Artificial convolution neural network techniques and applications for lung nodule detection

We have developed a double-matching method and an artificial visual neural network technique for lung nodule detection. This neural network technique is generally applicable to the recognition of medical image pattern in gray scale imaging. The structure of the artificial neural net is a simplified network structure of human vision. The fundamental operation of the artificial neural network is local two-dimensional convolution rather than full connection with weighted multiplication. Weighting coefficients of the convolution kernels are formed by the neural network through backpropagated training. In addition, we modeled radiologists' reading procedures in order to instruct the artificial neural network to recognize the image patterns predefined and those of interest to experts in radiology. We have tested this method for lung nodule detection. The performance studies have shown the potential use of this technique in a clinical setting. This program first performed an initial nodule search with high sensitivity in detecting round objects using a sphere template double-matching technique. The artificial convolution neural network acted as a final classifier to determine whether the suspected image block contains a lung nodule. The total processing time for the automatic detection of lung nodules using both prescan and convolution neural network evaluation was about 15 seconds in a DEC Alpha workstation.     

基于人工神经网络下的图像识别的研究

主要利用人工神经网络的理论知识研究在图像识别中的应用为目的,研究图像识别中图像分割的技术,同时详细分析了多层前馈神经网络的描述及BP算法工作过程。介绍隐层的选择及隐层神经元数选择的一些经验方法。针对BP算法存在的问题,提出加可变动量因子的BP算法,通过对网络训练过程参数调整以及增加可变动量因子等方面进行优化改进,实验证明加快了训练速度,改善了BP网络的学习效果。     

Optoelectronic Detecting System for Inner Walls of Pipes

This paper is concerned with a high characteristic image processing and recognition system that is used for inspecting real-time blemishes,streaks and cracks on the inner walls of high accuracy pipes .As a regular detector,the BP neural network is used for extracting features of the image inspected and classifying these images,it takes fully advantage of the function of artificial neural network ,such as the information distributed memory, large scale self-adapting parallel processing ,high fault-tolerant ability and so forth.Besides , an improved BP algorithm is used in the system for training the network ,and making the learning procedure of the net converges to the minimum of overall situation at high rate.     

Linear and non‐linear space diversity combining algorithms over fading channels in TDMA systems

This paper investigates the performances of various adaptive algorithms for space diversity combining in time division multiple access (TDMA) digital cellular mobile radio systems. Two linear adaptive algorithms are investigated, the least mean square (LMS) and the square root Kalman (SRK) algorithm. These algorithms are based on the minimization of the mean‐square error. However, the optimal performance can only be obtained using algorithms satisfying the minimum bit error rate (BER) criterion. This criterion can be satisfied using non‐linear signal processing techniques such as artificial neural networks. An artificial neural network combiner model is developed, based on the recurrent neural network (RNN) structure, trained using the real‐time recurrent learning (RTRL) algorithm. It is shown that, for channels characterized by Rician fading, the artificial neural network combiners based on the RNN structure are able to provide significant improvements in the BER performance in comparison with the linear techniques. In particular, improvements are evident in time‐varying channels dominated by inter‐symbol interference. Copyright © 2001 John Wiley & Sons, Ltd.     

一种复值函数型连接神经网络

本文提出了一种复值函数型连接神经网络(CFLNN)结构,可以对复数域信号进行快速处理。函数型连接神经网络通过对输入模式预先进行非线性扩展,增强了输入信号的模式表达,从而可以大为简化网络结构,降低计算复杂度。本文将函数型连接神经网络推广到了复值情况并给出了基于梯度下降的学习方法。计算复杂度分析显示本方法具有结构简单,计算量低的优点。最后,将本方法运用到对复值非线性系统的辩识问题中,仿真实验表明本CFLNN性能与传统复值前馈神经网络相近或更优。     

Statistical Evaluation of Pruning Methods Applied in Hidden Neurons of the MLP Neural Network

There are several papers on pruning methods in the artificial neural networks area. However, with rare exceptions, none of them presents an appropriate statistical evaluation of such methods. In this article, we proved statistically the ability of some methods to reduce the number of neurons of the hidden layer of a multilayer perceptron neural network (MLP), and to maintain the same landing of classification error of the initial net. They are evaluated seven pruning methods. The experimental investigation was accomplished on five groups of generated data and in two groups of real data. Three variables were accompanied in the study: apparent classification error rate in the test group (REA); number of hidden neurons, obtained after the application of the pruning method; and number of training/retraining epochs, to evaluate the computational effort. The non-parametric Friedman’s test was used to do the statistical analysis.     

