An Ophthalmic Evaluation of Central Serous Chorioretinopathy

Nowadays in the medical field, imaging techniques such as Optical Coherence Tomography (OCT) are mainly used to identify retinal diseases. In this paper, the Central Serous Chorio Retinopathy (CSCR) image is analyzed for various stages and then compares the difference between CSCR before as well as after treatment using different application methods. The first approach, which was focused on image quality, improves medical image accuracy. An enhancement algorithm was implemented to improve the OCT image contrast and denoise purpose called Boosted Anisotropic Diffusion with an Unsharp Masking Filter (BADWUMF). The classifier used here is to figure out whether the OCT image is a CSCR case or not. 150 images are checked for this research work (75 abnormal from Optical Coherence Tomography Image Retinal Database, in-house clinical database, and 75 normal images). This article explicitly decides that the approaches suggested aid the ophthalmologist with the precise retinal analysis and hence the risk factors to be minimized. The total precision is 90 percent obtained from the Two Class Support Vector Machine (TCSVM) classifier and 93.3 percent is obtained from Shallow Neural Network with the Powell-Beale (SNNWPB) classifier using the MATLAB 2019a program.     

Adaptive Window Based 3-D Feature Selection for Multispectral Image Classification Using Firefly Algorithm

Feature extraction is the most critical step in classification of multispectral image. The classification accuracy is mainly influenced by the feature sets that are selected to classify the image. In the past, handcrafted feature sets are used which are not adaptive for different image domains. To overcome this, an evolutionary learning method is developed to automatically learn the spatial-spectral features for classification. A modified Firefly Algorithm (FA) which achieves maximum classification accuracy with reduced size of feature set is proposed to gain the interest of feature selection for this purpose. For extracting the most efficient features from the data set, we have used 3-D discrete wavelet transform which decompose the multispectral image in all three dimensions. For selecting spatial and spectral features we have studied three different approaches namely overlapping window (OW-3DFS), non-overlapping window (NW-3DFS) adaptive window cube (AW-3DFS) and Pixel based technique. Fivefold Multiclass Support Vector Machine (MSVM) is used for classification purpose. Experiments conducted on Madurai LISS IV multispectral image exploited that the adaptive window approach is used to increase the classification accuracy.     

基于SSA-SVM的网络入侵检测研究

互联网快速发展使得网络空间越来越复杂,网络入侵导致网络安全问题备受关注。为提升网络入侵的检测效率和精度,构建了基于支持向量机的网络入侵检测模型。支持向量机模型的惩罚系数和核函数参数直接影响入侵模型的检测精度,采用麻雀搜索算法对惩罚系数和核函数参数进行优化,提出了基于麻雀搜索算法和支持向量机的网络入侵检测模型。将提出的网络入侵检测模型应用于实际的网络入侵检测中,并与PSO-SVM和SVM模型进行对比。结果表明,所提出的网络入侵检测模型能够有效降低网络入侵的误报率,这对确保网络安全具有一定的现实意义。     

融合MAML和CBAM的安卓恶意应用家族分类模型

为满足对新兴安卓恶意应用家族的快速检测需求,提出一种融合MAML(model-agnostic meta-learning)和CBAM(convolutional block attention module)的安卓恶意应用家族分类模型MAML-CAS。将安卓恶意应用样本集中的DEX文件可视化为灰度图,并构建任务集;融合混合域注意力机制CBAM,设计两个具有同等结构的卷积神经网络,分别作为基学习器和元学习器,这两个学习器在自动提取任务集中样本特征的同时,可从通道和空间两个维度来增强关键特征表达;利用元学习方法 MAML对两个学习器进行训练,其中基学习器完成特定恶意家族分类任务的属性学习,元学习器则学习不同任务的共性;在两个学习器训练完成后,MAML-CAS将获得初始化参数,在面对新的安卓恶意应用家族分类任务时,不需要重新训练,只需要少量样本就可以快速迭代;利用训练完成的基学习器提取安卓恶意应用家族特征,并利用SVM进行恶意家族分类。实验结果表明,MAML-CAS模型对新兴小样本安卓恶意应用家族具有良好的检测效果,检测速度较快,并具有较好的稳定性。     

融合CNN-BiLSTM-Attention的集成学习价格预测

价格预测对于大宗农产品市场的稳定具有重要意义,但是大宗农产品价格与多种因素有着复杂的相关关系.针对当前价格预测中对数据完整性依赖性强与单一模型难以全面利用多种数据特征等问题,提出了一种将基于注意力机制的卷积双向长短期记忆神经网络(CNN-BiLSTM-Attention)、支持向量机回归(SVR)与LightGBM组合的增强式集成学习方法,并分别在包含历史交易、天气、汇率、油价等多种特征数据的数据集上进行了实验.实验以小麦和棉花价格预测为目标任务,使用互信息法进行特征选择,选择误差较低的CNN-BiLSTM-Attention模型作为基模型,与机器学习模型通过线性回归进行增强式集成学习.实验结果表明该集成学习方法在小麦及棉花数据集上预测结果的均方根误差(RMSE)值分别为12.812, 74.365,较之3个基模型分别降低11.00%, 0.94%、4.44%,1.99%与13.03%, 4.39%,能够有效降低价格预测的误差.     

