|
|
开放场景睡姿识别方法：基于投票的新颖性检测
|
Abstract:
传统的睡眠姿势识别模型通常是在已知明确类别的数据集上训练的，而这种基于封闭集识别的方法在遇到一些奇特罕见的睡姿时容易将其误分类为已知的睡眠姿势，从而导致睡姿识别系统在开放环境下的可靠性与适用性大大降低。为了解决这个问题，提出一种基于开放集识别的睡姿检测模型。该模型主要完成两个任务：标准监督分类和新颖性检测。当样本被输入到模型时，分类器可以根据样本的新颖性得分，采用阈值比较，判断输入样本是未知或者识别为已知类别。模型分别在压力图和RGB图上做了验证，实验结果表明在开放场景下，该模型不仅能够准确识别已知的睡姿类别，识别率达到99%，而且能够有效地甄别出未知的睡姿，AUROC值达到92%，AUPR值达到95%。
Traditional sleep posture recognition models are usually trained on datasets with known and well-defined categories. However, this closed-set recognition method tends to misclassify some unusual and rare sleep postures as known sleep postures, which greatly reduces the reliability and applicability of the sleep posture recognition system in open environments. To address this issue, a novel open-set sleep posture detection model is proposed. This model performs two tasks: standard supervised classification and novelty detection. When a sample is input into the model, the classifier can determine whether the input sample is unknown or recognized as a known category based on the sample’s novelty score, using a threshold comparison. The model is validated on both pressure maps and RGB images, and experimental results show that in open scenarios, the model not only accurately recognizes known sleep posture categories with a recognition rate of 99%, but also effectively identifies unknown sleep postures, with an AUROC of 92% and an AUPR of 95%.
| [1] | Cartwright, R.D. (1984) Effect of Sleep Position on Sleep Apnea Severity. Sleep, 7, 110-114.
https://doi.org/10.1093/sleep/7.2.110 |
| [2] | Gay, P.C. (2004) Chronic Obstructive Pulmonary Disease and Sleep. Respiratory Care, 49, 39-52. |
| [3] | Heydarzadeh, M., Nourani, M. and Ostadabbas, S. (2016) In-Bed Posture Classification Using Deep Autoencoders. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, 16-20 August 2016, 3839-3842. https://doi.org/10.1109/EMBC.2016.7591565 |
| [4] | Tang, K., Kumar, A., Nadeem, M., et al. (2021) CNN-Based Smart Sleep Posture Recognition System. IoT, 2, 119-139.
https://doi.org/10.3390/iot2010007 |
| [5] | Viriyavit, W., Sornlertlamvanich, V., Kongprawechnon, W., et al. (2017) Neural Network Based Bed Posture Classification Enhanced by Bayesian Approach. 2017 8th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES), Chennai, 23-24 February 2017, 1-5.
https://doi.org/10.1109/ICTEmSys.2017.7958769 |
| [6] | Ren, W., Ma, O., Ji, H., et al. (2020) Human Posture Recognition Using a Hybrid of Fuzzy Logic and Machine Learning Approaches. IEEE Access, 8, 135628-135639. https://doi.org/10.1109/ACCESS.2020.3011697 |
| [7] | Yu, M.C., Wu, H., Liou, J.L., et al. (2013) Multiparameter Sleep Monitoring Using a Depth Camera. Biomedical Engineering Systems and Technologies: 5th International Joint Conference, BIOSTEC 2012, Vilamoura, 1-4 February 2012, 311-325. |
| [8] | Kuo, C.H., Yang, F.C., Tsai, M.Y., et al. (2004) Artificial Neural Networks Based Sleep Motion Recognition Using Night Vision Cameras. Biomedical Engineering: Applications, Basis and Communications, 16, 79-86.
https://doi.org/10.4015/S101623720400013X |
| [9] | Lee, H.J., Hwang, S.H., Lee, S.M., et al. (2013) Estimation of Body Postures on Bed Using Unconstrained ECG Measurements. IEEE Journal of Biomedical and Health Informatics, 17, 985-993.
https://doi.org/10.1109/JBHI.2013.2252911 |
| [10] | Scheirer, W.J., de Rezende Rocha, A., Sapkota, A., et al. (2012) Toward Open Set Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 1757-1772. https://doi.org/10.1109/TPAMI.2012.256 |
| [11] | Pouyan, M.B., Birjandtalab, J., Heydarzadeh, M., et al. (2017) A Pressure Map Dataset for Posture and Subject Analytics. 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Orlando, 16-19 February 2017, 65-68. https://doi.org/10.1109/BHI.2017.7897206 |
| [12] | Vaze, S., Han, K., Vedaldi, A., et al. (2021) Open-Set Recognition: A Good Closed-Set Classifier Is All You Need. |
| [13] | Sch？lkopf, B., Platt, J.C., Shawe-Taylor, J., et al. (2001) Estimating the Support of a High-Dimensional Distribution. Neural Computation, 13, 1443-1471. https://doi.org/10.1162/089976601750264965 |
| [14] | Pimentel, M.A.F., Clifton, D.A., Clifton, L., et al. (2014) A Review of Novelty Detection. Signal Processing, 99, 215-249. https://doi.org/10.1016/j.sigpro.2013.12.026 |
| [15] | Hassen, M. and Chan, P.K. (2020) Learning a Neural-Network-Based Representation for Open Set Recognition. Proceedings of the 2020 SIAM International Conference on Data Mining, Cincinnati, 7-9 May 2020, 154-162.
https://doi.org/10.1137/1.9781611976236.18 |
| [16] | Yang, Y., Hou, C., Lang, Y., et al. (2019) Open-Set Human Activity Recognition Based on Micro-Doppler Signatures. Pattern Recognition, 85, 60-69. https://doi.org/10.1016/j.patcog.2018.07.030 |
| [17] | Roitberg, A., Ma, C., Haurilet, M., et al. (2020) Open Set Driver Activity Recognition. 2020 IEEE Intelligent Vehicles Symposium, Vol. 4, 1048-1053. https://doi.org/10.1109/IV47402.2020.9304605 |
| [18] | Gal, Y. and Ghahramani, Z. (2016) Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. International Conference on Machine Learning, New York, 20-22 June 2016, 1050-1059. |
| [19] | Davis, J. and Goadrich, M. (2006) The Relationship between Precision-Recall and ROC Curves. Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, 25-29 June 2006, 233-240.
https://doi.org/10.1145/1143844.1143874 |
| [20] | Manning, C. and Schutze, H. (1999) Foundations of Statistical Natural Language Processing. MIT Press, Cambridge. |
