걸음걸이 데이터에서 분노 검출을 위한 다중 시간 윈도 특징 추출 기술
Multi-Time Window Feature Extraction Technique for Anger Detection in Gait Data
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
본 논문에서는 보행자의 걸음걸이로부터 분노 감정 검출을 위한 다중 시간 윈도 특징 추출 기술을 제안한다. 기존의 걸음걸이 기반 감정인식 기술에서는 보행자의 보폭, 한 보폭에 걸리는 시간, 보행 속력, 목과 흉부의 전방 기울기 각도(Forward Tilt Angle)를 계산하고, 전체 구간에 대해서 최솟값, 평균값, 최댓값을 계산해서 이를 특징으로 활용하였다. 하지만 이때 각 특징은 보행 전체 구간에 걸쳐 항상 균일하게 변화가 발생하는 것이 아니라, 때로는 지역적으로 변화가 발생한다. 이에 본 연구에서는 장기부터 중기 그리고 단기까지 즉, 전역적인 특징과 지역적인 특징을 모두 추출할 수 있는다중 시간 윈도 특징 추출(Multi-Time Window Feature Extraction) 기술을 제안한다. 또한, 제안하는 특징 추출 기술을 통해 각 구간에서 추출된 특징들을 효과적으로 학습할 수 있는 앙상블 모델을 제안한다. 제안하는 앙상블 모델(Ensemble Model)은 복수의 분류기로 구성되며, 각 분류기는 서로 다른다중 시간 윈도에서 추출된 특징으로 학습된다. 제안하는 특징 추출 기술과 앙상블 모델의 효과를검증하기 위해 일반인에게 공개된 3차원 걸음걸이 데이터 세트를 사용하여 시험 평가를 수행했다. 그 결과, 4가지 성능 평가지표에 대해서 제안하는 앙상블 모델이 기존의 특징 추출 기술로 학습된머신러닝(Machine Learning) 모델들과 비교하여 최고의 성능을 달성하는 것을 입증하였다.
Abstract
In this paper, we propose a technique of multi-time window feature extraction for anger detection in gait data. In the previous gait-based emotion recognition methods, the pedestrian's stride, time taken for one stride, walking speed, and forward tilt angles of the neck and thorax are calculated. Then, minimum, mean, and maximum values are calculated for the entire interval to use them as features. However, each feature does not always change uniformly over the entire interval but sometimes changes locally. Therefore, we propose a multi-time window feature extraction technique that can extract both global and local features, from long-term to short-term. In addition, we also propose an ensemble model that consists of multiple classifiers. Each classifier is trained with features extracted from different multi-time windows. To verify the effectiveness of the proposed feature extraction technique and ensemble model, a public three-dimensional gait dataset was used. The simulation results demonstrate that the proposed ensemble model achieves the best performance compared to machine learning models trained with existing feature extraction techniques for four performance evaluation metrics.
참고문헌 (32)
- Nicole K. Ciesinski, "A latent class analysis of intermittent explosive disorder symptoms", Journal of Affective Disorders, 302, pp.367~375 (2022), Elsevier BV[DOI]
- Michael S. McCloskey, "Cognitive-Behavioral Versus Supportive Psychotherapy for Intermittent Explosive Disorder: A Randomized Controlled Trial", Behavior Therapy, 53(6), pp.1133~1146 (2022), Elsevier BV[DOI]
- Jennifer R. Fanning, "Subtypes of aggression in intermittent explosive disorder", Journal of Psychiatric Research, 109, pp.164~172 (2019), Elsevier BV[DOI]
- Joshua Tseng, "Firearm legislation, gun violence, and mortality in children and young adults: A retrospective cohort study of 27,566 children in the USA", International Journal of Surgery, 57, pp.30~34 (2018), Ovid Technologies (Wolters Kluwer Health)[DOI]
- C. Pritchard, "International comparison of civilian violent deaths: a public health approach to reduce gun-related deaths in US youth", Public Health, 180, pp.109~113 (2020), Elsevier BV[DOI]
- Asli D.A. Tasci, "Lenient gun laws, perceived risk of gun violence, and attitude towards a destination", Journal of Destination Marketing & Management, 13, pp.24~38 (2019), Elsevier BV[DOI]
- Beom Kwon, "Toward an Online Continual Learning Architecture for Intrusion Detection of Video Surveillance", IEEE Access, 10, pp.89732~89744 (2022), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Pedro Canotilho Ribeiro, "RIMOC, a feature to discriminate unstructured motions: Application to violence detection for video-surveillance", Computer Vision and Image Understanding, 144, pp.121~143 (2016), Elsevier BV[DOI]
- G. Sreenu, "Intelligent video surveillance: a review through deep learning techniques for crowd analysis", Journal of Big Data, 6(1) (2019), Springer Science and Business Media LLC[DOI]
- Amira Ben Mabrouk, "Abnormal behavior recognition for intelligent video surveillance systems: A review", Expert Systems with Applications, 91, pp.480~491 (2018), Elsevier BV[DOI]
