Human activity monitoring and recognition (HAMR) based on smartphone sensor data is a field that promotes a lot of observation in current era due to its notable desire in various Ambient Intelligent applications such as healthcare, sports, surveillance, and remote health monitoring. In this context, many research works have unveiled incredible results using various smartphone sensors such as accelerometer, gyroscope, magnetometer, digital compass, microphone, GPS and camera. The waveform of sensor motion is quite different in several smartphone placements even for the identical activity. This makesit challenging to apprehend varied completely different activities with high precision. Due to the difference in behavioral habits, gender and age, the movement patterns of various individuals vary greatly, which boosts the problem of dividing boundaries of various activities. In HAMR, the main computational tasks are quantitative analysis of human motion and its automatic classification. These cause the inception of Machine Learning (ML) and Deep Learning (DL) techniques to automatically recognize various human activity signals collected using smartphone sensors. This paper presents a comprehensive survey of smartphone sensor based human activity monitoring and recognition using various ML and DL techniques to address the above mentioned challenges. This study unveils the “research gaps in the field of HAMR, to provide the future research directions in HAMR.

Smartphone based human activity monitoring and recognition using ML and DL: a comprehensive survey

Thakur D.
Writing – Original Draft Preparation
;
2020-01-01

Abstract

Human activity monitoring and recognition (HAMR) based on smartphone sensor data is a field that promotes a lot of observation in current era due to its notable desire in various Ambient Intelligent applications such as healthcare, sports, surveillance, and remote health monitoring. In this context, many research works have unveiled incredible results using various smartphone sensors such as accelerometer, gyroscope, magnetometer, digital compass, microphone, GPS and camera. The waveform of sensor motion is quite different in several smartphone placements even for the identical activity. This makesit challenging to apprehend varied completely different activities with high precision. Due to the difference in behavioral habits, gender and age, the movement patterns of various individuals vary greatly, which boosts the problem of dividing boundaries of various activities. In HAMR, the main computational tasks are quantitative analysis of human motion and its automatic classification. These cause the inception of Machine Learning (ML) and Deep Learning (DL) techniques to automatically recognize various human activity signals collected using smartphone sensors. This paper presents a comprehensive survey of smartphone sensor based human activity monitoring and recognition using various ML and DL techniques to address the above mentioned challenges. This study unveils the “research gaps in the field of HAMR, to provide the future research directions in HAMR.
2020
Healthcare
Human activity monitoring and recognition
Machine learning
Sensors
Smartphone
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/369765
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 46
  • ???jsp.display-item.citation.isi??? 30
social impact