Multi-level aircraft feature representation and selection for aviation environmental impact analysis

Gao, Zhenyu; Kampezidou, Styliani I.; Behere, Ameya; Puranik, Tejas G.; Rajaram, Dushhyanth; Mavris, Dimitri N.

doi:10.1016/j.trc.2022.103824

Cited by 14 publications

(4 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…engineering [23][24][25][26][27]. Specifically in Artificial Intelligence (AI), machine learning frameworks have been proposed for a variety of data-driven expert systems, such as recommendation systems [28], decision support systems [29], fault diagnosis [30,31], crowdsourcing [32], as well as, generic data science [33], and big data [34] applications.…”

Section: Of 36mentioning

confidence: 99%

“…Multi-output models utilize an l 2,1 norm penalization term which either includes or excludes a feature from the model for all outputs [111]. In the multi-output case, the average weight of a feature across all outputs is obtained and then these average weights are normalized in the [0, 1] range (relative importance) with the Min-Max scaling method so that a rank of feature relative importance is derived [23]. 2.…”

Section: Feature Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Fundamental Components and Principles of Supervised Machine Learning Workflows with Numerical and Categorical Data

Kampezidou,

Tikayat Ray,

Bhat

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper offers a comprehensive examination of the process involved in developing and automating supervised end-to-end machine learning workflows for forecasting and classification purposes. It offers a complete overview of the components (i.e. feature engineering, model selection, etc), principles (i.e. bias-variance decomposition, model complexity, overfitting, model sensitivity to feature assumptions and scaling, output interpretability, etc), models (i.e. neural networks, regression models, etc), methods (i.e. Cross-Validation, data augmentation, etc), metrics (i.e. Mean Squared Error, F1-score, etc) and tools that rule most supervised learning applications with numerical and categorical data, as well as their integration, automation, and deployment. The end goal and contribution of this paper is the education and guidance of the non-AI expert academic community over complete and rigorous machine learning pipelines and data science practices, from problem scoping to design and state-of-the-art automation tools, including basic principles and reasoning in the choice of methods. The paper delves into the critical stages of supervised machine learning workflow development, many of which are often omitted by researchers due to brevity, and covers foundational concepts essential for understanding and optimizing a functional machine learning workflow, thereby offering a holistic view of task-specific application development for applied researchers who are not AI experts.

show abstract

Section: Of 36mentioning

confidence: 99%

Section: Feature Selectionmentioning

confidence: 99%

Fundamental Components and Principles of Supervised Machine Learning Workflows with Numerical and Categorical Data

Kampezidou,

Tikayat Ray,

Bhat

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The Aviation Environmental Design Tool (AEDT) has been a cornerstone in aviation environmental impact assessment in the U.S., particularly at airports where The Aviation Environmental Design Tool (AEDT) has been a cornerstone in aviation environmental impact assessment in the U.S., particularly at airports where comprehensive aircraft operation and fleet mix data are readily available [11,12,17]. Researchers have explored strategies for optimizing aircraft departure and arrival procedures to enhance aviation environmental impact assessments, heavily relying on AEDT [18][19][20][21][22][23][24][25][26][27][28][29][30][31]. Notably, Behere et al [30] pioneered a data-driven approach to refining noise assessments using AEDT and openly accessible surveillance data.…”

Section: Introductionmentioning

confidence: 99%

An Experimental and Analytical Approach to Evaluate Transponder-Based Aircraft Noise Monitoring Technology

Yang,

Mott

2024

Aerospace

View full text Add to dashboard Cite

Aviation is a vital modern transportation sector connecting millions of passengers globally. Sustainable aviation development holds substantial community benefits, necessitating effective management of its environmental impacts. This paper addresses the need for an accurate and cost-effective aircraft noise monitoring model tailored to non-towered general aviation airports with limited resources for official air traffic data collection. The existing literature highlights a heavy reliance on air traffic data from control facilities in prevailing aircraft noise modeling solutions, revealing a disparity between real-world constraints and optimal practices. Our study presents a validation of a three-stage framework centered on a low-cost transponder unit, employing an innovative experimental and analytical approach to assess the model’s accuracy. An economical Automatic Dependent Surveillance-broadcast (ADS-B) receiver is deployed at Purdue University Airport (ICAO Code: KLAF) to estimate aircraft noise levels using the developed approach. Simultaneously, a physical sound meter is positioned at KLAF to capture actual acoustic noise levels, facilitating a direct comparison with the modeled data. Results demonstrate that the developed noise model accurately identifies aircraft noise events with an average error of 4.50 dBA. This suggests the viability of our low-cost noise monitoring approach as an affordable solution for non-towered general aviation airports. In addition, this paper discusses the limitations and recommendations for future research.

show abstract

“…It allows not only for more affordable and quieter flights but also for flights with a decreased or zero impact on the environment [1]. The goal of reducing or even eliminating conventional fuel consumption can be achieved by shifting toward electrified aircraft propulsion [2]. However, current battery technologies do not allow for fully electric large aircraft due to the low battery specific energy [1].…”

Section: Introductionmentioning

confidence: 99%

System-level Trade Study of Hybrid Parallel Propulsion Architectures on Future Regional and Thin Haul Turboprop Aircraft

Cai

Pastra

Xie

et al. 2023

AIAA SCITECH 2023 Forum

Self Cite

View full text Add to dashboard Cite

This paper evaluates the potential benefits of applying hybrid parallel propulsion architectures to future turboprop aircraft that are expected to enter into service in 2030. Two baseline aircraft models are established by infusing viable 2030 airframe and engine technologies on state-of-the-art 19-passenger and 50-passenger aircraft models. Two parametric parallel hybrid architectures are proposed and applied on both size classes: Architecture 1 has two propellers, each driven by an engine and an electric motor in parallel, and allows in-flight recharging; Architecture 2 has four propellers, each driven by either an engine or an electric motor, and allows parallel operation during the cruise. A design space exploration is conducted on the powertrain design variables and the electric component key performance parameters. A constrained optimization implies that Architecture 1 and 2 can achieve fuel savings of about 2.6% and 6.6%, respectively, given 2030 electric component technology assumptions. Electric taxi consistently results in fuel saving when battery technology is beyond the projected 2030 level. Preliminary sensitivity studies show that the performance of Architecture 2 is more sensitive to the battery technology compared to Architecture 1 due to its extensive use of battery energy during the cruise.

show abstract

Multi-level aircraft feature representation and selection for aviation environmental impact analysis

Cited by 14 publications

References 48 publications

Fundamental Components and Principles of Supervised Machine Learning Workflows with Numerical and Categorical Data

Fundamental Components and Principles of Supervised Machine Learning Workflows with Numerical and Categorical Data

An Experimental and Analytical Approach to Evaluate Transponder-Based Aircraft Noise Monitoring Technology

System-level Trade Study of Hybrid Parallel Propulsion Architectures on Future Regional and Thin Haul Turboprop Aircraft

Contact Info

Product

Resources

About