Indroduction

The devices which comprise an AI-powered Home Automation system should be able to
provide services both to each other and to the end user – and continuously acquire new data
for further learning.

The key part of such solutions constitutes a data analytics module where raw sensor
readings are processed and data patterns are identified, so the system knows event A (a
home owner unlocks the front door) is usually followed by event B (the heating is turned up).

With those data patterns, a Smart Home system should be able to predict a user’s behavior
based on historical data and develop the so-called situational awareness – i.e., understand a
user’s intentions at a given moment and change parameters accordingly.AI i.e Artificial
Intelligence is the future . Due to the ever expanding applications of AI, it’ll not only
change our workplace but will also change the way we live in our homes.

According to Cisco, connected home applications such as home automation,

home security and video surveillance, connected white goods, and tracking
applications, will represent 46%, or nearly half, of the total M2M connections
by 2021.

The availability of smart electronic devices is on the rise which can be

controlled by apps through smartphones and tablets. But when you have
multiple smart devices, do you want to juggle between different apps to operate
multiple appliances like TV, oven, entertainment system or air conditioning? I
believe you don’t.

Gadgets like Amazon’s Echo and Google home connects different devices to
each other through the Internet of things (IoT) by voice command, that’s called
a Connected home, but AI driven Home Automation is a step further.

Index terms -AI , Machine Learning , Data Mining , IOT

ABSTRACT
Home automation and Internet of Things are gaining popularity nowadays. In
today’s world, Automatic systems are being preferred over the manual system.
A Smart home automation system is based on making user life easier. The
Internet of Things generates a huge amount of data. Additionally, it contains a
huge number of sensors and their data which can control or monitor objects.
This paper verbalizes about how big machine learning and data mining can be
used for converting the normal home automation to the smart home
automation system. Here the user of this system can control their home using
their smartphone as well as computer or any devices which are connected to
the internet. And also get suggestions [using prediction algorithm], reminder,
and alerts additionally system interact with user.

References

REFERENCES
[1] Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data.
Heidelberg: Springer-Verlag, 2007.

[2] U. M. Fayyad, G. Piatetsky-Shapiro, and P. Smyth. From data mining to

knowledge discovery in databases. In AI Magazine.

[3] Data Mining: Concepts and Techniques. Morgan Kaufmann Publishers

Inc., 2005.

[4] A. K. Jain, M. N. Murty, and P. J. Flynn. Data clustering: A review. In ACM

Computing Surveys.

[5] B. I. Ahmad, F. Yakubu, M. A. Bagiwa, and U. I. Abdullahi. (2011). Remote

Home Management: An alternative for working at home while away. World of
Computer Science and Information Technology Journal (WCSIT), 1(4), pp.
144–147.
Link: http://ieeexplore.ieee.org/document/7575868
Author
Daniel Bishop
Daniel Bishop started off as a content consultant for small SEO and web design companies. Eventually,
he found his place as a junior editor for Design Rush, a B2B marketplace connecting brands with
agencies. Always searching for new opportunities, he loves sharing ideas with other professionals in the
digital community.

Steps

Many of the most exciting high-tech projects nowadays

include bringing together knowledge from two or more
well-established and fast-growing fields. One of the
prominent examples is applying machine learning in order
to filter and analyze the huge amount of data we obtain
from the Internet of Things (IoT). But first, let’s see why
IoT needs help from artificial intelligence in order to reach
its full potential.

