Investigative study and sensitivity analysis of Rapid Entire Body Assessment (REBA)

The paper aims primarily to study the sensitivity of Rapid entire body assessment (REBA) and identification of insensitive and sensitive posture zones. The investigative study, and sensitivity analysis of REBA offer deeper insights into the methodology used for the assessment of posture. Full factorial design is divided into parts using a forward approach to access the sensitivity. One parameter is varied keeping other parameters constant to understand its effect on the output score. Combinations of posture where no change was observed were identified. Posture scores were also noted involving sudden jumps. Regression analysis was performed to identify relative importance or weightage of the body and other variables in estimating the final REBA score. The justification of the REBA methodology available in the existing literature is very limited. This paper also demonstrates the need for understanding of REBA method among the researchers. With this paper, ergonomic practitioners can be made aware of insensitive and sensitive zones in posture assessment.OriginalityThis is the first paper that primarily aims to establish the sensitivity of REBA and identifying insensitive postures or problems in REBA assessment. Few research gaps are identified.     

Methods of constructing Bayesian networks based on scoring functions

Available methods of constructing Bayesian networks with the use of scoring functions are analyzed. The Cooper-Herskovits and MDL functions are described in detail and used to compare algorithms of constructing Bayesian networks. __________ Translated from Kibernetika i Sistemnyi Analiz, No. 2, pp. 81–88, March–April 2008.     

基于模糊动态贝叶斯网络的辐射源威胁估计

针对复杂电磁环境下观测数据的不确定性,建立辐射源威胁评估的离散模糊动态贝叶斯网络模型。对连续观测值通过模糊分类函数进行模糊分类,获得连续观测值属于各个模糊集合的隶属度,结果作为离散模糊动态贝叶斯网络的输入。对动态贝叶斯网络的推理算法进行了改进,使其能处理具有多个状态的观测值。仿真结果表明,依据离散模糊动态贝叶斯网络所建立的辐射源威胁评估模型,能够准确跟踪战场态势的变化,及时发现态势的转换边界,而且在观测值出现大量错误时,仍然可以给出正确的评估结果。     

基于贝叶斯网络的态势估计方法

分析了态势估计的主要功能,提出态势估计系统以事件检测为核心和起点。分析了使用贝 叶斯网络进行态势估计知识表示问题,并对态势估计中的时空知识表示进行了探讨,提出了构建贝叶斯 网络进行态势估计的步骤,分析了态势估计系统事件的层次。给出一个具体的实例,演示了使用贝叶斯 网络进行态势估计的过程。     

基于模糊贝叶斯网络的堆垛机系统可靠性分析

为解决因缺乏实际数据而无法准确估计堆垛机系统和部件的失效概率问题,提出了基于模糊集理论和主观贝叶斯方法的模糊贝叶斯网络诊断策略.该方法首先将故障树转换成相应的贝叶斯网络,然后运用模糊集理论,将专家给出的关于基本事件失效概率的主观语言评判值转换成模糊数,并通过去模糊化处理得到精确解.针对因事件的多态性所引起的条件概率不确定问题,该方法采用主观贝叶斯方法进行估计.通过堆垛机通信模块的可靠性分析实例,验证了该方法是有效的,表明其能够克服在系统建模时的参数不确定问题.     

基于贝叶斯分类器的高校学生信用评价模型

个人信用体系是社会信用体系的基础,而高校学生个人信用评价体系是社会信用体系下个人信用建设的重要组成部分以大学生群体为试点,选取与评价对象密切关系的13个指标建立大学生信用评价指标体系,并利用贝叶斯网络分类器的原理建立高校学生个人信用评价模型.模型结合关联分析的方法来寻找属性变量间的依赖关系,提出了模块化属性结点的思路,能同时实现用户信用分类和用户群体细分的功能.数据实验结果表明,模型有较好的信用评价分类效果.     

