Search

To investigate the impact of the filament winding angle of glass-fiber reinforced plastic (GFRP) on the seismic behavior of GFRP tube ultra-high performance concrete (UHPC) composite columns, this study designs two types of GFRP tube UHPC composite columns. Quasi-static tests are conducted on the specimens subjected to horizontal reciprocating load and axial force, and the skeleton curve characteristics of the structure are analyzed. Furthermore, a finite element analysis model of the composite column is established to explore the effects of the diameter-thickness ratio, circumferential elastic modulus of confined tubes, and tensile strength of concrete on the seismic performance of the composite column. The analysis includes a review of the skeleton curve, energy dissipation capacity, and stiffness degradation of the structure under different designs. The results indicate that the use of GFRP tubes effectively enhances the seismic performance of UHPC columns. The failure mode, peak load, and peak displacement of the composite columns are improved. The finite element analysis results are in good agreement with the experimental results, validating the effectiveness of the analysis model. Extended analysis reveals that the bearing capacity of the specimen increases while the energy dissipation capacity decreases with a decrease in the diameter-thickness ratio and an increase in the circumferential elastic modulus. Although the tensile strength of concrete has some influence on the seismic performance of the specimen, its effect is relatively small. Through regression analysis, a formula for shear capacity suitable for GFRP tube UHPC composite columns is proposed. This formula provides a theoretical reference for the design and engineering practice of GFRP tube UHPC composite columns. [ABSTRACT FROM AUTHOR]

• The combined use of NDVI MEAN and NDVI SD significantly improved the predictive ability for plant species diversity than NDVI MEAN alone. • Previous study had underestimated the potential of predicting plant species diversity based on NDVI-related indices. • Hill numbers showed its high capacity in spectral-species diversity research. The development of near-Earth remote sensing platforms, such as unmanned aerial vehicles (UAV), have provided new opportunities for wetland plant diversity monitoring. Most previous studies on the relationship between spectral and species diversity have focused on the development and use of spectral indices. However, commonly used species diversity indices may not be the best choice for spectral-species diversity research. In this paper, high spatial resolution multispectral images of freshwater marsh were obtained based on UAV in Sanjiang National Nature Reserve, Northeast China, and the commonly used species diversity indices (Richness, Shannon, and Gini-Simpson) and Hill numbers were calculated based on 135 quadrats information obtained from field surveys. The mean value of NDVI (NDVI MEAN), its standard deviation (NDVI SD) and coefficient of variation (NDVI CV) of each quadrat were calculated based on multispectral imagery as a proxy for the spectral indices of the quadrats. The univariate and multivariate linear models were employed to test the predictive ability of NDVI-related indices for commonly used species diversity indices and Hill numbers. The results showed that the predictive ability of NDVI MEAN for species diversity indices was limited, and the combined use of NDVI MEAN and NDVI SD significantly improved the predictive ability of species diversity. The predictive ability of NDVI-related indices to Hill numbers is better than that of commonly used species diversity indices. Commonly used species diversity indices can only represent one or several "point" of the community species diversity, the Hill numbers provide a continuous measure of community species diversity, which can balance the inconsistency between the abundance and coverage of species in the community. Previous spectral-species diversity studies might not have shown the real predictive ability of species diversity based on NDVI-related indices. Our study provides innovative ideas for the selection of species diversity indices in future spectral-species diversity studies. [ABSTRACT FROM AUTHOR]

Deep learning methods have significantly improved object detection performance, but small object detection remains an extremely difficult and challenging task in computer vision. We propose a feature fusion and spatial attention-based single shot detector (FASSD) for small object detection. We fuse high-level semantic information into shallow layers to generate discriminative feature representations for small objects. To adaptively enhance the expression of small object areas and suppress the feature response of background regions, the spatial attention block learns a self-attention mask to enhance the original feature maps. We also establish a small object dataset (LAKE-BOAT) of a scene with a boat on a lake and tested our algorithm to evaluate its performance. The results show that our FASSD achieves 79.3% mAP (mean average precision) on the PASCAL VOC2007 test with input 300 × 300, which outperforms the original single shot multibox detector (SSD) by 1.6 points, as well as most improved algorithms based on SSD. The corresponding detection speed was 45.3 FPS (frame per second) on the VOC2007 test using a single NVIDIA TITAN RTX GPU. The test results of a simplified FASSD on the LAKE-BOAT dataset indicate that our model achieved an improvement of 3.5% mAP on the baseline network while maintaining a real-time detection speed (64.4 FPS). [ABSTRACT FROM AUTHOR]

