Open-loop frequency response for a chaotic masking system

In this paper, a new numerical simulation approach is proposed for the study of open-loop frequency response of a chaotic masking system. Using Chua＇s circuit and the Lorenz system as illustrative examples, we have shown that one can employ chaos synchronization to separate the feedback network from a chaotic masking system, and then use numerical simulation to obtain the open-loop synchronization response, the phase response, and the amplitude response of a chaotic masking system. Based on the analysis of the frequency response, we have also proved that changing the amplitude of the exciting （input） signal within normal working domain does not influence the frequency response of the chaotic masking system. The new numerical simulation method developed in this paper can be extended to consider the open-loop frequency response of other systems described by differential or difference equations.

Side-Channel Leakage Analysis of Inner Product Masking

The Inner Product Masking(IPM)scheme has been shown to provide higher theoretical security guarantees than the BooleanMasking(BM).This scheme aims to increase the algebraic complexity of the coding to achieve a higher level of security.Some previous work unfolds when certain(adversarial and implementation)conditions are met,and we seek to complement these investigations by understanding what happens when these conditions deviate from their expected behaviour.In this paper,we investigate the security characteristics of IPM under different conditions.In adversarial condition,the security properties of first-order IPMs obtained through parametric characterization are preserved in the face of univariate and bivariate attacks.In implementation condition,we construct two new polynomial leakage functions to observe the nonlinear leakage of the IPM and connect the security order amplification to the nonlinear function.We observe that the security of IPMis affected by the degree and the linear component in the leakage function.In addition,the comparison experiments from the coefficients,signal-to-noise ratio(SNR)and the public parameter show that the security properties of the IPM are highly implementation-dependent.

基于FFT和Masking的实时语音通话降噪算法

针对语音通话质量的提升问题,提出一种基于快速傅里叶变换(Fast Fourier Transform,FFT)和Masking技术的实时语音通话降噪算法。首先,提出一个实时语音通话降噪的基本框架,并研究了帧分割、窗函数处理及FFT的数学原理。其次,阐述了基于人耳听觉特性的Masking方法及其在频域中的应用。最后,通过逆快速傅里叶变换(Inverse Fast Fourier Transform,IFFT)将信号转换回时域,并进行实验分析。实验结果表明,该降噪算法可以有效改善语音的清晰度和整体感知质量。

Data Masking for Chinese Electronic Medical Records with Named Entity Recognition

With the rapid development of information technology,the electronifi-cation of medical records has gradually become a trend.In China,the population base is huge and the supporting medical institutions are numerous,so this reality drives the conversion of paper medical records to electronic medical records.Electronic medical records are the basis for establishing a smart hospital and an important guarantee for achieving medical intelligence,and the massive amount of electronic medical record data is also an important data set for conducting research in the medical field.However,electronic medical records contain a large amount of private patient information,which must be desensitized before they are used as open resources.Therefore,to solve the above problems,data masking for Chinese electronic medical records with named entity recognition is proposed in this paper.Firstly,the text is vectorized to satisfy the required format of the model input.Secondly,since the input sentences may have a long or short length and the relationship between sentences in context is not negligible.To this end,a neural network model for named entity recognition based on bidirectional long short-term memory(BiLSTM)with conditional random fields(CRF)is constructed.Finally,the data masking operation is performed based on the named entity recog-nition results,mainly using regular expression filtering encryption and principal component analysis(PCA)word vector compression and replacement.In addi-tion,comparison experiments with the hidden markov model(HMM)model,LSTM-CRF model,and BiLSTM model are conducted in this paper.The experi-mental results show that the method used in this paper achieves 92.72%Accuracy,92.30%Recall,and 92.51%F1_score,which has higher accuracy compared with other models.

Image encryption based on a novel memristive chaotic system,Grain-128a algorithm and dynamic pixel masking

In this paper,we first propose a memristive chaotic system and implement it by circuit simulation.The chaotic dynamics and various attractors are analysed by using phase portrait,bifurcation diagram,and Lyapunov exponents.In particular,the system has robust chaos in a wide parameter range and the initial value space,which is favourable to the security communication application.Consequently,we further explore its application in image encryption and present a new scheme.Before image processing,the external key is protected by the Grain-128a algorithm and the initial values of the memristive system are updated with the plain image.We not only perform random pixel extraction and masking with the chaotic cipher,but also use them as control parameters for Brownian motion to obtain the permutation matrix.In addition,multiplication on the finite field GF(2^(8))is added to further enhance the cryptography.Finally,the simulation results verify that the proposed image encryption scheme has better performance and higher security,which can effectively resist various attacks.