PointPCA:一种三维空间点云的特征提取算法

点云是一个庞大的点的集合而且拥有重要的几何结构。由于其庞大的数据量,不可避免地就会在某些区域内出现一些相似点,这就使得在进行特征提取时提取到一些重复的信息,造成计算冗余,降低训练的准确率。针对上述问题,提出了一种新的神经网络——PointPCA,可以有效地解决上述问题;在PointPCA中,总共分为三个模块：a）采样模块：提出了一种average point samping（APS）采样方法,可以有效地规避一些相似的点,得到一组近似代表这组点云的新的点集;b）特征提取模块：采用分组中的思想,对这组新的点的集合进行多尺度空间特征提取;c）拼接模块：将每一尺度提取的特征向量拼接到一起组合为一个特征向量。经过实验表明,PointPCA比PointNet在准确率方面提升了4.6%,比PointNet++提升了1.1%;而且在mIoU评估测试中也有不错的效果。     

SVPWM教学研究之重点解析

SVPWM是电力电子技术教学中的重要内容,本文对空间矢量调制的教学重点做了一个较为全面系统的梳理。重点阐述SVPWM的核心思想,特别是三相正弦交流电SVPWM的基本原理,严格证明了三相电压的空间矢量相等与线电压相等等价。同时,证明在SVPWM下,逆变器输出的最大圆为基本空间矢量构成的正六边形的内接圆、直流母线电压利用率提高了约15.4%。     

Mammogram Learning System for Breast Cancer Diagnosis Using Deep Learning SVM

The most common form of cancer for women is breast cancer. Recent advances in medical imaging technologies increase the use of digital mammograms to diagnose breast cancer. Thus, an automated computerized system with high accuracy is needed. In this study, an efficient Deep Learning Architecture (DLA) with a Support Vector Machine (SVM) is designed for breast cancer diagnosis. It combines the ideas from DLA with SVM. The state-of-the-art Visual Geometric Group (VGG) architecture with 16 layers is employed in this study as it uses the small size of 3 × 3 convolution filters that reduces system complexity. The softmax layer in VGG assumes that the training samples belong to exactly only one class, which is not valid in a real situation, such as in medical image diagnosis. To overcome this situation, SVM is employed instead of the softmax layer in VGG. Data augmentation is also employed as DLA usually requires a large number of samples. VGG model with different SVM kernels is built to classify the mammograms. Results show that the VGG-SVM model has good potential for the classification of Mammographic Image Analysis Society (MIAS) database images with an accuracy of 98.67%, sensitivity of 99.32%, and specificity of 98.34%.     

A new method using feature extraction for identifying paddy rice species for quality seed selection

The purpose of this work was to explore a new feature extraction method for classifying paddy seeds using a feature extraction algorithm to achieve the area ratio, horizontal–slant and front–rear angles and find whether the proposed features have high discriminating power. Another objective was to find the smallest feature set that can ensure highly accurate recognition of seeds. A total of a 100 image features were extracted, and features having significant discriminating power were identified based on the analysis of variance (ANOVA). From the 100 features, 14 features were found to have high discriminating power and from these features, six were selected as the proposed features. Experimental results show that the proposed features and removal of redundant features enhanced the discriminating power of the feature set, and that the proposed features have an excellent discriminating property for seeds. The presented features resulted in the highest classification accuracy (98.8%) when compared to other methods.     

Structural damage diagnosis using incomplete static responses and LS-SVM

This paper presents novel approach to structural damage detection and estimation using incomplete static responses of a damaged structure and least squares support vector machine (LS-SVM). The presented method is based on the reduced stiffness matrix to formulate incomplete static responses as input parameters to the LS-SVM. The presented method is applied to a plane steel bridge, a four-span continuous beam and four-storey plane frame containing several damages. Also, the effect of the discrepancy in stiffness between the finite element model and the actual tested system has been investigated. The results show that the presented method is sensitive to the location and severity of the structural damage in spite of the incomplete noisy data and modelling errors.