Classification of Daily Activities for the Elderly Using Wearable Sensors

Abstract

Monitoring of activities of daily living (ADL) using wearable sensors can provide an objective indication of the activity levels or restrictions experienced by patients or elderly. The current study presented a two-sensor ADL classification method designed and tested specifically with elderly subjects. Ten healthy elderly were involved in a laboratory testing with 6 types of daily activities. Two inertial measurement units were attached to the thigh and the trunk of each subject. The results indicated an overall rate of misdetection being 2.8%. The findings of the current study can be used as the first step towards a more comprehensive activity monitoring technology specifically designed for the aging population.

StraightenUp+: Monitoring of Posture during Daily Activities for Older Persons Using Wearable Sensors

“…Performance evaluation of the device showed fairly accurate classification, with a rate of incorrect detection of 6.5%. A similar recent study in elders had a rate of misdetection of 2.8% [ 38 ]—however, in that study, participants used sensors in the trunk and thigh, and the system classified six activities, while our work classifies eight. The classification error in our study may be partly caused by the complex body movement of the elderly participants due to their functional deterioration.…”

“…Other studies have focused on detecting activities of older participants. Two accelerometers (placed on the trunk and thigh) were used to classify six activities of daily living for elders, with a 2.8% misdetection rate [ 38 ]. Another study specifically focused on hand gestures (e.g., eating, drinking, brushing hair) [ 27 ].…”

Sensing Physiological Change and Mental Stress in Older Adults From Hot Weather

“…For instance, activity monitoring in the home environment of older adults is a growing area of interest. Monitoring tools range from vision-based cameras, radio-based WiFi and radio frequency identification, and sensor-based tools such as accelerometers and smartwatches [11]- [13]. They can be attached to the trunk, limbs, wrist, or clothes to detect physical activities and mobility patterns [14].…”

Neural Network Ensembles for Sensor-Based Human Activity Recognition Within Smart Environments

“…HAR is concerned with the ability to recognize and interpret human activities automatically through the deployment of sensors and the processing of the data they generate [21]. Various approaches to recognizing activities within smart environments have been explored, including the extensive use of wearable devices [22,23] and video-based approaches [24], which is largely due to the increased accessibility of these technologies. Nevertheless, these approaches have associated limitations to consider, including concerns with ethics, comfort, privacy invasion, and obtrusiveness.…”