This paper addresses the problem of distributed speaker tracking in wireless acoustic sensor networks, also known as the Internet of Audio Things (IoAuT). We propose a novel Tempered Stein Variational Gradient Descent (T-SVGD) algorithm for distributed fusion of local likelihood probability density functions (PDFs) and approximation of the posterior distribution of the speaker state vector. In the proposed approach, the Gaussian Mixture Model (GMM) is employed to approximate the posterior predictive distribution, and a tempered initial sampling distribution is designed to enhance SVGD sampling. The average consensus fusion method is then utilized to achieve distributed fusion of the local likelihood PDFs across the network nodes. Subsequently, the T-SVGD algorithm is applied to approximate and sample the posterior distribution, thereby enabling distributed state estimation of the speaker position. Unlike conventional particle-based methods, the proposed algorithm deterministically transports and optimizes the sampling particles using the gradient information of the posterior distribution, resulting in superior tracking performance with fewer particles. This design strikes a favorable balance between tracking accuracy and computational efficiency, making it particularly suitable for IoAuT devices operating in complex acoustic environments, even under non-Gaussian noise and reverberation conditions. Extensive simulations and real-world experiments demonstrate that the proposed method achieves an average root mean square error (ARMSE) below 0.5 m under non-Gaussian noise at SNRs as low as 0 ~ 5 dB.

Studying brain activity and deciphering the information in electroencephalogram (EEG) signals has become an emerging research field, and substantial advances have been made in the EEG-based classification of emotions. However, using different EEG features and complementarity to discriminate other emotions is still challenging. Most existing models extract a single temporal feature from the EEG signal while ignoring the crucial temporal dynamic information, which, to a certain extent, constrains the classification capability of the model. To address this issue, we propose an Attention-Based Depthwise Parameterized Convolutional Gated Recurrent Unit (AB-DPCGRU) model and validate it with the mixed experiment on the SEED and SEED-IV datasets. The experimental outcomes revealed that the accuracy of the model outperforms the existing state-of-the-art methods, which confirmed the superiority of our approach over currently popular emotion recognition models.

Function control, which is an essential link in industrial automation, is undergoing a growing integration with ICTs (Information Communication Technologies) because of the flexible manufacturing and convenient interoperability in CPSs (Cyber-Physical Systems). However, it has also brought the increasing dangers of cyberattacks caused by malicious or intentional industrial process control exploitations. In order to effectively detect these cyber intrusions and anomalies, this paper proposes a function-aware anomaly detection approach based on WNN (Wavelet Neural Network), which perceives the abnormal function control changes in industrial control communication. By appropriately extracting the time-related function control characteristics from industrial communication packets, this approach builds an optimized wavelet neural network to model the normal function control behaviors and calculates the detection threshold to differentiate the aberrant industrial process control activities. Additionally, a real-world control system, whose communication protocol is Modbus/TCP, is simulated to furnish the analyzed function control data. According to the experimental results, we fully demonstrate this approach has the fine detection accuracy and adequate real-time capability.

Knowing the trajectory of each packet in a network enables a large range of network debugging and management tasks. Existing packet trajectory tracing approaches for software-defined networking (SDN) either require high message/computational overhead or only focus on one kind of network topology. In this paper, we propose UniROPE, a robust and lightweight packet trajectory tracing approach that supports various network topologies. Using the flow information, UniROPE dynamically selects one of the two proposed packet trajectory tracing algorithms to achieve a better tradeoff between accuracy and efficiency. We implement UniROPE using P4, a high-level language for programming SDN switch operations, and evaluate its performance in networks with different topologies, scales, and link failure probabilities. Results show that UniROPE achieves a high successful ratio of packet trajectory tracing with small message/computational overheads in various networks. We also use three case studies to show the effectiveness of the traced packet trajectory information for network debugging and management.

For wideband cognitive radio networks, small-scale primary users (SSPUs) such as wireless microphones and mobile devices are generally difficult to be accurately sensed/detected due to the use of weak transmit power and noise uncertainty. Recently, compressive sensing (CS) technologies and edge detection methods (such as wavelet transform) are widely researched and combined to achieve the effective wideband spectrum sensing with sub-Nyquist sampling rate. When the SSPUs exist in wideband cognitive radio networks, however, there will occur two challenging points: low signal-to-noise ratio (S-NR) conditions and reduction of spectrum sparsity, which may lead to performance degradation of the traditional edge-based compressive spectrum detection methods. To overcome these difficulties, this paper proposes a novel robust compressive wideband spectrum sensing algorith-m by exploiting the information entropy of the power spectrum of SSPUs and noise signals. Theoretical analysis results show that the sensed signals' power spectrum follows different statistical distributions when the SSPUs are present or not. Therefore, the proposed algorithm uses the information entropy as a test statistic to measure the varying of the statistical properties of the compressive reconstructed power spectrum of the sensed signals, and then make a decision on whether the primary users are present or not. Simulation results show the effectiveness of the proposed algorithm for detecting the SSPUs under low SNRs.