Window-Free IMU-Based Classification of Stair-Climbing Wheelchair Activities Using Machine Learning and Adaptive Boosting
Received: 15 October 2025 | Revised: 1 December 2025, 28 December 2025, and 5 January 2026 | Accepted: 6 January 2026 | Online: 9 February 2026
Corresponding author: Dechrit Maneetham
Abstract
To ensure safety, autonomy, and context-aware control, reliable state recognition is still a challenge for stair-climbing wheelchairs, which offer mobility in environments with steps, curbs, and landings. This study uses instantaneous Inertial Measurement Unit (IMU) data to develop a simplified, window-free method for classifying wheelchair stair-related activities. Instead of sliding-window preprocessing or temporal sequence modeling, this study uses an 18-channel feature set that includes orientation, gyroscope, accelerometer, magnetometer, linear acceleration, and gravity signals. Stratified evaluation and several metrics, such as accuracy, macro-F1, Matthews Correlation Coefficient (MCC), ROC-AUC, and per-class precision-recall, were used to systematically benchmark eight classifiers: Multinomial Logistic Regression (MLR), Gaussian Naïve Bayes (GNB), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), RBF-kernel Support Vector Classifier (SVC), a compact Multilayer Perceptron (MLP), and an adaptive CatBoost configuration. The results show that CatBoost performed almost flawlessly (Accuracy = 0.999, MCC = 0.999), closely followed by compact MLP. RF, KNN, and SVC formed a solid middle tier. In a window-free regime, feature importance analysis showed that instantaneous gyroscope and linear acceleration made very little contribution, while orientation and magnetometer channels were found to be the most crucial features. These results show that accurate and computationally efficient recognition of stair-climbing wheelchair states is possible by features driven by posture and heading. The proposed method facilitates low-latency embedded deployment and identifies areas for future development, such as lightweight temporal enhancements, angle encoding, and magnetometer calibration.
Keywords:
stair-climbing wheelchair, Inertial Measurement Unit (IMU), Human Activity Recognition (HAR), window-free classification, machine learningDownloads
References
Y. Zhu, H. Li, S. Lyu, X. Shan, Y. K. Jan, and F. Ma, "Stair-climbing wheelchair proven to maintain user’s body stability based on AnyBody musculoskeletal model and finite element analysis," PLOS ONE, vol. 18, no. 1, Jan. 2023, Art. no. e0279478. DOI: https://doi.org/10.1371/journal.pone.0279478
R. Baud, A. R. Manzoori, A. Ijspeert, and M. Bouri, "Review of control strategies for lower-limb exoskeletons to assist gait," Journal of NeuroEngineering and Rehabilitation, vol. 18, no. 1, Dec. 2021, Art. no. 119. DOI: https://doi.org/10.1186/s12984-021-00906-3
E. Bergamini, G. Ligorio, A. Summa, G. Vannozzi, A. Cappozzo, and A. Sabatini, "Estimating Orientation Using Magnetic and Inertial Sensors and Different Sensor Fusion Approaches: Accuracy Assessment in Manual and Locomotion Tasks," Sensors, vol. 14, no. 10, pp. 18625–18649, Oct. 2014. DOI: https://doi.org/10.3390/s141018625
O. D. Lara and M. A. Labrador, "A Survey on Human Activity Recognition using Wearable Sensors," IEEE Communications Surveys & Tutorials, vol. 15, no. 3, pp. 1192–1209, 2013. DOI: https://doi.org/10.1109/SURV.2012.110112.00192
O. Banos, J. M. Galvez, M. Damas, H. Pomares, and I. Rojas, "Window Size Impact in Human Activity Recognition," Sensors, vol. 14, no. 4, pp. 6474–6499, Apr. 2014. DOI: https://doi.org/10.3390/s140406474
