Hermite-Shannon-Cosine区间小波及其在图形自适应分划插值中的应用

动态曲线图是描述客观现象变换规律的常用工具,为实现动态曲线特征点的动态捕捉及精确表达,构造了同时具有插值性、光滑性、紧支撑性和对称性的Shannon-Cosine小波函数.首先利用Shannon小波函数的波动性和连续性,根据积分中值定理,设计了一种参数化的窗函数,通过参数调整,可满足Shannon-Cosine小波对支撑区间和光滑度的自适应控制的要求;其次,分析确定了对曲线进行小波变换时边界效应归因于曲线边界的不连续,因此,采用2点3次Hermite插值函数构建了区间小波;最后,采用多尺度Shannon-Cosine小波对冲击波传播曲线和反射Burger曲线进行多尺度自适应细分和逼近,自动捕捉曲线的特征点进行重构.实例结果表明,与其他方法相比,Hermite Shannon-Cosine区间小波逼近曲线具有较高的数值精度和较低的算法复杂度.     

改进U-Net型网络的遥感图像道路提取

目的 遥感图像道路提取在城市规划、交通管理、车辆导航和地图更新等领域中发挥了重要作用,但遥感图像受光照、噪声和遮挡等因素以及识别过程中大量相似的非道路目标干扰,导致提取高质量的遥感图像道路有很大难度。为此,提出一种结合上下文信息和注意力机制的U-Net型道路分割网络。方法 使用Resnet-34预训练网络作为编码器实现特征提取,通过上下文信息提取模块对图像的上下文信息进行整合,确保对道路的几何拓扑结构特征的提取;使用注意力机制对跳跃连接传递的特征进行权重调整,提升网络对于道路边缘区域的分割效果。结果 在公共数据集Deep Globe道路提取数据集上对模型进行测试,召回率和交并比指标分别达到0.847 2和0.691 5。与主流方法U-Net和CE-Net（context encoder network）等进行比较,实验结果表明本文方法在性能上表现良好,能有效提高道路分割的精确度。结论 本文针对遥感图像道路提取中道路结构不完整和道路边缘区域不清晰问题,提出一种结合上下文信息和注意力机制的遥感道路提取模型。实验结果表明该网络在遥感图像道路提取上达到良好效果,具有较高的研究和应用价值。     

自适应多模态特征融合胶质瘤分级网络

目的 胶质瘤的准确分级是辅助制定个性化治疗方案的主要手段,但现有研究大多数集中在基于肿瘤区域的分级预测上,需要事先勾画感兴趣区域,无法满足临床智能辅助诊断的实时性需求。因此,本文提出一种自适应多模态特征融合网络（adaptive multi-modal fusion net,AMMFNet）,在不需要勾画肿瘤区域的情况下,实现原始采集图像到胶质瘤级别的端到端准确预测。方法 AMMFNet方法采用4个同构异义网络分支提取不同模态的多尺度图像特征;利用自适应多模态特征融合模块和降维模块进行特征融合;结合交叉熵分类损失和特征嵌入损失提高胶质瘤的分类精度。为了验证模型性能,本文采用MICCAI （Medical Image Computing and Computer Assisted Intervention Society）2018公开数据集进行训练和测试,与前沿深度学习模型和最新的胶质瘤分类模型进行对比,并采用精度以及受试者曲线下面积（area under curve,AUC）等指标进行定量分析。结果 在无需勾画肿瘤区域的情况下,本文模型预测胶质瘤分级的AUC为0.965;在使用肿瘤区域时,其AUC高达0.997,精度为0.982,比目前最好的胶质瘤分类模型——多任务卷积神经网络同比提高1.2%。结论 本文提出的自适应多模态特征融合网络,通过结合多模态、多语义级别特征,可以在未勾画肿瘤区域的前提下,准确地实现胶质瘤分级预测。     

A multi-view attention-based deep learning system for online deviant content detection

With the exponential growth of user-generated content, policies and guidelines are not always enforced in social media, resulting in the prevalence of deviant content violating policies and guidelines. The adverse effects of deviant content are devastating and far-reaching. However, the detection of deviant content from sparse and imbalanced textual data is challenging, as a large number of stakeholders are involved with different stands and the subtle linguistic cues are highly dependent on complex context. To address this problem, we propose a multi-view attention-based deep learning system, which combines random subspace and binary particle swarm optimization (RS-BPSO) to distill content of interest (candidates) from imbalanced data, and applies the context and view attention mechanisms in convolutional neural network (dubbed as SSCNN) for the extraction of structural and semantic features. We evaluate the proposed approach on a large-scale dataset collected from Facebook, and find that RS-BPSO is able to detect whether the content is associated with marijuana with an accuracy of 87.55%, and SSCNN outperforms baselines with an accuracy of 94.50%.

