Vehicle driving path planning is an important information service in intelligent transportation systems. As an important basis for path planning optimization, the travel time prediction method has attracted much attention. However, traffic flow has features of high nonlinearity, time-varying, and uncertainty, which makes it hard for prediction method with single feature to meet the accuracy demand of intelligent transportation system in big data environment. In this paper, the historical vehicle Global Positioning System (GPS) information data is used to establish the traffic prediction model. Firstly, the Clustering in QUEst (CLIQUE)-based clustering algorithm V-CLIQUE is proposed to analyze the historical vehicle GPS data. Secondly, an artificial neural network (ANN)-based prediction model is proposed. Finally, the ANN-based weighted shortest path algorithm, A-Dijkstra, is proposed. We used mean absolute percentage error (MAPE) to evaluate the predictive model and compare it with the predicted results of Average and support regression vector (SRV). Experiments show that the improved ANN path planning model we proposed can accurately predict real-time traffic status at the given location. It has less relative error and saves time for users’ travel while saving social resources.

The attention mechanism enables graph neural networks (GNNs) to learn the attention weights between the target node and its one-hop neighbors, thereby improving the performance further. However, most existing GNNs are oriented toward homogeneous graphs, and in which each layer can only aggregate the information of one-hop neighbors. Stacking multilayer networks introduces considerable noise and easily leads to over smoothing. We propose here a multihop heterogeneous neighborhood information fusion graph representation learning method (MHNF). Specifically, we propose a hybrid metapath autonomous extraction model to efficiently extract multihop hybrid neighbors. Then, we formulate a hop-level heterogeneous information aggregation model, which selectively aggregates different-hop neighborhood information within the same hybrid metapath. Finally, a hierarchical semantic attention fusion model (HSAF) is constructed, which can efficiently integrate different-hop and different-path neighborhood information. In this fashion, this paper solves the problem of aggregating multihop neighborhood information and learning hybrid metapaths for target tasks. This mitigates the limitation of manually specifying metapaths. In addition, HSAF can extract the internal node information of the metapaths and better integrate the semantic information present at different levels. Experimental results on real datasets show that MHNF achieves the best or competitive performance against state-of-the-art baselines with only a fraction of 1/10 $\sim$ 1/100 parameters and computational budgets. Our code is publicly available at https://github.com/PHD-lanyu/MHNF

With the advent of the era of the Internet of Things (IoT), a large number of interconnected smart devices form a huge network. The network can be abstracted as a graph, and we propose to identify similar IoT devices in different networks by graph alignment. However, most methods rely on prelabeled cross-network node pairs such as anchor links, which are difficult to obtain due to personal privacy and security restrictions, especially in IoT. In addition, existing network entity alignment methods focus on individual pairs of nodes but ignore the tightly connected group structure in the network, which is a significant feature of IoT devices. In this paper, we propose a method of Hierarchical Unsupervised Network Alignment (HUNA) to identify similar IoT devices in different networks by a deep learning approach. First, we propose an Unsupervised Network Alignment method based on cycle adversarial networks (UNA), which utilizes the adversarial characteristics of cycle adversarial networks to achieve entity alignment under unsupervised conditions. Second, we further expand the model by carefully designing the group structure aggregation optimization module to aggregate the nodes with closely related attributes and structures into a coarse-grained node and align the coarse-grained nodes. Finally, we evaluate HUNA with real and synthetic datasets. Experimental results show that this method can improve the accuracy of node alignment by 10% and perform well in terms of parameter sensitivity.

With the advent of the era of artificial intelligence and big data, intelligent security robots not only improve the efficiency of the traditional intelligent security industry but also propose higher requirements for intelligent security. Aiming to solve the problem of long recognition time and high equipment cost of intelligent security robots, we propose a new face recognition method for intelligent security in this paper. We use the Goldstein branching method for phase unwrapping, which can improve the three-dimensional (3D) face reconstruction effect. Subsequently, by using the three-dimensional face recognition method based on face radial curve elastic matching, different weights are assigned to different curve recognition similarity for weighted fusion as the total similarity for recognition. Experiments show that the method has a higher face recognition rate and is robust to attitude, illumination, and noise.

Counterfeit Chinese liquor incidents in China have significantly disrupted market order and jeopardized the health of consumers. Currently, deep learning-based spectral detection techniques are extensively leveraged in non-invasive food inspection. Excessive reliance on labels severely limits its application in real scenarios. To make better use of limited samples, we are the first to use the “unsupervised pre-training & supervised fine-tuning” paradigm in combining the Transformer architecture for feature extraction and classification of the Chinese liquor spectrum, and propose Spectrum-BERT, which represents Bidirectional Encoder Representations from Transformers for Spectrum. Specifically, we creatively propose spectral curve partitioning and 1-D convolutional layer mapping to maintain the model’s sensitivity to characteristic peak locations and local information of spectral curves. Moreover, the paradigm of “unsupervised pre-training & supervised fine-tuning” addresses the limitation of label deficiency, thus improving the model’s applicability. Finally, we have conducted extensive experiments on the real liquor spectral dataset. Comparative experiments demonstrate that Spectrum-BERT outperforms all baselines on all metrics using only 70% supervised signal. The limit experimental results show that Spectrum-BERT can still maintain its lead using only the 10% supervised signal. Thanks to the more efficient model architecture, Spectrum-BERT’s model parameters and FLOPs are only 1/568 and 1/322 of those of baselines.