복합 낙상 시나리오 영상에서의 Transformer 모델 최적화 및 성능 평가

Acknowledgments

This work was supported by the Ministry of Education of the Republic of Korea and the National Research Foundation of Korea (NRF-2023S1A5A8079952).

References

• 박영석, 이종섭, 연지영, 최정일 (2021). “노인장기요양시설에서의 웰니스 IT서비스 특성과 이용의도와의 관계,” 경영학연구, 제50권 1호, pp.143-171.
  Park, Y S., Lee J. S., Yeon, J. Y. and Choi J. I. (2021). “The Relationship of Wellness IT Service Characteristics and Intention to Use in Long-Term Care Facilities for the Elderly,” Korean Management Review, 50 (1), 143-171. [ https://doi.org/10.17287/kmr.2021.50.1.143 ]
• 이한신 김판수 (2019). “소비자의 기술수용과 저항이 인공지능(AI) 사용의도에 미치는 영향,” 경영학연구, 제48권 5호, pp.1195-1219.
  Yi, H. S. and Kim, P. S. (2019). “The Effect of Consumer’s Technology Acceptance and Resistance on Intention to Use of Artificial Intelligence (AI),” Korean Management Review, 48(5), pp.1195-1219. [ https://doi.org/10.17287/kmr.2019.48.5.1195 ]
• 정옥경, 이중원, 박철 (2024). “디지털 헬스케어 고객경험이 서비스 만족과 주관적 웰빙에 미치는 영향: 원격진료 서비스를 중심으로,” 경영학연구, 제53권 3호, pp.729-759.
  Jung, O. K., Lee, J. W. and Park, C. (2024). “Effects of Customer Experience of the Digital Healthcare on Service Satisfaction and Subjective Well-Being: Focusing on Telemedicine Services,” Korean Management Review, 53(3), pp.729-759. [ https://doi.org/10.17287/kmr.2024.53.3.729 ]
• 한국지능정보사회진흥원. “낙상사고 위험동작 영상-센서 쌍 데이터,” AI-Hub, https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=data&dataSetSn=71641, , 2025년 4월 6일 접속.
  National Information Society Agency. “Video-Sensor Paired Data for Fall Risk Behaviors,” AI-Hub, https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=data&dataSetSn=71641, , retrieved April 6, 2025.
• 한국지능정보사회진흥원. “AI 허브,” AI-Hub, https://www.aihub.or.kr/, , 2025년 4월 2일 접속.
  National Information Society Agency. “AI Hub,” AI-Hub, https://www.aihub.or.kr/, , retrieved April 2, 2025.
• Aderinola, T. B., Palmerini, L., D’Ascanio, I., Chiari, L., Klenk, J., Becker, C., Caulfield, B., & Ifrim, G. (2025). “Accurate and efficient real-world fall detection using time series techniques. In G. Ifrim, T. B. Aderinola, & B. Caulfield (Eds.),” Advanced Analytics and Learning on Temporal Data (pp.52-79). Springer Nature Switzerland. [https://doi.org/10.1007/978-3-031-53317-2_4]
• Alanazi, T., Babutain, K., and Muhammad, G. (2024). “Mitigating Human Fall Injuries: A Novel System Utilizing 3D 4-Stream Convolutional Neural Networks and Image Fusion,” Image and Vision Computing, 148, 105153. [https://doi.org/10.1016/j.imavis.2024.105153]
• Alam, E., Sufian, A., Dutta, P., and Leo, M. (2022). “Vision-based human fall detection systems using deep learning: A review,” Computers in Biology and Medicine, 146, 105626. [https://doi.org/10.1016/j.compbiomed.2022.105626]
• Al-qaness, M. A., Dahou, A., Abd Elaziz, M., and Helmi, A. M. (2024). “Human activity recognition and fall detection using convolutional neural network and transformer-based architecture,” Biomedical Signal Processing and Control, 95, 106412. [https://doi.org/10.1016/j.bspc.2024.106412]
• Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lučić, M., and Schmid, C. (2021). “Vivit: A video vision transformer,” in Proceedings of the IEEE/CVF international conference on computer vision, pp.6836-6846. [https://doi.org/10.1109/ICCV48922.2021.00676]
• Ashfaq, M., Yun, J., Yu, S., and Loureiro, S. M. C. (2020). “I, Chatbot: Modeling the determinants of users’ satisfaction and continuance intention of AI-powered service agents,” Telematics and Informatics, 54, 101473. [https://doi.org/10.1016/j.tele.2020.101473]
• Assanovich, B., & Kosarava, K. (2025). “Vision-Based Fall Detector for Elderly Based on Sliding Window Approach and Feature Engineering,” Journal of Data Science and Intelligent Systems, 3(1), pp.27-34. [https://doi.org/10.47852/bonviewJDSIS42024100]
• Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization. arXiv. https://arxiv.org/abs/1607.06450, .
