Abstract
In the aviation sector, human factors are the primary cause of safety incidents. Intelligent prediction systems, which are capable of evaluating human state and managing risk, have been developed over the years to identify and prevent human factors. However, the lack of large useful labelled data has often been a drawback to the development of these systems. This study presents a methodology to identify and classify human factor categories from aviation incident reports. For feature extraction, a text pre-processing and Natural Language Processing (NLP) pipeline is developed. For data modelling, semi-supervised Label Spreading (LS) and supervised Support Vector Machine (SVM) techniques are considered. Random search and Bayesian optimization methods are applied for hyper-parameter analysis and the improvement of model performance, as measured by the Micro F1 score. The best predictive models achieved a Micro F1 score of 0.900, 0.779, and 0.875, for each level of the taxonomic framework, respectively. The results of the proposed method indicate that favourable predicting performances can be achieved for the classification of human factors based on text data. Notwithstanding, a larger data set would be recommended in future research.
Highlights
Over the last decade, air transport has been considered to be one of the fastest and safest methods of transportation for long-distance travel, being one of the largest contributors to the growth of political, social, and economic globalization.Before the current coronavirus pandemic, the commercial aviation sector was annually deploying over 37 million airplane departures and four billion passengers worldwide, with the International Civil Aviation Organization (ICAO) expecting these numbers to reach 90 million and 10 billion, respectively, by 2040 [1]
The aim of this research is to contribute to better knowledge regarding how to enhance aviation safety, by developing a comprehensive methodology that is based on data mining and machine learning techniques, to identify and classify the main human factors that are causal of aviation incidents, based on descriptive text data
It can be observed that the Distributed Bag of Words (DBoW) architecture generally performed slightly better than the Distributed Memory (DM) for the current data set
Summary
Before the current coronavirus pandemic, the commercial aviation sector was annually deploying over 37 million airplane departures and four billion passengers worldwide, with the International Civil Aviation Organization (ICAO) expecting these numbers to reach 90 million and 10 billion, respectively, by 2040 [1] These numbers have been strongly affected by the pandemic, some projections estimate that global air traffic could reach 2019 levels as early as 2024 [2]. Oftentimes, the increase in workload is not accompanied by a proportional gain in personnel and, as a consequence, employees are often subjected to an enormous quantity of rigorous requests, under pressured time frames, and complex environments [6] Compounded factors, such as career uncertainty and frequent demand for overtime, have contributed to an increasing risk of personnel capabilities detriment and, mistakes in safety sensitive tasks [6]. These circumstances have been further aggravated by the effects of the current pandemic, where companies had to forgo large portions of their employees in order to reduce cash burns and regain profit margins, while maintaining contractual obligations and preparing for a resurgence of traffic demand [7,8]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
