Physics‐based spectral sharpening through filter‐chart calibration

The spectral overlap of color‐sampling filters increases errors when using a diagonal matrix transform, for color correction and reduces color distinction. Spectral sharpening is a transformation of colors that was introduced to reduce color‐constancy errors when the colors are collected through spectrally overlapping filters. The earlier color‐constancy methods improved color precision when the illuminant color is changed, but they overlooked the color distinction. In this article, we introduce a new spectral sharpening technique that has a good compromise of color precision and distinction, based on real physical constraints. The spectral overlap is measured through observing a gray reference chart with a set of real and spectrally disjoint filters selected by the user. The new sharpening method enables to sharpen colors obtained by a sensor without knowing the camera response functions. Experiments with real images showed that the colors sharpened by the new method have good levels of color precision and distinction as well. The color‐constancy performance is compared with the data‐based sharpening method in terms of both precision and distinction. © 2014 Wiley Periodicals, Inc. Col Res Appl, 40, 564–576, 2015     

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。     

Road Extraction from High Resolution Remote Sensing Image based on Shape Analysis with Gestalt Theory

Simulating the psychological experience of human vision，a road extraction model based on the format tower is proposed to extract the road in the high resolution remote sensing image from the perspective of morphology.Firstly，based on the spectral and texture information，the suspected road targets are extracted by using segmentation technology.Then these targets are classified according to their reliability and extract the road targets for each category.Finally，three types of identified road information are verified and merged，and the continuous smooth road extraction results are obtained.Experiments on real high resolution images show that the results are consistent with the visual perception of the human eye，and the overall classification accuracy is higher，indicating that the algorithm is effective and feasible and has good use value.