• Bertasius, G., Wang, H., and Torresani, L. (2021). “Is space-time attention all you need for video understanding?,” in proceeding of the International Conference on Machine Learning (ICML), Virtual.
• Durga Bhavani, K. and Ferni Ukrit, M. (2024). “Design of inception with deep convolutional neural network based fall detection and classification model,” Multimedia Tools and Applications, 83(8), pp.23799-23817. [https://doi.org/10.1007/s11042-023-16476-6]
• Blackburn, J., Ousey, K., Stephenson, J., and Lui, S. (2022). “Exploring the impact of experiencing a long lie fall on physical and clinical outcomes in older people requiring an ambulance: A systematic review,” International Emergency Nursing, 62, 101148. [https://doi.org/10.1016/j.ienj.2022.101148]
• Bui, T., Liu, J., Cao, J., Wei, G., and Zeng, Q. (2024). “Elderly fall detection in complex environment based on improved YOLOv5s and LSTM,” Applied Sciences, 14(19), 9028. [https://doi.org/10.3390/app14199028]
• Cao, Y., Guo, M., Sun, J., Chen, X., and Qiu, J. (2024). “Fall detection based on LCNN and fusion model of weights using human skeleton and optical flow,” Signal, Image and Video Processing, 18(1), pp.833-841. [https://doi.org/10.1007/s11760-023-02776-9]
• Carreira, J. and Zisserman, A. (2017). “Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset,” in proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.6299-6308, Honolulu, Hawaii. [https://doi.org/10.1109/CVPR.2017.502]
• Chawan, V. R., Huber, M., Burns, N., and Daniel, K. (2022). “Person identification and tinetti score prediction using balance parameters: A machine learning approach to determine fall risk,” in proceeding of the 15th international conference on PErvasive technologies related to assistive environments, pp.203-212. [https://doi.org/10.1145/3529190.3529223]
• Chatterjee, S., Rana, N. P., Dwivedi, Y. K., and Baabdullah, A. M. (2021). “Understanding AI adoption in manufacturing and production firms using an integrated TAM-TOE model,” Technological Forecasting and Social Change, 170, 120880. [https://doi.org/10.1016/j.techfore.2021.120880]
• Chen, X., Liang, C., Huang, D., Real, E., Wang, K., Pham, H., Dong, X., Luong, T., Hsieh, C. J., Lu, Y., and Le, Q. V. (2023). “Symbolic Discovery of Optimization Algorithms,” Advances in Neural Information Processing Systems, 36, pp.49205-49233.
