• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.71-77
• /
• 2021

Recently, there is a demand for efficient program development of an IoT application support frameworks considering heterogeneous hardware characteristics. In addition, the scope of hardware support is expanding with the development of neuromorphic architecture that mimics the human brain to learn on their own and enables autonomous computing. However, most existing IoT IDE(Integrated Development Environment), it is difficult to support AI(Artificial Intelligence) or to support services combined with various hardware such as neuromorphic architectures. In this paper, we design an AI component abstract model that supports the second-generation ANN(Artificial Neural Network) and the third-generation SNN(Spiking Neural Network), and implemented an autonomous IoT IDE based on the proposed model. IoT developers can automatically create AI components through the proposed technique without knowledge of AI and SNN. The proposed technique is flexible in code conversion according to runtime, so development productivity is high. Through experimentation of the proposed method, it was confirmed that the conversion delay time due to the VCL(Virtual Component Layer) may occur, but the difference is not significant.

• International Journal of Aeronautical and Space Sciences
• /
• v.12 no.1
• /
• pp.78-83
• /
• 2011

Traditional autopilot design requires an accurate aerodynamic model and relies on a gain schedule to account for system nonlinearities. This paper presents the control architecture applied to a dynamic model inversion at a single flight condition with an on-line neural network (NN) in order to regulate errors caused by approximate inversion. This eliminates the need for an extensive design process and accurate aerodynamic data. The simulation results using a developed full nonlinear 6 degree of freedom model are presented. This paper also presents the stability evaluation for control systems to which NNs were applied. Although feedback can accommodate uncertainty to meet system performance specifications, uncertainty can also affect the stability of the control system. The importance of robustness has long been recognized and stability margins were developed to quantify it. However, the traditional stability margin techniques based on linear control theory can not be applied to control systems upon which a representative non-linear control method, such as NNs, has been applied. This paper presents an alternative stability margin technique for NNs applied to control systems based on the system responses to an inserted gain multiplier or time delay element.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.406-410
• /
• 2007

성대마이크는 디바이스의 특성상 환경 잡음을 최소화하는 장점이 있다. 그러나 고주파정보의 손실과 부분적인 포먼트 정보의 손실 때문에, 성대마이크를 이용한 명령어 인식기는 표준마이크를 이용한 명령어 인식기보다 낮은 성능을 보인다. 본 논문은 한국어 음운자질의 특성을 적용한 특징추출 알고리즘과 최적화된 인식모델을 이용하여 높은 성능을 갖는 명령어 인식시스템을 제안한다. 성대 울림 특성이 한국어 내의 분포 분석하여 성대 울림 정보만으로 명령어 인식기 개발이 가능함을 보이고 음성인식에 높은 성능을 보이는 Time Delay Neural Network(TDNN)[1]을 성대신호 명령어 인식에 최적화한 구조를 제안한다. 실험을 통해 찾은 최적 TDNN 구조를 성대신호에 적용한 했을 때 약 87%의 높은 성능을 보였다.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.8
• /
• pp.19-24
• /
• 1998

이 논문에서는 능동 소음 제어 시스템을 구성하는 요소들인 증폭기와 저주파 필터 와 같은 소자들의 비선형 특성과 공간에서의 주파수 대역에 따른 비선형 특성을 보상하여, 보다 효과적인 능동 소음 제어기를 설계하기 위해 시간 지연 신경 회로망을 이용하는 새로 운 방법을 제안한다. 공간을 포함한 2차 경로 함수를 모델링하여 보다 나은 성능을 갖는 능 동 소음 제어기를 구성하기 위한 기존의 최소 자승 오차 알고리듬에 기반한 filtered-x least mean square(LMS) 알고리듬과 오차 역전달 학습 알고리듬을 갖는 시간 지연 다층 구조 인 식자를 이용한 결과를 간단한 실험을 통하여 그 성능을 비교 분석한다.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1231-1242
• /
• 2019

This paper presents a two-dimensional attention-based long short-memory (2D-ALSTM) model for stock index prediction, incorporating input attention and temporal attention mechanisms for weighting of important stocks and important time steps, respectively. The proposed model is designed to overcome the long-term dependency, stock selection, and stock volatility delay problems that negatively affect existing models. The 2D-ALSTM model is validated in a comparative experiment involving the two attention-based models multi-input LSTM (MI-LSTM) and dual-stage attention-based recurrent neural network (DARNN), with real stock data being used for training and evaluation. The model achieves superior performance compared to MI-LSTM and DARNN for stock index prediction on a KOSPI100 dataset.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.11
• /
• pp.152-165
• /
• 1998

