SMU Classification: Restricted Large-scale IoT Systems for Ageing-in- Place: Experiences and Lessons Learnt towards Sustainability Hwee-Pink TAN, Ph.D. Associate Professor of Information Systems (Practice) Academic Director, SMU-TCS iCity Lab 15 August 2018
SMU Classification: Restricted About the SMU-TCS iCity Lab • Track record in executing large transformation projects for Established in August • governments 2011 to explore and • Digital reimagination with social pursue new research media, mobile, big data areas in Smart t Citie ties to analytics and IoT provide long-term competitive advantage to TCS - i = {intelligent, • Focused on integrating integrated, inclusive, computing, management and innovative} social science • Multi-disciplinary expertise on smart city solutions • State-of-the-art city campus in Singapore ideal for piloting solutions 2
SMU Classification: Restricted iCity Lab’s research focus Phase 1 (2011-2014) From thought leadership to smart aging Phase 2 (2014-2017) Citizen-centric community care for ageing-in-place Citizen engagement and services Phase 3 (2017-2020) Citizen as a aspects producer for resilient cities Application of IoT through social- behavioural lens vs Citizen as consumer and producer of services Community with special needs Partnership with key stakeholders Deployments at scale with caregivers 3
SMU Classification: Restricted Meeting the needs of seniors living alone “Can non-intrusive technologies be used to better enable person son-cent centric ric comm mmuni unity ty care re for me to age-in- place?” - Mr Lim, 73yo, living alone, beneficiary Source: The Straits Times, 12 April 2012 “Can the system compl plem emen ent, instead of burden, ou our r team am to provide targeted, as- • Elderly living alone need community support to needed and timely care for the elderly to age- ensure their 2x in- place?” 2x • Safety - Ms Tan, 45yo, community caregiver, user & • Physical wellbeing beneficiary More likely to More likely to Social wellbeing • die prematurely feel depressed 4
SMU Classification: Restricted Data-driven Community Eldercare Platform Aging-related Policy Enablers Community Dwelling Elderly dashboard In-home sensing Data management Analytics Surveys and observations OTT messaging DA DATA A Community Care INSIGHT IGHT & AC ACTION TION ENABLER BLER COLLE LECT CTION ION Enablers Modular by design, extensibility by choice 5 Technology Enablers
SMU Classification: Restricted Needs of key ecosystem partners “Are our HDB town wns sufficiently age-friendl riendly “Can I maximize the reli liability ity of the system where seniors living alone can remain and minimize the need for predictive physically, socially and mentally well and maintenance?” safe?” - Mr Ong, 43yo, - Ms Lee, 35yo, - CTO, Tech4Elderly Pte Ltd - Urban Planning Group, - Urban Redevelopment Authority “Is there evidence that data-driven “Is it economi omical cally ly viable e and useful to have community care can improve the wellbei llbeing in-home monitoring technologies that can of seniors living alone through both reactive improve the safety and wellbeing of seniors and preventive care” living alone?” - Dr Ho, 50yo, - Mr Yap, 40yo, - Ageing Planning Office, - Technology Research, - Ministry of Health - Housing Development Board 6
SMU Classification: Restricted Over 200 elderly reached with ~90 ‘live’ homes # elderly 2015 2016 2017 2018 beneficiaries (living alone) Marine Parade (>36 months) • Reactive care for 48 elderly {help button & prolonged inactivity} • Preventive care for 48 elderly {social, cognitive and physical wellbeing) Bedok South (>12 months) Care for 17 elderly for irregular medication patterns, help button and prolonged inactivity Year Bukit Merah / Tampines / Bedok North (< 12 months) • VWO/NOK care for 6 5 estates (>12 months) elderly • Reactive care for 50 elderly {help • Call centre care for 22 button & prolonged inactivity) elderly (Yellow Flag) Multiple estates (<2 months) • Preventive care (social wellbeing) Identifying cognitive impairment among 48 Community elderly through passive sensing and partner 7 wearables
