金属腔量子阱红外探测器共振波长的角度依赖性

测量了金属腔量子阱红外探测器在斜入射条件下的光电流谱,斜入射条件分为入射面垂直于器件长轴和平行于器件长轴两种情形.从实验和理论上研究了金属腔共振模对入射角度的依赖性.实验结果表明:入射面垂直于器件长轴时,腔模共振波长不随入射角度变化;入射面平行于器件长轴时,腔模共振波长随入射角度变大而向短波移动.测试结果和推导出的共振...     

Quantum Information Entropies on Hyperbolic Single Potential Wells

In this work, we study the quantum information entropies for two different types of hyperbolic single potential wells. We first study the behaviors of the moving particle subject to two different hyperbolic potential wells through focusing on their wave functions. The shapes of these hyperbolic potentials are similar, but we notice that their momentum entropy densities change along with the width of each potential and the magnitude of position entropy density decreases when the momentum entropy magnitude increases. On the other hand, we illustrate the behaviors of their position and momentum entropy densities. Finally, we show the variation of position and momentum entropies Sx and Sp with the change of the potential well depth u and verify that their sum still satisfies the BBM inequality relation.     

Computer-Aided Detection of Quantitative Signatures for Breast Fibroepithelial Tumors Using Label-Free Multi-Photon Imaging

Fibroadenomas (FAs) and phyllodes tumors (PTs) are major benign breast tumors, pathologically classified as fibroepithelial tumors. Although the clinical management of PTs differs from FAs, distinction by core needle biopsy diagnoses is still challenging. Here, a combined technique of label-free imaging with multi-photon microscopy and artificial intelligence was applied to detect quantitative signatures that differentiate fibroepithelial lesions. Multi-photon excited autofluorescence and second harmonic generation (SHG) signals were detected in tissue sections. A pixel-wise semantic segmentation method using a deep learning framework was used to separate epithelial and stromal regions automatically. The epithelial to stromal area ratio and the collagen SHG signal strength were investigated for their ability to distinguish fibroepithelial lesions. An image segmentation analysis with a pixel-wise semantic segmentation framework using a deep convolutional neural network showed the accurate separation of epithelial and stromal regions. A further investigation, to determine if scoring the epithelial to stromal area ratio and the SHG signal strength within the stromal area could be a marker for differentiating fibroepithelial tumors, showed accurate classification. Therefore, molecular and morphological changes, detected through the assistance of computational and label-free multi-photon imaging techniques, enable us to propose quantitative signatures for epithelial and stromal alterations in breast tissues.     

Space-Air-Ground Integrated Mobile Crowdsensing for Partially Observable Data Collection by Multi-Scale Convolutional Graph Reinforcement Learning

Mobile crowdsensing (MCS) is attracting considerable attention in the past few years as a new paradigm for large-scale information sensing. Unmanned aerial vehicles (UAVs) have played a significant role in MCS tasks and served as crucial nodes in the newly-proposed space-air-ground integrated network (SAGIN). In this paper, we incorporate SAGIN into MCS task and present a Space-Air-Ground integrated Mobile CrowdSensing (SAG-MCS) problem. Based on multi-source observations from embedded sensors and satellites, an aerial UAV swarm is required to carry out energy-efficient data collection and recharging tasks. Up to date, few studies have explored such multi-task MCS problem with the cooperation of UAV swarm and satellites. To address this multi-agent problem, we propose a novel deep reinforcement learning (DRL) based method called Multi-Scale Soft Deep Recurrent Graph Network (ms-SDRGN). Our ms-SDRGN approach incorporates a multi-scale convolutional encoder to process multi-source raw observations for better feature exploitation. We also use a graph attention mechanism to model inter-UAV communications and aggregate extra neighboring information, and utilize a gated recurrent unit for long-term performance. In addition, a stochastic policy can be learned through a maximum-entropy method with an adjustable temperature parameter. Specifically, we design a heuristic reward function to encourage the agents to achieve global cooperation under partial observability. We train the model to convergence and conduct a series of case studies. Evaluation results show statistical significance and that ms-SDRGN outperforms three state-of-the-art DRL baselines in SAG-MCS. Compared with the best-performing baseline, ms-SDRGN improves 29.0% reward and 3.8% CFE score. We also investigate the scalability and robustness of ms-SDRGN towards DRL environments with diverse observation scales or demanding communication conditions.     

Synthesis of PNIPAAm-g-P4VP Microgel as Draw Agent in Forward Osmosis by RAFT Polymerization and Reverse Suspension Polymerization to Improve Water Flux

Microgels have unique and versatile properties allowing their use in forward osmosis areas as a draw agent. In this contribution, poly(4-vinylpyridine) (P4VP) was synthesized via RAFT polymerization and then grafted to a poly(N-Isopropylacrylamide) (PNIPAAm) crosslinking network by reverse suspension polymerization. P4VP was successfully obtained by the quasiliving polymerization with the result of nuclear magnetic resonance and gel permeation chromatography characterization. The particle size and particle size distribution of the PNIPAAm-g-P4VP microgels containing 0, 5, 10, 15 and 20 wt% P4VP were measured by means of a laser particle size analyzer. It was found that all the microgels were of micrometer scale and the particle size was increased with the P4VP load. Inter/intra-molecular-specific interactions, i.e., hydrogen bond interactions were then investigated by Fourier infrared spectroscopy. In addition, the water flux measurements showed that all the PNIPAAm-g-P4VP microgels can draw water more effectively than a blank PNIPAAm microgel. For the copolymer microgel incorporating 20 wt% P4VP, the water flux was measured to be 7.48 L∙m⁻²∙h⁻¹.     

