基于声发射和高斯混合模型的灰岩破裂特征识别研究

通过单轴压缩条件下灰岩破裂过程的声发射试验研究,利用高斯混合模型(GMM)对加载过程声发射信号波形特征进行深入分析,探索性识别灰岩破裂失稳过程的裂纹模式及其前兆特征。分析结果表明,灰岩在单轴加载过程中先后主要存在张拉和剪切两种破裂模式。其中,张拉破裂的声发射信号波形特征在AF-RA坐标空间呈现低A_F值、高R_A值分布;剪切破裂的声发射信号波形特征在AF-RA坐标空间呈现低R_A值、高A_F值,且随着应力的增加分布中心向A_F轴靠拢。GMM分析结果揭示了灰岩在整个应力加载过程中以张拉裂纹为主,在加载前中期几乎全为张拉裂纹,临近破坏阶段过渡到剪切破坏为主。剪切裂纹所占比例的最大值出现在(0.8～0.9)σ_c阶段,也是AF-RA坐标轴分布呈现最大A_F值时。研究结果可为预测早期灰岩破裂失稳提供参考,同时为深入研究识别岩石破裂失稳前兆信号特征提供了一种分析方法。     

基于特征选择和深度信念网络的文本情感分类算法

由于人类语言的复杂性，文本情感分类算法大多都存在因为冗余而造成的词汇量过大的问题。深度信念网络（DBN）通过学习输入语料中的有用信息以及它的几个隐藏层来解决这个问题。然而对于大型应用程序来说，DBN是一个耗时且计算代价昂贵的算法。针对这个问题，提出了一种半监督的情感分类算法，即基于特征选择和深度信念网络的文本情感分类算法（FSDBN）。首先使用特征选择方法（文档频率（DF）、信息增益（IG）、卡方统计（CHI）、互信息（MI））过滤掉一些不相关的特征从而使词汇表的复杂性降低；然后将特征选择的结果输入到DBN中，使得DBN的学习阶段更加高效。将所提算法应用到中文以及维吾尔语中，实验结果表明在酒店评论数据集上，FSDBN在准确率方面比DBN提高了1.6%，在训练时间上比DBN缩短一半。     

基于卷积神经网络的构件分类策略的研究

为了提高软件复用过程中构件检索的效率，分析了软件构件分类技术的优缺点以及构件特征，从构件刻面信息的角度，采用卷积神经网络技术，提出一种基于卷积神经网络的构件分类策略；利用卷积神经网络对构件刻面特征进行提取，减少人为因素，提高刻面信息提取精确性，并训练出基于卷积神经网络的构件分类模型，通过具体的实验，来论证该模型的准确性，以达到提高构件检索效率的目的。     

改进HSR-FCN的服装图像识别分类算法研究

目前网络上的服装图像数量增长迅猛，对于大量服装图像实现智能分类的需求日益增加。将基于区域的全卷积网络（Region-Based Fully Convolutional Networks，R-FCN）引入到服装图像识别中，针对服装图像分类中网络训练时间长、形变服装图像识别率低的问题，提出一种新颖的改进框架HSR-FCN。新框架将R-FCN中的区域建议网络和HyperNet网络相融合，改变图片特征学习方式，使得HSR-FCN可以在更短的训练时间内达到更高的准确率。在模型中引入了空间转换网络，对输入服装图像和特征图进行了空间变换及对齐，加强了对多角度服装和形变服装的特征学习。实验结果表明，改进后的HSR-FCN模型有效地加强了对形变服装图像的学习，且在训练时间更短的情况下，比原来的网络模型R-FCN平均准确率提高了大约3个百分点，达到96.69%。     

