{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T21:07:13Z","timestamp":1790888833050,"version":"4.1.0"},"reference-count":50,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Fonds de Recherche du Qu\u00e9bec (FRQ) Audace International Qu\u00e9bec\u2013Luxembourg"},{"DOI":"10.13039\/501100001866","name":"Fonds National de la Recherche Luxembourg","doi-asserted-by":"crossref","award":["315603"],"award-info":[{"award-number":["315603"]}],"id":[{"id":"10.13039\/501100001866","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>(1) Background: Navigating surfaces during walking can alter gait patterns. This study aims to develop tools for automatic walking condition classification using inertial measurement unit (IMU) and foot pressure sensors. We compared sensor modalities (IMUs on lower-limbs, IMUs on feet, IMUs on the pelvis, pressure insoles, and IMUs on the feet or pelvis combined with pressure insoles) and evaluated whether gait cycle segmentation improves performance compared to a sliding window. (2) Methods: Twenty participants performed flat, stairs up, stairs down, slope up, and slope down walking trials while fitted with IMUs and pressure insoles. Machine learning (ML; Extreme Gradient Boosting) and deep learning (DL; Convolutional Neural Network + Long Short-Term Memory) models were trained to classify these conditions. (3) Results: Overall, a DL model using lower-limb IMUs processed with gait segmentation performed the best (F1=0.89). Models trained with IMUs outperformed those trained on pressure insoles (p&lt;0.01). Combining sensor modalities and gait segmentation improved performance for ML models (p&lt;0.01). The best minimal model was a DL model trained on IMU pelvis + pressure insole data using sliding window segmentation (F1=0.83). (4) Conclusions: IMUs provide the most discriminative features for automatic walking condition classification. Combining sensor modalities may be helpful for some model architectures. DL models perform well without gait segmentation, making them independent of gait event identification algorithms.<\/jats:p>","DOI":"10.3390\/s26010232","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T14:33:25Z","timestamp":1767191605000},"page":"232","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Outdoor Walking Classification Based on Inertial Measurement Unit and Foot Pressure Sensor Data"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6894-4403","authenticated-orcid":false,"given":"Oussama","family":"Jlassi","sequence":"first","affiliation":[{"name":"Department of Kinesiology and Physical Education, McGill University, Montreal, QC H2W 1S4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jill","family":"Emmerzaal","sequence":"additional","affiliation":[{"name":"Department of Kinesiology and Physical Education, McGill University, Montreal, QC H2W 1S4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1113-5218","authenticated-orcid":false,"given":"Gabriella","family":"Vinco","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Luxembourg, 4365 Esch-sur-Alzette, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederic","family":"Garcia","sequence":"additional","affiliation":[{"name":"Department of Precision Health, Luxembourg Institute of Health, 1445 Luxembourg, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2290-8437","authenticated-orcid":false,"given":"Christophe","family":"Ley","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Luxembourg, 4365 Esch-sur-Alzette, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4585-4643","authenticated-orcid":false,"given":"Bernd","family":"Grimm","sequence":"additional","affiliation":[{"name":"Department of Precision Health, Luxembourg Institute of Health, 1445 Luxembourg, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3581-7259","authenticated-orcid":false,"given":"Philippe C.","family":"Dixon","sequence":"additional","affiliation":[{"name":"Department of Kinesiology and Physical Education, McGill University, Montreal, QC H2W 1S4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.humov.2018.04.003","article-title":"Magnitude and variability of gait characteristics when walking on an irregular surface at different speeds","volume":"59","author":"Blair","year":"2018","journal-title":"Hum. Mov. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1016\/j.gaitpost.2008.11.012","article-title":"Gait alterations of diabetic patients while walking on different surfaces","volume":"29","author":"Allet","year":"2009","journal-title":"Gait Posture"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.gaitpost.2021.09.176","article-title":"The impact of outdoor walking surfaces on lower-limb coordination and variability during gait in healthy adults","volume":"91","author":"Ippersiel","year":"2022","journal-title":"Gait Posture"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/j.gaitpost.2018.01.027","article-title":"Gait adaptations of older adults on an uneven brick surface can be predicted by age-related physiological changes in strength","volume":"61","author":"Dixon","year":"2018","journal-title":"Gait Posture"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.jbiomech.2017.01.045","article-title":"Gait stability, variability and complexity on inclined surfaces","volume":"54","author":"Vieira","year":"2017","journal-title":"J. Biomech."