Improvement of the wavelet transform filtering algorithm with threshold denoising metod

• Autorzy: Wang Fan

Identyfikatory

DOI

10.29354/diag/209428

• Języki publikacji: EN

Abstrakty

EN

In recent years, the wavelet transform filtering algorithm has attracted significant attention due to widespread applications in signal denoising. However, its fixed threshold method has limitations, such as constrained denoising performance and loss of signal details, which requires improvement to adapt to complex noise environments. To address this issue, a wavelet transforms filtering algorithm combining adaptive thresholding and an improved threshold function is proposed. The algorithm dynamically calculates thresholds based on the statistical properties of the signal and employs a continuously differentiable threshold function to balance denoising and signal fidelity. Experimental tests on simulated signals with varying noise levels and real-world signals show that the improved algorithm achieves an SSIM index of 0.942, the closest to the original image, preserving image details and textures to the greatest extent. In denoising house images, the GAPTWavelet method clearly preserves the contours and textures of the house, with a PSNR of 87.90 dB and an MSE of 0.021 dB. When the maximum data size n=800, the algorithm’s runtime is 46 seconds, maintaining a fast response time. The study has shown that the improved algorithm outperforms traditional methods in terms of denoising performance, computational efficiency, and adaptability, demonstrating significant potential for practical applications in scenarios such as medical image denoising, engineering equipment fault diagnosis, and industrial signal monitoring, thereby highlighting its important practical significance in the fields of engineering and technical diagnostics.

Słowa kluczowe

EN

wavelet transform filtering algorithm; adaptive thresholding; fast and flexible denoising network; generative adversarial network; signal denoising; threshold function

• Wydawca: Polskie Towarzystwo Diagnostyki Technicznej
• Czasopismo: Diagnostyka
• Rocznik: 2025
• Tom: Vol. 26, No. 3
• Strony: art. no. 2025309
• Opis fizyczny: Bibliogr. 23 poz., rys., tab.

Twórcy

autor

Wang Fan

• Training Technology and Equipment Management Center, Shijiazhuang College of Applied Technology, Shijiazhuang, 050800, China