Non-Contact Physiological Measurement System for Wearing Masks During the Epidemic

Physiological signals indicate a person’s physical and mental state at any given time.Accordingly,many studies extract physiological signals from the human body with non-contact methods,and most of them require facial feature points.However,under COVID-19,wearing a mask has become a must in many places,so how non-contact physiological information measurements can still be performed correctly even when a mask covers the facial information has become a focus of research.In this study,RGB and thermal infrared cameras were used to execute non-contact physiological information measurement systems for heart rate,blood pressure,respiratory rate,and forehead temperature for peoplewearing masks due to the pandemic.Using the green(G)minus red(R)signal in the RGB image,the region of interest(ROI)is established in the forehead and nose bridge regions.The photoplethysmography(PPG)waveforms of the two regions are obtained after the acquired PPG signal is subjected to the optical flow method,baseline drift calibration,normalization,and bandpass filtering.The relevant parameters in Deep Neural Networks(DNN)for the regression model can correctly predict the heartbeat and blood pressure.In addition,the temperature change in the ROI of the mask after thermal image processing and filtering can be used to correctly determine the number of breaths.Meanwhile,the thermal image can be used to read the temperature average of the ROI of the forehead,and the forehead temperature can be obtained smoothly.The experimental results show that the above-mentioned physiological signals of a subject can be obtained in 6-s images with the error for both heart rate and blood pressure within 2%∼3%and the error of forehead temperature within±0.5°C.

Face Mask and Social Distance Monitoring via Computer Vision and Deployable System Architecture

The coronavirus(COVID-19)is a lethal virus causing a rapidly infec-tious disease throughout the globe.Spreading awareness,taking preventive mea-sures,imposing strict restrictions on public gatherings,wearing facial masks,and maintaining safe social distancing have become crucial factors in keeping the virus at bay.Even though the world has spent a whole year preventing and curing the disease caused by the COVID-19 virus,the statistics show that the virus can cause an outbreak at any time on a large scale if thorough preventive measures are not maintained accordingly.Tofight the spread of this virus,technologically developed systems have become very useful.However,the implementation of an automatic,robust,continuous,and lightweight monitoring system that can be efficiently deployed on an embedded device still has not become prevalent in the mass community.This paper aims to develop an automatic system to simul-taneously detect social distance and face mask violation in real-time that has been deployed in an embedded system.A modified version of a convolutional neural network,the ResNet50 model,has been utilized to identify masked faces in peo-ple.You Only Look Once(YOLOv3)approach is applied for object detection and the DeepSORT technique is used to measure the social distance.The efficiency of the proposed model is tested on real-time video sequences taken from a video streaming source from an embedded system,Jetson Nano edge computing device,and smartphones,Android and iOS applications.Empirical results show that the implemented model can efficiently detect facial masks and social distance viola-tions with acceptable accuracy and precision scores.

基于深度学习的水下目标识别技术

在水下复杂场景下,目标对象具有姿态不同、遮挡和背景复杂等特点,这对卷积网络的特征提取能力提出巨大挑战。Mask R-CNN算法在水下目标特征提取过程中也存在特征提取能力欠佳的问题,导致算法在水下目标检测准确性较差。因此,提出一种基于Mask R-CNN的改进水下目标目标识别方法。首先可采用金字塔切分的通道注意力模块PAS代替采用了ResNet50的3×3卷积模块,该模块可通过对每个通道进行金字塔的切分,针对通道切分完成后所得出来的通道特征图上的空间信息来进行不用的尺度特征层提取;同时通过采用另一种更加安全稳定和高效的ECANEt通道注意力模块代替PAS模块中的SENet通道注意力模,对多维度的通道注意力权重进行特征重标定;最后对特征金字塔FPN的网络结构进行改进,加强不同特征层之间的信息融合。根据不同场景下进行的实验对比,改进后的网络能够提高水下目标识别的准确率,平均检测精度可达91.3%。本文所提出的改进Mask RCNN网络模型,能够适应水下复杂多变的场景,为水下目标的识别提供理论依据与技术方案。

