Home // ADVCOMP 2022, The Sixteenth International Conference on Advanced Engineering Computing and Applications in Sciences // View article

Data and Feature Engineering Challenges in Machine Learning

Authors:
Kendall Nygard
Mostofa Ahsan
Aakanksha Rastogi
Rashmio Satyal

Keywords: Machine Learning, Data Management, Feature Engineering, Self-Driving Cars, Intrusion Detection

Abstract:
The process of developing of a machine learning application presents multiple challenges relating to data and their features. Based on experiences with several applied studies carried out using machine learning methodologies, we report on addressing challenges in the collection, quantity, distribution, quality, sampling, of and relevancy of data. We also address feature engineering and selection issues, including approaches to identifying, combining, and eliminating attributes and features that are not needed or of low significance. We include insight into overfitting and underfitting training data. Example applications include classification, anti-autonomy and trust modeling and analytics for self-driving cars and intrusion detection systems aimed at detecting malicious activity.

Pages: 1 to 10

Copyright: Copyright (c) IARIA, 2022

Publication date: November 13, 2022

Published in: conference

ISSN: 2308-4499

ISBN: 978-1-61208-990-4

Location: Valencia, Spain

Dates: from November 13, 2022 to November 17, 2022