诊断思维的模拟实验

为了对人工神经网络（ＡＮＮ）中的一些问题进行探索，我们把ＡＮＮ和数据库系统（ＤＢＳ）的方法结合起来，并试用于疾病诊断。试验表明，能加速训练过程，ＡＮＮ与外界的关系和人工神经元在训练、运行过程中的状态比较直观，诊断效果较为满意，值得进一步和完善。     

适用于工程应用的Fourier系数求解法

本文为Ｆｏｕｒｉｅｒ系数的确定提出了两种适用于工程应用的求解法：遗传算法（ＧＡ）和人工神经网络（ＡＮＮ）法。应用ＧＡ求解Ｆｏｕｒｉｅｒ系数时,将Ｆｏｕｒｉｅｒ系数作为解向量进行染色体编码,然后通过进化使得Ｆｏｕｒｉｅｒ展开充分逼近原函数从而获得最佳解：Ｆｏｕｒｉｅｒ级数通过三角变换后,能够用一标准的三层前馈网络描述,其网络权与Ｆｏｕｒｉｅｒ系数相应,利用ＢＰ算法训练该网络即可确定Ｆｏｕｒｉｅｒ系数     

人工神经网络的容量、学习与计算复杂性

本文讨论了人工神经网络（ＡＮＮ）解决问题的能力，从广泛的角度讨论了容量问题，推广与学习问题，深入研究了ＡＮＮ通过学习解决问题的计算复杂性，以及解决实际问题时困难所在。     

人工神经网络的容量,学习与计算复杂性

本文讨论了人工神经网络（ＡＮＮ）解决问题的能力，从广泛的角度讨论了容量问题，推广与学习问题，深入研究了ＡＮＮ通过学习解决问题的计算复杂性，以及解决实际问题时困难所在。     

利用隐含观测量估计将复杂神经网络分解为多个单隐元学习的新方法

本文从统计学的角度研究多层多隐元前神经网络（ＮＮ）的参数估计学习问题,利用ＮＮ激励函数的析线线性近似,提出一种求解多隐层多隐元ＮＮ每个隐元指导信号（隐含观测量）的新方法,利用每个隐元的指导信号估计可以半多隐多层多隐元ＮＮ的参数估计学习转化为多个相互独立的单隐元ＮＮ参数估计学习训练问题,从而将复杂系统参数估计问题转化为简单系统的参数估计问题而得以解决。     

环结构神经网络及其互联想性能

本文提出一种称为环结构神经网络（ＬＡＮＮ）模型及其学习算法，它能像Ｈｏｐｆｉｅｌｄ网络，双向联想记忆（ＢＡＭ）网络和其它类似网络一样工作，特别是它能执行多类样本之间的互联想记忆，理论分析和计算机模拟都证明ＬＡＮＮ具有很好的收敛性，是一种有效的网络结构，最后本文给出了计算机模拟结果。     

MOCVD生长GaN的喇曼散射谱

对在ＧａＡｓ（００１）、Ａｌ２Ｏ３（０００１）和Ｓｉ（１１１）等衬底上ＭＯＣＶＤ技术生长的ＧａＮ薄膜进行了背散射几何配置下的喇曼散射测试分析和比较，观察到了α相ＧａＮ的Ａ１（ＬＯ）模、Ａ１（ＴＯ）模、Ｅ１（ＬＯ）模和Ｅ２模．结合Ｘ射线衍射谱，分析了因不同生长工艺导致ＧａＮ／ＧａＡｓ样品的不同结构相的喇曼谱的差异，发现ＧａＮ的喇曼谱与ＧａＮ外延层的结构相、完整性及工艺条件有关，可利用其作为检测ＧａＮ外延层结构特性的一种有用手段．对含有少量β相ＧａＮ样品，观测到了包含有β相ＧａＮ贡献的声子模式（７４０ｃｍ－１）．     

