Automatic brain tissue segmentation in MR images using hybrid atlas forest based on confidence-weighted probability matrix

The segmentation of specific tissues in an MR brain image for quantitative analysis can assist the disease diagnosis and medical research. Therefore, a robust and accurate method for automatic segmentation is necessary. Atlas-based-method is a common and effective method of automatic segmentation where an atlas refers to a pair of image consist of an intensity image and its corresponding label image. Apart from the general multi-atlas-based methods, which propagate labels through the single atlas then fuse them, we proposed a hybrid atlas forest based on confidence-weighted probability matrix to consider the atlases set as a whole and treat each voxel differently. In the framework, we first register the atlas to the image space of target and calculate the confidence of voxels in the registered atlas. Then, a confidence-weighted probability matrix is generated and it augments to the intensity image of the atlas or target for providing spatial information of the target tissue. Third, a hybrid atlas forest is trained to gather the features and correlation information among the atlases in the dataset. Finally, the segmentation of the target tissues is predicted by the trained hybrid atlas forest. The segment performance and the components efficiency of the proposed method are evaluated on the two public datasets. Based on the experiment results and quantitative comparisons, our method can gather spatial information and correlation among the atlases to obtain an accurate segmentation.     

基于C#的飞机疲劳试验实时预警系统设计

为满足飞机疲劳试验对试验数据实时监控的需求,采用C#语言开发了一套飞机疲劳试验实时预警系统。该系统以疲劳试验数据管理系统为基础,计算各测量点、各工况的平均值和标准差,通过多种方法设定预警阈值。该系统界面友好、功能完备,可实现疲劳试验数据的实时监控,能够及时发现异常试验数据,尽早发现结构损伤并采取有效措施,可以大幅降低维修成本、缩短维修周期。     

Quantifying community resilience based on fluctuations in visits to points-of-interest derived from digital trace data

This research establishes a methodological framework for quantifying community resilience based on fluctuations in a population''s activity during a natural disaster. Visits to points-of-interests (POIs) over time serve as a proxy for activities to capture the combined effects of perturbations in lifestyles, the built environment and the status of business. This study used digital trace data related to unique visits to POIs in the Houston metropolitan area during Hurricane Harvey in 2017. Resilience metrics in the form of systemic impact, duration of impact, and general resilience (GR) values were examined for the region along with their spatial distributions. The results show that certain categories, such as religious organizations and building material and supplies dealers had better resilience metrics—low systemic impact, short duration of impact, and high GR. Other categories such as medical facilities and entertainment had worse resilience metrics—high systemic impact, long duration of impact and low GR. Spatial analyses revealed that areas in the community with lower levels of resilience metrics also experienced extensive flooding. This insight demonstrates the validity of the approach proposed in this study for quantifying and analysing data for community resilience patterns using digital trace/location-intelligence data related to population activities. While this study focused on the Houston metropolitan area and only analysed one natural hazard, the same approach could be applied to other communities and disaster contexts. Such resilience metrics bring valuable insight into prioritizing resource allocation in the recovery process.     

Using a hybrid two‐stage DEA model to analyze the profitability and marketability of medical manufacturing firms

The purpose of this study is to develop a modification of the model developed by Chen and Zhu in 2004. Calculating stage and overall efficiencies precisely and consistently has become a major challenge of the two‐stage DEA model. However, most other models do not calculate the optimality of intermediates. Although the model developed by Chen and Zhu measures the optimality of intermediates, the calculated efficiency scores still have some shortfalls. The modified model, named the hybrid two‐stage DEA model, fills the gap between calculating the optimality of intermediates and the consistency of overall efficiency scores. In addition to obtaining an accurate measurement for the optimality of intermediates, the model confines efficiency scores to a range from zero to one (a ratio efficiency score). In an empirical evaluation, we use data from 64 medical manufacturing firms to test the performance of the hybrid model and offer recommendations for the industry.     

A wavelet-based multi-dimensional temporal recurrent neural network for stencil printing performance prediction

The solder paste printing (SPP) is a critical procedure in a surface mount technology (SMT) based assembly line, which is one of the major attributes to the defect of the printed circuit boards (PCBs). The quality of SPP is influenced by multiple factors, such as the squeegee speed, pressure, the stencil separation speed, cleaning frequency, and cleaning profile. During printing, the printer environment is dynamically varying due to the physical change of solder paste, which can result in a dynamic variation of the relationships between the printing results and the influential factors. To reduce the printing defects, it is critical to understand such dynamic relationships. This research focuses on determining the printing performance during printing by implementing a wavelet filtering-based temporal recurrent neural network. To reduce the noise factor in the solder paste inspection (SPI) data, this research applies a three-dimensional dual-tree complex wavelet transformation for low-pass noise filtering and signal reconstruction. A recurrent neural network is utilized to model the performance prediction with low noise interference. Both printing sequence and process setting information are considered in the proposed recurrent network model. The proposed approach is validated using practical dataset and compared with other commonly used data mining approaches. The results show that the proposed wavelet-based multi-dimensional temporal recurrent neural network can effectively predict the printing process performance and can be a high potential approach in reducing the defects and controlling cleaning frequency. The proposed model is expected to advance the current research in the application of smart manufacturing in surface mount technology.     

