• The Journal of the Korea Contents Association
• /
• v.17 no.5
• /
• pp.624-632
• /
• 2017

Automatic butterfly identification using images is one of the interesting research fields because it helps the related researchers studying species diversity and evolutionary and development process a lot in this field. The performance of the butterfly species identification system is dependent heavily on the quality of selected features. In this paper, we propose color intensity (CI) entropy by using the distribution of color intensities in a butterfly image. We show color intensity entropy can increase the recognition rate by 10% if it is used together with previously suggested branch length similarity entropy. In addition, the performance comparison with other features such as Eigenface, 2D Fourier transform, and 2D wavelet transform is conducted against several well known machine learning methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.972-980
• /
• 2022

The butterfly species recognition technology based on machine learning using images has the effect of reducing a lot of time and cost of those involved in the related field to understand the diversity, number, and habitat distribution of butterfly species. In order to improve the accuracy and time efficiency of butterfly species classification, various features used as the inputs of machine learning models have been studied. Among them, branch length similarity(BLS) entropy or color intensity entropy methods using the concept of entropy showed higher accuracy and shorter learning time than other features such as Fourier transform or wavelet. This paper proposes a feature extraction algorithm using RGB color intensity entropy for butterfly color images. In addition, we develop butterfly recognition systems that combines the proposed feature extraction method with representative ensemble models and evaluate their performance.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.3 no.1
• /
• pp.47-53
• /
• 2022

The escape behavior of prey fish to predator attack is directly linked to the survival of the fish. In this study, I explored the escape behavior of Medaka fish to bird attacks. To simulate the attack, I designed a model triangular-shaped bird to slide along a fishing line connected between rods at both ends of the tank. The triangular shape was set to 10×15 (S=1), 15×20 (S=2), and 20×25 cm (S=3) with base×height. The slope (θ) of the fishing line, which determines the attack speed of the model bird, was set to values of 15° (θ=1), 30° (θ=2), and 45° (θ=3). The escape behavior was characterized using five variables: escape speed (ν), escape acceleration (α), responsiveness (γ), branch length similarity entropy (ε), and alignment (ϕ). The experimental results showed when (S, θ)=(fixed, varied), the change in values of the five variables were not significant. Thus, the fish respond more sensitively to S than to θ In contrast, when (S, θ)=(varied, fixed), ν, α, and γ showed increasing trends but ε and ϕ did not change much. This indicates the nature of fish escape behavior irrespective of the threat is inherent in ε and ϕ. I found that fish escape behavior can be divided into two types for the five physical quantities. In particular, the analysis showed that the type was mainly determined by the size of the model bird.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.903-909
• /
• 2021

Caenorhabditis elegans whose DNA sequence was completely identified is a representative species used in various research fields such as gene functional analysis and animal behavioral research. In the mean time, many researches on the bio-monitoring system to determine whether water is contaminated or not by using the swimming activities of nematodes. In this paper, we show the possibility of using the swimming activities of C. elegans in the development of a machine learning based bio-monitoring system which identifies chemicals that cause water pollution. To characterize swimming activities of nematode, BLS entropy is computed for the nematode in a frame. And, BLS entropy profile, an assembly of entropies, are classified into several patterns using clustering algorithms. Finally these patterns are used to construct data sets. We recorded images of swimming behavior of nematodes in the arenas in which formaldehyde, benzene and toluene were added at a concentration of 0.1 ppm, respectively, and evaluate the performance of the developed HMM.