• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.221-232
• /
• 2021

In recent years, with the existence of huge amounts of data stored in huge databases, the need for developing accurate tools for analyzing data and extracting information and knowledge from the huge and multi-source databases have been increased. Hence, new and modern techniques have emerged that will contribute to the development of all other sciences. Knowledge discovery techniques are among these technologies, one popular technique of knowledge discovery techniques is data mining which aims to knowledge discovery from huge amounts of data. Such modern technologies of knowledge discovery will contribute to the development of all other fields. Data mining is important, interesting technique, and has many different and varied algorithms; Therefore, this paper aims to present overview of data mining, and clarify the most important of those algorithms and their uses.

• Journal of Korea Water Resources Association
• /
• v.34 no.5
• /
• pp.567-575
• /
• 2001

A methodology is developed for designing the minimum-cost water distribution network. The method is based on network simulations and an optimization scheme using genetic algorithms. Being a stochastic optimization scheme, genetic algorithms have advantages over the conventional search algorithms in solving network problems known for their nonlinearities and herculean computational costs. While existing methods focus on the design of either entirely new or parallel augmentation of network systems, the proposed method can be applied to problems having both new branches of tree-type and paralle augmentation in loops. The applicability of the method was shown through a case study for Baekryeon water supply system. The optimized design resulted in the maximum 5.37% savings compared to the conventional design without optimization, while meeting the hydraulic constraints.

• Nuclear Engineering and Technology
• /
• v.54 no.1
• /
• pp.310-317
• /
• 2022

The mass attenuation coefficient is the primary physical parameter to model narrow beam gamma-ray attenuation. A new machine learning based approach is proposed to model gamma-ray shielding behavior of composites alternative to theoretical calculations. Two fuzzy logic algorithms and a neural network algorithm were trained and tested with different mixture ratios of vanadium slag/epoxy resin/antimony in the 0.05 MeV-2 MeV energy range. Two of the algorithms showed excellent agreement with testing data after optimizing adjustable parameters, with root mean squared error (RMSE) values down to 0.0001. Those results are remarkable because mass attenuation coefficients are often presented with four significant figures. Different training data sizes were tried to determine the least number of data points required to train sufficient models. Data set size more than 1000 is seen to be required to model in above 0.05 MeV energy. Below this energy, more data points with finer energy resolution might be required. Neuro-fuzzy models were three times faster to train than neural network models, while neural network models depicted low RMSE. Fuzzy logic algorithms are overlooked in complex function approximation, yet grid partitioned fuzzy algorithms showed excellent calculation efficiency and good convergence in predicting mass attenuation coefficient.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.65-72
• /
• 2007

In this study, we used nondestructive test based on ultrasonic test as inspection method and compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as pattern recognition algorithm of weld flaws. For this purpose, variables are applied the same to two algorithms. Where, feature variables are zooming flaw signals of reflected whole signals from weld flaws in time domain. Through this process, we compared advantages/ disadvantages of two algorithms and confirmed application methods of two algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.223-226
• /
• 1997

Usually, the Evolutionary Algorithms(EAs) are considered more efficient for optimal, system design because EAs can provide higher opportunity for obtaining the global optimal solution. This paper presents a mechanism of co-evolution consists of the two genetic algorithms(GAs). This mechanism includes host populations and parasite populations. These two populations are closely related to each other, and the parasite populations plays an important role of searching for useful schema in host populations. Host population represented by feedforward neural network and the result of co-evolution we will find the optimal structure of the neural network. We used the genetic algorithm that search the structure of the feedforward neural network, and evolution strategies which train the weight of neuron, and optimize the net structure. The validity and effectiveness of the proposed method is exemplified on the stabilization and position control of the inverted-pendulum system.

• Journal of Korean Institute of Industrial Engineers
• /
• v.31 no.1
• /
• pp.10-19
• /
• 2005

The minimum spanning tree (MST) problem is one of the traditional optimization problems. Unlike the MST, the degree constrained minimum spanning tree (DCMST) of a graph cannot, in general, be found using a polynomial time algorithm. So, finding the DCMST of a graph is a well-known NP-hard problem of importance in communications network design, road network design and other network-related problems. So, it seems to be natural to use evolutionary algorithms for solving DCMST. Especially, when applying an evolutionary algorithm to spanning tree problems, a representation and search operators should be considered simultaneously. This paper introduces a new tree representation scheme and a genetic operator for solving combinatorial tree problem using evolutionary algorithms. We performed empirical comparisons with other tree representations on several test instances and could confirm that the proposed method is superior to other tree representations. Even it is superior to edge set representation which is known as the best algorithm.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.5
• /
• pp.1520-1524
• /
• 2000

TCP congestion control algorithm prevents network congestion through the control of outgoing traffic size. The network, therefore, should monitor the incoming traffic size of a TCP to determine whether or not a TCP follows standard congestion control algorithms. Some TCP friendly test algorithms are proposed, But, these algorithms cannot be used in real environments because a router in a network does not know the RTT of a TCP flow. In this study, we propose a new RTT determination algorithm that can be used in a router. Our proposed algorithms is validated through the simulation studies.

• Electronics and Telecommunications Trends
• /
• v.38 no.5
• /
• pp.12-22
• /
• 2023

The development of neural networks is evolving towards the adoption of transformer structures with attention modules. Hence, active research focused on extending the concept of lightweight neural network algorithms and hardware acceleration is being conducted for the transition from conventional convolutional neural networks to transformer-based networks. We present a survey of state-of-the-art research on lightweight neural network algorithms and hardware architectures to reduce memory usage and accelerate both inference and training. To describe the corresponding trends, we review recent studies on token pruning, quantization, and architecture tuning for the vision transformer. In addition, we present a hardware architecture that incorporates lightweight algorithms into artificial intelligence processors to accelerate processing.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.271-276
• /
• 2003

In this study, we compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as shape recognition algorithm of welding flaws. For this purpose, variables are applied the same to two algorithm. Here, feature variable is composed of time domain signal itself and frequency domain signal itself, Through this process, we comfirmed advantages/disadvantages of two algorithms and identified application methods of two algorithms.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.11
• /
• pp.1167-1178
• /
• 1991

In this paper, we review the characteristics of battle field, consider required properties of mobile radio network, and design network control architecture proper to battle field network. Also we design distributed algorithm which constructs network control architecture and transmission schedule. For the information of network connectivity and the immediate reconfiguration caused by failure, loss, or movement of nodes, configuration and transmission schedule, algorithms are to be executed periodically and for entire network reliability, algorithms must to be executed fully distributedly. At the time of loss or failure of primary local control node, we suggest the method which diminishes transmission delay. We explain the operation of network with examples. Finally designed algorithms are verified and analized by computer simulation.