• Journal of Electrical Engineering and Technology
• /
• 제10권1호
• /
• pp.408-421
• /
• 2015

Because the wheel of V-belt continuously variable transmission (CVT) system driven by permanent magnet synchronous motor (PMSM) has much unknown nonlinear and time-varying characteristics, the better control performance design for the linear control design is a time consuming job. In order to overcome difficulties for design of the linear controllers, a hybrid recurrent Chebyshev neural network (NN) control system is proposed to control for a PMSM servo-driven V-belt CVT system under the occurrence of the lumped nonlinear load disturbances. The hybrid recurrent Chebyshev NN control system consists of an inspector control, a recurrent Chebyshev NN control with adaptive law and a recouped control. Moreover, the online parameters tuning methodology of adaptive law in the recurrent Chebyshev NN can be derived according to the Lyapunov stability theorem and the gradient descent method. Furthermore, the optimal learning rate of the parameters based on discrete-type Lyapunov function is derived to achieve fast convergence. The recurrent Chebyshev NN with fast convergence has the online learning ability to respond to the system's nonlinear and time-varying behaviors. Finally, to show the effectiveness of the proposed control scheme, comparative studies are demonstrated by experimental results.

• Environmental Engineering Research
• /
• 제25권4호
• /
• pp.545-553
• /
• 2020

Rainfall-Runoff modeling plays a crucial role in various aspects of water resource management. It helps significantly in resolving the issues related to flood control, protection of agricultural lands, etc. Various Machine learning and statistical-based algorithms have been used for this purpose. These techniques resulted in outcomes with an acceptable rate of success. One of the pertinent machine learning algorithms namely Adaptive Neuro Fuzzy Inference System (ANFIS) has been reported to be a very effective tool for the purpose. However, the computational complexity of ANFIS is a major hindrance in its application. In this paper, we resolved this problem of ANFIS by incorporating one of the evolutionary algorithms known as Particle Swarm Optimization (PSO) which was used in estimating the parameters pertaining to ANFIS. The results of the modified ANFIS were found to be satisfactory. The performance of this modified ANFIS is then compared with conventional ANFIS and another popular statistical modeling technique namely ARIMA model with respect to the forecasting of runoff. In the present investigation, it was found that proposed PSO-ANFIS performed better than ARIMA and conventional ANFIS with respect to the prediction accuracy of runoff.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1113-1128
• /
• 2020

Ad hoc networks play an important role in mobile communications, and the performance of nodes has a significant impact on the choice of communication links. To ensure efficient and secure data forwarding and delivery, an intelligent routing protocol (IAODV) based on learning method is constructed. Five attributes of node energy, rate, credit value, computing power and transmission distance are taken as the basis of segmentation. By learning the selected samples and calculating the information gain of each attribute, the decision tree of routing node is constructed, and the rules of routing node selection are determined. IAODV algorithm realizes the adaptive evaluation and classification of network nodes, so as to determine the optimal transmission path from the source node to the destination node. The simulation results verify the feasibility, effectiveness and security of IAODV.

• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(3)
• /
• pp.189-192
• /
• 2001

In this paper, we propose a ADALINE controller using fuzzy-backpropagation algorithm to adjust weight. In the proposed ADALINE controller, using fuzzy algorithm for traning neural network, controller make use of ADALINE due to simple and computing efficiency. This controller includes adaptive learning rate to accelerate teaming. It applies to servo-motor as an controlled process. And then it take a simulation for the position control, so the verify the usefulness of the proposed ADALINE controller.

• 한국융합학회논문지
• /
• 제5권4호
• /
• pp.163-169
• /
• 2014

A stable neural network control scheme for unknown non-linear systems is developed in this paper. While the control variable is optimised to minimize the performance index, convergence of the index is guaranteed asymptotically stable by a Lyapnov control law. The optimization is achieved using a gradient descent searching algorithm and is consequently slow. A fast convergence algorithm using an adaptive learning rate is employed to speed up the convergence. Application of the stable control to a single input single output (SISO) non-linear system is simulated. The satisfactory control performance is obtained.

