一种概率过程神经元网络模型及分类算法

针对动态信号分类及与先验类别知识融合问题,提出了一种概率过程神经元网络模型．模型将贝叶斯概率分类机制与过程神经元网络动态信号处理方法相结合,通过在前馈过程神经元网络中增加一个模式单元层,以及采用归一化指数类型激励函数,实现基于贝叶斯规则的动态信号分类．分析了概率过程神经元网络分类机制与贝叶斯分类规则的等价性,给出了具体的学习算法,实验结果验证了模型和算法的有效性．     

一种深度小波过程神经网络及在时变信号分类中的应用

针对多通道非线性时变信号分类问题,提出一种基于稀疏自编码器的深度小波过程神经网络(SAE-DWPNN)。通过构建一种多输入/多输出的小波过程神经网络(WPNN),实现对时变信号的多尺度分解和对过程分布特征的初步提取;通过在WPNN隐层之后叠加一个SAE深度网络,对所提取的信号特征进行高层次的综合和表示,并基于softmax分类器实现对时变信号的分类。SAE-DWPNN将现有过程神经网络扩展为深度结构,同时将深度SAE网络在信息处理机制上扩展到时间域,扩展了两类模型的信息处理能力。该网络可提取多通道时序信号的分布特征及其结构特征,并保持样本特征的多样性,提高了对信号时频特性和结构特征的分析能力。文中分析了SAE-DWPNN的性质,给出了综合训练算法。以基于12导联ECG信号的7种心血管疾病分类诊断为例,实验结果验证了模型和算法的有效性。     

一种基于过程神经元网络的非线性动态系统辨识模型及应用

针对复杂非线性动态系统辨识问题,提出了一种基于过程神经元网络（PNN）的辨识模型和方法．根 据系统待辨识的模型结构和反映系统模态变化特征的动态样本数据,利用PNN 对时变输入／输出信号的非线性变 换机制和自适应学习能力,建立基于PNN 的系统辨识模型．辨识模型能够同时反映多输入时变信号的空间加权聚 合以及阶段时间效应累积结果,直接实现非线性系统输入／输出之间的动态映射关系．文中构建了用于并联结构和 串－并联结构辨识的PNN 模型,给出了相应的学习算法和实现机制,实验结果验证了模型和算法的有效性．     

基于过程神经元网络的动态预测模型及其应用

〗针对动态系统过程预测预报问题，提出了一种基于过程神经元网络的动态预测方法．过程神经元网络的输入/输出均可以是时变函数，其时空聚合运算和激励可同时反映时变输入信号的空间聚合作用和输入过程中的阶段时间累积效应．基于过程神经元网络的动态预测模型能同时满足对系统的非线性辨识和过程预测，在机制上对动态预测预报问题有较好的适应性．文中给出了基于函数基展开和梯度下降法的学习算法，以电力负荷预报为例验证了模型和算法的有效性．     

一种分式过程神经元网络及其应用研究

针对带有奇异值复杂时变信号的模式分类和系统建模问题,提出了一种分式过程神经元网络.该模型是基于有理式函数具有的对复杂过程信号的逼近性质和过程神经元网络对时变信息的非线性变换机制构建的,其基本信息处理单元由两个过程神经元成对偶组成,逻辑上构成一个分式过程神经元,是人工神经网络在结构和信息处理机制上的一种扩展.分析了分式过程神经元网络的连续性和泛函数逼近能力,给出了基于函数正交基展开的学习算法.实验结果表明,分式过程神经元网络对于带有奇异值时变函数样本的学习性质和泛化性质要优于BP网络和一般过程神经元网络,网络隐层数和节点数可较大减少,且算法的学习性质与传统BP算法相同.     

一类反馈过程神经元网络模型及学习算法研究

提出了一种带有反馈输入的过程式神经元网络模型,模型为三层结构,其隐层和输出层均为过程神经元。输入层完成连续信号的输入,隐层完成输入信号的空间聚合和向输出层逐点映射,并将输出信号逐点反馈到输入层;输出层完成隐层输出信号的时、空聚合运算和系统输出。在对权函数实施正交基展开的基础上给出了该模型的学习算法。仿真实验证明了该模型的有效性和可行性。     

一种级联过程神经元网络及其应用研究

针对连续系统输入过程可分为若干时间阶段,输出为一个即依赖于当前阶段系统过程输入,又与前一阶段系统状态有关的离散过程,提出了一种级联过程神经元网络模型.将连续输入信号分阶段处理,不同阶段系统输入输出映射关系用不同过程子网络描述.考虑过程神经元网络计算的复杂性,提出了一种基于函数正交基展开的学习方法,利用基函数的正交性,简化计算过程.文中给出了学习算法,并以油藏开发三次采油过程模拟为例验证了模型和算法的有效性.     

