Towards an air traffic control complexity metric based on workspace constraints

Paassen, M. M. van; d'Engelbronner, Jurriaan G.

doi:10.1109/icsmc.2010.5641823

Cited by 3 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current task focused mainly on controlling aircraft towards one point, which is a situation where the number of aircraft is likely to be strongly related with the workload, which could have led to a measurement bias in favor of this metric. In [35] a number of suggestions are made to design future experimental test cases in such a way that one can better discriminate between the effects of number of aircraft under control, the number of instructions needed to control, and the complexity and criticality of these instructions; our current research follows those suggestions.…”

Section: Recommendationsmentioning

confidence: 89%

Solution-Space–Based Analysis of Dynamic Air Traffic Controller Workload

d'Engelbronner

Borst

Ellerbroek

et al. 2015

Journal of Aircraft

Self Cite

View full text Add to dashboard Cite

Air traffic controller workload is considered to be a limiting factor to air traffic growth. Previous research introduced the static solution space approach to assess the difficulty of aircraft merging tasks. In this paper the dynamic, tangent-based solution space will be introduced that includes the future trajectory intent of all aircraft. Metrics derived from the solution space, together with common metrics, were tested for correlations with controller workload. An experiment has been conducted where subjects were required to line up all aircraft in a sector towards a certain waypoint, while periodically rating their workload. High correlations were found between several solution space related metrics and subjective workload ratings. In contrast to the number of aircraft metric, which had the highest correlation with workload, the dynamic solution space may allow for controller workload prediction in realtime.

show abstract

Section: Recommendationsmentioning

confidence: 89%

Solution-Space–Based Analysis of Dynamic Air Traffic Controller Workload

d'Engelbronner

Borst

Ellerbroek

et al. 2015

Journal of Aircraft

Self Cite

View full text Add to dashboard Cite

show abstract

An Analysis of Complexity Measures for Product Design and Development

Crespo-Varela

Kremer

Tucker

et al. 2012

Volume 3: 38th Design Automation Conference, Parts a and B

View full text Add to dashboard Cite

Complexity metrics have been developed for multiple applications such as consumer products, software, trajectory selection and assembly systems. Although existing complexity metrics were developed to reduce product design and development costs, their lack of simplicity in formulation and robustness has limited their applicability. This paper proposes a standard methodology for comparing and evaluating these metrics and introduces dimensions of complexity that should be considered towards the goal of developing a generalizable product complexity measure. To this end, this paper introduces variables that integrate multiple facets of complexity into a single metric. A medical device case study is used to compare the efficiency and robustness of existing complexity measures. The medical device case study also serves as the motivation for the proposed complexity metric due to the complexity of the domain itself and the increasing importance of mitigating healthcare costs. Overall, product complexity metrics can aid medical device development by increasing the understanding about the design and its implications regarding development time and FDA approvals.

show abstract

Congestion Recognition of the Air Traffic Control Sector Based on Deep Active Learning

et al. 2022

View full text Add to dashboard Cite

The air traffic control sector (ATCS) is the basic unit of the airspace system. If we can identify the congestion of an ATCS, it will help provide decision support for planning and daily operations. However, current methods mainly characterize congestion from the static structure and the dynamic operational features, resulting in poor generalization and operability. To this end, we propose a deep learning method from the perspective of complex networks. It takes aircraft as nodes to construct an aircraft network and utilizes the complexity indices to characterize it. So, the problem of identifying congestion becomes the complexity of the aircraft network. Inspired by active learning methods, we construct a deep active learning (DAL) model for congestion recognition. It adopts an iterative semi-supervised approach to reduce the number of labeled samples while ensuring recognition performance. To make full use of a large number of unlabeled samples, the sparse autoencoder is employed to characterize all labeled samples and unlabeled samples. The hidden layer of the deep neural network is constructed by stacking. In the process of active learning iteration, minimum confidence, marginal sampling, and information entropy are introduced as measures to select samples from the unlabeled sample set with significantly different features from the labeled sample set. The model is applied to three representative sectors in China’s airspace as cases. Results suggest that DAL can reduce the labeled sample set’s redundancy and achieve the desired performance with the smallest number of samples. Additionally, DAL is superior to the existing mainstream methods in the four objective evaluation indices.

show abstract

Towards an air traffic control complexity metric based on workspace constraints

Cited by 3 publications

References 7 publications

Solution-Space–Based Analysis of Dynamic Air Traffic Controller Workload

Solution-Space–Based Analysis of Dynamic Air Traffic Controller Workload

An Analysis of Complexity Measures for Product Design and Development

Congestion Recognition of the Air Traffic Control Sector Based on Deep Active Learning

Contact Info

Product

Resources

About