Classifying Unstable and Stable Walking Patterns Using Electroencephalography Signals and Machine Learning Algorithms
Analyzing unstable gait patterns from Electroencephalography (EEG) signals is vital to develop real-time brain-computer interface (BCI) systems to prevent falls and associated injuries. This study investigates the feasibility of classification algorithms to detect walking instability utilizing EEG s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/13/6005 |
| _version_ | 1797590858292264960 |
|---|---|
| author | Rahul Soangra Jo Armour Smith Sivakumar Rajagopal Sai Viswanth Reddy Yedavalli Erandumveetil Ramadas Anirudh |
| author_facet | Rahul Soangra Jo Armour Smith Sivakumar Rajagopal Sai Viswanth Reddy Yedavalli Erandumveetil Ramadas Anirudh |
| author_sort | Rahul Soangra |
| collection | DOAJ |
| description | Analyzing unstable gait patterns from Electroencephalography (EEG) signals is vital to develop real-time brain-computer interface (BCI) systems to prevent falls and associated injuries. This study investigates the feasibility of classification algorithms to detect walking instability utilizing EEG signals. A 64-channel Brain Vision EEG system was used to acquire EEG signals from 13 healthy adults. Participants performed walking trials for four different stable and unstable conditions: (i) normal walking, (ii) normal walking with medial-lateral perturbation (MLP), (iii) normal walking with dual-tasking (Stroop), (iv) normal walking with center of mass visual feedback. Digital biomarkers were extracted using wavelet energy and entropies from the EEG signals. Algorithms like the ChronoNet, SVM, Random Forest, gradient boosting and recurrent neural networks (LSTM) could classify with 67 to 82% accuracy. The classification results show that it is possible to accurately classify different gait patterns (from stable to unstable) using EEG-based digital biomarkers. This study develops various machine-learning-based classification models using EEG datasets with potential applications in detecting unsteady gait neural signals and intervening by preventing falls and injuries. |
| first_indexed | 2024-03-11T01:29:26Z |
| format | Article |
| id | doaj.art-7ae1b90fd45046a4abf95119e64829e8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:29:26Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7ae1b90fd45046a4abf95119e64829e82023-11-18T17:29:56ZengMDPI AGSensors1424-82202023-06-012313600510.3390/s23136005Classifying Unstable and Stable Walking Patterns Using Electroencephalography Signals and Machine Learning AlgorithmsRahul Soangra0Jo Armour Smith1Sivakumar Rajagopal2Sai Viswanth Reddy Yedavalli3Erandumveetil Ramadas Anirudh4Fowler School of Engineering, Chapman University, Orange, CA 92866, USACrean College of Health and Behavioral Sciences, Chapman University, Orange, CA 92866, USASchool of Electronics Engineering, Vellore Institute of Technology, Vellore 632014, IndiaSchool of Electronics Engineering, Vellore Institute of Technology, Vellore 632014, IndiaSchool of Electronics Engineering, Vellore Institute of Technology, Vellore 632014, IndiaAnalyzing unstable gait patterns from Electroencephalography (EEG) signals is vital to develop real-time brain-computer interface (BCI) systems to prevent falls and associated injuries. This study investigates the feasibility of classification algorithms to detect walking instability utilizing EEG signals. A 64-channel Brain Vision EEG system was used to acquire EEG signals from 13 healthy adults. Participants performed walking trials for four different stable and unstable conditions: (i) normal walking, (ii) normal walking with medial-lateral perturbation (MLP), (iii) normal walking with dual-tasking (Stroop), (iv) normal walking with center of mass visual feedback. Digital biomarkers were extracted using wavelet energy and entropies from the EEG signals. Algorithms like the ChronoNet, SVM, Random Forest, gradient boosting and recurrent neural networks (LSTM) could classify with 67 to 82% accuracy. The classification results show that it is possible to accurately classify different gait patterns (from stable to unstable) using EEG-based digital biomarkers. This study develops various machine-learning-based classification models using EEG datasets with potential applications in detecting unsteady gait neural signals and intervening by preventing falls and injuries.https://www.mdpi.com/1424-8220/23/13/6005unstable gaitfall riskEEGmachine learningChronoNetrecurrent neural networks |
| spellingShingle | Rahul Soangra Jo Armour Smith Sivakumar Rajagopal Sai Viswanth Reddy Yedavalli Erandumveetil Ramadas Anirudh Classifying Unstable and Stable Walking Patterns Using Electroencephalography Signals and Machine Learning Algorithms Sensors unstable gait fall risk EEG machine learning ChronoNet recurrent neural networks |
| title | Classifying Unstable and Stable Walking Patterns Using Electroencephalography Signals and Machine Learning Algorithms |
| title_full | Classifying Unstable and Stable Walking Patterns Using Electroencephalography Signals and Machine Learning Algorithms |
| title_fullStr | Classifying Unstable and Stable Walking Patterns Using Electroencephalography Signals and Machine Learning Algorithms |
| title_full_unstemmed | Classifying Unstable and Stable Walking Patterns Using Electroencephalography Signals and Machine Learning Algorithms |
| title_short | Classifying Unstable and Stable Walking Patterns Using Electroencephalography Signals and Machine Learning Algorithms |
| title_sort | classifying unstable and stable walking patterns using electroencephalography signals and machine learning algorithms |
| topic | unstable gait fall risk EEG machine learning ChronoNet recurrent neural networks |
| url | https://www.mdpi.com/1424-8220/23/13/6005 |
| work_keys_str_mv | AT rahulsoangra classifyingunstableandstablewalkingpatternsusingelectroencephalographysignalsandmachinelearningalgorithms AT joarmoursmith classifyingunstableandstablewalkingpatternsusingelectroencephalographysignalsandmachinelearningalgorithms AT sivakumarrajagopal classifyingunstableandstablewalkingpatternsusingelectroencephalographysignalsandmachinelearningalgorithms AT saiviswanthreddyyedavalli classifyingunstableandstablewalkingpatternsusingelectroencephalographysignalsandmachinelearningalgorithms AT erandumveetilramadasanirudh classifyingunstableandstablewalkingpatternsusingelectroencephalographysignalsandmachinelearningalgorithms |