본문 바로가기
KERD
논문KCI 등재

유방암 분류를 위한 전이학습 기반 DNN-SVM 하이브리드 모형

Transfer Learning based DNN-SVM Hybrid Model for Breast Cancer Classification

김영순|임동훈|조귀래|백범수
한국컴퓨터정보학회 (The Korean Society Of Computer And Information)|2023.11|한국컴퓨터정보학회논문지 (Journal of The Korea Society of Computer and Information)|제28권 제11호|pp. 1-11|DOI https://doi.org/10.9708/jksci.2023.28.11.001

2

조회

0

다운로드

1

인용

0

참고문헌

키워드

유방암딥러닝Deep learningBreast cancerTransfer learning전이학습DNN-SVM Hybrid 모형DNN-SVM Hybrid model
주제분류컴퓨터학

초록

유방암은 전 세계적으로 여성들 대다수에게 가장 두려워하는 질환이다. 오늘날 데이터의 증가와 컴퓨팅 기술의 향상으로 머신러닝(machine learning)의 효율성이 증대되어 암 검출 및 진단 등에 중요한 역할을 하고 있다. 딥러닝(deep learning)은 인공신경망(artificial neural network, ANN)을기반으로 하는 머신러닝 기술의 한 분야로 최근 여러 분야에서 성능이 급속도로 개선되어 활용범위가 확대되고 있다. 본 연구에서는 유방암 분류를 위해 전이학습(transfer learning) 기반 DNN(Deep Neural Network)과SVM(support vector machine)의 구조를 결합한 DNN-SVM Hybrid 모형을 제안한다. 전이학습 기반제안된 모형은 적은 학습 데이터에도 효과적이고, 학습 속도도 빠르며, 단일모형, 즉 DNN과 SVM 이 가지는 장점을 모두 활용 가능토록 결합함으로써 모형 성능이 개선되었다. 제안된 DNN-SVM Hybrid 모형의 성능평가를 위해 UCI 머신러닝 저장소에서 제공하는 WOBC와 WDBC 유방암 자료를 가지고 성능실험 결과, 제안된 모형은 여러 가지 성능 척도 면에서 단일모형인 로지스틱회귀모형, DNN, SVM 그리고 앙상블 모형인 랜덤 포레스트보다 우수함을 보였다.

Abstract

Breast cancer is the disease that affects women the most worldwide. Due to the development of computer technology, the efficiency of machine learning has increased, and thus plays an important role in cancer detection and diagnosis. Deep learning is a field of machine learning technology based on an artificial neural network, and its performance has been rapidly improved in recent years, and its application range is expanding. In this paper, we propose a DNN-SVM hybrid model that combines the structure of a deep neural network (DNN) based on transfer learning and a support vector machine (SVM) for breast cancer classification. The transfer learning-based proposed model is effective for small training data, has a fast learning speed, and can improve model performance by combining all the advantages of a single model, that is, DNN and SVM. To evaluate the performance of the proposed DNN-SVM Hybrid model, the performance test results with WOBC and WDBC breast cancer data provided by the UCI machine learning repository showed that the proposed model is superior to single models such as logistic regression, DNN, and SVM, and ensemble models such as random forest in various performance measures.

참고문헌 (42)