Comparison of the Ovako Working Posture Analysis System,Rapid Upper Limb Assessment,and Rapid Entire Body Assessment based on the maximum holding times

The objectives of this study were to measure the maximum holding times (MHTs) for symmetric and asymmetric body postures and to compare three representative observational methods, i.e., Ovako Working Posture Analysis System (OWAS), Rapid Upper Limb Assessment (RULA), and Rapid Entire Body Assessment (REBA), based on the MHTs. An experiment was performed to obtain the MHTs, wherein the independent variables were the hand position, trunk rotation angle, and external load. The hand position was defined using the hand height as the percentage of the shoulder height and the hand distance as the percentage of the arm reach. While the four independent variables including the hand height, hand distance, trunk rotation angle, and external load significantly affected the MHTs and RULA grand score at α = 0.01, only three of them (except the external load) were significant on the OWAS action category and REBA score. RULA assessed the postures tested in the experiment more stressfully than the OWAS and REBA, and the RULA grand score was more sensitive to the MHTs. In addition, the RULA grand score had larger correlation coefficients with the MHTs and other criteria for postural loads, such as whole-body discomfort, compressive force at L5/S1, and percent capables at the shoulder and trunk, than the OWAS action category and REBA score. Based on the findings of this study, it is concluded that of the three observational methods, RULA may be better for assessing postural loads under the experimental conditions.Relevance to industryWork-related musculoskeletal disorders are a major worldwide problem in industries. For preventing their development owing to multiple risk factors, it is important to quantify exposure to such risk factors.     

基于贝叶斯的智能电能表可靠性评估方法

针对具有高可靠、长寿命特点的智能电能表,应用加速退化试验方法进行可靠性评估是一种有效的方法。开展加速退化试验过程中,在高加速应力激发下,一方面可观测到智能电能表的性能退化,也可能出现智能电能表的整表失效。如何融合智能电能表加速寿命试验过程中的整表失效数据、性能退化数据转化得到的伪寿命数据,从而进行智能电能表的综合可靠性评估,是智能电能表可靠性评估急需解决的问题。本文研究提出基于贝叶斯方法的智能电能表可靠性评估方法,给出融合智能电能表的整表失效数据、伪寿命数据的数据处理方法及计算模型,探讨了伪失效数据计算方法、整表失效数据与伪失效寿命数据相容性检验方法等。     

Expert system for predicting unstable angina based on Bayesian networks

The use of computer-based clinical decision support (CDS) tools is growing significantly in recent years. These tools help reduce waiting lists, minimise patient risks and, at the same time, optimise the cost health resources. In this paper, we present a CDS application that predicts the probability of having unstable angina based on clinical data. Due to the characteristics of the variables (mostly binary) a Bayesian network model was chosen to support the system. Bayesian-network model was constructed using a population of 1164 patients, and subsequently was validated with a population of 103 patients. The validation results, with a negative predictive value (NPV) of 91%, demonstrate its applicability to help clinicians. The final model was implemented as a web application that is currently been validated by clinician specialists.     

基于贝叶斯网络的移动支付风险评估模型

随着信息技术和网络的迅猛发展,支付业务、技术及工具不断创新,移动支付的发展在逐渐加快。移动支付给人们生活带来方便和快捷的同时,也存在着较高的潜在风险,容易遭受非法入侵和恶意攻击。就移动支付风险的分析及风险值的计算理论方面开展工作,在贝叶斯网络的基础上,针对移动支付的主要组成主体,提出移动支付风险评估模型,通过使用该模型进行移动支付风险评估不仅可以对目前移动支付的风险进行评估,还可以根据风险评估结果引导风险控制,对比风险控制前后的风险值判断风险控制的效果,通过案例分析,提出的移动支付风险评估模型可以很好地完成移动支付的风险评估要求。     

面向广义质量体系的软件质量贝叶斯评估模型

现有软件质量评估模型主要关注软件系统的基本质量特性,缺乏考虑顾客价值特性和开发商组织管理特性,不能全面和科学地评估软件系统质量.文章以贝叶斯网络刻画了广义质量特性变量间复杂依赖关系,构建了更有针对性的软件质量量化评估模型.应用实例表明,该模型能综合考虑软件系统广义质量特性,对软件质量作出合理评价,并能依据贝叶斯网络的反向推理功能找到影响软件质量的关键因素.     

