You are here: start » lissi_living_lab

LISSI living lab is devoted for designing and experimenting ubiquitous intelligence technologies that can be used for services composition, activity recognition, context aware services adaptation. One of our main application targets are Ambient Assisted Living (AAL) of Elderly and frail people.

In fact, dealing with the problems linked with the Ambient Assisted Living (AAL) of elderly people becomes particularly urgent. Today, one in three people over 80 years in Europe continue to stay at home, and the share of people over 60 years in the most industrialized European countries is over 10%. In 2020, it will be approaching 21%. According to the European Disability Forum, see http://www.edf-feph.org, disabled people already represent 50 million persons in the European Union (about 10% of the population), and it can then be considered that one in four Europeans has a family member with some form of disability – e.g., reduced mobility. National budget constraints, causing a reduction of available community services, as well as reduction in availability of family care (by 2017, for instance, the UK will reach the tipping point for care when the numbers of older people needing care will outstrip the numbers of working age family members currently available to meet that demand) call for the identification of alternative forms of monitoring and support for older persons with minor disabilities or mild cognitive decline. Several scenarios can be envisioned in this context;

  • Safety monitoring of people with mild dementia cognitive impairments. Detecting and preventing them from high risks and incidents of daily living.
  • Memory maintenance. It is very likely that the older person will forget taking his/her pills at due time and/or takes them more times than needed. The system can monitor the assumption, remembering which pills should be taken and when and asking the older person to confirm that they have been taken. The monitoring system could then refuse providing those pills that have been already taken and/or alert the caregiver in case of misuse.
  • A cognitive impaired older person can put him/herself at risk making inappropriate use of household equipment, such as the stove or the boiler. Such behaviours can be detected by the system that of precaution would stop, for example, the gas provision. The caregiver would then be alerted and – if considered safe – the command of turn it on again could be provided.

We are currently implementing the following scenarios for instance, Safety monitoring based on GWE, Diet Coaching, Kitchen Aid, Monitoring of therapeutic observance, Monitoring of Rehabilitation, etc.

The infrastructure of our living lab is built within the new premises of the LISSI research laboratory where we have created a realistic living environment that is similar to the ones used by elderly people. It consists of a kitchen, bathroom, bedroom and living room. The ubistruct living lab infrastructure is modular and can be reconfigured to meet different experimentation requirements and scenarios, thanks to the use of a variety of wireless and mobile furniture and equipment that can be found in the market. The latter range from wireless sensor networks and actuators to smart devices such as smartphones, tablets and a mobile robot. The hardware infrastructure is described in the following.

Power Management:

  1. ZPlug Boost is a wireless Power Outlet which can be switched On/Off by Zigbee™ protocol. It can commute 16A devices on 220V/230V. It measures the instantaneous power and cumulated consumption of the connected device.

Presence detection and identification:

  1. Active RFID: The RX202 from Wavetrend provides instant reporting of all detected Wavetrend active RFID tags. It allows user configurable tag data and read range filters. It is installed on the Kompai Mobile Robot and on Rasberry Pi modules through USB connection. The latter can be deployed in any location in the living space.
  1. Passive RFID: The RoboticsConnection RedBeeTM RFID Reader is a sophisticated reader that can work in standalone, or Networked BPAN (Broadcast Personal Area Network) mode. The reader is designed to work with all EM41xx family 125 kHz RFID tags including cards, buttons, capsules, disks, key fobs, and others. A wireless connexion can established between the The RedBeeTM reader and Robot or Mobile Raspberry Pi module by using XBee Zigbee wireless module, which acts as a wireless serial interface.
  2. Cricket: It is indoor location system for that is used by any agent to track humans or objects position accurately. A socket server provides fine-grained location information of Cricket beacons : space region identifiers, position coordinates X,Y and Z, and orientation. The Cricket native location computing system have been improved to correct deployment and measurement drawbacks. The Cricket beacons are installed on the mobile robot and Raspberry Pi to track respectively the robot and human positions in the ambient space.

Environment sensing:

  1. Doors opening and closing detection: The ZDoor is very low power Zigbee™ wireless sensor. It detects opening and closing of doors or windows with a magnet and reed-switch mechanism. ZDoor is compliant with Zigbee Pro 2007 stack and can be easily add in an existing network. This sensor is installed on cupboards doors, fridge as well as doors and windows of the living environment.
  2. Measuring ambient temperature, humidity and luminosity : The TelosB mote platform is an open source, low-power wireless sensor module that allows measuring RSSI, temperature, temperature, humidity and luminosity. The TelosB is compliant with IEEE 802.15.4. TelosB runs a Contiki embedded operating system.
  3. Motion detection: ZMove is a Zigbee™ passive infrared sensor (PIR sensor) that measures infrared (IR) light radiating from objects in its field of view in the ambient space. Motion detection events are send as alarms to the central node by the Zigbee™ wireless network.

Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 3.0 Unported