Mask在包装材料气体阻隔性能检测中的应用研究

目的研究和评价mask在材料气体阻隔性检测中的应用及其检测数据的重复性、准确性和数据稳定性。方法选用覆盖高阻隔、中阻隔、低阻隔等阻隔性能范围的5种样品,使用3种不同面积的mask和仪器测试腔原有面积对样品进行测试,并对测试结果重复性、稳定性和准确性进行分析评价。结果高阻隔材料PET硬片使用面积12.56 cm^(2)的mask测试时,可以得到较为稳定的检测结果,而在使用更小面积(1.77、5 cm^(2))的mask时,测试结果的相对标准偏差、相对极差和测试数据偏差都较差,不推荐使用。KOP/CPP在使用1.77 cm^(2)的mask测试时,测试结果相对标准偏差和测试数据偏差都略大于10%。PET/CPP在使用1.77 cm^(2)的mask测试时,其测试数据偏差略大于10%。BOPE/LDPE和TPU使用1.77 cm^(2)的mask测试可以得到良好的检测结果。结论Mask是解决试样材料特性、设备量程限制、试样尺寸等测试困难的优秀解决方案。对于中、低阻隔材料的透气性测试,使用mask可获得具有良好可信度和稳定性的测试数据。而在进行氧气透过率的测试时应尽量选择大的测试面积。小面积mask不适用于高阻隔材料的气体阻隔性测试。

基于牛脸和躯干综合信息的奶牛个体识别研究

针对基于单一信息对奶牛个体身份识别精度低的问题,本文提出1种基于牛脸和躯干综合信息对奶牛个体身份识别的方法。在Mask R-CNN目标检测模型的基础上进行改进,将注意力机制模块引入到Mask R-CNN的ResNet50特征提取网络的输出阶段,能够在图像通道和空间上增强奶牛身份信息。针对奶牛不同部位,本文对改进前后的Mask R-CNN模型分别基于牛脸、基于躯干以及基于牛脸和躯干综合信息进行了相关实验。实验结果表明,原始Mask R-CNN模型基于牛脸和躯干综合信息进行奶牛个体识别,比单独基于牛脸或躯干的识别精度提高2.3%~3.7%。改进后的Mask R-CNN模型在自建奶牛图像数据集上的准确率达到了93.63%,mAP值达到92.16%,相较于原始Mask R-CNN,准确率提高了2.92%,mAP值提高了2.63%。本文方法能够实现对养殖场环境下奶牛个体身份的识别,可为奶牛的精准养殖提供技术支持。

基于多尺度注意力特征融合的场景文本检测

针对目前文本检测中小尺度文本和长文本检测精度低的问题,提出了一种基于多尺度注意力特征融合的场景文本检测算法。该方法以Mask R-CNN为基线模型,引入Swin_Transformer作为骨干网络提取底层特征。在特征金字塔(feature pyramid networks,FPN)中,通过将多尺度注意力热图与底层特征通过横向连接相融合,使检测器的不同层级专注于特定尺度的目标,并利用相邻层注意力热图之间的关系实现了FPN结构中的纵向特征共享,避免了不同层之间梯度计算的不一致性问题。实验结果表明:在ICDAR2015数据集上,该方法的准确率、召回率和F值分别达到了88.3%、83.07%和85.61%,在CTW1500和Total-Text弯曲文本数据集上相较现有方法均有良好表现。

改进Mask R-CNN的馆藏报纸图像内容分割

开展馆藏报纸图像内容分割研究,能提升文字识别准确率,对促进机器识别取代人工操作、提高图书馆数字化工作效率具有重要意义。文章根据报纸图像呈现的特征,提出一种基于改进MaskR-CNN的算法,实现报纸图像内容分割。首先,通过优化锚框比例和损失函数,对原始MaskR-CNN算法进行改进。其次,采用数据增强、调整训练参数开展样本训练。最后,通过实验的方式对改进后的MaskR-CNN算法训练模型和原始算法训练模型进行比较,并采用AP_bbox和AP_segm评价指标对实验结果进行评估,改进后的算法训练模型AP_bbox为0.935,AP_segm为0.943,均超过原始算法训练模型。实验结果表明,改进后的MaskR-CNN算法能够实现报纸图像内容有效检测与分割。