基于NB分类方法的网络异常检测模型*

在深入研究网络异常行为及异常检测系统相关现状的基础上,提出了基于NB分类方法的网络异常检测模型,并详细论述了该模型的工作原理.实验结果表明该方法是有效的.     

A general framework for assessing system resilience using Bayesian networks: A case study of sulfuric acid manufacturer

Supply chains play an important role in modern society and national economic development. In recent years, supply chains are more susceptible to variety of disruptive events, including natural disasters, man-made attacks, and common failures due to their complexity, globalization, and interconnected structures. Hence, it is important to design resilient supply chains which are capable of withstanding and recovering rapidly from disruptive events. This paper first explores the key drivers that contribute to the design of resilient supply chains based on the notion of absorptive, adaptive and restorative capacities. Second, it introduces a generic conceptual framework comprising five key phases: threat analysis, resilience capacity design, resilience cost evaluation, resilience quantification, and resilience improvement. The primary challenge to the literature of system resilience is how to measure it qualitatively. Findings from literature indicate that many of the drivers to the system resilience are qualitative such as staff cooperation and collaboration during disruptive events, level of preparation against natural disaster, among others. To fill the gap between qualitative and quantitative assessment of resilience, we employed Bayesian network to quantify the system resilience. Bayesian network is a rigorous tool for measuring risks under uncertainty, representing dependency between causes and effects, and making special types of reasoning. Additionally, it is capable of handling both qualitative and quantitative variables in terms of probability. We implemented Bayesian network for quantifying the supply chain system resilience of sulfuric acid manufacturer in Iran. Different scenarios have been defined and implemented to identify critical variables that are susceptible to the system resilience of sulfuric acid manufacturer.     

基于Bayes与多层Bayes估计的WSN链路选择算法

无线传感器网络（WSN）节点能量有限,采用传统的链路选择的方法（经验法）进行链路选择,需要发送大量的数据包作为测试样本,这在WSN中是不合适的。设计了两种基于Bayes估计与一种基于多层Bayes估计的WSN链路选择算法,分别记为BLSP-B1、BLSP-B2、BLSP-HE。仿真实验发现,在小样本的条件下,BLSP-B1、BLSP-B2、BLSP-HE选择高质量的链路的概率比经验法要高出10%～20%,其中BLSP-HE算法最稳健,性能较好。     

A framework for the analysis of dynamic processes based on Bayesian networks and case-based reasoning

Bayesian networks are knowledge representation schemes that can capture probabilistic relationships among variables and perform probabilistic inference. Arrival of new evidence propagates through the network until all variables are updated. At the end of propagation, the network becomes a static snapshot representing the state of the domain for that particular time. This weakness in capturing temporal semantics has limited the use of Bayesian networks to domains in which time dependency is not a critical factor. This paper describes a framework that combines Bayesian networks and case-based reasoning to create a knowledge representation scheme capable of dealing with time-varying processes. Static Bayesian network topologies are learned from previously available raw data and from sets of constraints describing significant events. These constraints are defined as sets of variables assuming significant values. As new data are gathered, dynamic changes to the topology of a Bayesian network are assimilated using techniques that combine single-value decomposition and minimum distance length. The new topologies are capable of forecasting the occurrences of significant events given specific conditions and monitoring changes over time. Since environment problems are good examples of temporal variations, the problem of forecasting ozone levels in Mexico City was used to test this framework.     

A software system for assessing the spatially distributed ecological risk posed by oil shipping

A maritime accident involving an oil tanker may lead to large scale mortality or reductions in populations of coastal species due to oil. The ecological value at stake is the biota on the coast, which are neither uniformly nor randomly distributed. We used an existing oil spill simulation model, an observation database of threatened species, and a valuation method and developed a software system for assessing the spatially distributed ecological risk posed by oil shipping. The approach links a tanker accident model to a set of oil spill simulations and further to a spatial ecological value data set. The tanker accident model is a Bayesian network and thus we present a case of using a Bayesian network in geographic analysis. A case in the Gulf of Finland is used for illustration of the methodology. The method requires and builds on an extensive data collection and generation effort and modeling. The main difference of our work to earlier works on using a Bayesian network in geospatial setting is that in our case the Bayesian network was used to compute the probabilities of spatial scenarios directly in a global sense while in earlier works Bayesian networks have been used for each location separately to obtain global results. The result was a software system that was used by a distributed research team.     