Machine learning
Machine learning research is one of the most important efforts being made in the
broader field of artificial intelligence. In short, machine learning scientists and
engineers are trying to replicate the process of learning as it is displayed in humans.
This project demands imagining thehuman brain as a very powerful computer, with the
input being a combination of a number of external signals, and output being the
summation of these signals, or in other terms, a concrete action or process in the
human body that follows as a reaction to the input signals.
Now, for humans, learning means that the same input (signals) won’t always result in
the same output (behavior, action or process), as physical neural pathways are
changing and adapting according to the experience and feedback. Speaking in machine
terms, learning means independently updating the algorithm that decides how input
signals are calculated and how the output is determined.
And when we say that some software are capable of learning, that means that they are
able to update this algorithm themselves, based on previous results and feedback
(“experience”). In short, the software is given the objective and the raw data, while
finding the right algorithm that will result in satisfying the objective is their job. With all
this in mind, how can machine learning be used to help the IoT industry?
SEE ALSO: Are PKIs the key to securing the IoT?
Data analysis automation
The biggest benefit that machine learning brings to IoT is the automation of analysis
of colossal amounts of generated and exchanged data. Instead of a human data analyst
going through all these data manually, looking for patterns and anomalies, with
properly implemented machine learning we can use a completely reversed top-down
approach in analysis. In other words, given some desired outcome, the machine should
find the factors and variables that are supposed to lead to this outcome.
Predictive analysis
By gradually recognizing regular patterns andupdating the algorithm, software
becomes able to predict incoming desired or undesired events. A system, though often
supervised by a human scientist or engineer, is then automatically triggered by relevant
input data, using a formula that it came up with basically by itself. It can easily
recognize anomalies and inconsistencies that may have taken a human data analyst
ages to discover just by looking at the raw data.
Furthermore, a machine-learning system is not there just to recognize abnormal
behavior, but also to help us understand and establish long-term trends. This requires a
huge job of selecting, recognizing, sorting, processing and associating a vast amount of
collected data in order to makemeaningful and comprehensive predictions.
Prescriptive power of machine learning
Finally, these systems don’t just have the predictive power, but prescriptive as well.
Namely, the fact that they can predict future events based on the algorithms they build
also means that they can help in making devices and systems at the edge of the IoT
network more efficient. They can provide assistance not just with making predictions
about what will happen, but also with determining which factors and parameters
should be changed in order to get closer to the desired outcome.
Examples for this are numerous and there’s no doubt that more and more of the custom
software development companies will turn to machine learning solutions to improve
IoT analysis for their clients. One of the most well-known examples involves Google and
their cooling system. The company’s engineers set up a number of sensors that
monitored 120 different factors that could affect the cooling (pump speeds, fans, power,
windows etc.). Successful analysis of this data was ensured by software equipped with
machine learning abilities.
The result? An outright success. The system that monitored these variables came up
with a model which was so well-optimized that it reduced Google’s cooling expenses by
a staggering 40 percent. This task probably could’ve never been done so quickly and
efficiently by a human data analyst using traditional methods.
SEE ALSO: How machine learning is changing the travel industry

Data Management
Data management layer is most important part of this functional architecture.
It manages all data which are produced directly on indirectly by sensors. it
collects data which are produced by sensors and then its store this data in their
respectively databases or cloud platforms. And this data is useful for data
analysis layer.

Data Analytics
Data analytics layer is responsible for analysis data which are produced by
sensors and give appropriate or understandable format or graphical
representation. In this layer, we are finding patterns with past data or analysis
and compares with past analytical data and produced some predictable
moments of end-user

User Interface UI
In our architecture, their are two types of user interface available, Enduser
interface and Analysis Interface. End user interface contains all functionality
which is operated by users like user can turn on or off any fan or light using
this interface. End user interface directly connected with the user. Another one
is analysis user interface which provides all analytical data and their graphical
representation which produced by sensors. In this interface, we can configure
all configuration of our system.
DATA PROCESSING ARCHITECTURE

T his figure shows the flow of the data processing architecture. First, we can

get collect data from the physical world using different types sensors like LDR
can meager light density, LM35 can meager temperature and etc. Then in the
second step we can preprocess that data and convert into meaningful
information. Machine learning and data mining can use this information to
understand the user’s activity and find some appropriate patterns. Lastly its
make Decision on considering all parameters.
DIFFERENT LAYERS OF ARCHITECTURE

Data collection
The data collection layer provides functionality to accumulate any data
produced by devices present in the environment. Sensors and devices can push
their data into database For instance in the home automation smart-home
solution they send events messages containing their identifier, the type of data
they produce and the value of the data. Events are occurring whenever the
value measured has changed since the last emission.

Data Storage
According to our study, we have to perform data mining and machine learning
algorithms, once we collect the data, we need to store their data into a
dedicated database or cloud platforms. According to the volume of data to be
the store we might need big data storage solution or standard relational
database. In internet of things, there are a huge amount of sensors. Home
automation each event issued by their devices or sensors readings.

Data Preprocessing
When we want to apply Data analytics techniques or machine learning
algorithms Firstly we have to clean the data which are produced by the sensors
or devices/modules. We have arranged this data in a standard form which is
applicable to all data produced by different sensors. We have to define which
data are important and which data are ignorable. After data preprocessing
process we made an understandable database which is useful in next layers.

Data visualization
Visualizing data is an efficient and potent way for the terminus utilizer as well
as for the accommodation provider to get an expeditious insight of the health
status of the contrivances as well as of activities taking place in the habitation
when of course, all contrivances operates correctly.
Data mining
Data mining is the process of finding a meaningful pattern out of a large data
repository. In data mining task aims at discovering frequent part from a
sequence of events. The benefit of identifying frequent part is we can evaluate
the daily routing of the user. This approach has been useful to identify and
predict the user activity.

