Despite its recent success in various industries, artificial intelligence has not received full acceptance; hence, it been fully deployed by the aviation industry. This is partly attributed to, among other factors, AI (Artificial Intelligence) model works as a black-box with no clear explanations of how outputs are generated from input samples. Aviation an extremely sensitive application field, and this model’s opaqueness makes hard for human user industry to trust such model. The...

The timely identification of probable causes in aviation incidents is crucial for averting future tragedies and safeguarding passengers. Typically, investigators rely on flight data recorders, yet delays retrieval or damage to the devices can impede progress. In such instances, experts resort supplementary sources like eyewitness tes- timonies radar construct analytical narratives. Delays this process have tangible consequences, as evidenced by Boeing 737 MAX accidents involving Lion Air...

Abstract Stress is a word used to describe human reactions emotionally, cognitively and physically challenging experiences. A hallmark of the stress response activation autonomic nervous system, resulting in “fight-freeze-flight” threat from dangerous situation. Consequently, capability objectively assess track controller’s level while dealing with air traffic control (ATC) activities would make it possible better tailor work shift maintain high safety levels, as well preserve operator’s...

View Video Presentation: https://doi.org/10.2514/6.2023-4325.vid Safety is a critical aspect of the air transport system given even slight operational anomalies can result in serious consequences. To reduce chances aviation safety occurrences, accidents and incidents are reported to establish root cause, propose recommendations etc. However, analysis narratives pre-accident events presented using human understandable, raw, unstructured, text that cannot be understood by computer system. The...

Improvements in aviation safety analysis call for innovative techniques to extract valuable insights from the abundance of textual data available accident reports. This paper explores application four prominent topic modelling techniques, namely Probabilistic Latent Semantic Analysis (pLSA), (LSA), Dirichlet Allocation (LDA), and Non-negative Matrix Factorization (NMF), dissect incident narratives using Australian Transport Safety Bureau (ATSB) dataset. The study examines each technique's...

Improvements in aviation safety analysis call for innovative techniques to extract valuable insights from the abundance of textual data available accident reports. This paper explores application four prominent topic modelling techniques, namely Probabilistic Latent Semantic Analysis (pLSA), (LSA), Dirichlet Allocation (LDA), and Non-negative Matrix Factorization (NMF), dissect incident narratives using Australian Transport Safety Bureau (ATSB) dataset. The study examines each technique's...

Aviation safety is a global concern, requiring detailed investigations into incidents to understand contributing factors comprehensively. This study uses the National Transportation Safety Board (NTSB) dataset. It applies advanced natural language processing (NLP) techniques, including Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF), Semantic Analysis (LSA), Probabilistic (pLSA), and K-means clustering. The main objectives are identifying latent themes, exploring...

Safety is a critical aspect of the air transport system given even slight operational anomalies can result in serious consequences. To reduce chances aviation safety occurrences, accidents and incidents are reported to establish root cause, propose recommendations etc. However, analysis narratives pre-accident events presented using human-understandable, raw, unstructured, text that computer cannot understand. The ability classify categorise occurrences from their textual would help industry...

ABSTRACT Aircraft maintenance operations are carried out by aircraft technicians (AMTs) with the necessary competencies and qualifications. The level of competency directly affects safety effectiveness flight operations. aim this study is to determine culture responsibility assessment methods for AMTs. Data related were collected conducting individual interviews focus group discussions 83 participants. data analyzed using content analysis method coding technique. As a result participants, it...

Artificial intelligence (AI) has demonstrated success across various industries; however, its adoption in aviation remains limited due to concerns regarding the interpretability of AI models, which often function as black box systems with opaque decision-making processes. Given safety-critical nature aviation, lack transparency AI-generated predictions poses significant challenges for industry stakeholders. This study investigates classification performance multiple supervised machine...

The timely identification of probable causes in aviation incidents is crucial for averting future tragedies and safeguarding passengers. Typically, investigators rely on flight data recorders; however, delays retrieval or damage to the devices can impede progress. In such instances, experts resort supplementary sources like eyewitness testimonies radar construct analytical narratives. Delays this process have tangible consequences, as evidenced by Boeing 737 MAX accidents involving Lion Air...

This study presents a comparative analysis of four topic modeling techniques—Latent Dirichlet Allocation (LDA), BERT, Probabilistic Latent Semantic Analysis (PLSA), and Non-negative Matrix Factorization (NMF)—applied to aviation safety reports from the ATSB dataset spanning 2003–2023 (53,275 records). The evaluation focuses on coherence, interpretability, generalization, computational efficiency, scalability. Results indicate that NMF achieves highest coherence...

This study investigates the application of advanced deep learning models for classification aviation safety incidents, focusing on four models: Simple Recurrent Neural Network (sRNN), Gated Unit (GRU), Bidirectional Long Short-Term Memory (BLSTM), and DistilBERT. The were evaluated based key performance metrics, including accuracy, precision, recall, F1-score. DistilBERT achieved perfect with an accuracy 1.00 across all while BLSTM demonstrated highest among models, 0.9896, followed by GRU...

This study presents a comparative analysis of four topic modeling techniques —Latent Dirichlet Allocation (LDA), Bidirectional Encoder Representations from Transformers (BERT), Probabilistic Latent Semantic Analysis (pLSA), and Non-negative Matrix Factorization (NMF)—applied to aviation safety reports the ATSB dataset spanning 2013–2023. The evaluation focuses on coherence, interpretability, generalization, computational efficiency, scalability. results indicate that NMF achieves highest...

Aviation safety analysis increasingly relies on extracting actionable insights from narrative incident reports to support risk identification and improve operational safety. Topic modeling techniques such as Probabilistic Latent Semantic Analysis (pLSA) BERTopic offer automated methods uncover latent themes in unstructured narratives. This study evaluates the effectiveness of each model generating coherent, interpretable, semantically meaningful topics for aviation practitioners researchers....

This study investigates the application of advanced deep learning models for classification aviation safety incidents, focusing on four models: Simple Recurrent Neural Network (sRNN), Gated Unit (GRU), Bidirectional Long Short-Term Memory (BLSTM), and DistilBERT. The were evaluated based key performance metrics, including accuracy, precision, recall, F1-score. DistilBERT achieved perfect with an accuracy 1.00 across all while BLSTM demonstrated highest among models, 0.9896, followed by GRU...

This study focuses on the classification of safety occurrences in air transport system using natural language processing (NLP) and artificial intelligence (AI) models. The researchers utilized ResNet sRNN deep learning models to classify flight phases based unstructured text narratives occurrence reports from NTSB. evaluated performance these a dataset 27,000 found that both achieved an accuracy exceeding 68%, surpassing random guess rate 14% for seven-class problem. Additionally, exhibited...

Background. Air traffic controllers need to use their cognitive resources cope with multiple tasks while monitoring air traffic. They are trained through advanced 3D simulators; however, they might demonstrate simulator sickness symptoms during this training. The relationship between multitasking and the influence of different on these variables can be investigated inform further training practices for an efficient monitoring. Purpose. purpose quasi-experimental research was explore working...

The exchange of substances between mother and fetus via the placenta plays a vital role during development. A number developmental disorders in are observed diabetic pregnancies. Diabetes, together with placental apoptosis, can lead to functional disorders.Histological, ultrastructural apoptotic changes were investigated streptozotocin (STZ) induced rats.Animal experimentation.In this study, total 12 female Wistar Albino rats (control (n=6) (n=6)) used. Rats group, following administration...