Smart Home and Sensing

Technologies
at
Massey University

Subhas Mukhopadhyay and Hans Guesgen

Massey University, New Zealand
 Research Objectives
 Wellness of Human
 S2IS Group (Smart Sensing and Intelligent Systems)
 MUSE (Massey University Smart Environment)

 Sensors cum Embedded Intelligent Systems Development

 A few current PhD projects

 Wellness Protocol for Smart Home

 Model of Human Lifestyle
 Flexible Printed Sensors for Human Wellness
 Smart Sensors for Early Detection of Osteoporosis
 Smart Human Tracking
 Distributed Monitoring Using Internet Sensing

Special Presentation at Massey

Why Smart Home?

Special Presentation at Massey

 Wireless Sensor Network Based Smart Home

“Grandma is SAD”

Panic Button

N.K. Suryadevara and S.C. Mukhopadhyay, “Wireless Sensor Network Based Home Monitoring System for Wellness Determination of Elderly”, IEEE Sensors Journal,
Vol. 12, No. 6, June 2012, pp. 1965-1972.
 Sensors Integrated with Everyday Objects

Sensors and associated

instrumentation developed in-
house

N. K. Suryadevara and S.C. Mukhopadhyay, “Determining Wellness Through An Ambient Assisted Living Environment”, IEEE Intelligent Systems, May/June 2014, pp. 30-
37.
 Wearable Physiological Sensors Modules and
Human Emotion Recognition Unit

Angry Happy Sad Neutral

K. Kaur, S.C. Mukhopadhyay, J. Schnepper, M. Haefke and H. Ewald, “A Zigbee Based Wearable Physiological Parameters Monitoring System”, IEEE Sensors Journal, Vol.
12, No. 3, March 2012, pp.423-430.
 Smart Power Management based on WSN

Sensing Device + Lamp

Xbee End Device

Heater

Xbee Kettle
Coordinator
Toaster
Washing
Machine
N.K. Suryadevara, S.C. Mukhopadhyay, S.D. T. Kelly and S. P. S. Gill, WSN-Based Smart Sensors and Actuator for Power Management in Intelligent Buildings, IEEE
Transactions on Mechatronics, Vol. 20, No. 2, April 2015, pp. 564-571
Leakage gas and Fire monitoring
Big Picture of the project
Multi-Gateway Cluster Network- Environment Monitoring System

Internet/Website

Special Presentation at Massey

 Molecular recognition for rapid detection system of Phthalates
b Recognition

Molecular
Imprinting
Polymer
Laboratory preparation of MIP DEHP Extraction EIS setup for rapid testing system
(Soxhlet)
EXPERIMENTAL

EIS NYQUIST PLOT- DEHP-in MIP(0.1Hz-10kHz)

-18000000
-16000000
RESULTS

Imaginary Z (kΩ)

-14000000

-12000000

-10000000

-8000000
-6000000
-4000000

-2000000 AVERAGE -100 ppm DEHP-MIP AVERAGE-200 ppm DEHP-inMIP

AVERAGE-10 ppm DEHP-inMIP AVERAGE MIP in MilliQ(CONTROL)
0
0 10000000 20000000 30000000 40000000 50000000
Real Z (kΩ)
 Our Research
Activities of
Provide
Daily Living
Monitoring Assistance/Advise

Unobtrusive

Health
Wellness Physiological
Determination Informatics Monitoring
System
Wearable and
- Non -Invasive
Non-Wearable

Environmental
Monitoring
Special Presentation at Massey
Special Presentation at Massey
Wellness Determination:Tools

Special Presentation at Massey

 Wellness Functions, β1 and β2
Wellness Function, β1 used to determine the wellness of elderly based on the Inactive usage of house-hold
appliances.

Wellness function β1 =

Where β1 =Wellness function of the inhabitant based on Inactive usage measurement of appliances

t = Time of Inactive duration of all appliances (i.e.) duration time no appliances are used.
T= Maximum inactive duration during which no appliances are used.

If β1 is equal to 1.0 indicates the inhabitant is in healthy situation. If β1 is less than 1.0 and goes below 0.5 the
situation indicates some unusual situation.

Wellness Function "β1"

S4
S u b je ct L o c a tio n s

S3

S2

S1

0.00 0.10 0.20 0.30 0.40 0.50 0.60 0.70 0.80 0.90 1.00
β1
Special
N.K. Suryadevara and S.C. Mukhopadhyay, “Wireless Sensor Network Presentation
Based at Massey
Home Monitoring System for Wellness Determination of Elderly”, IEEE Sensors Journal,
Vol. 12, No. 6, June 2012, pp. 1965-1972.
 Wellness Functions, β2
Wellness function

Where β2 = Wellness function of the elderly based on excess usage

measurement of appliance.
Ta= Actual usage duration of any appliance.
Tn = Maximum usage time of appliance.

Under normal condition, Ta < Tn (i.e.) No Abnormality

Only if Ta > Tn then β2 is calculated.

The value of β2 close to 0.8 and above may be considered as normal situation.

