To address the poor robustness of the extracted image features in traditional smoke detection methods, a smoke recognition method based on Dense convolution neural Network (DenseNet) was proposed. Firstly, the dense network blocks were constructed by applying convolution operation and feature map fusion, and the dense connection mechanism was designed between the convolution layers, so as to promote the information circulation and feature reuse in the dense network block structure. Secondly, the DenseNet was designed by stacking the designed dense network blocks for smoke recognition, saving the computing resources and enhancing the expression ability of smoke image features. Finally, aiming at the problem of small smoke image data size, data augmentation technology was adopted to further improve the recognition ability of the training model. Experiments were carried out on public smoke datasets. The experimental results illustrate that the proposed method achieves high accuracy of 96.20% and 96.81% on two test sets respectively with only 0.44 MB model size.
In order to achieve robust, accurate and real-time recognition of surface scratches under complex texture background with uneven brightness, a surface scratch recognition method based on deep neural network was proposed. The deep neural network for surface scratch recognition consisted of a style transfer network and a focus Convolutional Neural Network (CNN). The style transfer network was used to preprocess surface scratches under complex background with uneven brightness. The style transfer networks included a feedforward conversion network and a loss network. Firstly, the style features of uniform brightness template and the perceptual features of the detected image were extracted through the loss network, and the feedforward conversion network was trained offline to obtain the optimal parameter values of network. Then, the images with uniform brightness and uniform style were generated by style transfer network. Finally, the proposed focus convolutional neural network based on focus structure was used to extract and recognize scratch features in the generated image. Taking metal surface with light change as an example, the scratch recognition experiment was carried out. The experimental results show that compared with traditional image processing methods requiring artificial designed features and traditional deep convolutional neural network, the false negative rate of scratch detection is as low as 8.54% with faster convergence speed and smoother convergence curve, and the better detection results can be obtained under different depth models with accuracy increased of about 2%. The style transfer network can retain complete scratch features with the problem of uneven brightness solved, thus improving the accuracy of scratch recognition, while the focus convolutional neural network can achieve robust, accurate and real-time recognition of scratches, which greatly reduces false negative rate and false positive rate of scratches.
Currently, due to the limitation of hardware for network protocol developing and huge cost of network building in hardware for performance evaluation, most of the literature focuses on software system which limits the results in theory. To solve these problems, a hardware-in-loop simulation system for distributed wireless network MAC (Media Access Control) protocols based on GNU Radio and the second generation of Universal Software Radio Peripheral (USRP2) was designed and implemented. Referring to the standard IEEE802.11 Distribution Coordination Function (DCF) protocol, the designed simulation system adopted the discrete-event simulation technique to realize simulation for multi-node distributed wireless networks with only the least hardware resources (i.e., one Personal Computer (PC) and two USRP2s). In the software, the MAC protocols were implemented using Python language, which is flexible and easy to change or extend. And in the physical layer, modularized modules in C++ language were adopted for signal processing, which further improves the scalability of the simulation system. The experimental results validate the reliability of the hardware-in-loop simulation system, in comparison with the Bianchi algorithm and time slot based saturation throughput calculation model.
The Automated Trust Negotiation (ATN) Model based on Interleaved Spiral Matrix Encryption (ISME) was proposed for the protection of sensitive information in the automated trust negotiation. The interleaved spiral matrix encryption and policy migration were used in the model to protect three kinds of sensitive information of negotiation. Compared with the traditional spiral matrix encryption algorithm, the concept of odd-even bit and triple were added into the interleaved spiral matrix encryption algorithm. In order to make the model adapt the application better, the concept of key attributes flag was introduced in the certification of negotiations, and thus it recorded the sensitive information which corresponded to the encrypted key effectively. Meanwhile, how to represent the negotiation rules through encryption function was listed in the negotiation model. To increase efficiency and success rate of the model, the 0-1 graph policy parity algorithm was proposed. The decomposition rules of six basic propositions were constructed by directed graph of graph theory in the 0-1 graph policy parity algorithm. The propositions abstracted by the access control policies could be determined effectively and the reliability and completeness was testified to prove the equivalence of semantics concept and syntax concept in logistic system. Finally, the simulation results demonstrate that the model of the average number of disclosure strategy is 15.2 less than the traditional model in 20 negotiations. The successful rate of the negotiation is increased by 21.7% and the efficiency of the negotiation is increased by 3.6%.
Concerning the problem that finding community structure in complex network is very complex, a community discovery algorithm based on node similarity was proposed. The basic idea of this algorithm was that node pairs with higher similarity had more posibility to be grouped into the same community. Integrating local and global similarity, it constructed a similarity matrix which each element represents the similarity of a pair of nodes, then merged nodes which have the most similarity to the same community. The experimental results show that the proposed algorithm can get the correct community structure of networks, and achieve better performance than Label Propagation Algorithm (LPA), GN (Girvan-Newman) and CNM (Clauset-Newman-Moore) algorithms in community detection.
Concerning that the increasement of accumulated error causes serious distortion of Unmanned Aerial Vehicle (UAV) remote sensing images stitching, a projection error correction algorithm based on space intersection was proposed, Using space intersection theory, the spatial coordinates of 3D points were calculated according to correspondence points. Then all 3D points were orthographic projected onto the same space plane, and the orthographic points were projected onto the image plane to get corrected correspondence points, Finally, M-estimator Sample Consensus (MSAC) algorithm was used to estimate the homography matrix, then the stitching image was obtained. The simulation results show that this algorithm can effectively eliminate the projection error, thus achieve the purpose of inhibiting UAV remote sensing image stitching error.