The Kalman filter (KF)-based active noise control (ANC) system demonstrates superior tracking and faster convergence compared to the least mean square (LMS) method, particularly in dynamic noise cancellation scenarios. However, in environments with extremely high noise levels, the power of the control signal can exceed the system’s rated output power due to hardware limitations, leading to output saturation and subsequent non-linearity. To mitigate this issue, a modified KF with an output constraint is proposed. In this approach, the disturbance treated as an measurement is re-scaled by a constraint factor, which is determined by the system’s rated power, the secondary path gain, and the disturbance power. As a result, the output power of the system, i.e. the control signal, is indirectly constrained within the maximum output of the system, ensuring stability. Simulation results indicate that the proposed algorithm not only achieves rapid suppression of dynamic noise but also effectively prevents non-linearity due to output saturation, highlighting its practical significance.

Virtual sensing (VS) technology enables active noise control (ANC) systems to attenuate noise at virtual locations distant from the physical error microphones. Appropriate auxiliary filters (AF) can significantly enhance the effectiveness of VS approaches. The selection of appropriate AF for various types of noise can be automatically achieved using convolutional neural networks (CNNs). However, training the CNN model for different ANC systems is often labour-intensive and timeconsuming. To tackle this problem, we propose a novel method, Transferable Selective VS, by integrating metric-learning technology into CNN-based VS approaches. The Transferable Selective VS method allows a pre-trained CNN to be applied directly to new ANC systems without requiring retraining, and it can handle unseen noise types. Numerical simulations demonstrate the effectiveness of the proposed method in attenuating suddenvarying broadband noises and real-world noises.

Reward shaping is a reinforcement learning technique that addresses the sparse-reward problem by providing frequent, informative feedback. We propose an efficient self-adaptive reward-shaping mechanism that uses success rates derived from historical experiences as shaped rewards. The success rates are sampled from Beta distributions, which evolve from uncertainty to reliability as data accumulates. Initially, shaped rewards are stochastic to encourage exploration, gradually becoming more certain to promote exploitation and maintain a natural balance between exploration and exploitation. We apply Kernel Density Estimation (KDE) with Random Fourier Features (RFF) to derive Beta distributions, providing a computationally efficient solution for continuous and high-dimensional state spaces. Our method, validated on tasks with extremely sparse rewards, improves sample efficiency and convergence stability over relevant baselines.

Existing reward shaping techniques for sparse-reward reinforcement learning generally fall into two categories: novelty-based exploration bonuses and significance-based hidden state values. The former promotes exploration but can lead to distraction from task objectives, while the latter facilitates stable convergence but often lacks sufficient early exploration. To address these limitations, we propose Dual Random Networks Distillation (DuRND), a novel reward shaping framework that efficiently balances exploration and exploitation in a unified mechanism. DuRND leverages two lightweight random network modules to simultaneously compute two complementary rewards: a novelty reward to encourage directed exploration and a contribution reward to assess progress toward task completion. With low computational overhead, DuRND excels in high-dimensional environments with challenging sparse rewards, such as Atari, VizDoom, and MiniWorld, outperforming several benchmarks.

Reward shaping is effective in addressing the sparse-reward challenge in reinforcement learning (RL) by providing immediate feedback through auxiliary, informative rewards. Based on the reward shaping strategy, we propose a novel multi-task reinforcement learning framework that integrates a centralized reward agent (CRA) and multiple distributed policy agents. The CRA functions as a knowledge pool, aimed at distilling knowledge from various tasks and distributing it to individual policy agents to improve learning efficiency. Specifically, the shaped rewards serve as a straightforward metric for encoding knowledge. This framework not only enhances knowledge sharing across established tasks but also adapts to new tasks by transferring meaningful reward signals. We validate the proposed method on both discrete and continuous domains, including the representative Meta-World benchmark, demonstrating its robustness in multi-task sparse-reward settings and its effective transferability to unseen tasks.