     

Guaranteeing performance for uncertain nonlinear systems with bounded state constraint and mismatching condition

The control design problem for the uncertain nonlinear system with bounded state constraint and mismatching condition is considered in this paper. The uncertainty in the system, which may be due to unknown system parameters and external disturbance, is nonlinear and time‐varying. The state of the system is constrained to be bounded. The system does not satisfy the (global) matching condition. A creative one‐to‐one state transformation is proposed by converting the bounded states into the unbounded ones. A step‐by‐step state transformation is proposed to convert the mismatched system into a matched system. The robust control is then proposed based on the transformed system. The control is demonstrated to be able to guarantee the uniform boundedness and uniform ultimate boundedness of the system in the presence of uncertainty, while the state constraint can be always guaranteed.     

Fixed‐time synchronization for complex‐valued BAM neural networks with time delays

In this paper, the fixed‐time synchronization for complex‐valued bidirectional associative memory (BAM) neural networks with time delays is studied. Based on the fixed‐time stability, the Lyapunov functional method and some inequality techniques, a new criterion is presented to guarantee that the addressed systems achieve synchronization in fixed time and a more accurate estimation independent of the initial conditions is given for the settling time. Meanwhile, a new nonlinear delayed controller different from the existing ones is designed. In the end, two numerical examples are provided to illustrate the effectiveness of the obtained result.     

结合注意力机制与BIM特征的电力能耗预测

能耗预测中引入外因序列有助于目标序列的预测,但在实际应用中各个外因序列与目标序列之间的相关程度往往不清晰,导致无法有效利用多外因序列辅助预测.针对该问题,提出一种结合注意力机制与BIM特征的电力能耗预测模型——BIMAttenNN(BIM Attention Nerual Network).通过结合注意力机制与BIM特征对外因序列自动选取并重构,将重构特征通过编码器-解码器结构的深度神经网络和线性回归分支准确预测未来电力能耗.实验结果表明,BIMAttenNN能够结合BIM特征自动捕捉电力序列间关系,与传统方法相比具有更高的预测精度.     

基于双向生成对抗网络的图像超分辨率算法

基于深度学习的图像超分辨率重建算法不能很好地处理现实生活中有多种复杂噪声干扰的低分辨率图片,提出一种双向的生成对抗网络,引入下采样网络及重建网络联合学习的方法.下采样网络模拟生成现实生活中有复杂噪声及受运动干扰的低分辨率图片,重建网络将模拟生成的低分辨率图片恢复为细节清晰的高分辨率图片.实验结果表明,该算法能够重建出视觉效果良好的超分辨率图像,在Set5、DIV2 K等通用测试集上,其客观评价指标(PSNR、SSIM)对比于SRGAN方法分别提高了约0.9 dB,0.25.     

基于LPD-NMF的多模态过程监视

为了提高NMF方法在方差差异明显的多模态过程中的监视效果,提出一种基于LPD-NMF的多模态过程监视方法.对多模态过程训练数据运用局部概率密度(LPD)进行预处理,消除方差差异明显的多模态特性.运用非负矩阵分解算法进行降维和局部特征提取,计算每个低维样本与其k个近邻欧氏距离的平方和,使用核密度估计(KDE)算法来确定控制限进行多模态过程监视.将该方法应用于数值例子和半导体数据,结果表明,其过程监视结果优于常规kNN、WkNN和LPD-kNN方法.     

Effect of friction reclaimed materials of waste brake-shoe on basic performance of mortar

Discarded train brake shoes mainly consist of steel-backed friction material. To be better reutilized, its essential features and its interaction in cement-based material need to be studied. Consequently, particle size analysis, SEM, IR and TGA were used to investigate two types of waste brake shoes, i e, mechanical grinding friction reclaimed material of waste brake-shoe (G-FRMWBS) and pyrolysis-friction reclaimed materials of waste brake-shoe (P-FRMWBS). The latter exhibited less organic content, larger range of particle size distribution and smaller medium particle diameter. Both types contained inorganic particles of spherical and irregular shapes, striped with steel fiber. Upon isometric substituting fine aggregates, G-FRMWBS lifted the strength of mortar effectively that was increased by 16.6% and 17.5% when the replacing rate was 5%; the value went up to 19.2% and 19.2% when the replacing rate was 10%. Moreover, inclusion of FRMWBS enhanced the chloride penetration resistance, and optimized the pore characteristic and ITZ (interfacial transition zone) as well.