Research Article
An Interactive Care System Based on a Depth Image and EEG for
Aged Patients with Dementia
Xin Dang, Bingbing Kang, Xuyang Liu, and Guangyu Cui
School of Computer Science and Software Engineering, Tianjin Polytechnic University, Tianjin 300387, China
Correspondence should be addressed to Xin Dang; xindang_tjpu@126.com
Received 24 February 2017; Accepted 14 May 2017; Published 18 July 2017
Academic Editor:
Junfeng Gao
Copyright © 2017 Xin Dang et al. This is an open access article distributed under the Creative Commons Attribution License, which
permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Due to the limitations of the body movement and functional decline of the aged with dementia, they can hardly make an efficient
communication with nurses by language and gesture language like a normal person. In order to improve the efficiency in the
healthcare communication, an intelligent interactive care system is proposed in this paper based on a multimodal deep neural
network (DNN). The input vector of the DNN includes motion and mental features and was extracted from a depth image and
electroencephalogram that were acquired by Kinect and OpenBCI, respectively. Experimental results show that the proposed
algorithm simplified the process of the recognition and achieved 96.5% and 96.4%, respectively, for the shuffled dataset and
90.9% and 92.6%, respectively, for the continuous dataset in terms of accuracy and recall rate.
1. Introduction
The expected growth of the older adult population in China
over the next 30 years will have an unprecedented impact
on the healthcare system, especially in terms of supply and
demand for healthcare workers. Moreover, the elders are
always short of self-care ability and require manual care.
Nurses have heavy working burden, especially when they
are taking care of the high-risk and 24-hour guardian
patients. In addition, the rehabilitation training always
depends on the experienced therapist. In fact, the shortage
of practitioners of nursing and rehabilitation is serious.
Therefore, the development of cheap and efficient intelligent
care equipment is a significant way to solve these problems.
With the development of automatic rollover, efficient
bedsore care beds appeared firstly and got a social positive
assessment in 2007. This research achieves some good results
on the smart rollover and bedsore care facility aspects. How-
ever, due to the high cost and complexity in a hardware
system and with the lack of automation, those techniques
are still in the lab.
Another limitation of those healthcare facilities is the
low efficiency of the communication between the equip-
ment and elders. The help requirement of the elders
always includes feeding, going to the toilet, rehabilitation
and massage treatments, or chat with someone. However,
there are some difficult states that are not well settled for
traditional human-machine interface technologies, such as
accent pronunciation, weak sound, and difficulty in mov-
ing. Thus, improving the efficiency and confidence of the
elders in their interaction with healthcare facilities
becomes one of the most important research topics, in
favor of both self-care and rehabilitation and reducing
the burden on their children.
With the increasing use of portable computing and com-
munication devices, researchers try to use smartphones or
tablet in improving the convenience in the healthcare inter-
actions. However, because of the declining vision, dry fingers,
complex operation process, and high-power consumption,
these devices will be abandoned after a period of time. Fur-
thermore, the development of somatosensory technology
provides a superior interaction experience in the medical
rehabilitation. Some low-cost somatosensory sensors provide
a high practical interaction system by gesture recognition and
speech recognition algorithm and are widely used in the
active sports therapy and rehabilitation of patients [1–4].
For the neuropsychology rehabilitation service, Chang
et al. developed a rehabilitation system, Kinect’s Kinempt,
Hindawi
Journal of Healthcare Engineering
Volume 2017, Article ID 4128183, 8 pages
https://doi.org/10.1155/2017/4128183