基于多任务卷积神经网络的人脸识别技术研究

深度神经网络是目前计算机机器学习领域的一个关键技术,可应用于图像处理。其中,多任务卷积神经网络(Multi-task Convolutional Neural Network,MTCNN)是一种基于卷积神经网络的多任务人脸检测框架,这里采用MTCNN人脸检测模型代替传统的卷积神经网络,在深度学习框架TensorFlow上进行人脸识别。首先,在数据预处理阶段利用灰度化方法将图像集转变为灰度图,降低图像通道。其次,基于MTCNN构建人脸检测模型,并利用Softmax函数进行分类识别。最后,实验过程中选择不同迭代次数进行准确性对比,在模型趋于稳定的情况下,得到较高的准确性。     

基于计算智能的信息处理技术的研究与应用

计算智能是人工智能的重要分支,以数据为基础,主要借鉴连接主义和行为主义的思想,基于生物进化和细胞网络等机制,具有分布、并行、自适应、自组织和自学习等特点.首先介绍了计算智能的起源和概念,然后以人工神经网络、遗传算法、蚁群算法为例阐述了其原理和应用,最后介绍了在新技术条件下,计算智能的发展趋势及有待解决的一些问题.     

改进神经网络的图像识别系统设计与硬件实现

针对现有图像识别系统大多采用软件实现,无法利用神经网络并行计算能力的问题。该文提出一套基于FPGA的改进RBF神经网络硬件化图像识别系统,将乘法运算改为加法运算解决了神经网络计算复杂不便于硬件化的问题,并且提出一种基于位比较的排序电路解决了大量数据的快速排序问题,以此为基础开发了多目标图像识别应用系统。系统特征提取部分采用FPGA实现,图像识别部分采用ASIC电路实现。实验结果表明,该文所提出的改进RBF神经网络算法平均识别时间较LeNet-5, AlexNet和VGG16缩短50%;所开发的硬件系统完成对10000张样本图片识别的时间为165 μs,对比于DSP芯片系统所需426.6 μs,减少了60%左右。     

极端学习机在立体图像质量客观评价中的应用

基于传统神经网络训练速度慢、易陷入局部极小值和泛化性能低等问题,提出采用极端学习机(ELM,extreme learning machine)对立体图像质量进行了客观评价。ELM是单隐层前馈神经网络(SLFNs)的泛化,输入权重可以随机赋值并通过解析获得输出权值。与传统神经网络算法相比,ELM算法具有参数选择简单、学习速度快及泛化性能好等优点。实验结果表明,以sigmoid为激励函数,对241幅不同等级的立体图像测试样本进行测试,其正确等级分类率达到93.85%。研究了不同激励函数条件下不同隐藏层节点数对极端学习机网络性能的影响,且将ELM和传统BP及支持向量机(SVM)在立体图像质量评价中的性能进行了分析比较。     

An artificial neural network for SPECT image reconstruction

An artificial neural network has been developed to reconstruct quantitative single photon emission computed tomographic (SPECT) images. The network is trained with an ideal projection-image pair to learn a shift-invariant weighting (filter) for the projections. Once trained, the network produces weighted projections as a hidden layer when acquired projection data are presented to its input. This hidden layer is then backprojected to form an image as the network output. The learning algorithm adjusts the weighting coefficients using a backpropagation algorithm which minimizes the mean squared error between the ideal training image and the reconstructed training image. The response of the trained network to an impulse projection resembles the ramp filter typically used with backprojection, and reconstructed images are similar to filtered backprojection images.     

基于ANN和残差修正的电力系统短期负荷预测

提出了一种人工神经网络与灰色理论模型相结合的综合预测方法。在神经网络结构设计中分别选取带有横向和纵向特征的负荷作为输入，并充分考虑气候敏感因素及特殊负荷日的影响。在分析预测差值的基础上，将灰色理论残差校正模型运用到预测结果的修正当中去。算例表明所提出的方法提高了预测精度。     

Introduction to the modified probabilistic neural network forgeneral signal processing applications

