presented through the cultivation results.

• 한국전기전자재료학회논문지
• /
• 제35권5호
• /
• pp.509-515
• /
• 2022

As the 4th industrial revolution based on ICT is progressing in the manufacturing field, interest in building smart factories that can be flexible and customized according to customer demand is increasing. To this end, it is necessary to maximize the efficiency of factory by performing an automated process in real time through a network communication between engineers and equipment to be able to link the established IT system. It is also necessary to collect and store real-time data from heterogeneous facilities and to analyze and visualize a vast amount of data to utilize necessary information. Therefore, in this study, four types of controllers such as PLC, Arduino, Raspberry Pi, and embedded system, which are generally used to build a smart factory that can connect technologies such as artificial intelligence (AI), Internet of Things (IoT), and big data, are configured. This study was conducted for the development of a program that can collect and store data in real time to visualize and manage information. For communication verification by controller, data communication was implemented and verified with the data log in the program, and 3D monitoring was implemented and verified to check the process status such as planned quantity for each controller, actual quantity, production progress, operation rate, and defect rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3458-3478
• /
• 2022

Automatic modulation recognition is the core algorithm in the field of modulation classification in communication systems. Our investigations show that deep learning (DL) based modulation recognition techniques have achieved effective progress for multiple-input multiple-output (MIMO) systems. However, network complexity is always an additional burden for high-accuracy classifications, which makes it impractical. Therefore, in this paper, we propose a low-complexity dimensional interactive lightweight network (DilNet) for MIMO systems. Specifically, the signals received by different antennas are cooperatively input into the network, and the network calculation amount is reduced through the depth-wise separable convolution. A two-dimensional interactive attention (TDIA) module is designed to extract interactive information of different dimensions, and improve the effectiveness of the cooperation features. In addition, the TDIA module ensures low complexity through compressing the convolution dimension, and the computational burden after inserting TDIA is also acceptable. Finally, the network is trained with a penalized statistical entropy loss function. Simulation results show that compared to existing modulation recognition methods, the proposed DilNet dramatically reduces the model complexity. The dimensional interactive lightweight network trained by penalized statistical entropy also performs better for recognition accuracy in MIMO systems.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 춘계학술대회
• /
• pp.381-382
• /
• 2015

MLCC와 같은 소형소자는 중간단계의 샘플검사가 용이 하지 않아 출하검사 위주로 생산 공정이 구성되어 있다. 양산공정 중간 단계의 샘플 검사가 가능해질 경우 고부가가치의 MLCC 생산효율을 극대화 할 수 있을 것으로 예상된다. 이에 본 연구에서는 사용자의 간섭을 최소화 하여 설비 운영 효율을 극대화 시켜주기 위해 MLCC의 위치 및 각도 추출에 영상처리기법을 적용하여 운영 효율이 극대화된 자동 검사 시스템을 구현 하고자 한다. 총 6가지의 MLCC 소자에 대해 검사 할 수 있었으며 1회 200개의 Chip에 대해 98.4%의 정확도로 Chip을 Pick-Up 하였다. 향후 연구과정에서 얻어진 원천기술에 대한 다양한 응용 방안을 연구를 통해 2차 전지, 반도체 소자 등의 사업 분야에 적용이 가능 할 것으로 예상되어 진다.

• 한국산학기술학회논문지
• /
• 제11권7호
• /
• pp.2534-2540
• /
• 2010

본 논문에서는 틸팅열차의 안전성 확보 및 운행효율 향상을 위해 “한국형 틸팅열차 신뢰성 평가 및 운용기술개발” 연구과제의 한 분야로 추진된 ATP 차상장치의 설치 및 시운전시험에 대한 내용 및 결과를 제시하고 있다. 한국철도기술연구원에서는 기존선의 속도 향상과 KTX 비수혜지역의 여객 서비스 향상을 위해 틸팅열차를 개발하였으며 개발된 틸팅열차의 신뢰성 평가를 위해 기존에 사용되고 있는 ATS 장치에 의한 10km 주행 시운전 시험을 진행하였다. 국토해양부에서는 KTX가 운행되지 않는 지역인 중앙선 및 충북선을 비롯한 7개 기존 노선을 200km/h 이상으로 고속화하기로 하였으며, 이에 따라 열차제어시스템은 기존의 ATS 장치에서 ATP 장치로 개량하여야 한다. 따라서 틸팅열차에도 ATP 차상장치를 설치하여 운행 적합성을 확인하여야 하기 때문에 한국철도공사의 경부선 및 호남선 ATP 구축사업에 사용된 것과 동일한 ATP 차상장치를 틸팅열차에 설치하여 시험하였다.

