ARTIFICIAL NEURAL NETWORK FOR AIR TRAFFIC CONTROLLER’S PRE-SIMULATOR TRAINING
Journal Title: Вісник Національного Авіаційного Університету - Year 2016, Vol 68, Issue 3
Abstract
Purpose: to develop the neural network model for evalua ting correctness and timeliness of decision-making by specialist of air traffic services during the pre-simulator training. Methods: researchers are based on the basic concepts of threat and error management in air tr affic control, for characteristic of situation complexity (threat- error-undesirable condition) the me thods of expert estimation and fuzzy sets theory have been used. Results : stages of the conflict situation developing have been classified and quantitative indicators of complexity level at each stage have been defined. Four layers neural network model for evaluating correctness and timeliness of decision-making by air traffic controller during the pre-simulator training has been built and its parameters have been obtained. The first layer (input) is exercises that perform cadets/listeners to solve potentially conflict situation, the second layer (hidden) is physiological characteristics of learner, the third layer (hidden) is the complexity of the exercise depending on the number of potentially conflict situations , the fourth layer (output) is assessment of cadets/listeners during performance of exercise. Neural network model also has additional inputs (Bias) that including restrictions on calculating parameters. With the he lp of modelling complex Fusion visualisation of results of educational task implementation by air traffic controller a ccording to specified parameters have been defined. Discussion: taking into account timeliness and correctness of in structor’s tasks performance during the pre- simulator education with the help of using artificial ne ural networks will allow determining the possibility of access of specialist of air traffic services to simula tor training. Multimodal system Fusion will give the possibility to improve the process of training of cadet' s/listener's – air traffic controllers through automated assessment of their actions.
Authors and Affiliations
Tatyana Shmelova, Yuliya Sikirda, Andriy Zemlyanskiy, Olena Danilenko, Vitalii Lazorenko
Keywords
Related Articles
- EP ID EP461369
- DOI 10.18372/2306-1472.68.10905
- Views 128
- Downloads 0
APPLICATION OF IMPRECISE MODELS IN ANALYSIS OF RISK MANAGEMENT OF SOFTWARE SYSTEMS
The analysis of functional completeness for existing detection systems was conducted. It made it possible to define information systems with a similar feature set, to assess the degree of similarity and the matching degr...
IDENTIFICATION OF ANIMAL –VEHICLE COLLISION LOCATIONS ACCORDING TO EVALUATION OF DRIVER INJURIES AND VEHICLE DAMAGE IN THE KYIV REGION
Purpose: We have implemented the evaluation of identification of animal –vehicle collision (AVC) in Kyiv region in 2007-2014, using the methodology of descriptive statistics for three pairs of variables,...
PRINCIPLES OF SAFETY MANAGEMENT OF AIR TRAFFIC FLOWS AND CAPACITY UNDER UNCERTAINTY CONDITIONS
Purpose: The aim of this study is to investigate the general principles of safety and capacity management in Aeronautical systems regarding air traffic flows operations under uncertainty conditions. In this work the theo...
PULSE CHARACTERISTICS OF NETWORK SATELLITE SYSTEMS ADAPTIVE ANTENNA FOR ASSESSING CORRELATION INTERFERENCE MATRIX
Purpose: On the basis of spatial filtering, we propose a method for direct calculation of the inverse correlation interference matrix with unknown parameters of the input action for controlling the pattern of the adaptiv...
PREREQUISITES FOR THE INTEGRAT ED GEOINFORMATION SYSTEMS IMPLEMENTATION FOR SPATIAL PL ANNING OF AIRPORT COMPLEXES
In the article the implementation possibilities of complex geographic information systems have been analyzed for spatial planning of airport complexes on the basis of research on the activity...