Machine Learning on Edge in Sensor Systems (SenSys-ML 2024)

TY - GEN

T1 - Machine Learning on Edge in Sensor Systems (SenSys-ML 2024)

AU - Yadav, Poonam

AU - Ngai, Edith C.H.

AU - Gupta, Manik

AU - Shresthamali, Shaswot

AU - Ranjan, Alok

N1 - Publisher Copyright: © 2024 IEEE.

PY - 2024/6/24

Y1 - 2024/6/24

N2 - The explosion of sensors in smartphones and the Internet of Things (IoT) is generating a massive amount of data. This has the potential to revolutionise fields like healthcare, environmental management, and city planning. However, to unlock this potential, we need machine learning (ML) to transform raw sensor data into actionable insights. Machine learning offers a powerful way to turn sensor data into something we can understand and use. However, several challenges stand in the way of bringing these ideas to life: (1) Limited Resources: Devices often have limited computing power, memory, and battery life. (2) Complex Systems: Building ML models for sensor systems can be intricate. (3) Real-World Testing: Designing effective studies and collecting reliable data (ground truth) can be difficult. Sensys-ML 2024 workshop tackles these challenges by providing early feedback on research involving machine learning for sensor systems (TinyML). This workshop focuses on approaches that combine sensor data with ML, especially those that run on devices themselves or leverage edge/fog computing.

AB - The explosion of sensors in smartphones and the Internet of Things (IoT) is generating a massive amount of data. This has the potential to revolutionise fields like healthcare, environmental management, and city planning. However, to unlock this potential, we need machine learning (ML) to transform raw sensor data into actionable insights. Machine learning offers a powerful way to turn sensor data into something we can understand and use. However, several challenges stand in the way of bringing these ideas to life: (1) Limited Resources: Devices often have limited computing power, memory, and battery life. (2) Complex Systems: Building ML models for sensor systems can be intricate. (3) Real-World Testing: Designing effective studies and collecting reliable data (ground truth) can be difficult. Sensys-ML 2024 workshop tackles these challenges by providing early feedback on research involving machine learning for sensor systems (TinyML). This workshop focuses on approaches that combine sensor data with ML, especially those that run on devices themselves or leverage edge/fog computing.

KW - Machine Learning

KW - Sensor Systems

KW - TinyML

KW - UltraML

UR - http://www.scopus.com/inward/record.url?scp=85197795751&partnerID=8YFLogxK

U2 - 10.1109/SenSys-ML62579.2024.00005

DO - 10.1109/SenSys-ML62579.2024.00005

M3 - Conference contribution

AN - SCOPUS:85197795751

T3 - Proceedings - 2024 IEEE 3rd Workshop on Machine Learning on Edge in Sensor Systems, SenSys-ML 2024

SP - 1

EP - 2

BT - Proceedings - 2024 IEEE 3rd Workshop on Machine Learning on Edge in Sensor Systems, SenSys-ML 2024

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE Workshop on Machine Learning on Edge in Sensor Systems, SenSys-ML 2024

Y2 - 13 May 2024 through 16 May 2024

ER -