基于TW3-C RUS法的骨龄评估方法研究

经典TW3-C RUS (Tanner and Whitehouse 3-Chinese RUS)法将手骨的关键骨骺区域严格划分为9个等级,未充分考虑骨骺发育的连续性,导致骨龄评估存在一定误差。针对该问题,本文提出一种基于TW3-C RUS法的改进骨龄评估方法。采用阈值法的思想,动态选择网络模型输出的前N个等级概率值,并将前N个概率值作为权值计算手骨的加权得分,降低由于手骨单一等级判定引起的误差。针对网络模型冗余问题,采用跨阶段局部网络(cross stage partial network, CSP-Net)轻量化深度残差网络(residual network 50,Resnext50)。实验表明,改进后的方法对男性骨龄评估的平均绝对误差(mean absolute error,MAE)为0.421 4岁,女性MAE为0.412 8岁,相比于经典TW3-C RUS法,骨龄评估准确率有明显提升。轻量化后的网络模型参数量为46.28 MB,相比Resnext50网络模型有明显降低。     

结合高效通道注意模块的残差网络骨龄评估

本文针对现有骨龄评估数据集数据规模小,样本 分布不均匀以及现有方法评估准确度 较低的问题,提出了一种新的结合高效通道注意模块的残差网络骨龄评估模型。通过结合深 度残差网络和高效通道注意模块来提高卷积效率,并改进损失函数,缓解样本分布不均匀问 题的影响;然后运用迁移学习的方法微调训练骨龄评估模型,提高模型训练效率;最后引入 随机深度算法提高模型泛化能力。实验结果表明,该方法在RSNA数据集和DHA数据集上的平 均绝对误差分别 为4.69个月和5.98个月,当容忍度为12个月时,骨龄评估的准确率可以达到 98.36%和94.88%,说明本文方法能够明显地提高骨龄评估的准确率,一定程度上缓解数据规 模小和数据分布不均匀带来的影响。     

皮肤图像的凹凸度和信息熵与年龄关系的研究

目的：常规手腕骨Tw3骨龄检测法不适用于骨骼停止发育的成年人的年龄检测,而人体皮肤在成年之后变化特征明显,通过求解皮肤特征参数与年龄关系,从而达到针对成年人年龄检测的目的。方法：采用医学图像处理技术,尤损检测并提取皮肤图像的量化参数凹凸度和信息熵,采用统计方法分析这些特征参数与年龄之间的关系。结果：成年人的年龄与皮肤图...     

激光扫描在鼻腔三维重建及测量中的初步应用

目的:通过激光扫描建立0至12岁汉族儿童各年龄段正常鼻腔的三维重建模型,并揭示鼻腔随年龄发育的规律.方法:在全麻状态下对60例0至12岁的进行分组并制取鼻腔模型,用激光扫描仪扫描鼻腔形态,通过计算机工程软件进行模型重建.结果:此法可准确扫描鼻腔内部形态,并通过三维重合重建每组理想的鼻腔内部形态,并可以分析鼻腔随年龄增长的变化情况.结论:激光扫描三维分析方法是分析正常儿童鼻腔形态的理想方法,应用此模型可重建各个年龄段理想的鼻腔内部形态,并可量化分析正常儿童随生长发育而变化的鼻腔形态.     

混合核函数SVM在变压器状态评估中的应用

核函数是SVM(Support Vector Machine,支持向量机)的重要组成部分,核函数的选取对分类效果有明显的影响。该文把混合核函数引入到变压器状态评估中。实例分析表明,混合核函数支持向量机提高了状态评估的准确率。     

关于海森堡模型中一种并行算法实现的讨论

使用并行算法（简称Z分法）fortran编程计算获取海森堡模型位型[N,k] （N为海森堡链总格点数, k为格点中自旋向上的电子数）的最小本征值的最短时间。研究方法：使用置换群方法产生模型的能量矩阵,将能量矩阵对角化所得到的本征值构成数据群,采用Z（Z=1,2……）分法Fortran编程计算获得群中最小数据的最短(或最长)时间。研究结论：(1）同一位型[N,k],使用2分法获取模型位型[N,k]的最小本征值的时间最长,而不等分或满等分（此时Z=1或位型[N,k]的矩阵维数）时的时间最短且二者相等。(2）对于不同位型[N,k] ,Z相同而当N（k）同,k（N）增大时,获取模型最小本征值的最短时间增加。通过讨论海森堡模型获取最小本征值的时间计量可为研究者们在计算工作中作提高运算效率的借鉴。     

