人工神经网络遥感分类方法研究现状及发展趋势探析

从人工神经网络技术本身出发,概括了其在遥感分类中的研究现状,分析了人工神经网络遥感分类方法与其它分类方法相比具有的优势,介绍了人工神经网络遥感分类的一些主要应用,并进一步对人工神经网络遥感分类方法的发展趋势进行了展望。     

基于粒子群训练的人工神经网络应用于多光遥感影像分类研究

为了提高多光谱遥感影像的分类精度,提出一种基于粒子群训练的人工神经网络的多光谱遥感影像的分类方法.该方法先建立一个针对多光谱遥感影像的神经网络分类模型,然后引入粒子群算法对神经网络进行网络权值与阈值的优化,再利用训练好的神经网络对多光谱遥感影像进行分类.该方法不仅利用了人工神经网络在解决多光谱遥感影像混合光谱的优势,而且克服了BP神经网络在训练时候收敛速度过慢、振荡的缺点.实验结果证明:基于粒子群训练的人工神经网络方法能够比较好地提高多光谱遥感影像的分类精度.     

基于粒子群训练的人工神经网络应用于多光谱遥感影像分类研究

为了提高多光谱遥感影像的分类精度,提出一种基于粒子群训练的人工神经网络的多光谱遥感影像的分类方法。该方法先建立一个针对多光谱遥感影像的神经网络分类模型,然后引入粒子群算法对神经网络进行网络权值与阈值的优化,再利用训练好的神经网络对多光谱遥感影像进行分类。该方法不仅利用了人工神经网络在解决多光谱遥感影像混合光谱的优势,而且克服了BP神经网络在训练时候收敛速度过慢、振荡的缺点。实验结果证明：基于粒子群训练的人工神经网络方法能够比较好地提高多光谱遥感影像的分类精度。     

神经网络在文本分类上的一种应用

现有的文本分类方法在知识获取方面存在不足。该文针对某种应用需求,提出了人工神经网络和文本分类结合的一种文本分类方法。采用特征词的向量空间来描述文本,利用人工神经网络的良好的学习能力,通过对文本样本集进行训练,从中提取出对文本分类的知识,再利用神经网络和所获得的分类知识实现对文本的分类。     

基于并行反向熵决策树算法的人工神经网络

针对数据分类挖掘问题,利用并行思想,提出一种基于并行反向熵决策树算法的人工神经网络.通过概率度量水平生成并行决策树对数据进行粗处理,以加快人工神经网络的分析速度.随后采用一组仿真数据对该方法进行测试和评估.实验结果表明,该并行分类方法比单个决策树具有更高的分类精度,并在保持分类结果良好可解释性的基础上优化了分类规则.     

用Scilab实现基于人工神经网络的数据分类

运用人工神经网络中的简单感知器模型和Widrow-Hoff学习法则，借助Scilab具体实现数据分类。通过对数据挖掘中数据分类的一个重要分类方法——人工神经网络方法的研究，证明了人工神经网络在数据分类中具有很大的潜力和优越性。     

基于分解云的分类器设计

基于云模型的分类算法多采用云变换和泛概念树方法,存在分类结果与先验知识不一致的问题。从粒度计算的角度对云模型理论进行了分析,揭示出云模型的粒度原理。提出了一种基于分解云的不同粒度下的云模型分类方法,并给出了分类方法的算法描述。用风云2C气象卫星的数据对算法进行了测试,从实验结果来看该方法具有较好的分类效果。     

基于人工神经网络的苹果气体识别方法研究

将气体传感器阵列与人工神经网络模式识别技术相结合,建立了电子鼻系统,对水果变化过程进行监控。尝试对3种不同状态(好、碰伤、坏)的苹果气体进行定性识别。实验结果表明:结合主成分分析的人工神经网络方式为模式识别、分类提供了快速准确的辨识方法,对红富士苹果进行分类时正确率在83.33%以上。     

人工神经网络在文物分类系统中的应用研究

人工神经网络由于其强大的学习和适应能力,广泛应用于模式识别、模式分类、自动控制、图像处理及智能系统的非线性建模等方面。文中对几种典型的人工神经网络的结构、功能、学习算法进行了综述,详细介绍了人工神经网络在文物分类系统中的应用,比较结果可以得出自组织竞争神经网络的分类效果要优于其它两种神经网络。     

人工神经网络在文物分类系统中的应用研究

人工神经网络由于其强大的学习和适应能力,广泛应用于模式识别、模式分类、自动控制、图像处理及智能系统的非线性建模等方面.文中对几种典型的人工神经网络的结构、功能、学习算法进行了综述,详细介绍了人工神经网络在文物分类系统中的应用,比较结果可以得出自组织竞争神经网络的分类效果要优于其它两种神经网络.     

