TY - GEN
T1 - Fatigue Estimation Using Wearable Devices and Virtual Instrumentation
AU - Modran, Horia Alexandru
AU - Ursuțiu, Doru
AU - Samoilă, Cornel
AU - Chamunorwa, Tinashe
AU - Aljihmani, Lilia
AU - Qaraqe, Khalid
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Modern wearable devices (smartwatches, wristbands, or rings) can incorporate several physiological sensors. Therefore, those devices can be used to monitor an individual’s health condition. Machine learning algorithms can be used to predict fatigue or other health problems. The aim of this study is to prevent and detect fatigue. Therefore, an Artificial Intelligence model for real-time prediction of fatigue using wearable devices will be developed. It will collect data using the sensors of the device (Heart Rate, Blood Oxygen level saturation, Blood pressure, and accelerometer) and it will be able to detect the incipient signs of fatigue. Several volunteers with IRB agreements wore the device for one week in their daily activities to collect the training data for the Machine Learning model. The machine learning model will be trained locally, and then deployed in the Cloud. The physiological data will be recorded by a wearable device and then send to be processed in the Cloud in real-time. When fatigue is detected, an alert will be triggered and sent to the device. This Artificial Intelligence application can be used especially by drivers to be warned in case of fatigue and by pilots, soldiers, or other workers. Therefore, it will be useful for keeping physical and mental health, as well as for avoiding unwanted accidents.
AB - Modern wearable devices (smartwatches, wristbands, or rings) can incorporate several physiological sensors. Therefore, those devices can be used to monitor an individual’s health condition. Machine learning algorithms can be used to predict fatigue or other health problems. The aim of this study is to prevent and detect fatigue. Therefore, an Artificial Intelligence model for real-time prediction of fatigue using wearable devices will be developed. It will collect data using the sensors of the device (Heart Rate, Blood Oxygen level saturation, Blood pressure, and accelerometer) and it will be able to detect the incipient signs of fatigue. Several volunteers with IRB agreements wore the device for one week in their daily activities to collect the training data for the Machine Learning model. The machine learning model will be trained locally, and then deployed in the Cloud. The physiological data will be recorded by a wearable device and then send to be processed in the Cloud in real-time. When fatigue is detected, an alert will be triggered and sent to the device. This Artificial Intelligence application can be used especially by drivers to be warned in case of fatigue and by pilots, soldiers, or other workers. Therefore, it will be useful for keeping physical and mental health, as well as for avoiding unwanted accidents.
KW - Artificial Intelligence
KW - Deep Learning
KW - Fatigue prediction
KW - Heart Rate
KW - Smartwatch
KW - Tremor
UR - http://www.scopus.com/inward/record.url?scp=85181804605&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-42467-0_97
DO - 10.1007/978-3-031-42467-0_97
M3 - Conference contribution
AN - SCOPUS:85181804605
SN - 9783031424663
T3 - Lecture Notes in Networks and Systems
SP - 1055
EP - 1064
BT - Open Science in Engineering - Proceedings of the 20th International Conference on Remote Engineering and Virtual Instrumentation
A2 - Auer, Michael E.
A2 - Langmann, Reinhard
A2 - Tsiatsos, Thrasyvoulos
PB - Springer Science and Business Media Deutschland GmbH
T2 - 20th International Conference on Remote Engineering and Virtual Instrumentation: Open Science in Engineering, REV 2023 co-organized with the International Edunet World Conference, IEWC 2023
Y2 - 1 March 2023 through 3 March 2023
ER -