{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:59:38Z","timestamp":1782845978699,"version":"3.54.5"},"reference-count":29,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Active commuting, such as skateboarding and kickboarding, is gaining popularity as an alternative to traditional modes of transportation such as walking and cycling. However, current activity trackers and smartphones, which rely on accelerometer data, are primarily designed to recognize symmetrical locomotive activities (eg, walking and running) and may struggle to accurately identify the unique push-push-glide motion patterns of skateboarding and kickboarding.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The primary objective of this study was to evaluate the feasibility of classifying skateboard and kickboard commuting behaviors using data from wearable sensors and smartphones. A secondary objective was to identify the most important sensor-derived features for accurate activity recognition.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Ten participants (4 women and 6 men; aged 12\u201055 y) performed 9 activities, including skateboarding, kickboarding, walking, running, bicycling, ascending stairs, descending stairs, sitting, and standing. Data were collected using wearable sensors (accelerometer, gyroscope, and barometer) placed on the wrist and the hip, as well as in the pocket to replicate the sensing characteristics of commercial activity trackers and smartphones. The signal processing approach included the extraction of 211 features from 10- and 20-second sliding windows. Random forest classifiers were trained to perform multiclass and binary classifications, including distinguishing skateboarding and kickboarding from other activities.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Wrist-worn sensor configurations achieved the highest balanced accuracies for multiclass classification (range 84%\u201088%). Skateboarding and kickboarding were identified with high sensitivity, ranging from 93% to 99% and 97% to 99%, respectively. Hip and pocket sensor configurations showed lower performance, particularly in distinguishing skateboarding (range 49%\u201058% sensitivity) from kickboarding (78% sensitivity). Binary classification models grouping skateboarding and kickboarding into a push-push-glide superclass achieved high accuracies (range 91%\u201095%). Key features for classification included low- and high-frequency accelerometer signals, as well as roll-pitch-yaw angles.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study demonstrates the feasibility of recognizing skateboard and kickboard commuting behaviors using wearable sensors, particularly wrist-worn devices. While hip and pocket sensors showed limitations in differentiating these activities, the broader push-push-glide classification achieved acceptable accuracy, suggesting its potential for integration into activity tracker software. Future research should explore sensor fusion approaches to further enhance recognition performance and address the question of energy expenditure estimation.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/71969","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T05:02:02Z","timestamp":1747717322000},"page":"e71969-e71969","source":"Crossref","is-referenced-by-count":0,"title":["Recognizing Skateboard and Kickboard Commuting Behaviors Using Activity Trackers: Feasibility Study Using Machine Learning Approaches"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9100-1855","authenticated-orcid":false,"given":"Nathanael","family":"Aubert-Kato","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6630-2364","authenticated-orcid":false,"given":"Hitomi","family":"Hatori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0332-1641","authenticated-orcid":false,"given":"Arisa","family":"Orihara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4326-3604","authenticated-orcid":false,"given":"Takashi","family":"Nakagata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3631-0460","authenticated-orcid":false,"given":"Yuji","family":"Ohta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-5337","authenticated-orcid":false,"given":"Julien","family":"Tripette","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,8,29]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0149990","article-title":"Health impacts of active transportation in Europe","volume":"11","author":"Rojas-Rueda","journal-title":"PLoS One"},{"issue":"12","key":"R2","doi-asserted-by":"publisher","first-page":"e179","DOI":"10.2337\/dc22-1267","article-title":"Commuter cycling and risk of type 2 diabetes: a cohort study in Japan","volume":"45","author":"Kuwahara","journal-title":"Diabetes Care"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/s40279-018-1023-0","article-title":"Active commuting and multiple health outcomes: a systematic review and meta-analysis","volume":"49","author":"Dinu","journal-title":"Sports Med"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ypmed.2015.04.010","article-title":"Health impact assessment of active transportation: a systematic review","volume":"76","author":"Mueller","journal-title":"Prev Med"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s11116-017-9796-9","article-title":"Skateboarding for transportation: exploring the factors behind an unconventional mode choice among university skateboard commuters","volume":"46","author":"Fang","journal-title":"Transportation (Amst)"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jth.2024.101888","article-title":"\u201cFun, faster than walking, and more convenient than a bike\u201d: skateboarding in a college town","volume":"38","author":"Rainey","journal-title":"J Transp Health"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jth.2020.100947","article-title":"Strengths and vulnerabilities of teenagers who skateboard for transport in New