  1. Statistics Korea, "Causes of Death Statistics in 2021", Korea National Statistical Office, ~ (2022)
  2. Hyuna Sung, "Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries", CA: A Cancer Journal for Clinicians, 71(3), pp.209~249 (2021), Wiley[DOI]
  3. Imen Zemni, "Breast cancer incidence and predictions (Monastir, Tunisia: 2002–2030): A registry-based study", PLOS ONE, 17(5), pp.1~12 (2022), Public Library of Science (PLoS)[DOI]
  4. Korea Central Cancer Registry, "Annual report of cancer statistics in Korea in 2020", Ministry of Health and Welfare, ~ (2023)
  5. M. Sewak, "SVM approach to breast cancer classification", International Multisymposium on Computer and Computational Sciences, pp.32~37 (2007)
  6. M. Fiuzy, "Introduction of a New Diagnostic Method for Breast Cancer Based on Fine Needle Aspiration(FNA)Test Data and Combining Intelligent Systems", Iranian journal of cancer prevention, 5(4), pp.169~177 (2012)
  7. Kausik Das, "Detection of Breast Cancer From Whole Slide Histopathological Images Using Deep Multiple Instance CNN", IEEE Access, 8(20163105), pp.213502~213511 (2020), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  8. V. N. Vapnik, "The Nature of Statistical Learning Theory" (1996), John Wiley & Sons
  9. G.P. Zhang, "Neural networks for classification: a survey", IEEE Transactions on Systems, Man and Cybernetics—Part C:Applications and Reviews, 30(4), pp.451~462 (2000), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  10. S. Gupta, "Date Mining Classification Techniques Applied for Breast Cancer Diagnosis and Prognosis", Indian Journal of Computer Science and Engineering, 2(2), pp.188~195 (2011)
  11. Ziba Khandezamin, "Detection and classification of breast cancer using logistic regression feature selection and GMDH classifier", Journal of Biomedical Informatics, 111(103591), pp.1~16 (2020), Elsevier BV[DOI]
  12. Pin Wang, "Comparative analysis of image classification algorithms based on traditional machine learning and deep learning", Pattern Recognition Letters, 141, pp.61~67 (2021), Elsevier BV[DOI]
  13. Iqbal H. Sarker, "Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions", SN Computer Science, 2(420), pp.1~20 (2021), Springer Science and Business Media LLC[DOI]
  14. Laith Alzubaidi, "Review of deep learning: concepts, CNN architectures, challenges, applications, future directions", Journal of Big Data, 8(53), pp.1~20 (2021), Springer Science and Business Media LLC[DOI]
  15. D. R. Sarvamangala, "Convolutional neural networks in medical image understanding: a survey", Evolutionary Intelligence, 15(1), pp.1~22 (2022), Springer Science and Business Media LLC[DOI]
  16. Ziquan Zhu, "A Survey of Convolutional Neural Network in Breast Cancer", Computer Modeling in Engineering & Sciences, 136(3), pp.2127~2172 (2023), Computers, Materials and Continua (Tech Science Press)[DOI]
  17. Yitan Zhu, "Converting tabular data into images for deep learning with convolutional neural networks", Scientific Reports, 11(11325), pp.1~11 (2021), Springer Science and Business Media LLC[DOI]
  18. Vadim Borisov, "Deep Neural Networks and Tabular Data: A Survey", IEEE Transactions on Neural Networks and Learning Systems, pp.1~21 (2022), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  19. Vadim Borisov, "DeepTLF: robust deep neural networks for heterogeneous tabular data", International Journal of Data Science and Analytics, 16(1), pp.85~100 (2022), Springer Science and Business Media LLC[DOI]
  20. Jane Aurelia, "A Hybrid Convolutional Neural Network-Support Vector Machine for X-ray Computed Tomography Images on Cancer", Open Access Macedonian Journal of Medical Sciences, 9(B), pp.1283~1289 (2021), Scientific Foundation SPIROSKI[DOI]
  21. Duggani Keerthana, "Hybrid convolutional neural networks with SVM classifier for classification of skin cancer", Biomedical Engineering Advances, 5, pp.1~8 (2023), Elsevier BV[DOI]
  22. S. X. Zhang, "Deep neural support vector machines for speech recognition", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.1~5 (2015)
  23. V. Karthikeyan, "Speaker identification using hybrid neural network support vector machine classifier", International Journal of Speech Technology, 25(4), pp.1041~1053 (2022), Springer Science and Business Media LLC[DOI]
  24. S. Ramraj, "Hybrid feature learning framework for the classification of encrypted network traffic", Connection Science, 35(1) (2023), Informa UK Limited[DOI]
  25. M. Iman, "A Review of Deep Transfer Learning and Recent Advancements", Technologies, 11(40), pp.1~18 (2022)[DOI]
  26. Sudeepta Mondal, "Transfer learning of deep neural networks for predicting thermoacoustic instabilities in combustion systems", Energy and AI, 5, pp.1~12 (2021), Elsevier BV[DOI]
  27. Andreas Ebbehoj, "Transfer learning for non-image data in clinical research: A scoping review", PLOS Digital Health, 1(2), pp.e0000014~ (2022), Public Library of Science (PLoS)[DOI]
  28. S. Kalyani, "Static Security Assessment in Power Systems Using Multi-Class SVM with Parameter Selection Methods", International Journal of Machine Learning and Computing, 1(2), pp.193~198 (2011), IACSIT Press[DOI]
  29. 임진수, "최적의 서포트 벡터 머신을 이용한 유방암 분류", 보건정보통계학회지, 38(1), pp.108~121 (2013), 한국보건정보통계학회
  30. "UCI Machine Learning Repository"[URL]
  31. Y. Sawada, "Whole Layers Transfer Learning of Deep Neural Networks for a Small Scale Dataset", International Journal of Machine Learning and Computing, 6(1) (2016)[DOI]
  32. M. Swamynathan, "Mastering Machine Learning with Python in Six Steps: A Practical Implementation Guide to Predictive Data Analytics Using Python" (2019), Apress
  33. Y. Yao, "Latent Backdoor Attacks on Deep Neural Networks", Proceedings of the 26th ACM Conference on Computer and Communications Security, pp.2041~2055 (2019)
  34. S. S. Tirumala, "Exploring Neural Network Layers for Knowledge Discovery", Procedia Computer Science, 193, pp.173~182 (2021)[DOI]
  35. Y. Dar, "Frozen Overparameterization:A Double Descent Perspective on Transfer Learning of Deep Neural Networks", Procedia Computer Science, 193, pp.173~182 (2021)
  36. Ziquan Zhu, "A Survey of Convolutional Neural Network in Breast Cancer", Computer Modeling in Engineering & Sciences, 136(3), pp.2127~2172 (2023), Computers, Materials and Continua (Tech Science Press)[DOI]
  37. 권영호, "피부 질환의 확인: 전이학습을 이용한 백반증 심각도 측정", 정보과학회논문지, 50(1), pp.72~79 (2023), 한국정보과학회[DOI]
  38. Muhammad Ali Syakur, "An Android Interactive Game to Improve Children’s Intellengence By Utylizing Brain Capabilyties And functions", Journal of Physics: Conference Series, 1477(2), pp.1~6 (2020), IOP Publishing[DOI]
  39. A Bagoly, "Machine Learning Developments in ROOT", Journal of Physics: Conference Series, 898, pp.1~8 (2017), IOP Publishing[DOI]
  40. D. Soydaner, "A Comparison of Optimization Algorithms for Deep Learning", International Journal of Pattern Recognition and Artificial Intelligence, 34, pp.1~26 (2020)[DOI]
  41. Simon Orozco-Arias, "Measuring Performance Metrics of Machine Learning Algorithms for Detecting and Classifying Transposable Elements", Processes, 8(6), pp.1~19 (2020), MDPI AG[DOI]
  42. Mukesh Kumar, "Optimized Stacking Ensemble Learning Model for Breast Cancer Detection and Classification Using Machine Learning", Sustainability, 14(21), pp.1~26 (2022), MDPI AG[DOI]