D. T. Dat, L. H. Ky, S. Hoang, and T. D. Thuan, "Building an Anti-Tip System for Robots Transporting People Up and Down the Stairs," Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 23756–23766, June 2025. DOI: https://doi.org/10.48084/etasr.10618
A. Wang, G. Chen, J. Yang, S. Zhao, and C. Y. Chang, "A Comparative Study on Human Activity Recognition Using Inertial Sensors in a Smartphone," IEEE Sensors Journal, vol. 16, no. 11, pp. 4566–4578, June 2016. DOI: https://doi.org/10.1109/JSEN.2016.2545708
K. Chen, D. Zhang, L. Yao, B. Guo, Z. Yu, and Y. Liu, "Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges, and Opportunities," ACM Computing Surveys, vol. 54, no. 4, pp. 1–40, May 2022. DOI: https://doi.org/10.1145/3447744
W. Chen, J. Li, S. Zhu, X. Zhang, Y. Men, and H. Wu, "Gait Recognition for Lower Limb Exoskeletons Based on Interactive Information Fusion," Applied Bionics and Biomechanics, vol. 2022, pp. 1–19, Mar. 2022. DOI: https://doi.org/10.1155/2022/9933018
W. H. K. De Vries, R. M. A. Van Der Slikke, M. P. Van Dijk, and U. Arnet, "Real-Life Wheelchair Mobility Metrics from IMUs," Sensors, vol. 23, no. 16, Aug. 2023, Art. no. 7174. DOI: https://doi.org/10.3390/s23167174
H. Najeh, C. Lohr, and B. Leduc, "Real-Time Human Activity Recognition on Embedded Equipment: A Comparative Study," Applied Sciences, vol. 14, no. 6, Mar. 2024, Art. no. 2377. DOI: https://doi.org/10.3390/app14062377
A. V. Dorogush, V. Ershov, and A. Gulin, "CatBoost: gradient boosting with categorical features support." arXiv, Oct. 24, 2018.
W. S. Lima, E. Souto, K. El-Khatib, R. Jalali, and J. Gama, "Human Activity Recognition Using Inertial Sensors in a Smartphone: An Overview," Sensors, vol. 19, no. 14, July 2019, Art. no. 3213. DOI: https://doi.org/10.3390/s19143213
G. McClatchey, M. Goršič, M. R. Adelman, W. C. Kephart, and J. R. Rammer, "Holistic Sensor-Based Approach for Assessing Community Mobility and Participation of Manual Wheelchair Users in the Real World," Journal of Sensor and Actuator Networks, vol. 13, no. 6, Oct. 2024, Art. no. 70. DOI: https://doi.org/10.3390/jsan13060070
J. Wang, Y. Chen, S. Hao, X. Peng, and L. Hu, "Deep learning for sensor-based activity recognition: A survey," Pattern Recognition Letters, vol. 119, pp. 3–11, Mar. 2019. DOI: https://doi.org/10.1016/j.patrec.2018.02.010
D. Su, Z. Hu, J. Wu, P. Shang, and Z. Luo, "Review of adaptive control for stroke lower limb exoskeleton rehabilitation robot based on motion intention recognition," Frontiers in Neurorobotics, vol. 17, July 2023, Art. no. 1186175. DOI: https://doi.org/10.3389/fnbot.2023.1186175
L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, Oct. 2001. DOI: https://doi.org/10.1023/A:1010933404324
D. Chicco and G. Jurman, "The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation," BMC Genomics, vol. 21, no. 1, Dec. 2020, Art. no. 6. DOI: https://doi.org/10.1186/s12864-019-6413-7
Y. Tian, J. Zhang, J. Wang, Y. Geng, and X. Wang, "Robust human activity recognition using single accelerometer via wavelet energy spectrum features and ensemble feature selection," Systems Science & Control Engineering, vol. 8, no. 1, pp. 83–96, Jan. 2020. DOI: https://doi.org/10.1080/21642583.2020.1723142
S. Mekruksavanich and A. Jitpattanakul, "Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data," Electronics, vol. 10, no. 14, July 2021, Art. no. 1685. DOI: https://doi.org/10.3390/electronics10141685
F. Bo, J. Li, W. Wang, and K. Zhou, "Robust Attitude and Heading Estimation under Dynamic Motion and Magnetic Disturbance," Micromachines, vol. 14, no. 5, May 2023, Art. no. 1070. DOI: https://doi.org/10.3390/mi14051070
