基于神经网络的水果识别系统设计

人工智能的时代给我们的日常生活带来了极大便利,水果作为生活中的必要品,每天食用适量的水果可以补充维生素C,对我们的身体健康十分有益,有关于对水果识别的研究就显得十分必要。在对水果进行识别时,通过针对不同水果的形状、大小、颜色、纹理等特征进行分析,根据训练BP神经网络达到对水果准确识别的目的。     

基于汽车领域的神经网络动态矩阵的误差补偿控制研究

基于预测控制算法的动态矩阵控制理论,改进得到了算法模型的误差相关矩阵,给出约束多变量DMC模型以及神经网络误差补偿的动态矩阵控制验证,在误差控制仿真验证中,应用神经网络误差补偿的预测控制效果优势明显,这一研究对模糊预测技术的进一步推广应用有一定的促进作用。     

一种速度优化的流水线模数转换电容误差平均技术

无源电容误差平均技术是一种本质线性(Inherently Linear)的流水线模数转换电容失配校准技术,但其转换速度是传统技术的一半.为了提高速度,本文提出了一种改进的电容误差平均技术.该技术从减少一个转换周期所需的时钟相数目和减少每个时钟相的时间两个方面来优化速度.电路分析和MATLAB仿真表明,在两种典型的情况下,改进的技术能将速度提高52%(跨导放大器为开关电容共模反馈)和64%(跨导放大器为非开关电容共模反馈)以上.改进的技术更适用于高速高精度及连续工作的应用场合.     

基于单片机的电路信息实时采集系统设计

为了提高电路信息实时采集的稳定性和可靠性,提出基于STC89C52单片机的电路信息实时采集系统设计方法。构造电路信息实时采集系统的总体结构模型,系统分为继电器模块、单片机控制模块、A/D采样电路模块、输出接口模块等。采用UART循环堆栈控制方法进行信号采样值幅度调整,对采集的实时信号通过放大滤波器输出至A/D转换器,采用单片机进行压控放大控制,输出高、低电压至继电器,实现实时采集信号的存储和放大输出。测试结果表明,信息实时采集系统具有较高的信号输出放大增益,信号输出的收敛性较好。     

无源雷达目标识别的神经网络模型构建

针对当前无源雷达目标识别存在的识别率低和容错性不足等问题,构建了一个基于BP神经网络的目标识别模型。围绕无源雷达目标识别效率提升和智能解决方案的构设问题,梳理总结了神经元原理、常用神经网络结构、激活函数和学习算法,设计了无源雷达目标识别总体流程,具体构建了神经网络目标识别模型,包括网络结构、隐含层节点数确定等,并给出了样本训练、测试和目标识别的工作流程,为无源雷达目标识别提供了方法途径。最后,给出了一个仿真实例,验证了模型的有效性。     

多任务衍射神经网络系统设计与实现

为探索利用衍射神经网络执行多任务图像分类识别的可行性,本文设计并搭建一种衍射神经网络系统。该系统采用空间光调制器（Spatial Light Modulator,SLM）做衍射神经网络的相位及振幅权重的调制以及网络层的光学全连接,并利用CMOS相机实现衍射神经网络中各衍射层输出的光电非线性激活与输出图像识别结果判别。设计的系统模型在MNIST和Fashion-MNIST图像分类识别中正确率达到94.1%和92.1%。最终通过搭建光路系统,光学实验正确率分别为91%和81.7%。所设计的衍射神经网络系统可满足多种图像分类识别应用需求,为衍射网络的设计与构建提供了新的思路。     

基于分解技术的动态结构神经网络

本文提出了基于分解技术的动态结构神经网络算法，这种算法能通过分析网络输入输出了空间的维数，确定每一隐含层神经元数目，为了加快学习效率，采用变误差混学习算法，仿真结果验证了这种算法的有效性。     