• Chu, X., Tian, Z., Zhang, B., Wang, X., & Shen, C. (2021). Conditional positional encodings for vision transformers. arXiv. https://arxiv.org/abs/2102.10882
• Chutimawattanakul, P. and Samanpiboon, P. (2022). “Fall detection for the elderly using yolov4 and lstm,” in proceeding of the 2022 19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), pp.1-5. [https://doi.org/10.1109/ECTI-CON54298.2022.9795534]
• Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv. https://arxiv.org/abs/2010.11929
• El-Bendary, N., Tan, Q., Pivot, F. C., & Lam, A. (2013). “Fall Detection and Prevention for the Elderly: A Review of Trends and Challenges,” International Journal on Smart Sensing and Intelligent Systems, 6(3), pp. 1230. [https://doi.org/10.21307/ijssis-2017-588]
• Ergüder, H., Uzun, T., & Baday, M. (2024). “Advancing Fall Detection Utilizing Skeletal Joint Image Representation and Deformable Layers,” Image Analysis and Stereology, 43(1), pp. 97-107. [https://doi.org/10.5566/ias.3087]
• Espinosa, R., Ponce, H., Gutiérrez, S., Martínez-Villaseñor, L., Brieva, J., & Moya-Albor, E. (2019). “A Vision-Based Approach for Fall Detection Using Multiple Cameras and Convolutional Neural Networks: A Case Study Using the UP-Fall Detection Dataset,” Computers in Biology and Medicine, 115, pp. 103520. [https://doi.org/10.1016/j.compbiomed.2019.103520]
• Feichtenhofer, C. (2020). “X3d: Expanding architectures for efficient video recognition,” in proceeding of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA. [https://doi.org/10.1109/CVPR42600.2020.00028]
• Florence, C. S., Bergen, G., Atherly, A., Burns, E., Stevens, J., and Drake, C. (2018). “Medical costs of fatal and nonfatal falls in older adults,” Journal of the American Geriatrics Society, 66(4), pp.693-698. [https://doi.org/10.1111/jgs.15304]
• Gao, M., Li, J., Zhou, D., Zhi, Y., Zhang, M., and Li, B. (2023). “Fall detection based on OpenPose and MobileNetV2 network,” IET Image Processing, 17(3), pp.722-732. [https://doi.org/10.1049/ipr2.12667]
• Gutiérrez, J., Rodríguez, V., and Martin, S. (2021). “Comprehensive review of vision-based fall detection systems,” Sensors, 21(3), pp.947. [https://doi.org/10.3390/s21030947]
• Hawley-Hague, H., Boulton, E., Hall, A., Pfeiffer, K., and Todd, C. (2014). “Human factors and adherence to home-based exercise programs in older adults at risk of falling: A systematic review,” Physical Therapy, 94(3), pp.319-336.
• Hoang, V. H., Lee, J. W., Piran, M. J., and Park, C. S. (2023). “Advances in skeleton-based fall detection in RGB videos: From handcrafted to deep learning approaches,” IEEE Access, 11, pp.92322-92352. [https://doi.org/10.1109/ACCESS.2023.3307138]
• Ioffe, S. and Szegedy, C. (2015). “Batch normalization : Accelerating deep network training by reducing internal covariate shift,” in proceeding of the International conference on machine learning, Lille, France.
• Inturi, A. R., Manikandan, V. M., and Garrapally, V. (2023). “A novel vision-based fall detection scheme using keypoints of human skeleton with long short-term memory network,” Arabian Journal for Science and Engineering, 48(2), pp.1143-1155. [https://doi.org/10.1007/s13369-022-06684-x]
• Islam, M. A., Jia, S., & Bruce, N. D. (2020). How much position information do convolutional neural networks encode?. arXiv. https://arxiv.org/abs/2001.08248, .
• Kaur, N., Rani, S., and Kaur, S. (2024). “Real-time video surveillance based human fall detection system using hybrid haar cascade classifier,” Multimedia Tools and Applications, 83(28), pp.71599-71617. [https://doi.org/10.1007/s11042-024-18305-w]
• Keskes, O. and Noumeir, R. (2021). “Vision-based fall detection using st-gcn,” IEEE Access, 9, pp.28224-28236. [https://doi.org/10.1109/ACCESS.2021.3058219]
• Kim, S., Kim, S., Woo, S., Oh, J., Son, Y., Jacob, L., Soysal, P., Park, J., Chen, L-K., and Yon, D. K. (2025). “Temporal trends and patterns in mortality from falls across 59 high-income and upper-middle-income countries, 1990–2021, with projections up to 2040: a global time-series analysis and modelling study,” The Lancet Healthy Longevity, 6(1), p.100672. [https://doi.org/10.1016/j.lanhl.2024.100672]
• Kingma, D. P. and Ba, J. L. (2015). “Adam: A method for stochastic optimization,” in Proceedings of the 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA.
