Deep Learning Model for Acoustics Signal Based Preventive Healthcare Monitoring and Activity of Daily Living

To cope with the increasing healthcare costs and nursing shortages in the Aging Society the care system is transferred, as much as possible, to the home environment, making use of ambient assisted living (AAL) monitoring and communication possibilities and to actively involve informal cares to fill in large part of the care that is needed. The proposed system is the AAL based, acoustics sensing system ready to dissect, recognize, and distinguish specific acoustic events occurring in day-by-day life situations, which empowers not only the individual subjects but also the healthcare professionals to remotely follow the status of each individual continuously. This system only processes the background acoustics related to the activity of daily living (ADL) for preventive healthcare. The novel contribution of the research is based on prototype development, audio signal processing algorithms and deep learning algorithms to satisfy the research gap.

I. Introduction and State of the Art

Achieving good health is inevitable for all but ambiguous for many alone-living. Deviation in the well-being sometimes can be detected by caretaker through the change in ADLs. With the volatile progress of Health Informatics potentials for connected homes, there is the perspective of smart home technology to assist (in)formal care, older adults, and societal actors to cut health care spending and improve quality of life. The monitoring of lifestyles could facilitate remote physicians or caregivers to give insight into symptoms of the disease, avoid unnecessary hospital admission and provide health improvement advice to residents [1]. Behavioral changes could be classified into three regions: short-term behavioral change, long-term behavior change, and seasonal behavioral change. Short-term behavioral changes range from a few days to a month, related to activities such as usage of the latrine, which may indicate stomach upset. The long-term behavioral changes are a few months to years, such as repetitive application toothbrush and shower in a day, which may indicate the memory loss that disrupts daily life or more severe forms of Alzheimer's [2].