12 February 2025 in IEEE Transactions on Signal Processing
Neural network-assisted (NNA) Kalman filters provide an effective solution to addressing the filtering issues involving partially unknown system information by incorporating neural networks to compute the intermediate values influenced by unknown data, such as the Kalman gain in the filtering process. However, whenever there are slight changes in the state-space model (SSM), previously trained networks used in NNA Kalman filters become outdated, necessitating extensive time and data for retraining. Furthermore, obtaining sufficient labeled data for supervised learning is costly, and the effectiveness of unsupervised learning can be inconsistent. To this end, to address the inflexibility of neural network architecture and the scarcity of training data, we propose a model-agnostic meta-learning based neural network-assisted Kalman filter in this paper, called MAML-KalmanNet, by employing a limited amount of labeled data and training rounds to achieve desirable outcomes comparable to the supervised NNA Kalman filters with sufficient training. MAML-KalmanNet utilizes a pre-training approach based on specifically tailored meta-learning, enabling the network to adapt to model changes with minimal data and time without the requirement of retraining. Simultaneously, by fully leveraging the information from the SSM, MAML-KalmanNet eliminates the requirement of a large amount of labeled data to train the meta-learning initialization network. Simulations show that MAML-KalmanNet can mitigate the shortcomings existing in NNA Kalman filters regarding the requirements of abundant training data and sensitive network architecture, while providing real-time state estimation across a range of noise distributions.
24 January 2025 in IEEE Signal Processing Letters
Both the minimum error entropy (MEE) and mixture MEE (MMEE) are extensively employed in distributed adaptive filters, exhibiting their robustness against non-Gaussian noise by capturing high-order statistical information from network data. However, the fixed shape of the Gaussian kernel function existing in MEE and MMEE restricts their flexibility, leading to reduced robustness and deteriorated performance. To address this issue, a novel diffusion generalized minimum total error entropy (DGMTE) algorithm is first proposed in this letter, using a generalized MEE criterion to significantly improve the performance of error-in-variables models-based algorithms under non-Gaussian noise. Moreover, as a special case of DGMTE, a generalized minimum total error entropy (GMTE) algorithm is also proposed, and the local convergence analysis of DGMTE is given. Finally, simulations show the superiorities of DGMTE in comparison with other representative algorithms.
14 March 2026 in Signal Processing
24 January 2026 in Signal Processing
1 January 2026 in IEEE Sensors Journal