{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:45:23Z","timestamp":1778604323603,"version":"3.51.4"},"reference-count":34,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Background\/Objective: Understanding the training effect in high-level running is important for performance optimization and injury prevention. This includes awareness of how different running surface types (e.g., hard versus soft) may modify biomechanics. Recent studies have demonstrated that deep learning algorithms, such as convolutional neural networks (CNNs), can accurately classify human activity collected via body-worn sensors. To date, no study has assessed optimal signal type, sensor location, and model architecture to classify running surfaces. This study aimed to determine which combination of signal type, sensor location, and CNN architecture would yield the highest accuracy in classifying grass and asphalt surfaces using inertial measurement unit (IMU) sensors. Methods: Running data were collected from forty participants (27.4 years + 7.8 SD, 10.5 \u00b1 7.3 SD years of running) with a full-body IMU system (head, sternum, pelvis, upper legs, lower legs, feet, and arms) on grass and asphalt outdoor surfaces. Performance (accuracy) for signal type (acceleration and angular velocity), sensor configuration (full body, lower body, pelvis, and feet), and CNN model architecture was tested for this specific task. Moreover, the effect of preprocessing steps (separating into running cycles and amplitude normalization) and two different data splitting protocols (leave-n-subject-out and subject-dependent split) was evaluated. Results: In general, acceleration signals improved classification results compared to angular velocity (3.8%). Moreover, the foot sensor configuration had the best performance-to-number of sensor ratio (95.5% accuracy). Finally, separating trials into gait cycles and not normalizing the raw signals improved accuracy by approximately 28%. Conclusion: This analysis sheds light on the important parameters to consider when developing machine learning classifiers in the human activity recognition field. A surface classification tool could provide useful quantitative feedback to athletes and coaches in terms of running technique effort on varied terrain surfaces, improve training personalization, prevent injuries, and improve performance.<\/jats:p>","DOI":"10.3390\/s25196203","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T08:05:36Z","timestamp":1759824336000},"page":"6203","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sensor Input Type and Location Influence Outdoor Running Terrain Classification via Deep Learning Approaches"],"prefix":"10.3390","volume":"25","author":[{"given":"Gabrielle","family":"Thibault","sequence":"first","affiliation":[{"name":"Department of Kinesiology and Physical Education, McGill University, Montreal, QC H2W 1S4, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]},{"given":"David J.","family":"Pearsall","sequence":"additional","affiliation":[{"name":"Department of Kinesiology and Physical Education, McGill University, Montreal, QC H2W 1S4, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Benca, E., Listabarth, S., Flock, F.K.J., Pablik, E., Fischer, C., Walzer, S.M., Dorotka, R., Windhager, R., and Ziai, P. (2020). Analysis of Running-Related Injuries: The Vienna Study. J. Clin. Med., 9.","DOI":"10.3390\/jcm9020438"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e151","DOI":"10.1016\/j.asmr.2021.09.032","article-title":"Injury Prevention, Safe Training Techniques, Rehabilitation, and Return to Sport in Trail Runners","volume":"4","author":"Vincent","year":"2022","journal-title":"Arthrosc. Sports Med. Rehabil."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1519\/JSC.0000000000003410","article-title":"Surface Stiffness and Footwear Affect the Loading Stimulus for Lower Extremity Muscles When Running","volume":"36","author":"Willwacher","year":"2022","journal-title":"J. Strength Cond. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1098\/rspb.1998.0388","article-title":"Running in the real world: Adjusting leg stiffness for different surfaces","volume":"265","author":"Ferris","year":"1998","journal-title":"Proc. R. Soc. B Biol. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3362","DOI":"10.1016\/j.jbiomech.2016.08.032","article-title":"Continuous three dimensional analysis of running mechanics during a marathon by means of inertial magnetic measurement units to objectify changes in running mechanics","volume":"49","author":"Reenalda","year":"2016","journal-title":"J. Biomech."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.gaitpost.2012.10.022","article-title":"Mechanics of overground accelerated running vs. running on an accelerated treadmill","volume":"38","author":"Segers","year":"2013","journal-title":"Gait Posture"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1016\/j.gaitpost.2013.04.026","article-title":"Effect of overground vs treadmill running on plantar pressure: Influence of fatigue","volume":"38","author":"Llana","year":"2013","journal-title":"Gait Posture"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Agostini, V., Gastaldi, L., Rosso, V., Knaflitz, M., and Tadano, S. (2017). A Wearable Magneto-Inertial System for Gait Analysis (H-Gait): Validation on Normal Weight and Overweight\/Obese Young Healthy Adults. Sensors, 17.","DOI":"10.3390\/s17102406"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wouda, F.J., Giuberti, M., Bellusci, G., Maartens, E., Reenalda, J., Van Beijnum, B.-J.F., and Veltink, P.H. (2018, January 26\u201329). On the Validity of Different Motion Capture Technologies for the Analysis of Running. Proceedings of the 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob), Enschede, The Netherlands.","DOI":"10.1109\/BIOROB.2018.8487210"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Abu-Faraj, Z.O., Harris, G.F., Smith, P.A., and Hassani, S. (2015). Human gait and Clinical Movement Analysis. Wiley Encyclopedia of Electrical and Electronics Engineering, American Cancer Society.","DOI":"10.1002\/047134608X.W6606.pub2"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1615\/CritRevBiomedEng.2020035013","article-title":"Human Locomotion Classification for Different Terrains Using Machine Learning Techniques","volume":"48","author":"Negi","year":"2020","journal-title":"Crit. Rev. Biomed. