电涡流式纸币厚度传感器设计

点钞机主要依靠磁性安全线、磁性油墨、光学特征等特征来识别伪钞,部分伪钞或残旧钞票粘贴有大小、位置不同的透明胶纸也要区分,难以通过现有技术识别。设计了一种多段机械式厚度传感器,将纸币的厚度转化为机械位移,利用基于TI公司的LDC1000电感数字转换器组成的精密位移传感器实现纸币不同部位厚度的定位检测。首先阐述了机械式厚度传感器的结构与工作原理,并介绍采用TI公司提供的WEBENCH?Designer LDC1000工具设计传感器电路系统。初步试验结果表明,该传感器可在1 mm检测范围内达到优于5μm的分辨率,检测速率达到10 kHz,满足纸币厚度检测要求。     

一种硬币鉴别系统的设计与实现

介绍了一种可用于我国现行流通硬币的鉴别系统.该系统以电涡流传感器、光电传感器为检测手段,以LM3S1138微控制器为控制核心,设计并实现了对硬币面值的快速识别及实时显示、对假币的辨伪和清退,系统鉴别精度高,成本低,具有一定的应用价值.     

LED触摸电子琴

使用普通LED发光二极管作为传感器，制作了8X8的LED传感器矩阵。利用PN节的光电效应检测发光二级管的电容变化来识别人手的触摸，并由处理器对采集到的触摸数据进行处理，以确定触摸点坐标，然后将位置以及强度信息通过串口发送给上位机。上位机接收到触摸位置数据后，根据触摸位置模拟不同的琴音，并通过音频输出对应的琴音，根据光线强度信息在上位机实现3D拄状图显示，从而完成了LED触摸电子琴的设计。     

基于伪双目立体成像自动识别新技术

现有的人民币伪钞等打印信息的识别技术主要是对钞票上的安全线、水印、磁性油墨、荧光油墨等物理特性进行识别。随着伪造技术的发展,特别是随着HD90、TJ55、AZ88、WL15、YX86等仿冒手段不断提高的伪钞的出现,对人民币的鉴伪技术提出了一种更高的要求。提出了一种基于人民币凹版印刷特性,利用普通平板扫描仪进行钞票的伪双目立体成像,对其浮雕纹理进行计算机自动识别,进而实现真、伪钞鉴别的新方法。通过实验验证了该方法的正确性和实用性。给出了基于此方法的伪双目立体成像扫描仪的快速验钞机原型设计。     

基于脑电传感器的面部动作识别研究

提出了一种利用脑电传感器进行面部动作识别的方案。相比传统的可见光、深度相机、肌电方案，该方案具有体验感好、识别准确率高的特点。通过分析面部动作对脑电传感器产生的干扰信号特点，给出了系统设计，描述了基于支持向量机进行模式识别与分类的算法，最后通过实验验证，证明了该方案可在少样本的条件下，实现高精度的面部动作识别。     

钞币面值和真伪的快速识别算法的研究

根据从传感器采集来的信号的特点,提出了在验钞系统中进行鉴伪和面额区分的模式识别算法,并详细阐述了算法的整个实现过程。为了识别钞票面额,采用了信号模板匹配的方案。为了鉴别钞票的真伪,应用了统计模式识别技术,并给出了进行真伪钞判别的线性函数。该算法已经应用到嵌入式系统当中,结果表明:并具有快速,准确,有效等优点,并具有非常好的市场应用前景。     

气吸式钞票计数机加识伪装置的研制

伪造钞票的识别技术,现在是一个世界性的难题.伪币的流通势必严重干扰国民经济正常运转,生产出具有伪币识别功能的钞票计数机,是金融系统实现办公自动化的关键.气吸式钞票计数机以其计数速度快,可整把钞票清点的特点普遍受到客户欢迎.本文介绍的这一装置可把识伪功能加装到CQ200型气吸式点钞机上.其成本低、价格廉、安装、操作简单、稳定可靠.在整把钞票清点过程中如遇伪钞可立即报警,并停止点钞工作.     

基于支持向量机算法的气体识别研究

利用多传感器或者传感器阵列,同时,结合神经网络技术来进行气体识别和定量分析研究已成为目前传感器领域的一个研究热点。介绍了一种在该领域还没有引起足够重视的算法———支持向量机算法(SVM)。利用该算法,结合多传感器技术,对 3种不同体积分数的有机溶剂进行了识别研究,并取得了较好的识别效果,证明了该算法在气体识别领域具有相当大的研究价值。     

基于智能手机运动传感器的步态特征身份识别方法

利用行为特征进行身份验证是生物识别的前沿技术。为优化基于步态特征的身份识别研究中对数据的处理并改进识别的方式，提出利用智能手机运动传感器数据提取步态特征用于身份识别的方法。首先，应用空间转换算法解决传感器坐标系漂移问题，使数据可以完整准确地刻画行为特征；然后，利用支持向量机（SVM）算法对用户切换所导致的步态特征变化进行分类识别。实验结果表明，经过欧拉角法处理后，所提方法识别准确率达到95.5%，在有效识别用户变换的同时降低了空间开销和实现难度。     