应用于模数转换的高精度带隙基准源

设计了一种应用于模数转换的高精度带隙基准电压源和电流源电路,利用温度补偿技术,该电路能分别产生零温度系数的基准电压VREF、零温度系数的基准电流IZTAT。仿真结果显示,采用标准0.18μm CMOS工艺,在室温27℃和2.8 V电源电压的条件下,电路工作频率为10 Hz和1 kHz时,电源抑制比(PSRR)分别为–107 dB和–69 dB,VREF及IZTAT的温度系数分别是20.6×10–6/℃和40.3×10–6/℃,功耗为238μW,可在2.4~3.6 V电源电压范围内正常工作。     

基于OpenCV的图形识别系统设计

有效识别图形是推进智能系统研究的重要环节,一些学者通过编程工具调用Open CV视觉库来对基本几何图形的形状和颜色进行识别,这些研究可以被应用到实际生活当中,如识别车牌、识别交通信号灯甚至其他需要图形识别的领域。利用Open CV对图形的识别流程主要包括对图形预处理、颜色提取、对图形进行滤波、分割、灰度、二值化、拟合等深处理,从而对三角形、方形等多边形以及圆形等不同形状图形的轮廓、颜色进行有效识别。结合Open CV对图形识别流程,设计图形识别系统,从而在现有研究的基础上提升Open CV视觉库对图形识别的效果。     

校园建设中基于卷积神经网络的人像识别系统设计

本文对校园建设中基于卷积神经网络的人像识别系统设计进行研究。现阶段,随着计算机技术以及机器学习技术的发展和进步,当前卷积神经网络以及人脸识别系统逐渐走向大众的视野,也逐渐成为研究人员重点研究内容和关注对象。当前建设智慧校园的过程中,最为重要的就是人脸识别系统的搭建,为了保证其有效性以及应用质量,可以应用卷积神经网络,其对于图像处理方面可以发挥出最大的作用和价值,可以针对图像进行深层次提取,了解图像特征,因此基于卷积神经网络的智慧校园人脸识别系统设计,具有更好的泛华能力,本文以此为基础,进行深入研究和分析。     

Improved neural networks for analog-to-digital conversion

In this paper we study the problem of designing a neural network that gives the correct binary representation of a given real number. Previously this problem has been studied by Tank and Hopfield. The network proposed by them exhibits hysteresis in the sense that the current vector of the network sometimes converges towards a binary vector that isnot the correct binary representation of the input current. The reason for this is that the network proposed by them has multiple asymptotically stable equilibria. In the present paper, we propose another neural network which has the property that it hasa single, globally attractive equilibrium for almost all values of the input current. Hence, irrespective of the initial conditions of the network, the current vector converges towards the correct binary representation of the input current.     

An efficient background calibration technique for analog-to-digital converters based on neural network

This paper introduces a background digital calibration algorithm based on neural network, which can adaptively calibrate multiple non-ideal factors in a single-channel ADC, such as gain error, mismatch, offset and harmonic distortion. It enables an efficient background calibration through a simple feed forward neural network and LM gradient descent algorithm. The simulation results show that in the case of a signal input close to the Nyquist frequency, for a 14-bit 500 MS/s prototype ADC, only about 40,000 data needed, the ENOB of the ADC can be increased from 7.81 to 13.06 and the SFDR from 49.7 dB to 106.8 dB assisted by a lower speed reference ADC.     

Image source identification with known post-processed based on convolutional neural network

Image source identification is important to verify the origin and authenticity of digital images. However, when images are altered by some post-processing, the performance of the existing source verification methods may degrade. In this paper, we propose a convolutional neural network (CNN) to solve the above problem. Specifically, we present a theoretical framework for different tampering operations, to confirm whether a single operation has affected photo response non-uniformity (PRNU) contained in images. Then, we divide these operations into two categories: non-influential operation and influential operation. Besides, the images altered by the combination of non-influential and influential operations are equal to images that have only undergone a single influential operation. To make our introduced CNN robust to both non-influential operation and influential operation, we define a multi-kernel noise extractor that consists of a high-pass filter and three parallel convolution filters of different sizes. The features generated by the parallel convolution layers are then fed to subsequent convolutional layers for further feature extraction. The experimental results provide the effectiveness of our method.     

