Orthogonal Time Frequency Space (OTFS) modulation can effectively support high-mobility communication scenarios. However, Orthogonal Frequency Division Multiplexing (OFDM) based OTFS suffers from high spectrum leakage. Implementing channel estimation and equalization that simultaneously supports both OTFS and OFDM also faces challenges. In this paper, we adopt Filter Bank Multi-Carrier (FBMC) modulation as an alternative to OFDM and propose a TF-domain pilot-aided channel estimation and equalization scheme, which can improve spectrum leakage and enhance compatibility. Specifically, first, based on the core function of the prototype filter, we choose the Hermite prototype filter with symmetric properties to construct the FBMC-based OTFS system, enhancing adaptability to dynamic channels. Second, considering the dynamic characteristics of fast time-varying channels, we construct Bessel fitting or priori information-assisted channel extrapolation mechanisms to achieve accurate tracking of channel parameters. Finally, we derive the criterion for determining the channel wide-sense stationarity time interval, which provides a basis for the update mechanism of prior information. Simulation results show that the proposed scheme can work robustly on doubly-selection channels. Compared to classical OTFS, FBMC-based OTFS significantly improves reliability in high mobility scenarios.

Millimeterwave (mmWave) techniques will be a key enabler for wireless communications to achieve high data rates. Additionally, Filter Bank Multi-Carrier (FBMC) with good spectral properties has also been regarded as an important transmission technique for future wireless communications. In this letter, we design and analyze an FBMC-based mmWave Multiple-input Multiple-output (MIMO) system. Specifically, we first pre-code quadrature amplitude modulation symbols in time to ensure that the MIMO technique becomes simple in FBMC. Secondly, we determine the optimal subcarrier spacing by maximizing the signal-to-interference ratio. Finally, using a lens antenna array combined with a simple channel estimator, we transmit data to the receiver. Simulation results show that FBMC can effectively support multi-antenna and mmWave techniques, providing favorable efficiency and reliability. Furthermore, we also verify that Alamouti's space time block code can provide considerable diversity gain.

Hyperspectral image (HSI) encompasses a wealth of spectral-spatial information, offering a sufficient foundation for classification. However, the presence of redundancy poses challenges for achieving accurate classification. In this letter, we design a spectral-spatial interactive transformer (S2IT) for HSI classification (HSIC). S2IT commences with a meticulously designed spectral-spatial reconstruction (S2R) module, which aims to augment the representation of shallow features. Subsequently, an adaptive asymmetric gating mechanism transformer (AGM-Former) aims to delve into and extract comprehensive local-global features from HSI. Ultimately, the spectral-spatial interactive attention (S2IA) synergizes the spectral-spatial features and enhances classification prowess. S2IT demonstrates rigorous experiments on three renowned datasets: Houston2013 (HU), Indian Pines (IP), and the University of Pavia (UP), which validates its effectiveness in enhancing HSIC accuracy.

Transformers are increasingly popular in computer vision, which treat an image as a sequence of image patches and learn robust global features from the sequence. However, pure transformers are not entirely suitable for hyperspectral and light detection and ranging (LiDAR) image classification because image classification requires both robust global features and discriminative local features. Therefore, this article introduces a novel convolution interaction transformer network (CITNet) for jointly classifying hyperspectral and LiDAR images. The process begins with a carefully designed multiscale asymmetric depthwise convolution (MADC) module that exploits the local–global correlations of shallow features. On this basis, a novel local–global transformer (LGTM) is equipped with a local–global feed-forward (LGF) network to extract in-depth local–global joint features from the multimodal data. Then, an optimization convolution cross-attention (OCA) module, incorporating a convolutional layer, is developed to simulate the spatial relationships of semantic tokens. Finally, extensive experiments are conducted on the well-known Trento (TR), Augsburg (AU), MUUFL (MU), and Houston2013 (HU) datasets. The overall accuracy (OA) reaches 99.76%, 97.40%, 91.06%, and 99.90%, respectively, which are 0.2%–1.66%, 0.32%–7.37%, 1.52%–12.71%, and 0.14%–93.79% higher than the state-of-the-art (SOTA) methods, demonstrating the effectiveness of CITNet in improving the joint classification accuracy of hyperspectral and LiDAR images.

The accuracy of hyperspectral image (HSI) classification relies on lots of labeled training samples. However, the existing HSI data can be used for training with extremely limited labeled samples. In this letter, we propose a semisupervised HSI classification network based on pseudo-label and spatial-spectral convolution (PS3DN), which can improve classification accuracy with limited labeled samples. First, we design an asymmetric dense residual network (ARDN), which uses asymmetric convolution kernels instead of square kernels to reduce the number of parameters. Then we use the Center-Focus loss function to update the network parameters, aiming to improve the robustness of the network. Further, we generate high-confidence pseudo-labels by this network, which reduces the need for labeled samples for the classification network. Finally, we propose a joint spatial-spectral convolutional (SSCNN) classification network, the fusion of spatial-spectral separation convolution and self-learning attention mechanism, to achieve more accurate classification. We conducted experiments on four public datasets, and the experimental results show that the classification accuracy of Pavia University (UP), Salinas (SA), Kennedy Space Center (KSC), and Indian Pines (IP) datasets is 92.45%, 96.91%, 98.38%, and 90.43%, respectively.

HSI has abundant spectral–spatial information. Using this information to improve the accuracy of HSI classification is a hot issue in the industry. This letter proposes an end-to-end multilevel hybrid attention network (DMCN). It is composed of a dense 3-D convolutional neural network (3D-CNN), grouped residual 2D-CNN, and coordinate attention that can perceive categories. In the case of a small number of training samples, DMCN can still extract spectral–spatial fusion information and learn spatial features more deeply for classification. Experiments are conducted on three well-known hyperspectral datasets, i.e., Indian Pines (IP), University of Pavia (UP), and Salinas (SA). The results show that DMCN achieved 92.39%, 97.28%, and 98.40% classification accuracy in IP, UP, and SA.

The SL0 algorithm for compressive sensing (CS) reconstruction uses smoothed ℓ0norm and introduces a sequence of smoothed functions to approximate the ℓ0norm. Therefore, the NP-hard problem of minimization of the ℓ0norm can be transferred to a convex optimization problem for smoothed functions. Considering the defects of SL0 algorithm in the iterative process and in order to choose an appropriate the ℓ0norm, we use Composite Inverse Proportion Model to approximate the ℓ0norm, introduce the thought of the OSL0 algorithm, and combine with the steepest descent method and the gradient projection principle to get the reconstruction signal, a new algorithm called Modified Smoothed ℓ0algorithm(MSL0) is proposed. Experimental results show that, under the same test conditions, the MSL0 algorithm is superior to SL0 and other same type algorithms both in the reconstruction quality and the performance.