Logistic Regression Analysis of Customer Satisfaction Data

Variation exists in all processes. Significant work has been done to identify and remove sources of variation in manufacturing processes resulting in large returns for companies. However, business process optimization is an area that has a large potential return for a company. Business processes can be difficult to optimize due to the nature of the output variables associated with them. Business processes tend to have output variables that are binary, nominal or ordinal. Examples of these types of output include whether a particular event occurred, a customer's color preference for a new product and survey questions that assess the extent of the survey respondent's agreement with a particular statement. Output variables that are binary, nominal or ordinal cannot be modeled using ordinary least‐squares regression. Logistic regression is a method used to model data where the output is binary, nominal or ordinal. This article provides a review of logistic regression and demonstrates its use in modeling data from a business process involving customer feedback. Copyright © 2006 John Wiley & Sons, Ltd.     

Answer to comment on ‘Noiseless amplification in cavity-based optical systems with an internal two-photon process. II. Self-frequency-doubling laser and second-harmonic generation,self-down-converting laser’

Abstract

A simple method to achieve space-variant pattern recognition is proposed with a typical VanderLugt arrangement, in which the input pattern is modulated by a random binary phase function. The output correlation location can be programmed into the filter function. With the introduction of random binary phase modulation, the impulse response of either phase-only or binary phase-only filter function is not edge enhanced, resulting in higher Horner efficiency. Computer simulations are conducted to verify the proposed method.     

Underreporting in traffic accident data, bias in parameters and the structure of injury severity models

Injury severities in traffic accidents are usually recorded on ordinal scales, and statistical models have been applied to investigate the effects of driver factors, vehicle characteristics, road geometrics and environmental conditions on injury severity. The unknown parameters in the models are in general estimated assuming random sampling from the population. Traffic accident data however suffer from underreporting effects, especially for lower injury severities. As a result, traffic accident data can be regarded as outcome-based samples with unknown population shares of the injury severities. An outcome-based sample is overrepresented by accidents of higher severities. As a result, outcome-based samples result in biased parameters which skew our inferences on the effect of key safety variables such as safety belt usage. The pseudo-likelihood function for the case with unknown population shares, which is the same as the conditional maximum likelihood for the case with known population shares, is applied in this study to examine the effects of severity underreporting on the parameter estimates. Sequential binary probit models and ordered-response probit models of injury severity are developed and compared in this study. Sequential binary probit models assume that the factors determining the severity change according to the level of the severity itself, while ordered-response probit models assume that the same factors correlate across all levels of severity. Estimation results suggest that the sequential binary probit models outperform the ordered-response probit models, and that the coefficient estimates for lap and shoulder belt use are biased if underreporting is not considered. Mean parameter bias due to underreporting can be significant. The findings show that underreporting on the outcome dimension may induce bias in inferences on a variety of factors. In particular, if underreporting is not accounted for, the marginal impacts of a variety of factors appear to be overestimated. Fixed objects and environmental conditions are overestimated in their impact on injury severity, as is the effect of separate lap and shoulder belt use. Combined lap and shoulder belt usage appears to be unaffected. The parameter bias is most pronounced when underreporting of possible injury accidents in addition to property damage only accidents is taken into account.     

Ordinal profile monitoring with random explanatory variables

Profiles characterise the functional relationship between the response variable and one or more explanatory variables and have been playing an important role in many applications. Profile monitoring mainly aims at checking the stability of this relationship. In many situations, we observe that the response variable is categorical with three or more attribute levels, and that there is natural order among the levels. Moreover, the explanatory variables are also random rather than fixed at some predefined values. To fully exploit the ordinal information, it is assumed that there is an unknown latent continuous distribution determining the levels of the ordinal response. Based on this, we propose a novel control chart for jointly monitoring the functional relationship, location shifts in the latent continuous distribution, and the random explanatory variables. Simulation results show that our proposed chart is efficient in detecting abnormalities and is robust to various latent distributions.     

Four-plane space-variant Fresnel-transform optical processor with a random phase encoder

We introduce a four-plane Fresnel-transform space-variant optical processor consisting of an input plane and two filter planes. One filter mask is programmable with a spatial light modulator. The second filter mask is a fixed random binary phase array with a known pseudorandom distribution of pixels. The order of the masks can be interchanged, giving different output characteristics. In one case the Horner efficiency of the correlator increases dramatically. In the other case the edge enhancement of the output image is removed. We discuss the theory for this general processor and its implementation with phase-only masks. We present experimental results when a binary magneto-optic spatial light modulator was used.     

