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.     

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.     

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...     

一种新型的无人机牧草分割网络—LMS-DeeplabV3+

目前草原环境复杂、牧草分散且与背景颜色差异小,无法实现高效精准的分割,因此本文提出了一种新型的轻量化多尺度DeeplabV3+网络(lightweight and multi-scale DeeplabV3+network, LMS-DeeplabV3+)。该网络以DeeplabV3+为基础网络,首先选用轻量级的MobilenetV2作为骨干网络用于初步特征提取,并为了适应牧草分割任务做了网络配置上的调整;其次在加强特征提取模块和解码模块中均使用深度可分离卷积代替普通卷积以轻量化网络;此外利用密集空洞空间金字塔池化(dense atrous spatial pyramid pooling, DASPP)模块捕获更大的感受野,加强各特征之间的交互;又引入卷积注意力机制(convolutional block attention module, CBAM)重分配权重加强特征提取。实验证明,提出的新网络与原始网络相比平均交并比(mean intersection over union,mIOU)提升了8.06个百分点、平均像素精度(mean pixel accuracy,mPA)提升了6.7...     

单A直和子空间

引入单直和子空间的概念,证明了线性空间可唯一分解为单直和子空间的直和,并且给出了计算方法.     

动态场景下基于视觉的SLAM技术研究

针对视觉同时定位与地图构建(SLAM)技术在动态环境中存在定位精度低、地图虚影等问题,提出了一种基于深度学习的动态SLAM算法。该算法利用网络参数少且目标识别率高的YOLOv8n改善系统的视觉前端,为视觉前端增加语义信息,提取动态区域特征点。然后采用LK光流法识别动态区域的动态特征点,剔除动态特征点并保留动态区域内的静态特征点,提高特征点利用率。此外,该算法通过增加地图构建线程,剔除YOLOv8n提取的动态物体点云,接收前端提取的语义信息,实现静态语义地图构建,消除由动态物体产生的虚影。实验结果显示,在动态环境下该算法与ORB-SLAM3相比,定位精度提升92.71%,与其他动态视觉SLAM算法相比,也有小幅度改善。     

科技博物馆公共空间利用初探

在科技博物馆界,利用公共空间进行展览教育活动已经成为一种发展趋势。本文在讨论科技博物馆公共空间的定义及功能的基础上,结合国内外实例归纳了依据空间结构编制情节和设立展示内容的方法。公共空间是人与环境、人与人在特定的环境中的交流场所,空间的情节决定了此种交流的内涵。编制公共空间的情节是科技博物馆公共空间设计的主要任务。本文认为有意义的主题、主题的展开方式、能够表达主题的展品、烘托主题的场景、情节或场景的顺序变化等五项元素是公共空间情节编制的主要内容。并据此总结了公共空间展示设计的基本思路和若干展示设计原则。     

基于红外辐射特性的单波段红外图像被动测距

以单波段红外图像被动测距为研究背景,首先分析了凝视型红外探测系统的工作原理,将其工作过程分为入瞳前和入瞳后两个不同的阶段,其中第一阶段与目标距离相关,而第二阶段则决定于红外探测系统本身的传递函数,而后对图像像素灰度与入瞳处辐亮度之间的关系进行了表述;然后针对点目标与面目标的成像特点,分别计算了相应的目标与背景的入瞳处幅亮度差,得出:两者的红外辐射特性存在一致性.基于短时间内目标近似匀速运动的假设,推导了单波段红外图像被动测距方法.最后利用外场实测中长波红外图像对该算法进行了验证,并对测距结果和测距误差进行了详细分析.