Assessment of the impact of dimensionality reduction methods on information classes and classifiers for hyperspectral image classification by multiple classifier system

Identification of the appropriate combination of classifier and dimensionality reduction method has been a recurring task for various hyperspectral image classification scenarios. Image classification by multiple classifier system has been evolving as a promising method for enhancing accuracy and reliability of image classification. Because of the diversity in generalization capabilities of various dimensionality reduction methods, the classifier optimal to the problem and hence the accuracy of image classification varies considerably. The impact of including multiple dimensionality reduction methods in the MCS architecture for the supervised classification of a hyperspectral image for land cover classification has been assessed in this study. Multi-source airborne hyperspectral images acquired over five different sites covering a range of land cover categories have been classified by a multiple classifier system and compared against the classification results obtained from support vector machines (SVM). The MCS offers acceptable classification results across the images or sites when there are multiple dimensionality reduction methods in addition to different classifiers. Apart from offering acceptable classification results, the MCS indicates about 5% increase in the overall accuracy when compared to the SVM classifier across the hyperspectral images and sites. Results indicate the presence of dimensionality reduction method specific empirical preferences by land cover categories for certain classifiers thereby demanding the design of MCS to support adaptive selection of classifiers and dimensionality reduction methods for hyperspectral image classification.     

基于SGNN的数字字符识别

自生成神经网络SGNN具有自主学习能力强和计算速度快的特点,可用于识别带噪声的数字字符。首先提取数字字符的特征矢量,然后将特征矢量输入SGNN中对SGNN进行训练建立分类器,通过比较未知样本特征矢量和分类器根节点权值矢量的距离远近从而得到识别结果。实验表明这种方法有较高的识别正确率,其性能优于BP神经网络。     

基于模糊关联分类器的民机超限事件诊断方法

现有的民用飞机超限事件智能诊断模型大多属于“黑盒”模型,不利于分析超限事件发生的原因.为此提出了一种基于模糊关联分类器(FAC,Fuzzy Associative Classifier)的民用飞机超限事件诊断方法.该方法抽取发生超限事件时对应的QAR(Quick Access Recorder)参数快照取值,采用模糊C均值(FCM,Fuzzy C-Means)聚类算法对抽取的QAR参数取值模糊预处理,然后基于Apriori算法生成模糊关联分类规则库,并由遗传算法对其进行裁剪,结合模糊分类推理方法形成FAC.采用B737-800实际样本数据进行了验证.实验结果表明,所提出的FAC能有效诊断超限事件,FAC识别超限事件的错误率与最小二乘支持向量机(LS-SVM,Least Squares Support Vector Machine)模型相当,但其解释性方面优于LS-SVM.     

基于目标性权值度量的多示例学习目标跟踪

针对多示例学习(MIL)跟踪算法在包概率计算过程中对示例样本不加以区分导致分类器性能下降,及采用最大化似然函数选择相应的弱分类构造强分类增加了算法复杂度的问题,提出了一种基于目标性权值学习的多示例目标跟踪算法,该算法利用目标性测量每个示例样本对包概率的重要性,根据其目标性测量结果对每个正示例样本赋予相应的权值,从而判别性地计算包概率,提高跟踪精度。同时在弱分类器选择过程中,采用最大化弱分类器与似然函数概率内积的方法从弱分类器池中选择弱分器构造强分类器,减少算法的计算复杂度。通过对不同复杂场景下视频序列的跟踪,实验结果表明,本文所提出的目标性权值学习的多示例目标跟踪算法优于其对比算法,表现出较好的跟踪精度和鲁棒性能。     

贝叶斯分类器在液体火箭发动机故障诊断中的应用

研究数据挖掘技术在火箭发动机故障诊断中的应用,利用两种典型的贝叶斯分类器——朴素贝叶斯分类器和TAN分类器对液体火箭发动机故障进行分类,对某型号液体火箭发动机的试车数据和仿真数据进行了故障诊断,结果和实际试车情况相符,从而验证了贝叶斯分类器可以应用于液体火箭发动机故障诊断。     

树分类器在多界面粘接质量图像诊断中的应用

在对固体火箭发动机的钢、衬层、绝热层复合结构粘接质量进行超声图像诊断过程中,利用两检测回波之间的谐振关系确定作为特征值的延迟时间,并把特征值提取和多界面粘接状态识别归结为一个多模式识别问题,利用自行设计的二叉树分类器对其进行分类识别,获得了高质量的诊断图像.      