单兵智能头盔在消防救援中的探索与应用

目的 在消防装备于高层建筑、地下建筑、大型商业综合体等复杂救援环境中无法满足信息感知和状态感知需求的背景下,探索和分析智能头盔当前在应急救援、军队作战、采矿安全等领域的应用研究现状,以期解决当前消防救援活动中环境视野差、协同效率低、救援人员健康状态无法保证等问题,提高消防救援装备的功能性和保障性,避免救援活动中可能发生的安全事故。方法 人工智能、多设备协作、多模态感知等概念是智慧消防新的发展结合点,以消防救援装备的智能化、集成化趋势为基础,提出了利用增强现实技术满足视觉增强、信息协同、物体识别等信息感知需求,利用脑电监测技术满足人员健康状态监测、疲劳预警等状态感知需求。结论 在城市快速发展的背景下,单兵智能头盔在消防救援领域的应用具有可靠性高、功能扩展性强、任务辅助效率高等优势,但同时面临功耗大、重量大、设备交互研究不足等挑战;适用于消防救援场景的单兵智能头盔有动态舒适性多目标优化、多通道类人感知和意图协同交互、系统故障诊断及容错控制等方面的设计研究趋势。     

Large hydrocarbon fuel pool fires: physical characteristics and thermal emission variations with height

In a recent paper [P.K. Raj, Large LNG fire thermal radiation-modeling issues and hazard criteria revisited, Process Safety Progr., 24 (3) (2005)] it was shown that large, turbulent fires on hydrocarbon liquid pools display several characteristics including, pulsating burning, production of smoke, and reduced thermal radiation, with increasing size. In this paper, a semi-empirical mathematical model is proposed which considers several of these important fire characteristics. Also included in this paper are the experimental results for the variation of the fire radiance from bottom to top of the fire (and their statistical distribution) from the largest land spill LNG pool fire test conducted to date. The purpose of the model described in this paper is to predict the variation of thermal radiation output along the fire plume and to estimate the overall thermal emission from the fire as a function its size taking into consideration the smoke effects. The model utilizes experimentally measured data for different parameters and uses correlations developed from laboratory and field tests with different fuels. The fire dynamics and combustion of the fuel are modeled using known entrainment and combustion efficiency parameter values. The mean emissive power data from field tests are compared with model predictions. Model results for the average emissive powers of large, hypothetical LNG fires are indicated.     

Diffraction efficiency of random binary-amplitude diffracting screens

The diffraction characteristics of random binary-amplitude diffracting screens are investigated. It is shown that, for such a random diffracting screen with complex amplitude transmittance t equal to either 0 or 1, the diffraction efficiency of the screen is maximized when 50% of the screen has transmittance t = 1, independent of other characteristics of the screen. The maximum diffraction efficiency equals ?. For this result to hold the screen must be adequately modeled by a stationary binary random process.     

Metaheuristics for the Stochastic Hoist Scheduling Problem (SHSP)

Experts look for solutions to increase production delivery, but industrial systems are generally disturbed by random events. In many cases, there is a lack of information about random events consequences on the production time and quality of the manufactured products. Surface treatment lines are robotic cells with time window constraints and so random events can have important consequences on production management. Products could be damaged by constraint violations and rejected by the control quality department. Moreover, owing to the structure of these systems, variations in transportation times can induce unrecoverable situations (deadlock occurrences, for example). Therefore, experts look for schedules to prevent random events consequences. One of the most difficult operational problems in surface treatment lines is the proper coordination of the material-handling resources management and job input scheduling. Previous related research works concern the makespan minimization problem and do not take into account the random events consequences: this problem is denoted by the Hoist Scheduling Problem (HSP). This paper focuses on the Stochastic Hoist Scheduling Problem (SHSP), which is the HSP with random events implying variations in transportation times. It appears that no previous work can be reported concerning such stochastic problems but only deterministic ones. A method is proposed here based on stochastic metaheuristics used to determine the production schedules for which the random events consequences are low. An industrial study that highlights the efficiency of the method is proposed. A company that cannot be named for confidential reasons has provided the test data.     

基于集成创新理论的城市主战消防车设计

目的 在城市消防救援任务日渐复杂的背景下,消防应急救援车辆使用功能需求更加细分,呈现出不同的功能形态和使用需求。为了应对复杂的城市抢险救援工作,通过设计一款城市主战消防车,满足消防车适用当前城市救援任务的需求。方法 以集成创新理论为指导,调研和分析国内外城市主战消防车的造型、乘员室以及器材的布置,总结国内此类车型存在的不足,提出消防车设计原则,并设计一款消防车进行论证分析。结论 采用集成创新设计,把现有的各种资源要素优化组合,进行创造性设计,能够显著提高消防车综合性能,更好地执行消防救灾灭火任务,减少社会财产损失,促进经济的平稳发展以及人们安定的生活。     

Analyzing ordinal data from a split-plot design in the presence of a random block effect

Many industrial experiments involve some factors that are hard to change. In this situation, experimenters often choose to perform an experiment with restricted randomization, such as a split-plot or a strip-plot experiment. In this article, we discuss the analysis of an experiment concerning the adhesion between steel tire cords and rubber. Besides an ordinal response, the experiment also involves one hard-to-change factor. Therefore, the experimenters performed a split-plot experiment. An additional complication of the experiment is that there is also a blocking factor. A proper analysis of the experiment requires the inclusion of random effects in the model to account for its split-plot nature and its blocked nature. The need for random effects and the ordinal response necessitate the use of a mixed cumulative logit model.     

