A new image fusion approach for infrared and visible images is explored, combining fusion with data compression based on sparse representation and compressed sensing. The proposed approach first ...compresses the sensing data by random projection and then obtains sparse coefficients on compressed samples by sparse representation. Finally, the fusion coefficients are combined with the fusion impact factor and the fused image is reconstructed from the combined sparse coefficients. Experimental results validate its rationality and effectiveness, which can achieve comparable fusion quality on the less-compressed sensing data.
Traditional methods of multi-label text classification, particularly deep learning, have achieved remarkable results. However, most of these methods use word2vec technology to represent sequential ...text information, while ignoring the logic and internal hierarchy of the text itself. Although these approaches can learn the hypothetical hierarchy and logic of the text, it is unexplained. In addition, the traditional approach treats labels as independent individuals and ignores the relationships between them, which not only does not reflect reality but also causes significant loss of semantic information. In this paper, we propose a novel Hierarchical Graph Transformer based deep learning model for large-scale multi-label text classification. We first model the text into a graph structure that can embody the different semantics of the text and the connections between them. We then use a multi-layer transformer structure with a multi-head attention mechanism at the word, sentence, and graph levels to fully capture the features of the text and observe the importance of the separate parts. Finally, we use the hierarchical relationship of the labels to generate the representation of the labels, and design a weighted loss function based on the semantic distances of the labels. Extensive experiments conducted on three benchmark datasets demonstrated that the proposed model can realistically capture the hierarchy and logic of text and improve performance compared with the state-of-the-art methods.
With the rising popularity of social networks and service recommendations, research on new methods of friend recommendation have become a key topic, especially when based on quality-driven resource ...processing in an edge computing environment. Traditional methods seldom systematically combine static attributes (e.g., interests, geographical locations, and common friends), dynamic behaviors (e.g., liking, making comments, forwarding and @), and network structures (e.g., social ties) to recommend a new friend to a target user. Meanwhile, with the advent of deep learning, it has become more challenging to integrate these features into a deep neural network framework for friend recommendation. For example, how do we optimally make use of these features to form a united framework and what type of deep neural network architecture should be introduced into a novel recommendation method in an edge computing environment? In this paper, we propose DFRec++, a hybrid deep neural network framework combining attribute attention and network embeddings to make social friend recommendations with the help of both interactive semantics and contextual enhancement. More specifically, we first utilize the latent dirichlet allocation (LDA) topic model to generate common interest topics between users and compute the similarity of the explicit static attribute vector representation of topics, locations, and common friends. Then we feed dynamic behavior attributes into a convolutional neural network (CNN) to obtain the implicit vector representation of the interactions and context between two users. Subsequently, a multi-attention mechanism is designed to further improve the deep vector representation of the attribute information. Next, the LINE-based network embeddings algorithm is applied to embed the network structure into a low-dimensional vector. Finally, the attribute attention vector and the network embeddings are concatenated to form a deep feature representation, which is subsequently fed to a fully connected neural network (FCNN) to capture the probability of friendship between two users. The output of FCNN indicates the probability of two users becoming friends. We conducted experiments on a real-world Weibo dataset and the results show that DFRec++ outperforms several existing methods.
•The paper proposes a novel dynamic graph recurrent convolutional neural network model, named Dynamic-GRCNN, to deeply capture the spatio-temporal traffic flow features for more accurately predicting ...urban passenger traffic flows.•The paper presents incidence dynamic graph structures based on historically passenger traffic flows to model traffic station relationships. Different from existing traffic transportation network topological structures based graph relationships between stations, the incidence dynamic graph structures firstly model the traffic relationships from historical passenger flows.•For real urban passenger traffic flows, the paper demonstrates that dynamic spatial-temporal incidence graphs are more suitable to model external changes and influences.•The paper compares Dynamic-GRCNN with state-of-the-art deep learning approaches on three benchmark datasets which contain different types of passenger traffic flows for evaluation. The results show that Dynamic-GRCNN significantly outperforms all the baselines in both effectiveness and efficiency in urban passenger traffic flows prediction.
