The mainstream algorithms used for ship classification and detection can be improved based on convolutional neural networks (CNNs). By analyzing the characteristics of ship images, we found that the difficulty in ship image classification lies in distinguishing ships with similar hull structures but different equipment and superstructures. To extract features such as ship superstructures, this paper introduces transformer architecture with self-attention into ship classification and detection, and a CNN and Swin transformer model (CNN-Swin model) is proposed for ship image classification and detection. The main contributions of this study are as follows: (1) The proposed approach pays attention to different scale features in ship image classification and detection, introduces a transformer architecture with self-attention into ship classification and detection for the first time, and uses a parallel network of a CNN and a transformer to extract features of images. (2) To exploit the CNN’s performance and avoid overfitting as much as possible, a multi-branch CNN-Block is designed and used to construct a CNN backbone with simplicity and accessibility to extract features. (3) The performance of the CNN-Swin model is validated on the open FGSC-23 dataset and a dataset containing typical military ship categories based on open-source images. The results show that the model achieved accuracies of 90.9% and 91.9% for the FGSC-23 dataset and the military ship dataset, respectively, outperforming the existing nine state-of-the-art approaches. (4) The good extraction effect on the ship features of the CNN-Swin model is validated as the backbone of the three state-of-the-art detection methods on the open datasets HRSC2016 and FAIR1M. The results show the great potential of the CNN-Swin backbone with self-attention in ship detection.

Neuronal cell types are essential to the comprehensive understanding of the neuronal function and neuron can be categorized by their anatomical property. However, complete morphology data for neurons with a whole brain projection, for example the pyramidal neurons in the cortex, are sparse because it is difficult to trace the neuronal fibers across the whole brain and acquire the neuron morphology at the single axon resolution. Thus the cell types of pyramidal neurons have yet to be studied at the single axon resolution thoroughly. In this work, we acquire images for a Thy1 H-line mouse brain using a fluorescence micro-optical sectioning tomography system. Then we sample 42 pyramidal neurons whose somata are in the layer 5 of the motor cortex and reconstruct their morphology across the whole brain. Based on the reconstructed neuronal anatomy, we analyze the axonal and dendritic fibers of the neurons in addition to the soma spatial distributions, and identify two axonal projection pattern of pyramidal tract neurons and two dendritic spreading patterns of intratelencephalic neurons. The raw image data are available upon request as an additional asset to the community. The morphological patterns identified in this work can be a typical representation of neuron subtypes and reveal the possible input-output function of a single pyramidal neuron.

A fault diagnosis rule extraction method oriented to machine foot signal based on dynamic support threshold and association coefficient interestingness (DST‐ACI) discriminant criterion is proposed in this paper. The new method includes three main innovations. First, the feature state coding method based onK‐means clustering fully takes into account the imbalanced distribution of signal feature values due to the noise interference, and divide the signal feature values into several range intervals to generate the feature state code. Second, the frequent feature pattern mining method based on dynamic support threshold (DST) discriminant criterion can dynamically adjust support threshold according to the frequency of the feature states in each candidate pattern. Third, the fault diagnosis rule extraction method based on the association coefficient interestingness (ACI) discriminant criterion introduces a new metrics called ACI to evaluate the correlation between the pattern and the fault. Four types of fault simulation experiments were carried out, and the performance of the DST‐ACI method was tested using the collected vibration signal. The results show that compared with the coding method based on equal‐width discretization or equal‐density discretization, the accuracy of the transactional dataset generated by the feature state coding method based on K‐means clustering is higher. Compared with the frequent feature pattern mining method based on the constant support threshold criterion, the pattern mined by the DST‐based criterion has generally higher support. Compared with the existing confidence‐lift‐based and confidence‐improint‐based fault diagnosis rule extraction frameworks, the positive correlation between the feature states and the fault type of the rules extracted based on the DST‐ACI framework is generally stronger.

The versatility of the existing A-optimal-based CNN for solving multiple types of signals classification problems has not been verified by different signals datasets. Moreover, the existing A-optimal-based CNN uses a simplified approximate function as the optimization objective function instead of precise analytical function, which affects the signals classification accuracy to a certain extent. In this paper, a classification method called IA-optimal CNN is proposed. To improve the stability of the classifier, the trace of the covariance matrix of the weights of the fully connected layer is used as the optimization objective function, and the parameter optimization model is established without any simplification of the optimization objective function. In addition, to avoid the difficulty of not being able to obtain the analytical expression formula of the partial derivative of the inverse matrix with regard to the networks parameters, a novel dual function is introduced to transform the optimization problem into an equivalent binary function optimization problem. Furthermore, based on the above analytical solution results, the parameters are updated using the alternate iterative optimization method and the accurate weight update formula is deduced in detail. Five signals datasets are used to test the universality of the IA-optimal CNN in signals classification fields. The performance of IA-optimal CNN is showed, and the experimental results are compared with the existing A-optimal-based classification algorithm. Lastly, the following conclusion is proved theoretically: For the A-optimal-based CNN, the trace of the covariance matrix will continue to decrease and approach a convergence value in the iterative process, but it is impossible for the networks to strictly reach the A-optimal state.