• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.39-42
• /
• 1996

Modeling techniques such as linear regression have been used to predict hurricane activity many months in advance of the start of the hurricane season with some success. In this paper, we construct feedforward neural networks to model Atlantic basin hurricane activity and compare the predictions of our neural network models to the predictions produced by statistical models found in the weather forecasting literature. We find that our neural network models produce reasonably accurate predictions that, for the most part, compare favorably to the predictions of statistical models.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권3호
• /
• pp.174-178
• /
• 2002

This paper discusses a blind equalization technique for FIR channel system, that might be minimum phase or not, in digital communication. The proposed techniques consist of two parts. One is to estimate the original channel coefficients based on fourth-order cumulants of the channel output, the other is to employ RBF neural network to model an inverse system fur the original channel. Here, the estimated channel is used as a reference system to train the RBF. The proposed RBF equalizer provides fast and easy teaming, due to the structural efficiency and excellent recognition-capability of R3F neural network. Throughout the simulation studies, it was found that the proposed blind RBF equalizer performed favorably better than the blind MLP equalizer, while requiring the relatively smaller computation steps in tranining.

• 정보처리학회논문지A
• /
• 제8A권1호
• /
• pp.56-62
• /
• 2001

This paper presents a neural network based variable structure control scheme for nonlinear systems. In this scheme, a set of local variable structure control laws are designed on the basis of the linear models about preselected representative points which cover the range of the system operation of interest. From the combination of the set of local variable structure control laws, neural networks infer the approximate control input in between the operating points. The neural network based variable structure control alleviates the effects of model uncertainties, which cannot be compensated by the control techniques using feedback linearization. It also relaxes the discontinuity in the system’s behavior that appears when the control schemes based on the family of the linear models are applied to nonlinear systems. Simulation results of a ball and beam system, to which feedback linearization cannot be applied, demonstrate the feasibility of the proposed method.

• 한국정보통신학회논문지
• /
• 제6권1호
• /
• pp.14-24
• /
• 2002

본 논문에서는 학습과 정정 기능을 갖는 PWM 뉴럴네트워크를 설계하였다. 설계된 PWM 뉴럴시스템에서, 네트워크의 입력과 출력 신호들은 PWM 신호에 의해서 표현되어진다. 뉴럴네트워크에서 곱셈은 가장 많이 사용하는 동작이다. 승산과 합산의 기능은 PWM 기술과 간단한 혼합모드 회로기술에 의해서 실현된다. 그러므로 설계된 뉴럴네트워크는 단지 소규모의 칩상에서 구현될 수가 있다. 하나의 뉴런과 세개의 시냅스, 연관된 학습회로로 설계된 네트워크회로는 양호한 선형성과 넓은 범위의 동작범위를 가지고 있다. PWM을 이용한 신경망회로의 학습능력을 검증하기 위해, 델타 학습 규칙을 적용하였다. AND 기능과 OR 기능 학습 예측 HSPICE 시뮬레이션을 통해서 설계한 신경망회로의 기능이 성공적임을 증명하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.401-403
• /
• 1992

For the control of robotic manipulators with unknown or uncertain dynamics, leaming control schemes are very effective control schemes for repeated trajectory following tasks. In this class of controllers, control techniques using neural networks have been gaining much attention in recent years.. In this note, we discuss the leaming control techniques using neural networks and propose a new model-based control scheme using multilayered neural networks. Three-layerd neural network is used as a feedback controller to compensate the mismatched terms between model plant and real plant. Computer simulations are performed to show the applicability and the limitation of the proposed controller.

• Advances in concrete construction
• /
• 제10권3호
• /
• pp.247-256
• /
• 2020

In this paper the possibility of using different regression models to predict the mechanical properties of limestone concrete after exposure to high temperatures, based on the results of non-destructive techniques, that could be easily used in-situ, is discussed. Extensive experimental work was carried out on limestone concrete mixtures, that differed in the water to cement (w/c) ratio, the type of cement and the quantity of superplasticizer added. After standard curing, the specimens were exposed to various high temperature levels, i.e., 200℃, 400℃, 600℃ or 800℃. Before heating, the reference mechanical properties of the concrete were determined at ambient temperature. After the heating process, the specimens were cooled naturally to ambient temperature and tested using non-destructive techniques. Among the mechanical properties of the specimens after heating, known also as the residual mechanical properties, the residual modulus of elasticity, compressive and flexural strengths were determined. The results show that residual modulus of elasticity, compressive and flexural strengths can be reliably predicted using an artificial neural network approach based on ultrasonic pulse velocity, residual surface strength, some mixture parameters and maximal temperature reached in concrete during heating.

• 전기전자학회논문지
• /
• 제2권1호
• /
• pp.134-138
• /
• 1998

트래픽의 통계적 변동과 고도의 시변 특성 때문에, 최소의 반응시간을 가지고 고도의 동적인 기술과 적응 그리고 학습능력을 요구하는 네트워크의 자원으로 관리하도록 한다. 뉴럴 네트워크는 ATM 셀 도착율과 큐 길이를 정규화시키며, 그것은 적응 학습 알고리즘을 가지고, ATM 네트워크에서 발생되는 특주를 방지하기 위한 방법을 연구한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5159-5178
• /
• 2018

Network Intrusion detection is a rapidly growing field of information security due to its importance for modern IT infrastructure. Many supervised and unsupervised learning techniques have been devised by researchers from discipline of machine learning and data mining to achieve reliable detection of anomalies. In this paper, a deep convolutional neural network (DCNN) based intrusion detection system (IDS) is proposed, implemented and analyzed. Deep CNN core of proposed IDS is fine-tuned using Randomized search over configuration space. Proposed system is trained and tested on NSLKDD training and testing datasets using GPU. Performance comparisons of proposed DCNN model are provided with other classifiers using well-known metrics including Receiver operating characteristics (RoC) curve, Area under RoC curve (AuC), accuracy, precision-recall curve and mean average precision (mAP). The experimental results of proposed DCNN based IDS shows promising results for real world application in anomaly detection systems.

• International Journal of Computer Science & Network Security
• /
• 제22권2호
• /
• pp.145-152
• /
• 2022

One of the impacts of Covid-19 on education systems has been the shift to online education. This shift has changed the way education is consumed and perceived by students. However, the exact nature of student perception about online education is not known. The aim of this study was to understand the perceptions of Saudi higher education students (e.g., post-school students) about online education during the Covid-19 pandemic. Various aspects of online education including benefits, features and cybersecurity were explored. The data collected were analysed using statistical techniques, especially artificial neural networks, to address the research aims. The key findings were that benefits of online education was perceived by students with positive experience or when ensured of safe use of online platforms without the fear cyber security breaches for which recruitment of a cyber security officer was an important predictor. The issue of whether perception of online education as a necessity only for Covid situation or a lasting option beyond the pandemic is a topic for future research.

• 충청수학회지
• /
• 제34권3호
• /
• pp.221-234
• /
• 2021

We introduce high-order Hopfield neural networks with Leakage delays. Furthermore, we study the uniqueness and existence of Hopfield artificial neural networks having the weighted pseudo almost periodic forcing terms on finite delay. Our analysis is based on the differential inequality techniques and the Banach contraction mapping principle.