Attention mechanisms have recently shown strong potential in improving the performance of convolutional neural networks (CNNs). This letter proposes a fully convolutional attention block (FCAB) that can be combined with a CNN to refine important features and suppress unnecessary ones in synthetic aperture radar (SAR) images. The FCAB consists of a channel attention module and a spatial attention module. For the channel attention module, we use average-pooling and max-pooling to learn complementary features, and apply group convolution to aggregate the information of the two types of channels. Global average-pooling is then used to encode the channel-wise importance. For the spatial attention module, the average-pooling and max-pooling along the channel axis are used to generate two spatial feature maps, and then two very lightweight convolutional layers are used to encode the spatial weight map. Experimental results on SAR images demonstrate that our FCAB can focus on important channels and object regions. It uses relatively few parameters and is computationally efficient, while bringing about significant performance gain for SAR recognition.

High-resolution range profile (HRRP) has obtained intensive attention in radar target recognition and convolutional neural networks (CNNs) are among predominant approaches to deal with HRRP recognition problems. However, most CNNs are designed by the rule-of-thumb and suffer from much more computational complexity. Aiming at enhancing the channels of one-dimensional CNN (1D-CNN) for extracting efficient structural information oftargets form HRRP and reducing the computation complexity, we propose a novel framework for HRRP-based target recognition based on 1D-CNN with channel attention and channel pruning. By introducing an aggregation-perception-recalibration (APR) block for channel attention to the 1D-CNN backbone, channels in each 1D convolutional layer can adaptively learn to recalibrate the extracted features for enhancing the structural information captured from HRRP. To avoid rule-of-thumb design and reduce the computation complexity of 1D-CNN, we proposed a new method incorporated withthe global best leading artificial bee colony (GBL-ABC) to prune the original network based on the lottery ticket hypothesis in an automatic and heuristic manner. The extensive experimental results on the measured data illustrate that the proposed algorithm achievesthe superiorrecognition rate by combing APR and GBL-ABC simultaneously.

It is of great significance to measure the knowledge amount conveyed by Atanassov’s intuitionistic fuzzy sets (AIFSs). Many efforts have been done to define a suitable knowledge measure for AIFSs, or uncertainty measure, named as a dual measure of knowledge measure. However, many of these measures are developed from the view of point of intuitionistic fuzzy entropy, which cannot well reflect the knowledge amount associated with an AIFS. Other knowledge measures developed based on the difference between an AIFS and its complement may lead to information loss in the scenario of decision making. This paper proposed a new knowledge measure for AIFSs. The axiomatic definition of knowledge measure is extended to a more general level. The properties of the new developed knowledge measure are investigated through mathematical analysis and numerical examples. Further discussion on the relation between knowledge measure and entropy measure is proposed to clear up the relation and distinction between them.

Abstract When training base classifier by ternary Error Correcting Output Codes (ECOC), it is well know that some classes are ignored. On this account, a non-competent classifier emerges when it classify an instance whose real label does not belong to the meta-subclasses. Meanwhile, the classic ECOC dichotomizers can only produce binary outputs and have no capability of rejection for classification. To overcome the non-competence problem and better model the multi-class problem for reducing the classification cost, we embed reject option to ECOC and present a new variant of ECOC algorithm called as Reject-Option-based Re-encoding ECOC (ROECOC). The cost-sensitive classification model and cost-loss function based on Receiver Operating Characteristic (ROC) curve are built respectively. The optimal reject threshold values are obtained by combing the condition to be met for minimizing the loss function and the ROC convex hull. In so doing, reject option (t1, t2) provides a three-symbol output to make dichotomizers more competent and ROECOC more universal and practical for cost-sensitive classification issue. Experimental results on two kinds of datasets show that our scheme with low-degree freedom of initialized ECOC can effectively enhance accuracy and reduce cost.

Recent research developments of extreme learning machine (ELM) with multilayer network architecture lead to a promising high performance with extremely fast training speed for representation learning. In this work, the authors are dedicated to develop an efficient and expressive representation learning method with hierarchical ELM, and proposing a novel architectural unit named as double random hidden layers ELM auto‐encoder (DELM‐AE). The novel DELM‐AE consists of one input layer, two random hidden mapping layers for encoding feature, and one output layer for decoding feature. When stacking DELM‐AE in the hierarchical structure, they can construct an H‐DELM model, where the input of the current AE is the feature representation learned by the previous one, but the output is identical to the original input information and is not the input. Hence, the H‐DELM can reproduce the original input data as much as possible to learn more expressive and compact feature. They validate their method on various widely public datasets, and the results demonstrate that H‐DELM can bring significant performance improvements in terms of classification accuracy and robustness compared with existing relevant multilayer ELM and other deep learning algorithms at a slight computational cost.