[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117907-en":3,"doc-seo-117907-105":29,"detail-sidebar-cat-0-en-105":89},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":20,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},117907,962084925636,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Longboarding techniques classification using Machine Learning","Longboarding techniques classification using machine learning models longboard rider motion into predictive technique labels through a complete workflow from raw sensor data to model outputs. The approach normalizes spatial orientation using 3D rotation matrices and re-aligns inclination and acceleration signals into a fixed coordinate system, then segments the time series into optimized windows (3s) for feature computation. Key features derive from displacement and acceleration statistics across axes, and model training evaluates accuracy via F1 scores, train/test performance, and runtime. Future work targets neural-network improvements and broader trials with more riders and configurations, plus mobile deployment for Android and iOS using sensor data.","Longboarding techniques classification using Machine Learning  \nTuan (Kevin) Le 1,2, 3 , Evans Sajtar 1 , McKenzie Lamb P.hD 2  \n1 Department of Computer Science, DePauw University, Greencastle, IN, 2 Department of Mathematical Science, DePauw University, Greencastle, IN, 3 Department of Physics, DePauw University, Greencastle, IN  \nBackground Data Normalization  \n\n|  | \u003Cbr>Feature extractions |  |\n| --- | --- | --- |\n|  |  |  |\n\nFigure 2: Predictor’s workflow, i.e. all the steps happening from raw data to predictions within the model.  \nFigure: Rotation matrix applied on a small sample of the position displacement data. Above is the raw data, and below is the rotated data  \n- An application aiming to classify a rider’s longboard ride’s techniques  \n- Experimentations with different methods for reducing loss and improving accuracy in predicting Longboard activities.  \n- Vector normalization using 3-dimensional rotation matrices that rotate the 3 dimensions around a vector.  \n- These inclination data are reversed and used for rotating all acceleration data back to a fixed coordinate system where Azimuth, Pitch, and Roll are collectively 0's.  \nData segmentation  \n- data will be split into windows of similar time intervals. From each time window, we consider the last and first points to be vector data.  \n- After experiments with all possible time intervals, we found that 3s is the most optimal and high-performing time interval.  \n- This is largely based on the data so for different configurations of data, different periods of time may work better. As for all the configurations we have tested, 3s durations work best.  \n- Sum of frequencies of position displacement vector in x and z dimensions  \n- Maximum and Minimum values of position displacement in x and z dimensions  \n- difference between the maximum and minimum accelerations in the y dimension  \n- Root mean squared of position displacement in x and z and acceleration in y (while ignoring NaN) .  \nFigure 6: Feature importance when using Random Forest Classifier to classify Longboard Activity. From left to right, Acceleration di  \nfference, Amplitude in x, Displacement frequency in x, Amplitude in z, Displacement frequency in z, Root-mean squared of acceleration in y, displacement in x and z  \nData collection  \n- Android mobile application called \"Physics Toolbox Sensor Suite\"  \n- which records data in non-harmonic time intervals, frequently 0.01s-0.03s.  \n- Linear acceleration changes whenever the mobile device speeds up, slows down, or changes direction.  \n- When the device is at rest with respect to the surface of the earth, it reads acceleration values of 0, 0, 0.  \nResults and future directions  \nTable: F1 score, train score (the fraction of correctly classified samples when learning the training set), test score (the fraction of correctly classified samples when learning the testing set) and training time of different classifier  \nNext steps:  \n- Higher accuracy with neural network models and modified versions of classifiers.  \n- Model deployment for an Android and IOS application.  \n- Do more test runs with different riders and configurations.  \nAcknowledgement  \nFigure: position displacement in 3 dimensions with respect to time (pumping.csv)  \nAppreciation for Dr. McKenzie Lamb for advising, Evans Sajtar for assisting on building the application, and all the individuals who helped refine and shape the direction and methods of the research.","cbCaij1RswUj3F1Z","https://ap.wps.com/l/cbCaij1RswUj3F1Z","pdf",704570,1,"English","en",105,"# Predictor’s workflow\n## Data normalization and coordinate alignment\n## Data segmentation\n## Feature extraction\n# Model evaluation and results\n## F1 score and train/test scores\n## Runtime comparison\n# Results and future directions","[{\"question\":\"What problem does the document address?\",\"answer\":\"It builds an application and modeling pipeline to classify a rider’s longboard ride techniques and predict longboard activities from sensor data.\"},{\"question\":\"How is the input data prepared before classification?\",\"answer\":\"The method normalizes orientation using 3D rotation matrices, reverses inclination transformations to return acceleration into a fixed coordinate system, and segments the time series into windows optimized through experiments.\"},{\"question\":\"Which data source and evaluation metrics are used?\",\"answer\":\"Data are collected with an Android app (Physics Toolbox Sensor Suite), and results are evaluated using F1 score along with train and test scores and training time for different classifiers.\"}]","Longboarding techniques classification using Machine Learning | PDF",1785680329,3,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":27},"longboarding-techniques-classification-using-machine-learning","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":28},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/longboarding-techniques-classification-using-machine-learning/117907/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does the document address?","Question",{"text":73,"@type":74},"It builds an application and modeling pipeline to classify a rider’s longboard ride techniques and predict longboard activities from sensor data.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How is the input data prepared before classification?",{"text":78,"@type":74},"The method normalizes orientation using 3D rotation matrices, reverses inclination transformations to return acceleration into a fixed coordinate system, and segments the time series into windows optimized through experiments.",{"name":80,"@type":71,"acceptedAnswer":81},"Which data source and evaluation metrics are used?",{"text":82,"@type":74},"Data are collected with an Android app (Physics Toolbox Sensor Suite), and results are evaluated using F1 score along with train and test scores and training time for different classifiers.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]