The controller of railway vehicle is the main command control electric appliance which controls the operation of railway vehicle. Any fault of the electronic circuit of the controller will cause the safety accident of railway vehicle. Aiming at the problem of low accuracy in fault diagnosis of controller electronic circuits caused by fuzzy meaning in feature extraction, a fault diagnosis method based on maximum variance rotating principal component analysis and confidence rule base was proposed. Firstly, the dimensionality of the data was reduced by the principal component analysis of the maximum variance rotation to improve the explan ability of the factors after dimensionality reduction. Then the belief rule base reasoning method based on evidence reasoning was used to diagnose the fault, and the CMA-E algorithm was used to optimize the initial parameters of the established model, so as to improve the accuracy of fault diagnosis of electronic circuit of railway vehicle. The effectiveness of the proposed method is verified by simulation and experiment.
Attention mechanism plays a significant role in the current encoder-decoder framework of image captioning. Nevertheless, many attention mechanisms only fuse textual feature and image feature once, failing to adequately integrate the feature between context and image. Furthermore, many image captioning networks based on scene graphs only consider the node information but ignore the structure, which is insufficient in grasping the spatial object relationship. To address the above problems, we propose structural attention and increased global attention. Two attentions select critical image features from image detail and global image. The increased global attention, focusing on global image features, enhances integration between text and image via fusing detailed image features into global attention. To better describe the relationship among image objects, our network allows for both the node information by content attention and the structure information by structural attention. Structural attention computes the similarity between the structure information of scene graph and local attention, building the image objects relationship differing from content attention. We evaluate the performance of our image captioning network in MS COCO and Visual Genome datasets. The results of the experiments show that our method achieves superior performance compared with the existing methods.
Faces contain abundant biological and sociological information. Inter-ethnicity identification using facial images has been intensively studied, while intra-ethnicity classification has received less attention. In this paper, we propose an Ensemble of Convolutional Autoencoders (E-CAE) model to attempt to distinguish Chinese, Japanese, and Korean faces and individuals from different regions of China. To accomplish this task, CJK and RoC datasets are built and E-CAE yields a classification accuracy of 80.69% on CJK dataset and 61.81% on RoC dataset. The experimental results demonstrate that our model outperforms existing methods for fine-grained ethnicity recognition in terms of accuracy and robustness. To our knowledge, this is the first work that performs fine-grained ethnicity recognition at the scale of provinces.
This paper concerns the problem of stochastic stability and stabilization for a class of discrete-time hidden semi-Markov jump systems (HS-MJSs) with time-varying emission probability. By virtue of the hidden semi-Markov model, such stochastic switching system has shown superior capacity of describing the asynchronous phenomenon between the practical system mode and the observed one. Moreover, the proposed emission probability is time-varying and satisfies piecewise homogeneous property in this paper. Based on the presented Lyapunov function, an observed-mode-dependent controller is constructed to stabilize the closed-loop HS-MJSs. Finally, the effectiveness of the proposed control scheme has been verified by a numerical example.
The traveling salesman problem is known to be NP-hard and has numerous areas of applications. This paper proposes a collaborative neurodynamic optimization algorithm based on Boltzmann machines for solving the traveling salesman problem. A population of Boltzmann machines is employed for local search, and their initial states are repeatedly reinitialized by using the particle swarm optimization update rule for global repositioning. The efficacy of the proposed collaborative neurodynamic optimization algorithm is substantiated on four traveling salesman problem benchmark instances.
