Abstract Sensing, Computing and Communication Integration (SC2) is widely believed as a new enabling technology. A non‐negative tensor sparse factorisation (NTSF) algorithm based on tensor analysis is proposed for sensing and classification of Small Geological Structure in coal mines. Utilising this method, advanced detection of geological anomalies hidden in coal seams was achieved. The morphological properties of geological anomalies in coal seams and the propagation characteristics of guided waves were first thoroughly studied. A three‐dimensional (3D) medium geometry model was developed for a complicated coal seam with Goaf, collapse column, scouring zone, and tiny fault based on COMSOL Multiphysics. On this model, the third‐order tensors data was constructed. Then, the TUCKER‐based NTSF algorithm was employed for feature extraction and classification. To achieve multi‐dimensional feature, the two‐dimensional data in the form of a matrix is collected, and a multiplicative update method is introduced to update the algorithm iteratively. Finally, the Support Vector Machine (SVM) multi‐classifier with Gaussian radial basis kernel function is selected for classification of Small Geological Structure. The experimental results show that the classification accuracy based on the NTSF and SVM is as high as 97.33%, which demonstrates that the proposed algorithm is suitable for Sensing and Classification of Small Geological Structure in coal mines.

Abstract The globally optimal generalised sequential fusion (GSF) algorithm in the sense of linear minimum variance for multi‐sensor stochastic uncertain systems is investigated by the authors. Specifically, in the GSF algorithm, the estimation of measurement noise is considered, and ma (ma ≥ 1) sensors' measurement data are fused at the ath reception instant, which makes it very flexible and suitable for practical applications. The centralised and sequential fusion algorithms are special cases of the proposed GSF algorithm. Furthermore, for any ma, a = 1, 2, …, M, the estimated values of the GSF algorithm remain invariant and globally optimal. Moreover, the independence between the estimated values and fusion order is proved in the proposed GSF algorithm. Finally, simulation results are given to demonstrate the usefulness of the developed algorithm.

Abstract It is difficult for a receiver to intercept the signals from a radar system that can emit low probability of intercept (LPI) polyphase coded signals. The traditional Wigner Hough transform (WHT) algorithm requires a large amount of computation and takes a long time to estimate the parameters of the LPI radar polyphase coded signals. To address this problem, an iterative angle search (IAS) algorithm, which when used in combination with the WHT algorithm significantly reduces the computational cost is proposed. When the signal‐to‐noise ratio is in the range of −4 to 20 dB, the carrier frequency, number of subcodes, and number of cycles of the carrier frequency per subcode of five polyphase coded signals, namely, Frank, P1, P2, P3, and P4, are accurately estimated in simulation experiments. Based on the selected IAS algorithm parameters, the estimation accuracy of the proposed method is the same as that of the traditional WHT algorithm. However, the operation time is only 5.14% of that of the traditional method. The IAS algorithm has certain application prospects. Experiments indicate that the proposed algorithm provides excellent performance and can rapidly and accurately estimate the parameters of LPI polyphase codes.

The globally optimal generalised sequential fusion (GSF) algorithm in the sense of linear minimum variance for multi-sensor stochastic uncertain systems is investigated. In GSF algorithm, the estimation of measurement noise is considered and ma (ma ≥ 1) sensors’ measurement data is fused at the ath sampling instant, which makes it very flexible and suitable for practical applications.

Abstract The existing deep learning‐based face super‐resolution techniques can achieve satisfactory performance. However, these methods often incur large computational costs, and deeper networks generate redundant features. Some lightweight reconstruction networks also present limited representation ability because they ignore the entire contour and fine texture of the face for the sake of efficiency. Here, the authors propose a convenient alternating projection network (CAPN) for efficient face super‐resolution. First, the authors design a novel alternating projection block cascaded convolutional neural network to alternately achieve content consistency and learn detailed facial feature differences between super‐resolution and ground‐truth face images. Second, the self‐correction mechanism enabled the convolutional layer to capture faithful features that facilitate adaptive reconstruction. Moreover, a convenient connection operation can reduce the generation of redundant facial features while maintaining accurate reconstruction information. Extensive experiments demonstrated that the proposed CAPN can effectively reduce the computational cost while achieving competitive qualitative and quantitative results compared to state‐of‐the‐art super‐resolution methods.

