RS-Net: A Dynamic Weight Hybrid Model Integrating SDE and ConvLSTM for Stochastic Signal Processing
Abstract
This paper proposes an adaptive weight-driven stochastic differential-neural hybrid model (RS-Net), designed to address the challenge of dynamically integrating mathematical models and neural networks in modeling non-stationary random signals. RS-Net employs a dynamic weight module (DWM) to adjust the contribution ratio of stochastic differential equations (SDEs) and convolutional LSTMs (ConvLSTMs) in real time based on the residual error. The modular pipeline of RS-Net includes a hybrid architecture of SDE and ConvLSTM, with the DWM serving as the core innovation. By designing a dynamic weight module (DWM), the model can adjust the contribution ratio of the stochastic differential equation (SDE) and the convolutional LSTM online according to the real-time residual (mean absolute value 0.041±0.012). In the NASA turbine vibration signal (SNR=3dB), the RS-Net denoised the SNR to 18.7dB, which is 4.2dB higher than the LSTM, and the RMSE is reduced by 37.4%; in the S&P 500 volatility prediction, the MAPE is only 2.13%, which is 27.5% better than the fixed weight model. In particular, in the non-stationary section of the signal (such as sudden failure), the dynamic weight mechanism makes the model error drop by 58%, verifying its robustness to timevarying characteristics. 100 Monte Carlo experiments show that the RS-Net weight fluctuation variance is only 0.034, significantly lower than the fixed weight of 0.412, proving the stability of the adaptive strategy. The experimental results show that RS-Net breaks through the static limitations of traditional hybrid methods through deep coupling of data and model and provides a new paradigm for complex random signal analysis.
Full Text:
PDFReferences
Sun, J., Li, C., Wang, Z., & Wang, Y. (2023). A memristive fully connect neural network and application of medical image encryption based on central diffusion algorithm. IEEE Transactions on Industrial Informatics, 20(3), 3778-3788.
Genzel, M., Macdonald, J., & März, M. (2022). Solving inverse problems with deep neural networks–robustness included. IEEE transactions on pattern analysis and machine intelligence, 45(1), 1119-1134.
Chen, Y., Zhang, C., Liu, C., Wang, Y., & Wan, X. (2022). Atrial fibrillation detection using a feedforward neural network. Journal of Medical and Biological Engineering, 42(1), 63-73.
Zhou, M., Long, Y., Zhang, W., Pu, Q., Wang, Y., Nie, W., & He, W. (2021). Adaptive genetic algorithm-aided neural network with channel state information tensor decomposition for indoor localization. IEEE Transactions on Evolutionary Computation, 25(5), 913-927.
Viera-Martin, E., Gómez-Aguilar, J. F., Solís-Pérez, J. E., Hernández-Pérez, J. A., & Escobar-Jiménez, R. F. (2022). Artificial neural networks: a practical review of applications involving fractional calculus. The European Physical Journal Special Topics, 231(10), 2059-2095.
Song, S., Xiong, X., Wu, X., & Xue, Z. (2021). Modeling the SOFC by BP neural network algorithm. International Journal of Hydrogen Energy, 46(38), 20065-20077.
Yu, F., Kong, X., Mokbel, A. A. M., Yao, W., & Cai, S. (2022). Complex dynamics, hardware implementation and image encryption application of multiscroll memeristive Hopfield neural network with a novel local active memeristor. IEEE transactions on circuits and systems II: express briefs, 70(1), 326-330.
Naskath, J., Sivakamasundari, G., & Begum, A. A. S. (2023). A study on different deep learning algorithms used in deep neural nets: MLP SOM and DBN. Wireless personal communications, 128(4), 2913-2936.
Chen, D., Liu, R., Hu, Q., & Ding, S. X. (2021). Interaction-aware graph neural networks for fault diagnosis of complex industrial processes. IEEE Transactions on neural networks and learning systems, 34(9), 6015-6028.
Fei, R., Guo, Y., Li, J., Hu, B., & Yang, L. (2023). An improved BPNN method based on probability density for indoor location. IEICE TRANSACTIONS on Information and Systems, 106(5), 773-785.
Singh, P. K., Chauhan, S. S., Sharma, A., Prakash, S., & Singh, Y. (2025). Prediction of higher heating values based on imminent analysis by using regression analysis and artificial neural network for bioenergy resources. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, 239(1), 412-421.
Tang, D., Wang, C., Lin, H., & Yu, F. (2024). Dynamics analysis and hardware implementation of multi-scroll hyperchaotic hidden attractors based on locally active memristive Hopfield neural network. Nonlinear Dynamics, 112(2), 1511-1527.
Liu, S., He, T., & Dai, J. (2021). A survey of CRF algorithm based knowledge extraction of elementary mathematics in Chinese. Mobile Networks and Applications, 26(5), 1891-1903.
Selvakumarasamy, S., Kulathooran, R., & Rengaraju, B. (2024). Effect of Drying on Insulin Plant Leaves for Its Sustainability and Modeling the Drying Kinetics by Mathematical Models and Artificial Neural Network. Environmental Modeling & Assessment, 29(5), 901-914.
Cong, S., & Zhou, Y. (2023). A review of convolutional neural network architectures and their optimizations. Artificial Intelligence Review, 56(3), 1905-1969.
Di Franco, G., & Santurro, M. (2021). Machine learning, artificial neural networks and social research. Quality & quantity, 55(3), 1007-1025.
Shu, W., Cai, K., & Xiong, N. N. (2021). A short-term traffic flow prediction model based on an improved gate recurrent unit neural network. IEEE Transactions on Intelligent Transportation Systems, 23(9), 16654-16665.
DOI: https://doi.org/10.31449/inf.v49i26.8594

This work is licensed under a Creative Commons Attribution 3.0 License.