正弦信号的直接FFT参数估计与相位差分法对比研究

该文研究了基于FFT的正弦信号参数估计问题,揭示了频率与初相估计间的相互联系,并对相位差分法的估值误差公式进行了推导和仿真验证。两种算法的对比说明相位差分法运算量小,可以在不高的信噪比下获得彼此独立的高精度参数估值,因此更加有利于工程的实现。     

基于遗传算法的恶意代码对抗样本生成方法

机器学习已经广泛应用于恶意代码检测中,并在恶意代码检测产品中发挥重要作用。构建针对恶意代码检测机器学习模型的对抗样本,是发掘恶意代码检测模型缺陷,评估和完善恶意代码检测系统的关键。该文提出一种基于遗传算法的恶意代码对抗样本生成方法,生成的样本在有效对抗基于机器学习的恶意代码检测模型的同时,确保了恶意代码样本的可执行和恶意行为的一致性,有效提升了生成对抗样本的真实性和模型对抗评估的准确性。实验表明,该文提出的对抗样本生成方法使MalConv恶意代码检测模型的检测准确率下降了14.65%;并可直接对VirusTotal中4款基于机器学习的恶意代码检测商用引擎形成有效的干扰,其中,Cylance的检测准确率只有53.55%。     

《工业互联网安全成熟度模型:从业者指南》对我国的启示

为加速推动安全成熟度模型在工业互联网重要领域的应用落地,2019年2月25日,美国工业互联网产业联盟发布《工业互联网安全成熟度模型:从业者指南》,构建了完备的安全成熟度模型,形成了动态的工业互联网安全评估流程,并成功应用该模型开展安全实践评估工作。对此,我国应充分重视,加快开展重点领域安全评估管理实践,提速安全评测标准的研制,加快推动重点领域安全实践应用,强化安全态势感知能力建设,发挥我国产业联盟桥梁纽带作用,构建完备可靠的工业互联网安全评估体系。     

草甘膦导致板栗叶片形态畸形的扫描电镜观察

除草剂应用不当会影响板栗的正常生长发育,本文分析了过量草甘膦喷洒后对板栗不同成熟度叶片形态的影响。实验利用扫描电镜观察对喷洒过除草剂的不同发育程度的板栗叶片及对照叶片下表皮显微结构进行分析,结果表明:从表型上看,没有喷洒草甘膦的对照板栗叶片正常,而喷洒除草剂后的板栗叶片卷曲皱缩,致畸等;从超微结构看,对照叶片的下表皮布满腺毛,因而不能观察到表皮结构及气孔等。喷洒除草剂的板栗叶片的下表皮腺毛不饱满,萎蔫,甚至无腺毛,可以观察到表皮结构及气孔,不同发育时期的气孔密度不同。过量草甘膦导致板栗叶片形态畸形。     

The BoneXpert Method for Automated Determination of Skeletal Maturity

Bone age rating is associated with a considerable variability from the human interpretation, and this is the motivation for presenting a new method for automated determination of bone age (skeletal maturity). The method, called BoneXpert, reconstructs, from radiographs of the hand, the borders of 15 bones automatically and then computes “intrinsic” bone ages for each of 13 bones (radius, ulna, and 11 short bones). Finally, it transforms the intrinsic bone ages into Greulich Pyle (GP) or Tanner Whitehouse (TW) bone age. The bone reconstruction method automatically rejects images with abnormal bone morphology or very poor image quality. From the methodological point of view, BoneXpert contains the following innovations: 1) a generative model (active appearance model) for the bone reconstruction; 2) the prediction of bone age from shape, intensity, and texture scores derived from principal component analysis; 3) the consensus bone age concept that defines bone age of each bone as the best estimate of the bone age of the other bones in the hand; 4) a common bone age model for males and females; and 5) the unified modelling of TW and GP bone age. BoneXpert is developed on 1559 images. It is validated on the Greulich Pyle atlas in the age range 2–17 years yielding an SD of 0.42 years [0.37; 0.47] 95% conf, and on 84 clinical TW-rated images yielding an SD of 0.80 years [0.68; 0.93] 95% conf. The precision of the GP bone age determination (its ability to yield the same result on a repeated radiograph) is inferred under suitable assumptions from six longitudinal series of radiographs. The result is an SD on a single determination of 0.17 years [0.13; 0.21] 95% conf.      

