Pulmonary nodules in Computerized Tomography (CT) images have large size variation as well as small and irregular size which leads to low detection sensitivity. In order to solve this problem, a method based on Feature Pyramid Network (FPN) was proposed. First, FPN was used to extract multi-scale features of nodules and strengthen the features of small objects and object boundary details. Second, a semantic segmentation network (named Mask FPN) was designed based on the FPN to segment and extract the pulmonary parenchyma quickly and accurately, and the pulmonary parenchyma area could be used as location map of object proposals. At the same time, a deconvolution layer was added on the top layer of FPN and a multi-scale prediction strategy was used to optimize the Faster Region Convolution Neural Network (R-CNN) in order to improve the performance of pulmonary nodule detection. Finally, to solve the problem of imbalance of positive and negative samples in the pulmonary nodule dataset, Focal Loss function was used in the Region Proposed Network (RPN) module in order to increase the detection rate of nodules. The proposed algorithm was tested on the public dataset LUNA16. Experimental results show that the improved network with FPN and deconvolution layer is helpful to the detection of pulmonary nodules, and focal loss function is also helpful to the detection. Combining with multiple improvements, when the average number of candidate nodules per scan was 46.7, the sensitivity of the presented method was 95.7%, which indicates that the method is more sensitive than the other convolutional networks such as Faster Region-Convolutional Neural Network (Faster R-CNN) and UNet. The proposed method can extract nodule features of different scales effectively and improve the detection sensitivity of pulmonary nodules in CT images. Meantime, the method can also detect small nodules effectively, which is beneficial to the diagnosis and treatment of lung cancer.

Aiming at the shortage of the airport gate resources and the disturbance caused by the actual flight arrival and departure time deviation from the planned time, a gate assignment scheduling method was proposed by adding buffer time between the adjacent flights in the same gate. Firstly, a robust gate assignment model with a goal to achieve minimum gate idle time and apron occupancy time was established. Then, a Lagrangian relaxation optimization algorithm based on double targets was designed, and the dual problem in the Lagrangian algorithm was solved by using the subgradient algorithm. Based on the operation data of a hub airport in China, the simulation results show that, compared with those of the original gate assignment scheme, the gate usage amount and the gate idle time of the proposed method is respectively reduced by 15.89% and 7.56%, the gate occupancy rate of the optimization scheme of proposed method is increased by 18.72% and the conflict rate is reduced to 3.57%, proving that the proposed method achieves the purpose of effectively improving the utilization and robustness of airport gates.

In order to solve the dynamic evaluation problem of cloud computing security, a method named interval-valued hesitant fuzzy grey compromise relation analysis for accurately evaluating the security of cloud computing was proposed. Firstly, a new interval-valued hesitant fuzzy distance formula was defined to measure the distance between two interval-valued hesitant fuzzy sets. Then, two new interval-valued hesitant fuzzy normalization formulas were constructed to solve the different dimensions of attributes. Meanwhile, the concept of grey compromise relation degree was put forward to consider all the expert opinions and solve the situation when the attributes have conflicts. On the basis of this, a new interval-valued hesitant fuzzy grey compromise relation analysis method was presented to evaluate the security of cloud computing. The analysis results show that the proposed method is feasible, and its scientific and effective characters are proved by comparing with the existed interval-valued hesitant fuzzy multiple attribute decision making literatures.

The moving object detection with moving camera has the problems that it is difficult to model the background and the computation cost is usually high. In order to solve the problems, a method for detecting moving object with moving camera based on motion saliency was proposed, which realized accurate moving object detection and avoided complex background modeling. The moving objects were detected according to the saliency of the video scene, which was computed based on the simulation of the attention mechanism in human vision system and the moving properties of background and foreground when the camera moved in translation. Firstly, the motion features of object were extracted by optical flow method and the background motion texture was suppressed by 2-D Gaussian convolution. Then the global saliency of motion features was measured by counting the histogram. According to the temporal salient map, the color information of foreground and background was extracted respectively. Finally, Bayesian model was used to deal with temporal salient map for extracting salient moving objects. The experimental results on the public video datasets show that the proposed method can suppress background motion noise, while detecting the moving object distinctly and accurately in the dynamic scene with moving camera.