P. Chawaphan, D. Maneetham, and P. N. Crisnapati, "Stairclimbing Wheelchair Dataset," Mendeley Data, vol. 1, Dec. 2024.
A. R. Rachakonda and A. Bhatnagar, "A : Extending area under the ROC curve for probabilistic labels," Pattern Recognition Letters, vol. 150, pp. 265–271, Oct. 2021. DOI: https://doi.org/10.1016/j.patrec.2021.06.023
Q. Lin, G. Ye, J. Wang, and H. Liu, "RoboFlow: a Data-centric Workflow Management System for Developing AI-enhanced Robots," in Proceedings of the 5th Conference on Robot Learning, Jan. 2022, pp. 1789–1794.
A. De La Cruz Huayanay, J. L. Bazán, and C. M. Russo, "Performance of evaluation metrics for classification in imbalanced data," Computational Statistics, Aug. 2024. DOI: https://doi.org/10.1007/s00180-024-01539-5
D. Chicco and G. Jurman, "The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification," BioData Mining, vol. 16, no. 1, Feb. 2023, Art. no. 4. DOI: https://doi.org/10.1186/s13040-023-00322-4
E. Christodoulou, J. Ma, G. S. Collins, E. W. Steyerberg, J. Y. Verbakel, and B. Van Calster, "A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models," Journal of Clinical Epidemiology, vol. 110, pp. 12–22, June 2019. DOI: https://doi.org/10.1016/j.jclinepi.2019.02.004
A. Ali, W. Samara, D. Alhaddad, A. Ware, and O. A. Saraereh, "Human Activity and Motion Pattern Recognition within Indoor Environment Using Convolutional Neural Networks Clustering and Naive Bayes Classification Algorithms," Sensors, vol. 22, no. 3, Jan. 2022, Art. no. 1016. DOI: https://doi.org/10.3390/s22031016
A. N. Beskopylny et al., "Concrete Strength Prediction Using Machine Learning Methods CatBoost, k-Nearest Neighbors, Support Vector Regression," Applied Sciences, vol. 12, no. 21, Oct. 2022, Art. no. 10864. DOI: https://doi.org/10.3390/app122110864
I. D. Mienye and N. Jere, "A Survey of Decision Trees: Concepts, Algorithms, and Applications," IEEE Access, vol. 12, pp. 86716–86727, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3416838
Y. Wang and Y. Li, "Mapping the ratoon rice suitability region in China using random forest and recursive feature elimination modeling," Field Crops Research, vol. 301, Oct. 2023, Art. no. 109016. DOI: https://doi.org/10.1016/j.fcr.2023.109016
S. Y. Sheikh and M. T. Jilani, "A ubiquitous wheelchair fall detection system using low-cost embedded inertial sensors and unsupervised one-class SVM," Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 1, pp. 147–162, Jan. 2023. DOI: https://doi.org/10.1007/s12652-021-03279-6
L. Madaoui, O. Kerdjidj, and M. Kedir-Talha, "Design and implementation of IMU-based locomotion mode recognition system on Zynq SoC," Microprocessors and Microsystems, vol. 102, Oct. 2023, Art. no. 104927. DOI: https://doi.org/10.1016/j.micpro.2023.104927
A. K. Sharma, S. H. Liu, X. Zhu, and W. Chen, "Predicting Gait Parameters of Leg Movement with sEMG and Accelerometer Using CatBoost Machine Learning," Electronics, vol. 13, no. 9, May 2024, Art. no. 1791. DOI: https://doi.org/10.3390/electronics13091791
Downloads
How to Cite
License
Copyright (c) 2026 Pharan Chawaphan, Dechrit Maneetham, Padma Nyoman Crisnapati
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