基于深度学习的实例分割边界框回归方法研究

针对实例分割任务中图像中可能出现相互遮挡或边缘模糊导致边界框定位不准确的问题,本文提出了一种新的边界框回归损失函数。将边界框位置预测转化为估计定位置信度随位置变化的概率分布;考虑坐标点间存在联系,提出一种面积差计算方法;为了证明此方法可以很好地应用于先检测后分割的实例分割模型,本文使用Mask R-CNN作为基线。实验结果表明:在边界框检测及实例分割任务中,本文方法的精度优于其他方法,对于小物体的检测与分割效果更显著,训练和评估速度也更快。

基于Mask R-CNN的电力关键设备运行状态检测

为判断电力关键设备两端负载电压与干路总电压之间的数值关系,提出基于Mask R-CNN的电力关键设备运行状态检测方法。在Mask R-CNN网络结构中,判断电量信号的时域范围与频域范围。然后根据负荷阻抗特征计算交流参数的取值结果,再联合已获取的电信号参量,求解连续相关函数,从而检测电力关键设备运行状态。实验过程中,设备两端负载电压、内阻消耗电压之和与干路总电压之间的差值未超过1.5 V,说明该方法能够证明电力关键设备两端负载电压、内阻消耗电压之和等于干路总电压数值的猜想成立,可以根据该验证检测电力关键设备运行状态是否正常。

基于尾灯灯语的混行交通流车辆驾驶意图识别模型研究

针对长期存在自动驾驶车辆(autonomous vehicle,AV)与人工驾驶车辆(human-driven vehicle,HV)混行的交通现状,结合深度学习和HSV颜色特征提取方法,提出了一种在混行交通环境下基于尾灯灯语的车辆驾驶意图识别模型。以Mask R-CNN(mask region proposal convolutional neural network)车辆模型检测出的感兴趣区域RoI(region of interest)为限制,将区域内的HV作为研究对象,根据尾灯位置相关性,在HV车尾区域添加纵横向约束来定位传递灯语信号的左右尾灯;在规定的灯语组合及转向灯闪烁频率基础上,提出了一种基于时间序列的灯语识别算法,运用多目标判别相关性滤波CSRT(channel and spatial relatability tracking)跟踪HV尾灯并统计尾灯时序状态;以动态灯语作为输入,构建基于尾灯灯语的驾驶意图识别模型;使用基于真实路况信息的Cityspaces数据集和交通流视频数据对模型进行训练、验证和测试。研究结果表明:基于尾灯灯语的驾驶意图识别模型对视频流车辆尾灯检测准确率和召回率分别为96.0%、98.2%,对驾驶意图识别的平均准确率达到了95.9%,单帧识别耗时为20 ms,为高速混行环境下的AV决策规划提供了有效的理论依据。

改进Mask RCNN的盾构隧道渗漏水检测方法

渗漏水是盾构隧道结构存在潜在损伤或缺陷的重要表征,快速、准确检测出渗漏水位置,对隧道安全运营和维护具有重要意义。现有的方法大多采用光学影像对隧道渗漏水进行检测,受隧道内空间和光线条件限制,难以获得高质量病害图片。因此,本文提出了一种基于激光点云数据与改进Mask RCNN相结合的渗漏水检测方法。首先对激光点云反射强度进行修正;然后生成灰度图像并建立渗漏水病害数据集;最后在Mask RCNN算法中引入空洞卷积和变形卷积,实现了隧道渗漏水病害的快速检测。利用某地铁采集的数据进行验证,结果表明,本文提出的改进Mask RCNN算法相较于原始算法和FCN算法检测精度均有明显提升,在盾构隧道渗漏水识别方面性能表现较好。

