본문 바로가기
KERD
논문KCI 등재

상관관계 기반 특징 선별 기법을 사용한 걸음걸이 기반 성별 분류

Gait-Based Gender Classification Using a Correlation-Based Feature Selection Technique

권범
한국컴퓨터정보학회 (The Korean Society Of Computer And Information)|2024.03|한국컴퓨터정보학회논문지 (Journal of The Korea Society of Computer and Information)|제29권 제3호|pp. 55-66|DOI https://doi.org/10.9708/jksci.2024.29.03.055

0

조회

0

다운로드

2

인용

0

참고문헌

키워드

인공지능Artificial Intelligence머신러닝Machine Learning특징 추출Feature ExtractionFeature SelectionGender ClassificationGait Data특징 선별보행 데이터성별 분류
주제분류컴퓨터학

초록

성별 분류 기술은 법의학, 감시 시스템, 인구 통계 연구 등 다양한 분야에서 활용될 수 있기 때문에, 연구자들로부터 많은 관심을 받고 있다. 남성과 여성의 보행 사이에는 서로 구별되는 특징이 있다는것이 기존 연구들에서 밝혀지면서, 3차원 보행 데이터에서 성별을 분류하는 다양한 기술들이 제안됐다. 하지만, 기존 기술들을 사용해 3차원 보행 데이터로부터 추출한 보행 특징 중에는 서로 유사 또는중복되거나 성별 분류에 도움이 되지 않는 특징들도 있다. 이에 본 연구에서는 상관관계 기반 특징선별 기술을 활용해, 성별 분류에 도움이 되는 특징들을 선별하는 방법을 제안한다. 그리고 제안하는특징 선별 기술의 효용성을 입증하기 위해서, 인터넷상에 공개된 3차원 보행 데이터 세트(Dataset)를활용하여 제안하는 특징 선별 기술을 적용하기 전과 후에 대해 성별 분류 모델들의 성능을 비교 분석하였다. 실험에는 이진 분류 문제에 적용할 수 있는 여덟 가지의 머신러닝 알고리즘(Machine Learning Algorithms)을 활용하였다. 실험 결과, 제안하는 특징 선별 기술을 사용하면 성별 분류 성능은 유지하면서, 특징의 개수를 82개에서 60개까지, 22개를 줄일 수 있다는 것을 입증하였다.

Abstract

Gender classification techniques have received a lot of attention from researchers because they can be used in various fields such as forensics, surveillance systems, and demographic studies. As previous studies have shown that there are distinctive features between male and female gait, various techniques have been proposed to classify gender from three dimensional(3-D) gait data. However, some of the gait features extracted from 3-D gait data using existing techniques are similar or redundant to each other or do not help in gender classification. In this study, we propose a method to select features that are useful for gender classification using a correlation-based feature selection technique. To demonstrate the effectiveness of the proposed feature selection technique, we compare the performance of gender classification models before and after applying the proposed feature selection technique using a 3-D gait dataset available on the Internet. Eight machine learning algorithms applicable to binary classification problems were utilized in the experiments. The experimental results show that the proposed feature selection technique can reduce the number of features by 22, from 82 to 60, while maintaining the gender classification performance.

참고문헌 (45)