人工神经网络模型发展及应用综述

人工神经网络与其他学科领域联系日益紧密,人们通过对人工神经网络层结构的探索和改进来解决各个领域的问题。根据人工神经网络相关文献进行分析,综述了人工神经网络算法以及网络模型结构的发展史,根据神经网络的发展介绍了人工神经网络相关概念,其中主要涉及到多层感知器、反向传播神经网络、卷积神经网络以及递归神经网络,描述了卷积神经网络发展当中出现的部分卷积神经网络模型和递归神经网络中常用的相关网络结构,分别综述了各个人工神经网络算法在相关领域的应用情况,总结了人工神经网络的未来发展方向。     

Neural networks and graph theory

The relationships between artificial neural networks and graph theory are considered in detail. The applications of artificial neural networks to many difficult problems of graph theory, especially NP-complete problems, and the applications of graph theory to artificial neural networks are discussed. For example graph theory is used to study the pattern classification problem on the discrete type feedforward neural networks, and the stability analysis of feedback artificial neural networks etc.     

Short-long term anomaly detection in wireless sensor networks based on machine learning and multi-parameterized edit distance

Heterogeneous wireless sensor networks are a source of large amount of different information representing environmental aspects such as light, temperature, and humidity. A very important research problem related to the analysis of the sensor data is the detection of relevant anomalies. In this work, we focus on the detection of unexpected sensor data resulting either from the sensor system itself or from the environment under scrutiny. We propose a novel approach for automatic anomaly detection in heterogeneous sensor networks based on coupling edge data analysis with cloud data analysis. The former exploits a fully unsupervised artificial neural network algorithm, whereas cloud data analysis exploits the multi-parameterized edit distance algorithm. The experimental evaluation of the proposed method is performed applying the edge and cloud analysis on real data that has been acquired in an indoor building environment and then distorted with a range of synthetic impairments. The obtained results show that the proposed method can self-adapt to the environment variations and correctly identify the anomalies. We show how the combination of edge and cloud computing can mitigate the drawbacks of purely edge-based analysis or purely cloud-based solutions.     

Determination of spatial and temporal characteristics as an aid to neural network cloud classification

Previous studies of cloud classification from meteorological satellite imagery have shown that artificial neural networks (ANNs) perform as well as, or better than, statistical pattern recognition when multispectral features, supplemented with selected textural features, are used. These features, however, represent only a subset of the full range of features available in this imagery. Spatial characteristics based on the shape of clouds, and temporal characteristics, derived from image sequences, can be more direct pointers to cloud type. In this paper the methods for the determination of such parameters are described, some results are presented, and the effectiveness of the methods are discussed.     

图卷积神经网络在点云语义分割中的研究综述

点云数据蕴含丰富的空间信息,可以通过激光雷达、3D传感器等设备大量采集,被广泛应用于自动驾驶、虚拟现实、城市规划和3D重建等领域。点云语义分割作为3D场景理解、识别和各种应用的基础而受到广泛关注。但不规则的点云数据无法直接作为传统卷积神经网络的输入,而图卷积神经网络可以利用图卷积算子直接对点云数据进行特征提取,使得图卷积神经网络已逐步成为点云语义分割领域的一个重要研究方向。基于此,对图卷积神经网络在3D点云语义分割应用中的研究进展进行综述,根据图卷积的类型对基于图卷积神经网络的点云语义分割方法进行分类,按照不同类别对比分析主流方法的模型架构及其特点,描述几个相关点云语义分割领域常用的公共数据集和评价指标,对点云语义分割方法进行总结和展望。     

