A sensing strategy for the reverse engineering of machined parts

The reverse engineering of machined parts requires sensing an existing part and producing a design (and perhaps a manufacturing process) for it. We have developed a reverse engineering system that has proven effective with a set of machined parts. This paper describes the system, presents some results, and discusses strategy for a new system.This work was supported by ARPA under ARO grant number DAAH04-93-G-0420, DARPA grant N00014-91-J-4123, NSF grant CDA 9024721, and a University of Utah Research Committee grant. All opinions, findings, conclusions or recommendations expressed in this document are those of the authors and do not necessarily reflect the views of the sponsoring agencies.     

抗几何失真的视频Hashing算法研究

文中提出了一种基于视频灰度直方图形状的Hashing算法,能有效抵抗各种常见的几何失真和视频处理操作.算法的鲁棒性原理如下:1)由于直方图的形状与像素位置无关,故基于直方图的视频Hashing算法能有效抵抗各种常见的几何攻击;2)由于在计算Hashing前对视频帧进行了平滑预处理,故算法对加噪攻击、模糊滤波、有损压缩等处理操作有很好的鲁棒性;3)由于计算Hashing前在时间轴上进行了低通滤波预处理,故算法能抵抗帧率变化、帧丢失等时域同步攻击.实验结果表明,所提出的Hashing算法有良好的唯一性和鲁棒性能.     

基于特征线匹配的城市建筑物识别方法研究

随着手机GPS位置测定、导航以及摄像功能的普及,对于移动状态下的位置定位以及都市空间建筑物实时搜索等应用功能存在日益增长的需求。介绍了图像处理方式的城市建筑物识别方法,通过对两种图像匹配算法--SIFT和Local Search的比较分析表明,构造物轮廓线及其组合是一种相对稳定的几何特征,在匹配时受图像的仿射变换、画质变化以及镜头畸变等因素干扰较小,此外,基于轮廓的图像匹配指数还能反映摄影位置的变化。因此,对Local Search进行了改进,利用实时图的建筑物的特征轮廓线与从三维数据库中提取的建筑群特征轮廓线进行匹配,然后选择匹配指数高的记录作为识别结果。结果表明基于Local Search算法的建筑物识别技术可以很好地适应移动条件下建筑物快速识别的要求。     

Automatic Channel Detection Using DNN on 2D Seismic Data

Geologists interpret seismic data to understand subsurface properties and subsequently to locate underground hydrocarbon resources. Channels are among the most important geological features interpreters analyze to locate petroleum reservoirs. However, manual channel picking is both time consuming and tedious. Moreover, similar to any other process dependent on human intervention, manual channel picking is error prone and inconsistent. To address these issues, automatic channel detection is both necessary and important for efficient and accurate seismic interpretation. Modern systems make use of real-time image processing techniques for different tasks. Automatic channel detection is a combination of different mathematical methods in digital image processing that can identify streaks within the images called channels that are important to the oil companies. In this paper, we propose an innovative automatic channel detection algorithm based on machine learning techniques. The new algorithm can identify channels in seismic data/images fully automatically and tremendously increases the efficiency and accuracy of the interpretation process. The algorithm uses deep neural network to train the classifier with both the channel and non-channel patches. We provide a field data example to demonstrate the performance of the new algorithm. The training phase gave a maximum accuracy of 84.6% for the classifier and it performed even better in the testing phase, giving a maximum accuracy of 90%.     

Connecting the dots: Understanding the interrelated impacts of type,quality and children's awareness of design features and the mathematics content learning goals in digital math games and related learning outcomes

This study focused on an examination of how type, quality and children's awareness of design features in digital math games, along with an awareness of the mathematics goals of the game, were related to learning outcomes. We conducted a parallel conversion mixed methods study with 45 students in Grades 3 and 4 (ages 9–10). Students participated in clinical interviews using three digital math games. The results suggest a moderated mediation relationship in which the quality of the design features moderated the mediating impact of children's awareness of the game's design features, specifically when the child was aware of the mathematics content learning goal (MCLG) of the game. These findings show how important it is that design features are of high quality in a digital math game, and how this is intertwined with children's awareness of the features and the MCLG. When these variables intertwined in just the right way, the interactions between the children and the digital math game afforded mathematical learning growth.     

