Automatic joint classification and segmentation of whole cell 3D images

We present a machine learning tool for automatic texton-based joint classification and segmentation of mitochondria in MNT-1 cells imaged using ion-abrasion scanning electron microscopy (IA-SEM). For diagnosing signatures that may be unique to cellular states such as cancer, automatic tools with minimal user intervention need to be developed for analysis and mining of high-throughput data from these large volume data sets (typically ). Challenges for such a tool in 3D electron microscopy arise due to low contrast and signal-to-noise ratios (SNR) inherent to biological imaging. Our approach is based on block-wise classification of images into a trained list of regions. Given manually labeled images, our goal is to learn models that can localize novel instances of the regions in test datasets. Since datasets obtained using electron microscopes are intrinsically noisy, we improve the SNR of the data for automatic segmentation by implementing a 2D texture-preserving filter on each slice of the 3D dataset. We investigate texton-based region features in this work. Classification is performed by k-nearest neighbor (k-NN) classifier, support vector machines (SVMs), adaptive boosting (AdaBoost) and histogram matching using a NN classifier. In addition, we study the computational complexity vs. segmentation accuracy tradeoff of these classifiers. Segmentation results demonstrate that our approach using minimal training data performs close to semi-automatic methods using the variational level-set method and manual segmentation carried out by an experienced user. Using our method, which we show to have minimal user intervention and high classification accuracy, we investigate quantitative parameters such as volume of the cytoplasm occupied by mitochondria, differences between the surface area of inner and outer membranes and mean mitochondrial width which are quantities potentially relevant to distinguishing cancer cells from normal cells. To test the accuracy of our approach, these quantities are compared against manually computed counterparts. We also demonstrate extension of these methods to segment 3D images obtained using electron tomography.     

Two-Dimensional Multilabel Active Learning with an Efficient Online Adaptation Model for Image Classification

Conventional active learning dynamically constructs the training set only along the sample dimension. While this is the right strategy in binary classification, it is suboptimal for multilabel image classification. We argue that for each selected sample, only some effective labels need to be annotated while others can be inferred by exploring the label correlations. The reason is that the contributions of different labels to minimizing the classification error are different due to the inherent label correlations. To this end, we propose to select sample-label pairs, rather than only samples, to minimize a multilabel Bayesian classification error bound. We call it two-dimensional active learning because it considers both the sample dimension and the label dimension. Furthermore, as the number of training samples increases rapidly over time due to active learning, it becomes intractable for the offline learner to retrain a new model on the whole training set. So we develop an efficient online learner to adapt the existing model with the new one by minimizing their model distance under a set of multilabel constraints. The effectiveness and efficiency of the proposed method are evaluated on two benchmark data sets and a realistic image collection from a real-world image sharing Web site—Corbis.     

Analysis of application patterns of Z-type MEMS microspring

In this paper, we design a Z-type microspring, which consists of several “Z” type micromechanical beams within mutual connection. With good mechanical performance and mature LIGA fabrication technology, Ni is chosen as the material of Z-type MEMS microspring. The mechanical properties of electroformed Ni have been tested by the Micro Hardness Tester, and the Young’s modulus is 219 GPa. Different from traditional springs, microsprings can be divided into three application patterns in direction x, y, and z to study. Applying the Castigliano second theorem of energy method in macro theory, the formulas used to calculate the spring constant of Z-type microspring in the directions of the three application patterns were derived, and verified by the ANSYS finite element method. Using the Tytron250 micro force test machine, the experiments of the Z-type microspring deformation properties were carried out. The spring constant, rupture force and rupture strength of Z-type microspring in direction y are 3821 N/m, 1.64 N and 1.61 GPa, respectively. The experimental results agree with the theoretical analysis. Based on the analysis above, the change laws of the spring constant of microspring in the three application patterns are summarized.     

