• 한국추진공학회지
• /
• 제11권1호
• /
• pp.43-50
• /
• 2007

본 논문에서는 고도 변화만을 고려한 탈설계 영역에서 항공기용 터보 축 엔진의 결함 진단을 위해 지지 벡터 장치(SVM)과 인공신경망(ANN)을 Hybrid로 사용한 분할 학습 알고리즘을 사용하였다. 지상 정지 상태에서보다 학습 데이터와 테스트 데이터 수가 크게 증가하지만, 분할 학습 알고리즘을 이용한 가스터빈 엔진의 결함 진단이 고도 변화를 고려한 탈설계 영역에서도 높은 결함 예측 정확성을 가짐을 확인하였다.

• Steel and Composite Structures
• /
• 제28권4호
• /
• pp.509-516
• /
• 2018

The differential quadrature (DQ) and teaching-learning based optimization (TLBO) methods are coupled to introduce a hybrid numerical method for maximizing fundamental natural frequency of laminated composite skew plates. The fiber(s) orientations are selected as design variable(s). The first-order shear deformation theory (FSDT) is used to obtain the governing equations of the plate. The equations of motion and the related boundary conditions are discretized in space domain by employing the DQ method. The discretized equations are transferred from the time domain into the frequency domain to obtain the fundamental natural frequency. Then, the DQ solution is coupled with the TLBO method to find the maximum frequency of the plate and its related optimum stacking sequences of the laminate. Convergence and applicability of the proposed method are shown and the optimum fundamental frequency parameter of the plates with different skew angle, boundary conditions, number of layers and aspect ratio are obtained. The obtained results can be used as a benchmark for further studies.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 1999년도 춘계종합학술대회
• /
• pp.370-374
• /
• 1999

본 논문에서는 역전파 알고리즘과 헵 학습규칙의 장점을 최대한 살려 이용하고, 역전파 알고리즘의 문제점인 지역 최소점에 빠지는 경우와 학습시간이 느린 단점과 헵 학습규칙의 문제점인 학습 패턴의 저장능력이 매우 제한되고 선형적 분리가 되지 않는 복잡한 문제에는 적용할 수 없다는 단점등을 개선하기 위하여 혼합형 학습규칙을 제안한다. 제안하는 학습규칙은 입력층과 은닉층에 흔합형 학습규칙과 은닉층과 출력층에 역전파(Back-Propagation) 학습규칙을 적용한 혼합형이다. 제안한 혼합형 학습규칙을 이용한 신경회로망의 유용성을 확인하기 위하여 단일관절 매니플레이터를 이용하여 추종제어에 대한 시뮬레이션을 하여 기존의 역전파 알고리즘을 이용한 직접적응 제어 방식과 제어성능을 비교 검토한 결과 다음과 같은 특성을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권7호
• /
• pp.3076-3092
• /
• 2020

An IKPCA-ELM-based intrusion detection method is developed to address the problem of the low accuracy and slow speed of intrusion detection caused by redundancies and high dimensions of data in the network. First, in order to reduce the effects of uneven sample distribution and sample attribute differences on the extraction of KPCA features, the sample attribute mean and mean square error are introduced into the Gaussian radial basis function and polynomial kernel function respectively, and the two improved kernel functions are combined to construct a hybrid kernel function. Second, an improved particle swarm optimization (IPSO) algorithm is proposed to determine the optimal hybrid kernel function for improved kernel principal component analysis (IKPCA). Finally, IKPCA is conducted to complete feature extraction, and an extreme learning machine (ELM) is applied to classify common attack type detection. The experimental results demonstrate the effectiveness of the constructed hybrid kernel function. Compared with other intrusion detection methods, IKPCA-ELM not only ensures high accuracy rates, but also reduces the detection time and false alarm rate, especially reducing the false alarm rate of small sample attacks.

• Journal of information and communication convergence engineering
• /
• 제13권2호
• /
• pp.123-131
• /
• 2015

Training neural networks is a complex task with great importance in the field of supervised learning. In the training process, a set of input-output patterns is repeated to an artificial neural network (ANN). From those patterns weights of all the interconnections between neurons are adjusted until the specified input yields the desired output. In this paper, a new hybrid algorithm is proposed for global optimization of connection weights in an ANN. Dynamic swarms are shown to converge rapidly during the initial stages of a global search, but around the global optimum, the search process becomes very slow. In contrast, the gradient descent method can achieve faster convergence speed around the global optimum, and at the same time, the convergence accuracy can be relatively high. Therefore, the proposed hybrid algorithm combines the dynamic particle swarm optimization (DPSO) algorithm with the backpropagation (BP) algorithm, also referred to as the DPSO-BP algorithm, to train the weights of an ANN. In this paper, we intend to show the superiority (time performance and quality of solution) of the proposed hybrid algorithm (DPSO-BP) over other more standard algorithms in neural network training. The algorithms are compared using two different datasets, and the results are simulated.

