Situated design of line-oriented flight training (LOFT): a case study in a Brazilian airline

This paper describes an exploratory situated approach for the design, development, standardization, and implementation of line-oriented flight training (LOFT) in a major airline. LOFT was conceived in aviation industry to be a practical application of crew resource management (CRM) concepts. The situated approach combines a set of methods and techniques from ergonomics and human factors disciplines. These methods were supported by social construction enabling the involvement and participation of different actors of the operational, tactical, and strategic level of the company. Under this framework, situated design is progressively established by socially constructed patterns up to a situated design comprising the construction of scenarios, training tools, procedures, structures, organization, flight documents, operations, and further training management contents. Our findings indicate that LOFT situated design, framed by social construction, can be applied to any aviation system with a specific culture and organization, which may be different from the ones that were implicitly or explicitly taken into account during the development of general LOFT guidelines.     

An Extensive Evaluation of Decision Tree–Based Hierarchical Multilabel Classification Methods and Performance Measures

Hierarchical multilabel classification is a complex classification problem where an instance can be assigned to more than one class simultaneously, and these classes are hierarchically organized with superclasses and subclasses, that is, an instance can be classified as belonging to more than one path in the hierarchical structure. This article experimentally analyses the behavior of different decision tree–based hierarchical multilabel classification methods based on the local and global classification approaches. The approaches are compared using distinct hierarchy‐based and distance‐based evaluation measures, when they are applied to a variation of real multilabel and hierarchical datasets' characteristics. Also, the different evaluation measures investigated are compared according to their degrees of consistency, discriminancy, and indifferency. As a result of the experimental analysis, we recommend the use of the global classification approach and suggest the use of the Hierarchical Precision and Hierarchical Recall evaluation measures.     

GA-based method for feature selection and parameters optimization for machine learning regression applied to software effort estimation

ContextIn software industry, project managers usually rely on their previous experience to estimate the number men/hours required for each software project. The accuracy of such estimates is a key factor for the efficient application of human resources. Machine learning techniques such as radial basis function (RBF) neural networks, multi-layer perceptron (MLP) neural networks, support vector regression (SVR), bagging predictors and regression-based trees have recently been applied for estimating software development effort. Some works have demonstrated that the level of accuracy in software effort estimates strongly depends on the values of the parameters of these methods. In addition, it has been shown that the selection of the input features may also have an important influence on estimation accuracy.ObjectiveThis paper proposes and investigates the use of a genetic algorithm method for simultaneously (1) select an optimal input feature subset and (2) optimize the parameters of machine learning methods, aiming at a higher accuracy level for the software effort estimates.MethodSimulations are carried out using six benchmark data sets of software projects, namely, Desharnais, NASA, COCOMO, Albrecht, Kemerer and Koten and Gray. The results are compared to those obtained by methods proposed in the literature using neural networks, support vector machines, multiple additive regression trees, bagging, and Bayesian statistical models.ResultsIn all data sets, the simulations have shown that the proposed GA-based method was able to improve the performance of the machine learning methods. The simulations have also demonstrated that the proposed method outperforms some recent methods reported in the recent literature for software effort estimation. Furthermore, the use of GA for feature selection considerably reduced the number of input features for five of the data sets used in our analysis.ConclusionsThe combination of input features selection and parameters optimization of machine learning methods improves the accuracy of software development effort. In addition, this reduces model complexity, which may help understanding the relevance of each input feature. Therefore, some input parameters can be ignored without loss of accuracy in the estimations.     

Constrained Fractional Variational Problems of Variable Order

Isoperimetric problems consist in minimizing or maximizing a cost functional subject to an integral constraint. In this work, we present two fractional isoperimetric problems where the Lagrangian depends on a combined Caputo derivative of variable fractional order and we present a new variational problem subject to a holonomic constraint. We establish necessary optimality conditions in order to determine the minimizers of the fractional problems. The terminal point in the cost integral, as well as the terminal state, are considered to be free, and we obtain corresponding natural boundary conditions.      

