Cloud-Based Smart Dog Music Therapy and Pneumonia Detection System for Reducing the Difficulty of Caring for Patients With Dementia

Abstract

There is currently no cure for Alzheimer's disease, leaving patients to rely solely on good quality care services to prolong their life. Besides, it has been found that the onset of pneumonia can accelerate the progression of dementia and even lead to death. This has led to an increased caregiving burden and a level of emotional stress among caregivers that can be unbearable. The aim of this study was to build a Smart Dog music therapy and pneumonia detection system, which combines a robotic dog, cloud technology, a multi-agent system, an adaptive network-based fuzzy inference system (ANFIS), a web application, and sensor technology to deliver care for patients with Alzheimer's disease and help mitigate the difficulties faced by caregivers. Interviews were conducted with caregivers following the use of the system to determine its usefulness in caregiving work and whether it improved their overall caregiving experience. A majority of the interviewed caregivers agreed that the system brought about improvements.

Intelligent Sensing Technologies for the Diagnosis, Monitoring and Therapy of Alzheimer’s Disease: A Systematic Review

“…Lyu et al [ 55 ] developed a system consisting of a smart robotic dog along with an adaptive fuzzy logic inference module and cloud technology. A corresponding web application along with a few sensors such as pulse oximeter, electroencephalogram (EEG) and smartwatch was also part of the system.…”

“…In the case of handheld smart devices, [ 55 ] introduced a robotic dog that could monitor mood changes, temperature and heart rate using various sensors. The results of the study indicate that the mood of the patients improves due to the interactive robot, posing less burden on the caregivers.…”

“…Hence, feasible and practical solutions to mitigate this issue should be researched. According to the reviewed studies, only a couple of the studies are detecting mood issues [ 36 , 55 ] while only one study focuses on emotional encouragement through music [ 57 ]. Hence, further research should be carried out giving more attention to incorporate behavioural changes of Alzheimer’s patients.…”

Deep Regression via Multi-Channel Multi-Modal Learning for Pneumonia Screening

“…The third category, which is based on multi-modal analysis, has attracted considerable attention in the literature [10], [12]- [16], and our method is closely related to this category. In 2016, Shin et al [11] proposed a method used CNN to extract features from chest X-Rays and used LSTM to generated MeSH (Medical Subject Headings) terms for chest X-Rays.…”

“…It is a replacement of fully-connected layers to enable the summing of spatial information of feature maps. After global average pooling, the outputs with size[32,16,16, 2048] will be transformed into vectors with size[32,1,1, 2048]. Then a fully-connected layer is used to reduce dimensions to 128 and fit the number of LSTM units.…”