一种基于卷积神经网络的雷达目标分类方法

雷达作为对低空和地面目标探测及监视预警的主要手段,在安全领域应用广泛。针对现阶段实际应用中雷达目标分类技术中过于依赖人工提取特征的问题,提出了一种基于卷积神经网络的分类方法,对雷达回波数据进行二维傅里叶变换得到距离-多普勒图像,再以距离-多普勒图集作为数据集,训练神经网络,得到能够完成雷达目标识别的网络模型。结果表明,相较于传统方法,基于卷积神经网络的目标识别模型在省去人工工作的同时提高了目标识别精度。     

Super-resolution registration using tissue-classified distance fields

We present a method for registering the position and orientation of bones across multiple computed-tomography (CT) volumes of the same subject. The method is subvoxel accurate, can operate on multiple bones within a set of volumes, and registers bones that have features commensurate in size to the voxel dimension. First, a geometric object model is extracted from a reference volume image. We use then unsupervised tissue classification to generate from each volume to be registered a super-resolution distance field--a scalar field that specifies, at each point, the signed distance from the point to a material boundary. The distance fields and the geometric bone model are finally used to register an object through the sequence of CT images. In the case of multiobject structures, we infer a motion-directed hierarchy from the distance-field information that allows us to register objects that are not within each other's capture region. We describe a validation framework and evaluate the new technique in contrast with grey-value registration. Results on human wrist data show average accuracy improvements of 74% over grey-value registration. The method is of interest to any intrasubject, same-modality registration applications where subvoxel accuracy is desired.     

基于U2-Net和VGG16的天然气泄露检测

目前在深度学习领域很少以天然气泄露图像为数据进行研究,本文使用甲烷红外图像训练的卷积神经网络(VGG16)来实现泄露检测。另外,针对泄露的甲烷气体与背景图像存在相似性的问题,使用U²-Net图像分割网络代替背景建模方法来提取泄露气体区域。通过迁移VGG16网络模型结构和卷积层参数,在卷积层和激励层之间加入BN层以提高训练速度,将最后一层池化层替换为基于最大池化算法的动态自适应池化方法以提高检测精度。将改进的VGG16神经网络对分割的红外图像进行训练并与其他卷积神经网络进行对比,使用准确率,精准率,召回率和F1-score来对模型进行综合评价,其表现效果最好。与现有的检测方法进行对比,所提出的检测方法准确率更高。该检测方法能够实现高精度泄漏检测,满足天然气泄露检测准确性的要求,且模型具有较好的泛化能力和鲁棒性。     

Research onconvolutional neural network for reservoir parameter prediction

As the branch of artificial intelligence,artificial neural network solved many difficult practical problems in pattern recognition and classification prediction field successfully.However,they cannot learn the feature from networks.In recent years,deep learning becomes more and more advanced,but the research on the field of geological reservoir pa-rameter prediction is still rare.A method to predict reservoir parameters by convolutional neural network was presented,which can not only predict reservoir parameters accurately,but also get features of the geological reservoir.The study es-tablished the convolutional neural network model.Results show that the convolutional neural network can be used for reservoir parameter prediction,and get high prediction precision.Moreover,convolutional features from convolutional neural network provided important support for geological modeling and logging interpretation.     

基于改进U-Net卷积神经网络的钢轨表面损伤检测方法

基于卷积神经网络的深度学习方法对钢轨表面损伤的自动化检测起到非常重要的推动作用,因此提出一种基于卷积神经网络的钢轨表面损伤检测方法。首先,在经典U-Net的收缩路径和扩展路径之间增加一个分支网络,可以辅助U-Net输出理想的分割图。然后,将Type-I RSDDs高速铁路轨道数据集作为检测样本,使用数据增强的手段扩增检测样本后馈入改进的U-Net中进行训练和测试。最后,采用评价指标对所提方法进行评估。实验结果表明,所提方法的检测准确率达到99.76%,相比于其他方法的最高水平提高6.74个百分点,说明所提方法可以显著提高检测准确率。     