관련 논문AI추천

딥러닝 기반 앙상블을 이용한 유방암 분류임동훈, 정광모, 최도연한국보건정보통계학회 · 보건정보통계학회지2018 · 제43권 제2호최적의 서포트 벡터 머신을 이용한 유방암 분류손주태, 손진영, 임동훈, 임진수한국보건정보통계학회 · 보건정보통계학회지2013 · 제38권 제1호유방암 분류 성능 향상을 위한 배깅 서포트 벡터 머신오윤식, 임동훈, 임진수한국보건정보통계학회 · 보건정보통계학회지2014 · 제39권 제1호Stacking Ensemble Technique for Classifying Breast Cancer권현진, 박진혁, 이영호대한의료정보학회 · Healthcare Informatics Research2019 · 제25권 제4호TabNet 모델 기반 정형 데이터를 활용한 유방암 예측박민정, 안도연, 이수현한국인공지능융합기술학회 · 인공지능융합기술연구2024 · 제4권 제1호A Hybrid Bayesian Network Model for Predicting Breast Cancer Prognosis박래웅, 최종필, 한태화대한의료정보학회 · Healthcare Informatics Research2009 · 제15권 제1호

이 간행물의 다른 논문 (24건)

LSTM-Autoencoder기반 특징추출과 재구성을 사용한 수온 예측 연구송구득, 박수현pp. 13-20Deep SVDD 알고리즘 기반의 품질 검사 시스템 설계김승우, 김정준, 전광우, 강전성, 지성철, 정현준pp. 21-28A Comparative Study on Data Augmentation Using Generative Models for Robust Solar Irradiance Prediction김대성진, 김보영, 이지민, 문지훈, 오진영pp. 29-42시간적, 공간적 특성을 활용하는 딥러닝기반 고무의 레오미터 품질 적합성 검사 모델장용훈, 이명섭, 이복동, 박재현pp. 43-52AutoML과 라이프로그를 활용한 인지기능 장애 예측모형최현철, 이새봄, 윤치호pp. 53-63
원문 보기