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1097\/00005768-200011000-00016","article-title":"Surface effects on ground reaction forces and lower extremity kinematics in running","volume":"32","author":"Dixon","year":"2000","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1080\/14763141.2016.1212918","article-title":"The effect of three surface conditions, speed and running experience on vertical acceleration of the tibia during running","volume":"16","author":"Boey","year":"2017","journal-title":"Sports Biomech."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.gaitpost.2016.05.017","article-title":"Surface effects on dynamic stability and loading during outdoor running using wireless trunk accelerometry","volume":"48","author":"Aeles","year":"2016","journal-title":"Gait Posture"},{"key":"ref_15","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_16","doi-asserted-by":"crossref","unstructured":"Lam, G., Rish, I., and Dixon, P.C. (2023). Estimating individual minimum calibration for deep-learning with predictive performance recovery: An example case of gait surface classification from wearable sensor gait data. J. Biomech., 154.","DOI":"10.1016\/j.jbiomech.2023.111606"},{"key":"ref_17","unstructured":"(2025, July 16). Getting Your VO2 Max. Estimate. Available online: https:\/\/www8.garmin.com\/manuals-apac\/webhelp\/venusq\/EN-SG\/GUID-AD20C854-A0C5-401C-B4DD-55EDE4E1F54F-2318.html."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.gaitpost.2019.09.005","article-title":"Machine learning algorithms can classify outdoor terrain types during running using accelerometry data","volume":"74","author":"Dixon","year":"2019","journal-title":"Gait Posture"},{"key":"ref_19","first-page":"84","article-title":"Survey on Human Activity Recognition based on Acceleration Data","volume":"10","author":"Slim","year":"2019","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_20","unstructured":"Negi, S., Negi, P.C.B.S., Sharma, S., and Sharma, N. (2020). Electromyographic and Acceleration Signals-Based Gait Phase Analysis for Multiple Terrain Classification Using Deep Learning, Social Science Research Network. Available online: https:\/\/papers.ssrn.com\/abstract=3657175."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Moya Rueda, F., Grzeszick, R., Fink, G.A., Feldhorst, S., and Ten Hompel, M. (2018). Convolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors. Informatics, 5.","DOI":"10.3390\/informatics5020026"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Dehzangi, O., Taherisadr, M., and ChangalVala, R. (2017). IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion. Sensors, 17.","DOI":"10.3390\/s17122735"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1016\/j.jelekin.2011.02.005","article-title":"Classification of muscle activity based on effort level during constant pace running","volume":"21","author":"Stirling","year":"2011","journal-title":"J. Electromyogr. Kinesiol. Off. J. Int. Soc. Electrophysiol. Kinesiol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Gao, S., Wang, Y., Fang, C., and Xu, L. (2020). A Smart Terrain Identification Technique Based on Electromyography, Ground Reaction Force, and Machine Learning for Lower Limb Rehabilitation. Appl. Sci., 10.","DOI":"10.3390\/app10082638"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zheng, X., Wang, M., and Ordieres-Mer\u00e9, J. (2018). Comparison of Data Preprocessing Approaches for Applying Deep Learning to Human Activity Recognition in the Context of Industry 4.0. Sensors, 18.","DOI":"10.3390\/s18072146"},{"key":"ref_26","first-page":"1","article-title":"A Survey on Deep Learning for Human Activity Recognition","volume":"54","author":"Gu","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1016\/j.promfg.2018.07.152","article-title":"Worker Activity Recognition in Smart Manufacturing Using IMU and sEMG Signals with Convolutional Neural Networks","volume":"26","author":"Tao","year":"2018","journal-title":"Procedia Manuf."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Pinz\u00f3n-Arenas, J.O., Jim\u00e9nez-Moreno, R., and Herrera-Benavides, J.E. (2019, January 24\u201326). Convolutional Neural Network for Hand Gesture Recognition using 8 different EMG Signals. Proceedings of the 2019 XXII Symposium on Image, Signal Processing and Artificial Vision (STSIVA), Bucaramanga, Colombia.","DOI":"10.1109\/STSIVA.2019.8730272"},{"key":"ref_29","unstructured":"Xsens (2019, June 01). MVN User Manual. Available online: https:\/\/www.xsens.com\/hubfs\/Downloads\/usermanual\/MVN_User_Manual.pdf."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cmpb.2016.11.007","article-title":"biomechZoo: An open-source toolbox for the processing, analysis, and visualization of biomechanical movement data","volume":"140","author":"Dixon","year":"2017","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_31","unstructured":"McGrath, D., Greene, B.R., O\u2019Donovan, K.J., and Caulfield, B. (2025, July 16). Gyroscope-Based Assessment of Temporal Gait Parameters During Treadmill Walking and Running|Sports Engineering. Available online: https:\/\/link.springer.com\/article\/10.1007\/s12283-012-0093-8."},{"key":"ref_32","unstructured":"Chollet, F. (2018). Deep Learning with Python, Manning."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","article-title":"Deep learning for sensor-based activity recognition: A survey","volume":"119","author":"Wang","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Shah, V., Flood, M.W., Grimm, B., and Dixon, P.C. (2022). Generalizability of deep learning models for predicting outdoor irregular walking surfaces. J. Biomech., 139.","DOI":"10.1016\/j.jbiomech.2022.111159"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/19\/6203\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:49:50Z","timestamp":1760035790000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/19\/6203"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,7]]},"references-count":34,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["s25196203"],"URL":"https:\/\/doi.org\/10.3390\/s25196203","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,7]]}}}