Systematic image quality assessment for sewer inspection

Closed circuit television (CCTV) has been applied in many developing or developed counties for sewer inspection due to its low setup cost and technical requirement. Several automated diagnosis systems of sewer pipe defects had been developed to assist the technicians in interpreting or classifying sewer pipe defects. However, many researchers pointed out that good image quality is the prerequisite for accurate interpretation and diagnosis of CCTV inspection but has not a proper evaluation approach. In this paper, a CCTV image quality index considering both of the luminance distortion and the contrast distortion of a CCTV image compared by reference images is proposed and was applied to assess the image quality of the CCTV images shot for a sewer house-connection project. The experimental result indicates that rather than luminance contrast plays a more important role in the CCTV image quality that can be effectively improved by contrast enhancement. Since CCTV image quality can hardly distinguished by human eyes, the proposed image quality index can provide helpful information to efficiently assist the on-site technicians in precisely shooting better CCTV images for the pipe defection. Additionally, a sensitivity analysis of contrast stretch was implemented to quantify the CCTV image quality improvement. CCTV imaging conditions, such as pipe materials and imager status, are found as the factors affecting the CCTV image quality. In the future, a real-time CCTV image quality assessment will be developed by modifying the CCTV image quality index as an instantaneous reference for imaging adjustment that can be expected to be practicable for the on-site sewer inspection because of the extremely short computation time.     

Implementing automated diagnostic systems for breast cancer detection

This paper intends to an integrated view of implementing automated diagnostic systems for breast cancer detection. The major objective of the paper is to be a guide for the readers, who want to develop an automated decision support system for detection of breast cancer. Because of the importance of making the right decision, better classification procedures for breast cancer have been searched. The classification accuracies of different classifiers, namely multilayer perceptron neural network (MLPNN), combined neural network (CNN), probabilistic neural network (PNN), recurrent neural network (RNN) and support vector machine (SVM), which were trained on the attributes of each record in the Wisconsin breast cancer database, were compared. The purpose was to determine an optimum classification scheme with high diagnostic accuracy for this problem. This research demonstrated that the SVM achieved diagnostic accuracies which were higher than that of the other automated diagnostic systems.     

Implementing automated diagnostic systems for breast cancer detection

This paper intends to an integrated view of implementing automated diagnostic systems for breast cancer detection. The major objective of the paper is to be a guide for the readers, who want to develop an automated decision support system for detection of breast cancer. Because of the importance of making the right decision, better classification procedures for breast cancer have been searched. The classification accuracies of different classifiers, namely multilayer perceptron neural network (MLPNN), combined neural network (CNN), probabilistic neural network (PNN), recurrent neural network (RNN) and support vector machine (SVM), which were trained on the attributes of each record in the Wisconsin breast cancer database, were compared. The purpose was to determine an optimum classification scheme with high diagnostic accuracy for this problem. This research demonstrated that the SVM achieved diagnostic accuracies which were higher than that of the other automated diagnostic systems.     

Fault diagnosis of power transformer based on support vector machine with genetic algorithm

Diagnosis of potential faults concealed inside power transformers is the key of ensuring stable electrical power supply to consumers. Support vector machine (SVM) is a new machine learning method based on the statistical learning theory, which is a powerful tool for solving the problem with small sampling, nonlinearity and high dimension. The selection of SVM parameters has an important influence on the classification accuracy of SVM. However, it is very difficult to select appropriate SVM parameters. In this study, support vector machine with genetic algorithm (SVMG) is applied to fault diagnosis of a power transformer, in which genetic algorithm (GA) is used to select appropriate free parameters of SVM. The experimental data from several electric power companies in China are used to illustrate the performance of the proposed SVMG model. The experimental results indicate that the SVMG method can achieve higher diagnostic accuracy than IEC three ratios, normal SVM classifier and artificial neural network.     