复数FIR DF设计的神经网络优化方法

本文基于人工神经网络（ＡＮＮ）能量函数优化理论，提出了一种ＦＩＲ数字滤波器（ＤＦ）神经网络优化设计（ＮＮＯ）方法的理论框架。该理论将实数与复数ＦＩＲ ＤＦ设计工作统一起来。表征设计质量的加权均方误差被当作ＡＮＮ能量函数，以此导出ＦＩＲ－ＮＮＯ的Ｌｙａｐｕｎｏｖ方程，文中说明了算法实现的基本原则，并给出了两个实数线位和一个复数非线性相位ＦＩＲ ＤＦ设计实例。通过与其它几种方法的比较证明了该方法的有效     

自适应神经网络判决树及其在人脸识别领域的应用

提出了一种神经网络与判决树结合而成的新结构－自适应神经网络判决树（ＡＮＮＤＴ）。实验表明，基于ＡＮＮＤＴ的人脸识别方法，能够综合利用多种神经网络模型和特征提取算法，不仅具有较高的识别速度、准确率、容错性和健壮性，而且基本满足开发实用化人脸识别系统的要求。     

用子波网络实现自适应子波变换

本文从傅里叶变换（ＦＴ）的角度引入连续和离散自适应于波变换（ＷＴ），作为应用，在数学上比较子耳，眼功能和连续ＷＴ，以给人工神经网络（ＡＮＮ）提供多分辨率分析（ＭＲＡ）并行输入，这种七妙的预处理可以实现特征保持的数据压缩，避免过训练或地拟合对ＡＮＮ概括和抽象能力的影响。这可以用来解释嘈杂鸡尾酒会效应。一个例子是，对Ｎ个数据要求有Ｎ阶阶复杂性快速数据压缩的多波段红外图像，引入离散ＷＴ作为完备，正交和归     

A novel hybrid model for inversion problem of atmospheric refractivity estimation

Atmospheric refractivity estimation is an important issue for performance evaluation of communication systems and air surveillance radars. A novel hybrid model based on artificial neural networks (ANNs) and genetic algorithms (GAs) for inversion problem of atmospheric refractivity estimation is introduced. In this paper, inversion problem and clutter model problem of refractivity from clutter (RFC) method are separated and only inversion problem is studied. A problem specific ANN structure is designed and an original GA is developed to fulfill atmospheric refractivity estimations. In hybrid method, ANNs make pre-estimation and GAs use these results as a starting population for post-estimation. When the results obtained from the single solutions of ANNs and GAs are compared to the results obtained from hybrid model, a significant improvement in the accuracy of estimated results is observed.     

Avoiding Pitfalls in Neural Network Research

Artificial neural networks (ANNs) have gained extensive popularity in recent years. Research activities are considerable, and the literature is growing. Yet, there is a large amount of concern on the appropriate use of neural networks in published research. The purposes of this paper are to: 1) point out common pitfalls and misuses in the neural network research; 2) draw attention to relevant literature on important issues; and 3) suggest possible remedies and guidelines for practical applications. The main message we aim to deliver is that great care must be taken in using ANNs for research and data analysis     

Depth efficient neural networks for division and related problems

An artificial neural network (ANN) is commonly modeled by a threshold circuit, a network of interconnected processing units called linear threshold gates. It is shown that ANNs can be much more powerful than traditional logic circuits, assuming that each threshold gate can be built with a cost that is comparable to that of AND/OR logic gates. In particular, the main results indicate that powering and division can be computed by polynomial-size ANNs of depth 4, and multiple product can be computed by polynomial-size ANNs of depth 5. Moreover, using the techniques developed, a previous result can be improved by showing that the sorting of n n-bit numbers can be carried out in a depth-3 polynomial-size ANN. Furthermore, it is shown that the sorting network is optimal in depth     

On the application and design of artificial neural networks formotor fault detection. II

For part I see ibid., vol.40, no.2, p.181-8 (1993). Some neural network design considerations, such as network performance, network implementation, size of training data set, assignment of training parameter values, and stopping criteria, are discussed. A fuzzy logic approach to configuring the network structure is presented, to automate the network design. Successful results are obtained from using artificial neural networks (ANNs) on motor fault detection and fuzzy logic in the network configuration design. It is concluded that these emerging technologies are promising for future widespread industrial usage     