分式过程神经元网络在网络流量预测中的应用

为更好解决网络流量预测问题,依据函数逼近论中分式的函数逼近性质和拟合能力要远远大于线性函数的性质,以及过程神经元网络对时变函数的非线性变换能力,提出一种分式过程神经元网络模型及其学习算法。实验结果证明,该网络模型对具有奇异值过程函数的柔韧逼近性质和在奇异值点附近区域反应的灵敏性优于一般过程神经元网络,以网络实测数据对模型进行训练和流量预测,取得了较好的应用效果。     

一类反馈过程神经元网络模型及其学校算法

提出了一种基于权函数基展开的反馈过程神经元网络模型．该模型为三层结构,由输入层、过程神经元隐层和过程神经元输出层组成．输入层完成系统时变过程信号的输入及隐层过程神经元输出信号向系统的反馈;过程神经元隐层用于完成输入信号的空间加权聚合和激励运算,同时将输出信号传输到输出层并加权反馈到输入层;输出层完成隐层输出信号的空间加权聚集和对时间的聚合运算以及系统输出．文中给出了学习算法,并以旋转机械故障自动诊断问题为例验证了模型和算法的有效性．     

一种时变输入输出过程神经元网络及学习算法研究

针对输入／输出均为时变函数的非线性系统建模问题,提出一种时变输入输出过程神经元网络模型,并给出了具体的学习算法．过程神经元网络的输入、输出均可为时变函数,其空间、时间聚合算子分别取为空间加权求和及含时间变参积分,聚合运算和激励能同时反映时变输入信号的空间聚合作用和输入过程中的阶段时间累积效应．仿真实验结果验证了所提出模型和算法的有效性．     

Wavelet networks for sensor signal classification in flank wear assessment

It is known that the force and vibration sensor signals in a turning process are sensitive to the gradually increasing flank wear. Based on this fact, this paper investigates a flank wear assessment technique in turning through force and vibration signals. Mainly to reduce the computational burden associated with the existing sensor-based methods for flank wear assessment, a so-called wavelet network is investigated. The basic idea in this new method is to optimize simultaneously the wavelet parameters (that represent signal features) and the signal-interpretation parameters (that are equivalent to neural network weights) to eliminate the feature extraction phase without increasing the computational complexity of the neural network. A neural network architecture similar to a standard one-hidden-layer feedforward neural network is used to relate sensor signal measurements to flank wear classes. A novel training algorithm for such a network is developed. The performance of this n ew method is compared with a previously developed flank wear assessment method which uses a separate feature extraction step. The proposed wavelet network can also be useful for developing signal interpretation schemes for manufacturing process monitoring, critical component monitoring, and product quality monitoring.     

On the use of convolutional neural networks for robust classification of multiple fingerprint captures

Fingerprint classification is one of the most common approaches to accelerate the identification in large databases of fingerprints. Fingerprints are grouped into disjoint classes, so that an input fingerprint is compared only with those belonging to the predicted class, reducing the penetration rate of the search. The classification procedure usually starts by the extraction of features from the fingerprint image, frequently based on visual characteristics. In this work, we propose an approach to fingerprint classification using convolutional neural networks, which avoid the necessity of an explicit feature extraction process by incorporating the image processing within the training of the classifier. Furthermore, such an approach is able to predict a class even for low‐quality fingerprints that are rejected by commonly used algorithms, such as FingerCode. The study gives special importance to the robustness of the classification for different impressions of the same fingerprint, aiming to minimize the penetration in the database. In our experiments, convolutional neural networks yielded better accuracy and penetration rate than state‐of‐the‐art classifiers based on explicit feature extraction. The tested networks also improved on the runtime, as a result of the joint optimization of both feature extraction and classification.     

