National University of Defense Technology

About: National University of Defense Technology is a education organization based out in Changsha, China. It is known for research contribution in the topics: Radar & Synthetic aperture radar. The organization has 39430 authors who have published 40181 publications receiving 358979 citations. The organization is also known as: Guófáng Kēxuéjìshù Dàxué & NUDT.

Star Graph Neural Networks for Session-based Recommendation

Abstract: Session-based recommendation is a challenging task. Without access to a user's historical user-item interactions, the information available in an ongoing session may be very limited. Previous work on session-based recommendation has considered sequences of items that users have interacted with sequentially. Such item sequences may not fully capture complex transition relationship between items that go beyond inspection order. Thus graph neural network (GNN) based models have been proposed to capture the transition relationship between items. However, GNNs typically propagate information from adjacent items only, thus neglecting information from items without direct connections. Importantly, GNN-based approaches often face serious overfitting problems. We propose Star Graph Neural Networks with Highway Networks (SGNN-HN) for session-based recommendation. The proposed SGNN-HN applies a star graph neural network (SGNN) to model the complex transition relationship between items in an ongoing session. To avoid overfitting, we employ highway networks (HN) to adaptively select embeddings from item representations. Finally, we aggregate the item embeddings generated by the SGNN in an ongoing session to represent a user's final preference for item prediction. Experiments on two public benchmark datasets show that SGNN-HN can outperform state-of-the-art models in terms of P@20 and MRR@20 for session-based recommendation.

Progress in research on mixing techniques for transverse injection flow fields in supersonic crossflows

Abstract: The transverse injection flow field has an important impact on the flowpath design of scramjet engines. At present a combination of the transverse injection scheme and any other flame holder has been widely employed in hypersonic propulsion systems to promote the mixing process between the fuel and the supersonic freestream; combustion efficiency has been improved thereby, as well as engine thrust. Research on mixing techniques for the transverse injection flow field is summarized from four aspects, namely the jet-to-crossflow pressure ratio, the geometric configuration of the injection port, the number of injection ports, and the injection angle. In conclusion, urgent investigations of mixing techniques of the transverse injection flow field are proposed, especially data mining in the quantitative analytical results for transverse injection flow field, based on results from multi-objective design optimization theory.

Learning Deep Ship Detector in SAR Images From Scratch

Abstract: Recently, deep learning-based methods have brought new ideas for ship detection in synthetic aperture radar (SAR) images. However, several challenges still exist: 1) deep models contain millions of parameters, whereas the available annotated samples are not sufficient in number for training. Therefore, most deep detectors have to fine-tune networks pre-trained on ImageNet, which incurs learning bias due to the huge domain mismatch between SAR images and ImageNet images. Furthermore, it has a little flexibility to redesign the network structure; and 2) ships in SAR images are relatively small in size and densely clustered, whereas most deep detectors have poor performance with small objects due to the rough feature map used for detection and the extreme foreground–background imbalance. To address these problems, this paper proposes an effective approach to learn deep ship detector from scratch. First, we design a condensed backbone network, which consists of several dense blocks. Hence, earlier layers can receive additional supervision from the objective function through the dense connections, which makes it easy to train. In addition, feature reuse strategy is adopted to make it highly parameter efficient. Therefore, the backbone network could be freely designed and effectively trained from scratch without using a large amount of annotated samples. Second, we improve the cross-entropy loss to address the foreground–background imbalance and predict multi-scale ship proposals from several intermediate layers to improve the recall rate. Then, position-sensitive score maps are adopted to encode position information into each ship proposal for discrimination. The comparison results on the Sentinel-1 data set show that: 1) learning ship detector from scratch achieved better performance than ImageNet pre-trained model-based detectors and 2) our method is more effective than existing algorithms for detecting the small and densely clustered ships.

Lightweight and Efficient Microwave-Absorbing Materials Based on Loofah-Sponge-Derived Hierarchically Porous Carbons

Abstract: Lightweight, low-cost, and effective microwave-absorbing materials are important in electronics, communication, and military defense. Recently, microwave-absorbing materials stemming from biomass have drawn increasing attention for their sustainable properties, low cost, and high performances. In this work, loofah-sponge-derived carbon/CoFe2O4 composites have been prepared by functionalization and subsequent pyrolysis treatment. The porous composites prepared from the loofah sponge exhibit a typical lotus-root-like structure with low density. The composites exhibit an efficient absorption value of −43.8 dB at 8.3 GHz (X band) with a thickness of 3 mm. The high-performance absorption is ascribed to the synergistic attenuation effect of magnetic nanoparticles and dielectric lotus-root-like carbon substrate. The obtained results demonstrated that the loofah-sponge-derived carbon/CoFe2O4 composites with lotus-root-like microstructure have great potential to be lightweight and low-cost microwave-absorbing mate...