Blind Speech Watermarking Method with Frame Self-Synchronization Based on Spread-Spectrum Using Linear Prediction Residue

State-of-the-art speech watermarking techniques enable speech signals to be authenticated and protected against any malicious attack to ensure secure speech communication. In general, reliable speech watermarking methods must satisfy four requirements: inaudibility, robustness, blind-detectability, and confidentiality. We previously proposed a method of non-blind speech watermarking based on direct spread spectrum (DSS) using a linear prediction (LP) scheme to solve the first two issues (inaudibility and robustness) due to distortion by spread spectrum. This method not only effectively embeds watermarks with small distortion but also has the same robustness as the DSS method. There are, however, two remaining issues with blind-detectability and confidentiality. In this work, we attempt to resolve these issues by developing an approach called the LP-DSS scheme, which takes two forms of data embedding for blind detection and frame synchronization. We incorporate blind detection with frame synchronization into the scheme to satisfy blind-detectability and incorporate two forms of data embedding process, front-side and back-side embedding for blind detection and frame synchronization, to satisfy confidentiality. We evaluated these improved processes by carrying out four objective tests (PESQ, LSD, Bit-error-rate, and accuracy of frame synchronization) to determine whether inaudibility and blind-detectability could be satisfied. We also evaluated all combinations with the two forms of data embedding for blind detection with frame synchronization by carrying out BER tests to determine whether confidentiality could be satisfied. Finally, we comparatively evaluated the proposed method by carrying out ten robustness tests against various processing and attacks. Our findings showed that an inaudible, robust, blindly detectable, and confidential speech watermarking method based on the proposed LP-DSS scheme could be achieved.     

Investigation on the Peroxidase-like Activity of Vitamin B6 and Its Applications in Colorimetric Detection of Hydrogen Peroxide and Total Antioxidant Capacity Evaluation

The peroxidase-like activity of vitamin B6 (VB6) was firstly demonstrated by catalyzing the peroxidase chromogenic substrate 3,3′,5,5′-tetramethylbenzidine (TMB) at the existence of H₂O₂. The influence of different factors on the catalytic property of VB6, including pH, temperature, VB6 concentration, and incubation time, were investigated. The steady-state kinetic study results indicate that VB6 possesses higher affinity to H₂O₂ than natural horseradish peroxidase and some other peroxidase mimics. Besides, the radical quenching experiment results confirm that hydroxyl radical (•OH) accounts for the catalytic process. Based on the excellent peroxidase-like catalytic activity of VB6, the colorimetric methods for H₂O₂ and gallic acid (GA) detection were developed by measuring the absorbance variance of the catalytic system. Under the optimal conditions, the linear ranges of the methods for H₂O₂ and GA determination with good selectivity are 50.0–600.0 μM and 10.0–50.0 μM, respectively. In addition, the developed method was applied in the detection of H₂O₂ in milk samples and evaluation of total antioxidant capacity of different tea infusions. This study may broaden the application prospect of VB6 in environmental and biomedical analysis fields, contribute to profound insight of the physiological functions of VB6, as well as lay foundation for further excavation of small-molecule peroxidase mimics.     

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。     

基于改进GMM与帧差法的运动棉杂率分析算法研究

针对清梳棉流程中产出棉含杂高、质量差的问题,结合改进高斯混合模型(Gaussian mixed model,GMM)与帧差法,提出一种局部运动棉杂率控制优化方法。首先针对清棉机除杂原理及棉杂特性进行分析;其次通过提取视频关键帧并改进GMM与帧差法对图像序列“与”运算实现目标的精确提取,进而通过设计GMM分类器获得棉杂率并进行分析;最后与传统的检测算法作对比验证。实验表明,改进后的算法在有效性以及实用性方面优于传统算法。同时,通过引入闭环控制能满足工业高精度、实时性的需求。     

