Search

For the recognition of armored targets in complex battlefield environments, how to reduce missed and false alarms while achieving real-time is an urgent issue. To this end, the GCD-YOLOv5 algorithm is innovatively proposed. Firstly, array lidar is used to acquire the armor target data. Secondly, the armor target data is expanded with an improved GAN(Generative Adversarial Network) to increase the diversity of training data. Afterward, the expanded dataset is fed into the GCD-YOLv5(You Only Look Once) for training. And the GCD-YOLOv5 is reflected in the following aspects. Firstly, the CBAM(Convolutional Block Attention Module) and the multi-scale feature fusion are added to improve the feature extraction capability and detection efficiency, increasing the recognition capability of small and obscured targets. Secondly, combining with DETR(Detection Transformer) to lighten YOLOv5 to achieve the real-time requirement. Thirdly, the YOLOv5 loss function and prediction box filtering method are improved to increase the detection accuracy and the confidence of the detection boxes. The experimental results show that the GCD-YOLOv5 algorithm has higher accuracy and real-time, the mAP(mean Average Precision) can reach 99.7%, and fps is 68.56% higher compared to YOLOv5, which significantly improves the recognition capability of armored targets in complex battlefield environments.

With the development of quantum technology, an arising researching point is to solve some new cipher problems with quantum technology to ensure their security. As we know, the sequential signature means to sign a contract or a document by many signers one by one. It has been widely used to realize layered authentication. In this paper, we propose a quantum sequential signature protocol with a set of strongly nonlocal orthogonal product (Y-SNOP) states. It is proved that the present protocol is secure, i.e., anyone cannot deny or forge a valid signature even some of them conspire. Compared with the existing quantum multi signature with some nonlocal orthogonal product (NOP) states, the present protocol seems more efficient and easier to be realized in Noisy Intermediate-Scale Quantum (NISQ) device as no entangled resources are required.

The noise suppression of high-resolution range profile (HRRP) is a prerequisite for Geiger-mode of avalanche photodiodes (GM-APD) lidar to achieve precise sensing. However, it is difficult to balance the suppression effect and the integrity of detailed information. Considering this problem, we propose a Bayesian network-based improved loop filter (BNILF) for abnormal noise suppression. Based on the ILF, the Bayesian non-average local filtering model is established to calculate a distance of Pearson distance, which gives the criterion of noise judgment. Furthermore, the block preselection is used to accelerate identify abnormal noise and complete range profile noise suppression. To evaluate the performance of this algorithm, simulation and physical system experiments are carried out. The results show that the proposed algorithm has a better noise suppression effect and a higher detailed information protection ability in comparison with the existing typical approaches.

Due to the unprecedentedly increasing demands of waterway transportation on the Yangtze River during the latest years, traffic congestion at the Three Gorges Dam (TGD) has becoming a serious problem. In busiest seasons, a vessel may need to wait up to 3 days for passing the TGD via the ship lift or the five-stage ship lock. In order to improve the navigation efficiency and the utilization of passing facilities, a co-scheduling problem of ship lift and ship lock at the TGD is modeled in this paper. Besides, the improvement on effectiveness, safety and fairness of the navigation scheduling by introducing the ship lift is taken into account. The mathematical model proposed is, by nature, a two-stage problem, where the first-stage variables determine the assignments of passing facilities and the second-stage variables schedule the vessels. In order to solve the proposed mathematical model, a hybrid metaheuristic algorithm is used at the first stage to determine the allocation of vessels to different passing facilities and to different lockage through the maximization of facility utilization rate. The second-stage problem is then solved by CPLEX. The proposed mathematical model and algorithm are validated through a set of numerical experiments and a case study. The results show both the navigation efficiency and the utilization of passing facilities can be improved by using the proposed methods.

In this paper, an interference detection algorithm based on fuzzy logic fusion is proposed for the interference monitoring system (IMS) of the global satellite navigation system (GNSS). In particular, for the problem of reduced detection performance caused by noise fluctuations in a complex electromagnetic environment, the proposed algorithm introduces the idea of fuzzy logic. According to the credibility of local detection results in different regions determined by noise uncertainty, we adopt a two-step cooperative detection mechanism in the fusion center (FC). When a definite detection result is obtained in the first step, the decision is finished. Otherwise, we will execute the decision algorithm based on the fuzzy logic fusion of the second step. The experimental results show that the proposed algorithm has the best detection performance, compared with the traditional energy detection algorithm and the energy detection algorithm based on soft data. Furthermore, compared with soft data, the system overhead of the proposed algorithm is also reduced without increasing the amount of calculation.

To improve the accuracy of user implicit rating prediction, we combine the traditional latent factor model (LFM) and bidirectional gated recurrent unit neural network (BiGRU) model to propose a hybrid model that deeply mines the latent semantics in the unstructured content of the text and generates a more accurate rating matrix. First, we utilize the user’s historical behavior (favorites records) to build a user rating matrix and decompose the matrix to obtain the latent factor vectors of users and literature. We also apply the BERT model for word embedding of the research papers to obtain the sequence of word vectors. Then, we apply the BiGRU with the user attention mechanism to mine the research paper textual content and to generate the new literature latent feature vectors that are used to replace the original literature latent factor vectors decomposed from the rating matrix. Finally, a new rating matrix is generated to obtain users’ ratings of noninteractive research papers and to generate the recommendation list according to the user latent factor vector. We design experiments on the real datasets and verify that the research paper recommendation model is superior to traditional recommendation models in terms of precision, recall, F1-value, coverage, popularity and diversity.

Human action recognition from skeleton sequences has attracted a lot of attention in the computer vision community. Long short term memory (LSTM) network has shown its promising performance for this problem, due to their strengths in modeling the dependencies and temporal dynamics of sequential data. However, original LSTM is difficult to grasp the dynamics of entire sequence data, if the input feature of each time step is just a simple combination of raw skeleton data. In this paper, we present a fusion model to make full use of the skeleton data through multi-stream LSTM for action recognition. In each stream of the model, skeleton feature fed to each step of LSTM are extracted from different time duration, which are called single frame feature, short term feature, and long term feature, respectively. Single frame feature represents static pose, which is converted from joints coordinates directly. Short term feature represents skeleton kinematics, which is extracted from a short time window. Long term feature represents joints mutuality during the action process, which is extracted from a longer time window. All these features are modeled by LSTM, and the final states of LSTM streams are fused to predict the underlying actions. The proposed model makes better use of the skeleton dynamics than standard LSTM model. Experimental results on two benchmark skeleton data sets NTU RGB+D data set and SBU interaction dataset show that our proposed approach achieved significant performance.