Real-time physiological identification using incremental learning and semi-supervised learning

Physiological monitoring;Wearable sensors;Electrocardiogram;Incremental learning;Semi-supervised learning;Computer science;Computer and Information Science, College of Engineering & Computer Science

Shivarudrappa, ShashankMedjahed, Brahim ;

University of Michigan

关键词: Physiological monitoring;    Wearable sensors;    Electrocardiogram;    Incremental learning;    Semi-supervised learning;    Computer science;    Computer and Information Science, College of Engineering & Computer Science;   

Others  :  https://deepblue.lib.umich.edu/bitstream/handle/2027.42/143516/49698122_Thesis_Shashank_Shivarudrappa.pdf?sequence=1&isAllowed=y

瑞士|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

The widespread usage of wearable sensors such as smart watches provide access to valuable objective physiological (suchasElectrocardiogram(ECG)) signals ubiquitously.Healthcare domain has been tremendously benefited by the collection of physiological signals which can be used for health monitoring of patients. The signals from the wearablesensors enabled the researchers and data experts to process them and identify thehuman physiological state by classifying the human activities. This led to the growth and development of smart ecosystem in the healthcare domain.In this thesis, ECG signalshave been investigated as the physiological measure to detect human activities. Variousmeasures are extracted from ECG, such as heart rate variability, average heart rate etc. and their relationships with different human activities are investigated. To builda comprehensive analytical machine learning model for ECG signals and to enable thecontinuous monitoring of humans, one would need access to real time streaming ofcontinuous data. So, the data would be unsupervised most of the time and it would bevery expensive (almost practically impossible) to label all the data streaming in real time.Also, it is highly probable that the data is collected from different sessions and varying situations. Therefore, the machine learning models need to be able to adapt to newsessions. This would be a major challenge in human state monitoring provided that the conventional predictive models work only on the stationary data. Also, these models would fail to work on the data from multiple sessions. To provide a practical solution toaddress above issues, two advanced methods in machine learning have been discussedin this research: Incremental learning and Semi supervised learning. Incremental learningis a paradigm in Machine learning where the stream of input data is continuously used toextend the existing knowledge learnt by the model. The incremental learning module hasbeen built in Apache Spark platform which provides a scalable cloud infrastructure to apply machine learning algorithms on streaming data. Semi supervised learning isanother solution implemented in this thesis where some out of all the data points are labelled. Different semi supervised algorithms have been studied and applied which learn the relationship between features and adapts the model to data from multiple sessions.Finally, the results are compared and the implementation ideas for the discussed solutionshave been proposed.