If β2 goes less than 0.5 indicates excess usage of the appliance and may lead to
an abnormal condition.

Special Presentation at Massey

 Wellness Function: β2
Subject #1 Subject #2

Subject #4
Subject #3

Special Presentation at Massey

 Prediction of Future Behaviour (Trend Analysis)
Plot for four week Bed usage data Sequence plot + Trend cycle(green)
for four week Bed usage data

Additive Extended + Seasonal = Forecast

model Trend factor value
value Week #5 Error in the forecast is not likely
T SAF F to be more than twice the
5 SUN 9:46:53 + 0:10:42 = 9:57:35 standard deviation of the
5 MON 9:43:19 + 0:10:30 = 9:53:49
residuals ( 95% confidence)
5 TUE 9:29:21 + -0:11:35 = 9:17:46
5 WED 9:29:38 + -0:25:22 = 9:04:16
5 THU 9:30:16 + 0:05:27 = 9:35:43 Maximum Likely Error is
5 FRI 9:34:41 + -0:25:02 = 9:09:39 2 x00:22:57≈ +/- 45Mins(Approx)
5 SAT 9:36:53 + 0:35:23 = 10:12:16
 1 2 00 .

Forecast
1 1 00 .
Observed
1 0 00 . Trend

9 0 0.
Observed

8 0 0.

7 0 0.

6 0 0.

0 10 20
Days 30 40 50 60 70
Days
Fig 9(a) Toilet usage Trend for 70 days Fig 9(b) Toilet usage (Ninth week forecast pattern)

2400.

120 0 . (b) 2200.

Observed
2000.
110 0 .

100 0 .
1800.
Observed
1600.

90 0 . 1400.
Trend

80 0 . Forecast 1200.

1000.

70 0 .
8 00 .

60 0 . 6 00 .

0 10 20 30 40 50 60 70
0 10 20 30 40 50 60 70

Days Days
Fig 9 (c) Toilet usage (Tenth week forecast pattern) Fig 9(d) Chair Usage Trend for 70 days

N.K.Suryadevara, S. C. Mukhopadhyay, R. Wang, R.K. Rayudu, Forecasting the behavior of an elderly using wireless sensors data in a smart home, Elsevier:
Engineering Applications of Artificial Intelligence, Available online 12 September 2013, ISSN 0952-1976, http://dx.doi.org/10.1016/j.engappai.2013.08.004.
Internet Sensing (Internet of Things)
‘The Internet of Things’ is a network of items –
each embedded with sensors – which are connected
to the Internet.
“… all about physical items talking to each
other..”

Machine-to-machine communications and person-

to-computer communications will be extended to
things.

Technologies that will drive the future Internet

of Things: Sensor technologies including RFID,
smart things, nanotechnology and
miniaturization.
Special Presentation at Massey
 Fundamental block for Internet Sensing

• Stand-alone node
• Server based
Local Home gateway Server based
Smart Home
 Internet Sensing and Cloud Computing

• Cloud Computing: Integrating sensors

into computing devices

Special Presentation at Massey

 Summary of Wireless Protocols
Standard ZigBee BlueTooth WiFi WiMax
(IEEE 802.15.4) (IEEE 802.15.1 (IEEE 802.11 (IEEE 802.11
WPAN) WLAN) WWAN)

Range 100 m 10 m 5 km 15 km

Data rate 250-500 kbps 1 Mbps-3 Mbps 1Mbps-450 Mbps 75 Mbps

Band-width 2.4 GHz 2.4 GHz 2.4, 3.7, and 5 2.3, 2.5 and 3.5
GHz GHz

Network Star, Mesh, Cluster Star Star, Tree, P2P Star, Tree, P2P
Topology Tress

Applications Wireless Sensors Wireless Sensors PC based Data Mobile internet

(Monitoring and (Monitoring and acquisition,
Control) Control) Mobile Internet

Special Presentation at Massey

Development of New
Protocol

Wellness Protocol: A Proposal and

Implementation for Smart Home

Special Presentation at Massey

 Comparison between ZigBee and Wellness
Protocol
Title ZigBee Mesh
Node Types, Benefits Coordinators, Routers, End Devices.
End Devices potentially less
expensive because of reduced
functionality.
Wellness Protocol
One main type is End-device plus
router; it also has router, end-
device and coordinator. Increases
reliability in home environments
where packet size matters.

Sleeping Routers and Battery Only end devices can sleep All node can go into sleep and
life but coordinator has to maintain
time synchronization.

Packet size Usually minimum 18bytes+ For Basic is 10Bytes

example XBee S-2 in API mode with
one sensor
Latency High Less
Complexity related to data High Less
extraction from packet
Real time operation Perform average Perform better
Data handling and storage Quite complex Simple
Packet reliability parameters Affected by huge packet structure Improve by customized smart
home packet structure

PhD Confirmation 15th Jan 2015

Packet Encapsulation structure

Special Presentation at Massey

Experimental Results: IoT based Website
Real-time sensor activity for appliance usage

Special Presentation at Massey