基于小波包能量谱和M-ary SVM的功率变换器故障诊断

针对功率变换器的故障诊断问题,提出一种基于小波包能量谱和M-ary支持向量机的故障诊断方法。首先,通过小波包分解得到故障信号能量谱特征向量,并结合傅里叶变换分析故障信号主要频率特征点,实现故障特征向量的降维;然后,基于M-ary支持向量机的分类模型诊断出功率变换器多故障模式。实验结果表明,相比于传统的BP神经网络和一对一支持向量机故障诊断方法,本文方法诊断精度高,需要的子分类器数目少,诊断速度快,适用于在线故障诊断。      

基于SVM-MLP的乳腺癌预测

乳腺癌一直是影响女性健康最重要的问题之一,已经成为全球女性发病率最高的恶性肿瘤.近年来,利用机器学习和深度学习方法来诊断癌症已经成为发展较快的一个分支.通过使用逻辑回归模型(LR)、高斯核函数支持向量机(SVM)、前馈神经网络(MLP)对同一数据集进行预测,得出其中SVM迭代时间最短,前馈神经网络预测准确率最高.为了减...     

Integrating radiologist feedback with computer aided diagnostic systems for breast cancer risk prediction in ultrasonic images: An experimental investigation in machine learning paradigm

With advancements in machine learning algorithms and computer aided diagnostic (CAD) systems, the performance of automated analysis of radiological images has improved substantially in recent times. However, the lack of integration between the radiologist and CAD systems restrains the rate of progress as well as the reach of such advancements in clinical use. This article aims to improve the clinical efficiency of ultrasound based CAD systems for classification of breast lesions by integrating back-propagation artificial neural network (BPANN), support vector machine (SVM) and radiologist feedback. The acquired breast ultrasound images were subjected to wavelet based filtering in order to reduce speckle noise followed by feature extraction, feature selection and classification. Experiments on a database of 178 ultrasound images of breast anomalies (88 benign and 90 malignant) show that the proposed methodology achieves classification accuracy of 98.621% and 98.276%, respectively, when all 457 and 19 most relevant features selected by multi-criteria feature selection method were used for classification. The accuracy achieved is significantly higher than that using conventional classifiers based on BPANN and SVM. Further, it is found that integrating expert opinion in CAD systems improves its overall performance. The quantitative results obtained are discussed in light of some recently reported studies.     

基于支持向量机的机械故障智能分类研究

故障样本不足是制约故障诊断技术向智能化方向发展的主要原因之一，支持向量机（SVM)是一种基于统计学习理论(SLT)的机器学习算法，它能在训练样本很少的情况下达到很好的分类效果，从而为故障诊断技术向智能化发展提供了新的途径．本文介绍了支持向量机分类算法，以滚动轴承的故障分类为例，探讨了该算法在故障诊断领域中的应用，并与BP神经网络分类方法进行了对比研究，结果表明，SVM方法在少样本情况下的分类效果优于BP神经网络分类方法．     

基于机器视觉和轻量级卷积网络的安瓿瓶包装质量检测算法

针对人工检测安瓿瓶包装质量时存在的速度慢以及受主观因素影响导致的准确率低等问题，提出一种机器视觉和轻量级卷积神经网络结合的安瓿瓶包装质量检测方法。首先，采用机器视觉中基于阈值分割以及仿射变换的方法对待测图片进行阈值处理、倾斜校正和安瓿瓶区域的裁剪；然后，根据图像特点以及缺陷识别要求设计分类算法的网络结构；最后，采集生产现场图片构建安瓿瓶包装缺陷数据集，之后对提出的安瓿瓶包装缺陷识别网络进行了验证，并测试了部署在Jetson Nano嵌入式平台上的算法的准确率及检测速度。实验结果表明：以每盒五支装的产品为例，所提安瓿瓶包装质量检测算法平均每盒耗时70.1 ms，即可达14盒/秒，而准确率为99.94%，能够实现在Jetson Nano嵌入式平台上的在线高精度安瓿瓶包装质量检测。     

Pixel-Wise Defect Detection by CNNs without Manually Labeled Training Data

In machine learning driven surface inspection one often faces the issue that defects to be detected are difficult to make available for training, especially when pixel-wise labeling is required. Therefore, supervised approaches are not feasible in many cases. In this paper, this issue is circumvented by injecting synthetized defects into fault-free surface images. In this way, a fully convolutional neural network was trained for pixel-accurate defect detection on decorated plastic parts, reaching a pixel-wise PRC score of 78% compared to 8% that was reached by a state-of-the-art unsupervised anomaly detection method. In addition, it is demonstrated that a similarly good performance can be reached even when the network is trained on only five fault-free parts.     