基于样条插值函数的离散过程神经网络训练*

为解决过程神经元网络不能直接输入离散样本的问题,提出基于样条插值函数的离散过程神经网络训练算法。首先,将离散过程样本按采样点分段,在采样区间内分别构造样本和权值的分段样条函数;然后,计算样本函数和权函数的乘积在采样区间上的积分,并将此积分值提交给网络的隐层过程神经元;最后,在输出层计算网络输出。分别采用一次、二次、三次样条函数,设计了三种不同的算法。实验结果表明：一次样条计算效率高,逼近能力差;三次样条计算效率低,但逼近能力好;二次样条在计算效率和逼近能力两方面都比较理想。因此,二次样条函数是离散过程神经网络的较好选择。     

基于改进的卷积神经网络的中文情感分类

探究了基于卷积神经网络的句子级别的中文文本情感分类,模型以文本经过预处理后得到的词向量作为输入。传统的卷积神经网络是由线性卷积层、池化层和全连接层堆叠起来的,提出以跨通道卷积层替代传统线性卷积滤波器,对基本的卷积神经网络进行改进,提高网络的表达能力。实验表明,改进后的卷积神经网络在保证训练速度的情况下,识别率达到91.89%,优于传统的卷积神经网络,有较好的识别能力。     

压缩感知与动态纹理模型的视频信号分类

针对视频数据的动态纹理特性,提出结合视频压缩感知技术,首先通过压缩采样技术对视频数据进行采样,得到少量的采样数据;然后建立线性动态系统模型,通过少量的压缩采样数据直接估计出模型参数;最后通过计算模型间的马氏距离实现动态纹理视频数据的分类。实验结果表明,提出的压缩感知参数估计方法在20%的低采样率情况下,对交通视频数据的分类正确率达到87%以上。     

反馈神经网络用于多输入输出动态系统建模

使用前馈神经网络对多输入输出动态系统建模有很多不足之处.反馈神经网络具有动态特性,拥有记忆环节,对多输入输出的动态模型进行建模,克服了前馈神经网络只能反应静态映射的缺点,反馈神经网络能够反应出多输入输出的动态过程,并且有非常高的稳定性,能够过滤外界干扰信号,精度高.利用反馈神经网络对电炉进行辨识,取得了良好的效果.     

Continuous process control using neural networks

We present some adaptive control strategies based on neural networks that can be used for designing controllers for continuous process control problems. Specifically, a learning algorithm has been formulated based on reinforcement learning, a weakly supervised learning technique, to solve set-point control and control scheduling for continuous processes where the process cannot be modeled easily. It is shown how reinforcement learning can be used to learn the control strategy adaptively based on exploration of the control space without making assumptions about the process model. A new learning scheme, handicapped learning, was developed to learn a control schedule that specifies a schedule of set points. Applications studied include the control of a nonisothermal continuously stirred tank reactor at its unstable state and the learning of the daily time-temperature schedule for an environment controller. Experimental results demonstrate good learning performance, indicating that the learning algorithm can be used for solving transient startup and boundary value control problems.     

正交信号校正的自回归模型及其在动态过程监测中的应用

针对采样数据的自相关性, 提出一种基于自回归(AR) 模型的动态过程建模方法. 首先, 利用正交信号校正(OSC) 消除用于AR模型回归的两数据集间的正交不相关信号; 然后, 在处理过的数据上进行偏最小二乘(PLS) 回归建模. 该方法对模型潜隐成分和残差信息同时进行在线监测, 并借鉴贝叶斯推理方法将多个监测指标进行融合, 以易化触发故障警报的决策过程. 最后通过在田纳西-伊斯曼(Tennessee Eastman, TE) 过程上的仿真实验验证了所提出方法的有效性.

     

Multi-class pattern classification using neural networks

Multi-class pattern classification has many applications including text document classification, speech recognition, object recognition, etc. Multi-class pattern classification using neural networks is not a trivial extension from two-class neural networks. This paper presents a comprehensive and competitive study in multi-class neural learning with focuses on issues including neural network architecture, encoding schemes, training methodology and training time complexity. Our study includes multi-class pattern classification using either a system of multiple neural networks or a single neural network, and modeling pattern classes using one-against-all, one-against-one, one-against-higher-order, and P-against-Q. We also discuss implementations of these approaches and analyze training time complexity associated with each approach. We evaluate six different neural network system architectures for multi-class pattern classification along the dimensions of imbalanced data, large number of pattern classes, large vs. small training data through experiments conducted on well-known benchmark data.     

Classical and superposed learning for quantum weightless neural networks

A supervised learning algorithm for quantum neural networks (QNN) based on a novel quantum neuron node implemented as a very simple quantum circuit is proposed and investigated. In contrast to the QNN published in the literature, the proposed model can perform both quantum learning and simulate the classical models. This is partly due to the neural model used elsewhere which has weights and non-linear activations functions. Here a quantum weightless neural network model is proposed as a quantisation of the classical weightless neural networks (WNN). The theoretical and practical results on WNN can be inherited by these quantum weightless neural networks (qWNN). In the quantum learning algorithm proposed here patterns of the training set are presented concurrently in superposition. This superposition-based learning algorithm (SLA) has computational cost polynomial on the number of patterns in the training set.