This paper introduces a practical and easy-to-understand network for signal processing called the modified probabilistic neural network (MPNN). It begins with a short introduction to the application of artificial neural networks to signal processing followed by a background and review of the MPNN theory. The MPNN is a regression technique similar to Specht's (1991) general regression neural network, which is based on a single radial basis function kernel whose bandwidth is related to the noise statistics. It has advantages in application to time and spatial series signal processing problems because it is constructed directly and simply from the training signal waveform characteristics or features. An illustrative example involving noisy Doppler-shifted swept frequency sonar signal detection compares the effectiveness of the first- and second-order Volterra, multilayer perceptron neural network, radial basis function neural network, general regression neural network and MPNN filters, demonstrating some features of the MPNN for practical design     

关于稀疏编码理论及其应用

稀疏编码的概念源于视神经网络的研究,是对只有一小部分神经元同时处于活跃状态的多维数据的神经网络的表示方法。稀疏编码理论在视神经细胞的响应特性和外部环境刺激的统计特性之间建立一种科学的数量联系,逐渐成为了一种有效理解人类神经系统信息加工机制的理论工具,在盲源信号分离、语音信号处理、图像特征提取、自然图像去噪、以及模式识别等方面取得了许多成果,具有重要的实用价值。     

用HDL语言描述和模拟图像二值化神经网络

神经网络专用电路实现是目前神经网络实现研究的主要方向。本文基于我们所提出的数字式细胞神经网络．针对它在数字图像二值化中的应用，采用硬件描述语言对这个专用电路进行描述和模拟。在系统设计中，采用了微程序控制方法和流水线技术。仿真结果表明了硬件实现算法的正确性和可行性，同时也为神经网络的实现打下了良好的基础。     

基于神经网络的图像识别

神经网络图像识别技术是随着当代计算机技术、图像处理、人工智能、模式识别理论等发展起来的一种新型图像识别技术。在进行图像识别之前需要利用数字图像处理技术进行图像预处理以及特征提取。本文选取字符图像0~9作为识别目标,对图像预处理过程进行了叙述,并在此基础上选取字符图像矩阵每行的与每列的黑色像素点之和以及图像欧拉数这两个特征作为BP神经网络的输入样本。经实验仿真表明图像的平均识别率为89%,这表明图像预处理的结果和提取的特征是合适的、有效的,设计的BP网络也较好的完成了模式分类识别工作。     

数据挖掘技术在建模、优化和故障诊断中的应用

数据挖掘技术是当今智能系统理论的重要研究内容,它综合运用人工智能、计算智能（人工神经网、遗传算法）、模式识别、数理统计等先进技术从大量数据中挖掘和发现有价值和隐含的知识。文中介绍数据挖掘技术的原理以及在建模、优化和故障诊断中的应用和,包括：基于遗传算法的模糊规则生成,基于粗糙集的规则挖掘和基于混合模型的邦联建模。     

BP神经网络的发展现状综述

讨论目前人工神经网络领域中BP神经网络的特点、改进算法以及在实际中的应用。主要包括模式识别及分类、故障智能诊断、图像处理、函数拟合、最优预测等方面的应用。最后对目前人工神经网络的存在问题和发展前景做了初步探讨。     

人体头发中重金属元素铬含量的高光谱检测

头发中的重金属含量可以反映出人体健康的变化。提出了运用高光谱数据检测头发中重金属元素铬含量的方法。对头发的透射率波长曲线进行了包络线消除、吸收特征参量化等处理。以化学检测的铬含量作为标准数据,化学检测精度可达90%以上。然后训练人工神经网络,通过调节网络的隐含层层数、结点数和激活函数来优化模型。实验计算表明,隐含层层数为1,结点数为7或9的人工神经网络的预测效果较好。利用统计实验结果对人工神经网络的内部精度和外部精度进行评价。人体头发中铬的敏感波段为1380 nm～1550 nm、1880 nm～2100 nm、2120 nm～2210 nm;训练后的神经网络预测的均方根误差为13%,精度达87%。实验结果表明,应用高光谱技术可以快速无损地检测人体头发中的重金属元素铬的含量。     

Using deep learning for detecting BotCloud

The differences of the basic network flow characteristics between BotCloud and normal cloud services were not obvious, and this led to the inefficiency of the method in BotCloud detection based on network flow characteristics analysis. To solve this problem, a CNN(convolution neural network)-based method for detecting the BotCloud was pro-posed. First, it extracted the basic network flow characteristics from network flow data packets. Second, it mapped the basic network flow characteristics into gray image. Finally, in order to detect BotCloud, it utilized CNN algorithm to learn and extract characteristics that were more abstract to express the hidden model and structural relationship in the network data flow. The experimental results show that the proposed method can not only enhance the accuracy of detec-tion, but also greatly reduce the time required for detecting.