No abstract

AimDNA barcoding has been widely applied to species diversity assessment in various ecosystems, including temperate forests, subtropical forests, and tropical rain forests. However, tropical coral islands have never been barcoded before due to the difficulties in field exploring. This study aims at barcoding the flowering plants from a unique ecosystem of the tropical coral islands in the Pacific Ocean and supplying valuable evolutionary information for better understanding plant community assembly of those particular islands in the future.LocationXisha Islands, China.MethodsThis study built a DNA barcode database for 155 plant species from the Xisha Islands using three DNA markers (ITS, rbcL, and matK). We applied the sequence similarity method and a phylogenetic‐based method to assess the barcoding resolution.ResultsAll the three DNA barcodes showed high levels of PCR success (96%–99%) and sequencing success (98%–100%). ITS performed the highest rate of species resolution (>95%) among the three markers, while plastid markers delivered a relatively poor species resolution (85%–90%). Our analyses obtained a marginal increase in species resolution when combining the three DNA barcodes.Main conclusionsThis study provides the first plant DNA barcode data for the unique ecosystem of tropical coral islands and considerably supplements the DNA barcode library for the flowering plants on the oceanic islands. Based on the PCR and sequencing success rates, and the discriminatory power of the three DNA regions, we recommend ITS as the most successful DNA barcode to identify the flowering plants from Xisha Islands. Due to its high sequence variation and low fungal contamination, ITS could be a preferable candidate of DNA barcode for plants from other tropical coral islands as well. Our results also shed lights on the importance of biodiversity conservation of tropical coral islands.

Airborne radars are susceptible to a large number of clutter, noise and variable jamming signals in the real environment, especially when faced with active main lobe jamming, as the waveform shortcut technology in the traditional regime can no longer meet the actual battlefield radar anti-jamming requirements. Therefore, it is necessary to study anti-main-lobe jamming techniques for airborne radars in complex environments to improve their battlefield survivability. In this paper, we propose an airborne radar waveform design method based on a deep reinforcement learning (DRL) algorithm under clutter and jamming conditions, after previous research on reinforcement-learning (RL)-based airborne radar anti-jamming waveform design methods that have improved the anti-jamming performance of airborne radars. The method uses a Markov decision process (MDP) to describe the complex operating environment of airborne radars, calculates the value of the radar anti-jamming waveform strategy under various jamming states using deep neural networks and designs the optimal anti-jamming waveform strategy for airborne radars based on the duelling double deep Q network (D3QN) algorithm. In addition, the method uses an iterative transformation method (ITM) to generate the time domain signals of the optimal waveform strategy. Simulation results show that the airborne radar waveform designed based on the deep reinforcement learning algorithm proposed in this paper improves the signal-to-jamming plus noise ratio (SJNR) by 2.08 dB and 3.03 dB, and target detection probability by 26.79% and 44.25%, respectively, compared with the waveform designed based on the reinforcement learning algorithm and the conventional linear frequency modulation (LFM) signal at a radar transmit power of 5 W. The airborne radar waveform design method proposed in this paper helps airborne radars to enhance anti-jamming performance in complex environments while further improving target detection performance.

Datasets usually suffer from supervised information missing and weak generalization ability in deep convolution neural network. In this paper, pseudolabel (PL) of Weakly Supervised Learning (WSL) was used to address the problem of supervised information missing, while Cross Network (CN) of Multitask Learning (MTL) was used to solve the problem of weak generalization ability in deep convolution neural network. In PL, the data of supervised information missing was predicted; thus, PL of the corresponding data was generated. In CN, PL data and labeled data were taken as two tasks to train together. Firstly, the labeled data was divided into training dataset and testing dataset, respectively, and image preprocessing was carried out. Secondly, the network was initialized and trained, and the model with high accuracy and good generalization was selected as the optimal model. Then, the optimal model was used to predict the unlabeled data and generate PL. Finally, the steps above were repeated several times to find a better optimal model. In the experiments of the fusion model of PL and CN, Facial Beauty Prediction was regarded as main task and the others as auxiliary tasks. Experimental results show that the model was suitable for multitask training of different tasks in different or similar datasets, and the accuracy of the main task of Facial Beauty Prediction reaches 64.76%, higher than the highest accuracy by conventional methods.

No abstract