• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.649-658
• /
• 2003

We propose a hierarchical architecture of ART2 Network for performance improvement and fast pattern classification model using fitness selection. This hierarchical network creates coarse clusters as first ART2 network layer by unsupervised learning, then creates fine clusters of the each first layer as second network layer by supervised learning. First, it compares input pattern with each clusters of first layer and select candidate clusters by fitness measure. We design a optimized fitness function for pruning clusters by measuring relative distance ratio between a input pattern and clusters. This makes it possible to improve speed and accuracy. Next, it compares input pattern with each clusters connected with selected clusters and finds winner cluster. Finally it classifies the pattern by a label of the winner cluster. Results of our experiments show that the proposed method is more accurate and fast than other approaches.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.4
• /
• pp.183-193
• /
• 2019

Process mining is an analytical technique aimed at obtaining useful information about a process by extracting a process model from events log. However, most existing process models are deterministic because they do not include stochastic elements such as the occurrence probabilities or execution times of activities. Therefore, available information is limited, resulting in the limitations on analyzing and understanding the process. Furthermore, it is also important to develop an efficient methodology to discover the process model. Although genetic process mining algorithm is one of the methods that can handle data with noises, it has a limitation of large computation time when it is applied to data with large capacity. To resolve these issues, in this paper, we define a stochastic process tree and propose a tabu search-genetic process mining (TS-GPM) algorithm for a stochastic process tree. Specifically, we define a two-dimensional array as a chromosome to represent a stochastic process tree, fitness function, a procedure for generating stochastic process tree and a model trace as a string of activities generated from the process tree. Furthermore, by storing and comparing model traces with low fitness values in the tabu list, we can prevent duplicated searches for process trees with low fitness value being performed. In order to verify the performance of the proposed algorithm, we performed a numerical experiment by using two kinds of event log data used in the previous research. The results showed that the suggested TS-GPM algorithm outperformed the GPM algorithm in terms of fitness and computation time.

• Science of Emotion and Sensibility
• /
• v.20 no.3
• /
• pp.97-108
• /
• 2017

The purpose of this study was to propose a product planning and design direction for smart fitness wear that will improve the impact of personal training based on researching the requirements of smart fitness wear and its acceptance level, as well as the functional demand. The study conducted in-depth interviews with professional fitness trainers and derived five categories and thirteen keywords by analyzing the categorical data analysis using the interview data. In addition, we surveyed general consumers to measure the acceptance level of smart fitness wear and the functional demand for product development. The results revealed that the difference in the acceptance level of smart fitness wear generally depended on the characteristics related to exercise involvement and exercise-related culture rather than on the demographic characteristics. With regard to the difference in the functional demand of smart fitness wear, the results showed that professional trainers focused on the scientific improvement of the effect of exercise while general consumers focused on the function that considers the sustainability of exercise. Based on the results, we proposed product planning and design directions such as 'mounting of heart rate sensing, muscle activity sensing, motion angle or posture sensing, and motion sensing', 'development of concepts and contents for expert line, ordinary line', 'compression wear design', and 'differentiation of product development according to exercise areas'.

• Korean Security Journal
• /
• no.56
• /
• pp.83-105
• /
• 2018

Special security guards play the role to safely operate and manage nuclear power plants from unintended internal and external threats. Physical fitness management of special security guards is one of the most important factors for improving and maintaining the level of physical protection. Thus, the purpose of this study is to analyze the physical fitness factor and physical fitness level required for mission accomplishment through job analysis of special security guards. The special security guards of Nuclear Power Plant in Korea were performing 7 jobs, 26 duties, 159 tasks. In order to accomplish theses tasks, the following physical fitness were required: muscle strength and muscle endurance of the hand, upper limb, lower limb and core, quickness, agility and Cardio function. The duties that require a lot of physical fitness were in the order of conducting arrest and self-defense, conducting unarmed defensive tactics, demonstrating proficiency with semiautomatic rifle, using protective equipment, performing emergency plan and defensive strategy, etc. The results of this study are expected to provide basic data necessary for establishing guidelines for fitness qualification and training of special security guards in the future and contribute to enhancement of physical protection of nuclear power plants.

