• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1271-1274
• /
• 2003

In this paper we propose a turbojet engine controller based on fuzzy inference method. Fuel flow control input is designed by fuzzy inference in order to avoid surge and flame-out during acceleration and deceleration. Acceleration and deceleration demands are used as control commands, which can achieve effective performance without surge and flame-out.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.1331-1336
• /
• 2008

This paper suggests a method using Bayesian inference to estimate the parameters of Weibull distribution and acceleration parameters under the condition that the stresses are time-dependent functions. A Bayesian model based on the discrete time approximation is formulated to infer the parameters of interest from the failure data of the virtual tests and a statistical analysis is considered to decide the most probable mean values of the parameters for reasoning of the failure data.

• 한국항공우주학회지
• /
• 제49권10호
• /
• pp.883-892
• /
• 2021

본 논문에서는 드론을 활용한 감시정찰 임무의 효율성을 향상하기 위해 드론 탑재장비에서 실시간으로 구동 가능한 딥러닝 기반의 객체 인식 모델을 개발하는 연구를 수행하였다. 드론 영상 내 객체 인식 성능을 높이는 목적으로 학습 단계에서 학습 데이터 전처리 및 증강, 전이 학습을 수행하였고 각 클래스 별 성능 편차를 줄이기 위해 가중 크로스 엔트로피 방법을 적용하였다. 추론 속도를 개선하기 위해 양자화 기법이 적용된 추론 가속화 엔진을 생성하여 실시간성을 높였다. 마지막으로 모델의 성능을 확인하기 위해 학습에 참여하지 않은 드론 영상 데이터에서 인식 성능 및 실시간성을 분석하였다.

• 반도체디스플레이기술학회지
• /
• 제21권3호
• /
• pp.7-11
• /
• 2022

Object detection technology is one of the main research topics in the field of computer vision and has established itself as an essential base technology for implementing various vision systems. Recent DNN (Deep Neural Networks)-based algorithms achieve much higher recognition accuracy than traditional algorithms. However, it is well-known that the DNN model inference operation requires a relatively high computational power. In this paper, we analyze the inference time complexity of the state-of-the-art object detection architecture Yolov7 in various environments. Specifically, we compare and analyze the time complexity of four types of the Yolov7 model, YOLOv7-tiny, YOLOv7, YOLOv7-X, and YOLOv7-E6 when performing inference operations using CPU and GPU. Furthermore, we analyze the time complexity variation when inferring the same models using the Pytorch framework and the Onnxruntime engine.

• 반도체디스플레이기술학회지
• /
• 제21권1호
• /
• pp.75-78
• /
• 2022

Deep Neural Networks (DNN) has become an essential data processing architecture for the implementation of multiple computer vision tasks. Recently, DNN-based algorithms achieve much higher recognition accuracy than traditional algorithms based on shallow learning. However, training and inference DNNs require huge computational capabilities than daily usage purposes of computers. Moreover, with increased size and depth of DNNs, CPUs may be unsatisfactory since they use serial processing by default. GPUs are the solution that come up with greater speed compared to CPUs because of their Parallel Processing/Computation nature. In this paper, we analyze the inference time complexity of DNNs using well-known computer vision library, OpenCV. We measure and analyze inference time complexity for three cases, CPU, GPU-Float32, and GPU-Float16.

• ETRI Journal
• /
• 제42권4호
• /
• pp.491-504
• /
• 2020

We present AB9, a neural processor for inference acceleration. AB9 consists of a systolic tensor core (STC) neural network accelerator designed to accelerate artificial intelligence applications by exploiting the data reuse and parallelism characteristics inherent in neural networks while providing fast access to large on-chip memory. Complementing the hardware is an intuitive and user-friendly development environment that includes a simulator and an implementation flow that provides a high degree of programmability with a short development time. Along with a 40-TFLOP STC that includes 32k arithmetic units and over 36 MB of on-chip SRAM, our baseline implementation of AB9 consists of a 1-GHz quad-core setup with other various industry-standard peripheral intellectual properties. The acceleration performance and power efficiency were evaluated using YOLOv2, and the results show that AB9 has superior performance and power efficiency to that of a general-purpose graphics processing unit implementation. AB9 has been taped out in the TSMC 28-nm process with a chip size of 17 × 23 ㎟. Delivery is expected later this year.

