基于径向基函数网络的非线性通用模型控制

为了克服通用模型控制器要求过程一阶微分模型应该有显式解的局限性，提出了一种基于神经网络的通用模型控制方法，将非线性过程模型应用逆系统的方法在控制算法中直接嵌入过程模型，从而保证通用模型控制策略的可实现性。其参考轨迹是一条典型的二阶曲线，由于径向基函数网络具有许多优点，该控制策略中的神经网络为径向基函数网络。该控制器参数具有明显的物理意义，参数整定方便。仿真实验验证了该控制策略的有效性。     

基于IRBFNN和IRAN的非线性动态系统在线自适应建模

将资源分配网络算法(RAN)与相似隐单元合并操作、冗余隐单元删除操作和基于滑动数据窗连接权值学习相结合,形成了改进的资源分配网络(IRAN)算法。IRAN算法用于非线性动态系统的在线建模,能有效地改善模型精度和泛化能力。将改进径向基函数(RBF)神经网络(IRBFNN)和IRAN结合可以用于不确定非线性动态系统自适应建模。仿真研究表明:所提出的建模方法在模型精简、泛化和自适应等方面均具有优良的性能。     

基于RBF的肾阳虚大鼠甲状腺与性腺功能的动态分析

目的 通过建立肾阳虚大鼠三碘甲腺原氨酸(T3)、甲状腺素(T4)与睾酮(T)的人工神经网络模型,探讨肾阳虚过程中甲状腺与性腺功能的动态关系.方法 肌肉注射氢化可的松复制肾阳虚大鼠模型,分别观察早期、中期和晚期肾阳虚大鼠T3、T4与T等指标,建立T3、T4与T之间的径向基函数网络模型,利用模型分析甲状腺与性腺功能之间的变化规律和特征.结果 肾阳虚网络模型的相对均方误差都在10%以内.结论 径向基函数网络模型能比较准确反映肾阳虚大鼠甲状腺与性腺功能之间复杂的非线性关系.     

基于深度学习方法的精神分裂症听觉稳态诱发电位分析

目的文本旨在使用深度学习方法对精神分裂症建立自动分类模型,为临床上精神分裂症患者的鉴别诊断提供参考。方法通过提取受试听觉稳态诱发电位的能量、相位、信噪比和微分熵作为模型输入特征,使用准确率、灵敏度、特异度和受试工作者特性曲线对深度信念网络和支持向量机构建的模型进行分析和比较。结果深度信念网络模型的准确率、灵敏度、特异度、曲线下面积分别为85.6%、88.33%、75.50%和0.88。深度信念网络模型诊断能力明显高于基于线性核、径向基函数核、sigmoid核的三种支持向量机模型。结论基于深度信念网络算法的诊断模型可以有效协助临床医生对于精神分裂症患者的诊断,达到早期发现疾病的效果。     

基于论文相似网络拓扑结构的聚类方法比较

以R语言中的复杂网络处理包igraph为工具,基于语义相似性算法构建论文相似网络,然后采用四种代表性网络聚类算法（随机游走法、标签传播法、最大模块度法、边介数法）对构建出的网络进行聚类分析。最后结合金标准和网络社团划分评价指标D函数比较四种算法的准确性和稳定性,发现随机游走算法最为卓越,同时明确了复杂网络的预处理也是一个影响聚类效果的重要因素。     

基于递推正交最小二乘的RBF网络结构优化

讨论了次胜者受罚的竞争学习规则,提出了基于最小二乘（OLS）递推算法,采用改进的Givens旋转变换技术避免了大型矩阵的QR分解运算。在满足系统测量精度条件下,使用反向优选算法优化RBF网络结构。仿真结果表明,所得算法能有效地解决网络学习隐层单元的确定需要人介入的问题,适用于非线性系统的建模。     

基于概率裁剪的球形译码算法

在适当的裁剪函数下,基于概率裁剪的球形译码(SPSD)算法能有效逼近最大似然检测(ML)算法性能,但其复杂度在低信噪比下较高。本文重点对SPSD算法的复杂度进行优化,并提出改进算法。改进算法利用迫零检测(ZF)解计算出初始半径,能有效降低球形译码的搜索范围,并优化裁剪函数,在几乎不损失性能的前提下,有效降低算法复杂度。仿真结果表明,在多输入多输出(MIMO)系统中,改进算法能够逼近SPSD算法的性能,并有效减少算法复杂度,能很好地达到检测算法性能和复杂度之间的折中。     