  1. Y. An, "Discover customers’ gender from online shopping behavior", IEEE Access, 10, pp.13954~13965 (2022)[DOI]
  2. J. C. Boscolo, "Gender differences : Visual attention and attitude toward advertisements", Marketing Intelligence & Planning, 39(2), pp.300~314 (2021)[DOI]
  3. M. Ghasemi Siani, "Comparing young adult responses to rational and emotional sports product advertisements : the moderating role of product type and gender", International Journal of Sports Marketing and Sponsorship, 22(4), pp.798~815 (2021)[DOI]
  4. A. Katrodia, "Consumer buying behavior at shopping malls : Does gender matter?", Journal of Economics and Behavioral Studies, 10(1), pp.125~134 (2018)[DOI]
  5. F. Lin, "Human gender classification : A review", International Journal of Biometrics, 8(3-4), pp.275~300 (2017)[DOI]
  6. L. Cao, "Gender recognition from body", Proc. 16th ACM International Conference on Multimedia, pp.725~728 (2008)
  7. Y. Dong, "Eyebrow shape-based features for biometric recognition and gender classification : A feasibility study", Proc. International Joint Conference on Biometrics(IJCB), pp.1~8 (2011)
  8. M. Nazir, "PSO-GA based optimized feature selection using facial and clothing information for gender classification", Journal of Applied Research and Technology, 12(1), pp.145~152 (2014)
  9. C. C. Lee, "Gender recognition based on combining facial and hair features", Proc. International Conference on Advances in Mobile Computing & Multimedia, pp.537~540 (2013)
  10. B. Kwon, "Implementation of human action recognition system using multiple Kinect sensors", Proc. Pacific-Rim Conf. Multimedia (PCM), pp.334~343 (2015)
  11. B. Kwon, "An enhanced multi-view human action recognition system for virtual training simulator", Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA), pp.1~4 (2016)
  12. B. Kwon, "Implementation of a virtual training simulator based on 360°multi-view human action recognition", IEEE Access, 5, pp.12496~12511 (2017)[DOI]
  13. B. Kwon, "Human skeleton data augmentation for person identification over deep neural network", Applied Sciences, 10(14), pp.1~22 (2020)[DOI]
  14. B. Kwon, "Ensemble learning for skeleton-based body mass index classification", Applied Sciences, 10(21), pp.1~23 (2020)[DOI]
  15. B. Kwon, "Optimal camera point selection toward the most preferable view of 3-D human pose", IEEE Transactions on Systems, Man, and Cybernetics : Systems, 52(1), pp.533~553 (2022)[DOI]
  16. B. Kwon, "Multi-time window feature extraction technique for anger detection in gait data", Journal of the Korea Society of Computer and Information, 28(4), pp.41~51 (2023)[DOI]
  17. C. Vora, "A review of gait analysis based on age and gender prediction", Proc. International Conference on Advancements in Smart Computing and Information Security (ASCIS), pp.77~89 (2022)
  18. S. U. Ko, "Sex-specific differences in gait patterns of healthy older adults : results from the Baltimore longitudinal study of aging", Journal of Biomechanics, 44(10), pp.1974~1979 (2011)[DOI]
  19. J. H. Yoo, "Gender classification in human gait using support vector machine", Proc. International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS), pp.138~145 (2005)
  20. D. Kastaniotis, "Gait-based gender recognition using pose information for real time applications", Proc. 18th International Conference on Digital Signal Processing (DSP), pp.1~6 (2013)
  21. V. O. Andersson, "Gender and body mass index classification using a Microsoft Kinect sensor", Proc. 28th International Florida Artificial Intelligence Research Society Conference (FLAIRS), pp.103~106 (2015)
  22. R. Miyamoto, "Gender prediction by gait analysis based on time series variation on joint position", Journal of Systemics, Cybernetics, and Informatics, 13(3), pp.75~82 (2015)[DOI]
  23. M. M. Bachtiar, "Gait with a combination of swing arm feature extraction for gender identification using Kinect skeleton", Proc. International Seminar on Intelligent Technology and Its Applications (ISITIA), pp.79~82 (2016)
  24. M. H. Ahmed, "Human gender classification based on gait features using Kinect sensor", Proc. 3rd IEEE International Conference on Cybernetics, pp.1~5 (2017)
  25. S. Camalan, "Gender detection using 3D anthropometric measurements by Kinect", Metrology and Measurement Systems, 25(2), pp.253~267 (2018)[DOI]
  26. B. Kwon, "Joint swing energy for skeleton-based gender classification", IEEE Access, 9, pp.28334~28348 (2021)[DOI]
  27. M. Azhar, "A gait-based real-time gender classification system using whole body joints", Sensors, 22(23), pp.1~19 (2022)[DOI]
  28. M. Azhar, "Real-time dynamic and multi-view gait-based gender classification using lower-body joints", Electronics, 12(1), pp.1~19 (2022)[DOI]
  29. O. I. Alsaif, "Using skeleton model to recognize human gait gender", IAES International Journal of Artificial Intelligence, 12(2), pp.974~983 (2023)[DOI]
  30. V. O. Andersson, "Person identification using anthropometric and gait data from Kinect sensor", Proc. Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence, pp.425~431 (2015)
  31. B. Kwon, "Toward an online continual learning architecture for intrusion detection of video surveillance", IEEE Access, 10, pp.89732~89744 (2022)[DOI]
  32. B. Kwon, "EDA-78 : A novel error detection algorithm for Lempel-Ziv-78 compressed data", Wireless Personal Communications, 111, pp.2177~2189 (2020)[DOI]
  33. B. Kwon, "Accurate blind Lempel-Ziv-77parameter estimation via 1-D to 2-D data conversion over convolutional neural network", IEEE Access, 8, pp.43965~43979 (2020)[DOI]
  34. B. Kwon, "Error detection algorithm for Lempel-Ziv-77compressed data", Journal of Communications and Networks, 21(2), pp.100~112 (2019)[DOI]
  35. B. Kwon, "Novel error detection algorithm for LZSS compressed data", IEEE Access, 5, pp.8940~8947 (2017)[DOI]
  36. B. Kwon, "Identification and restoration of LZ77 compressed data using a machine learning approach", Proc. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp.1787~1790 (2018)
  37. B. Kwon, "Path loss prediction using an ensemble learning approach", Journal of the Korea Society of Computer and Information, 29(2), pp.1~12 (2024)[DOI]
  38. B. Kwon, "Accurate path loss prediction based on neural network ensemble", Sensors, 24(1), pp.1~20 (2024)[DOI]
  39. B. Kwon, "Cross-antenna interference cancellation and channel estimation for MISO-FBMC", QAM-Based eMBMS, 2018, pp.24, 3281~3293
  40. B. Kwon, "Effective interference nulling virtual MIMO broadcasting transceiver for multiple relaying", IEEE Access, 5, pp.20695~20706 (2017)[DOI]
  41. B. Kwon, "Scattered reference symbol-based channel estimation and equalization for FBMC-QAM systems", IEEE Transactions on Communications, 65(8), pp.3522~3537 (2017)[DOI]
  42. B. Kwon, "Iterative interference cancellation and channel estimation in evolved multimedia broadcast multicast system using filter-bank multicarrier-quadrature amplitude modulation", IEEE Transactions on Broadcasting, 62(4), pp.864~875 (2016)[DOI]
  43. B. Kwon, "Virtual MIMO broadcasting transceiver design for multi-hop relay networks", Digital Signal Processing, 46, pp.97~107 (2015)[DOI]
  44. B. Kwon, "A downlink power control algorithm for long-term energy efficiency of small cell network", Wireless Networks, 21, pp.2223~2236 (2015)[DOI]
  45. B. Kwon, "A target position decision algorithm based on analysis of path departure for an autonomous path keeping system", Wireless Personal Communications, 83, pp.1843~1865 (2015)[DOI]