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/S0966-6362(02)00159-5","article-title":"Acceleration patterns of the head and pelvis when walking on level and irregular surfaces","volume":"18","author":"Menz","year":"2003","journal-title":"Gait Posture"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Emmerzaal, J., Ippersiel, P., and Dixon, P.C. (2025). Non-Linear Gait Dynamics Are Affected by Commonly Occurring Outdoor Surfaces and Sex in Healthy Adults. Sensors, 25.","DOI":"10.3390\/s25134191"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1016\/j.gaitpost.2008.10.057","article-title":"Effects of walking surfaces and footwear on temporo-spatial gait parameters in young and older people","volume":"29","author":"Menant","year":"2009","journal-title":"Gait Posture"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.2105\/AJPH.2005.083055","article-title":"Outdoor falls among middle-aged and older adults: A neglected public health problem","volume":"96","author":"Li","year":"2006","journal-title":"Am. J. Public Health"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.jbiomech.2022.111159","article-title":"Generalizability of deep learning models for predicting outdoor irregular walking surfaces","volume":"139","author":"Shah","year":"2022","journal-title":"J. Biomech."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40430-024-05318-7","article-title":"Classifying walking pattern on different surfaces by optimising features extracted through IMU sensor data using SSA optimisation","volume":"47","author":"Chauhan","year":"2025","journal-title":"J. Braz. Soc. Mech. Sci. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Y\u0131ld\u0131z, A. (2023). Towards environment-aware fall risk assessment: Classifying walking surface conditions using IMU-based gait data and deep learning. Brain Sci., 13.","DOI":"10.3390\/brainsci13101428"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"103414","DOI":"10.1016\/j.apergo.2021.103414","article-title":"Applying deep neural networks and inertial measurement unit in recognizing irregular walking differences in the real world","volume":"96","author":"Hu","year":"2021","journal-title":"Appl. Ergon."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/s12283-021-00359-w","article-title":"Automatic classification of running surfaces using an ankle-worn inertial sensor","volume":"24","author":"Worsey","year":"2021","journal-title":"Sports Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1569","DOI":"10.1109\/TBME.2021.3065809","article-title":"A machine learning strategy for locomotion classification and parameter estimation using fusion of wearable sensors","volume":"68","author":"Camargo","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kim, P., Lee, J., and Shin, C.S. (2021). Classification of walking environments using deep learning approach based on surface EMG sensors only. Sensors, 21.","DOI":"10.3390\/s21124204"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Shin, D., Lee, S., and Hwang, S. (2021). Locomotion mode recognition algorithm based on Gaussian mixture model using IMU sensors. Sensors, 21.","DOI":"10.3390\/s21082785"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Seo, K.J., Lee, J., Cho, J.E., Kim, H., and Kim, J.H. (2025). Gait Environment Recognition Using Biomechanical and Physiological Signals with Feed-Forward Neural Network: A Pilot Study. Sensors, 25.","DOI":"10.3390\/s25144302"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100804","DOI":"10.1016\/j.patter.2023.100804","article-title":"Leakage and the reproducibility crisis in machine-learning-based science","volume":"4","author":"Kapoor","year":"2023","journal-title":"Patterns"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"gix019","DOI":"10.1093\/gigascience\/gix019","article-title":"The need to approximate the use-case in clinical machine learning","volume":"6","author":"Saeb","year":"2017","journal-title":"GigaScience"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"McQuire, J., Watson, P., Wright, N., Hiden, H., and Catt, M. (2021, January 9\u201312). Uneven and irregular surface condition prediction from human walking data using both centralized and decentralized machine learning approaches. Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, TX, USA.","DOI":"10.1109\/BIBM52615.2021.9669395"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ng, H.R., Sossa, I., Nam, Y., and Youn, J.H. (2022). Machine learning approach for automated detection of irregular walking surfaces for walkability assessment with wearable sensor. Sensors, 23.","DOI":"10.3390\/s23010193"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Warmerdam, E., Burger, L.M., Mergen, D.F., Orth, M., Pohlemann, T., and Ganse, B. (2024). The walking surface influences vertical ground reaction force and centre of pressure data obtained with pressure-sensing insoles. Front. Digit. Health, 6.","DOI":"10.3389\/fdgth.2024.1476335"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1038\/s41597-022-01580-3","article-title":"A Multi-Modal Gait Database of Natural Everyday-Walk in an Urban Environment","volume":"9","author":"Losing","year":"2022","journal-title":"Sci. Data"},{"key":"ref_25","unstructured":"Schepers, M., Giuberti, M., and Bellusci, G. (2018). Xsens MVN: Consistent Tracking of Human Motion Using Inertial Sensing, XSENS TECHNOLOGIES B.V."},{"key":"ref_26","unstructured":"(2025, April 08). IEE Smart Sensing Solutions. Available online: https:\/\/iee-sensing.com\/health-tech\/."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1016\/S0021-9290(01)00222-6","article-title":"ISB recommendation on definitions of joint coordinate system of various joints for the reporting of human joint motion\u2014Part I: Ankle, hip, and spine","volume":"35","author":"Wu","year":"2002","journal-title":"J. Biomech."