Accurate and real-time traffic passenger flows forecasting at transportation hubs, such as subway/bus stations, is a practical application and of great significance for urban traffic planning, control, guidance, etc. Recently deep learning based methods are promised to learn the spatial-temporal features from high non-linearity and complexity of traffic flows. However, it is still very challenging to handle so much complex factors including the urban transportation network topological structures and the laws of traffic flows with spatial and temporal dependencies. Considering both the static hybrid urban transportation network structures and dynamic spatial-temporal relationships among stations from historical traffic passenger flows, a more effective and fine-grained spatial-temporal features learning framework is necessary. In this paper, we propose a novel spatial-temporal incidence dynamic graph neural networks framework for urban traffic passenger flows prediction. We first model dynamic traffic station relationships over time as spatial-temporal incidence dynamic graph structures based on historically traffic passenger flows. Then we design a novel dynamic graph recurrent convolutional neural network, namely Dynamic-GRCNN, to learn the spatial-temporal features representation for urban transportation network topological structures and transportation hubs. To fully utilize the historical passenger flows, we sample the short-term, medium-term and long-term historical traffic data in training, which can capture the periodicity and trend of the traffic passenger flows at different stations. We conduct extensive experiments on different types of traffic passenger flows datasets including subway, taxi and bus flows in Beijing. The results show that the proposed Dynamic-GRCNN effectively captures comprehensive spatial-temporal correlations significantly and outperforms both traditional and deep learning based urban traffic passenger flows prediction methods.
In this paper, the 3D model of the centrifugal compressor is established by Solidworks software at first. Second, the numerical simulation of the centrifugal compressor is carried out by using CFX ...software. Combined with the simulation results, the conclusion that properly reducing the outlet width of diffuser can effectively restrain the generation of flow separation and reduce the influence of impeller rotation on diffuser is revealed. Finally, the internal flow field structure and machine performance of the diffuser are improved. The research provides a reference for improving the performance and flow field structure of the compressor as well as the design of the vaneless diffuser.
Abstract In the context of the deep integration of artificial intelligence and industrial fields, precise calculation of multi-step process capability has become a current research hotspot. In most ...industrial fields, the estimation of multi-step process capability is mostly in the rough estimation stage, and there are relatively few precise quantitative calculation methods. This paper focuses on multi-step processes in the industrial field, using deep learning models to learn the features of each step step step by step, and then comprehensively estimating the weights between each step, ultimately achieving accurate prediction of multi-step process capabilities. This paper conducts in-depth analysis of the performance and efficiency of different models on such problems by designing a large number of validation experiments, and also provides ideas and suggestions for subsequent research in this field.
•Proposed a dynamic word embedding method (DB-WE) for intelligent feature extraction from background network traffic data.•Introduced the contrastive learning method SimCSE for efficient generation ...of high-quality and numerous background network traffic.•Developed DBWE-Corbat, a complete background network traffic generation model that integrates DB-WE and SimCSE.•Demonstrated through extensive experiments that DBWE-Corbat can generate high-quality traffic data to satisfy the needs of cyber range construction.•The proposed approach offers an efficient and intelligent method for generating background network traffic data that accurately captures the spatiotemporal characteristics of traffic.
Background network traffic generation is critical to replicating the real network environment in Cyber Range. But how to sufficiently extract the spatio-temporal features of traffic and generate superior background network traffic are still problems for the Cyber Range. In this paper, we propose a background network traffic generative model, DBWE-Corbat. Our solution relies on intelligent feature extraction based on the DB-WE dynamic word embedding method. Which consists of Doc2Vec and two Bidirectional Long Short-Term Memory (Bi-LSTM) layers. Specifically, first we convert the traffic feature tuple data into a static word vector. Then, we capture the spatio-temporal features of the traffic for characterization. Finally, we generate high-quality and numerous background network traffic by learning the feature distribution of small samples based on the contrastive learning model SimCSE. Extensive experiments show that our approach can generate high-quality traffic data. It meets the requirements of cyber range construction compared to other traffic generation methods.
PDF
