Search

In recent years, deep learning (DL) networks have achieved considerable success in the synthetic aperture radar (SAR) target detection task. Here, in current DL-based methods, originally designed for natural images, SAR images usually have been treated as real-valued images and solely utilize the magnitude information for feature extraction. However, different from natural images, SAR images are complex-valued data. The conversion from the complex-valued images to the real-valued images potentially leads to disregarding valuable target features inherent in original SAR data. To develop the complex-valued information inherent in SAR images adequately, a target detection method for SAR images using the complex-valued network (CV-SAR-Det) is proposed in this article. Specifically, the CV-SAR-Det mainly includes three complex-valued elements: network structure, loss function, and data augmentation. First, the network adopts a fully complex-valued structure for target detection, which effectively leverages the separability characteristics of targets inherent in the complex-valued SAR image. Second, a complex-valued loss function is designed for the optimization of the CV-SAR-Det, which highlights the importance of the complex-valued information. Finally, to further improve the detection performance, a complex-valued data augmentation method is proposed for diversifying the training data, which also improves the robustness of the network. The advantages of the CV-SAR-Det have been demonstrated by the experimental results based on the MiniSAR-KU/KA datasets, which are superior to the latest SAR target detection methods.

Traditional synthetic aperture radar (SAR) image sea-land segmentation algorithms overlook the ship distribution priori-information provided by the automatic identification system (AIS) data, resulting in poor segmentation performance in complex environments such as ports, marine wetlands, beaches, and other sea-land boundaries. To address the above issues, this article comprehensively uses dual-polarization (VV and VH) SAR images and AIS data as the data source, and it specifically proposes a novel pyramid vision transformer (PVT) assisted by the long-time AIS data (AIS-PVT) for sea-land segmentation. AIS-PVT is the first attempt to integrate the ship distribution density priori-information, provided by the long-time AIS data, into the PVT network, thus the multiscale features of the sea and land can be better distinguished. In the decoding stage, we design a feature filter module (FFM). It aggregates features separately along two spatial directions from the skip connections, enhancing the representation of objects of interest while reducing the influence of redundant information. Furthermore, we develop a boundary-pixel-aware function to steer the model training process, allowing AIS-PVT to concentrate more on the neighborhood information of boundary pixels. Importantly, the AIS-PVT method captures global multiscale information and enhances the model’s data fusion capability. The conclusive experimental results demonstrate the superior performance of our approach in sea-land segmentation tasks, outperforming other state-of-the-art (SOTA) techniques.

Well understanding the access behavior of hot data is significant for NAND flash memory due to its crucial impact on the efficiency of garbage collection (GC) and wear leveling (WL), which respectively dominate the performance and life span of SSD. Generally, both GC and WL rely greatly on the recognition accuracy of hot data identification (HDI). However, in this paper, the first time we propose a novel concept of hot data prediction (HDP), where the conventional HDI becomes unnecessary. First, we develop a hybrid optimized echo state network (HOESN), where sufficiently unbiased and continuously shrunk output weights are learnt by a sparse regression based on L2 and L1/2 regularization. Second, quantum-behaved particle swarm optimization (QPSO) is employed to compute reservoir parameters (i.e., global scaling factor, reservoir size, scaling coefficient and sparsity degree) for further improving prediction accuracy and reliability. Third, in the test on a chaotic benchmark (Rossler), the HOESN performs better than those of six recent state-of-the-art methods. Finally, simulation results about six typical metrics tested on five real disk workloads and on-chip experiment outcomes verified from an actual SSD prototype indicate that our HOESN-based HDP can reliably promote the access performance and endurance of NAND flash memories. [ABSTRACT FROM AUTHOR]