Transcript Two-Phased Approaches to Load Balancing in Cloud Computing

Detecting Intrusion in Large
Farm Lands Using Virtual
Fences
Ajayi, O.O & Olaifa, O.O.
Department of Computer Sciences
University of Lagos
Abstract
Farm lands and plantations in Nigeria are usually very large in size and
can run into hundreds or thousands of acres.
Constructing fences along these large expanses of land can be
prohibitively expensive and sometimes ineffective as intruders can
easily jump over them or drill holes in them.
This work proposes the use of virtual fence - an IoT based intrusion
detection system that uses active sensors to detect the presence of
intruders for monitoring purposes.
With collected information, farmlands owners can know precisely
when and where to deploy or intensify measures.
We deployed motion sensors around specific locations and logged the
data generated. Obtained results are then presented.
2
Order of Presentation
• Introduction & Problem definition
• A Potential Solution
• IoT: Definition & Applications
• Virtual Fences: an Application of IoT
• Proposed Solution
• Results & Discussion
• Conclusion
3
Introduction
Farm lands and plantations in Nigeria are usually very large in size running into
hundreds of acres and in most cases fencing these large expanses of land can be
prohibitively expensive. Farmers therefore result to building fences using sticks and
ropes and these provide the only security measure.
These security measures are trivial and very ineffective as intruders can easily jump
over them and cart away with as much crops as they can carry without the
knowledge of the owners; especially when such fences are built around dark
crevices.
As agriculture and crop farming have the potentials to boost the National economic,
security and safety of crops is therefore imperative.
4
A Potential Solution
• To overcome this challenge, we propose the use of
virtual fences.
• A virtual fence is simply a bounded enclosure around
an area of interest without the use of any physical
barrier (Umstatter, 2010).
• It is an application of Internet of Things (IoT) in Smart
Farming (Beecham Research, 2014).
5
What is IoT?
• The concept of IoT is not really new, but it has in recent times
become a recurrent buzz word in the world today.
• IoT in the simplest form is about providing intelligence and
autonomy to everyday objects within our surrounding.
• McKinsey defines it as sensors and actuators connected by
networks to computing systems. (McKinsey, 2015).
• IoT is a network of objects that have been embedded with
components that enable them perform preset actions, retrieve
and exchange data over an IP network with little or no human
intervention (ITU, 2015).
6
IoT & Its Applications
• IoT provides the ability to monitor and manage objects
electronically and through the Internet. It has seen applications
in energy management, health care, home, factories and cities at
large.
• From intelligent fridges to automatic kettles, smart TVs to
motion triggered lamps to heart rate monitors,
• The applications of IoT is limited only by our imagination.
• Some of the most common application areas are summarized as
follows:
7
IoT Application…
8
IoT Analytics, 2015
IoT Application…
9
IoT Analytics, 2016
Virtual Fences:
An Application of IoT
11
Approaches to Virtual Fencing
A virtual fence is simply a bounded enclosure around an area
of interest without the use of any physical barrier
• Geo-fencing: GPS based fencing approach that uses
geographical co-ordinates to determine approximate
locations to regions or places of interest.
• Beacons: These simply broadcast signals that can be used to
trigger pre-defined actions. These does not determine
location like geo-fencing but act more like triggers.
• Hybrid: A combination of both approaches. It has the
advantage of location based and detection / triggers.
12
IoT Virtual Fences: A Literature Review
Authors
Summary of work
Butler, et al., 2006 The authors presented a technique for guiding grazing
cows through dynamic routes using IoT based virtual
fences as pathways.
Goyal, et al., 2012 A comparative study of four fencing techniques was
carried out: brick, electric, GPS based virtual and RF based
virtual fences. The author concluded that a hybrid brick +
virtual fences was most ideal
Felemban, 2013
Implemented a perimeter monitoring platform using pairs
of Infra Red sensors
Chan, et al. 2014
Studied the potency and range of Radio Frequency based
virtual fences in indoor & outdoor conditions with results
in favour of indoor conditions.
McKinsey, 2015
Reviewed the potential economic value of IoT and its
integration into numerous aspects of daily life.
13
Our Proposed Approach
To solve the challenge of security of crops within large farmlands,
we propose the use of virtual fences. These are made up:
• A motion sensor: a Passive Infra-Red (PIR) sensor.