基于红外热像的车站混凝土结构损伤智能检测方法

车站作为一种典型的混凝土建筑,受工艺和材料配比的限制,大多数混凝土结构均具有一定的内部缺陷。因此,为了保证车站人员的安全,研究提出了一种基于红外热像及掩膜循环卷积神经网络的混凝土结构内部损伤智能检测方法。实验结果显示,该方法对不同类型缺陷的检测精度最高为99.7%,最低为93.3%;Io U最高为98.4%,最低为91.5%。在缺陷尺寸量化中,预测尺寸与实际尺寸的比值均趋近于1,二者的相对误差最大为1.35%,最小为0.04%,平均相对误差为0.70%。在实际应用中,智能检测模型的平均精度均值、平均Io U和平均召回率分别为92.1%、90.2%和84.4%,相较于测试中有所下降,但仍保持在良好水平上。上述结果表明,基于红外热像及掩膜循环卷积神经网络的智能检测模型能有效实现混凝土内部损伤的准确检测,有效保障车站混凝土结构的性能。

基于改进Mask-RCNN算法的作物害虫分类识别

智能虫情测报灯对农业生产中及时察觉虫害、虫灾问题有重大作用,准确的害虫分类识别为虫情测报提供可靠数据支撑的关键。该研究对智能虫情测报灯所需核心识别算法进行改进,针对分类目标多尺度、存在多种相似非目标害虫干扰、易产生目标粘连等问题,提出一种基于改进Mask-RCNN(mask region-based convolutional neural network)模型的害虫图像智能识别模型。该模型使用DeAnchor算法改进Mask-RCNN的锚框引导机制,使用NDCC(novelty detection consistent classifiers)训练分类器进行联合分类和检测,改善非目标杂虫的误识别问题。改进后模型对无杂虫、不同虫体密度图像的识别准确率最高达到96.1%,最密集时可达90.6%,在仅有非目标的图片识别中,误检率降至9%,非目标与目标共存且密度为40虫/图的误检率降至15%。试验表明,该文所提模型在现有分类模型的基础上,增强了对密集区域的检测能力,改善了非目标误识别问题,在实际检测环境下的害虫分类识别精度更高,可为虫害防治工作提供数据参考。

基于实例分割技术的草莓叶龄及冠幅表型快速提取方法

[目的/意义]为解决高通量草莓叶龄及冠幅提取问题,提出一种基于移动式表型平台和实例分割技术的高通量表型提取方法。[方法]利用小型移动式表型平台对温室内盆栽草莓植株的俯拍图像进行数据获取,并利用改进型Mask R-CNN(Convolutional Neural Network)模型对图像进行处理,以此获取草莓植株叶龄信息。首先利用带有分组注意力模块的Split-Attention Networks(ResNeSt)骨干网络替换原有网络,从而提高图像特征信息提取精度和执行效率。在训练时,利用Mosaic方法对草莓图像进行数据增强,并且使用二元交叉熵损失函数对原本的交叉熵分类损失函数进行优化,以达到更好的植株与叶片的检测准确度。在此基础上,对训练结果进行后处理,利用标定比值对冠幅进行计算。[结果和讨论]该方法能够在ResNeSt-101骨干网络下,实现80.1%的掩膜准确率和89.6%的检测框准确率,并且能够以99.3%的植株检测正确率和98.0%的叶片数量检出率实现高通量的草莓叶龄估算工作。而模型推理后草莓植株南北和东西向冠幅测试值与真实值相比误差均低于5%的约占98.1%。[结论]该方法有着较高的鲁棒性,能够为智慧农业下高通量植物表型获取与解析工作提供技术支持。

基于改进Mask R-CNN的矿石类型检测算法

针对不同的矿石类型进行选矿工艺参数设置和操作有利于保障精矿质量,提高回收率和降低物资消耗。由于缺乏矿石类型实时检测有效手段,选矿过程的精准操作目前较难实现。为此,本文提出一种全面改进的Mask R-CNN矿石类型检测算法。算法步骤:①使用ResNetV1d-50提取矿石图像各阶段的特征图,并在主干网络中加入可变形卷积以便增强异形矿石的特征;②改进FPN,通过在主干网络的C5特征层加入特征残差模块,并融合到P5特征层,得到具有更强语义信息的多尺度特征图;③改进RPN,设计自适应的正样本IOU选取方案来匹配宽高比异常的矿石,进一步提高异形矿石的识别精度;④在RoIAlign网络基础上加入Global-Context,以提高小矿石的检测能力;⑤在数据增强和训练技巧方面对模型进行改进。结果表明,本文算法的平均精度为67.92%,平均交并比为63.54%,分别比基准模型提高了13.67%和9.71%。本文研究方法在矿石类型识别领域具有较好的应用价值。