基于局部密度的单类分类器LP改进算法

为了提高基于支持域的单类分类器识别率,提出将局部密度加入到分类器设计当中。在Campbe ll等的LP算法基础上,通过k近邻方法对每个样本点引入局部密度因子pi,重新刻画了原算法,使处于不同密度区的数据对分类器的作用不再被同等对待,高密度区的数据对分类超平面作用被强化,而低密度区的数据被削弱,结果使分类超平面自动靠近高密度区而提高了识别率。真实数据集上的实验结果表明,引入局部密度的D-LP算法其泛化性能较原算法有较大提高。     

Integration of artificial intelligence with meta classifiers for the gully erosion susceptibility assessment in Hinglo river basin,Eastern India

The main aim of this study is to evaluate the gully erosion susceptibility coupling the artificial intelligence and machine learning ensemble approaches. In the present study, the multilayer perceptron neural network (MLP) was used as the base classifier and the hybrid ensemble machine learning methods i.e. Bagging and Dagging were used as the functional classifiers. The Hinglo river basin, an important tributary of the Ajay River was selected as the study area, consists with the parts of Chhotonagpur plateau and Rarh lateritic region. The study area is facing the gully erosion problems which are interrupted the growth of the agriculture. The gully erosion susceptibility maps (GESMs), prepared by MLP, MLP-Bagging and MLP-Dagging were classified into four classes such as low, moderate, high and very high susceptibility classes with the help of natural break method (NBM) in GIS environment. The very high susceptibility class covered 19.41% (MLP), 13.52% (MLP-Bagging) and 15.30% (MLP-Dagging) areas of the basin. For the evaluation and comparison of the models, receiver operating characteristics (ROC), accuracy, mean absolute error (MAE) and root mean square error (RMSE) were applied. Overall, all the gully erosion susceptibility models were performed as excellent. Integration of hybrid ensemble models with MLP has increase the accuracy of the MLP models. Among these models MLP-Dagging has achieved the highest accuracy in compare to the other models. The importance of the selected factors in the present study was assessed by the Relief-F method. The results show that the soil type factor has the highest predictive performance. Sensitivity analysis also showed soil type as most important factor. The gully erosion susceptibility maps (GESMs) are considered as the efficient tool which could be used to take the necessary steps for mitigating and controlling the soil erosion problem and sustainable environmental management and development.     

一种基于改进核主成分分析的SAR图像识别方法研究

针对传统核主成分分析方法识别SAR图像时,存在图像像素之间关联性差、对目标姿态角依赖性强等局限性,研究了一种基于改进核主成分分析的SAR图像识别方法。其研究思想是,结合SAR图像的特点提出了一种基于局部特征核主成分分析的特征提取方法,并设计了一种基于灰关联分析的双分类器对提取特征进行分类。NSTAR仿真实验表明：该方法不仅可以增强图像像素之间的相关性,而且对目标姿态角不存在依赖性,仿真结果验证了方法的有效性和可行性。     

The automated prediction of solar flares from SDO images using deep learning

In the last few years, there has been growing interest in near-real-time solar data processing, especially for space weather applications. This is due to space weather impacts on both space-borne and ground-based systems, and industries, which subsequently impacts our lives. In the current study, the deep learning approach is used to establish an automated hybrid computer system for a short-term forecast; it is achieved by using the complexity level of the sunspot group on SDO/HMI Intensitygram images. Furthermore, this suggested system can generate the forecast for solar flare occurrences within the following 24 h. The input data for the proposed system are SDO/HMI full-disk Intensitygram images and SDO/HMI full-disk magnetogram images. System outputs are the “Flare or Non-Flare” of daily flare occurrences (C, M, and X classes). This system integrates an image processing system to automatically detect sunspot groups on SDO/HMI Intensitygram images using active-region data extracted from SDO/HMI magnetogram images (presented by Colak and Qahwaji, 2008) and deep learning to generate these forecasts. Our deep learning-based system is designed to analyze sunspot groups on the solar disk to predict whether this sunspot group is capable of releasing a significant flare or not. Our system introduced in this work is called ASAP_Deep. The deep learning model used in our system is based on the integration of the Convolutional Neural Network (CNN) and Softmax classifier to extract special features from the sunspot group images detected from SDO/HMI (Intensitygram and magnetogram) images. Furthermore, a CNN training scheme based on the integration of a back-propagation algorithm and a mini-batch AdaGrad optimization method is suggested for weight updates and to modify learning rates, respectively. The images of the sunspot regions are cropped automatically by the imaging system and processed using deep learning rules to provide near real-time predictions. The major results of this study are as follows. Firstly, the ASAP_Deep system builds on the ASAP system introduced in Colak and Qahwaji (2009) but improves the system with an updated deep learning-based prediction capability. Secondly, we successfully apply CNN to the sunspot group image without any pre-processing or feature extraction. Thirdly, our system results are considerably better, especially for the false alarm ratio (FAR); this reduces the losses resulting from the protection measures applied by companies. Also, the proposed system achieves a relatively high scores for True Skill Statistics (TSS) and Heidke Skill Score (HSS).