Compared to the conventional centralized multichannel active noise control (MCANC) algorithm, which requires substantial computational resources, decentralized approaches exhibit higher computational efficiency but typically result in inferior noise reduction performance. To enhance performance, distributed ANC methods have been introduced, enabling information exchange among ANC nodes; however, the resulting communication latency often compromises system stability. To overcome these limitations, we propose a self-boosted weight-constrained filtered-reference least mean square (SB-WCFxLMS) algorithm for the distributed MCANC system without internode communication. The WCFxLMS algorithm is specifically designed to mitigate divergence issues caused by the internode cross-talk effect. The self-boosted strategy lets each ANC node independently adapt its constraint parameters based on its local noise reduction performance, thus ensuring effective noise cancellation without the need for inter-node communication. With the assistance of this mechanism, this approach significantly reduces both computational complexity and communication overhead. Numerical simulations employing real acoustic paths and compressor noise validate the effectiveness and robustness of the proposed system. The results demonstrate that our proposed method achieves satisfactory noise cancellation performance with minimal resource requirements.

Photoplethysmography (PPG) is commonly used to gather health-related information but is highly affected by motion artifacts from daily activities. Inspired by the strong denoising capabilities and generalization of diffusion probabilistic models, this paper proposes a novel PPG denoising method using a diffusion probabilistic model to reduce the impact of these artifacts. While typical diffusion models handle Gaussian noises, motion artifacts often involve non-Gaussian noise. To address this, the proposed method incorporates noisy PPG signals into both the diffusion and reverse processes, allowing the model to adapt better to complex and non-Gaussian noises. A dataset with clean and noisy PPG signals from 15 subjects performing various motion tasks was collected for evaluation. The results show the proposed model significantly improves PPG signal quality, reducing the Peak-Rejection-Rate (PRR) from 0.24 to 0.03. It also enhances the accuracy of heart rate (HR) estimation and various heart rate variability (HRV) measures, showing robustness and good generalization across different tasks and subjects.

Delayless noise control is achieved by our earlier generative fixed-filter active noise control (GFANC) framework through efficient coordination between the co-processor and real-time controller. However, the one-dimensional convolutional neural network (1D CNN) in the co-processor requires initial training using labelled noise datasets. Labelling noise data can be resource-intensive and may introduce some biases. In this paper, we propose an unsupervised-GFANC approach to simplify the 1D CNN training process and enhance its practicality. During training, the co-processor and real-time controller are integrated into an end-to-end differentiable ANC system. This enables us to use the accumulated squared error signal as the loss for training the 1D CNN. With this unsupervised learning paradigm, the unsupervised-GFANC method not only omits the labelling process but also exhibits better noise reduction performance compared to the supervised GFANC method in real noise experiments.

Selective Fixed-filter Active Noise Control (SFANC) is limited by its selection of a single candidate from pre-trained control filters. In contrast, Generative Fixed-filter Active Noise Control (GFANC) addresses this limitation by employing an adaptive combination of sub control filters to generate more suitable control filters for different primary noises. However, GFANC solely relies on the information from the current noise frame to generate its control filter, resulting in potential inaccuracies when dealing with dynamic noises. Therefore, we propose a GFANC-Kalman approach that integrates an efficient one-dimensional convolutional neural network (1D CNN) with a Kalman filter to further improve the performance of GFANC. Specifically, the weight vector used to combine sub control filters is predicted by the 1D CNN for each noise frame, and then processed by the Kalman filter with minimal complexity. By considering the correlation between adjacent noise frames, the Kalman filter can enhance the accuracy and robustness of weight vector prediction. Hence, GFANC-Kalman is more able to adapt to changes in noise distribution, particularly for dynamic noises. Numerical simulations validate the efficacy of the proposed GFANC-Kalman approach in dealing with real-world dynamic noises.

The selective fixed-filter active noise control (SFANC) method can select suitable pre-trained control filters to attenuate incoming noises. However, the limited number of pre-trained filters is insufficient to effectively control various forms of noise, especially when the incoming noise differs much from the filter-training noises. To address this limitation and generate more appropriate control filters, a generative fixed-filter active noise control approach based on Bayesian filter (GFANC-Bayes) is proposed in this paper. The GFANC-Bayes method can automatically generate suitable control filters by combining sub control filters. The combination weights of sub control filters are predicted via a one-dimensional convolutional neural network (1D CNN). Based on prior information and predicted information, Bayesian filtering technique is applied to decide the combination weights. By considering the correlation between adjacent noise frames, the Bayesian filter can enhance the accuracy and robustness of predicting combination weights. Simulations on real-world noises indicate that the GFANC-Bayes method achieves superior noise reduction performance than SFANC and a faster response time than FxLMS. Moreover, experiments on different acoustic paths demonstrate its robustness and transferability.

