Биология ва тиббиёт муаммолари 2025, №3 (161)

Тема статьи

Z-TRANSCGAN: A Z-SCORE NORMALIZED TRANSFORMER-BASED CONDITIONAL GAN FOR GAIT DATA AUGMENTATION (262-272)

Авторы

Yuanyuan Sun, Fei Liu, Yue Yang, Huarong Shao, Shodikulova Gulandom Zikriyayevna, Babamuradova Zarrina Bakhtiyarovna, Bing Ji

Учреждение

1 - School of Control Science and Engineering, Shandong University, Jinan, 250061, China; 2 - Engineering Research Center for Sugar and Sugar Complex, National-Local Joint Engineering Laboratory of Polysac-charide Drugs, Key Laboratory of Carbohydrate and Glycoconjugate Drugs, Shandong Academy of Pharmaceutical Sci-ence, Jinan, Shandong 250101, China; 3 - Samarkand State Medical University, Republic of Uzbekistan, Samarkand

Аннотация

Gait analysis is essential for disease diagnosis, identity verification, and rehabilitation assessment. However, the effectiveness of deep learning approaches in gait analysis is hindered by the difficulty of collecting large-scale, high-quality gait time-series data, which is costly, labor-intensive, and subject to strict privacy regulations. Experimental findings on the HOA dataset indicate that Z-TransCGAN surpasses TTS-CGAN, achieving a 1.42% increase in average classification accuracy (ACC) and a 0.85% increase in the area under the curve (AUC). These results validate the efficacy of Z-TransCGAN as a data augmentation strategy for gait analysis, improving both synthetic data generation and downstream classification performance.

Ключевые слова

Deep learning; Conditional Generative Adversarial Networks (CGANs); Gait analysis; Data augmentation; Transformer.

Литературы

[1] Tran L, Choi D. Data augmentation for inertial sen-sor-based gait deep neural network[J]. IEEE Access, 2020, 8: 12364-12378. [2] Li J B, Farrell J W, Valles D. Data Augmentation for Classifying Multiple Sclerosis Severity through Iner-tial Measurement Unit-Based Gait Analysis[C]//2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2024: 6443-6450. [3] Duong H T, Nguyen-Thi T A. A review: preprocessing techniques and data augmentation for sentiment analysis[J]. Computational Social Networks, 2021, 8(1): 1. [4] Cao P, Li X, Mao K, et al. A novel data augmentation method to enhance deep neural networks for detection of atrial fibrillation[J]. Biomedical Signal Processing and Control, 2020, 56: 101675. [5] Pan Q, Li X, Fang L. Data augmentation for deep learning-based ECG analysis[M]//Feature engineering and computational intelligence in ECG monitoring. Singapore: Springer Singapore, 2020: 91-111. [6] Liu B, Zhang Z, Cui R. Efficient time series augmen-tation methods[C]//2020 13th international congress on image and signal processing, BioMedical engi-neering and informatics (CISP-BMEI). IEEE, 2020: 1004-1009. [7] Iglesias G, Talavera E, González-Prieto Á, et al. Data augmentation techniques in time series domain: a survey and taxonomy[J]. Neural Computing and Ap-plications, 2023, 35(14): 10123-10145. [8] Creswell A, White T, Dumoulin V, et al. Generative adversarial networks: An overview[J]. IEEE signal processing magazine, 2018, 35(1): 53-65. [9] Ledig C, Theis L, Huszár F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4681-4690. [10] Bousmalis K, Silberman N, Dohan D, et al. Unsuper-vised pixel-level domain adaptation with generative adversarial networks[C]//Proceedings of the IEEE conference on computer vision and pattern recogni-tion. 2017: 3722-3731. [11] Zhang H, Xu T, Li H, et al. Stackgan: Text to photo-realistic image synthesis with stacked generative ad-versarial networks[C]//Proceedings of the IEEE inter-national conference on computer vision. 2017: 5907-5915. [12] Brophy E, Wang Z, She Q, et al. Generative adversar-ial networks in time series: A survey and taxonomy[J]. arxiv preprint arxiv:2107.11098, 2021. [13] Mogren O. C-RNN-GAN: Continuous recurrent neural networks with adversarial training[J]. arxiv preprint arxiv:1611.09904, 2016. [14] Esteban C, Hyland S L, Rätsch G. Real-valued (medi-cal) time series generation with recurrent conditional gans[J]. arxiv preprint arxiv:1706.02633, 2017. [15] Yoon J, Jarrett D, Van der Schaar M. Time-series generative adversarial networks[J]. Advances in neu-ral information processing systems, 2019, 32. [16] Ni H, Szpruch L, Wiese M, et al. Conditional sig-wasserstein gans for time series generation. arxiv[J]. arxiv preprint arxiv:2006.05421, 2020. [17] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information pro-cessing systems, 2017, 30. [18] Jiang Y, Chang S, Wang Z. Transgan: Two pure trans-formers can make one strong gan, and that can scale up[J]. Advances in Neural Information Processing Systems, 2021, 34: 14745-14758. [19] Diao S, Shen X, Shum K, et al. TILGAN: transformer-based implicit latent GAN for diverse and coherent text generation[C]//Findings of the Association for Computational linguistics: ACL-IJCNLP 2021. 2021: 4844-4858. [20] Mirza M, Osindero S. Conditional generative adver-sarial nets[J]. arxiv preprint arxiv:1411.1784, 2014. [21] Li X, Ngu A H H, Metsis V. Tts-cgan: A transformer time-series conditional gan for biosignal data aug-mentation[J]. arxiv preprint arxiv:2206.13676, 2022. [22] LI X, METSIS V, WANG H, et al. Tts-gan: A trans-former-based time-series generative adversarial net-work[C]//International conference on artificial intelli-gence in medicine. Cham: Springer International Pub-lishing, 2022: 133-143. [23] LIANG Z, XU Y, HONG Y, et al. A Survey of Multimodel Large Language Models[C]//Proceedings of the 3rd International Conference on Computer, Ar-tificial Intelligence and Control Engineering. 2024: 405-409. [24] Shandong University Gait analysis disease diagnosis method and system based on feature interaction re-balancing: 2024,11665713 X [P]. February 18, 2025 (under application) [25] Bertaux A, Gueugnon M, Moissenet F, et al. Gait analysis dataset of healthy volunteers and patients before and 6 months after total hip arthroplasty[J]. Scientific Data, 2022, 9(1): 399. [26] Pan X, Yu Z, Yang Z. A multi-scale convolutional neural network combined with a portable near-infrared spectrometer for the rapid, non-destructive identification of wood species[J]. Forests, 2024, 15(3): 556. [27] Madane A, Dilmi M, Forest F, et al. Transformer-based conditional generative adversarial network for multivariate time series generation[J]. arxiv preprint arxiv:2210.02089, 2022.