基于双通道注意力的轻量化PCB缺陷检测研究

印刷电路板 (printed circuit board,PCB)在实际生产过程中存在缺陷样式多种多样、缺陷小、缺陷位置难以定位的问题,而一个巨大的模型难以实现实时检测的要求,且大量的深度可分离卷积层建立的轻量级模型也不能达到足够的精度,为此提出一种基于YOLOv5s的PCB缺陷检测算法。 将原始Backbone的Conv模块跟C3模块用GhostConv替换,在Neck部分则引入了一种新的轻量级卷积技术GSConv,减轻模型大小的同时保持精度,GSConv在模型的准确性和速度之间完成了一个极好的权衡,针对许多注意力模块无法关注全局信息同时模型大的问题,提出了多尺度的轻量化双通道注意力模块(double channel depthwise attention module,DWAM),进一步提高模型精度。通过多组实验, 结果表明,改进算法所有类别的平均mAP为99.14%,且模型的GFLOPs为7.194 G,Params为7.175,原始的YOLOv5s平均mAP为96.86%,GFLOPs为6.89 G,Params为6.596,虽然Params以及GFLOPs有所增大,但是还是满足轻量网络的要求,并且精度相对于YOLOv5s提高了2.25%,且对于每个类别的缺陷识别准确率都有改善,大幅减少计算量和模型参数的同时保证了准确率,满足工业检测生产需求的同时便于移动端部署。     

融合注意力机制的轻量级摔倒检测

摔倒检测大都依靠传感器设备,此类方法受设备自身和环境因素影响较大,常常无法发挥该有的作用,同时,基于视觉的方法往往实时性较差,鲁棒性不强。针对上述问题,本文提出了一种鲁棒性强、能有效部署在嵌入式设备上的轻量化摔倒检测算法。以YOLOv5为基准模型,首先,融合轻量级注意力机制模块,使网络更关注要识别的目标区域,增强网络的识别精度。其次,使用模型压缩方法对模型进行剪枝,减小模型体积和计算量,使模型轻量化,以提高推理速度和便于部署在嵌入式设备中。最后,对剪枝后的模型进行知识蒸馏,在不提升模型复杂度的前提下提升模型的检测精度。实验结果表明：本文模型相较于基准模型,mAP增加了1.7%,召回率提高了1.2%,模型体积减小了79.1%,浮点运算量降低了70.9%。将本文模型部署在嵌入式设备Jetson Nano上,检测速率达到13.2 frame/s,基本满足实时性摔倒检测的要求。     

一种通用的数据采集系统设计及其FPGA实现

基于多相滤波技术和能量检测方法,完成了一种通用的数据采集系统设计及其FPGA实现,可兼容低速、高速和突发信号的采集。仿真和实测结果表明,该系统满足实际需要。     

A Fault Detection Method for Electrohydraulic Switch Machine Based on Oil-Pressure-Signal-Sectionalized Feature Extraction

A turnout switch machine is key equipment in a railway, and its fault condition has an enormous impact on the safety of train operation. Electrohydraulic switch machines are increasingly used in high-speed railways, and how to extract effective fault features from their working condition monitoring signal is a difficult problem. This paper focuses on the sectionalized feature extraction method of the oil pressure signal of the electrohydraulic switch machine and realizes the fault detection of the switch machine based on this method. First, the oil pressure signal is divided into three stages according to the working principle and action process of the switch machine, and multiple features of each stage are extracted. Then the max-relevance and min-redundancy (mRMR) algorithm is applied to select the effective features. Finally, the mini batch k-means method is used to achieve unsupervised fault diagnosis. Through experimental verification, this method can not only derive the best sectionalization mode and feature types of the oil pressure signal, but also achieve the fault diagnosis and the prediction of the status of the electrohydraulic switch machine.     

结合视觉Transformer和CNN的道路裂缝检测方法

提出了一种结合视觉Transformer和CNN的道路裂缝检测方法。利用CNN来捕获局部的细节信息,同时利用视觉Transformer来捕获全局特征。通过设计的Fusion特征融合模块将两者提取的特征有机地结合在一起,从而解决了单独使用CNN或视觉Transformer方法存在的局限。最终将结果传递至交互式解码器,生成道路裂缝的检测结果。实验结果表明,无论是在公开的数据集上还是在自建的数据集上,相较于单独使用CNN或视觉Transformer的方法,所提出的方法在道路裂缝检测任务中有更好的效果。     

激光斜入射条件下“猫眼”效应的实验研究

"猫眼"目标回波功率是激光主动探测系统的重要指标,可用来评估光电装备"猫眼"效应的强弱,并为探测器的优化设计提供参考。依据所建立的斜入射条件下"猫眼"目标回波功率数学模型,仿真分析了入射角对"猫眼"目标回波功率的影响,利用搭建的激光主动探测系统对典型"猫眼"目标进行了实验研究,理论仿真结果与实验结果表明,激光在有限斜入射条件下,"猫眼"目标回波功率将随入射角的增大而迅速下降,并很快湮没于噪声之中。这为进一步研究基于"猫眼"效应的激光主动探测适用条件提供必要的实验依据。