[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119213-en":3,"doc-seo-119213-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119213,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Classification of Gym Exercises Using Tiny Machine Learning - Thesis","This thesis explores Tiny Machine Learning (TinyML) to classify gym exercises using low-power edge devices, enabling efficient data processing close to where data is generated. The work develops a real-time prototype that detects exercise types and estimates executed repetitions. It covers the full pipeline: wearable-sensor data collection, preprocessing, model training, and deployment on a constrained microcontroller platform. Bluetooth Low Energy is used for near real-time data transmission to a smartphone application, delivering immediate feedback. Results confirm the feasibility and effectiveness of real-time exercise classification and indicate potential for future fitness and health monitoring.","CLASSIFICATION OF GYM EXERCISES USING TINY MACHINE LEARNING  \nthesis presented by:  \nAlbert Graner Babi`a  \nDirection: Ilker Demirkol  \nGrau d’Enginyeria en Sistemes TIC Course 2023/2024  \nAbstract  \nThis thesis explores the application of Tiny Machine Learning (TinyML) for classifying gym exercises using low-power edge devices. With the increasing demand for efficient data processing closer to the data source, TinyML offers a promising solution by deploying machine learning models on resource-constrained microcontrollers. This project focuses on the development of a prototype capable of detecting and classifying gym exercises in real-time, detecting the executed repetitions. The methodology includes data collection through wearable sensors, preprocessing of the collected data, model training, and deployment on an edge device. The prototype integrates Bluetooth Low Energy (BLE) for real-time data transmission to a smartphone application, providing users with immediate feedback on their workout performance. The results demonstrate the feasibility and effectiveness of using TinyML for real-time exercise classification, highlighting the potential for future applications in fitness and health monitoring.  \nResum  \nAquesta tesi explora l’aplicaci´o de Tiny Machine Learning (TinyML) per a laclassificaci´o d’exercicis del gimn`as utilitzant dispositius de baixa pot`encia a lavora de la xarxa (dispositius Edge) . Amb la creixent demanda de processamenteficient de dades m´es a prop de la font de dades, el TinyML ofereix una soluci´oprometedora desplegant models d’aprenentatge autom`atic en microcontroladors de recursos limitats. Aquest projecte es centra en el desenvolupament d’un prototip capa¸c de detectar i classificar exercicis del gimn`as en temps real, detectant-ne les repeticions executades. La metodologia inclou la recopilaci´o de dades mitjan¸cant sensors portables, el preprocessament de les dades recollides, l’entrenament del model i el desplegament en un dispositiu Edge. El prototip integra Bluetooth Low Energy (BLE) per a la transmissi´o de dades en temps real a una aplicaci´ode tel`efon intel·ligent, proporcionant als usuaris un feedback immediat sobre elseu rendiment durant l’exercici. Els resultats demostren la viabilitat i efic`aciad’utilitzar el TinyML per a la classificaci´o d’exercicis en temps real, destacantel seu potencial per a futures aplicacions en la monitoritzaci´o de la salut i el condicionament f´ısic.  \nContents  \n1 Introduction 5  \n1.1 State of the Art ............................. 6  \n1.2 Problem Statement ........................... 9  \n1.3 Scope .................................. 9  \n2 Antecedents 10  \n2.1 Previous Work ............................. 10  \n2.2 Machine Learning Theoretical Background .............. 11  \n3 System Design 14  \n3.1 Requirements Analysis ......................... 14  \n3.2 System Architecture .......................... 16  \n3.3 Hardware Design ............................ 17  \n3.3.1 Microcontroller Board ..................... 17  \n3.3.2 Sensors .............................. 19  \n3.3.3 Powering System ........................ 20  \n3.4 Use Case Design ............................ 22  \n3.4.1 Overview of Gym Exercises .................. 22  \n3.4.2 Detection of Exercise Repetitions ............... 22  \n3.5 Software Design ............................. 24  \n3.5.1 Machine Learning Model Development and Training Software 25  \n3.5.2 Inference and Deployment Software .............. 30  \n3.5.3 Smartphone Application Development ............ 40  \n4 Data Collection and Preprocessing 42  \n4.1 Data Collection ............................. 43  \n4.2 Data Thresholding ........................... 44  \n4.3 Data Preprocessing ........................... 48  \n5 Model Development and Training 55  \n5.1 Model Architecture ........................... 55  \n5.2 Model Performance Analysis and Deployment ............ 56  \n6 Protective Case Design 60  \n7 Overall Performance Analysis 63  \n8 Conclusions 65  \n","cbCaimhgJO5p4rxt","https://ap.wps.com/l/cbCaimhgJO5p4rxt","pdf",6174268,1,72,"English","en",105,"# Introduction\n## State of the Art\n## Problem Statement\n## Scope\n# System Design\n## Requirements Analysis\n## System Architecture\n## Hardware Design\n## Use Case Design\n## Software Design\n# Data Collection and Preprocessing\n## Data Collection\n## Data Thresholding\n## Data Preprocessing\n# Model Development and Training\n## Model Architecture\n## Model Performance Analysis and Deployment\n# Overall Performance Analysis\n# Conclusions","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"The thesis addresses how to classify gym exercises efficiently using TinyML on low-power edge devices, processing data near the source for timely inference.\"},{\"question\":\"How does the system detect exercise repetitions?\",\"answer\":\"It collects data with wearable sensors, preprocesses the signals, trains a machine learning model, and deploys it on a microcontroller to perform real-time inference for repetition detection.\"},{\"question\":\"How is data transmitted and feedback delivered to users?\",\"answer\":\"The prototype uses Bluetooth Low Energy (BLE) to send real-time data to a smartphone application, which provides immediate feedback during workouts.\"}]","Classification of Gym Exercises Using Tiny Machine Learning - Thesis | PDF",1785723129,181,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"classification-of-gym-exercises-using-tiny-machine-learning-thesis","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/classification-of-gym-exercises-using-tiny-machine-learning-thesis/119213/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis address?","Question",{"text":76,"@type":77},"The thesis addresses how to classify gym exercises efficiently using TinyML on low-power edge devices, processing data near the source for timely inference.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the system detect exercise repetitions?",{"text":81,"@type":77},"It collects data with wearable sensors, preprocesses the signals, trains a machine learning model, and deploys it on a microcontroller to perform real-time inference for repetition detection.",{"name":83,"@type":74,"acceptedAnswer":84},"How is data transmitted and feedback delivered to users?",{"text":85,"@type":77},"The prototype uses Bluetooth Low Energy (BLE) to send real-time data to a smartphone application, which provides immediate feedback during workouts.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]