An official website of the United States government
Advances made in Unmanned Aircraft Vehicles (UAVs) have increased rapidly in the last decade resulting in new applications in both civil and military spheres. However, with the growth in the usage of these systems, various cybersecurity challenges arose unveiling the vulnerabilities of UAV wireless networks. Among the attacks that threaten the network's availability and reduce their performance are jamming attacks. Several approaches have been proposed to address this problem; however, most of them are not suitable for UAVs due to their reduced size, weight, and power constraints. In this paper, we propose a lightweight machine learning technique, LightGBM, to detect deceptive jamming attacks on UAV networks. The performance of this model is compared to that of three boosting and bagging-based machine learning models namely, XGBoost, Gradient Boost, and Random Forest. The results show that, although the LightGBM model has slightly lower accuracy (98.4%) than Gradient Boost (99%) and Random Forest (98.87%), it is 21 times faster and occupies two times less memory during the prediction than Gradient Boost and Random Forest.
more »
« less
Advancing a Major U.S. Airline’s Practice in Flight-level Checked Baggage Prediction
In this paper, we aim to address a relevant estimation problem that aviation professionals encounter in their daily operations. Specifically, aircraft load planners require information on the expected number of checked bags for a flight several hours prior to its scheduled departure to properly palletize and load the aircraft. However, the checked baggage prediction problem has not been sufficiently studied in the literature, particularly at the flight level. Existing prediction approaches have not properly accounted for the different impacts of overestimating and underestimating checked baggage volumes on airline operations. Therefore, we propose a custom loss function, in the form of a piecewise quadratic function, which aligns with airline operations practice and utilizes machine learning algorithms to optimize checked baggage predictions incorporating the new loss function. We consider multiple linear regression, LightGBM, and XGBoost, as supervised learning algorithms. We apply our proposed methods to baggage data from a major airline and additional data from various U.S. government agencies. We compare the performance of the three customized supervised learning algorithms. We find that the two gradient boosting methods (i.e., LightGBM and XGBoost) yield higher accuracy than the multiple linear regression; XGBoost outperforms LightGBM while LightGBM requires much less training time than XGBoost. We also investigate the performance of XGBoost on samples from different categories and provide insights for selecting an appropriate prediction algorithm to improve baggage prediction practices. Our modeling framework can be adapted to address other prediction challenges in aviation, such as predicting the number of standby passengers or no-shows.
more »
« less
- PAR ID:
- 10503192
- Publisher / Repository:
- Oxford Academic
- Date Published:
- Journal Name:
- Intelligent Transportation Infrastructure
- ISSN:
- 2752-9991
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Phase of flight (POF) prediction estimates the future state of aircraft along planned trajectories, allowing the prediction of potential conflicts as well as optimization of air space, controlled by the Federal Aviation Administration. In this paper, we present a study conducted to develop three different POF forecasting machine learning models and a statistical regression model using four-dimensional GPS and RADAR Track data from 57 flights provided by an En Route Computer System. The investigated machine learning models include Long Short-Term Memory Recurrent Neural Network (LSTM-RNN), Support Vector Machine (SVM), and Neural Ordinary Differential Equations (NODE). These were developed to forecast the horizontal and vertical POF of the current aircraft for the next time step. The results in this study indicate that LSTM-RNN models are more suitable for POF prediction than SVM and statistical regression models, with NODE being a promising model for future trajectory prediction research.more » « less
-
Understanding the characteristics of air-traffic delays and disruptions is critical for developing ways to mitigate their significant economic and environmental impacts. Conventional delay-performance metrics reflect only the magnitude of incurred flight delays at airports; in this work, we show that it is also important to characterize the spatial distribution of delays across a network of airports. We analyze graph-supported signals, leveraging techniques from spectral theory and graph-signal processing to compute analytical and simulation-driven bounds for identifying outliers in spatial distribution. We then apply these methods to the case of airport-delay networks and demonstrate the applicability of our methods by analyzing U.S. airport delays from 2008 through 2017. We also perform an airline-specific analysis, deriving insights into the delay dynamics of individual airline subnetworks. Through our analysis, we highlight key differences in delay dynamics between different types of disruptions, ranging from nor’easters and hurricanes to airport outages. We also examine delay interactions between airline subnetworks and the system-wide network and compile an inventory of outlier days that could guide future aviation operations and research. In doing so, we demonstrate how our approach can provide operational insights in an air-transportation setting. Our analysis provides a complementary metric to conventional aviation-delay benchmarks and aids airlines, traffic-flow managers, and transportation-system planners in quantifying off-nominal system performance.more » « less
-
Supervised learning models have been used in various domains such as lending, college admission, face recognition, natural language processing, etc. However, they may inherit pre-existing biases from training data and exhibit discrimination against protected social groups. Various fairness notions have been proposed to address unfairness issues. In this work, we focus on Equalized Loss (EL), a fairness notion that requires the expected loss to be (approximately) equalized across different groups. Imposing EL on the learning process leads to a non-convex optimization problem even if the loss function is convex, and the existing fair learning algorithms cannot properly be adopted to find the fair predictor under the EL constraint. This paper introduces an algorithm that can leverage off-the-shelf convex programming tools (e.g., CVXPY (Diamond and Boyd, 2016; Agrawal et al., 2018)) to efficiently find the global optimum of this non-convex optimization. In particular, we propose the ELminimizer algorithm, which finds the optimal fair predictor under EL by reducing the non-convex optimization to a sequence of convex optimization problems. We theoretically prove that our algorithm finds the global optimal solution under certain conditions. Then, we support our theoretical results through several empirical studiesmore » « less
-
Supervised learning models have been used in various domains such as lending, college admission, face recognition, natural language processing, etc. However, they may inherit pre-existing biases from training data and exhibit discrimination against protected social groups. Various fairness notions have been proposed to address unfairness issues. In this work, we focus on Equalized Loss (EL), a fairness notion that requires the expected loss to be (approximately) equalized across different groups. Imposing EL on the learning process leads to a non-convex optimization problem even if the loss function is convex, and the existing fair learning algorithms cannot properly be adopted to find the fair predictor under the EL constraint. This paper introduces an algorithm that can leverage off-the-shelf convex programming tools (e.g., CVXPY) to efficiently find the global optimum of this non-convex optimization. In particular, we propose the ELminimizer algorithm, which finds the optimal fair predictor under EL by reducing the non-convex optimization to a sequence of convex optimization problems. We theoretically prove that our algorithm finds the global optimal solution under certain conditions. Then, we support our theoretical results through several empirical studiesmore » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1093/iti/liae001