• Micro-controller: This provides an interface between the IP
network and the motion sensor. An Arduino controller was used.
It read data from the PIR sensor and sends same to a remote
database through the connected IP network..
• Internet Connectivity: A WiFi shield was installed on the Microcontroller to provide Internet access to our system. A GSM
adapter with a SIM card installed could also have been used to
provide Internet access, should the install location be outside
WiFi coverage zones.
• Database: All received information are stored on the database. In
our work, we used the Microsoft SQL Sever.
14
Fig. a.
Fig. a. Experimental
deployment of a virtual
fence along the perimeters
of a lawn.
Fig. b.
Fig. b. Sensor unit: Micro
Controller + PIR + WiFi
Shield
15
Proposed Approach Contd.
• For experimental purposes, a lawn was used to simulate a
farmland with sensor modules placed around the perimeter of
the lawn.
• Signs carrying the message “Do not cross the lawn, Use the
Pathways” were installed right at the edge of the lawn.
• We chose this area because people are fond of walking across
lawns rather than on the provided pathways. This we believe is
analogous to intruders crossing in through wrong paths.
• Once anyone crosses the path, the PIR senses a break and sends
a “HIGH” signal to the micro-controller, which in turn updates
a remote database onto which it is connected.
• Timestamp and sensor id are included in the message stored on
the database.
16
Obtained Results
Data logs extract
Results & Discussions
• Our experiment show that people walked across the lawn and
these passages were detected and recorded by the sensor
modules. It therefore means that the use of sensors similar to
ours can be used to detect intrusion with data logged for future
analysis.
• Relevant information such as time of the day, locations and
possibly distance were also logged.
• Over a period of time and with a large number of sensors, the
data gathered can be extremely large. Information Retrieval
tools can be used to normalize the data and extract relevant
information which can then be used to make intelligent
decisions; such as when and where to intensify security
measures in a bid to cub theft or other related malicious
activities being experienced.
18
Conclusion & Future Work
• In this work, we have shown that it is possible to use virtual fences to
monitor perimeters and at a low cost.
• Our proposed system is relatively cheap and therefore can offer
tremendous advantages in terms of cost savings when compared to
building high brick fences and employing security personals to
patrols the entire perimeter.
• These modules can be installed along the entire perimeter to provide
discreet remote monitoring.
By ways of improvement on this work,
• Sonar sensors which give information about the exact distance the
intruder is from the sensor could be used in place of the PIR sensors.
19
• Other sensors which are able to read heat signatures could be used to
determine if the intruder is human or animal.
References
• Beecham Research (2014) Towards Smart Farming: Agriculture Embracing the IoT Vision. Available
https://www.beechamresearch.com/files/BRL%20Smart%20Farming%20Executive%20Summary.pdf
(visited 26/05/2016).
• Butler, Z., Corke, P., Peterson, R. and Rus, D. (2006) From Robots to Animals: Virtual Fences for
Controlling Cattle. International Journal of Robotics Research, Vol. 25, No. 5-6, pp 485-508.
• Chan, H., Rahman, T. and Arsad, A. (2014) Performance Study of Virtual Fence Unit Using Wireless
Sensor Network. 8th Intl. Conference on Sensor Technology, Liverpool, UK, pp 534–537
• Felemban, E. (2013) Advanced Border Intrusion Detection and Surveillance Using Wireless Sensor
Network Technology, Intl. Journal. Communications, Network and System Sciences, Vol. 6, pp 251259
• Goyal, V., Mudgil, A. and Dhawan, D. (2012) Design and Implementation of Virtual Fencing using
RF modules, Intl. Journal of Engineering Research and Technology.
• ITU (2015) Internet of Things Global Standards Initiative. Available at http://www.itu.int/en/ITUT/gsi/iot/Pages/default.aspx. (visited 26/05/2016).
• IoT Analytics (2015) The Top 10 IoT application areas – based on real IoT Projects Available at
https://iot-analytics.com/top-10-iot-project-application-areas-q3-2016/ (visited 26/08/2016).
• Umstatter, C. (2010) The Evolution of Virtual Fences: A Review. Computer and Electronics in
Agriculture, pp 10-22.
20
Thank You