Zealand","volume":"20","author":"Ward","journal-title":"J Transp Health"},{"issue":"11","key":"R8","doi-asserted-by":"publisher","first-page":"2381","DOI":"10.1007\/s00421-014-2959-x","article-title":"Self-selected speeds and metabolic cost of longboard skateboarding","volume":"114","author":"Board","journal-title":"Eur J Appl Physiol"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.jshs.2023.10.010","article-title":"2024 Adult Compendium of Physical Activities: a third update of the energy costs of human activities","volume":"13","author":"Herrmann","journal-title":"J Sport Health Sci"},{"issue":"4","key":"R10","doi-asserted-by":"publisher","first-page":"495","DOI":"10.2114\/jpa2.26.495","article-title":"Metabolic equivalents during scooter exercise","volume":"26","author":"Kijima","journal-title":"J Physiol Anthropol"},{"issue":"11 Suppl","key":"R11","doi-asserted-by":"publisher","first-page":"S490","DOI":"10.1249\/01.mss.0000185571.49104.82","article-title":"The technology of accelerometry-based activity monitors: current and future","volume":"37","author":"Chen","journal-title":"Med Sci Sports Exerc"},{"issue":"11 Suppl","key":"R12","doi-asserted-by":"publisher","first-page":"S501","DOI":"10.1249\/01.mss.0000185660.38335.de","article-title":"Principles of design and analyses for the calibration of accelerometry-based activity monitors","volume":"37","author":"Welk","journal-title":"Med Sci Sports Exerc"},{"issue":"4","key":"R13","doi-asserted-by":"publisher","first-page":"1300","DOI":"10.1152\/japplphysiol.00465.2009","article-title":"An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer","volume":"107","author":"Staudenmayer","journal-title":"J Appl Physiol (1985)"},{"issue":"11","key":"R14","doi-asserted-by":"publisher","first-page":"1681","DOI":"10.1017\/S0007114510005441","article-title":"Real-time estimation of daily physical activity intensity by a triaxial accelerometer and a gravity-removal classification algorithm","volume":"105","author":"Ohkawara","journal-title":"Br J Nutr"},{"issue":"1 Suppl 1","key":"R15","doi-asserted-by":"publisher","first-page":"S32","DOI":"10.1249\/MSS.0b013e3182399cf7","article-title":"Calibration and validation of wearable monitors","volume":"44","author":"Bassett","journal-title":"Med Sci Sports Exerc"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-26174-1","article-title":"Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants","volume":"8","author":"Willetts","journal-title":"Sci Rep"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-09521-1","article-title":"Human activity recognition of children with wearable devices using LightGBM machine learning","volume":"12","author":"Csizmadia","journal-title":"Sci Rep"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-59602-6","article-title":"Development and validation of a smartwatch algorithm for differentiating physical activity intensity in health monitoring","volume":"14","author":"Chen","journal-title":"Sci Rep"},{"issue":"5","key":"R19","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1249\/MSS.0b013e3181c37458","article-title":"Refined two-regression model for the ActiGraph accelerometer","volume":"42","author":"Crouter","journal-title":"Med Sci Sports Exerc"},{"issue":"3","key":"R20","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/j.gaitpost.2010.01.005","article-title":"Classifying household and locomotive activities using a triaxial accelerometer","volume":"31","author":"Oshima","journal-title":"Gait Posture"},{"key":"R21","unstructured":"Shih PC Han K Poole ES Rosson MB Carroll JM . Use and adoption challenges of wearable activity trackers. Presented at: IConference 2015; Mar 24-27, 2015; Newport Beach, CA, USA."},{"issue":"4","key":"R22","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1249\/MSS.0b013e31823bf95c","article-title":"Physical activity classification using the GENEA wrist-worn accelerometer","volume":"44","author":"Zhang","journal-title":"Med Sci Sports Exerc"},{"issue":"5","key":"R23","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1249\/MSS.0000000000000840","article-title":"Hip and wrist accelerometer algorithms for free-living behavior classification","volume":"48","author":"Ellis","journal-title":"Med Sci Sports Exerc"},{"key":"R24","unstructured":"Aubert-Kato N Hatori H Orihara A Nakagata T Ohta Y Tripette J . Data and code \u201cRecognizing skateboard and kickboard commuting behaviors using activity trackers: a feasibility study using machine learning approaches\u201d. Zenodo. URL: https:\/\/zenodo.org\/records\/14769798 [Accessed 06-08-2025]"},{"key":"R25","unstructured":"Bishop CM . Pattern Recognition and Machine Learning. Springer; 2006. ISBN: 9780387310732"},{"issue":"85","key":"R26","first-page":"2825","volume":"12","author":"Pedregosa","journal-title":"J Mach Learn Res"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","journal-title":"Mach Learn"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Sukor ASA Zakaria A Rahim NA . Activity recognition using accelerometer sensor and machine learning classifiers. Presented at: CSPA 2018; Mar 9-10, 2018; Batu Feringghi, Malaysia. [doi: 10.1109\/CSPA.2018.8368718]","DOI":"10.1109\/CSPA.2018.8368718"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.1016\/j.gaitpost.2021.06.017","article-title":"Machine-learning models for activity class prediction: a comparative study of feature selection and classification algorithms","volume":"89","author":"Chong","journal-title":"Gait Posture"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/formative.jmir.org\/2025\/1\/e71969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:01:56Z","timestamp":1782842516000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2025\/1\/e71969"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,29]]},"references-count":29,"URL":"https:\/\/doi.org\/10.2196\/71969","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,29]]},"article-number":"v9i3e71969"}}