Macrocell path loss prediction using artificial intelligence techniques

The prediction of propagation loss is a practical non-linear function approximation problem which linear regression or auto-regression models are limited in their ability to handle. However, some computational Intelligence techniques such as artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFISs) have been shown to have great ability to handle non-linear function approximation and prediction problems. In this study, the multiple layer perceptron neural network (MLP-NN), radial basis function neural network (RBF-NN) and an ANFIS network were trained using actual signal strength measurement taken at certain suburban areas of Bauchi metropolis, Nigeria. The trained networks were then used to predict propagation losses at the stated areas under differing conditions. The predictions were compared with the prediction accuracy of the popular Hata model. It was observed that ANFIS model gave a better fit in all cases having higher R² values in each case and on average is more robust than MLP and RBF models as it generalises better to a different data.     

Evolving artificial neural networks

Learning and evolution are two fundamental forms of adaptation. There has been a great interest in combining learning and evolution with artificial neural networks (ANNs) in recent years. This paper: 1) reviews different combinations between ANNs and evolutionary algorithms (EAs), including using EAs to evolve ANN connection weights, architectures, learning rules, and input features; 2) discusses different search operators which have been used in various EAs; and 3) points out possible future research directions. It is shown, through a considerably large literature review, that combinations between ANNs and EAs can lead to significantly better intelligent systems than relying on ANNs or EAs alone     

Artificial neural network medical decision support tool: predicting transfusion requirements of ER patients.

Blood product transfusion is a financial concern for hospitals and patients. Efficient utilization of this dwindling resource is a critical problem if hospitals are to maximize patient care while minimizing costs. Traditional statistical models do not perform well in this domain. An additional concern is the speed with which transfusion decisions and planning can be made. Rapid assessment in the emergency room (ER) necessarily limits the amount of usable information available (with respect to independent variables available). This study evaluates the efficacy of using artificial neural networks (ANNs) to predict the transfusion requirements of trauma patients using readily available information. A total of 1016 patient records are used to train and test a backpropagation neural network for predicting the transfusion requirements of these patients during the first 2, 2-6, and 6-24 h, and for total transfusions. Sensitivity and specificity analysis are used along with the mean absolute difference between blood units predicted and units transfused to demonstrate that ANNs can accurately predict most ER patient transfusion requirements, while only using information available at the time of entry into the ER.     

Positioning in WLAN environment by use of artificial neural networks and space partitioning

Short range wireless technologies such as wireless local area network (WLAN), Bluetooth, radio frequency identification, ultrasound and Infrared Data Association can be used to supply position information in indoor environments where their infrastructure is deployed. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. In this paper, the position determination by the use of artificial neural networks (ANNs) is explored. The single ANN multilayer feedforward structure and a novel positioning technique based on cascade-connected ANNs and space partitioning are presented. The proposed techniques are thoroughly investigated on a real WLAN network. Also, an in-depth comparison with other well-known techniques is shown. Positioning with a single ANN has shown good results. Moreover, when utilising space partitioning with the cascade-connected ANNs, the median error is further reduced for as much as 28%.     

Classification of seismic signals by integrating ensembles ofneural networks

We examine a classification problem in which seismic waveforms of natural earthquakes are to be distinguished from waveforms of man-made explosions. We present an integrated classification machine (ICM), which is a hierarchy of artificial neural networks (ANNs) that are trained to classify the seismic waveforms. In order to maximize the gain of combining the multiple ANNs, we suggest construction of a redundant classification environment (RCE) that consists of several “experts” whose expertise depends on the different input representations to which they are exposed. In the proposed scheme, the experts are ensembles of ANN, trained on different bootstrap replicas. We use various network architectures, different time-frequency decompositions of the seismic waveforms, and various smoothing levels in order to achieve an RCE. A confidence measure for the ensemble's classification is defined based on the agreement (variance) within the ensembles, and an algorithm for a nonlinear integration of the ensembles using this measure is presented. An implementation on a data set of 380 seismic events is described, where the proposed ICM had classified correctly 92% of the testing signals. The comparison we made with classical methods indicates that combining a collection of ensembles of ANNs can be used to handle complex high dimensional classification problems