With the rapid development of information technology and the increasing application of UAV in various fields, the security problems of unmanned aerial vehicle (UAV) communication network have become increasingly prominent. It has become an important scientific challenge to design a routing protocol that can provide efficient and reliable node to node packet transmission. In this paper, an efficient Digital Signature algorithm based on the elliptic curve cryptosystem is applied to routing protocol, and an improved security method suitable for on-demand routing protocol is proposed. The UAV communication network was simulated through the NS2 simulation platform, and the execution efficiency and safety of the improved routing protocol were analyzed. In the simulation experiment, the routing protocols of ad-hoc on demand distance vector (AODV), security ad-hoc on demand distance vector (SAODV), and improved security ad-hoc on demand distance vector (ISAODV) are compared in terms of the performance indicators of packet delivery rate, throughput, and end-to-end delay under normal conditions and when attacked by malicious nodes. The simulation results show that the improved routing protocol can effectively improve the security of the UAV communication network. [ABSTRACT FROM AUTHOR]

In this paper, a blind modulation classification method based on compressed sensing using a high-order cumulant and cyclic spectrum combined with the decision tree–support vector machine classifier is proposed to solve the problem of low identification accuracy under single-feature parameters and reduce the performance requirements of the sampling system. Through calculating the fourth-order, eighth-order cumulant and cyclic spectrum feature parameters by breaking through the traditional Nyquist sampling law in the compressed sensing framework, six different cognitive radio signals are effectively classified. Moreover, the influences of symbol length and compression ratio on the classification accuracy are simulated and the classification performance is improved, which achieves the purpose of identifying more signals when fewer feature parameters are used. The results indicate that accurate and effective modulation classification can be achieved, which provides the theoretical basis and technical accumulation for the field of optical-fiber signal detection. [ABSTRACT FROM AUTHOR]

With the rapid development of information technology, the problem of the network security of unmanned aerial vehicles (UAVs) has become increasingly prominent. In order to solve the intrusion detection problem of massive, high-dimensional, and nonlinear data, this paper proposes an intrusion detection method based on the deep belief network (DBN) optimized by particle swarm optimization (PSO). First, a classification model based on the DBN is constructed, and the PSO algorithm is then used to optimize the number of hidden layer nodes of the DBN, to obtain the optimal DBN structure. The simulations are conducted on a benchmark intrusion dataset, and the results show that the accuracy of the DBN-PSO algorithm reaches 92.44%, which is higher than those of the support vector machine (SVM), artificial neural network (ANN), deep neural network (DNN), and Adaboost. It can be seen from comparative experiments that the optimization effect of PSO is better than those of the genetic algorithm, simulated annealing algorithm, and Bayesian optimization algorithm. The method of PSO-DBN provides an effective solution to the problem of intrusion detection of UAV networks. [ABSTRACT FROM AUTHOR]

A novel technique is proposed to implement optical signal-to-noise ratio (OSNR) estimation by using an improved binary particle swarm optimization (IBPSO) and deep neural network (DNN) based on amplitude histograms (AHs) of signals obtained after constant modulus algorithm (CMA) equalization in an optical coherent system. For existing OSNR estimation models of DNN and AHs, sparse AHs with valid features of original data are selected by IBPSO algorithm to replace the original, and the sparse sets are used as input vector to train and test the particle swarm optimization (PSO) optimized DNN (PSO-DNN) network structure. Numerical simulations have been carried out in the OSNR ranges from 10 dB to 30 dB for 112 Gbps PM-RZ-QPSK and 112 Gbps PM-NRZ-16QAM signals, and results show that the proposed algorithm achieves a high OSNR estimation accuracy with the maximum estimation error is less than 0.5 dB. In addition, the simulation results with different data input into the deep neural network structure show that the mean OSNR estimation error is 0.29 dB and 0.39 dB under original data and 0.29 dB and 0.37 dB under sparse data for the two signals, respectively. In the future dynamic optical network, it is of more practical significance to reconstruct the original signal and analyze the data using sparse observation information in the face of multiple impairment and serious interference. The proposed technique has the potential to be applied for optical performance monitoring (OPM) and is helpful for better management of optical networks. [ABSTRACT FROM AUTHOR]

With the wide application of wireless sensor networks in military and environmental monitoring, security issues have become increasingly prominent. Data exchanged over wireless sensor networks is vulnerable to malicious attacks due to the lack of physical defense equipment. Therefore, corresponding schemes of intrusion detection are urgently needed to defend against such attacks. Considering the serious class imbalance of the intrusion dataset, this paper proposes a method of using the synthetic minority oversampling technique (SMOTE) to balance the dataset and then uses the random forest algorithm to train the classifier for intrusion detection. The simulations are conducted on a benchmark intrusion dataset, and the accuracy of the random forest algorithm has reached 92.39%, which is higher than other comparison algorithms. After oversampling the minority samples, the accuracy of the random forest combined with the SMOTE has increased to 92.57%. This shows that the proposed algorithm provides an effective solution to solve the problem of class imbalance and improves the performance of intrusion detection. [ABSTRACT FROM AUTHOR]