• 4차산업연구
• /
• 제3권2호
• /
• pp.11-17
• /
• 2023

Purpose - Recently, in the field of language education, interest in edutech has increased due to difficulties in classroom teaching due to COVID-19. Accordingly, we would like to analyze research topics related to e-learning before and after COVID-19 and examine the implications for the future Korean language education field. Research design, data, and methodology - This study organized a list of papers to be analyzed by searching for e-learning terms applicable to Korean language education in RISS. The collected data was electronically documented, keywords were extracted using text mining techniques, and word frequencies were checked, and then viewed through cloud visualization. Result - It was confirmed that research on e-learning in the field of Korean language education has increased rapidly in 2021 and 2022. In particular, extensive research on online learning methods has been actively conducted due to the difficulties of face-to-face learning in the COVID-19 era. There have been many studies on teaching and learning methods, such as flipped learning, hybrid learning, blended learning, mobile learning, and smart learning. Conclusion - Since the research so far has mainly focused on online class management methods. Therefore, future research suggests that efforts should be made to develop educational contents and teaching methods using specific ICT technologies. These efforts will contribute to advancing smart education that future education aims for.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.280-286
• /
• 2005

본 논문은 이분형 목적변수를 가지는 데이터에서, 의사결정나무나 신경망과 같은 지도 학습(Supervised Learning)의 훈련을 통한 각종 예측 및 분류 정확도를 향상시키기 위해서 오차 패턴을 이용한 새로운 Hybrid 데이터 마이닝 기법을 제안한다. 오차 패턴을 이용한 Hybrid 기법이란 데이터 마이닝의 서로 다른 기법을 각 데이터에 적용한 다음 기법간의 불일치되는 부분만을 다시 패턴화 하여, 이를 최종 모형에 적용하여, 기존에 1개의 방법만을 사용하였을 경우보다, 더욱 좋은 정확도를 가질 수 있도록 하는 방법이다. 본 기법의 검증을 위하여, 10개의 실제 검증용 자료를 사용하였으며, 분석 결과 신경망과 의사결정나무 분석과 같은 기존의 방법보다 전체적으로 예측력이 향상됨을 보였다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제24권2호
• /
• pp.72-81
• /
• 2000

In this paper, we design an adaptive neuro-fuzzy inference system(ANFIS) precompensator for load frequency control of 2-area power systems. While proportional integral derivative (PID) controllers are used in power systems, they may have some problems because of high nonlinearities of the power systems. So, a neuro-fuzzy-based precompensation scheme is incorporated with a convectional PID controller to obtain robustness to the nonlinearities. The proposed precompensation technique can be easily implemented by adding a precompensator to an existing PID controller. The applied neruo-fuzzy inference system precompensator uses a hybrid learning algorithm. This algorithm is to use both a gradient descent method to optimize the premise parameters and a least squares method to solve for the consequent parameters. Simulation results show that the proposed control technique is superior to a conventional Ziegler-Nichols PID controller in dynamic responses about load disturbances.

• Structural Engineering and Mechanics
• /
• 제62권5호
• /
• pp.537-550
• /
• 2017

Structural sizing is a rewarding task due to its non-convex constrained nature in the design space. In order to provide both global exploration and proper search refinement, a hybrid method is developed here based on outstanding features of Evolutionary Computing and Teaching-Learning-Based Optimization. The new method introduces an observer phase for memory exploitation in addition to vector-sum movements in the original teacher and learner phases. Proper integer coding is suited and applied for structural size optimization together with a fly-to-boundary technique and an elitism strategy. Performance of the proposed method is further evaluated treating a number of truss examples compared with teaching-learning-based optimization. The results show enhanced capability of the method in efficient and stable convergence toward the optimum and effective capturing of high quality solutions in discrete structural sizing problems.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 추계학술대회 논문집 학회본부
• /
• pp.207-209
• /
• 1995

The PID controller is widely used due to its fast response and robustness. But its performance is not so good compared with modem controllers such as adaptive, robust, fuzzy, neural controller. Therefore, it is natural to replace PID controller by modem controllers. But, the problem is that modem controller can not be easily applied to the real time process. Hence, this paper proposes such a structure that PID controller and Self-Learning Fuzzy Controller(SLFC) are in parallel with each other. The parameter of SLFC will be updated by gradient descent method using neuro - identifier. The usefulness of this hybrid controller will be proved by simulation results.