Lifeguards in the sky: Examining the public acceptance of beach-rescue drones

The use of rescue drones is expected to increase in forthcoming years. However, the success of their implementation through different applications will depend on public acceptance. Studies to date have analyzed public support for the use of drones with various applications, although public acceptance of drones in specific contexts remains to be explored. In particular, the use of drones for beach rescues has proven beneficial in reducing response times, thus helping to save lives. In this study, we analyze the public acceptance of lifesaving drones and their associated variables. Data collected from a survey of beach users (N = 3363) for this study are used to measure public acceptance of rescue drones. We found that public acceptance of rescue drones is moderate, with approximately half of all participants accepting their use. In terms of influencing variables, we found that the factors most associated with their use are ‘perceived benefits’ and ‘perceived risks’. We also found that the participants from beaches without lifeguard services were more likely to accept the use of rescue drones. These results initiated a discussion on the variables that are associated with the public acceptance in the specific context of lifesaving. In addition, based on the results of this study, we propose implementation plans for rescue drones that might also include public information campaigns on their benefits for beach users.     

以问题为导向的老旧小区火灾救援产品设计

目的 老旧小区因建筑规划不完善,物业管理不规范,容易成为火灾高发地,且不便于组织施救,对当地居民生命财产安全形成了巨大威胁,基于此,进一步探索适应于这一特殊环境的火灾救援解决方案。方法 以问题为导向,分析老旧小区环境混乱、配套设施不足,以及现有救援产品针对性、适应性不强等原因,并引入基础条件、核心功能和附属功能等影响因素,分别从通过性、水源、行进、作业、工效和美学等方面进行定义,并分解成若干问题微单元,最后精确锁定、逐一破解。结论 以问题为导向的设计思维,能将设计对象的本质清晰地呈现出来,在应用于老旧小区火灾救援产品设计过程中,将问题划分为适应配套缺陷的基本问题、保证功能实施的核心问题、促使方案完善的延伸问题等3个层次,系统地解决各类难题,最终获得切实可行、符合实际需求的产品方案。     

A Machine-Fabricated 3D Honeycomb-Structured Flame-Retardant Triboelectric Fabric for Fire Escape and Rescue

Fire disaster is one of the most common hazards that threaten public safety and social development: how to improve the fire escape and rescue capacity remains a huge challenge. Here, a 3D honeycomb-structured woven fabric triboelectric nanogenerator (F-TENG) based on a flame-retardant wrapping yarn is developed. The wrapping yarn is fabricated through a continuous hollow spindle fancy twister technology, which is compatible with traditional textile production processes. The resulting 3D F-TENG can be used in smart carpets as a self-powered escape and rescue system that can precisely locate the survivor position and point out the escape route to timely assist victim search and rescuing. As interior decoration, the unique design of the honeycomb weaving structure endows the F-TENG fabric with an excellent noise-reduction ability. In addition, combining with its good machine washability, air permeability, flame-retardency, durability, and repeatability features, the 3D F-TENG may have great potential applications in fire rescue and wearable sensors as well as smart home decoration.     

非储压干粉灭火装置产气药柱的性能研究

基于非储压干粉灭火装置的安全、高效等特点,设计不同氧化剂配比的产气药柱的基本配方,对比不同氧差下药柱的燃速,并对残渣进行XRD试验分析、产气量测试比较。结果表明:氧化剂含量对燃速和产气量影响很大,设计氧差时要考虑氧化剂耗氧量;药柱燃烧后残渣过多会降低性能。为寻求稳定燃速和低残渣,应控制氧差在-15至-20之间为佳。最优基本配方（质量分数）是氧化剂77.2%、可燃剂11.4%、黏结剂11.4%。氧差-15时,燃速达到8.95 g/s,产气量为0.245 L/g;较某消防药柱产气量提升19%。     