Operational time-series data modeling via LSTM network integrating principal component analysis based on human experience

Today’s information technologies involve increasingly intelligent systems, which come at the cost of increasingly complex equipment. Modern monitoring systems collect multi-measuring-point and long-term data which make equipment health prediction a “big data” problem. It is difficult to extract information from such condition monitoring data to accurately estimate or predict health statuses. Deep learning is a powerful tool for big data processing that is widely utilized in image and speech recognition applications, and can also provide effective predictions in industrial processes. This paper proposes the Long Short-term Memory Integrating Principal Component Analysis based on Human Experience (HEPCA-LSTM), which uses operational time-series data for equipment health prognostics. Principal component analysis based on human experience is first conducted to extract condition parameters from the condition monitoring system. The long short-term memory (LSTM) framework is then constructed to predict the target status. Finally, a dynamic update of the prediction model with incoming data is performed at a certain interval to prevent any model misalignment caused by the drifting of relevant variables. The proposed model is validated on a practical case and found to outperform other prediction methods. It utilizes a powerful deep learning analysis method, the LSTM, to fully process big condition monitoring series data; it effectively extracts the features involved with human experience and takes dynamic updates into consideration.     

Heterogeneous Memristive Models Design and Its Application in Information Security

Based on the three-dimensional classic Chua circuit, a nonlinear circuit containing two flux-control memristors is designed. Due to the difference in the design of the characteristic equation of the two magnetron memristors, their position form a symmetrical structure with respect to the capacitor. The existence of chaotic properties is proved by analyzing the stability of the system, including Lyapunov exponent, equilibrium point, eigenvalue, Poincare map, power spectrum, bifurcation diagram et al. Theoretical analysis and numerical calculation show that this heterogeneous memristive model is a hyperchaotic five-dimensional nonlinear dynamical system and has a strong chaotic behavior. Then, the memristive system is applied to digital image and speech signal processing. The analysis of the key space, sensitivity of key parameters, and statistical character of encrypted scheme imply that this model can applied widely in multimedia information security.     

支持规避设计的海量专利质量评价模型

专利规避设计需从现有专利中遴选具有核心竞争力的目标专利，以提升技术起点。针对设计领域的海量专利信息，提出了专利质量多指标主客观综合评价模型。分析专利书目信息与专利质量存在的正相关关系，甄选存活期、权利项数、同族专利数、引证数和被引证数等书目信息指标，构建了专利质量多指标综合评价指标体系，提升了评价方法的科学性和可操作性；提出将德尔菲法、层次分析法和均方差决策法相结合的主客观赋权法，确定专利质量评价指标权重，既保证了评价的权威性，又减小了个人偏见与从众妥协等因素的影响；建立了基于质量评价模型遴选目标专利的过程模型，并通过应用实例验证了该模型对遴选具有核心竞争力专利的有效性。     

基于聚类的数据加权优化在犯罪预测中的应用

近年来，我国传统暴力犯罪与成年人犯罪呈下降态势，但是，犯罪案由层出不穷。为有效提升公安实践工作中犯罪预测能力，打击各类违法犯罪事件,本文针对犯罪数据，提出一种新型犯罪预测模型。利用密度聚类分析方法将犯罪数据分类，然后进行数据降维提取关键属性生成特征数据，继而对特征数据进行加权优化并采用机器学习的方式对特征数据进行学习，从而预测犯罪案由。实验结果表明，与传统方法相比，本文方法具有更好的预测效果，为公安实践工作中类似案件的侦破和预防，提供新的路径支撑。     

熔融制样-能量色散X射线荧光光谱仪分析硅酸盐中32 种组分

为充分发挥小型实验室设备的功能,实验采用熔融制样,使用台式能量色散X射线荧光光谱仪(10W, Rh靶)定量分析了硅酸盐样品中的Na₂O、MgO、Al₂O₃、SiO₂、P₂O₅、SO₃、Cl、K₂O、CaO、TiO₂、V、Cr、MnO、Fe₂O₃、Co、Ni、Cu、Zn、Ga、Rb、Sr、Y、Zr、Nb、As、Ba、La、Ce、Th、U、Hf、Pb等32种主、次、痕量组分。对3种不同的解谱方法进行比较,确定Na、Mg、Al、Si、P、As、Ce、Cr、Cu、Ga、La、Nb、Ni、Pb、Th、U、V、Y选择感兴趣区解谱,其余元素用高斯或经改进的高斯函数的最小二乘法拟合解谱。选用有代表性的多个硅酸盐类样品,比较了理论检出限及10次重复测定计算3倍标准偏差得出的检出限,发现以3倍标准偏差作为检出限再取它们的平均值则更具代表性和使用意义。各组分的检出限为0.2~1740μg/g。精密度试验表明,各组分测定结果的相对标准偏差(RSD)为0.12%~10.5%(Na为轻元素,由于含量低,小能谱测定的精密度稍差);对两个土壤标准样品进行正确度验证,测定值与标准值一致。