Performance assessment of multicriteria damage identification genetic algorithms

Damage detection methods based on model updating method have usually been developed as single objective optimization problems. However, the lack of a clear objective function in the context of real-world damage detection problems advises simultaneous optimizations of several objectives with the purpose of improving the performance of the procedure. The application of genetic algorithms for solving multiobjective optimization constitutes an emergent research area nowadays. However, their application to damage identification problems is very limited and, practically, no comparative study has been presented up to now. In this paper, some multiobjective GAs based on aggregating functions and Pareto optimality are compared.     

Hierarchical multi-label classification using local neural networks

Hierarchical multi-label classification is a complex classification task where the classes involved in the problem are hierarchically structured and each example may simultaneously belong to more than one class in each hierarchical level. In this paper, we extend our previous works, where we investigated a new local-based classification method that incrementally trains a multi-layer perceptron for each level of the classification hierarchy. Predictions made by a neural network in a given level are used as inputs to the neural network responsible for the prediction in the next level. We compare the proposed method with one state-of-the-art decision-tree induction method and two decision-tree induction methods, using several hierarchical multi-label classification datasets. We perform a thorough experimental analysis, showing that our method obtains competitive results to a robust global method regarding both precision and recall evaluation measures.     

Adaptive Multiresolution Methods for the Simulation of Waves in Excitable Media

We present fully adaptive multiresolution methods for a class of spatially two-dimensional reaction-diffusion systems which describe excitable media and often give rise to the formation of spiral waves. A novel model ingredient is a strongly degenerate diffusion term that controls the degree of spatial coherence and serves as a mechanism for obtaining sharper wave fronts. The multiresolution method is formulated on the basis of two alternative reference schemes, namely a classical finite volume method, and Barkley’s approach (Barkley in Phys. D 49:61–70, 1991), which consists in separating the computation of the nonlinear reaction terms from that of the piecewise linear diffusion. The proposed methods are enhanced with local time stepping to attain local adaptivity both in space and time. The computational efficiency and the numerical precision of our methods are assessed. Results illustrate that the fully adaptive methods provide stable approximations and substantial savings in memory storage and CPU time while preserving the accuracy of the discretizations on the corresponding finest uniform grid.     

Nested block designs: Flexible and efficient schedule-based asynchronous duty cycling

In schedule-based asynchronous duty cycling, nodes activate and deactivate their radio interfaces according to a specially designed wakeup schedule, which guarantees overlapping active time between nodes, irrespective of their synchronization offsets. When compared to synchronous duty cycling, such an approach has the advantage of being simple to implement, eliminating the need for synchronization protocols, complex computations or extra hardware. However, among published proposals, there is no single schedule-based mechanism that provides the lowest latency in all scenarios, when considering duty cycling symmetry, frame delivery probability and duty cycling rate. This paper introduces nested block designs, a new schedule that extends the use of block designs to application scenarios for which they were previously not possible or not as efficient as other schedules. Nested block designs provide the lowest latency among known schedule-based asynchronous duty cycling mechanisms for a wide range of applications, as confirmed by analytical models and real implementations on WSN motes.     

Sustainable interoperability on space mission feasibility studies

The evolution of ICT towards fast and robust data exchange promoted the blooming of successful technical and business concepts like cloud computing and virtualisation of enterprise assets. The escalation of service providers enabled the specialisation of enterprises (particularly SMEs) and the building of provider networks. This move from enterprise-concentric to service-dispersed strategies is leading to concerns about reaching and maintaining the interoperability between customer–provider pairs and their associated business networks. This is particularly true in the aerospace industry: a highly-competitive and demanding business supported by numerous applications, which may be general-purposed, specific, proprietary or open-sourced, all needing to be interoperable with the lowest impact on the business itself. This paper addresses the need for improving the sustainability of enterprise interoperability via the application of negotiations, with the objective of reducing the impact of changes and achieving the best solutions in the interoperability between the enterprises and their surrounding environment. It proposes a framework that features a negotiation mechanism for the management of changes towards the sustainability of the seamless business-to-business interactions, and describes its application on the real business case of the ESA-CDF space mission feasibility studies.