支持向量机在工业过程中的应用

支持向量机(SVM)是一种基于统计学习理论,针对小样本学习问题的通用学习算法,它采用结构风险最小化(Structural risk minimization,SRM)准则,大大提高了模型的泛化能力,成功地解决了神经网络的过学习问题。目前主要应用在模式识别领域,在工业过程中的应用相对较少。本文首先从理论研究、算法结构、参数选择和扩展SVM4个方面详细介绍了近些年来支持向量机的研究进展;然后对SVM在工业过程中的应用现状进行分析,指出进一步研究的方向。     

基于机器视觉和轻量级卷积网络的安瓿瓶包装质量检测算法

针对人工检测安瓿瓶包装质量时存在的速度慢以及受主观因素影响导致的准确率低等问题,提出一种机器视觉和轻量级卷积神经网络结合的安瓿瓶包装质量检测方法。首先,采用机器视觉中基于阈值分割以及仿射变换的方法对待测图片进行阈值处理、倾斜校正和安瓿瓶区域的裁剪;然后,根据图像特点以及缺陷识别要求设计分类算法的网络结构;最后,采集生产现场图片构建安瓿瓶包装缺陷数据集,之后对提出的安瓿瓶包装缺陷识别网络进行了验证,并测试了部署在Jetson Nano嵌入式平台上的算法的准确率及检测速度。实验结果表明：以每盒五支装的产品为例,所提安瓿瓶包装质量检测算法平均每盒耗时70.1 ms,即可达14盒/秒,而准确率为99.94%,能够实现在Jetson Nano嵌入式平台上的在线高精度安瓿瓶包装质量检测。     

PSO-SVM算法在肝脏B超图像识别中的应用

为提高肝脏B超图像的诊断准确率,研究了将粒子群算法(Particle Swarm Optimization,PSO)和支持向量机(Support Vec-tor Machine,SVM)相结合进行肝脏B超图像识别的方法;该方法首先提取肝脏B超图像的空域和频域的纹理特征,然后运用SVM对108幅肝脏B超图像进行分类,利用PSO算法优化SVM的模型参数,最后将该方法与基于网格搜索法优化的SVM和基于BP神经网络的分类方法进行了对比;实验结果表明,在PSO-SVM算法下,所提取的两种纹理特征相结合能够有效地描述肝脏B超图像,基于粒子群优化算法的支持向量机模型具有较高的识别精度,平均分类准确率达94.44%,这就表明PSO-SVM算法适用于对肝脏B超图像的识别。     

基于卷积神经网络及改进支持向量机的行人检测

针对自动驾驶实际道路场景复杂导致行人误检率高的问题,提出一种基于卷积神经网络及改进支持向量机的行人检测方法。利用聚合通道特征快速获取图像候选区域,将归一化后的候选区域图像输入卷积神经网络对其进行深度特征提取;利用主成分分析法将卷积神经网络末端所得到的特征向量进行降维处理,减少其冗余特征信息以获得精确的行人特征描述;将行人特征送至优化后的支持向量机完成分类。考虑支持向量机在分类过程中存在核函数参数选择困难的问题,利用改进后的蚁群算法对其进行优化选择,获得最优支持向量机参数以提高分类精度。实验结果表明,不同场景下的行人平均检测精确度达到92%,误检率大幅下降且具有较好的实时性。     

A study of pipe interacting corrosion defects using the FEM and neural networks

In this paper we present an application of the neural network technology for the assessment of pipes with interacting defects. Finite element simulations are carried out on a pipe containing two aligned and equally shaped defects of 80 × 32 mm and various defect spacing, providing a database containing the relation between the failure pressures of pipes with multiple and single defects. Neural networks are conceived by using this database, establishing interaction rules and a pipe assessment of interacting defects in the longitudinal and circumferential directions. The neural networks results are compared with those derived from the Det Norske Veritas code (DNV RP-F101).     