Clustering: This task aims at grouping elements from an astronomically

immense set of elements so that the elements inside the same group are more
akin to each other, then element belonging to different groups.

Machine learning
Machine learning and data mining can give an important role to make any
normal home automation to the smart home automation system. Its help to
predict user activity.

Machine learning has a remotely homogeneous objective than Data mining

with the difference that the patterns found are executable structures which can
be applied to a fresh data in order to predict future data or infer incipient data

Classification: This task aim at appropriate determine a category to which a

given observation belongs. The approach makes use of a training set containing
observations correctly classified.

Regression: It is similar to the classification task in the case where possible

values for the category are numerical instead of categorical. In the context of
the Smart Home, a decision could be made on how to adjust the heater
thermostat predicated on the same sensors quantifications.

CONCLUSIONS

R ecently, the home automation and IoT (Internet of things) market are

growing very fast and need vast range of development that can be carried out
in the concept of smart home-automation. In our paper, we are trying to give
more automation using machine learning and data mining concepts. Here we
are trying to predict user activities and gave appropriate suggestion to the user.
Our motive to provide more comfortable and convenience system for the smart
user.

Examples

Some examples of IoT, Big Data, and machine learning working together include:

 Health care: continuous monitoring of chronic diseases

 Smart Cities: traffic patterns and congestion management
 Manufacturing: optimization and predictive maintenance
 Transportation: optimizing routes and fuel consumption
 Automobile: smart cars
 Telecom: anomaly detection
 Retail: location-based advertising
The main objective of this project is to build a smart home device which can be used to control the
home appliances via internet. The home automation device that you build can be integrated with almost
all the home appliances and can be used to control them remotely from any part of the world.

To facilitate the wireless connectivity with the system, the Arduino Uno will be embedded with a WiFi
module. This establishes the internet connection to the system and all the home appliances can in turn
be connected and controlled by

The device can also be connected to an Android App which you can develop on your own using some
applications like MIT App inventor etc. By using this app, you will be able to monitor and control the
home appliances from any part of the world with ease.

You can also include a PIR sensor with this project to make it switch ON automatically the appliances
whenever a person enters the room and switch OFF the appliances whenever the person leaves the
room.

Project Description:

Arduino Uno: The digital and analog input/output pins are equipped in boards that may be interfaced to
various expansion boards and other circuits. Serial communication interface is a feature in this board,
including USB which will be used to load the programs from computer.

Voltage regulator: It is used to maintain a constant voltage level and also used for regulating AC or DC
voltages. A voltage regulator contain negative feed-forward design or it may also contain negative
feedback control loops.

WiFi Module: ESP8266 WiFi module is generally used to establish the wireless communication between
the devices. But this module is not capable of 5-3V logic shifting and will require an external logic level
converter.

PIR Sensor: It is capable of sensing motion of the human and therefore it is also called as a motion
sensor. Whenever a human pass through this sensor it will automatically sense the motion through IR
radiation and send the data to the microcontroller.

Relay Driver (IC ULN2803 APG): The relay driver IC that you use will have the following characteristics,
500-mA rated collector current, High voltage outputs – 50 V, Output clamp diodes, Inputs compatible
with various types of logic.

Project Step 1: In order to establish connection between the client and the server, the Wifi option in the
Smartphone is enabled

Step 2: It is connected to the Wifi module of the system

Step 3: Each electronic/electrical appliance in the system is connected to the digital pins on the Arduino
Uno Board

Step 4: A Relay is used for connecting each device to the Arduino, which helps in converting high Voltage
supply to low voltage

Step 5: A C-program is loaded on to the microprocessor chip on the Arduino Uno Board which specifies
what action is to be performed on receiving particular inputs

Step 6: An Android Application has been developed which enables the end user to monitor and control
the appliances from any remote location

Step 7: Socket Programming has been used to achieve client-server communication

Step 8: Successful controlling and monitoring of appliances

Project You need to use USB to serial converter that allows the system operation at 3.3V. You can
connect the pins of the ESP8266 module via jumper wires to the corresponding pins on the USB. The
Arduino Uno connected with ESP8266 WiFi module is used to implement the micro web server for the
home gateway. A conventional light switch will be integrated with the Arduino using relay driver module
to demonstrate the switching capability. This hardware architecture is very flexible and allows other
home appliances and devices to be seamlessly integrated with minimal changes

Programming language: Arduino Programming (C++)

Kit required to develop Home Automation using IOT and Arduino:

Arduino Uno

ESP 8266

WiFi module

Relay Driver

Technologies you will learn by working on Home Automation using IOT and Arduino:

IOT

Automation Technologies