基于云遗传的RBF神经网络的交通流量预测

以神经网络和混沌时间序列理论为基础,提出了一种基于云遗传的RBF神经网络优化算法。该算法利用云模型云滴的随机性和稳定倾向性的特点,由正态云模型的Y条件云发生器实现交叉操作,由基本云发生器实现变异操作,提高了遗传搜索的效率,精简了网络结构。将该算法应用到Logistic混沌时间序列和实测交通流时间序列进行算法的有效性验证,并与传统的RBF算法和遗传算法优化的RBF算法（GARBF）进行比较。仿真结果表明该算法对混沌时间序列和交通流预测的精度有较大提高,从而证明该算法在交通流时间序列预测领域的可行性和有效性。     

Use of NARX neural networks for Meteosat Second Generation SEVIRI very short-term cloud mask forecasting

In this article, a novel technique based on artificial neural networks (NN) is proposed for cloud coverage short-term forecasting (nowcasting). In particular, the capabilities of multi-layer perceptron NN and time series analysis with nonlinear autoregressive with exogenous input NN are explored and applied to the European meteorological system ‘Meteosat Second Generation’ with its payload Spinning Enhanced Visible and InfraRed Imager. The general neural architecture consists of a first stage addressing the prediction of the radiance images at six bands (0.6, 0.8, 1.6, 3.9, 6.2 and 10.8 μm). In a second stage a cloud masking algorithm, always based on NN, is applied to the predicted images for the cloud coverage nowcasting. The scheme was compared with the most basic forecast algorithm for the prediction: the persistent model. Two test areas characterized by different climatology have been considered for the performance analysis. The results show that about 85% of the changes occurring in the time window were recognized by the proposed technique.     

基于生物脑网络连接特性的高效神经网络算法

人工神经网络发展至今,已经在计算机视觉、类脑智能等方面得到广泛应用.在过去几十年中,人们对神经网络的研究注重追求更高的准确率,从而忽略了对网络计算成本的控制.而人脑作为高效且节能的网络,其对人工智能的发展起到了重要启示作用.如何仿真生物脑网络的连接特性,建立超低能耗的人工神经网络模型实现基本相同的目标识别正确率成为当前研究的热点.为建立低能耗的人工神经网络模型,本文结合大脑网络的连接特性,通过改变人工神经网络的连接实现网络的高效性.实验结果表明,结合生物脑网络的连接特性,改变网络的连接,很大程度上减少了网络的计算成本,而网络的性能并没有受到明显影响.     

Using an artificial neural network to detect activations during ventricular fibrillation.

Ventricular fibrillation is a cardiac arrhythmia that can result in sudden death. Understanding and treatment of this disorder would be improved if patterns of electrical activation could be accurately identified and studied during fibrillation. A feedforward artificial neural network using backpropagation was trained with the Rule-Based Method and the Current Source Density Method to identify cardiac tissue activation during fibrillation. Another feedforward artificial neural network that used backpropagation was trained with data preprocessed by those methods and the Transmembrane Current Method. Staged training, a new method that uses different sets of training examples in different stages, was used to improve the ability of the artificial neural networks to detect activation. Both artificial neural networks were able to correctly classify more than 92% of new test examples. The performance of both artificial neural networks improved when staged training was used. Thus, artificial neural networks may beuseful for identifying activation during ventricular fibrillation.     

Shallow and deep learning for image classification

The paper is focused on the idea to demonstrate the advantages of deep learning approaches over ordinary shallow neural network on their comparative applications to image classifying from such popular benchmark databases as FERET and MNIST. An autoassociative neural network is used as a standalone program realized the nonlinear principal component analysis for prior extracting the most informative features of input data for neural networks to be compared further as classifiers. A special study of the optimal choice of activation function and the normalization transformation of input data allows to improve efficiency of the autoassociative program. One more study devoted to denoising properties of this program demonstrates its high efficiency even on noisy data. Three types of neural networks are compared: feed-forward neural net with one hidden layer, deep network with several hidden layers and deep belief network with several pretraining layers realized restricted Boltzmann machine. The number of hidden layer and the number of hidden neurons in them were chosen by cross-validation procedure to keep balance between number of layers and hidden neurons and classification efficiency. Results of our comparative study demonstrate the undoubted advantage of deep networks, as well as denoising power of autoencoders. In our work we use both multiprocessor graphic card and cloud services to speed up our calculations. The paper is oriented to specialists in concrete fields of scientific or experimental applications, who have already some knowledge about artificial neural networks, probability theory and numerical methods.