Title
Classifying Human Manual Control Behavior Using LSTM Recurrent Neural Networks
Author
Versteeg, Rogier (Student TU Delft)
Pool, D.M. (TU Delft Control & Simulation)
Mulder, Max (TU Delft Control & Simulation)
Date
2024
Abstract
This article discusses a long short-term memory (LSTM) recurrent neural network that uses raw time-domain data obtained in compensatory tracking tasks as input features for classifying (the adaptation of) human manual control with single- and double-integrator controlled element dynamics. Data from two different experiments were used to train and validate the LSTM classifier, including investigating effects of several key data preprocessing settings. The model correctly classifies human control behavior (cross-experiment validation accuracy 96%) using short 1.6-s data windows. To achieve this accuracy, it is found crucial to scale/standardize the input feature data and use a combination of input signals that includes the tracking error and human control output. A possible online application of the classifier was tested on data from a third experiment with time-varying and slightly different controlled element dynamics. The results show that the LSTM classification is still successful, which makes it a promising online technique to rapidly detect adaptations in human control behavior.
Subject
Behavioral sciences
Classification
cybernetics
Data models
Frequency control
human–machine systems
manual control
neural networks
Pattern recognition
Real-time systems
Task analysis
Training
To reference this document use:
http://resolver.tudelft.nl/uuid:da0041d8-2f77-4716-8816-d70e0c66cd05
DOI
https://doi.org/10.1109/THMS.2023.3327145
Embargo date
2024-06-03
ISSN
2168-2291
Source
IEEE Transactions on Human-Machine Systems, 54 (1), 89-99
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Part of collection
Institutional Repository
Document type
journal article
Rights
© 2024 Rogier Versteeg, D.M. Pool, Max Mulder