Convolutional neural networks and graph convolutional neural networks are two classical deep learning models that have been widely used in hyperspectral image classification tasks with remarkable achievements. However, hyperspectral image classification models based on graph convolutional neural networks using only shallow spectral or spatial features are insufficient to provide reliable similarity measures for constructing graph structures, limiting their classification performance. To address this problem, we propose a new end-to-end hyperspectral image classification model combining 3D–2D hybrid convolution and a graph attention mechanism (3D–2D-GAT). The model utilizes the collaborative work of hybrid convolutional feature extraction module and GAT module to improve classification accuracy. First, a 3D–2D hybrid convolutional network is constructed and used to quickly extract the discriminant deep spatial-spectral features of various ground objects in hyperspectral image. Then, the graph is built based on deep spatial-spectral features to enhance the feature representation ability. Finally, a network of graph attention mechanism is adopted to learn long-range spatial relationship and distinguish the intra-class variation and inter-class similarity among different samples. The experimental results on three datasets, Indian Pine, the University of Pavia and Salinas Valley show that the proposed method can achieve higher classification accuracy compared with other advanced methods.

Hyperspectral image (HSI) classification is an important part of its processing and application. Aiming at the problems of high data dimensionality and high spatial neighborhood correlation in HSI classification, we propose a spatial-spectral joint classification method of HSI with locality and edge preserving in this paper. Firstly, the input HSI is normalized, and the feature is extracted by principal component analysis. The first principal component image is taken as the guidance image. Secondly, guided filtering is used to extract the spatial features of each band separately. Then, the extracted spatial features are superimposed, and low-dimensional embedding is completed through local Fisher discriminant analysis. Finally, the obtained low-dimensional embedded features are input into a random forest classifier to get classification results. The experimental results of two HSI show that the proposed method achieves higher classification accuracy than other related methods. In the case of randomly selecting 10% and 1% samples from each class of ground object as training samples, the overall classification accuracy is improved to 99.57% and 97.79%, respectively. This method effectively uses the spatial and local information of the image in low dimensional embedding, and preserves the boundaries of the ground objects, thus improving the classification effect.

Vehicular Ad Hoc Networks (VANETs) expand the application business of intelligent transportation systems. However, open communication environment issues a new challenge to the security of transmitting data. Data transmissions is vulnerable to malicious attacks, and the jamming attack interrupts the legitimate communications by transmitting jamming signals. To this end, we concern about the security of communication between vehicles and Road-side Units. We propose a novel dueling double deep Q-networks-based secrecy data rate maximization (D3QNSDR) algorithm for VANETs. Under the transmission power constraints, the secrecy data rate is maximally improved by the joint optimization of bandwidth allocation and transmission power. To get the optimal ant-jamming response policy, a decision making of the bandwidth allocation and transmission power is formalized as a Markov Decision Process (MDP) optimization. Then, a novel D3QN algorithm is designed to obtain the solution of the MDP. The experimental results show that the performance of D3QN-SDR outperforms benchmarks in terms of the attack success rate and secrecy data rate

A place name and address matching model based on semantic mining is proposed in this paper. Firstly, the semantic features of place name and address description information is analyzed. Then, spatial object cognitive representation model geographic ontology is constructed to formalize the place name and address described by natural language. Finally, the inference rules of spatial relations are defined in order to achieve semantic matching and retrieval of referential address. Experiments show that the proposed method can accurately express and reasoning out the location information of geographical entity, and can serve the place name and address matching tasks with semantic characteristics.