IPCA在故障检测与分离中的应用

针对现有ＢＰ网络在故障诊断中存在的缺陷，提出了利用小波函数构造故障诊断神经元网络，利用变尺度算法进行网络训练，加快了网络的训练速度。并交结果运用到一个ＣＳＴＲ非稳态故障诊断的过程中，仿真实例表明，小波网络较ＢＰ网络具有更好的故障诊断能力。     

基于深度学习技术中医优势病种证候到治法方剂算法模型的构想

目前开展的中医辩证论治信息化研究都只针对"辩证"过程进行探索,而同样重要"论治"过程(即选法定方)的信息化却被相关研究人员所忽略。目前,"论治"过程的研究只是运用浅层算法进行简单关联,推导出结果的准确性难以得到验证。本项目以神经网络作为改进算法的基本架构,采用一种学习深层非线性网络结构,实现复杂函数逼近的深度学习技术与中医的"因位性势"相结合,利用挖掘出的信息建立的数据仓库,训练模型,确定新型算法中更为高效的网络权重。在训练模型的过程中采用具有较强的非线性映射能力、高度自学习和自适应的能力的共轭梯度BP神经网络以反向传播学习算法的方式,从输出层经各中间层逐层修正各连接权值,得出最为优化的网络权重,推荐出准确、合理的治法与方剂。本算法模型探索了中医名老专家选法定方的思维模式,并核查中医生治疗过程是否规范合理,检出误治、失治病例,从而提高临床疗效,使中医治疗过程实现规范化与标准化。     

基于小波网络的非稳态故障诊断方法

针对现有ＢＰ网络在故障诊断中存在的缺陷，提出了利用小波函数构造故障诊断神经元网络，利用变尺度算法进行网络训练，加快了网络的训练速度。并交结果运用到一个ＣＳＴＲ非稳态故障诊断的过程中，仿真实例表明，小波网络较ＢＰ网络具有更好的故障诊断能力。     

Detection of Obstructive Respiratory Abnormality Using Flow–Volume Spirometry and Radial Basis Function Neural Networks

In this work detection of pulmonary abnormalities carried out using flow-volume spirometer and Radial Basis Function Neural Network (RBFNN) is presented. The spirometric data were obtained from adult volunteers (N = 100) with standard recording protocol. The pressure and resistance parameters were derived using the theoretical approximation of the activation function representing pressure–volume relationship of the lung. The pressure–time and resistance–expiration volume curves were obtained during maximum expiration. The derived values together with spirometric data were used for classification of normal and obstructive abnormality using RBFNN. The results revealed that the proposed method is useful for detecting the pulmonary functions into normal and obstructive conditions. RBFNN was found to be effective in differentiating the pulmonary data and it was confirmed by measuring accuracy, sensitivity, specificity and adjusted accuracy. As spirometry still remains central in the observations of pulmonary function abnormalities these studies seems to be clinically relevant.     

深圳市肠道传染病与气象及媒介因素的贝叶斯正规化BP神经网络模型

目的探讨肠道传染病与相关的主要气象指标和媒介生物密度指标的关系,建立深圳市肠道传染病发病率的BP神经网络模型,并评价其拟合效果和预测效果。方法从监测系统收集2000～2005年每月的气象资料、媒介生物监测数据以及肠道传染病疫情数据,利用Stata 8.0对与肠道传染病发病率相关的气象因素及媒介生物因素进行筛选,利用Matlab 7.0软件完成贝叶斯正规化BP神经网络模型的构建、训练及模拟。结果在各种气象因素与媒介生物密度指标中,与肠道传染病发病相关程度较高的指标分别为蟑螂密度、蝇密度、平均气温和雨量。月肠道传染病发病率的回代平均误差率和R2分别为14.9%和0.87。而进行预测时,以月份为单位的肠道传染病发病率预测平均误差率为18.4%,而以年为单位的肠道传染病发病率预测的平均误差率较低,为8.4%。结论肠道传染病伤与气象因素、媒介生物因素之间关系的贝叶斯BP神经网络模型拟合效果较好,预测准确度较高,BP神经网络在传染病发病率预测研究领域具有一定的实用价值。     

A Radial Basis Function Neural Network Model for Classification of Epilepsy Using EEG Signals

Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patient’s epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to evaluate epileptic patients and classify epilepsy groups such as partial and primary generalized epilepsy by using Radial Basis Function Neural Network (RBFNN) and Multilayer Perceptron Neural Network (MLPNNs). Four hundred eighteen patients with epilepsy diagnoses according to International League against Epilepsy (ILAE 1981) were included in this study. The correct classification of this data was performed by two expert neurologists before they were executed by neural networks. The neural networks were trained by the parameters obtained from the EEG signals and clinic properties of the patients. Experimental results show that the predictions of both neural network models are very satisfying for learning data sets. According to test results, RBFNN (total classification accuracy = 95.2%) has classified more successfully when compared with MLPNN (total classification accuracy = 89.2%). These results indicate that RBFNN model may be used in clinical studies as a decision support tool to confirm the classification of epilepsy groups after the model is developed.     