• 한국의학물리학회지:의학물리
• /
• 제10권3호
• /
• pp.159-168
• /
• 1999

Cardiac disease is one of the leading causes of death in Korea. In quantitative analysis of cardiac function and morphological information by three-dimensional reconstruction of magnetic resonance images, left ventricle provides an important role functionally and physiologically. However, existing procedures mostly rely on the extensive human interaction and are seldom evaluated on clinical applications. In this study, we developed a system which could perform automatic extraction of enpicardial and endocardial contour and analysis of cardiac function to evaluate reliability and stability of each system comparing with the result of ARGUS system offered 1.5T Siemens MRI system and manual method performed by clinicians. For various aspects, we investigated reliability of each system by compared with left ventricular contour, end-diastolic volume (EDV), end-systolic volume (ESV), stock volume (SV), ejection fraction (EF), cardiac output (CO) and wall thickness (WT). When comparing with manual method, extracted results of developed process using minimum error threshold (MET) method that automatically extracts contour from cardiac MR images and ARGUS system were demonstrated as successful rate 90% of the contour extraction. When calculating cardiac function parameters using MET and comparing with using correlation coefficients analysis method, the process extracts endocardial and epicardial contour using MET, values from automatic and ARGUS method agreed with manual values within :t 3% average error. It was successfully demonstrated that automatic method using threshold technique could provide high potential for assessing of each parameters with relatively high reliability compared with manual method. In this study, the method developed in this study could reduce processing time compared with ARGUS and manual method due to a simple threshold technique. This method is useful for diagnosis of cardiac disease, simulating physiological function and amount of blood flow of left ventricle. In addition, this method could be valuable in developing automatic systems in order to apply to other deformable image models.

• 한국의학물리학회지:의학물리
• /
• 제26권1호
• /
• pp.52-58
• /
• 2015

본 연구팀이 개발한 신개념 강내형 치과 진단 장치에서 촬영한 X선 치아영상으로부터 치아 우식증을 조기 단계에서 판별하고 치과의사의 정확한 진단을 돕기 위해서 병변진단 보조시스템인 치아 와동 자동 검출 프로그램을 개발하고자 하였다. 치아 와동 자동 검출 시스템을 구성하고 있는 기본 알고리즘은 치아 와동과 정상 치아를 구분 할 수 있는 영상분별 알고리즘과 치아 영상의 고유 특성 정보를 분석하고 이를 병변 검출에 적용할 수 있는 알고리즘으로 나눌 수가 있는데, 본 연구에서는 먼저, DRLSE 방법을 적용하여 병변과 정상치아 사이의 윤곽선 분할 성능을 테스트 하였다. 개발된 알고리즘의 와식 판별 성능을 테스트하기 위해서 다양한 형태의 와식을 포함하는 전치, 견치, 소구치 등의 7개의 치아팬텀을 제작하고 치아 와식 분별을 실시하였다. 총 14 개의 와식 중에 와식의 경계를 부분적으로 식별한 2개를 제외하고는 12개 와식의 경계를 정확하게 구별하여 개발된 자동 치아 병변 알고리즘의 가능성을 입증하였다. 그러나 실제 치아 와식의 형태는 개개인마다 다르고 복잡하기 때문에 무작위로 선택된 실제 치아에 적용하기 위해서는 보강된 알고리즘이 필요하다. 향후에는 치아에 대한 사전정보를 처리하고 적용하는 패턴 인식 혹은 기계학습 알고리즘을 추가하여 보다 효과적이고 정확한 병변 알고리즘으로 개선할 예정이다.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 춘계학술발표회논문집
• /
• pp.71-76
• /
• 2004

Development of industry is increased Traffic Volume and have brought increase of road. As a result, Maintenance-management expense of the whole road is rapidly increase. Operation of PMS (Pavement Management System) need that it is efficiently for maintenance-management the whole road network Into budget limited. PMS is effective management through Investigation of roughness, crack, plastic deformation, etc of road. Advanced nation recognizes necessity of maintenance-management of road, progress to investigation and research. Our country is lacking that systematic pms's application and research. Therefore, this research estimated using of surveying method of DGPS that roughness of road for investigation-step of PMS. At the future, this paper may contribute in research of automatic surveying system for road surface.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 춘계학술대회 논문집
• /
• pp.350-355
• /
• 2011

This paper gives an overview and developing status of the on-board Automatic Train Control (ATC) System employed to control the Urban Maglev vehicle in Korea. In the construction of demonstration line for Urban Maglev Program, the Daewoo Engineering Company (DEC) has participated as a supplier of the whole ATC System since 2009. According to the contract with Korea Rail Network Authority, DEC is under progress for the development of the whole ATC system including Safety Integration Level (SIL) assessment from the ISA, which is followed by the international standards IEC62278, IEC62279, and EN50129. Once the Urban Maglev Program is completed successfully in 2013, the developed system will be the first localized whole ATC system which has SIL assessment and commercial operation experience in Korea.

• ETRI Journal
• /
• 제35권3호
• /
• pp.406-413
• /
• 2013

In this paper, an orthogonal frequency division multiple access (OFDMA)-based minimum end-to-end delay (MED) distributed routing scheme for mobile backhaul wireless mesh networks is proposed. The proposed scheme selects routing paths based on OFDMA subcarrier synchronization control, subcarrier availability, and delay. In the proposed scheme, OFDMA is used to transmit frames between mesh routers using type-I hybrid automatic repeat request over multipath Rayleigh fading channels. Compared with other distributed routing algorithms, such as most forward within radius R, farthest neighbor routing, nearest neighbor routing, and nearest with forwarding progress, simulation results show that the proposed MED routing can reduce end-to-end delay and support highly reliable routing using only local information of neighbor nodes.