Emergency medical service rescue times in Riyadh

The emergency medical service (EMS) in Saudi Arabia is managed by each hospital through the Saudi Red Crescent Society (SRCS). There are approximately 165 ambulance stations in the country, each with two ambulances. The SRCS collects data on EMS requests and ambulance arrival times at the accident scene. Each emergency incident has its own implications (accident, fire, injury, etc.) and must be dealt with individually. The aims of this study are to evaluate ambulance rescue time, which includes response time, in the city of Riyadh, the capital of Saudi Arabia; to analyze this time for road traffic accidents; and to compare the response time in Riyadh with corresponding times in other countries. A sample of 874 emergency calls was collected during 1999. Ambulance rescue time consists of three components: response time, time at the scene and travel time to the hospital. Data analysis showed that rescue time is, on average, 35.84 min (S.D. = 6.43 min). Within this time, the average response time is 10.23 min (S.D. = 5.66 min). Other service components (e.g. ambulance time at the accident scene and travel time to the hospital) are analyzed and detailed statistics are given. Ambulance speed to the accident averages approximately 55.05 km/h (S.D. = 27.42 km/h). One primary finding is that there is room for improvement in the rescue time in Riyadh, which would save more lives, through an increase in the efficiency of ambulance team performance. A test statistic is developed in this study to carry out a simple hypothesis testing for percentiles. This test statistic, which is generic and can be used for other applications, is used to compare EMS response time in Riyadh with that in other parts of the world.     

Regulating safety in an unsafe world (risk reduction for and with communities)

Safety regulators and the public they serve often have contrasting views on risk perception and the veracity of institutional estimates of risk and harm. Conflict and distrust between these groups is often a result of a lack of public involvement in decision making on safety related matters. Such concerns also emerge from differences in professional training, authority and experience between the groups. Fire services internationally, carryout fire safety assessments on behalf of communities. This assessment role is unusual in that unlike conventional approaches to regulatory safety assessment, fire fighters are direct end-users of their own regulatory assessment and closer to the people they protect. This paper discusses how fire services are beginning to seek closer links with communities by defining clear regulatory frameworks for conventional safety assessments and conceptual frameworks that allow a redefinition of their role towards establishing partnerships with communities to promote sustained safety.     

Representation and problem solving with Distribution Envelope Determination (DEnv)

Distribution Envelope Determination (DEnv) is a method for computing the CDFs of random variables whose samples are a function of samples of other random variable(s), termed inputs. DEnv computes envelopes around these CDFs when there is uncertainty about the precise form of the probability distribution describing any input. For example, inputs whose distribution functions have means and variances known only to within intervals can be handled. More generally, inputs can be handled if the set of all plausible cumulative distributions describing each input can be enclosed between left and right envelopes. Results will typically be in the form of envelopes when inputs are envelopes, when the dependency relationship of the inputs is unspecified, or both. For example in the case of specific input distribution functions with unspecified dependency relationships, each of the infinite number of possible dependency relationships would imply some specific output distribution, and the set of all such output distributions can be bounded with envelopes. The DEnv algorithm is a way to obtain the bounding envelopes. DEnv is implemented in a tool which is used to solve problems from a benchmark set.     

Simultaneous retrieval of the complex refractive indices of the core and shell of coated aerosol particles from extinction measurements using simulated annealing

Simultaneously retrieving the complex refractive indices of the core and shell of coated aerosol particles given the measured extinction efficiency as a function of particle dimensions (core diameter and coated diameter) is much more difficult than retrieving the complex refractive index of homogeneous aerosol particles. Not only must the minimization be performed over a four-parameter space, making it less efficient, but in addition the absolute value of the difference between the measured extinction and the calculated extinction does not have an easily distinguished global minimum. Rather, there are a number of local minima to which almost all conventional retrieval algorithms converge. In this work, we develop a new (to our knowledge) retrieval algorithm that employs the numerical method known as simulated annealing with an innovative "temperature" schedule. This study is limited only to spherical particles with a concentric shell and to cases in which the diameter of both the core and the coated particle are known. We find that when the top ranking particle sizes according to their information content are combined from separate experiments to make up the particle size distribution, the simulated annealing retrieval algorithm is quite robust and by far superior to a greedy random perturbation approach often used.     

气溶胶灭火剂的配方及优化设计的研究

文章为了研究气溶胶灭火剂在工程应用中的灭火能力及所遇到的腐蚀问题,采用对比实验方法对K型和S型的气溶胶灭火剂的配方进行了研究。主要选择了以锶盐为主、钾盐为辅的氧化剂,设计并优化了几种配方。结果表明:从灭火效能、喷射时间、Cu板颜色变化等性能参数可以看出,当Sr(NO3)2与KNO3的比值在1.4～5.0范围内效果最好,灭火效能为95 g/m3,喷射时间为42 s,且Cu板没有明显地变绿,既保证了气溶胶的灭火能力,又较好地解决了腐蚀性的问题。