A Radial Basis Function Neural Network (RBFNN) Approach for Structural Classification of Thyroid Diseases

The thyroid is a gland that controls key functions of body. Diseases of the thyroid gland can adversely affect nearly every organ in human body. The correct diagnosis of a patient’s thyroid disease clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. This study investigates Multilayer Perceptron Neural Network (MLPNN) and Radial Basis Function Neural Network (RBFNN) for structural classification of thyroid diseases. A data set for 487 patients having thyroid disease is used to build, train and test the corresponding neural networks. The structural classification of this data set was performed by two expert physicians before the input variables and results were fed into the neural networks. Experimental results show that the predictions of both neural network models are very satisfying for learning data sets. Regarding the evaluation data, the trained RBFNN model outperforms the corresponding MLPNN model. This study demonstrates the strong utility of an artificial neural network model for structural classification of thyroid diseases.     

Neural Network Approaches to Grade Adult Depression

Depression is a common but worrying psychological disorder that adversely affects one's quality of life. It is more ominous to note that its incidence is increasing. On the other hand, screening and grading of depression is still a manual and time consuming process that might be biased. In addition, grades of depression are often determined in continuous ranges, e.g., 'mild to moderate' and 'moderate to severe' instead of making them more discrete as 'mild', 'moderate', and 'severe'. Grading as a continuous range is confusing to the doctors and thus affecting the management plan at large. Given this practical issue, the present paper attempts to differentiate depression grades more accurately using two neural net learning approaches-'supervised', i.e., classification with Back propagation neural network (BPNN) and Adaptive Network-based Fuzzy Inference System (ANFIS) classifiers, and 'unsupervised', i.e., 'clustering' technique with Self-organizing map (SOM), built in MATLAB 7. The reason for using the supervised and unsupervised learning approaches is that, supervised learning depends exclusively on domain knowledge. Supervision may induce biasness and subjectivities related to the decision-making. Finally, the performance of BPNN and ANFIS are compared and discussed. It was observed that ANFIS, being a hybrid system, performed much better compared to the BPNN classifier. On the other hand, SOM-based clustering technique is also found useful in constructing three distinct clusters. It also assists visualizing the multidimensional data clusters into 2-D.     

规范式分段线性化法在非线性电阻网络故障诊断中的应用

本型文针对非线性电阻网络,提出了一种规范式分段线性化求所有解,并采用BPNN对非线性电阻网络硬故障进行诊断的方法,克服了用一般方法对非线性电阻网络故障诊断时易存在的漏诊问题。     

基于支持向量机的化工过程故障诊断

引入了基于统计学习理论的支持向量机技术，以连续搅拌釜式反应器——CSTR模型为例，研究了非线性化工复杂反应过程的故障诊断问题。实验结果表明，支持向量机方法与传统故障诊断方法相比，具有更好的精度、速度以及适应性。     

犬异体单肺移植的实验研究

目的:通过犬异体单肺移植,掌握供肺的灌注、切取、保存、修剪的方法以及受体单肺移植的手术方法。方法:杂种犬10只,分为供体和受体,进行5次动物实验,其中异体左肺移植4例,异体右肺移植1例。先吻合支气管,后吻合肺动脉,最后心房袖,移植后于不同时点暂阻断对侧肺动脉并检测植入肺的功能参数。结果:所有移植肺通气和换气功能均正常,移植后犬恢复自主呼吸,能站立行走。术后1例存活5d,供体肺冷缺血时间4h;另1例存活3d,供体肺冷缺血时间17h;余3例均在24h内死亡。结论:犬异体单肺移植早期犬死亡的主要原因是移植肺的缺血再灌注损伤。     

提肛运动对于直肠癌保肛术后肛门功能恢复的疗效观察

目的探讨提肛运动对于直肠癌患者Dixon术后肛门功能的作用。方法提肛组在术后2周即每日进行提肛运动的功能锻炼,对照组不采取任何干预措施,测定两组术后3个月后直肠肛门压力。结果提肛组患者排便次数及控便能力明显优于对照组(P<0.05),但对于粪便质地及其里急后重感,两组比较无统计学意义(P>0.05);提肛组肛管最大收缩压较对照组明显提高(P<0.05),而肛管静息压及肛管括约肌功能长度两组比较差异均无统计学意义(P>0.05)。结论提肛运动可明显提高直肠癌保肛术后肛门的控便能力。