관련 논문AI추천

기계학습 모델을 이용한 노인보행과비노인보행의 구별 방법에 관한 연구김가영, 엄수현, 이소연, 장성원, 정수환, 최상일한국정보처리학회 · 정보처리학회논문지. 컴퓨터 및 통신시스템2021 · 제10권 제9호걸음걸이 데이터에서 분노 검출을 위한 다중 시간 윈도 특징 추출 기술권범, 오태근한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2023 · 제28권 제4호불균형한 클래스 데이터에서 오버샘플링 및 3차원 보행 분석을 통한 BMI 분류 정확도 개선권범한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2024 · 제29권 제9호스마트 깔창의 압력센서를 이용한 보행형태 분류서우덕, 신원용, 이성신, 최상일한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2018 · 제23권 제2호스마트폰 사용자의 효율적인 개인 분류를 위한 특징 선택김영인한국지식정보기술학회 · 한국지식정보기술학회 논문지2021 · 제16권 제1호DTW를 이용한 보행 분석 시 warping path 특성이현섭대한체육학회 · 대한체육학회지2020 · 제18권 제1호

이 간행물의 다른 논문 (22건)

보간기법을 적용한 AIS 데이터 기반 선박 경로 예측 딥러닝 연구이규철, 이원희, 윤승원, 장다현pp. 1-10점진적 단계학습과 가중치 전달 기반 향상된 ACGAN양단아, 도인실, 변진모pp. 11-20애착 유형으로 보는 ChatGPT 상호 작용: 사용자 경험에 대한 새로운 시점셰이천, 오창훈pp. 21-41커리큘럼 러닝 기반 LoRA 파인튜닝 성능 향상 방법론김남규, 김대건pp. 43-54ASOS, AWS, 티센망 데이터를 이용한 딥신경망의 저수율 예측 성과에 관한 비교 연구윤종욱, 이호준, 박혜승, 양현호pp. 67-74
원문 보기