28 April 2023 in IEEE Transactions on Geoscience and Remote Sensing
Recently, few-shot learning (FSL) has exhibited great potentials in hyperspectral image (HSI) classification due to its promising performance under few training samples. Although existing FSL methods have achieved great success, some limitations can still be witnessed. On the one hand, current methods mainly rely on the single metric to identify, which cannot effectively represent the class distribution with few labeled samples. On the other hand, existing methods usually only use the last deep feature of feature extractor, which may lead to the under-utilization of scarce labeled samples. To overcome the above issues, a novel multistage relation network with dual-metric (DM-MRN) is proposed for few-shot HSI classification. Firstly, a sample recombination strategy is designed to increase the variety of classification tasks in training period. Secondly, an embedding module is employed to extract deep features of the input image patches. Thirdly, we propose two relation modules: image-to-class (I2C) block and image-to-image (I2I) block. I2C block is designed to compute I2C-level relation score between second-order features, and I2I block is conceived to generate I2I-level relation score between first-order features. Finally, DM-MRN is constructed by integrating one embedding module, two I2C blocks, and one I2I block. In addition, an adaptive weighting strategy is designed to fuse the obtained relation scores, and classification can be achieved by assigning each query sample to the class with the highest value of the fused relation score. Extensive experiments carried out on five popular HSI data sets demonstrate that the proposed method outperforms other traditional and advanced models under few training samples in terms of classification accuracy and generalization performance, i.e., the performance improvement in terms of OA is around 0.30%-27.98% under 10 labeled samples per class.
1 April 2023 in Journal of Physics: Conference Series
The voltage balance of the series diodes is the premise to ensure the stable and reliable operation of the high voltage uncontrolled rectifier valve. When traditional RC and RCD voltage balancing methods are applied to high voltage uncontrolled rectifier valves in far-reaching offshore wind farms, the complex and changeable operating environment poses a challenge to the anti-interference of the balance effect of the snubber circuit. In this paper, an active RCD adaptive voltage balancing control strategy with strong anti-interference ability is proposed based on the establishment of the active RCD voltage balancing model of the high voltage uncontrolled rectifier valve. The parameter tuning method of the active RCD snubber circuit is given, and the auto-PID control strategy of the active RCD snubber circuit is proposed according to its nonlinear time-varying characteristics. The simulation example verifies that the active RCD adaptive voltage balancing strategy of the high voltage uncontrolled rectifier valve has strong anti-interference performance, which provides a reference for the design of the high voltage uncontrolled rectifier valve voltage sharing system in the far-reaching offshore wind farm.