You are here

Intelligent Pervasive Communication Systems for Realizing Personalized Healthcare in Connected Environments

Feature Topic


The ever growing number of embedded and network-enabled physical devices collectively termed as the ‘Internet of Things (IoT) has become an enabler for facilitating richer context awareness, personalization through integration of information sharing and connectivity, into everyday consumer devices. The global IoT market is expected to hit $7.1 trillion (USD) by 2020 (International Data Corporation) with the medical sensing market expected to reach USD 15.01 billion by 2022 ( This influx of personal, mobile and wearable devices is set to revolutionize the e- and m-health systems by bringing personalised real-time health informatics to consumers as well as enhancing existing dedicated clinical biomedical and healthcare delivery systems. The use of unobtrusive wearable sensors, self-checking devices and emerging micro- and nano-fabrication of implantable devices are able to track the progression and evolution of physiological indicators (e.g. blood pressure, blood gas, pulse, insulin level, EKG, and affective states). Mobile and in-situ wireless sensing networks for monitoring user activity, kinematics, and user interaction through assistive technology can provide broader indicators of user behavior and contextualization of acute health issue and the management of long-term conditions. Such contextually available data can enrich clinical- based systems and remote health monitoring schemes to provide patient-centered care delivery. The utilization of these heterogeneous ubiquitous data sources presents key challenges of effectively fusing together spatially and temporally diverse multi-source data and gaining useful insight and knowledge from these sources.

There have been significant breakthroughs in the development of nature-inspired computational intelligence (CI) techniques which can allow for the utilization of this vast wealth of data by revealing hidden patterns and relationships, handling the various sources of uncertainties and modeling stochastic and complex real-world processes to build effective tools for personalized health care delivery. Techniques such deep learning approaches can model complex patterns and correlations in different data (audio-visual, numerical etc.) that can be used to predictively model health-related outcomes: certain health conditions, patient physiological, mental states, treatment and therapy responses. Fuzzy logic systems provide a means to exploit multiple and diverse inputs available in modern medical environments and deal with the inherent uncertainties and noisy data. State-of-the art data fusion techniques such as the monotone/fuzzy integrals and approaches for uncertain data models can be used for combining inter-source uncertainty arising from multiple data sources such as physiological sensors or variability in opinions of physicians on medical diagnosis and treatment plans. Techniques such as cellular automata, artificial immune systems and related approaches are able to model highly complex networked systems of connected devices, self-aware and self-configuring software and hardware agents. Finally, advances in evolutionary techniques can assess and optimize drug delivery treatment management recommendations and the optimization of the distributed storage and retrieval infrastructures for realizing unique arrangements of connected devices and information resources for driving these applications. We cordially invite investigators to contribute their original research articles written in tutorial style, with an emphasis on real-life applications, as well as review articles that will stimulate further activities in this area and improve our understanding of the key scientific and engineering problems.

Topics of Interest

We seek original and high quality submissions related to one or more of the following topics:

  • Ambient intelligent architectures and paradigms for ubiquitous healthcare systems
  • Real time signal and image processing for ubiquitous computing and bio-sensing applications
  • Hardware implementation, computational complexity reduction and optimization of ubiquitous e-health systems
  • Nature-Inspired smart hybrid systems for connected healthcare systems, services and applications
  • Deep learning-based predictive health informatics from multi-source data
  • Artificial immune system modelling for telemedicine and m-health solutions
  • Computational learning and optimisation techniques for chronic disease and health risk management applications
  • Healthcare prototype for bio-medical image-based intelligent pervasive healthcare systems
  • Ubiquitous computing for innovative healthcare systems, services and applications
  • Ambient intelligent agents for personalised healthcare systems
  • Data/Image, feature, decision, and multilevel information fusion
  • Uncertainty handling in multi-sensor, multi-source data fusion
  • Intelligent wireless sensing infrastructures for healthcare delivery
  • Meta heuristic algorithms for implementing ubiquitous communication architectures and protocols
  • Optimising security assurance for e- and m-health systems


Arun Kumar Sangaiah, (Corresponding Guest Editor)
VIT University, Vellore, Tamil Nadu, India

Faiyaz Doctor
University of Essex, UK

Jian-Wei Niu
Beihang University, Beijing, China

Jing-Ming Guo
National Taiwan University of Science and Technology, Taiwan

Jocelyn Aulin
Huawei Technologies Sweden AB, Sweden

Wael Guibene
Intel Labs, Ireland