• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2762-2764
• /
• 2001

In this study, we introduce and investigate a class of dynamic perceptron architectures, discuss a comprehensive design methodology and carry out a series of numeric experiments. The proposed dynamic perceptron architectures are called as Polynomial Neural Networks(PNN). PNN is a flexible neural architecture whose topology is developed through learning. In particular, the number of layers of the PNN is not fixed in advance but is generated on the fly. In this sense, PNN is a self-organizing network. PNN has two kinds of networks, Polynomial Neuron(FPN)-based and Fuzzy Polynomial Neuron(FPN)-based networks, according to a polynomial structure. The essence of the design procedure of PN-based Self-organizing Polynomial Neural Networks(SOPNN) dwells on the Group Method of Data Handling (GMDH) [1]. Each node of the SOPNN exhibits a high level of flexibility and realizes a polynomial type of mapping (linear, quadratic, and cubic) between input and output variables. FPN-based SOPNN dwells on the ideas of fuzzy rule-based computing and neural networks. Simulations involve a series of synthetic as well as experimental data used across various neurofuzzy systems. A detailed comparative analysis is included as well.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.3
• /
• pp.203-215
• /
• 2022

Bayesian Networks are multivariate probabilistic factor graphs that are used to assess underlying factor relationships. From January 2005 to December 2018, the study examines how Dynamic Bayesian Networks can be utilized to estimate portfolio risk and return as well as determine inter-factor relationships among reversal profit-generating components in Pakistan's emerging market (PSX). The goal of this article is to uncover the factors that cause reversal profits in the Pakistani stock market. In visual form, Bayesian networks can generate causal and inferential probabilistic relationships. Investors might update their stock return values in the network simultaneously with fresh market information, resulting in a dynamic shift in portfolio risk distribution across the networks. The findings show that investments in low net profit margin, low investment, and high volatility-based designed portfolios yield the biggest dynamical reversal profits. The main triggering aspects related to generation reversal profits in the Pakistan market, in the long run, are net profit margin, market risk premium, investment, size, and volatility factor. Investors should invest in and build portfolios with small companies that have a low price-to-earnings ratio, small earnings per share, and minimal volatility, according to the most likely explanation.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.15-24
• /
• 2024

One of the most significant issues in combinatorial optimization is the classical NP-complete conundrum known as the 0/1 Knapsack Problem. This study delves deeply into the investigation of practical solutions, emphasizing two classic algorithmic paradigms, brute force, and dynamic programming, along with the metaheuristic and nature-inspired family algorithm known as the Genetic Algorithm (GA). The research begins with a thorough analysis of the dynamic programming technique, utilizing its ability to handle overlapping subproblems and an ideal substructure. We evaluate the benefits of dynamic programming in the context of the 0/1 Knapsack Problem by carefully dissecting its nuances in contrast to GA. Simultaneously, the study examines the brute force algorithm, a simple yet comprehensive method compared to Branch & Bound. This strategy entails investigating every potential combination, offering a starting point for comparison with more advanced techniques. The paper explores the computational complexity of the brute force approach, highlighting its limitations and usefulness in resolving the 0/1 Knapsack Problem in contrast to the set above of algorithms.

• Journal of KIISE:Software and Applications
• /
• v.29 no.6
• /
• pp.386-395
• /
• 2002

In this paper, we suggest dynamic genetic tree-maps(DGTM) using optimal features on recognizing data. The DGTM uses the genetic algorithm about the importance of features rarely considerable on conventional neural networks and introduces GTM(genetic tree-maps) using tree structure according of the priority of features. Hence, we propose the extended formula, DGTM(dynamic GTM) has dynamic functions to separate and merge the neuron of neural network along the similarity of features.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.2
• /
• pp.393-406
• /
• 1993

In resistance spot welding process, size of molten nuggest have been utilized to assess the integrity of the weld quality. However real-time monitoring of the nugget size is an extremely difficult problem. This paper describes the design of an artificial neural networks(ANN) estimator to predict the nugget size for on-line use of weld quality monitoring. The main task of the ANN estimator is to realize the mapping characteristics from the sampled dynamic resistance signal to the actual negget size through training. The structure of the ANN estimator including the number of hidden layers and nodes in a layer is determined by an estimation error analysis. A series of welding experiments are performed to assess the performance of the ANN estimator. The results are quite promissing in that real-time estimation of the invisible nugget size can be achieved by analyzing the dynamic resistance signal without any conventional destructive testing of welds.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.9
• /
• pp.512-519
• /
• 2000

