• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.6
• /
• pp.767-772
• /
• 2018

Recently, some meta-heuristic algorithms, such as GA(Genetic Algorithm) and GP(Genetic Programming), have been used to optimize CNN(Convolutional Neural Network). The CNN, which is one of the deep learning models, has seen much success in a variety of computer vision tasks. However, designing CNN architectures still requires expert knowledge and a lot of trial and error. In this paper, the recent attempts to automatically construct CNN architectures are investigated and analyzed. First, two GA based methods are summarized. One is the optimization of CNN structures with the number and size of filters, connection between consecutive layers, and activation functions of each layer. The other is an new encoding method to represent complex convolutional layers in a fixed-length binary string, Second, CGP(Cartesian Genetic Programming) based method is surveyed for CNN structure optimization with highly functional modules, such as convolutional blocks and tensor concatenation, as the node functions in CGP. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.535-538
• /
• 2003

We employ Genetic Programming (GP) which is optimized with Simulated Annealing (SA) to recognize characteristic of a plan. Its result is described in Laplace function. The algorithm proceeds with automatic PID designs for the plant.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.50 no.5
• /
• pp.234-240
• /
• 2001

Audible noise (AN) produced by corona discharges from high voltage transmission lines is one of the more important considerations in line design. Therefore, line designers must pre-determine the AN using prediction formulas. This paper presents the results of applying evolutionary computation techniques using AN data from lines throughout the world to develop new, highly accurate formulas for predicting a A-weighted AN during heavy rain and stable rain from overhead ac lines. Calculated ANs using these new formulas and existing formulas are compared with measured data.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.6
• /
• pp.573-579
• /
• 2008

This paper introduces a new approach to develop a fast gait for quadruped robot using GP(genetic programming). Planning gaits for legged robots is a challenging task that requires optimizing parameters in a highly irregular and multidimensional space. Several recent approaches have focused on using GA(genetic algorithm) to generate gait automatically and shown significant improvement over previous results. Most of current GA based approaches used pre-selected parameters, but it is difficult to select the appropriate parameters for the optimization of gait. To overcome these problems, we proposed an efficient approach which optimizes joint angle trajectories using genetic programming. Our GP based method has obtained much better results than GA based approaches for experiments of Sony AIBO ERS-7 in Webots environment.

• Smart Structures and Systems
• /
• v.15 no.3
• /
• pp.897-911
• /
• 2015

This study presents a novel approach based on advancements in Evolutionary Computation for data-driven modeling of complex multi-dimensional memory-dependent systems. The investigated example is a benchmark coupled three-dimensional system that incorporates 6 Bouc-Wen elements, and is subjected to external excitations at three points. The proposed technique of this research adapts Genetic Programming for discovering the optimum structure of the differential equation of an auxiliary variable associated with every specific degree-of-freedom of this system that integrates the imposed effect of vibrations at all other degrees-of-freedom. After the termination of the first phase of the optimization process, a system of differential equations is formed that represent the multi-dimensional hysteretic system. Then, the parameters of this system of differential equations are optimized in the second phase using Genetic Algorithms to yield accurate response estimates globally, because the separately obtained differential equations are coupled essentially, and their true performance can be assessed only when the entire system of coupled differential equations is solved. The resultant model after the second phase of optimization is a low-order low-complexity surrogate computational model that represents the investigated three-dimensional memory-dependent system. Hence, this research presents a promising data-driven modeling technique for obtaining optimized representative models for multi-dimensional hysteretic systems that yield reasonably accurate results, and can be generalized to many problems, in various fields, ranging from engineering to economics as well as biology.

• Structural Engineering and Mechanics
• /
• v.71 no.4
• /
• pp.329-339
• /
• 2019

Assessment of failure probability, especially for a complex structure, requires a considerable number of calls to the numerical model. Reliability methods have been developed to decrease the computational time. In this approach, the original numerical model is replaced by a surrogate model which is usually explicit and much faster to evaluate. The current paper proposed an efficient reliability method based on Monte Carlo simulation (MCS) and multi-gene genetic programming (MGGP) as a robust variant of genetic programming (GP). GP has been applied in different fields; however, its application to structural reliability has not been tested. The current study investigated the performance of MGGP as a surrogate model in structural reliability problems and compares it with other surrogate models. An adaptive Metropolis algorithm is utilized to obtain the training data with which to build the MGGP model. The failure probability is estimated by combining MCS and MGGP. The efficiency and accuracy of the proposed method were investigated with the help of five numerical examples.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.677-682
• /
• 2006

Multi-domain design is difficult because such systems tend to be complex and include a mixtures of electrical, mechanical, hydraulic, and thermal components. To design an optimal system, unified and automated procedure with efficient search technique is required. This paper introduces design method for multi-domain system to obtain design solutions automatically, combining bond graph which is domain independent modeling tool and genetic programming which is well recognized as a powerful tool for open-ended search. The suggested design methodology has been applied for design of electric fitter, electric printer drive, and and pump system as a proof of concept for this approach.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2005.04a
• /
• pp.317-324
• /
• 2005

Korean shipyards have accumulated a great amount of data. But they do not have appropriate tools to utilize the data in practical works. Engineering data contains experts' experience and know-how In its own. It is very useful to extract knowledge or information from the accumulated existing data by using datamining technique. This paper treats an evolutionary computation method based on genetic programming (GP), which can be one of the components to realize datamining.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.509-513
• /
• 2004

An area of research called evolvable hardware (EHW) has recently emerged which combines aspects of evolutionary computation with hardware design and synthesis. The features that can be used to identify and classify evolvable hardware are the evolutionary algorithm, the implementation and the genotype representation. This paper gives an introduction to the field. It continues by including classifying the EHW and the applications of the area.

• Proceedings of the KIEE Conference
• /
• 1996.11a
• /
• pp.166-168
• /
• 1996

This paper presents an power system optimization method which solves real and reactive power dispatch problems using evolutionary computation such as genetic algorithms(GAs), evolutionary programming(EP), and evolution strategy(ES). Many conventional methods to this problem have been proposed in the past, but most these approaches have the common defect of being caught to a local minimum solution. Recently, global search methods such as GAs, EP, and ES are introduced. The proposed methods, applied to the IEEE 30-bus system, were run for 12 other exogenous parameters. Each simulation result, by which evolutionary computations are compared and analyzed, shows the possibility of applications of evolutionary computation to large scale power systems.