The societal challenge to improve proactive healthcare and community services through technological advances in the Internet of Things (IoT), calls for granular and continuous nationwide instrumentation, driven by data mining technologies.

Example healthcare challenges include behaviour and lifestyle-related diseases, such as obesity, depression, work-related stress, stroke, falls and cardiovascular health issues. A paradigm shift from a reactive towards a proactive model, is of paramount importance for the sustainability of healthcare costs of an ageing population (e.g. in the UK and Japan). In this direction, mobile healthcare sensors manifest a promising engineering approach to the problem. For example a data fusion of environmental and wearable biosensors, such Electrocardiogram (ECG), accelerometer, global positioning (GPS), can help detect medical emergencies such falls and strokes, analyse longer-term illnesses such as depression and anxiety, intervene, e.g. with visualisation-based therapies, or gather more data, e.g. with application-aided mood collection or crowdsourcing.

One enabling technology to healthcare data mining involves centralised (big) data mining. However, continuous and real-time mobile communications of healthcare sensor data are limited by energy (battery) and bandwidth physical constrains. Instead, the aim of this CAMAD 2015 Special Session on Healthcare Data mining in sENSor nEtworks (HealthDENSE) is to advance recent research of sensor-based healthcare data mining. This involves, in-network activity and behaviour analytics, time-series data mining, and delay-tolerant communications. The scope of HealthDENSE further extends to knowledge-based network optimisation through sensor data mining. Finally, recent advances on data mining for privacy protection can be adopted and adapted for e-health citizen privacy.

Submission of original and unpublished work in all areas related to HealthDENSE is welcome. Topics of interest include, but are not limited to, the following areas.
* In-network or sensor data mining.
* Time series data fusion.
* Behaviour analytics.
* Distributed symptom detection model for learning and inference.
* Mood and stress-related analytics.
* Anomaly detection in ECG and activity data.
* Healthcare mobile ad hoc network simulation.
* Knowledge-based wireless network optimisation for e-health.
* Healthcare data offloading and delay-tolerant networks.
* Sensor health-aware routing.
* Data mining for e-health privacy protection.

HealthDENSE’15 Chair and Organiser:
---------------------------------------
Dr Georgios Kalogridis
Principal Research Engineer & Team Leader
Toshiba Research Europe Limited
Telecommunications Research Laboratory
32 Queen Square, Bristol, BS1 4ND, UK
Email: george@toshiba-trel.com