• 정보보호학회논문지
• /
• 제31권3호
• /
• pp.433-441
• /
• 2021

안드로이드 어플리케이션은 생산성과 게임 등의 다양한 카테고리에 걸쳐 출시되며, 사용자는 개인의 사용 패턴에 따라 다양한 어플리케이션 및 악성코드에 노출된다. 반면 대부분의 분석 엔진은 기존에 존재하는 데이터셋을 활용하며, 주기적인 업데이트가 이루어진다고 해도 사용자의 선호도를 반영하지 않는다. 따라서 알려진 악성코드에 대한 탐지율은 높은 반면, 애드웨어와 같은 유형의 악성코드는 탐지가 어렵다. 또한 기존의 엔진은 서버를 거쳐야 하므로, 추가적인 비용이 발생하며, 사용자는 가용성과 실시간성을 보장받지 못하는 문제가 발생한다. 이러한 문제를 해결하기 위해 논문에서는 서버와 단 한번만의 통신이 요구되는 on-device 악성코드 분석과 전이학습을 통한 모델 재훈련을 수행하는 분석 시스템을 제안한다. 또한 해당 시스템은 디바이스 내부에서 디컴파일을 포함한 전체 프로세스가 이루어지므로, 서버 시스템에서의 부하를 분산할 수 있다. 이러한 분석 시스템을 구현하여 테스트한 결과, 전이 학습이전 기준 최대 90.3%의 정확도를 얻었으며, Adware 카테고리에 대하여 전이학습을 수행한 뒤 최대 95.1% 의 정확도로, 기존 대비 4.8% 높은 정확도를 얻을 수 있었다.

• 한국정보통신학회논문지
• /
• 제9권1호
• /
• pp.22-33
• /
• 2005

본 논문에서 직접순차 확산 스펙트럼 시스템의 적응 횡단선 필터에서 LMS 알고리즘의 수렴 속도를 향상시키기 위한 효율적인 신호간섭 제어기법을 제안한다. 수신 데이터를 재순환하여 심볼 시간주기에 계수들을 곱함으로써 적응되는 제안된 알고리즘의 수렴특성이 수렴 속도의 향상을 이론적으로 증명하기 위해 분석한다. 스텝-크기 매개변수 ${\mu}$가 증가됨에 따라 알고리즘의 수렴 속도가 제어된다. 또한, 스텝-크기 매개변수 ${\mu}$의 증가는 실험적으로 계산된 학습 곡선에서 분산을 감소시키는 효과를 갖는다. 고유치 확산을 증가시킴에 따라 즉응 등화기의 수렴속도를 천천히 제어하고 평균 자승 에러의 안정-상태 값을 증가시키는 효과를 나타내며 데이터-재사용 LMS 기술이 수렴속도를 (B+1)배만큼 증가시켜 필터 알고리즘에서 신호간섭제어의 우수성을 입증한다.

• 대한전기학회논문지
• /
• 제40권4호
• /
• pp.374-381
• /
• 1991

As a diagnostic image of hospitl, the utilization of digital image is steadily increasing. Image coding is indispensable for storing and compressing an enormous amount of diagnostic images economically and effectively. In this paper adaptive two stage vector quantization based on Kohonen's neural network for the compression of cardioangiography among typical angiography of radiographic image sequences is presented and the performance of the coding scheme is compare and gone over. In an attempt to exploit the known characteristics of changes in cardioangiography, relatively large blocks of image are quantized in the first stage and in the next stage the bloks subdivided by the threshold of quantization error are vector quantized employing the neural network of frequency sensitive competitive learning. The scheme is employed because the change produced in cardioangiography is due to such two types of motion as a heart itself and body motion, and a contrast dye material injected. Computer simulation shows that the good reproduction of images can be obtained at a bit rate of 0.78 bits/pixel.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2651-2673
• /
• 2019

In order to detect Denial of Service (DoS) attacks, victim-side detection methods are used popularly such as static threshold-based method and machine learning-based method. However, as DoS attacking methods become more sophisticated, these methods reveal some natural disadvantages such as the late detection and the difficulty of tracing back attackers. Recently, in order to mitigate these drawbacks, source-side DoS detection methods have been researched. But, the source-side DoS detection methods have limitations if the volume of attack traffic is relatively very small and it is blended into legitimate traffic. Especially, with the subtle attack traffic, DoS detection methods may suffer from high false positive, considering legitimate traffic as attack traffic. In this paper, we propose an effective source-side DoS detection method with traffic seasonality aware adaptive threshold. The threshold of detecting DoS attack is adjusted adaptively to the fluctuated legitimate traffic in order to detect subtle attack traffic. Moreover, by understanding the seasonality of legitimate traffic, the threshold can be updated more carefully even though subtle attack happens and it helps to achieve low false positive. The extensive evaluation with the real traffic logs presents that the proposed method achieves very high detection rate over 90% with low false positive rate down to 5%.