• Knowles, B. and Hanson, V. L. (2018). “The wisdom of older technology (non) users,” Communications of the ACM, 61(3), pp.72-77. [https://doi.org/10.1145/3179995]
• Kwolek, B. and Kepski, M. (2014). “Human fall detection on embedded platform using depth maps and wireless accelerometer,” Computer Methods and Programs in Biomedicine, 117 (3), pp.489-501. [https://doi.org/10.1016/j.cmpb.2014.09.005]
• Li, K., Wang, Y., Gao, P., Song, G., Liu, Y., Li, H., & Qiao, Y. (2022). Uniformer: unified transformer for efficient spatiotemporal representation learning. arXiv. https://arxiv.org/abs/2201.04676
• Li, X., Wang, Y., Zhou, Z., and Qiao, Y. (2020). “Smallbignet: Integrating core and contextual views for video classification,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. [https://doi.org/10.1109/CVPR42600.2020.00117]
• Lin, T. Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017). “Focal loss for dense object detection,” in Proceedings of the IEEE international conference on computer vision, Venice, Italy. [https://doi.org/10.1109/ICCV.2017.324]
• Liu, W., Liu, X., Hu, Y., Shi, J., Chen, X., Zhao, J., Wang, S., and Hu, Q. (2022). “Fall detection for shipboard seafarers based on optimized BlazePose and LSTM,” Sensors, 22(14), p. 5449. [https://doi.org/10.3390/s22145449]
• Loshchilov, I., & Hutter, F. (2017). Fixing weight decay regularization in Adam. arXiv. https://arxiv.org/abs/1711.05101
• Luo, B. (2023). “Human fall detection for smart home caring using Yolo networks,” International Journal of Advanced Computer Science and Applications, 14(4), pp.53-58. [https://doi.org/10.14569/IJACSA.2023.0140409]
• Martínez-Villaseñor, L., Ponce, H., Brieva, J., Moya-Albor, E., Núñez-Martínez, J., and Peñafort-Asturiano, C. (2019). “UP-fall detection dataset: A multimodal approach,” Sensors, 19(9), p.1988. [https://doi.org/10.3390/s19091988]
• McCall, S., Kolawole, S. S., Naz, A., Gong, L., Ahmed, S. W., Prasad, P. S., and Ardakani, S. P. (2024). “Computer Vision Based Transfer Learning-Aided Transformer Model for Fall Detection and Prediction,” IEEE Access, 12, pp.28798-28809. [https://doi.org/10.1109/ACCESS.2024.3368065]
• Mobsite, S., Alaoui, N., Boulmalf, M., and Ghogho, M. (2023). “Semantic segmentation-based system for fall detection and post-fall posture classification,” Engineering Applications of Artificial Intelligence, 117, 105616. [https://doi.org/10.1016/j.engappai.2022.105616]
• Mudiyanselage, S. P. K., Yao, C. T., Maithreepala, S. D., and Lee, B. O. (2024). “Emerging Digital Technologies Used for Fall Detection in Older Adults in Aged Care: A Scoping Review,” Journal of the American Medical Directors Association, 26(1), 105330. [https://doi.org/10.1016/j.jamda.2024.105330]
• Mujirishvili, T., Maidhof, C., Florez-Revuelta, F., Ziefle, M., Richart-Martinez, M., and Cabrero-García, J. (2023). “Acceptance and Privacy Perceptions Toward Video-based Active and Assisted Living Technologies: Scoping Review,” Journal of Medical Internet Research, 25, e45297. [https://doi.org/10.2196/45297]
• Nevi, G., Pizzichini, L., Bastone, A., and Dezi, L. (2025). “Adoption of AI by micro and small health enterprises: effects of entrepreneurial orientation on the TOE model,” European Journal of Innovation Management, forthcoming. [https://doi.org/10.1108/EJIM-07-2024-0770]