基于自监督学习的病理图像层次分割

在苏木精-伊红(HE)染色病理图像中，细胞染色分布的不均匀和各类组织形态的多样性给病理图像的自动分割带来极大挑战。为解决该问题，提出了一种基于自监督学习的病理图像三步层次分割方法，对病理图像中各类组织进行由粗略到精细的全自动逐层分割。首先，根据互信息的计算结果在RGB色彩空间中进行特征选择；其次，采用K-means聚类将图像初步分割为各类组织结构的色彩稳定区域与模糊区域；然后，以色彩稳定区域为训练集采用朴素贝叶斯分类对模糊区域进行进一步分割，得到完整的细胞核、细胞质和胞外间隙这三类组织结构；最后，对细胞核部分进行结合形状和色彩强度的混合分水岭分割得到细胞核间的精确边界，进而量化计算细胞核个数、核占比、核质比等指标。对脑膜瘤HE染色病理图像的分割实验结果表明，所提方法对于染色和细胞形态差异保持较高的鲁棒性，各类组织区域分割误差在5%以内，在细胞核分割精度的对比实验中平均正确率在96%以上，满足临床自动图像分析的要求，其量化结果可以为定量病理分析提供依据。     

A self-adaptive synthetic over-sampling technique for imbalanced classification

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50%-80%) is used for training and the rest—for validation. In many problems, however, the data are highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesizing feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesize data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesizing data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, for example, support vector machines, k-nearest neighbour classifiers deep neural, rule-based classifiers, decision trees, and so forth. The results demonstrated that (a) a significantly more balanced (and fair) classification results can be achieved and (b) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.     

Parameter tuning Naïve Bayes for automatic patent classification

I present an analysis of feature selection for automatic patent categorization. For a corpus of 7,309 patent applications from the World Patent Information (WPI) Test Collection (Lupu, 2019), I assign International Patent Classification (IPC) section codes using a modified Naïve Bayes classifier. I compare precision, recall, and f-measure for a variety of meta-parameter settings including data smoothing and acceptance threshold. Finally, I apply the optimized model to IPC class and group codes and compare the results of patent categorization to academic literature.     

油藏开发地质勘探的常见问题分析

就油藏开发地质勘探的常见问题进行分析,从油藏开发的分类、油藏开发程序以及油藏储量计算等方面综合考虑影响油藏开发的因素,为现实油藏开发工程提供理论依据,提升油藏开发技术水准。     

Geographical discrimination of honeys through antioxidant capacity,mineral content and colour

The assessment of geographical origin of honey is economically important for producers and consumers as every region may present particular quality characteristics. In this study, honeys from the seven different regions of Buenos Aires province (Argentina) were characterised by their antioxidant capacity (DPPH, FRAP), total phenolic content (TPC), mineral composition, colour and ash. Honeys showed significant differences among their antioxidant capacity (DPPH), ash, colour and mineral content (P ≤ 0.05). Besides, a good antioxidant activity and low amounts of Cu and Zn (<1.0–1.5 and 0.7–1.8 mg kg^?1, respectively) were found in the samples. Significant Pearson's correlations (P ≤ 0.05) among the different parameters were found. Moreover, the linear discriminant analysis allowed the classification of honeys in their original groups with a prediction success of 98%. The present results suggest that honeys could be correctly classified by their geographical origin through their TPC, colour, ash and mineral concentrations.     

Multiobjective PSO based adaption of neural network topology for pixel classification in satellite imagery

The proposed work involves the multiobjective PSO based adaption of optimal neural network topology for the classification of multispectral satellite images. It is per pixel supervised classification using spectral bands (original feature space). This paper also presents a thorough experimental analysis to investigate the behavior of neural network classifier for given problem. Based on 1050 number of experiments, we conclude that following two critical issues needs to be addressed: (1) selection of most discriminative spectral bands and (2) determination of optimal number of nodes in hidden layer. We propose new methodology based on multiobjective particle swarm optimization (MOPSO) technique to determine discriminative spectral bands and the number of hidden layer node simultaneously. The accuracy with neural network structure thus obtained is compared with that of traditional classifiers like MLC and Euclidean classifier. The performance of proposed classifier is evaluated quantitatively using Xie-Beni and β indexes. The result shows the superiority of the proposed method to the conventional one.