Simulation and Classification of Spatial Disorientation in a Flight use-case using Vestibular Stimulation
- Citation Author(s):
- Submitted by:
- Jamilah Foucher
- Last updated:
- Tue, 09/06/2022 - 05:05
- Data Format:
A commonly used definition of spatial disorientation (SD) in aviation is "an erroneous sense of one’s position and motion relative to the plane of the earth’s surface". There exists a wide range of SD use-cases dictated by situational factors, therefore SD has been predominantly studied using reduced motion detection experimental contexts in isolation. The study of SD by use-case makes it difficult to understand general SD occurrence and thus provide viable solutions. To investigate SD in a generalized manner, a two-part Human Activity Recognition (HAR) study was performed. In Part I, a generalized SD perception dataset was created using whole-body experimental motion detection methods in a naturalistic flight context; joystick response was measured during rotational or translational vestibular stimulation. Results showed that SD occurred less for faster speeds than slower speeds, and specific orientations and axes were more difficult to detect motion. Part II evaluated supervised and unsupervised model parameters, including: model architecture, data use-case, feature-type, feature quantity, ground-truth labeling, unsupervised labeling. Long-Short Term Memory (LSTM), Random Forest (RF), and Transformer Encoder models most accurately predicted SD with mean accuracy of 0.84, 0.82, and 0.77 respectively. Using permutation importance (PIM), a dependency score for time, frequency, and time \& frequency feature-types quantified the amount that each model architecture depended on a feature-type. The lenient ground-truth label best characterized features, and K-medoids clustering using position and velocity features most accurately replicated ground-truth labels.
Foucher et al., Simulation and Classification of Spatial Disorientation in a Flight use-case using Vestibular Stimulation. IEEE Access submission, 2022. There are two types of files to download: 1. The experimental cabin motion and joystick response data, created from the whole-body motion simulator iMose shown in the main image: a) rotdat.pkl is a pickle file that contains joystick responses for the rotational experiment, b) transdat.pkl is a pickle file that contains joystick responses for the translational experiment. 2. The python code that loads the time-series and initial detection responses in a pandas Dataframe. Motor_classification_python_load_data.py contains the subfunctions and code for loading two types of Dataframes.
- Rotational and translational data exp_data.tar.gz (5.16 MB)
- Main script for loading the experimental data Motor_classification_python_load_data.py (34.11 kB)
How to download this dataset?
Thank you for your interest in our research! Our apologies for not making the data available online, we were in the process of doing a second revision of the paper and uploading the data was delayed. We have uploaded the data for both rotational and translational experiments, and supplied code for loading the data and for our main analyses. Let us know if you have any other problems accessing the data. All the best.
This dataset is associated with an IEEE Access submission in review: Foucher et al., Simulation and Classification of Spatial Disorientation in a Flight use-case using Vestibular Stimulation. IEEE Access (in revision), 2022.