Edge-optimized machine learning models for real-time personalized health monitoring on wearables
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2024.
| Main Authors: | , , , , |
|---|---|
| 其他作者: | |
| 格式: | Thesis |
| 語言: | English |
| 出版: |
Brac University
2024
|
| 主題: | |
| 在線閱讀: | http://hdl.handle.net/10361/22912 |
| id |
10361-22912 |
|---|---|
| record_format |
dspace |
| spelling |
10361-229122024-05-26T21:02:29Z Edge-optimized machine learning models for real-time personalized health monitoring on wearables Rafee, Athar Noor Mohammad Dutta, Antu Haque, Afsan Rahman, Asif Barua, Aditta Noor, Jannatun Department of Computer Science and Engineering, Brac University Edge AI Embedded system Decision tree TinyML Micro-controller Resource-constraint Wearable technology Machine learning Signal processing This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2024. Cataloged from PDF version of thesis. Includes bibliographical references (pages 50-54). Personalized health monitoring, including Human Activity Recognition (HAR) and Fall Detection, is crucial for healthcare. Traditionally, most research in this field has relied on wearable sensors to collect data. The collected data is then typically sent to high-powered devices or servers for processing and analysis. However, there are some challenges with this approach. The reliance on high-powered devices can lead to delays in data processing and might not be suitable for real-time health monitoring. Additionally, the continuous transmission of data can raise privacy concerns and consume significant energy, which is not ideal for wearable devices that are often battery-powered, hence this study. Arduino UNO, based on the ATmega328P with 2 KiB SRAM, and ESP32 AI Thinker, with a dual-core Xtensa LX6 microprocessor, 320 KiB memory, and 3 MiB Flash Memory, are cost-effective and power-efficient, ideal for edge computing. In our research, we utilized the UCI HAPT and UMAFall Detection datasets for Human Activity Recognition and Fall Detection to optimize machine learning models for deployment on Arduino UNO and ESP32. On HAPT dataset, we achieved an impressive accuracy of up to 94% with a precision of 87% while on UMAFall Detection dataset, we achieved an accuracy of 81% with a precision of 77%. Notably, our trained Logistic Regression model for HAPT dataset clocked an average execution time of just 462 microseconds on ESP32 and 17634 micro seconds on Arduino UNO. Similarly, for UMAFall Detection dataset, our trained Decision Tree model clocked an average execution time of just 37 microseconds on ESP32 and 121 micro seconds on Arduino UNO. Furthermore, we significantly optimized resource usage for both HAPT and UMAFall datasets using our trained Decision Tree model, with memory usage minimized to 0.508 KB and 0.509 KB and flash size managed efficiently to a minimum of 6.606 KB and 26.518 KB on Arduino UNO, leaving plenty of resources for developers to add other programs on top of the ML model. It significantly outdid recent studies in terms of highly resource-constrained MCUs and compute resource usage efficiency. Athar Noor Mohammad Rafee Antu Dutta Afsan Haque Asif Rahman Aditta Barua B.Sc in Computer Science and Engineering 2024-05-26T03:10:25Z 2024-05-26T03:10:25Z ©2024 2024-01 Thesis ID: 20101396 ID: 20101282 ID: 20301145 ID: 20101287 ID: 20101023 http://hdl.handle.net/10361/22912 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 67 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Edge AI Embedded system Decision tree TinyML Micro-controller Resource-constraint Wearable technology Machine learning Signal processing |
| spellingShingle |
Edge AI Embedded system Decision tree TinyML Micro-controller Resource-constraint Wearable technology Machine learning Signal processing Rafee, Athar Noor Mohammad Dutta, Antu Haque, Afsan Rahman, Asif Barua, Aditta Edge-optimized machine learning models for real-time personalized health monitoring on wearables |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2024. |
| author2 |
Noor, Jannatun |
| author_facet |
Noor, Jannatun Rafee, Athar Noor Mohammad Dutta, Antu Haque, Afsan Rahman, Asif Barua, Aditta |
| format |
Thesis |
| author |
Rafee, Athar Noor Mohammad Dutta, Antu Haque, Afsan Rahman, Asif Barua, Aditta |
| author_sort |
Rafee, Athar Noor Mohammad |
| title |
Edge-optimized machine learning models for real-time personalized health monitoring on wearables |
| title_short |
Edge-optimized machine learning models for real-time personalized health monitoring on wearables |
| title_full |
Edge-optimized machine learning models for real-time personalized health monitoring on wearables |
| title_fullStr |
Edge-optimized machine learning models for real-time personalized health monitoring on wearables |
| title_full_unstemmed |
Edge-optimized machine learning models for real-time personalized health monitoring on wearables |
| title_sort |
edge-optimized machine learning models for real-time personalized health monitoring on wearables |
| publisher |
Brac University |
| publishDate |
2024 |
| url |
http://hdl.handle.net/10361/22912 |
| work_keys_str_mv |
AT rafeeatharnoormohammad edgeoptimizedmachinelearningmodelsforrealtimepersonalizedhealthmonitoringonwearables AT duttaantu edgeoptimizedmachinelearningmodelsforrealtimepersonalizedhealthmonitoringonwearables AT haqueafsan edgeoptimizedmachinelearningmodelsforrealtimepersonalizedhealthmonitoringonwearables AT rahmanasif edgeoptimizedmachinelearningmodelsforrealtimepersonalizedhealthmonitoringonwearables AT baruaaditta edgeoptimizedmachinelearningmodelsforrealtimepersonalizedhealthmonitoringonwearables |
| _version_ |
1814308171006607360 |