• Núñez-Marcos, A. and Arganda-Carreras, I. (2024). “Transformer-based fall detection in videos,” Engineering Applications of Artificial Intelligence, 132, 107937. [https://doi.org/10.1016/j.engappai.2024.107937]
• Ramirez, H., Velastin, S. A., Meza, I., Fabregas, E., Makris, D., and Farias, G. (2021). “Fall detection and activity recognition using human skeleton features,” IEEE Access, 9, pp.33532-33542. [https://doi.org/10.1109/ACCESS.2021.3061626]
• Ramirez, H., Velastin, S. A., Cuellar, S., Fabregas, E., and Farias, G. (2023). “BERT for activity recognition using sequences of skeleton features and data augmentation with GAN,” Sensors, 23(3), 1400. [https://doi.org/10.3390/s23031400]
• Ren, L. and Peng, Y. (2019). “Research of fall detection and fall prevention technologies: A systematic review,” IEEE Access, 7, pp. 77702-77722. [https://doi.org/10.1109/ACCESS.2019.2922708]
• Richardson, S., Lawrence, K., Schoenthaler, A., and Mann, D. (2022). “A framework for digital health equity,” NPJ Digital Medicine, 5(1), 119. [https://doi.org/10.1038/s41746-022-00663-0]
• Salimi, M., Machado, J. J., and Tavares, J. M. R. (2022). “Using deep neural networks for human fall detection based on pose estimation,” Sensors, 22(12), 4544. [https://doi.org/10.3390/s22124544]
• Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L. C. (2018). “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, Utah, USA. [https://doi.org/10.1109/CVPR.2018.00474]
• Shazeer, N. (2020). Glu variants improve transformer. arXiv. https://arxiv.org/abs/2002.05202
• Smith, L. N. (2018). A disciplined approach to neural network hyper-parameters: Part 1--learning rate, batch size, momentum, and weight decay. arXiv. https://arxiv.org/abs/1803.09820
• Su, C., Wei, J., Lin, D., Kong, L., & Guan, Y. L. (2024). A novel model for fall detection and action recognition combined lightweight 3D-CNN and convolutional LSTM networks. Pattern Analysis and Applications, 27(1), Article 3. [https://doi.org/10.1007/s10044-023-01181-z]
• Suarez, J. J. P., Orillaza, N., and Naval, P. (2022). “AFAR: A real-time vision-based activity monitoring and fall detection framework using 1D convolutional neural networks,” in Proceedings of the 2022 14th International Conference on Machine Learning and Computing, pp.555-559. [https://doi.org/10.1145/3529836.3529916]
• Sykes, E. R. (2025). “Next-generation fall detection: harnessing human pose estimation and transformer technology,” Health Systems, 14(2), pp.85-103. [https://doi.org/10.1080/20476965.2024.2395574]
• Tran, D., Bourdev, L., Fergus, R., Torresani, L., and Paluri, M. (2015). “Learning spatiotemporal features with 3D convolutional networks,” in Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4489-4497, Santiago, Chile. [https://doi.org/10.1109/ICCV.2015.510]
• Tran, D., Wang, H., Torresani, L., and Feiszli, M. (2019). “Video classification with channel-separated convolutional networks,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, South Korea, IEEE, pp.5552-5561. [https://doi.org/10.1109/ICCV.2019.00565]
• Ursul, I. (2024). “Elderly Fall Detection Using Unsupervised Transformer Model,” Electronics and information technologies/Електроніка та інформаційні технології, 26. [https://doi.org/10.30970/eli.26.7]
• Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). “Attention is all you need,” in Advances in Neural Information Processing Systems 30, Long Beach, CA, USA, Curran Associates, Inc., pp.5998-6008.