Soft computing approach to fault diagnosis of centrifugal pump

Fault detection and isolation in rotating machinery is very important from an industrial viewpoint as it can help in maintenance activities and significantly reduce the down-time of the machine, resulting in major cost savings. Traditional methods have been found to be not very accurate. Soft computing based methods are now being increasingly employed for the purpose. The proposed method is based on a genetic programming technique which is known as gene expression programming (GEP). GEP is somewhat a new member of the genetic programming family. The main objective of this paper is to compare the classification accuracy of the proposed evolutionary computing based method with other pattern classification approaches such as support vector machine (SVM), Wavelet-GEP, and proximal support vector machine (PSVM). For this purpose, six states viz., normal, bearing fault, impeller fault, seal fault, impeller and bearing fault together, cavitation are simulated on centrifugal pump. Decision tree algorithm is used to select the features. The results obtained using GEP is compared with the performance of Wavelet-GEP, support vector machine (SVM) and proximal support vector machine (PSVM) based classifiers. It is observed that both GEP and SVM equally outperform the other two classifiers (PSVM and Wavelet-GEP) considered in the present study.     

项目部合作开发报表系统

结合项目部合作开发报表生成及查询的实际需要,按照公司报表系统通用要求,全力开发易操作且高效率的报表系统。详细阐述报表系统所应用的软硬件环境、系统特点、系统操作说明及在实际工作中应用的优点综述。     

D-2-DenseNet噪音鲁棒的城市音频分类模型

为了提高噪音环境下城市音频分类系统的鲁棒性,提出了一种双特征2阶密集卷积神经网络（D-2-DenseNet）噪音鲁棒的城市音频分类模型.首先介绍了噪音添加和噪音鲁棒处理,阐述了一种双特征互补偿的算法;然后结合2阶密集卷积神经网络与自适应机制提出了一种噪音鲁棒音频分类模型：双特征2阶密集卷积神经网络.模型采用双特征互补偿自适应算法,可在特征提取与模型训练中更有针对性地提取有效音频信息,降低噪音干扰,以提高噪音鲁棒性.最后,基于Dcase2016数据集开展噪音环境下城市音频分类测试.实验结果表明,模型分类准确率分别可达77.12%、75.52%,与基线模型相比,平均分类准确率分别提高了8.51%和10.38%,验证了模型良好的噪音鲁棒性.     

断层破裂过程对减隔震桥梁地震反应的影响

为了研究断层破裂过程对减隔震桥梁地震反应的影响,提出利用相位特性模拟方向性效应的改进随机格林函数法. 以1994年美国北岭地震的断层条件为例,通过与实际地震记录对比验证模拟方法的有效性;应用改进的随机格林函数法模拟相同震中距离的4组地震动时程作为输入条件,比较断层破裂过程对相同震中距离、不同方位的减隔震桥梁地震反应影响. 结果表明,利用持时包络曲线与相位差分分布的相似性可以方便模拟随机格林函数的地震动加速度时程;在相同震中距离条件下,断层破裂方向的观测点地震动以及对应位置的桥梁结构地震反应明显大于非破裂方向位置的观测点;当破裂方向上地震动时程不具有脉冲特性时,断层周围的减隔震桥梁地震反应主要受地震动强度的影响,桥梁方位的影响不明显.     

一种新颖的低层视觉特征到高层语义的映射方法*

通过在低层视觉特征上提取图像的局部颜色和纹理特征,再利用模糊神经网络建立低层视觉特征和高层语义特征之间的映射,实现了图像属性信息的有效传递和可靠检索.最后,为了提高检索效率,把相关反馈引进到图像检索系统中.实验证明,该方法取得了较好的检索查全率和准确率.