To address the noise issue in experimentally acquired body pressure distribution data, this study proposes a convolutional autoencoder-based data reconstruction method to enhance data quality and usability. First, the body pressure distribution data is normalized. And Gaussian noise is added to construct the training set. A convolutional autoencoder model is designed and used for feature extraction and denoising. Subsequently, experimentally collected body pressure distribution data is utilized as the test set to evaluate the accuracy and stability of the reconstruction results. Experimental results demonstrate that the model achieves a mean relative error of 0.010 with a standard deviation of 0.018 across 98 test samples, indicating high accuracy and stability. Finally, the trained model is applied to process experimentally collected body pressure data, revealing the variation patterns of pressure distribution metrics with seat positions.
TANGJ Y, WEIH J .Evaluation method and application of static comfort of car seat[J].Auto Time, 2022(8):160-161.(in Chinese)
[3]
MASTRIGTS H V, GROENESTEIJNL, VINKP, et al .Predicting passenger seat comfort and discomfort on the basis of human, context and seat characteristics:a literature review[J].Ergonomics, 2017, 60(7):889-911.
GAOK Z, LUOQ, ZHANGZ F, et al .Vibration comfort evaluation of vehicle seat based on body pressure distribution[J].Automotive Engineering, 2022, 44(12):1936-1943,1963.(in Chinese)
[6]
HUANGQ Y, JINX P, GAOM Y, et al. Influence of lumbar support on tractor seat comfort based on body pressure distribution[J]. PloS ONE, 2023, 18(4): 1-17.
PENG Q, YUAN H, GUO W, et al, Study on the law of automobile seat body pressure distribution and strategy of Automobile Seat Adjustment[J]. Machine Design & Research, 2023, 39(3): 185-192. (in Chinese)
FANX Y, ZHENH T, SHANGZ Y,et al. Similarity measurement of neuronal morphology based on convolutional auto-encoder and spatial registration[J]. Chinese Journal of Biomedical Engineering, 2023, 42(1): 62-73. (in Chinese)
[11]
WEIL, GUOX X, TIANX L, et al .Three-dimensional autoencoder for the flow field reconstruction of an inclined circular disk[J].Ocean Engineering, 2024, 299: 117284.
WANGY C, LIUL T, XUH Z. Noisy gravity data reconstruction using the convolutional autoencoder[J]. Geomatics and Information Science of Wuhan University, 2022, 47(4):543-550.(in Chinese)
[14]
FAINSTEINF, CATONIJ, ELEMANSC P H, et al. The reconstruction of flows from spatiotemporal data by autoencoders[J]. Chaos, Solitons & Fractals, 2023, 176: 114115.
[15]
BOURLARDH, KAMPY. Auto-association by multilayer perceptrons and singular value decomposition[J]. Biological Cybernetics, 1988, 59(4/5): 291-294.
[16]
VINCENTP, LAROCHELLEH, BENGIOY, et al .Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th International Conference on Machine Learning.July 5-9, 2008, Helsinki, Finland. ACM, 2008:1096-1103.
[17]
MASCIJ, MEIERU, CIREŞAND, et al .Stacked convolutional auto-encoders for hierarchical feature extraction[C]// Artificial Neural Networks and Machine Learning-ICANN 2011. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011: 52-59.
基金资助
广西重点研发计划项目(AB23026112)
Key Research and Development Program of Guangxi(AB23026112)