• Wamba-Taguimdje, S. L., Wamba, S. F., Kamdjoug, J. R. K., and Wanko, C. E. T. (2020). “Influence of artificial intelligence (AI) on firm performance: the business value of AI-based transformation projects,” Business Process Management Journal, 26(7), pp.1893-1924. [https://doi.org/10.1108/BPMJ-10-2019-0411]
• Wang, J., Lan, C., Liu, C., Ouyang, Y., Qin, T., Lu, W., Hou, W., Chen, Y., and Yu, P. S. (2023). “Generalizing to Unseen Domains: A Survey on Domain Generalization,” IEEE Transactions on Knowledge and Data Engineering, 35(8), pp.8052-8072.
• Wang, H., Xu, S., Chen, Y., and Su, C. (2025). “LFD-YOLO: a lightweight fall detection network with enhanced feature extraction and fusion,” Scientific Reports, 15(1), pp. 5069. [https://doi.org/10.1038/s41598-025-89214-7]
• Wang, X., Ellul, J., and Azzopardi, G. (2020). “Elderly fall detection systems: A literature survey,” Frontiers in Robotics and AI, 7, pp.71. [https://doi.org/10.3389/frobt.2020.00071]
• Wang, X., Girshick, R., Gupta, A., and He, K. (2018). “Non-local neural networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, pp.7794-7803. [https://doi.org/10.1109/CVPR.2018.00813]
• World Health Organization, “Falls,” World Health Organization, https://www.who.int/news-room/fact-sheets/detail/falls, , retrieved July 2025.
• Wu, Y. and He, K. (2018). “Group normalization,” in Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, pp.3-19. [https://doi.org/10.1007/978-3-030-01261-8_1]
• Xu, D., Wang, Y., Zhu, S., Zhao, M., and Wang, K. (2024). “Relationship between fear of falling and quality of life in nursing home residents: The role of activity restriction,” Geriatric Nursing, 57, pp.45-50. [https://doi.org/10.1016/j.gerinurse.2024.03.006]
• Xun, J., Wang, X., Wang, X., Fan, X., Yang, P., and Zhang, Z. (2025). “An efficient algorithm for pedestrian fall detection in various image degradation scenarios based on YOLOv8n,” Scientific Reports, 15, pp.9036. [https://doi.org/10.1038/s41598-025-93667-1]
• Yadav, S. K., Luthra, A., Tiwari, K., Pandey, H. M., and Akbar, S. A. (2022). “ARFDNet: An efficient activity recognition & fall detection system using latent feature pooling,” Knowledge-Based Systems, 239, pp.107948. [https://doi.org/10.1016/j.knosys.2021.107948]
• Yu, M., Gong, L., and Kollias, S. (2017). “Computer vision based fall detection by a convolutional neural network,” in Proceedings of the 19th ACM International Conference on Multimodal Interaction, Glasgow, UK, Association for Computing Machinery, pp.416-420. [https://doi.org/10.1145/3136755.3136802]
• Yu, X., Wang, C., Wu, W., and Xiong, S. (2025). “A Real-time Skeleton-based Fall Detection Algorithm based on Temporal Convolutional Networks and Transformer Encoder,” Pervasive and Mobile Computing, 102016. [https://doi.org/10.1016/j.pmcj.2025.102016]
• Zahan, S., Hassan, G. M., and Mian, A. (2022). “Sdfa: Structure-aware discriminative feature aggregation for efficient human fall detection in video,” IEEE Transactions on Industrial Informatics, 19(8), pp.8713-8721. [https://doi.org/10.1109/TII.2022.3221208]
• Zhang, M., Lucas, J., Ba, J., and Hinton, G. E. (2019). “Lookahead optimizer: k steps forward, 1 step back,” in Advances in Neural Information Processing Systems 32, Vancouver, BC, Canada, Curran Associates, Inc., pp.9188-9198.