支持向量机与RBF神经网络回归性能比较研究

支持向量机与RBF神经网络相比各有优缺点,通过对支持向量机与RBF神经网络的研究,从理论上分析了这两种学习机在回归预测原理上的异同,通过仿真实验对比了两者在测试集上的逼近能力及泛化能力。仿真结果表明,对于小样本集,支持向量机的逼近能力及泛化能力要优于RBF神经网络。对实际应用中回归模型的选择问题提出了建议。     

无线视网膜成像系统

针对传统检眼镜、眼底照相机等眼科检查设备结构复杂、移动性差、不能实时观察视网膜情况等缺陷,设计和实现了一种无线视网膜成像系统.对视网膜图像获取和WiFi无线局域网技术进行了研究,通过WiFi无线局域网技术、HTTP网络编程,用装有网卡的PC机远程控制眼底照相机采集视网膜图像,并将图像进行实时传输、显示和保存.最终将装有网卡的PC机与眼底照相机通过WiFi相连接,方便快捷的完成视网膜图像的无线采集和实时观察,为医生提供眼科疾病诊断、治疗的客观依据.     

Fault diagnosis of sensor by chaos particle swarm optimization algorithm and support vector machine

Fault diagnosis of sensor timely and accurately is very important to improve the reliable operation of systems. In the study, fault diagnosis of sensor by chaos particle swarm optimization algorithm and support vector machine is presented in the paper, where chaos particle swarm optimization is chosen to determine the parameters of SVM. Chaos particle swarm optimization is a kind of improved particle swarm optimization, which can not only avoid the search being trapped in local optimum and but also help to search the optimum quickly by using chaos queues. The wireless sensor is employed as research object, and its four fault types including shock, biasing, short circuit and shifting are applied to test the diagnostic ability of CPSO-SVM compared with other diagnostic methods. The diagnostic results show that CPSO-SVM has higher diagnostic accuracy of wireless sensor than PSO-SVM and BP neural network.     

基于改进果蝇算法的模拟电路故障诊断

针对模拟电路中非线性元件故障的定位问题,提出一种改进的果蝇算法优化支持向量机的故障诊断方法。首先对被诊断电路的输出信号进行采样,用Volterra级数提取输出信号的特征,然后利用改进的果蝇算法优化SVM的核函数参数和结构参数,建立诊断模型,在对数放大器电路中对故障进行诊断分类。通过实验可以看出,该方法能够有效避免支持向量机参数选择的随机性,有利于提高诊断精度,并且有较快的诊断速度。     

Malignant Mesothelioma Disease Diagnosis using Data Mining Techniques

Malignant mesothelioma (MM) is very aggressive progress tumors of the pleura. MM in humans results from exposure to asbestos and asbestiform fibers. The incidence of MM is extremely high in some Turkish villages. Under computationally efficient data mining (DM) techniques, classification procedures were performed for MM disease diagnosis. The support vector machine (SVM) achieved promising results, outperforming the multilayer perceptron ensembles (MLPE) neural network method. It was observed that SVM is the best classification with 99.87% accuracy obtained via 10-fold crossvalidation in 5 runs when compare to MLPE neural network, which gives 99.56% classification accuracy. Sensitivity analysis is performed to find the important inputs for MM disease diagnosis under SVM model. Alkaline phosphatase (ALP) ranging from 300 to 500 gives the maximum possibility of having the MM disease. The MM disease dataset was prepared from a faculty of medicine’s database using new patient’s hospital reports from the south east region of Turkey.