A Neural networks has been used for a expert system and fault diagnosis system. It is possible to nonlinear function mapping and parallel processing. Therefore It has been developing for a Diagnosis system of nuclear plower plant. In general Neural Networks is a static mapping but Dynamic Neural Network(DNN) is dynamic mapping.쪼두 a fault occur in system a state of system is changed with transient state. Because of a previous state signal is considered as a information DNN is better suited for diagnosis systems than static neural network. But a DNN has many weights so a real time implementation of diagnosis system is in need of a rapid network architecture. This paper presents a algorithm for RCP monitoring Alarm diagnosis system using Self Dynamic Neural Network(SDNN). SDNN has considerably fewer weights than a general DNN. Since there is no interlink among the hidden layer. The effectiveness of Alarm diagnosis system using the proposed algorithm is demonstrated by applying to RCP monitoring in Nuclear power plant.

• The Journal of Information Technology
• /
• v.8 no.3
• /
• pp.131-142
• /
• 2005

The principles on which the Internet was designed and has evolved were first laid out in an explicit way 20 years age. The basic principle is that in layered communications network such as the Internet, functions should always be implemented at the end systems whenever the option exists. This applies to all functions that can be implemented either in the network or at the end systems. End-to-end arguments have recently been reexamined as the Internet and its uses have evolved, and a new set of requirements has begun to emerge. In addition to these, it add a new, and perhaps more important, requirement to this list in the case of heterogeneous networks: the proliferation of unpredictable wireless networks. Wireless networks must cope with dynamic link conditions not present in wired infrastructures, which place a heavy burden on quality of service management solutions. Managing QoS in the face of constantly changing operating conditions demands dynamic management approaches that span multiple layers in the protocol stack. Such as cross-layer design approaches have recently received attention in the context of cellular and mobile special networks. This article introduce the notion of network predictability and describe its relationship to achievable QoS. This relationship is used to propose a framework for cross layer design that can be used to guide development efforts and direct investment decisions for future networks.

• Journal of Communications and Networks
• /
• v.8 no.2
• /
• pp.234-240
• /
• 2006

We study the dynamic burst assembly based on traffic prediction and offset and delay differentiation in optical burst switching network. To improve existing burst assembly mechanism and build an adaptive flexible optical burst switching network, an approach called quality of service (QoS) based adaptive dynamic assembly (QADA) is proposed in this paper. QADA method takes into account current arrival traffic in prediction time adequately and performs adaptive dynamic assembly in limited burst assembly time (BAT) range. By the simulation of burst length error, the QADA method is proved better than the existing method and can achieve the small enough predictive error for real scenarios. Then the different dynamic ranges of BAT for four traffic classes are introduced to make delay differentiation. According to the limitation of BAT range, the burst assembly is classified into one-dimension limit and two-dimension limit. We draw a comparison between one-dimension and two-dimension limit with different prediction time under QoS based offset time and find that the one-dimensional approach offers better network performance, while the two-dimensional approach provides strict inter-class differentiation. Furthermore, the final simulation results in our network condition show that QADA can execute adaptive flexible burst assembly with dynamic BAT and achieve a latency reduction, delay fairness, and offset time QoS guarantee for different traffic classes.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.58 no.2
• /
• pp.164-171
• /
• 2009

This paper presents new learning algorithm of dynamic Bayesian networks (DBN) by means of constrained least square (LS) estimation algorithm and gradient descent method. First, we propose constrained LS based parameter estimation for a Markov chain (MC) model given observation data sets. Next, a gradient descent optimization is utilized for online estimation of a hidden Markov model (HMM), which is bi-linearly constructed by adding an observation variable to a MC model. We achieve numerical simulations to prove its reliability and superiority in which a series of non stationary random signal is applied for the DBN models respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.11
• /
• pp.2477-2487
• /
• 1997

In this paepr, we propose a dynamic multicast routin algorithm for constructing the delay-constrained minimal spanning tree in the VP-based ATM networks, in which we consider the effiiciency enen in the case wheree the destination dynamically joins/departs the multicast connection. For constructing the delay-constrained spanning tree, we frist generate a reduced network consisting of only VCX nodes from a given ATM network, originally consisting of VPX/VCX nodes. Then, we obtain the delay-constrained spanning tree with a minimal tree cost on the reduced network by using our proposed heuristic algorithm. Through numerical examples, we show that our dynamic multicast routing algorithm can provide an efficient usage of network resources when the membership nodes frequently changes during the lifetime of a multicast connection. We also demonstrate the more cost-saving can be expected in dense networks when applyingour proposed algorithm.