AI Insight
This study presents a multi-stage adaptive filtering system that automatically adjusts its processing stages and parameters to remove non-stationary noise from real-time measurement signals. The architecture uses least mean square algorithms with a stopping mechanism based on correlation testing and signal-to-noise ratio monitoring. Testing showed the method reduced mean squared error by 38-82% and mean absolute error by 15-45% compared to conventional filters, while requiring 3.5-4 times less computational time than fixed-threshold approaches.
Why it matters
The system offers improved noise filtering for real-time monitoring equipment in challenging environments while using fewer computational resources, making it suitable for implementation in resource-constrained devices like portable sensors and embedded measurement systems. This could enhance reliability of data collection in industrial monitoring, medical devices, and field instrumentation where signal quality is compromised by variable environmental noise.
Understand the Science
by Thanh Han-Trong, Thang Bui Van, Quang Hoang Minh, Anh Do Trung
In many real-time measurement and monitoring systems, the quality of acquired signals is often severely degraded by complex environmental noise sources with non-stationary properties, rendering analysis, important feature extraction, and decision-making unreliable. This study proposes a multi-stage adaptive denoising architecture based on the least mean square (LMS) algorithm, in which the number of filter stages and the step size are automatically adjusted according to error statistics, the remaining correlation between the residual and the reference signal, and the real-time signal-to-noise ratio (SNR) of the signal. The stopping mechanism is determined by a two-tailed Fisher-z correlation test, with effective sample size correction in the presence of autocorrelation and modulation based on SNR, to ensure the stability of the adaptive system against non-stationary noise. The filter is evaluated on simulated signal datasets and real-world measured data. Compared with the conventional LMS filter configuration under the tested simulated conditions, the proposed architecture reduces mean squared error (MSE) by 38–82% and mean absolute error (MAE) by 15–45%, while improving both SNR and peak signal-to-noise ratio (PSNR). The execution time of the proposed method is approximately 3.5–4 times lower than that of the fixed-threshold method under the tested settings. These results indicate that the proposed method can improve the trade-off between denoising performance and computational efficiency, showing potential for low-latency implementation on resource-constrained devices.
Source: Low-latency stage-adaptive cascade architecture for real time non-stationary noise filtering