SMU Classification: Restricted What our users & beneficiaries say? “… For or a layp yper erso son li like ke me, me, it it wa was ea easy sy to to se see and inter terpret ret. I didn’t have to ask too much questions for confirmation and we we managed ed to to save the senior or. ” - Senior Case Worker 1, MontfortCare “…… from om a new ew wor worker ers per erspecti spective, e, to to be be able to to se see all ll th the inf informatio ormation on on th the scre screen en is is ver ery hel elpful and it’s ver very ea easy sy for or people to to respond ond." - Senior Case Worker 2, MontfortCare “…. one other things I thought this was good, it gives s elderl rly y some e form rm of securit ity to know that they are being monitored, specially those are frail, that they are not left alone in the community” - Case Worker 2, THK Moral Society “ In In general, l, I feel positiv ive about the sensor or syste tem. If something happens to me, someone will know …” - Elderly, Mdm Khoo, 77 – Marine Terrace “I feel that it is beneficial for me as I am getting old too. I’m slightly more fragile and I think with age, it’s a bit harder to do certain things like heavy household chores. ……. It helps me feel l a s sense e of securit ity ” - Elderly, Mdm Teng, 88 – Bedok South 8
SMU Classification: Restricted In-home unobtrusive monitoring system Legend: Help/fr p/friend endshi ship Moti tion on Sensor sor Gateway butt tton Sensorized Door Beacon on medication box Contact 9
SMU Classification: Restricted Evolution of In-Home Monitoring System Vendor A system Vendor B system Open, reliable and extensible system • Built in-house • Proprietary gateway with off-the-shelf z-wave • Proprietary comms • Fully-based on off-the- sensors standards shelf devices • Unused UI indicates • 2G system • Open comms standards power consumption • No ack with help button • Extensible • ACK with help button • Full system monitoring • Senior-centric design • Minimal disruption to their lives • Maximum dependability 10
SMU Classification: Restricted Technology-enabled Personalized & Timely Reactive Community Care Provide timely care and intervention Medication non- Help / friendship VWO/Call Centre/NOK adherence request Refinements Community Data analysis & Care Model Person-centric rules anomaly detection Prolonged inactivity Prolonged away Prolonged inactivity Person-centric @ home Care execution duration (Door) Response & evaluation protocol Anomaly-triggered Alert (Person-centric) Elderly Community Living Alone Volunteers Community Caregivers 11
SMU Classification: Restricted Prolonged inactivity / dwell time @ home A A period of prolonged inactivity at home / zonal dwell time can indicate trouble for the elderly resident When this duration exceeds a threshold, trigger an alert to caregivers Challenge: enge: How w to to set t th the ri right t alert rt th thre reshol old for r different erent elderly erly with th different erent daily ro routi tines es 12
SMU Classification: Restricted Data-driven alert threshold personalization Pers rson onali lize zed Alert ert Th Thre resh shol old Historical Inactivity Data High blood pressure, Early 80s diabetes and high cholesterol Aunty Tan Aunty Chan Methods Exceedance-based Stays home mostly Daily exercise routine Day/Night Threshold Frail, fall history Generally fit Socializes infrequently, Socializes frequently with few visitors 13
SMU Classification: Restricted Balancing needs of elderly and caregiver 15 15 Sep – 31 Dec ‘15 1 J Jan an – 31 Dec ‘16 Event of stress Daytime Threshold 8 hours 5.7 hours detected faster! (Average) Nighttime Threshold 8 hours 4.9 hours (Average) False se Alarm rm Rate e Due to 5 False se Alarms arms / 3.5 Mo Months ths = 63 63 False se Alarms arms / 12 12 Mo Months ths = = Within Threshol reshold Exceeda eedance ce* 1.4 Per r Month th 5.3 Per r Month th tolerable fatigue Overall False Alarm Rate 43 False Alarms / 3.5 Months = 121 False Alarms / 12 Months = limit! 12.3 Per Month 10.1 Per Month 14
SMU Classification: Restricted Technology-enabled Personalized Reactive Community Care (Medication regularity) Zone Marine ine Pa Parade Bedok ok South th HDB type Rental Rental Total l no of elderl erly 10 14 Senior ior profil ile Generally healthy and socially active Vulnerable and frequently admitted to hospital #Medicati ication on types es 4 to 10 1 to 15 Medicati ication on intake e frequenc ency 1 to 3 1 to 4 Period riod Jul 15 - Apr 16 Jul 16 - Feb 18 Careg egiv iver er MontfortCare Neighbours for Active Living St Study type Observational Interventional 15
Recommend
More recommend