• 한국전자통신학회논문지
• /
• 제11권2호
• /
• pp.197-202
• /
• 2016

단일 센서만을 운용하여 옥외활동 중에 있는 사용자의 안전도를 측정하고 판단할 수 있는 방안을 제안한다. 3축 가속도 센서는 다른 센서와 비교하여 가격대비 인지 성능이 우수한 면이 있다. 크기가 작고, 측정하는 값이 상대적으로 에러와 장애로부터 독립적인 측면이 있다. 3축 가속도 센서를 부착한 개인이 옥외에서 비정상적인 상태로 돌입하는 것을 감지할 수 있도록 하기 위하여 3축 가속도가 감지하여 보고하는 에너지 값을 분석하고 이를 계산하여 실시간 안전도를 정량적으로 표기할 수 있도록 하였다.

• Earthquakes and Structures
• /
• 제22권1호
• /
• pp.53-64
• /
• 2022

This study proposes an intelligent semi-active isolation system combining a variable-stiffness control device and ground motion characteristic prediction. To determine the optimal control parameter in real-time, a genetic algorithm (GA)-fuzzy control law was developed in this study. Data on various types of ground motions were collected, and the ground motion characteristics were quantified to derive a near-fault (NF) characteristic ratio by employing an on-site earthquake early warning system. On the basis of the peak ground acceleration (PGA) and the derived NF ratio, a fuzzy inference system (FIS) was developed. The control parameters were optimized using a GA. To support continuity under near-fault and far-field ground motions, the optimal control parameter was linked with the predicted PGA and NF ratio through the FIS. The GA-fuzzy law was then compared with other control laws to verify its effectiveness. The results revealed that the GA-fuzzy control law could reliably predict different ground motion characteristics for real-time control because of the high sensitivity of its control parameter to the ground motion characteristics. Even under near-fault and far-field ground motions, the GA-fuzzy control law outperformed the FPEEA control law in terms of controlling the isolation layer displacement and the superstructure acceleration.

• 한국항행학회논문지
• /
• 제11권3호
• /
• pp.343-349
• /
• 2007

본 연구에서는 전형적인 패턴인식 기법을 적용한 지적도면 인식 방법의 시간지연 문제를 해결하기 위하여 퍼지추론을 이용한 지적도면 인식 방법을 제안하였다. 퍼지 입력 파라미터는 지적도면에 있는 선분의 굵기와 색, 문자 및 숫자를 활용하였다. 퍼지 관계맵(Fuzzy Association Map: FAM)을 생성하였고 추론결과 지적도에서 서비스에 필요한 정보들을 추출 할 수 있었다. 결과물은 지적도를 이용하여 건축물이 들어설 수 있는 공간을 예측하고 이를 3차원으로 자동 형성시키는 방안의 전 단계 과정인 바, u-Gov 기반의 토지 등기 열람 서비스 사업과 인터넷 민원서비스 고도화 사업과 연계하여 적용 시킬 수 있다.

• Structural Engineering and Mechanics
• /
• 제69권3호
• /
• pp.317-326
• /
• 2019

This research aims to assess the tight seismic risk curve of the intake tower at Geumgwang reservoir by considering the recorded historical earthquake data in the Korean Peninsula. The seismic fragility, a significant part of risk assessment, is updated by using Bayesian inference to consider the uncertainties and computational efficiency. The reservoir is one of the largest reservoirs in Korea for the supply of agricultural water. The intake tower controls the release of water from the reservoir. The seismic risk assessment of the intake tower plays an important role in the risk management of the reservoir. Site-specific seismic hazard is computed based on the four different seismic source maps of Korea. Probabilistic Seismic Hazard Analysis (PSHA) method is used to estimate the annual exceedance rate of hazard for corresponding Peak Ground Acceleration (PGA). Hazard deaggregation is shown at two customary hazard levels. Multiple dynamic analyses and a nonlinear static pushover analysis are performed for deriving fragility parameters. Thereafter, Bayesian inference with Markov Chain Monte Carlo (MCMC) is used to update the fragility parameters by integrating the results of the analyses. This study proves to reduce the uncertainties associated with fragility and risk curve, and to increase significant statistical and computational efficiency. The range of seismic risk curve of the intake tower is extracted for the reservoir site by considering four different source models and updated fragility function, which can be effectively used for the risk management and mitigation of reservoir.