Evaluation and prediction mental workload in user interface of maritime operations using eye response

Eye response measurement is one of the objective measure methods and useful for assessing of operators' mental workload (MWL). The main objectives of this paper are to consider the relationship between operators' MWL and eye responses in the task of operating marine engine interface. Also, an artificial neural network (ANN) model was developed to predict the operators' MWL based on integrating eye response data. Eye response indices (pupil dilation, blink rate, fixation rate, and saccadic rate) were recorded, and two subjective rating methods (The National Aeronautics and Space Administration's Task Load Index [NASA-TLX] and subjective workload assessment technique [SWAT]) were used for 27 participants. The results again confirm that the eye response is sensitive to MWL in workload levels of the task when using the interface control. The ANN model developed by measuring these indices can predict the operators' MWL with the determination coefficient (R²) of 0.971, 0.912 and 0.918 for training, validation, and testing, respectively. These results indicated that the ANN approach is quite accurate for the prediction of operators' MWL based on eye response indices.Relevance to industryThe developed model is expected to provide the operator with a reference value of their MWL by evaluating their physiological indices. This result might be applied for developing an intelligent prediction model in the actual work environment to inform or support the operator in a variety of ways. From this, the manager can organize the human resources for each task to sustain the appropriate MWL as well as to improve the work performance.     

基于循环神经网络的数据库查询开销预测

数据库负载管理、性能调优中,开销预测模型是提高其效率的关键技术。首先,由于数据库系统的复杂性和计算机资源的竞争,很难精确地估计不同操作的开销。其次,由于查询计划结构的复杂性,现有研究更多使用笼统的查询信息,而很少利用查询计划中操作层面的信息,并依据这些信息来获得开销模型。另外,现有的研究大多没有真正预测查询的执行时间,而是预测了类似查询优化器中开销模型生成的开销。为了减少负载管理的复杂性,本文提出了基于循环神经网络的精细模型来预测查询开销,以查询计划中的操作行为和其实际运行时间作为特征提取的来源。特别地,考虑到查询计划结构的复杂性,本文采用一种特殊的循环神经网络,长短期记忆（Long-Short Term Memory,LSTM）。给一个特定的查询计划,在该计划实际执行之前,模型就能产生其预测的执行时间。这会比现有数据库的查询优化器产生的开销预估结果（任意单位）更具有参考性;也优于需要在执行开始之后才能预测的查询进度指示器。本文提出的这种创新方法来预测查询执行时间,可以用于解决数据库负载管理中的关键问题。通过实验验证,模型的正确率高于71%,一定程度上证明了方法的可行性。     

Nonlinear dynamical systems for theory and research in ergonomics

Abstract

Nonlinear dynamical systems (NDS) theory offers new constructs, methods and explanations for phenomena that have in turn produced new paradigms of thinking within several disciplines of the behavioural sciences. This article explores the recent developments of NDS as a paradigm in ergonomics. The exposition includes its basic axioms, the primary constructs from elementary dynamics and so-called complexity theory, an overview of its methods, and growing areas of application within ergonomics. The applications considered here include: psychophysics, iconic displays, control theory, cognitive workload and fatigue, occupational accidents, resilience of systems, team coordination and synchronisation in systems. Although these applications make use of different subsets of NDS constructs, several of them share the general principles of the complex adaptive system.

Practitioner Summary: Nonlinear dynamical systems theory reframes problems in ergonomics that involve complex systems as they change over time. The leading applications to date include psychophysics, control theory, cognitive workload and fatigue, biomechanics, occupational accidents, resilience of systems, team coordination and synchronisation of system components.     

A shuffled frog-leaping algorithm for flexible job shop scheduling with the consideration of energy consumption

Flexible job shop scheduling problem (FJSP) has been extensively investigated and objectives are often related to time. Energy-related objective should be considered fully in FJSP with the advent of green manufacturing. In this study, FJSP with the minimisation of workload balance and total energy consumption is considered and the conflicting between two objectives is analysed. A shuffled frog-leaping algorithm (SFLA) is proposed based on a three-string coding approach. Population and a non-dominated set are used to construct memeplexes according to tournament selection and the search process of each memeplex is done on its non-dominated member. Extensive experiments are conducted to test the search performance of SFLA and computational results show the conflicting between two objectives of FJSP and the promising advantages of SFLA on the considered FJSP.     