By assigning the massive computing tasks of the traditional multichannel active noise control (MCANC) system to several distributed control nodes, distributed multichannel active noise control (DM-CANC) techniques have become effective global noise reduction solutions with low computational costs. However, existing DMCANC algorithms simply complete the distribution of traditional centralized algorithms by combining neighbour nodes’ information but rarely consider the degraded control performance and system stability of distributed units caused by delays and interruptions in communication. Hence, this paper develops a novel DMCANC algorithm that utilizes the compensation filters and neighbour nodes’ information to counterbalance the cross-talk effect between channels while maintaining independent weight updating. Since the neighbours’ information required barely affects the local control filter updating in each node, this approach can tolerate communication delay and interruption to some extent. Numerical simulations demonstrate that the proposed algorithm can achieve satisfactory noise reduction performance and high robustness to real-world communication challenges.

Due to the slow convergence and poor tracking ability, conventional LMS-based adaptive algorithms are less capable of handling dynamic noises. Selective fixed-filter active noise control (SFANC) can significantly reduce response time by selecting appropriate pre-trained control filters for different noises. Nonetheless, the limited number of pre-trained control filters may affect noise reduction performance, especially when the incoming noise differs much from the initial noises during pre-training. Therefore, a generative fixed-filter active noise control (GFANC) method is proposed in this paper to overcome the limitation. Based on deep learning and a perfect-reconstruction filter bank, the GFANC method only requires a few prior data (one pre-trained broadband control filter) to automatically generate suitable control filters for various noises. The efficacy of the GFANC method is demonstrated by numerical simulations on real-recorded noises.

Active noise control (ANC) has been widely utilized to reduce unwanted environmental noise. The primary objective of ANC is to generate an anti-noise with the same amplitude but the opposite phase of the primary noise using the secondary source. However, the effectiveness of the ANC application is impacted by the speaker’s output saturation. This paper proposes a two-gradient direction ANC algorithm with a momentum factor to solve the saturation with faster convergence. In order to make it implemented in real-time, a computation-effective variable step size approach is applied to further reduce the steady-state error brought on by the changing gradient directions. The time constant and step size bound for the momentum two-gradient direction algorithm is analyzed. Simulation results show that the proposed algorithm performs effectively in the time-unvaried and time-varied environment.

Practical active noise control (ANC) systems, like the active noise cancellation headphone, usually adopt a control filter with preset coefficients to achieve satisfactory noise reduction performance for dynamic noise and higher robustness. In this strategy, selecting the appropriate control filter for different types of noise is critical to the noise cancellation performance, and this selection mechanism is typically determined by trial and error. Hence, this article proposes a computation-efficient one-dimensional convolutional neural network capable of selecting the most suitable pre-trained control filter for each distinct primary noise. Applying the similarity matching method allows the proposed model to have a better generalization and can even deal with zero-shot noise, whose class does not exist in the training set. The Large-margin softmax (L-softmax) is also investigated to improve the proposed model's performance. Furthermore, when dealing with the N-shot learning problem, where there are few known real-world noise samples for the ANC system, an additional fine-tuning strategy is used to improve control filter selection accuracy. Numerical simulations on measured primary and secondary paths validate the proposed method's efficacy.

The selective fixed-filter active noise control (SFANC) method selecting the best pre-trained control filters for various types of noise can achieve a fast response time. However, it may lead to large steady-state errors due to inaccurate filter selection and the lack of adaptability. In comparison, the filtered-X normalized least-mean-square (FxNLMS) algorithm can obtain lower steady-state errors through adaptive optimization. Nonetheless, its slow convergence has a detrimental effect on dynamic noise attenuation. Therefore, this paper proposes a hybrid SFANC-FxNLMS approach to overcome the adaptive algorithm’s slow convergence and provide a better noise reduction level than the SFANC method. A lightweight one-dimensional convolutional neural network (1D CNN) is designed to automatically select the most suitable pre-trained control filter for each frame of the primary noise. Meanwhile, the FxNLMS algorithm continues to update the coefficients of the chosen pre-trained control filter at the sampling rate. Owing to the effective combination of the two algorithms, experimental results show that the hybrid SFANC-FxNLMS algorithm can achieve a rapid response time, a low noise reduction error, and a high degree of robustness.

