Applications and progress of machine learning in wearable intelligent sensing systems
In recent years,a proliferation of wearable applications has been observed,fueled by the rapid development of sensor and integrated circuit manufacturing technology.This surge extends beyond a fleeting trend,signifying a substantial shift in our interaction with technology and our approach to data collection in daily life.Accompanying this shift,a key research focus has emerged on the integration of artificial intelligence and machine learning methods,aiming to augment and broaden the wearable systems'applications.Enabled by these methods,machine learning-assisted wearable intelligent sensing systems are not merely passive data collectors.Active monitoring and tracking of human activities and vital signs are conducted,unlocking considerable potential in human-computer interactions,digital health,and clinical diagnosis areas.We have organized and summarized the recent advancements in wearable sensor devices,machine learning algorithms,and their collaborative roles in wearable sensing applications.The evolution of wearable devices is traced from simple fitness trackers to sophisticated devices capable of monitoring a wide spectrum of biological and physical parameters.Various types of wearable devices and the diverse sensors they incorporate are then classified.These sensors,empowered with advanced technologies,are designed to monitor an extensive array of human activities and vital signs,including heart rate,blood pressure,body temperature,and physical activities.Furthermore,a thorough analysis is provided on the different categories of wearable devices,encompassing but not limited to smartwatches,fitness bands,smart clothing,and implantable devices.Each category's unique features and applications have been evolved,driven by both technological advancements and user needs.We turn our attention to the crucial function of machine learning within the framework of wearable sensing systems.Renowned for their capabilities to adapt from data and foresee results,machine learning algorithms are utilized to sift through data collected by wearable technology,unlocking valuable insights in the process.This portion of the review provides an in-depth examination of different machine learning paradigms:Supervised,unsupervised,reinforcement,and deep learning,and elucidates their tailored applications in wearable sensing systems for identifying activities,monitoring health,and detecting anomalies.Additionally,the challenges faced by machine learning-assisted wearable sensing systems are addressed.These challenges span data privacy and security,energy efficiency,and the need for robust and reliable algorithms.Emphasis is placed on areas requiring improvement and further research,including enhancing the accuracy and reliability of sensors and developing energy-efficient algorithms.In conclusion,potential solutions and future directions are proposed for the development of machine learning-assisted wearable sensing systems,with an emphasis on the need for continued innovation and research in this field.
NETL
NSTL
万方数据
维普