• https://orcid.org/0009-0008-1138-1546

Bibliografia

• 1. Wang Z, Li Z, Teng X, Chen D. LPMsDE: multiscale denoising and enhancement method based on laplacian pyramid framework for forward-looking sonar image. IEEE Access. 202311(6):132942- 132954. https://doi.org/10.1109/ACCESS.2023.3335372.
• 2. Li Y, Ramli DA. Advances in time-frequency analysis for blind source separation; challenges, contributions, and emerging trends. IEEE Access. 2023;11(3):137450-137474. https://doi.org/10.1109/ACCESS.2023.3338024.
• 3. Ranjan R, Sahana BC, Bhandari AK. Cardiac artifact noise removal from sleep EEG signals using hybrid denoising model. IEEE Transactions on Instrumentation and Measurement. 2022;71(11):1-10. https://doi.org/10.1109/TIM.2022.3198441.
• 4. Cibira G, Glesk I, Dubovan J. SNR-based denoising dynamic statistical threshold detection of FBG spectral peaks. Journal of Lightwave Technology. 2022;41(8):2526-2539. https://doi.org/10.1109/JLT.2022.3229965.
• 5. Wei X, Feng G, Qi T, Guo J, Li Z. Reduce the noise of transient electromagnetic signal based on the method of SMA-VMD-WTD. IEEE Sensors Journal. 2022;22(15):14959-14969. https://doi.org/10.1109/JSEN.2022.3184697.
• 6. Hou Y, Liu R, Shu M, Xie X, Chen C. Deep neural network denoising model based on sparse representation algorithm for ecg signal. IEEE Transactions on Instrumentation and Measurement. 2023;72(4):1-11. https://doi.org/10.1109/TIM.2023.3251408.
• 7. Molaei AM, Fromenteze T, Skouroliakou V, Hoang TV, Kumar R, Fusco V, Yurduseven O. Development of fast Fourier-compatible image reconstruction for 3D near-field bistatic microwave imaging with dynamic metasurface antennas. IEEE Transactions on Vehicular Technology. 2022;71(12):13077-13090. https://doi.org/10.1109/TVT.2022.3201155.
• 8. Jiang L, Shang W, Jiao Y, Xiang S. An adaptive generalized S-transform algorithm for seismic signal analysis. IEEE Access, 2022;10(7):127863-127870. https://doi.org/10.1109/ACCESS.2022.3227426.
• 9. Yuan H, Du R, Wang X, Wei X, Dai H. Advanced online broadband impedance spectrum acquisition of fuel cells by S-transform. IEEE Transactions on Industrial Electronics. 2022;70(4):3740-3750. https://doi.org/10.1109/TIE.2022.3177814.
• 10. Tian X, Zhu Q, Li Y, Wu M. Cross-domain joint dictionary learning for ECG inference from PPG. IEEE Internet of Things Journal. 2022;10(9: 8140-8154. https://doi.org/10.1109/JIOT.2022.3231862.
• 11. Yao H M, Guo R, Li M, Jiang L, Ng MKP. Enhanced supervised descent learning technique for electromagnetic inverse scattering problems by the deep convolutional neural networks. IEEE Transactions on Antennas and Propagation. 2022; 70(8):6195-6206. https://doi.org/10.1109/TAP.2022.3196496.
• 12. Chen Y, Zhang D, Zhang H, Wang QG. Dual-path mixed-domain residual threshold networks for bearing fault diagnosis. IEEE Transactions on Industrial Electronics. 2022;69(12):13462-13472. https://doi.org/10.1109/TIE.2022.3144572.
• 13. Peng L, Guo A, Zhang S. Research on fault diagnosis method of High-Speed EMU air compressor based on ICEEMDAN and wavelet threshold combined noise reduction. IEEE Access. 2024;12(8):173484-173501. https://doi.org/10.1109/ACCESS.2024.3479721.
• 14. Wang X, Liu Z, Dai M, Li W, Tang J. Time-shift denoising combined with DWT-enhanced condition domain adaptation for motor bearing fault diagnosis via current signals. IEEE Sensors Journal. 2024;24(21):35019-35035. https://doi.org/10.1109/JSEN.2024.3455099.
• 15. Iqbal N. DeepSeg: Deep segmental denoising neural network for seismic data. IEEE Transactions on Neural Networks and Learning Systems. 2022;34(7): 3397-3404. https://doi.org/10.1109/TNNLS.2022.3205421.
• 16. Yao D, Zhou T, Yang J. Intelligent framework for bearing fault diagnosis in high-noise environments: A location-focused soft threshold denoising approach. IEEE Sensors Journal. 2024;24(7):9523-9535. https://doi.org/10.1109/JSEN.2024.3362349.
• 17. Li X, Chen J, Wang J, Li X and Kan Y. Research on fault diagnosis method of bearings in the spindle system for CNC machine tools Based on DRSNTransformer. IEEE Access. 2024;12(4):74586-74595. https://doi.org/10.1109/ACCESS.2024.3404968.
• 18. Meng Y, Zhang J. A novel gray image denoising method using convolutional neural network. IEEE Access. 2022;10(4):49657-49676. https://doi.org/10.1109/ACCESS.2022.3169131.
• 19. Yu W, Shen Y, He H, Yu X, Song S, Zhang J, Letalief KB. An adaptive and robust deep learning framework for THz ultra-massive MIMO channel estimation. IEEE Journal of Selected Topics in Signal Processing. 2023;17(4):761-776. https://doi.org/10.1109/JSTSP.2023.3282832.
• 20. Zhang K, Long M, Chen J, Liu M, Li J. CFPNet: A denoising network for complex frequency band signal processing. IEEE Transactions on Multimedia. 2023;25(3):8212-8224. https://doi.org/10.1109/TMM.2022.3233398.
• 21. Zhang K, Zuo W, Zhang L. FFDNet: Toward a fast and flexible solution for CNN-based image denoising. IEEE Transactions on Image Processing. 2018;27(9):4608-4622. https://doi.org/10.1109/TIP.2018.2839891.
• 22. Xu B, Zhou D, Li W. Image enhancement algorithm based on GAN neural network. IEEE Access. 2022; 10(3):36766-36777. https://doi.org/10.1109/ACCESS.2022.3163241.
• 23. Chen K, Kong Q, Dai Y, Xu Y, Yin F, Xu L, Cui S. Recent advances in data-driven wireless communication using gaussian processes: a comprehensive survey. China Communications. 2022;19(1):218-237. https://doi.org/10.23919/JCC.2022.01.016.