Aiming at the problem that collaborative sparse image Compressive Sensing (CS) reconstruction based on fixed transform bases can not adequately exploit the self similarity of images, an improved reconstruction algorithm combining the Total Variation (TV) with adaptive low-rank regularization was proposed in this paper. Firstly, the similar patches were found by using image block matching method and formed into nonlocal similar patch groups. Then, the weighted low-rank approximation for nonlocal similar patch groups was adopted to replace the 3D wavelet transform filtering used in collaborative sparse representation. Finally, the regularization term of combining the gradient sparsity with low-rank prior of nonlocal similarity patch groups was embedded to reconstruction model, which is solved by Alternating Direction Multiplier Method (ADMM) to obtain the reconstructed image. The experimental results show that, in comparison with the Collaborative Sparse Recovery (RCoS) algorithm, the proposed method can increase the Peak Signal-to-Noise Ratio (PSNR) of reconstructed images about 2 dB on average, and significantly improve the quality of reconstructed image with keeping texture details better for nonlocal self-similar structure is precisely described.

The fairness of verifiable encrypted signature scheme is completely determined by the arbitrators neutral problem, which reduces the security of signature exchange. In order to deal with this issue, using the properties of bilinear pairings and combining with certificateless public key cryptography and verifiable encrypted signature, a blind verifiable encrypted signature was designed without certificate. The adjudicator in this scheme cannot restore the original signature directly, thereby the security of exchange signature protocols was enhanced. The proposed scheme was also provably secure in the random oracle module under Discrete Logarithm Problem (DLP) and Computational Differ-Hellman Problem (CDHP) assumption.

The system adopted artificial immune theory. Through analyzing the detection results of the traditional real-time intrusion detection system Snort, and according to the characteristic that antibody concentration dynamically changes with the network intrusion intensity, the current risk value of network was calculated to reflect all kinds of attacks and overall risk profile. Snort relies on the rule matching to detect data packets. The detection process does not take into account the current network risk, resulting in the problem of high false positives rate. This system set pass threshold and dropped threshold based on different degree of attack danger to reduce the false alarm rate of Snort, and took “pass, alarm, discard packet, etc.” as response measures according to the risk value. The experimental results show that the system can calculate the real-time risk faced by the host and network accurately, reduce the false positive rate and take response measures according to risk value effectively.

Combined Input-Crosspoint-Queued (CICQ) Crossbar outperforms traditional switch fabrics. In this paper, the features of CICQ switches were discussed and a new scheduling algorithm called Hybrid Optimization Packet Scheduling (HOPS) was proposed. This algorithm was based on a hybrid optimization method. The throughput of the algorithm was guaranteed in the first stage of input scheduling and the delay performance was improved by serving the longer queue in the second stage. HOPS was mainly based on Round-Robin (RR) mechanism and at most one comparison operation was done at input port, so it had a complexity of O(1) and easy to implement in hardware. With fluid model techniques, it was proved that HOPS algorithm can achieve 100% throughput for any admissible traffic without using speed-up. The simulation results show that HOPS algorithm exhibits favorable delay, throughput performance and stability under any admissible traffic.

The paper incorporated the multifractal analysis method into the idea of Quaternion Wavelet Transform (QWT), which took advantage of the rotation-invariant properties and multifractal properties of texture image, and could make up for the lacks of ability to decompose input image into multiple orientation in texture classification when using wavelet transform. The experiment of texture classification using the images from UIUC shows the method has higher classification accuracy and the average correct classification rate is 96.69%. It proves this texture classification method is reasonable and effective.