},{"key":"ref_28","unstructured":"Leng, Z., Iyer, A., and Pl\u00f6tz, T. (2025). Scaling Human Activity Recognition: A Comparative Evaluation of Synthetic Data Generation and Augmentation Techniques. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6474","DOI":"10.3390\/s140406474","article-title":"Window Size Impact in Human Activity Recognition","volume":"14","author":"Banos","year":"2014","journal-title":"Sensors"},{"key":"ref_30","unstructured":"(2025, April 08). The Pandas Development Team. pandas-dev\/pandas: Pandas. Available online: https:\/\/zenodo.org\/records\/17992932."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"ref_32","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.neucom.2018.03.067","article-title":"Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh\u2014A Python package)","volume":"307","author":"Christ","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1038\/s41598-024-84702-8","article-title":"Boosting any learning algorithm with Statistically Enhanced Learning","volume":"15","author":"Felice","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1093\/bioinformatics\/btm344","article-title":"A review of feature selection techniques in bioinformatics","volume":"23","author":"Saeys","year":"2007","journal-title":"Bioinformatics"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"168","DOI":"10.18178\/joig.12.2.168-175","article-title":"Gait Recognition Using Hybrid LSTM-CNN Deep Neural Networks","volume":"12","author":"Burges","year":"2024","journal-title":"J. Image Graph."},{"key":"ref_38","unstructured":"Kumar, D., and Gupta, T. (2024, January 25\u201326). Fusion of CNN and LSTM Models for Enhanced Gait Swing Phase Identification. Proceedings of the 2024 Global Conference on Communications and Information Technologies (GCCIT), Bangalore, India."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.actaastro.2025.06.049","article-title":"Convolutional neural network and long short-term memory hybrid model-based gait prediction for spacesuit intelligent assistive device in low gravity environment","volume":"236","author":"Lv","year":"2025","journal-title":"Acta Astronaut."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"110012","DOI":"10.1016\/j.gaitpost.2025.110012","article-title":"The effect of inaccurate initial contact events on kinematics in healthy and pathological gait","volume":"123","author":"Dumphart","year":"2026","journal-title":"Gait Posture"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Blades, S., Marriott, H., Hundza, S., Honert, E.C., Stellingwerff, T., and Klimstra, M. (2023). Evaluation of Different Pressure-Based Foot Contact Event Detection Algorithms across Different Slopes and Speeds. Sensors, 23.","DOI":"10.3390\/s23052736"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kobayashi, S., Katsurada, R., and Hasegawa, T. (2019, January 20\u201323). Estimation of sidewalk surface type with a smartphone. Proceedings of the 2019 7th International Conference on Information Technology: IoT and Smart City, Shanghai, China.","DOI":"10.1145\/3377170.3377263"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-020-0563-y","article-title":"A database of human gait performance on irregular and uneven surfaces collected by wearable sensors","volume":"7","author":"Luo","year":"2020","journal-title":"Sci. Data"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1080\/02640414.2019.1680083","article-title":"Determining motions with an IMU during level walking and slope and stair walking","volume":"38","author":"Chen","year":"2019","journal-title":"J. Sports Sci."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.advengsoft.2017.07.002","article-title":"Salp Swarm Algorithm: A bio-inspired optimizer for engineering design problems","volume":"114","author":"Mirjalili","year":"2017","journal-title":"Adv. Eng. Softw."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"5001","DOI":"10.1007\/s10994-021-06096-2","article-title":"TSFuse: Automated feature construction for multiple time series data","volume":"113","author":"Hendrickx","year":"2024","journal-title":"Mach. Learn."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Hashmi, M.Z.U.H., Riaz, Q., Hussain, M., and Shahzad, M. (2019). What lies beneath one\u2019s feet? terrain classification using inertial data of human walk. Appl. Sci., 9.","DOI":"10.3390\/app9153099"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Bunker, M.T., Sher, A., Akpokodje, V., Villagra, F., Parthal\u00e1in, N.M., and Akanyeti, O. (2021). Towards fuzzy context-aware automatic gait assessments in free-living environments. UK Workshop on Computational Intelligence, Springer.","DOI":"10.1007\/978-3-030-87094-2_41"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"e13130","DOI":"10.1111\/exsy.13130","article-title":"Towards personalized environment-aware outdoor gait analysis using a smartphone","volume":"40","author":"Sher","year":"2023","journal-title":"Expert Syst."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1631\/FITEE.1800601","article-title":"Recognition of walking environments and gait period by surface electromyography","volume":"20","author":"Kyeong","year":"2019","journal-title":"Front. Inf. Technol. Electron. Eng."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/232\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T05:30:15Z","timestamp":1767245415000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,30]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010232"],"URL":"https:\/\/doi.org\/10.3390\/s26010232","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,30]]}}}