Optimal Energy-Storage Configuration for Microgrids Based on SOH Estimation and Deep Q-Network

Energy storage is an important adjustment method to improve the economy and reliability of a power system. Due to the complexity of the coupling relationship of elements such as the power source, load, and energy storage in the microgrid, there are problems of insufficient performance in terms of economic operation and efficient dispatching. In view of this, this paper proposes an energy storage configuration optimization model based on reinforcement learning and battery state of health assessment. Firstly, a quantitative assessment of battery health life loss based on deep learning was performed. Secondly, on the basis of considering comprehensive energy complementarity, a two-layer optimal configuration model was designed to optimize the capacity configuration and dispatch operation. Finally, the feasibility of the proposed method in microgrid energy storage planning and operation was verified by experimentation. By integrating reinforcement learning and traditional optimization methods, the proposed method did not rely on the accurate prediction of the power supply and load and can make decisions based only on the real-time information of the microgrid. In this paper, the advantages and disadvantages of the proposed method and existing methods were analyzed, and the results show that the proposed method can effectively improve the performance of dynamic planning for energy storage in microgrids.     

网络多层语义深度挖掘及流媒体缓存策略研究

对网络音视频数据进行多层次语义的深度挖掘,统计分析用户行为,建立一个流行度预测模型,在此基础上提出智能化的代理缓存替换策略.初步模拟实验表明该策略能提高缓存字节命中率,减短客户端的请求延迟时间.     

基于知识蒸馏与改进ViT网络的花卉图像细粒度分类

由于自然条件下拍摄的花卉图像背景复杂,而且其存在类内差异性大和类间相似性高的问题,现有主流方法仅依靠卷积模块提取花卉的局部特征难以实现准确的细粒度分类。针对上述问题,本文提出了1种高精度、轻量化的花卉分类方法(ConvTrans-ResMLP),通过结合Transformer模块和残差MLP(multi-layer perceptron)模块实现对花卉图像的全局特征提取,并在Transformer模块中加入卷积计算使得模型仍保留提取局部特征的能力;同时,为了进一步将花卉分类模型部署到边缘设备中,本研究基于知识蒸馏技术实现对模型的压缩与优化。实验结果表明,本文所提出的方法在Oxford 17、Oxford 102和自制的Flowers 32数据集上的准确率分别达98.62%、97.61%和98.40%;知识蒸馏后本文的轻量化模型的大小约为原来的1/18,而准确率仅下降2%左右。因此,本研究能较好地提升边缘设备下花卉细粒度分类的效率,对促进花卉培育的自动化发展具有切实意义。     

基于LSDANet的手机芯片屏蔽壳表面缺陷检测方法

为了解决手机芯片屏蔽壳表面白印缺陷微小、尺度各异等因素影响检测快速性和准确性的问题,本文提出一种基于长短连接通路和双注意力网络(long short link and double attention network, LSDANet)的手机芯片屏蔽壳表面缺陷检测方法。首先,通过构建基于编码和解码的语义分割模型和利用长短距离连接通路,提高网络模型对尺度各异缺陷的特征提取能力。其次,分别设计基于通道和空间的注意力机制,增大5—10 pixel尺寸的白印缺陷在空间和通道上的特征权重。最后,融合双注意力机制和长短距离连接通路分割模型,构建LSDANet缺陷检测网络,应用于手机芯片屏蔽壳表面缺陷检测。实验数据表明,LSDANet网络能够达到96.21%的平均像素精度、66.13%的平均交并比和39.03的每秒检测帧数,相比多种语义分割算法均具有更高的检测精度和速度。     

融合注意力线性特征多样化的DR分级模型

糖尿病视网膜病变(diabetic retinopathy, DR)是目前人类的主要致盲疾病之一。针对DR数据集中样本类间差异小和类分布不均衡等制约分级性能提高的问题,本文提出一种融合注意力线性特征多样化(fusion of attention linear feature diversification, FALFD)的分级算法。该算法首先用改进的Res2Net残差网络作为模型骨干来增大感受野,进一步提高网络捕捉特征信息的能力;其次引入自适应特征多样化模块(adaptive feature diversification module, AFDM)对眼底图像可分辨的微小病理特征进行识别,获得具有高语义信息的局部特征,避免单一特征区域的限制,进而提高分级准确度;再后利用双线性注意力融合模块(bilinear attention fusion module, BAFM)增加可判别区域特征的网络权重占比;最后采用正则化焦点损失(focal loss, FL)进一步提升算法的分类性能。在IDRID数据集上,灵敏度和特异性分别为94.20%和97.05%,二次加权系数为87.83%;在APTO...