高仿真光敏印章盖印印文的自动识别

为了实现高仿真光敏印章印文的自动识别,探究训练样本量、网络模型对识别准确率的影响,通过扫描打印伪造法、拓印设计伪造法制备2枚高仿光敏印章,盖印3 000枚印文作为训练样本,30枚印文作为测试样本,利用卷积神经网络4种模型实现高仿真光敏印章印文的鉴别。4种网络模型均能得到100%的识别准确率。仿真实验结果表明,针对高仿真光敏印章印文识别任务,卷积神经网络能作为一种可行的方法为检验提供辅助参考;综合分析4种网络模型,Resnet50是最优选择。     

Performance-based classifier combination in atlas-based image segmentation using expectation-maximization parameter estimation

It is well known in the pattern recognition community that the accuracy of classifications obtained by combining decisions made by independent classifiers can be substantially higher than the accuracy of the individual classifiers. We have previously shown this to be true for atlas-based segmentation of biomedical images. The conventional method for combining individual classifiers weights each classifier equally (vote or sum rule fusion). In this paper, we propose two methods that estimate the performances of the individual classifiers and combine the individual classifiers by weighting them according to their estimated performance. The two methods are multiclass extensions of an expectation-maximization (EM) algorithm for ground truth estimation of binary classification based on decisions of multiple experts (Warfield et al., 2004). The first method performs parameter estimation independently for each class with a subsequent integration step. The second method considers all classes simultaneously. We demonstrate the efficacy of these performance-based fusion methods by applying them to atlas-based segmentations of three-dimensional confocal microscopy images of bee brains. In atlas-based image segmentation, multiple classifiers arise naturally by applying different registration methods to the same atlas, or the same registration method to different atlases, or both. We perform a validation study designed to quantify the success of classifier combination methods in atlas-based segmentation. By applying random deformations, a given ground truth atlas is transformed into multiple segmentations that could result from imperfect registrations of an image to multiple atlas images. In a second evaluation study, multiple actual atlas-based segmentations are combined and their accuracies computed by comparing them to a manual segmentation. We demonstrate in both evaluation studies that segmentations produced by combining multiple individual registration-based segmentations are more accurate for the two classifier fusion methods we propose, which weight the individual classifiers according to their EM-based performance estimates, than for simple sum rule fusion, which weights each classifier equally.     

Comparative study of field strength prediction methods in medium wave band

Recently developed digital radio systems for the medium wave band require accurate field strength prediction algorithms for coverage estimation. Presented is a comparison of estimation accuracy provided by the most relevant field strength prediction methods employed for ground-wave propagation at this band. Moreover, a field strength prediction method recently developed by the authors, has been considered in the analysis. Empirical values from measurement campaigns carried out in three different broadcasting networks have been used to analyse the accuracy of the prediction methods. Comparison between predicted and measured values allows objective evaluation of the estimation accuracy of each method under different reception conditions. The proposed method provides the most accurate results on field strength predictions, consequently it is a suitable method for the coverage estimation of the new digital radio systems.     

基于空谱联合的多假设预测高光谱图像压缩感知重构算法

为充分利用高光谱图像的空间相关性和谱间相关性,该文提出一种基于空谱联合的多假设预测压缩感知重构算法。将高光谱图像分组为参考波段图像和非参考波段图像,参考波段图像利用光滑Landweber投影算法重构,对于非参考波段图像,引入空谱联合的多假设预测模型,提高重构精度。非参考波段图像中每个图像块的预测值不仅来自非参考波段图像未经预测的初始重构值的相邻图像块,而且来自参考波段重构图像相应位置及其邻近的图像块,利用预测值得到测量域中的残差,然后对残差进行重构并对预测值进行修正,此残差比原图像更稀疏,且算法采用迭代方式提高重构图像的精度。借助Tikhonov正则化方法求解多假设预测的权重系数,并基于结构相似性判断是否改变多假设预测搜索窗口大小,最后利用交叉验证计算重构算法终止迭代的判据参数。实验结果表明,所提算法优于仅利用空间相关性或谱间相关性进行预测和不预测的重构算法,其重构图像的峰值信噪比提高2 dB以上。