Handling the complexities of real-life job shops when implementing workload control: a decision framework and case study

The workload control literature highlights the importance of balancing the shop floor workload, but also acknowledges that this can conflict with processing the most urgent orders – hence, there is a trade-off. In practice, shops contain many complexities, e.g. simultaneous batching and sequence-dependent set-up times that may conflict with processing the most urgent orders and require other solutions than workload balancing to avoid capacity losses. This adds to the trade-off dilemma, which traditionally only considers timing and balancing. This paper develops a framework that determines whether to address a complexity through order release or dispatching. It comprises two dimensions: (i) the typical position of a complexity in the routing of an order and (ii) the criticality of the complexity. A case study is presented, which demonstrates the framework’s utility and illustrates the development of specific solutions designed to handle the complexities. Most complexities present in the case require handling at the order release stage. The challenges of handling multiple complexities at this decision level are evaluated. Finally, the implications for managers and future research are outlined.     

基于随机模型预测控制的数据中心微电网能量优化调度研究

针对数据中心负荷的随机性和可再生能源出力的不确定性,为保证数据中心在实际运行中的稳定性和经济性,提出了一种基于随机模型预测控制的数据中心微电网能量优化调度方法。引入场景分析法描述不确定因素,以数据中心运行成本最低为目标建立优化模型,通过模型预测控制的滚动优化和反馈校正,协调系统内各设备的出力情况,减小数据中心的运行成本,并降低不确定因素对其运行产生的不良影响。以某个典型数据中心微电网系统为例进行仿真分析,仿真结果验证了所提方法的有效性。     

The relationship between physical workload and quality within line-based assembly

Reducing costs and improvement of product quality are considered important to ensure productivity within a company. Quality deviations during production processes and ergonomics have previously shown to be associated. This study explored the relationship between physical workload and real (found during production processes) and potential (need of extra time and assistance to complete tasks) quality deviations in a line-based assembly plant. The physical workload on and the work rotation between 52 workstations were assessed. As the outcome, real and potential quality deviations were studied during 10 weeks. Results show that workstations with higher physical workload had significantly more real deviations compared to lower workload stations. Static work posture had significantly more potential deviations. Rotation between high and low workload was related to fewer quality deviations compared to rotation between only high workload stations. In conclusion, physical ergonomics seems to be related to real and potential quality deviation within line-based assembly.

Practitioner Summary: To ensure good productivity in manufacturing industries, it is important to reduce costs and improve product quality. This study shows that high physical workload is associated with quality deviations and need of extra time and assistance to complete tasks within line-based assembly, which can be financially expensive for a company.     

数据中心电费最小化的负载调度策略

为了降低电费成本,一些数据中心使用绿色能源供电。然而,负载的波动性和电价的时间差异性给数据中心电费成本带来了挑战。针对上述问题,提出一种低成本的负载调度算法,使得数据中心电费最小化。首先,建立电力耗费模型;然后,将电费最小化问题形式化为一个多目标约束的优化问题;最后,求解该优化问题得到相应的负载调度策略。实验结果表明:该算法可以在保证负载性能的前提下,有效降低数据中心的电费成本。     

A defeasible reasoning framework for human mental workload representation and assessment

Human mental workload (MWL) has gained importance in the last few decades as an important design concept. It is a multifaceted complex construct mainly applied in cognitive sciences and has been defined in many different ways. Although measuring MWL has potential advantages in interaction and interface design, its formalisation as an operational and computational construct has not sufficiently been addressed. This research contributes to the body of knowledge by providing an extensible framework built upon defeasible reasoning, and implemented with argumentation theory (AT), in which MWL can be better defined, measured, analysed, explained and applied in different human–computer interactive contexts. User studies have demonstrated how a particular instance of this framework outperformed state-of-the-art subjective MWL assessment techniques in terms of sensitivity, diagnosticity and validity. This in turn encourages further application of defeasible AT for enhancing the representation of MWL and improving the quality of its assessment.     

以瓶颈为中心多层次负荷集成的订单交货期预测方法

针对MTO(make-to-order)生产环境下的订单交货期预测问题,提出了一种集成订单接收、订单投放与车间调度等多层次负荷,以瓶颈为中心的订单交货期预测(bottleneck driven due-date forecasting, BDDF)方法。该方法先根据订单是否通过瓶颈,分类估计“鼓链”与“非鼓链”订单在不同层次的负荷,同时利用Little’s法则估计各个层次的通过时间,求和得到订单的交货期。运用FlexSim建模仿真比较了BDDF方法与两种经典交货期预测方法在不同订单池排序规则、车间调度规则以及保护产能水平组合下的系统绩效。结果表明,BDDF方法在拖期率、平均拖期以及延期标准差指标上均优于两种经典方法。同时,订单池排序规则、调度规则以及保护产能水平都会影响BDDF方法的系统绩效,需要根据实际情况选择合适的参数,以更好地控制订单交货期,避免订单延期。