Classification of Operational Records in Aviation Using Deep Learning Approaches

2025-01-02

AI Summary

This study addresses the safety-critical three-class classification problem—commercial, military, and private flight operations—in aviation operational records, where severe class imbalance (particularly scarce military and private samples) and inadequate sequential modeling jointly increase the risk of safety-critical misclassification. Using the Socrata dataset (4,864 instances), we conduct the first systematic comparative evaluation of BLSTM, LSTM, CNN, and sRNN for this task. Results show that BLSTM achieves the highest overall accuracy (72%) and best class-balanced performance; LSTM attains the highest recall for the commercial class (71% overall accuracy); while CNN (67%) and sRNN (69%) exhibit significant misclassification of private flights. The analysis reveals that class imbalance dominantly impairs recognition of military and private operations, and critically validates the necessity of bidirectional sequential modeling for reliable aviation safety–relevant classification.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Natural Language Processing: Safety and Robustness
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Ensuring safety in the aviation industry is critical, even minor anomalies can lead to severe consequences. This study evaluates the performance of four different models for DP (deep learning), including: Bidirectional Long Short-Term Memory (BLSTM), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Simple Recurrent Neural Networks (sRNN), on a multi-class classification task involving Commercial, Military, and Private categories using the Socrata aviation dataset of 4,864 records. The models were assessed using a classification report, confusion matrix analysis, accuracy metrics, validation loss and accuracy curves. Among the models, BLSTM achieved the highest overall accuracy of 72%, demonstrating superior performance in stability and balanced classification, while LSTM followed closely with 71%, excelling in recall for the Commercial class. CNN and sRNN exhibited lower accuracies of 67% and 69%, with significant misclassifications in the Private class. While the results highlight the strengths of BLSTM and LSTM in handling sequential dependencies and complex classification tasks, all models faced challenges with class imbalance, particularly in predicting the Military and Private categories. Addressing these limitations through data augmentation, advanced feature engineering, and ensemble learning techniques could enhance classification accuracy and robustness. This study underscores the importance of selecting appropriate architectures for domain specific tasks

Problem

• Aviation Industry
• Deep Learning Models
• Flight Mission Classification

Innovation

• Deep Learning Models
• Aerospace Data Classification
• Model Fusion Strategy