一种基于Bayesian信念网络的客户行为预测方法

提出一种基于Bayesian信念网络（BN）的客户行为预测方法．通过知识学习构建客户行为Bayesian网络（CBN）,根据CBN对预实例计算联合分布概率,准确预测了一对一营销优化中的客户行为．CBN学习算法包括连线和定向部分,复杂度为O（N^4）条件相关测试．在零售行业一对一营销实际应用表明,CBN学习算法较现有BN学习算法更快构建CBN,预测精度高于朴素Bayesina分类法．     

A novel wearable system for the online assessment of risk for biomechanical load in repetitive efforts

Work-related Musculo Skeletal Disorders (WMSD) are considered the third main reason for disability and early retirement in the U.S. and are widespread in many occupations, involving both heavy and light biomechanical loads. In Italy, only taking into account the years 2009–2010, it is estimated an exponential increasing in the number of WMSD reports. In particular a 159.7% increment has been reported compared to the 2006 statistics. In this context, it is clear how important correctly diagnosing this kind of pathology is becoming. Traditional methods for WMDS assessment are based on observational techniques, in which experts manually segment, label and evaluate movements with the help of pro-forma sheets. Since these methods are currently based on visual inspection and subjective judgment, they could benefit from objective measurements in terms of both reliability and repeatability. Moreover an automatic tool for ergonomics assessment would vastly reduce the time that an expert needs to carry out the same assessment manually. In this context a novel wearable wireless system capable of assessing the muscular efforts and postures of the human upper limb for WMSDs diagnosis is proposed. The system, being non-obstructive, can be used to monitor workers in ecologic environment while they are carrying on their everyday tasks. A real-time assessment is obtained according to two of the most common indexes for the analysis of risk factors on workplaces: the Rapid Upper Limb Assessment (RULA) and the Strain Index (SI). The system exploits inertial measurement units (IMUs) to reconstruct the upper limb posture, modeled as a 7 degrees of freedom (DoF) kinematic chain. As far as muscular efforts are concerned, surface EMG sensors are used to assess forearm flexor muscles strain. As an example of the proposed system application the results of a first data collection campaign regarding super-market cashiers during everyday real-life operations is reported.Relevance to industry: The presented system has a high potential impact on industry as a timely intervention on the WMSD factors may reduce pathologies and reduce the recovery of expert workers.     

基于模糊集和熵的工控系统灰色风险评估模型

为减少工业控制系统(ICS)风险评估中专家主观性的影响,使评估结果体现资产在可用性、完整性和机密性(AIC)3个方面不同的安全需求,提出一种基于模糊集和熵的灰色风险评估模型。结合威胁种类和安全目标,建立风险评估指标体系;引入模糊集和信息熵对权重的计算方法进行改进;将灰色理论用于风险评估,计算出ICS整体的风险、各设备风险以及设备在AIC这3方面面临的不同风险。对民航某ICS的应用结果表明,该模型能较为全面地评估系统的风险,为ICS防护提供重要依据。     

一种基于贝叶斯网络的燃气轮机故障诊断方法

针对电厂中现役燃气轮机故障样本少,以往的故障诊断方法依赖于海量的带有故障标签的数据,无法在实际生产中取得预期的诊断效果的现象,本文将重点着眼于利用贝叶斯网络进行反事实推理,完成对燃气轮机故障原因的分析。本文首先介绍了贝叶斯网络的基本原理,其次将故障模式和影响分析及故障树技术用于贝叶斯网络的搭建,弥补了基于数据驱动的故障诊断方法缺少专业知识支撑的缺陷,最后通过实际案例分析,表明了这一方法用于燃气轮机的故障诊断时,可以根据燃气轮机在运行中出现的异常现象,分析出可能出现的故障,以及相应的故障原因,帮助运行及检修人员及时发现故障,及时排除故障。为实际生产中的燃气轮机的故障诊断技术提供了一种灵活,高效,可靠的方法。