예쁜꼬마선충의 수영 행동 영상과 기계학습 모델을 이용한 수질 오염 물질 구분 방법 = A Method for the Classification of Water Pollutants using Machine Learning Model with Swimming Activities Videos of Caenorhabditis elegans

국문 초록 (Abstract)

예쁜꼬마선충(Caenorhabditis elegans)은 염기서열이 완전히 밝혀진 동물로 유전자 기능 분석, 동물 행동 연구 등 다양한 연구 분야에 사용되는 대표적인 생물 종이다. 그동안 선충을 이용해 물의 오염 여부를 판별하기 위한 바이오 모니터링 시스템에 대한 여러 연구들이 있었다. 본 논문은 하천의 수질 오염의 원인이 되는 화학물질을 식별하기 위해 선충의 수영 행동이 활용 가능한 지를 보여주기 위해 기계학습 기반의 바이오 모니터링 시스템을 제안한다. 선충의 수영 행동을 대표하기 위해 선충을 대상으로 가지 길이 유사성(Branch Length Similarity) 엔트로피를 계산한다. 그리고 BLS 엔트로피의 조합인 BLS 엔트로피 프로파일을 클러스터링 알고리즘을 사용해 몇 가지 패턴으로 유형화하여 데이터 집합을 만든다. 0.1ppm 농도의 포름알데히드, 벤젠, 톨루엔이 첨가된 아레나에서 선충의 수영 행동을 촬영하고 개발한 히든 마코프 모델(Hidden Markov Model: HMM)의 성능을 검증한다.

다국어 초록 (Multilingual Abstract)

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.

참고문헌 (Reference)

1 "scikit learn module for KMeans clustering algorithm"

2 L. O. Teles, "Video-tracking of zebrafish(Danio rerio)as a biological early warning system using two distinct artificial neural networks : Probabilistic neural network(PNN)and selforganizing map(SOM)" 165 : 241-248, 2015

3 M. E. Hurtado-Díaz, "Thallium Toxicity in Caenorhabditis elegans : Involvement of the SKN-1 Pathway and Protection by S-Allylcysteine" 38 (38): 287-298, 2020

4 "Somoclu module implemented in python for Self-organizing Map"

5 M. Fernandes, "Resilience assessment of a biological early warning system based on the locomotor behavior of zebrafish(Danio rerio)" 23 : 18858-18868, 2016

6 "Hmmlearn module implemented in python for Hidden Markov model"

7 Q. A. V. Le, "Daphnia in water quality biomonitoring-"omic"approaches" 8 (8): 1-6, 2016

8 Y. S. Park, "Computational characterization of behavioral response of medaka(Oryzias latipes)treated with diazinon" 71 (71): 215-228, 2005

9 S. Villa, "Comparison of the behavioural effects of phamaceuticals and pesticides on Diamesa zernyi larvae(Chironomidae)" 238 : 130-139, 2018

10 P. Wittkowski, "Caenorhabditis elegans As a Promising Alternative Model for Environmental Chemical Mixture Effect Assessment-A Comparative Study" 53 (53): 12725-12733, 2019

11 C. W. Ji, "Analyzing the Response Behavior of Lumbriculus variegatus(Oligochaeta : Lumbriculidae)to Different Concentrations of Copper Sulfate Based on Line Body Shape Detection and a Recurrent Self-Organizing Map" 17 (17): 2627-, 2020

12 I. S. Jeong, "A biological monitoring method based on the response behavior of caenorhabditis elegans to chemicals in water" 33 (33): 47-55, 2019

13 Sagarika Pattnaik, "A Semi-supervised Learning of HMM to Build a POS Tagger for a Low Resourced Language" 한국정보통신학회 18 (18): 207-215, 2020