Radar waveform design performance is compromised by insufficient prior information regarding radiators and clutter. This letter addresses this challenge by leveraging structured covariance matrices to enhance the robustness of multiple-input multiple-output (MIMO) radar waveform design. We explore the joint optimization of MIMO radar transmit waveforms and receive filters in environments with radiators and clutter, even in the absence of adequate prior information. To tackle this issue, an iterative method is employed under worst-case assumptions regarding the covariance matrices of the radiators and clutter. By applying the alternating direction method of multipliers (ADMM) algorithm, this letter introduces a novel approach for designing waveforms and structuring the covariance matrices' parameters in spectrally crowded and cluttered environments. Simulation results demonstrate that the proposed method significantly improves performance in mismatched environments.

A visual mechanical signal detection and loading platform with super-resolution based on deep learning is designed to improve the detection accuracy of mechanical signals. The visual mechanical signal detection and loading platform with super-resolution include three-dimensional (3D) biological force quantitative detection platform and the mechanical signal loading platform with 3D magnetic distortion and ultrahigh resolution. In the 3D biological force quantitative detection platform, four 3D force sensors are used to collect mechanical signals, and the improved fuzzy clustering fusion method is used to fuse the mechanical signals collected by 3D force sensors to improve the detection accuracy of mechanical signals. The mechanical signal loading platform of 3D magnetic distortion and ultrahigh resolution technology connects the 3D magnetic distortion instrument and microscope, collects images through high-speed scanning components and distorted magnetic field, reconstructs the collected images by deep learning method, obtains ultrahigh-resolution mechanical signal visual images, and triggers mechanical signal loading and release by synchronous interactive system. The consequences of the experiment demonstrate that the designed platform can display the super-resolution mechanical signals through the visual interface. The mechanical signals are loaded in different directions, and the detection accuracy of mechanical signals is higher than 99.5%.

To accurately detect and identify whether there are abnormalities in the information of the expressway networking system, an information security event reasoning and traceability method based on deep learning is proposed to build a data security protection system that includes the data life periodicity of the expressway networking system. In this system, the information security event model based on intrusion detection message exchange format is established. The model uses the information risk event reasoning method based on a deep convolution neural network to infer the risk event during data sharing of the expressway networking system, reorganize and standardize the risk event information according to the format of the information security event standardization model, and store it in the risk event database in the form of Extensible Markup Language data document. The information risk event traceability method based on the electronic fingerprint takes all risk events in the database as the target. After designing the electronic fingerprint of risk events, the original network attack tree is constructed to realize risk event traceability combined with fingerprint information. Testing indicates that the reasoning and traceability results of this method to the information security events of the expressway networking system are consistent with those in reality and our method has good usability.

To ensure the reliability and safety of expressway networking systems, this paper designs a data flow risk monitoring system for expressway networking systems based on deep learning. The monitoring system is composed of data flow risk analysis, formulation of safety strategy, real-time monitoring, and disaster recovery. Data flow risk analysis is the basis for the operation of each part of the system. Meanwhile, indexes such as network management, data assets, and network resources are selected to build a data flow risk monitoring index system. The deep convolution neural network model is constructed, and the data flow risk monitoring index data are input into the deep convolution neural network to extract the index data features through the convolution and pooling process. Based on this, feature mapping is realized with a multilayer perceptron, and the index data risk classification results of data flow risk monitoring are output by the SoftMax classifier. The experimental results show that the monitoring system can obtain accurate data flow risk analysis results which effectively reduces the data loss rate, alleviate the impact of different types of malicious attacks, and ensure the stability and security of the experimental object.

Support correlation filter tracking method uses cyclic sampling to transform the calculation into frequency domain, which solves the problems of sampling and large computation of support vector machine. However, the current method can not exploit the information of backgrounds because all samples are generated by cyclic sampling around the target in the tracking process. To solve this problem, this paper proposes a background awareness support correlation filter tracking method using mask matrix. In the tracking process, the mask matrix is used to extract the patchs densely from background as negative samples, so the background information is used effectively. Experiments on OTB100 database show that compared with Scale Kerneling Supported Correlation Filtering (SKSCF), the proposed algorithm achieves a gain of 4.2% in mean OP and 6.2% AUC score respectively.

Most existing methods only consider the local features of the samples, and their experimental results show better performance than traditional Non-deep learning methods. However, in these methods, the global features of the sample space are usually ignored, and these ignored global features will affect the classification accuracy. To solve this problem, a novel triple capsule network framework is proposed to text classification. The training in the first stage, to obtain a basic capsule network for obtaining local features. Then, three capsule networks sharing parameters are combined spatially, and the triplet loss function is used in the second stage of training. By comparative learning, the capsule network can learn global features that can represent the spatial distance between different categories. Through comparison experiments on six datasets and ten general benchmark algorithms, the results show that our results is the first in the four datasets.