基于IABC-SVR算法的拉曼光谱定量分析山羊血清蛋白含量

提出了一种基于拉曼光谱和改进人工蜂群算法优化支持向量机回归(IABC-SVR)算法快速定量检测山羊血清蛋白含量的方法.传统人工蜂群算法在数据区域规模较大时,收敛速度逐渐减慢,出现效率低、精准度下降、局部最优解概率高等问题.所提出的算法解决了这些问题,使算法在进化前期避免陷入局部最优解,在进化中后期能够保持解的全局搜索能...     

神经网络量子态及其应用

神经网络量子态是由人工神经网络所表示的量子态。得益于机器学习,尤其是深度学习近年来取得的突破性进展,神经网络量子态的研究得到了广泛的关注,成为当前的热点前沿方向。文章将介绍不同的神经网络量子态,其物理性质与典型应用场景,最新进展,以及面临的挑战。     

具有感存算一体化的新型神经形态视觉传感器

传统的数字图像处理系统包括图像传感器与图像处理单元,二者在物理空间上分离,图像信息在其间的传输造成了延时与能耗。此外,数字图像传感器基于“帧”的工作原理,可能丢失一些重要信息,或者造成数据冗余。人类视觉系统提供了一种高效并行的信息处理方式。神经形态视觉传感器能够模拟人类视网膜的功能,同时具备感知光信号、存储信号和进行信息预处理的功能。这类感存算一体化的神经形态视觉传感器简化了人工视觉系统的电路复杂性,提升了信息处理效率,节省了系统功耗。文章总结了传统的数字图像传感器存在的问题,介绍了几种重要的人工神经网络,讨论了新型神经形态视觉传感器的研究进展和存在的问题。     

基于原子操纵技术的人工量子结构研究

扫描隧道显微镜原子操纵技术是指利用扫描探针在特定材料表面以晶格为步长搬运单个原子或分子的技术.它是纳米尺度量子物理与器件研究领域一种独特而有力的研究手段.利用这种手段,人们能够以原子或分子为单元构筑某些常规生长或微加工方法难以制备的人工量子结构,通过对格点原子、晶格尺寸、对称性、周期性的高度控制,实现对局域电子态、自旋序、以及能带拓扑特性等量子效应的设计与调控.原子操纵技术与超快测量及自动控制技术的结合,使得人们能够进一步研究原子级精准的量子器件,因而该技术成为探索未来器件新机理、新工艺的重要工具.本文首先简介原子操纵方法的发展过程和技术要点,然后分别介绍人工电子晶格、半导体表面人工量子点、磁性人工量子结构、人工结构中的信息存储与逻辑运算、单原子精度原型器件等方面的最新研究进展,以及单原子刻蚀和自动原子操纵等方面的技术进展,最后总结并展望原子操纵技术的应用前景和发展趋势.     

Brain-like synaptic memristor based on lithium-doped silicate for neuromorphic computing

Artificial synapse is one of the potential electronics for constructing neural network hardware. In this work, Pt/LiSiO_x/TiN analog artificial synapse memristor is designed and investigated. With the increase of compliance current (C. C.) under 0.6 mA, 1 mA, and 3 mA, the current in the high resistance state (HRS) presents an increasing variation, which indicates lithium ions participates in the operation process for Pt/LiSiO_x/TiN memristor. Moreover, depending on the movement of lithium ions in the functional layer, the memristor illustrates excellent conduction modulation property, so the long-term potentiation (LTP) or depression (LTD) and paired-pulse facilitation (PPF) synaptic functions are successfully achieved. The neural network simulation for pattern recognition is proposed with the recognition accuracy of 91.4%. These findings suggest the potential application of the LiSiO_x memristor in the neuromorphic computing.     

用自适应谐振网络进行图像纹理的分类与识别

分析了自适应谐振（ＡＲＴ２）神经网络模型的模式分类能力，并利用该网络来进行图像纹理的分类和识别，对６类自然景物的纹理图片分类和识别的结果验证了方法的有效性，对心脏超声图片的分类也取得一些初步成果．     

人工神经网络应用于维生素B族4组分同时测定

应用人工神经网络原理，采用Levenberg-Marquardt BP算法，对于吸收光谱严重重叠的维生素B1，B2，B6和烟酰胺4组分同时进行含量测定。四者的平均回收率分别为100％，98％，96％，100％。该方法用于复合维生素B片剂中B1，B2，B6和烟酰胺的同时测定，获得较满意的结果。实验表明，该方法与现有的算法相比具有训练速度快、预测结果准确度高等特点，有望能成为多组分分析的有效方法之一。     

基于光谱和神经网络模型的作物与杂草识别方法研究

利用光谱技术来识别作物与杂草是精细农业中一个非常重要的研究内容,但光谱数据中含有大量冗余数据,如何预处理以及建立识别模型,是决定识别准确率的关键。利用在325～1 075 nm波段的光谱识别了三种杂草（牛筋草、凹头苋、空心莲子草）与大豆幼苗。在幼苗生长的第三周与第六周分别采集杂草与作物的光谱,共378个样本。用其中的250个光谱样本,包括第一期和第二期采集的光谱样本,在采用db12小波经过三层分解后,将其小波系数作为输入数据建模,构造了一个径向基函数神经网络。然后,利用余下的光谱样本检验该模型的识别能力。结果表明,该模型对作物与杂草光谱具有极强的识别能力,只有3个第二期的牛筋草样本被判断为空心莲子草,其余的样本全部正确识别。这个结果表明,采用可见/近红外光谱识别大豆幼苗与三种伴随生长的杂草是可行的,同时也说明,随着作物的生长阶段的不同,其光谱的变化不会影响到种类识别。     

Modern methods of improving the range accuracy of CTFM sonars

In a CTFM (continuous transmission frequency modulated) sonar, the error in range measurement is usually dominated by the low resolution of the range coding frequency of the system. Modern real time spectrum analysers using 1024 point DFTs (discrete Fourier transforms) can display the range codes of the sonar at a resolution approximately equal to 0.2%. To produce a range code accurate to half of the resolution, the linearity of the CTFM sweep must, however, be kept as low as 0.01%. This requirement creates several difficulties in the design of the frequency sweep when both non-linearity and stability of the voltage-controlled oscillator (VCO) and of the controlling voltage ramp are to be considered. A practical approach for achieving the above specifications is described. Properties of electronic components and of state of the art devices and the restrictions of their operating conditions are discussed. Illustrations are given for two measuring instruments: an underwater sonar system for quantitative assessment of fish population, and a diagnostic sonar.     

Modeling the Effect of Injection Molding Process Parameters on Warpage Using Neural Network Theory

A back propagation artificial neural network (BPANN) prediction model for warpage of injection-molded polypropylene was developed based on an orthogonal design method. The BPANN model was trained by the input and output data obtained from the moldflow software platform simulations. It is proved that the BPANN model can predict the warpage with reasonable accuracy. Utilizing the BPANN model, the effects of the process parameters, packing pressure (Pp), melt temperature (T_me), mold temperature (T_mo), packing time (t_p), cooling time (t_c), and fill pressure (p_f), on the warpage were investigated. The most important process parameter affecting the warpage was Pp, and the second most important was T_me. The rest of the process parameters, T_mo, t_p, t_c, and p_f, were found to be relatively less influential. Warpage increased with elevating T_mo. In contrast, an increase in Pp and T_me caused the warpage to decrease.