A fully automated recurrent neural network for unknown dynamic system identification and control

This paper presents a fully automated recurrent neural network (FARNN) that is capable of self-structuring its network in a minimal representation with satisfactory performance for unknown dynamic system identification and control. A novel recurrent network, consisting of a fully-connected single-layer neural network and a feedback interconnected dynamic network, was developed to describe an unknown dynamic system as a state-space representation. Next, a fully automated construction algorithm was devised to construct a minimal state-space representation with the essential dynamics captured from the input-output measurements of the unknown system. The construction algorithm integrates the methods of minimal model determination, parameter initialization and performance optimization into a systematic framework that totally exempt trial-and-error processes on the selections of network sizes and parameters. Computer simulations on benchmark examples of unknown nonlinear dynamic system identification and control have successfully validated the effectiveness of the proposed FARNN in constructing a parsimonious network with superior performance.     

基于神经网络的实时故障诊断系统设计

本文以某型飞机电力起动系统为对象,介绍了如何将神经网络应用于飞机电力起动系统的故障诊断,较好地解决了利用故障字典法对该系统实施故障诊断时所存在的缺乏自组织、自学习能力和测试信号选取受限等弊端,建立了该系统的故障样本并对其进行了仿真研究。     

基于神经网络的光伏系统MPPT控制算法设计

提出一种基于人工神经网络(ANN)的最大功率点跟踪(MPPT)控制算法。该算法通过扰动和观察(P&O)方法获得人工神经网络模型所需的参数,并分为离线和在线两种模式:离线模式通过测试神经网络参数,找到最佳的网络结构、激活函数和训练算法;在线模式实现优化人工神经网络以便应用于光伏系统。人工神经网络的输入变量为输出功率参数和电压参数,输出变量为归一化的增加或者减少占空比(+1或者-1)。通过Matlab/Simulink模型对所提跟踪算法的性能进行测试验证,结果显示所提算法表现出良好的动态响应速度和稳态控制精度。     

超声成像仪动态滤波器设计

针对超声在人体中传播能量随深度增加而衰减的特点,为了提高图像分辨率,设计了一种应用于超声成像系统中动态滤波器电路。文中给出了滤波器的硬件设计电路图,通过电路测试证明该设计简单可行,对回波信号进行匹配滤波,得到最佳的信噪比,满足系统设计要求。     

High-quality voice conversion system based on GMM statistical parameters and RBF neural network

A voice conversion （VC） system was designed based on Gaussian mixture model （GMM） and radial basis function （RBF） neural network. As a voice conversion model, RBF network needs quantities of training data to improve its performance. For one speech, the networks trained by different segments of data have different transformation effects. Since trying segment by segment to obtain the best conversion effect is complex, a conversion method was proposed, that uses GMM for statistics before training RBF network to aim at the problem. The speech transformation and representation using adaptive interpolation of weighted spectrum （STRAIGHT） model is used for accurate extraction of vocal tract spectrum. Then GMM is used to classify the numerous spectral parameters. The obtained mean parameters were trained in RBF network. Experiment reveals that, the soft classification ability of GMM can promptly realize the reduction and classification of training data under the premise of ensuring the training effect. The selection complexity is decreased thereafter. Compared to the conventional RBF network training methods, this method can make the transformation of spectral parameters more effective and improve the quality of converted speech.     

基于神经网络的假肢无线控制系统的设计

为了改善残疾人生活水平和促进医疗事业发展,提出一种基于神经网络的假肢无线控制系统设计方案。该系统以STM32为核心芯片,通过采集上肢肱二头肌、肱三头肌、指浅屈肌、指伸肌4块肌肉的肌电信号,使用BP神经网络与SOFM神经网络相结合对肌电信号进行模式识别,实时控制肌电假肢的完成伸臂、屈臂、腕内旋、腕外旋、握拳、张手6种动作行为。实验结果表明,该系统对6种动作的整体识别率可达97%,并且采用无线实时的控制方式,能够更方便地帮助部分肢体残疾患者完成这些基本的操作行为。