This study proposes the analysis and evaluation method of time series ultrasonic signal using the chaoral post-process system for precision rate enhancement of ultrasonic pattern recognition. Chaos features extracted from time series data for analysis quantitatively weld defects For this purpose, feature extraction objectives in this study are fractal dimension, Lyapunov exponent, shape of strange attrator. Trajectory changes in the strange attractor indicated that even same type of defects carried substantial difference in chaoticity resulting from distance shifts such as nearby 0.5, 1.0 skip distance. Such difference in chaoticity enables the evaluation of unique features of defects in the weld zone. In quantitative chaos fenture extraction, feature values of 0.835 and 0.823 in the case of slag inclusion and 0.609 and 0.573 in the case of crack were suggested on the basis of fractal dimension and Lyapunov exponent. Proposed chaoral post-process system in this study can enhances precision rate of ultrasonic pattern recognition results from defect signals of weld zone, such as slag inclusion and crack.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.6
• /
• pp.744-752
• /
• 1999

In this paper, we studied the response characteristics of $\alpha$, $\beta$ separated type, combined type, PI typed, and feedforward type in 2DOF-PID controller through the simulation and the experiments designed with the multivariable flow control system. The parameters $\alpha$ and $\beta$ give an affect to characteristics of controller in separated type but $\gamma$ does not give an affect to the characteristics of 2-DOF PID. The more $\beta$ increases, the more overshoot decreases and especially, in case of PI type represent clearly. The $\alpha$, $\beta$ separated type has a very small overshoot and its magnitudes in 2-DOF PID onctroller increases in order of $\alpha$, $\beta$ combined type, PI type, feedforward type, conventional type. The response characteristics of simulation are similar to that of experiments but the experimental characteristics in the multivariable flow control system has the delayed response. The time delay of response in experiments depends on 2-DOF parameter $\alpha$, $\beta$, $\gamma$ and the overshoot increase as the $\alpha$, $\beta$, $\gamma$ increase. So, we can have a satisfactory response by tuning D gain.

• Journal of Korean Society of Transportation
• /
• v.22 no.3 s.74
• /
• pp.145-157
• /
• 2004

The cycle length design model of the Korean traffic responsive signal control systems is devised to vary a cycle length as a response to changes in traffic demand in real time by utilizing parameters specified by a system operator and such field information as degrees of saturation of through phases. Since no explicit guideline is provided to a system operator, the system tends to include ambiguity in terms of the system optimization. In addition, the cycle lengths produced by the existing model have yet been verified if they are comparable to the ones minimizing delay. This paper presents the studies conducted (1) to find shortcomings embedded in the existing model by comparing the cycle lengths produced by the model against the ones minimizing delay and (2) to propose a new direction to design a cycle length minimizing delay and excluding such operator oriented parameters. It was found from the study that the cycle lengths from the existing model fail to minimize delay and promote intersection operational conditions to be unsatisfied when traffic volume is low, due to the feature of the changed target operational volume-to-capacity ratio embedded in the model. The 64 different neural network based cycle length design models were developed based on simulation data surrogating field data. The CORSIM optimal cycle lengths minimizing delay were found through the COST software developed for the study. COST searches for the CORSIM optimal cycle length minimizing delay with a heuristic searching method, a hybrid genetic algorithm. Among 64 models, the best one producing cycle lengths close enough to the optimal was selected through statistical tests. It was found from the verification test that the best model designs a cycle length as similar pattern to the ones minimizing delay. The cycle lengths from the proposed model are comparable to the ones from TRANSYT-7F.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.1-11
• /
• 2001

This paper presents a learning-based approach for the construction of license Plate recognition system. The system consist of three modules. They are respectively, car detection module, license plate recognition module and recognition module. Car detection module detects a car in the given image sequence obtained from the camera with simple color-based approach. Segmentation module extracts the license plate in detect car image using neural network as filters for analyzing the color and texture properties of license plate. Recognition module then reads characters in detected license plate with support vector machine (SVM)-based characters recognizer. The system has been tested from parking lot and tollgate, etc. and have show the following performances on average: Car detect rate 100%, segmentation rate 97.5%, and character recognition rate about 97.2%. Overall system performances is 94.7% and processing time is one sec. Then our propose system does well using real world.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1055-1065
• /
• 2023

Recently, various studies using deep reinforcement learning (deep RL) technology have been conducted to solve complex problems using big data collected at industrial internet of things. Deep RL uses reinforcement learning"s trial-and-error algorithms and cumulative compensation functions to generate and learn its own data and quickly explore neural network structures and parameter decisions. However, studies so far have shown that the larger the size of the learning data is, the higher are the memory usage and search time, and the lower is the accuracy. In this study, model-agnostic learning for efficient federated deep RL was utilized to solve privacy invasion by increasing robustness as 55.9% and achieve 97.8% accuracy, an improvement of 5.5% compared with the comparative optimization-based meta learning models, and to reduce the delay time by 28.9% on average.