电磁流量计示值误差校准不确定度评定

针对目前电磁流量计在出厂时只标注有允许误差或准确度等级,其不确定度未予表述这一现状,依据<电磁流量计检定规程>JJG 1033-2007,进行水流量标准装置实流校验试验.分别介绍了评定的测量依据、环境条件、测量标准、被测对象、测量过程以及评定结果的使用.示值误差校准不确定度分析评定表明,该标定装置的不确定度对于电磁流量计的测量非常重要.     

基于MODIS的海表面温度反演系统设计与实现

海表面温度(SST)是重要的海洋物理参数,对海洋研究具有重要意义.通过遥感数据反演是目前获取SST数据的主要方法之一.遥感反演数据具有反映大区域尺度的海温连续分布状况,且数据获取及时稳定等特点.本文基于IDL构建了面向EOS/MODIS数据的SST反演系统,讨论了系统的功能和结构,给出了具体的数据反演处理流程,对系统中采用的SST反演算法和云检测方法进行了详细说明.最后以我国东海海域为例,将反演结果与多年观测资料对比,表明系统反演得到的SST分布规律与多年观测资料一致,同时还利用同步观测的浮标数据和NASA MODIS SST产品对反演结果进行验证,结果显示系统反演的SST平均误差为1℃.数据精度满足海洋预报和其他科学研究的需要.     

多光谱数据波段选择方法试验研究——以湖北神农架林区为例

本文以神农架林区植被信息提取为例,从统计特征的角度出发,采用最佳指数因子、联合熵与类间、类内可分性判别准则三种波段选择方法。在对三种波段选择方法计算结果综合分析的基础上,结合试验区地物光谱特征和TM传感器不同波段功能,采用逐步逼近的思路,从候选波段组合中确定了最佳波段组合。试验得出TM传感器453波段组合为神农架林区植被信息提取的最佳波段组合。     

基于GA和FEM的夹具布局和变夹紧力优化设计

通过夹具布局和夹紧力大小的优化可以提高薄壁件加工精度．建立了夹具布局和变夹紧力分层优化模型．首先,以工件加工变形最小化和变形最均匀化为目标函数,对夹具布局进行优化设计;其次,基于优化的夹具布局对变夹紧力进行设计．采用有限元法计算工件的加工变形,加工变形求解时综合考虑了接触力、摩擦力、切削力、夹紧力和切屑的影响．采用遗传算法求解优化模型,获得优化的夹具布局和变夹紧力．通过实例分析,验证了分层优化设计方法可以进一步减小工件加工变形,提高加工变形均匀度．     

基于使用控制模型的防恶意下载系统

为了对恶意下载行为实施有效控制,研究通用访问控制框架和使用控制模型(UCON),提出基于流量的UCON。设计并实现基于UCON的防恶意下载系统,阐述其关键技术和实现方法。实验结果表明,该模型能有效控制用户下载行为,具有高安全性和较强的操作灵活性。     

基于无线通信网的桥梁检测系统中转器设计

针对现有桥梁应变多点检测中存在的问题引入无线通信、嵌入式、低功耗等技术,使用C8051微控制器和nRF905无线芯片实现无线组网中转,增加组网能力及测量距离。设计完善的特定无线网络通信协议和基于该协议之上的网络调试接口,使有限的信道得到最大利用,无线数据传输速率得到提高,并增强调试安装测试的灵活性、适应性。该系统不仅能完成传统的静态测试,而且能完成动态测试和单路实时显示。     

基于上下文的自适应运动搜索算法

通过分析序列编码结果,根据已编码帧预测模式分布和序列的运动信息,对运动特性不同的宏块选择不同的运动搜索方案。结合提前退出策略以及分层的搜索模式,提出一种新的运动搜索算法。实验结果表明,算法编码质量接近全搜索算法,算法执行时间小于全搜索算法,在速度和质量上都优于钻石搜索算法、新3步法、六边形搜索算法,适用于不同运动特性的视频序列。