Abstract Recent research and development interests deal with metasurfaces for wireless systems beyond their consideration as intelligent tunable reflectors. Among the latest proposals is the simultaneously transmitting (a.k.a. refracting) and reflecting reconfigurable intelligent surface (STAR‐RIS) which intends to enable bidirectional indoor‐to‐outdoor, and vice versa communications thanks to its additional refraction capability. This double functionality provides increased flexibility in concurrently satisfying the quality‐of‐service requirements of users located at both sides of the metasurfaces, for example, the achievable data rate and localisation accuracy. The authors focus on STAR‐RIS‐empowered simultaneous indoor and outdoor three‐dimensional (3D) localisation, and study the fundamental performance limits via Fisher information analyses and Cramér Rao lower bounds (CRLBs). The authors also devise an efficient localisation algorithm based on an off‐grid compressive sensing (CS) technique relying on atomic norm minimisation (ANM). The impact of the training overhead, the power splitting at the STAR‐RIS, the power allocation between the users, the STAR‐RIS size, the imperfections of the STAR‐RIS‐to‐BS channel, as well as the role of the multi‐path components on the positioning performance are assessed via extensive computer simulations. It is theoretically demonstrated that high‐accuracy, up to centimetre level, 3D localisation can be simultaneously achieved for indoor and outdoor users, which is also accomplished via the proposed ANM‐based estimation algorithm.

Abstract With oceanic reverberation and a large amount of data being the main sources of interference for underwater acoustic target detection, it is difficult to obtain a more robust detection performance by relying on the traditional constant false alarm rate (CFAR) detection method. An adaptive sonar CFAR detection method based on a back propagation (BP) neural network is proposed. The method combines the artificial intelligence algorithm and the traditional detection algorithm, and uses the classification ability of the algorithm to select the detection algorithm, which can effectively improve the adaptation ability of the algorithm and the environment and the false alarm control ability. The method combines the artificial intelligence algorithm and the traditional detection algorithm, and uses the classification ability of the algorithm to select the detection algorithm, which can effectively improve the adaptation ability of the algorithm and the environment and the false alarm control ability. This method uses a BP neural network to train the target echo signal to complete the clutter background classification and establish the clutter background recognition classification set. According to the output result of each classification, the best CFAR detector is selected from four CA/SO/GO/OS‐CFAR detectors to detect the target. The simulation results show the detection performance of the proposed method in a uniform environment, a multi‐target environment, and a clutter edge environment. The results show that the environment adaptability is strong for different clutter backgrounds, which further improves the control ability of false alarms under a non‐uniform background.

We propose a novel algorithm to estimate the DOAs from narrowband signals based on the DNN technique. The neural network architecture is based on an MLP and a group of parallel DNNs to perform detection and DOA estimation, respectively. A set of simulation results has also been applied to confirm the generalisation and effectiveness of the proposed approach.

Abstract Sparse time‐frequency analysis (STFA) can precisely achieve the spectrum of the local truncated signal. However, when the signal is disturbed by unexpected data loss, STFA cannot distinguish effective signals from missing data interferences. To address this issue and establish a robust STFA model for time‐frequency analysis (TFA) in data loss scenarios, a stationary Framelet transform‐based morphological component analysis is introduced in the STFA. In the proposed model, the processed signal is regarded as a sum of the cartoon, texture and data‐missing parts. The cartoon and texture parts are reconstructed independently by taking advantage of the stationary Framelet transform. Then, the signal is reconstructed for STFA. The forward‐backwards splitting method is employed to split the robust STFA model into the data recovery and robust time‐frequency imaging stages. The two stages are then solved separately by using the alternating direction method of multipliers (ADMM). Finally, several experiments are conducted to show the performance of the proposed robust STFA method under different data loss levels, and it is compared with some existing state‐of‐the‐art time‐frequency methods. The results indicate that the proposed method outperforms the compared methods in obtaining the sparse spectrum of the effective signal when data are missing. The proposed method has a potential value in TFA in scenarios where data is easily lost.

Abstract Although current attention‐based speech enhancement methods have been proven to be capable of significantly improving the noise reduction performance, a bottleneck has arisen in juggling both detailed features and high‐level features: The more attention paid to such performance indicators as speech intelligibility index and articulation index will lead to the loss of subtle features such as syllable continuity and timbre distortion. To tackle such a problem, we divide the speech enhancement model into multiple stages, with a special attention mechanism introduced in each stage so that the detailed speech information is retained and the features of high levels are captured. In this research, a Multi‐Stage Attention Network (MSANet) is implemented in cascade by using three different attention modules: Self Attention, Channel Attention and Spatial Attention. The attention module in each stage needs only to focus on the features of its corresponding stage, thus giving full play to their respective advantages without affecting or damaging the features of other stages, helping decouple the feature extraction process and obtaining the features capable of complementing one another. The comparisons and ablation experiments show that the performance of MSANet is superior to those of current mainstream time domain or time‐frequency domain state‐of‐the‐art methods. Compared to the baseline, PESQ score of their model (3.11) has increased by 5%, CSIG (4.44) has increased by 2.5%, CBAK (3.63) has increased by 2.8% and COVL (3.81) has increased by 3.8%, which demonstrates the potential of MSANet as speech feature extraction backbones. An implementation of the PyTorch version is available here: http://www.msp‐lab.cn:1436/msp/MSANet .