• Journal of the Korea Convergence Society
• /
• v.10 no.12
• /
• pp.387-397
• /
• 2019

The purpose of this study is to analyze the relationship between health related physical fitness, cognitive function, depression and quality of life variables of elderly people in a comprehensive way based on quantitative evaluation. The subjects of this study were 385 people who voluntarily participated in the elderly welfare center in Gyeonggi and Seoul the elderly people. As for the data collection methods, were measured the characteristics, depression and quality of life, cognitive function questionnaires along with measures of lower and upper body strength, dynamic equilibrium and agility, total endurance and grip strength. As a result, the first was a statistically significant correlation between integrated health of the elderly, cognitive function, quality of life and depression. Second, the analysis of cognitive function, elderly integrated health, quality of life, and depression revealed statistical significance among all variables. Third, there was the partial intervention effect of function in the quality of life and depression of the elderly.

• Journal of the Korean Applied Science and Technology
• /
• v.37 no.3
• /
• pp.551-563
• /
• 2020

The purpose of this study was to identify the characteristics of health-related indicators according to the participation of swimming program by adults with intellectual disabilities(ID). To this end, 20 adults with IDs, aged 20-39 living in Busna, were selected. Participants divided into two groups: swimming program participation(n=10) and non-participation(n=10). Data were collected by measuring the subjects health-related physical fitness, stress hormones, and immune function and data analysis was conducted using SPSS 18.0, paired t-test, independent t-test and two-way ANOVA. As a result, muscle strength(p<.001), muscular endurance(p<.001), flexibility(p<.001), cardiovascular endurance(p<.01) improvement of exercise group significantly but there was no significant difference in the control group. The stress hormone cortisol(p<.01) was significantly decreased in the exercise group and there was no significant difference in the control group. The immunoglobulins, IgA(p<.05), IgG(p<.001), IgM(p<.05) were significantly increased in the exercise group, but not significantly different in the control group. Therefore, regular swimming program can be said to be a very effective exercise program for improving the physical fitness of adults with IDs, and it is thought that it can reduce stress and help improve immune function. This suggests the need for active physical activity program development and intervention to maintain the health of adults with IDs and prevent chronic diseases.

• Journal of Korea Multimedia Society
• /
• v.10 no.10
• /
• pp.1284-1294
• /
• 2007

In this paper, a blind nonlinear channel equalization is implemented by using a Modified Fuzzy C-Means (MFCM) algorithm. The proposed MFCM searches the optimal channel output states of a nonlinear channel from the received symbols, based on the Bayesian likelihood fitness function instead of a conventional Euclidean distance measure. Next, the desired channel states of a nonlinear channel are constructed with the elements of estimated channel output states, and placed at the center of a Radial Basis Function (RBF) equalizer to reconstruct transmitted symbols. In the simulations, binary signals are generated at random with Gaussian noise. The performance of the proposed method is compared with that of a hybrid genetic algorithm (GA merged with simulated annealing (SA): GASA), and the relatively high accuracy and fast searching speed are achieved.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.8
• /
• pp.790-797
• /
• 2007

This paper proposes a new measure of cost function ruggedness in local optimization with DEAS. DEAS is a computational optimization method developed since 2002 and has been applied to various engineering fields with success. Since DEAS is a recent optimization method which is rarely introduced in Korean, this paper first provides a brief overview and description of DEAS. In minimizing cost function with this non-gradient method, information on function shape measured automatically will enhance search capability. Considering the search strategies of DEAS are well designed with binary matrix structures, analysis of search behaviors will produce beneficial shape information. This paper deals with a simple quadratic function contained with various magnitudes of noise, and DEAS finds local minimum yielding ruggedness measure of given cost function. The proposed shape information will be directly used in improving DEAS performance in future work.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.463-464
• /
• 2007

This paper presents the hardware-based genetic algorithm, written in VHDL. Due to parallel computation and no function call overhead, a hardware-based GA advantage a speedup over a software-based GA. The proposed architecture is constructed on a field-programmable gate arrays, which are easily reconfigured. Since a general-purpose GA requires that the fitness function be easily changed, the hardware implementation must exploit the reprogrammability.

• Journal of Advanced Navigation Technology
• /
• v.18 no.2
• /
• pp.170-177
• /
• 2014

Genetic Algorithms are robust search and optimization techniques but have some problems such as premature convergence and convergence to local extremum. As population diversity converges to low value, the search ability decreases and converges to local extremum but population diversity converges to high value, then the search ability increases and converges to global optimum or genetic algorithm may diverge. To guarantee that genetic algorithms converge to the global optima, the genetic operators should be chosen properly. In this paper, we propose the genetic operators with the hybrid function of the average Hamming distance and the fitness value to maintain the diversity of the GA's population for escaping from the premature convergence. Results of simulation studies verified the effects of the mutation operator for maintaining diversity and the other operators for improving convergence properties as well as the feasibility of using proposed genetic operators on convergence properties to avoid premature convergence and convergence to local extremum.