Joint iris-periocular recognition based on feature fusion can overcome some inherent drawbacks of unimodal biometrics, but most of the prior works are limited by conventional feature extraction approaches and fixed fusion schemes. To achieve more accurate and adaptive recognition, an end-to-end deep feature fusion network for joint iris-periocular recognition is proposed in this paper. Multiple attention mechanisms including self-attention and co-attention mechanisms are integrated into the network. Specifically, two forms of self-attention mechanisms, spatial attention and channel attention, are inserted into the feature extraction module, aiming to effectively learn the most important features and suppress unnecessary ones. Also, co-attention mechanism is introduced in the feature fusion module, which can adaptively fuse features to obtain more representative iris-periocular features. Additionally, in order to further enhance the discriminative power of the learned features, the proposed network is trained with a joint supervision of softmax loss and center loss. On two publicly available datasets, the proposed network with a small number of parameters outperforms unimodal biometrics and several iris-periocular recognition approaches.

The need for data trading promotes the emergence of data market. However, in conventional data markets, both data buyers and data sellers have to use a centralized trading platform which might be dishonest. A dishonest centralized trading platform may steal and resell the data seller's data, or may refuse to send data after receiving payment from the data buyer. It seriously affects the fair data transaction and harm the interests of both parties to the transaction. To address this issue, we propose a novel blockchain-based data trading framework with Trusted Execution Environment (TEE) to provide a trusted decentralized platform for fair data trading. In our design, a blockchain network is proposed to realize the payments from data buyers to data sellers, and a trusted exchange is built by using a TEE for the first time to achieve fair data transmission. With these help, data buyers and data sellers can conduct transactions directly. We implement our proposed framework on Ethereum and Intel SGX, security analysis and experimental results have demonstrated that the framework proposed can effectively guarantee the fair completion of data tradings.

Hashing methods have been widely applied to approximate nearest neighbor search for large-scale image retrieval, due to its computation efficiency and retrieval quality. Deep hashing can improve the retrieval quality by representation learning and hash coding. Existing deep hashing methods only take image spatial features into account and result in the lack of accurate semantic similarities of images pairs. In this paper, a novel deep hashing network, Deep Captioning Hashing Network (DCHN), is proposed to enhance semantic similarities of hash codes. In DCHN, the binary hash codes are generated in a Bayesian learning framework by fusing deep spatial representation and deep content captioning representation obtained by image captioning. Our analysis and simulation results have demonstrated that DCHN can achieve better retrieval performance in complex scene images compared with other supervised hashing methods and unsupervised methods on two complex scene image datasets MS COCO and NUS-WIDE.

Joint face-iris identification can integrate complementary information from face and iris to fulfill the requirement of performance improvement and security. However, most of the current face-iris multimodal biometric systems acquire face and iris with different sensors which brings about the increase of capturing complexity and device cost. Besides, they are limited by the identification performance degradation under non-ideal scenarios. In order to address these problems, a robust single-sensor face and iris biometric identification system based on multimodal feature extraction (MFE) network is proposed. Only a single sensor is needed to obtain face and iris images in the proposed system, with the goal of improving recognition performance while minimizing sensor cost and acquisition time. The MFE network is designed as a general network module to extract both face and iris features and it is trained with a triplet framework to reduce intra-class variations and enlarge inter-class variations. Our experimental results on CASIA.v4-distance and FRGC v2.0 non-ideal datasets show that the proposed system achieves better identification performance in terms of Equal Error Rate (EER) and False Reject Rate (FFR), etc. compared with other unimodal and multimodal biometric systems.

Recent approaches for real-time semantic segmentation usually employ the encoder-decoder architecture as the backbone to generate a high-quality segmentation prediction. There has been a lot of research on designing efficient encoding methods. However, enhancing the performance of components in decoder is also crucial for pixel-level recognition. In this paper, we propose a self-learned feature reconstruction (SFR) method and an offset-dilated feature fusion (ODFF) module to improve the prediction reconstruction capability of the decoder. Concretely, SFR can effectively reconstruct the high-resolution feature maps by recombining feature space, in which the space transformation matrix implicitly contained in a convolution layer can selectively highlight features at each position by leveraging the knowledge of label space in a self-learned way. Moreover, ODFF module can effectively fuse multilevel features with multiscale contextual information by feeding the feature maps into designed parallel offset-dilated convolutions, which enhances the feature representation capability of the decoder. Experiments on Cityscapes and CamVid datasets demonstrate the superior performance of our proposed methods embedded in ESPNet.