Download - An Ontology for Wearables Data Interoperability and Ambient Assisted Living Application Development
An ontology for wearables data interoperability and Ambient Assisted
Living application development
Natalia Díaz-Rodríguez, S Grönroos, F Wickström, J Lilius, H Eertink, A Braun, P Dillen, J Crowley, J Alexandersson
World Conference on Soft Computing, Berkeley, California. May 23rd 2016 50th Anniversary of Fuzzy Logic and Its Applications and 95th Birthday Anniversary of LOTFI A. ZADEH
Background: Ambient Assisted Living• Usage of technology to provide assistance to people who need
it in their daily activities, in the less obtrusive way • Aim: support older/disadvantaged people, independent living,
safety
USE CASE: ACTIVE HEALTHY AGEING Project
EIT Digital Action Line on Health and well-being [Img credit: M.Ros et al.2011]
Vertical activities in Active Healthy Ageing Project• Cognitive Endurance: detection of mild cognitive impairment
(1st stages of dementia). Reminiscence therapy. Tracking: physical activity and HR • Burn-out turnout: stress, HR, activity (lifestyle patterns),
sleep • Virtual social gym: physical fitness (HR and calories) • ConnectedCare: Personalized alarm management, online
collaboration platform for caregivers and professionals
Interaction between AHA Platform components with PHL data-store1. Home Application Gateway (INRIA -Grenoble/DFKI/Åbo
Akademi): • Sensor data interpretation
2. Mobidot MoveSmarter platform (Novay) • Interprets mobility data (GPS and accelerometer data) • Detects individual trips and travel modalities
3. Philips bracelet: • Monitors HR and derived stress levels.
Case study: A Kinect ontology for physical exercise annotation and recognition• Active Healthy Ageing project (EIT Digital) • Philips Personal Health Labs (PHL) • Sensor data aggregation platform
AHA Project -> Wearables Ontology: • Different datatypes, units, frequency and update rate • Wearable devices and vital signs for health continuous monitoring
• Person’s weight • Height • Location • Step & calorie count • Sleep • Location • Activity level • Activity energy expenditure • Heart rate • Stress level and valence (GSR) • Ambient light level • Ambient temperature • Skin temperature • Skin conductance
Kinect Ontology Classes
Kinect Ontology classes, data & object properties
Sit to stand session for elders activity monitoringSitStandSessionDDMMYY: {"name": "SitStandSession", "ended_at": "2013-08-13 11:32:29” "started_at": "2013-08-13 11:20:34”}
Examples of useExample 1: Defining basic movement (Stand, BendDown, TwistRight, MoveObject, etc).
Example 2: When defining, e.g. SitStandExercise workout, the N of series done in time as well as the exercise quality can be measured and compared with predefined medical guidelines, to give feedback.
Examples of use 2Example 3: Historic analysis can be provided to monitor posture quality in time. E.g. having back less straight than 1 year ago can be notified to correct/prevent on time.
Example 4: An office worker can be notified when he is not having straight back and neck or when he has been sitting for too long.
Further integrationActivity recognition in AAL
Future work
Activity recognition: • Multiple human sensing • Parallel/interleaved activities • Automatic ontology learning and evolution
work • (FOL/DL) Logics support for temporal
constraints
A folkloric dance flamenco virtual tutor
Future work• FPV Wearable cameras for AAL (elders, visually impaired) • Unsupervised activity modelling and automatic dataset
annotation • EGOSHOTS Dataset: https://github.com/NataliaDiaz/Egoshots
More info? collaborations? Master students without topic?Welcome!
[email protected] [email protected]
https://about.me/NataliaDiazRodriguez
• Wearables, security and access control, activity recognition and Kinect ontologies available: https://github.com/NataliaDiaz/Ontologies
• AHA Platform Project: https://www.eitdigital.eu/fileadmin/files/HWB-pictures/EIT-Handout-HWB_EoY-1213-spreads-HR.pdf