- Beom Kwon, "Implementation of a Virtual Training Simulator Based on 360° Multi-View Human Action Recognition", IEEE Access, 5, pp.12496~12511 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Youddha Beer Singh, "A systematic literature review of speech emotion recognition approaches", Neurocomputing, 492, pp.245~263 (2022), Elsevier BV[DOI]
- Felipe Zago Canal, "A survey on facial emotion recognition techniques: A state-of-the-art literature review", Information Sciences, 582, pp.593~617 (2022), Elsevier BV[DOI]
- Kyoungoh Lee, "From Human Pose Similarity Metric to 3D Human Pose Estimator: Temporal Propagating LSTM Networks", IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2), pp.1781~1797 (2023), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Beom Kwon, "Human Skeleton Data Augmentation for Person Identification over Deep Neural Network", Applied Sciences, 10(14), pp.4849~ (2020), MDPI AG[DOI]
- Beom Kwon, "Joint Swing Energy for Skeleton-Based Gender Classification", IEEE Access, 9, pp.28334~28348 (2021), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Beom 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), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Beom Kwon, "Ensemble Learning for Skeleton-Based Body Mass Index Classification", Applied Sciences, 10(21), pp.7812~ (2020), MDPI AG[DOI]
- B. Kwon, "Implementation of Human Action Recognition System Using Multiple Kinect Sensors", Proc. 16th Pacific Rim Conference on Multimedia (PCM), pp.334~343 (2015)
- B. Kwon, "An Enhanced Multi-View Human Action Recognition System for Virtual Training Simulator", Proc. Asia–Pacific Signal and Information Processing Association Annual Summit Conference (APSIPA ASC), pp.1~4 (2016)
- Joann M. Montepare, "The identification of emotions from gait information", Journal of Nonverbal Behavior, 11(1), pp.33~42 (1987), Springer Science and Business Media LLC[DOI]
- E. Crane, "Motion Capture and Emotion : Affect Detection in Whole Body Movement", Proceedings of the 2nd International Conference on Affective Computing Intelligent Interaction (ACII), pp.95~101 (2007)
- M. Karg, "Expression and Automatic Recognition of Exhaustion in Natural Walking", Proceedings of IADIS International Conference on Interfaces and Human Computer Interaction (IHCI), pp.165~172 (2008)
- M. Karg, "A Two-Fold PCA-Approach for Inter-Individual Recognition of Emotions in Natural Walking", Proceeding of the 6th International Conference on Machine Learning and Data Mining in Pattern Recognition (MLDM), pp.51~61 (2009)
- M. Karg, "A Comparison of PCA, KPCA and LDA for Feature Extraction to Recognize Affect in Gait Kinematics", Proceedings of the 3rd International Conference on Affective Computing Intelligent Interaction and Workshops (ACIIW), pp.1~6 (2009)
- Michelle Karg, "Recognition of Affect Based on Gait Patterns", IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 40(4), pp.1050~1061 (2010), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Baobin Li, "Identifying Emotions from Non-Contact Gaits Information Based on Microsoft Kinects", IEEE Transactions on Affective Computing, 9(4), pp.585~591 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- P. Xue, "Emotion Recognition from Human Gait Features Based on DCT Transform", Proceedings of International Conference on Human Centered Computing (HCC), pp.511~517 (2019)
- Y. Zhuang, "G-GCSN : Global Graph Convolution Shrinkage Network for Emotion Perception from Gait", Proceedings of the 15th Asian Conference on Computer Vision (ACCV), pp.46~57 (2020)
- V. Narayanan, "ProxEmo: Gait-Based Emotion Learning and Multi-view Proxemic Fusion for Socially-Aware Robot Navigation", Proceedings of IEEE, 2021, 8200~8207
- U. Bhattacharya, "STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits", Proceedings of the AAAI Conference Artificial Intelligence, pp.1342~1350 (2020)
- Y. Ma, "A Motion Capture Library for the Study of Identity, Gender, and Emotion Perception from Biological Motion", Behavior Research Methods, 38(1), pp.134~141 (2006)[DOI]