全光纤安防系统模式识别混合编程的实现

介绍了宽域全光纤监控预警系统及光纤扰动信号模式识别算法.利用小波包分解对信号进行分解与重构,并提取各频段内信号分量能量谱作为特征向量;应用综合考虑观测数据和确定性先验知识的BVC-RBF神经网络实现信号分类,提高了网络的泛化能力.利用Matlab引擎、动态链接库(DLL)、组件对象模型(COM)3种混合编程方法将Mat...     

交换环上辛代数和正交代数的抛物子代数的导子

设R是有1的交换环,L是R上的辛代数或正交代数,h是L的极大环面子代数,b是L中包含h的标准Borel子代数.在2∈R可逆的条件下,本文详细描述了b与L之间的中间李代数,并且证明这些中间李代数的导子都是内导子.     

基于稀疏栅格优化的蜂窝车联网定位算法

蜂窝车联网(cellular-V2X,C-V2X)中的定位方案是车路协同与车联网业务发展的重要技术途径之一.目前基于基站、卫星等诸多定位方案,在车联网业务以及车路协同场景中常会遇到定位精度、定位处理时延、部署成本等诸多方面的挑战.针对这些问题,文章对已有栅格定位算法进行优化,提出一种基于统计信息网格(statistic...     

基于YOLOv5s-FCS的钢材表面缺陷检测

针对传统钢材表面缺陷检测方法易出现误检、漏检和部分缺陷种类检测精度低等问题,本文设计了一种钢材表面缺陷网络YOLOv5s-FCS。首先本文引用了FReLU激活函数构建了卷积模块CBF,有效增强了网络的空间解析能力,优化了网络检测精度;其次,本文将坐标注意力机制嵌入到网络的neck部分来增强网络特征融合的能力,从而使网络能够提取更加丰富的特征信息;最后,将YOLOv5s的损失函数替换为SIoU loss,提高了预测框的回归精度。通过在NEU-DET数据集上进行消融实验、可视化对比实验,结果表明,YOLOv5s-FCS网络的mAP值达到了0.747,相较于原YOLOv5s网络提高了8.3%,相较于YOLOv3网络提高了11.8%,相较于YOLOXs网络提高了4.2%,相较于YOLOv6s提高了1.4%,验证了该方法的可行性、有效性。     

知识牵引与数据驱动的兵棋AI设计及关键技术

在分析知识推理型与数据学习型兵棋人工智能(artifical intelligence, AI)优缺点的基础上, 提出了基于知识牵引与数据驱动的AI设计框架。针对框架中涉及的基于数据补全的战场态势感知,基于遗传模糊系统的关键点推理,基于层次任务网的任务规划、计划修复与重规划,基于深度强化学习的算子动作策略优化等关键技术进行深入探讨。结果表明,所提框架具有较强的适应性, 不仅能够满足分队、群队、人机混合等兵棋推演的应用需求, 而且适用于解决一般回合制或即时策略性的博弈对抗问题。     

The industrial asymmetry of the stock price prediction with investor sentiment: Based on the comparison of predictive effects with SVR

As a representative emerging financial market, the Chinese stock market is more prone to volatility because of investor sentiment. It is reasonable to use efficient predictive methods to analyze the influence of investor sentiment on stock price forecasting. This paper conducts a comparative study about the predictive performance of artificial neural network, support vector regression (SVR) and autoregressive integrated moving average and selects SVR to study the asymmetry effect of investor sentiment on different industry index predictions. After studying the relevant financial indicators, the results divide the Shenwan first-class industries into two types and show that the industries affected by investor sentiment are composed of young companies with high growth and high operative pressure and there are a great number of investment bubbles in those companies.     

Maize HapMap2 identifies extant variation from a genome in flux

Whereas breeders have exploited diversity in maize for yield improvements, there has been limited progress in using beneficial alleles in undomesticated varieties. Characterizing standing variation in this complex genome has been challenging, with only a small fraction of it described to date. Using a population genetics scoring model, we identified 55 million SNPs in 103 lines across pre-domestication and domesticated Zea mays varieties, including a representative from the sister genus Tripsacum. We find that structural variations are pervasive in the Z. mays genome and are enriched at loci associated with important traits. By investigating the drivers of genome size variation, we find that the larger Tripsacum genome can be explained by transposable element abundance rather than an allopolyploid origin. In contrast, intraspecies genome size variation seems to be controlled by chromosomal knob content. There is tremendous overlap in key gene content in maize and Tripsacum, suggesting that adaptations from Tripsacum (for example, perennialism and frost and drought tolerance) can likely be integrated into maize.     

一种快速高效二维时域有限元束传播法

提出并建立了一种新型的快速分析平面光波光路器件传输特性的2D时域有限元束传播法(FE-TD-BPM)模型.与常规时域差分格式的有限元束传播法相比,在时域实现了一维有限元(FEM)离散化处理,基于完全匹配层(PML)边界条件给出了全有限元离散化模型.为了验证算法的精度以及速度,模拟分析了直脊波导以及波导光栅,并且与已有文献的计算结果进行比较,结果表明,该算法无条件稳定、计算速度快,与常规时域差分格式的有限元束传播法相差在0.002%以内,并节省了约70%的机时.