It is well-known that the convolutional neural network (CNN) is an effective method for synthetic aperture radar (SAR) target classification. In the convolutional layer of CNN, convolutional kernels of different sizes can extract different feature information of the target. The small-size kernel can extract the local texture feature information, and the large-size kernel can extract the global contour feature information. Traditional CNN methods usually use fixed-size kernels for convolution, and they generally lose part of the target’s feature information, resulting in the inaccurate classification of the SAR targets. This article proposes a novel CNN model based on multikernel-size feature fusion (MKSFF-CNN) for SAR target classification. MKSFF-CNN designs a convolutional methodology with a multichannel parallel topology, it uses convolutional kernels of different sizes to extract the multikernel-size deep features of the SAR target, and then, these features are fused in an optimal way to acquire the lowest loss. Moreover, MKSFF-CNN concatenates the fused features extracted by the convolutional layers of different dimensions to achieve the finest classification. MKSFF-CNN greatly elevates the feature representation completeness of the SAR targets so that more useful feature information can be exploited for SAR target classification. Undoubtedly, MKSFF-CNN can achieve a better classification performance compared with traditional CNN models with a fixed kernel size. The superiority of MKSFF-CNN is validated on the moving and stationary target acquisition and recognition (MSTAR) dataset with the detailed objective and subjective evaluation.

Traditional constant false alarm rate (CFAR) detectors suffer probability of detection (PD) degradation influenced by the outliers such as interfering ship targets, side lobes, and ghosts, especially in crowded harbors and busy shipping lines. In this paper, a new two-parameter CFAR detector based on adaptively truncated clutter statistics (TS-LNCFAR) is proposed. The new two-parameter CFAR detector uses log-normal as the statistical model; by adaptive-threshold-based clutter truncation in the background window, the outliers are removed from the clutter samples, while the real clutter is preserved to the largest degree. The log-normal model is accurately built using the truncated clutter statistics through the maximum-likelihood estimator. Compared with traditional CFAR detectors, the parameter estimation is more accurate, and TS-LNCFAR has a better false alarm regulation property and a high PD in a multiple-target environment. Furthermore, the parameter estimation and threshold calculation do not need iterative numerical calculation, and TS-LNCFAR has a high computational efficiency. The superiority of the proposed TS-LNCFAR detector is validated on the multilook Envisat-ASAR and TerraSAR-X data.

C₂H₂, C₂H₄, and C₂H₆ are important oil-dissolved gases in power transformers. Detection of the composition and content of oil-dissolved gases in transformers is very significant in the diagnosis and assessment of the state of transformer operations. The commonly used oil-gas analysis methods have many disadvantages, so this paper proposes a Ni-doped carbon nanotube (Ni-CNT) gas sensor to effectively detect oil-dissolved gases in a transformer. The gas-sensing properties of the sensor to C₂H₂, C₂H₄, and C₂H₆ were studied using the test device. Based on the density functional theory (DFT) the adsorption behaviors of the three gases on intrinsic carbon nanotubes (CNTs) and Ni-CNTs were calculated. The adsorption energy, charge transfer, and molecular frontier orbital of the adsorption system were also analyzed. Results showed that the sensitivity of the CNT sensor to the three kinds of gases was in the following order: C₂H₂ > C₂H₄ > C₂H₆. Moreover, the doped Ni improved the sensor response, and the sensor response and gas concentration have a good linear relationship.

Traditional constant false alarm rate (CFAR) detectors only use the contrast information between ship targets and clutter, and they suffer probability of detection (PD) degradation in multiple target situations. This paper proposes a correlation-based joint CFAR detector using adaptively-truncated statistics (hereafter called TS-2DLNCFAR) in SAR images. The proposed joint CFAR detector exploits the gray intensity correlation characteristics by building a two-dimensional (2D) joint log-normal model as the joint distribution (JPDF) of the clutter, so joint CFAR detection is realized. Inspired by the CFAR detection methodology, we design an adaptive threshold-based clutter truncation method to eliminate the high-intensity outliers, such as interfering ship targets, side-lobes, and ghosts in the background window, whereas the real clutter samples are preserved to the largest degree. A 2D joint log-normal model is accurately built using the adaptively-truncated clutter through simple parameter estimation, so the joint CFAR detection performance is greatly improved. Compared with traditional CFAR detectors, the proposed TS-2DLNCFAR detector achieves a high PD and a low false alarm rate (FAR) in multiple target situations. The superiority of the proposed TS-2DLNCFAR detector is validated on the multi-look Envisat-ASAR and TerraSAR-X data.

In the application of human activity recognition (HAR) based on channel state information (CSI), due to the high dynamic characteristics of wireless channel to different environments, the features of human activity samples in different locations are different. In addition, the existing CSI-based HAR approaches limit the extraction of activity features to the Euclidean space and ignores the rich relational information between samples, categories and locations, which result in insufficient generalization performance for location-independent HAR. To address this challenge, this paper proposes a CSI-based location-independent HAR system CSI-MTGN. The system represents the classification task under each training sample collection location (TSCL) as a task, which is composed of three interactive parts: sample hidden representation, activity features extraction based on hierarchical graph neural network (HGNN) and information exchange based on multi-task learning. The proposed system improves the sample hidden representation, which is benefit for activity feature extraction and classification. The HGNN is designed to express various relationship information between samples, categories and locations in the form of graph structure, and the classification task under each TSCL is constructed through data augmentation, so as to improve the knowledge understanding and inference capabilities of the recognition model. The multi-task learning is used to achieve implicit data augmentation by sharing parameters among tasks through soft parameter sharing, and improves the generalization performance of the system. To validate the performance of the proposed system, experiments were conducted in a hall and a conference room, where samples of 10 categories of activities under 7 TSCLs were used for training the system, and the HAR accuracy rates at any locations were 94.1% and 93.3%, respectively.