+1 Recommend
1 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Virtual Care Giver: Virtual Agent for Personalized Home Elderly Care


      Science Impact, Ltd.

      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.


          The rapidly ageing population is a known phenomenon that is observed across the globe. However, being elderly should not mean a compromised quality of life, and with the development of technology comes the ability to provide the elderly with autonomy and help assist them in their lives. One team of researchers is interested in the super smart society (Society 5.0) – the next-generation society, where heterogeneous systems are interconnected over cyber and physical spaces to provide advanced services for individual citizens – and is hoping to exploit its full potential. Personalised care: The Vitual Care Giver uses emerging face recognition and image processing technology to generate a 3D model of a face from a given picture. Services such as text-to-speech, speech-to-text, dialogue and facial expression are made available to the user. It uses a profile of each elderly person to provide personalised care that is customised to the individual. In addition to being used for care of the elderly in their homes, it can also be used for psychological counselling. Although other integrated virtual agent interfaces are in existence, these all work based on predefined scripts and scenarios. What makes Nakamura’s system particularly innovative is the fact it strives to adapt to different situations and backgrounds, delivering personalised services. ‘The adaptation is autonomous. The system knows the situation from sensor readings, as well as the user’s preference/profile obtained by conversations. Of course, the system learns from the data to see what care is appropriate for that elderly person in that situation,’ he explains. A buddy for everybody: The key challenge the team faces concerns integrating the different heterogeneous components, as Nakamura explains: ‘For the autonomous SensorBox, we implemented software modules to automatically monitor the status of sensors and the network, and to restart the system when any fault occurs,’ he explains. ‘This kind of IoT system consists of a number of components, so the reliability of the system is determined by the multiplication of the components. The real challenge is not in development, but in operation. Thus, we found it important to decipher how to minimise human effort for operation and maintenance.’

          Related collections

          Author and article information

          Science Impact, Ltd.
          December 26 2018
          December 26 2018
          : 2018
          : 11
          : 31-33
          © 2018

          This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

          Earth & Environmental sciences, Medicine, Computer science, Agriculture, Engineering


          Comment on this article