基于SVM的人体姿态识别技术研究

随着科技发展，可穿戴式的传感器研究越发得到重视，显现出低功耗、便携性高、低成本以及使用场景不受限制等优势。其中重要的一方面应用就是人体姿态识别，为了识别日常生活中站姿、跪姿以及卧姿三种不同姿态而进行研究。根据人体姿态识别技术理论分析和应用需求选择单传感器进行姿态识别的方案。选用六轴传感器MPU6050结合STM32单片机硬件的方案，采集三种不同姿态的加速度以及角速度数据，经小波去噪和四元数转换后，基于高斯核函数的一对一支持向量机算法对人体姿态进行分类，模型训练框架基于TensorFlow,验证了利用机器学习算法解决三种人体姿态识别问题的可行性。     

荧光检测技术在复点机辨伪中的应用

根据荧光检测技术的原理，在实验室对各种真钞、伪钞进行荧光测试、光谱分析，发现当紫外线照射钞票表面时，真钞、伪钞表面的物质被入射的紫外线激发，发射出不同波长、不同强度的荧光，文章中的复点机正是利用这一光谱范围内荧光强度的差异来进行辨伪的，该方法简便、识别率高，已运用到复点机的生产中。     

基于CCD传感器和DSP的数粒机系统设计

应用数字信号处理器(DSP)与线阵CCD设计了先进的数粒机系统,替代了传统系统中的PLC与光电池。以DSP为控制核心,将喂料、检测计数、装瓶及人机界面等子系统有机集成在一起,采用边缘检测原理实现药粒的检测和计数,设计的数粒机系统具有受粉尘影响小、数粒速度快等特点,适用于各种形状尺寸药粒的检测计数,实际应用证明了系统设计的先进性、可靠性和快速性。     

Towards secure cyber-physical information association for parts

Counterfeiting is a significant problem for safety-critical systems, since cyber-information, such as a quality control certification, may be passed off with a flawed counterfeit part. Safety-critical systems, such as planes, are at risk because cyber-information cannot be provably tied to a specific physical part instance (e.g., impeller). This paper presents promising initial work showing that using piezoelectric sensors to measure impedance identities of parts may serve as a physically unclonable function that can produce unclonable part instance identities. When one of these impedance identities is combined with cyber-information and signed using existing public key infrastructure approaches, it creates a provable binding of cyber-information to a specific part instance. Our initial results from experimentation with traditionally and additively manufactured parts indicate that it will be extremely expensive and improbable for an attacker to counterfeit a part that replicates the impedance signature of a legitimate part.     

磁传感器的非线性误差修正技术

介绍了最小二乘法多项式曲线拟合的原理和方法,以及该方法在磁传感器误差修正中的应用。对磁传感器的测量数据进行处理,利用计算机的高级语言计算拟合函数的系数,设定拟合准确度,得到函数的系数,将系数转换成十六进制数,保存到仪器的微计算机中,利用汇编语言编制误差修正程序,对测量误差进行自动修正。     

Digital twin improved via visual question answering for vision-language interactive mode in human–machine collaboration

The human–machine collaboration system is a key means of manufacturing. Its surveillance, prognostic, and health management are related to safety and manufacturing persistence. This paper begins with the mission requirements of intelligent manufacturing. The study is based on the visual question answering (VQA) technology with a digital twin to increase efficiency. The research contents are as follows: (1) A method of modeling human–machine collaboration based on digital twins is proposed. (2) A VQA is adopted in the digital twin. The video and neural language are considered. (3) VQA technology is introduced into the modeling of the human–machine collaboration system for consistent integration. With VQA technology, humans and machines can collaborate. Human–machine interaction and product counting are implemented in a case study to provide a comprehensive perception.     

A fast calculation of metric scores for learning Bayesian network

Frequent counting is a very so often required operation in machine learning algorithms. A typical machine learning task, learning the structure of Bayesian network (BN) based on metric scoring, is introduced as an example that heavily relies on frequent counting. A fast calculation method for frequent counting enhanced with two cache layers is then presented for learning BN. The main contribution of our approach is to eliminate comparison operations for frequent counting by introducing a multi-radix number system calculation. Both mathematical analysis and empirical comparison between our method and state-of-the-art solution are conducted. The results show that our method is dominantly superior to state-of-the-art solution in solving the problem of learning BN.     

New applications for LTPS array technology including lab‐on‐chip and MEMS actuators

Abstract— The use of low‐temperature poly‐Si technology for new applications beyond displays is presented. These applications include lab‐on‐chip, MEMS actuators, and sensors. As a key example, the use of high‐voltage poly‐Si TFTs for rapid heating and temperature control, as is required for DNA amplification within lab‐on‐chip, is described in detail. Other examples given include MEMS ink‐jet printer heads and the formation of photosensors and impedance sensors for optical and electronic input, which can be used not only in displays and lab‐on‐chip, but also for new applications such as fingerprint sensing and particle counting.     

Multi-modality imagery database for plant phenotyping

Among many applications of machine vision, plant image analysis has recently began to gain more attention due to its potential impact on plant visual phenotyping, particularly in understanding plant growth, assessing the quality/performance of crop plants, and improving crop yield. Despite its importance, the lack of publicly available research databases containing plant imagery has substantially hindered the advancement of plant image analysis. To alleviate this issue, this paper presents a new multi-modality plant imagery database named “MSU-PID,” with two distinct properties. First, MSU-PID is captured using four types of imaging sensors, fluorescence, infrared, RGB color, and depth. Second, the imaging setup and the variety of manual labels allow MSU-PID to be suitable for a diverse set of plant image analysis applications, such as leaf segmentation, leaf counting, leaf alignment, and leaf tracking. We provide detailed information on the plants, imaging sensors, calibration, labeling, and baseline performances of this new database.