Smart Classroom Monitoring using Machine Learning and IoT

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 05 | May 2023 www.irjet.net p-ISSN: 2395-0072
© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 324
Smart Classroom Monitoring using Machine Learning and IoT
Niveditha S
1
, AnushreeN D
2
, ChaithraShree A V
3
, Likhitha M C
4
, Yogitha R
5
1
HOD and Assistant Professor , Department of Computer Science and Engineering, Jnana Vikas Institute of
Technology, Karnataka, India
2
Undergraduate Student, Department of Computer Science and Engineering, Jnana Vikas Institute of Technology,
Karnataka, India
3
Karnataka, India
4
Karnataka, India
5
Karnataka, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Students are more willing to adopt creative
teaching techniques and demand innovative university
campus life in this era ofsmart classroom technologies. IoT
and cloudcomputing technologies can offer solutions for a
smart and sustainable campus to enhancestudents' learning
processes and boost the effectiveness of routine tasks carried
out within the institution. This project focuses on integrating
the cloud into the educational processusing the IoTparadigm.
IOT in education enables students to study cutting-edge
technologies that aid in the development offreshconceptsand
rational solutions to societal challenges. Using online portals,
PDA users can view their homework assignments and test
results. Online video lectures allow studentstoremotelyjoinin
on class lectures thanks to the ability to upload videos to the
cloud. Information sent to and from sensor modules is
processed by the software module before being sent to cloud
storage.
Key Words: microcontroller board, sensor, wireless and
wired interfaces, software module, cloud storage.
1.INTRODUCTION
Universities have recentlybegun to focus on Internet
of Things and cloudcomputing to create smart campuses.
A SmartCampus connects many peripherals,infrastructure,
and facilities to provide smart lighting, security, tracking,
and effective use ofresources like manpower, electricity,
water, etc. According to the traditional classroom model,
managing the classroom's daily operations and teaching
must take up equal amounts of time. Tohandle the workflow
that drastically reduces theamount of time faculty have to
devoteto It extends the amountoftimespentinstructing and
interacting with students. This project demonstrates a
technique that uses cloud computing,IoT,andanapplication
development platform to lessen secondary human labour.
Additionally, it has automatic fan and light on/offfunctions
that are based on the ambient conditions. With this
approach, teachers wereable to concentrate more on what
they do best— teaching—and less on running the
classroom's daily operations.
2.LITERATURE SURVEY
2.1 Services Computing System Based on Smart
Classroom
Published in: ICT for Smart Society 2019 International
Conference (ICISS))
Abstract : In order to give its learning methods using AI-
based technology, a smart classroom blends traditional and
correspondence learning. Its goal is to support both
synchronous and asynchronous learning. In order for
teachers and students to apply a variety of teaching
strategies, engage in active learning, and share knowledge,
the smart classroom also makes use of the connectivity of
smart devices.
2.2 Smart classroom: A universal classroom's
entrance design
Published in: 2014 International Conference on Web and
Open Access to Learning (ICWOAL)
Abstract: Today new techniques and researches in
computers helped us to shift from conventional educationto
smart classroom. The pupils should be able to cooperate
with one another using laptops, tablets, or other technology.
2.3 Automatic Light Switching and Temperature based
fan speedcontrolusingmicrowave.temperatureand
LDR sensor.
Published in: 2021 International Research journal of
Engineering and Technology(IRJET).
Abstract: Because it provides necessities, comforts, and
conveniences, energy use has decreased; as a result, we
dislike its use The approach for automatic lighting system

and temperature equipment switching will be covered in
detail in the paper that follows.Itentailsmonitoringsunlight
intensity, detecting human presence, and regulating fan
speed in accordance with ambient temperature. Our design
may be broken down into three different categories: a
human detection circuit using a microwave sensor, a light
detection circuit using an LDR to detect sunlight, and a fan
speed control system using a temperature sensor and
associated switching circuits.
3.METHODOLOGY
The word "Smart Classroom" is used to describe a
classroom that been outfitted with technology to support
preaching. We frequently see that the instructor spends a lot
of time from the time they enter the class until they leave it
on secondary tasks like taking attendance, which can take a
long time (especially in classes with more than 60 students),
and then changing the lighting in the room, among other
things. The teacher is thus only given a portion of theallotted
time, which is frequently not enough. The greatest way to fix
this problem would be with smart classrooms.
The secondary duty might be finished in a very little
amount of the allocated time with the help of a smart
classroom, making it easier for teachers to focus on their
primary task of teaching. With the use of the facial
recognition system, it allows the teacher to trackattendance.
as well as manage the lighting and projector. The study
materials are even accessible to pupils via email. Ouridea for
a simple smart automation system can do everything from
recording attendees' attendance using facial recognition to
regulating the electrical devices in the space. It has occurred
to us to create an Android-based application that would be
essential for performing numerous tasks, like taking
attendance and managing the lights in the room. The routers
that must be put in each classroom and lecture hall would
allow this programme to run on the local server. This
application would be accessed by the academic staff. The
installation of a camera in the classroom is necessary,among
other things, for facial recognition to track attendance.There
would be a system for students in addition to the teaching
flank. Each student would receive the study materials via
mail after a predetermined amountof time. In a folder they
wish the pupils to have access to, the teachers upload the
materials.
4.ARCHITECTURE DIAGRAM
Fig-1 Hardware Architecture
Arduino : An open-source piece of hardware and software
called Arduino makes single-board microcontrollers and
microcontroller kits that may be used to build interactive
objects and digital devices that can sense and control things
in both the real world and the virtual one. Use of the open-
source hardware and software created by the project is
governed under the GNU Lesser General Public Licence
(LGPL).Commercially, Arduino boards are available as
assembled products or as kits designed for a specific
application. The Arduino Uno board and pin diagram,
respectively.
There are other variations of the Arduino Uno, including the
Arduino Nano, Arduino Pro Mini, Arduino Mega, Arduino
Due, and Arduino Leonardo.
Fig -2 Arduino Uno Board

Fig-3 Arduino Uno board pin diagram
Wi-Fi: enables the operation of local area networks without
wires and wiring.
Relay: A relay is a switch used to manage circuits. An
electrically controlledswitch isa relay.Mechanical switching
is often operated by an electromagnet in relays. It is a 5-
terminal gadget with 1 coil inside. A slit moves from one
point to another when the coil is activated.
LDR: Light Dependent Resistors (LDR) are used to measure
light intensity or to signal thepresence or absence of light.
Particularly in light/dark sensor circuits, LDRs, or light
dependent resistors, are particularly valuable. These aid in
automatically turning on and off lights, such as streetlights,
etc. Normally, an LDR's resistance is very high—up to
1,000,000,000 ohms—but when it is illuminated by light,
that resistance drops sharply. Electronic opto sensors are
objects that change their electrical propertieswhen exposed
to visible or infrared light. The light dependent resistor
(LDR), photo diode, and phototransistors are the most
popular products of this category.
Open CV: Open CV is a sizable open-source database. To
recognize items, people, or even human handwriting, one
can process photos and videos.
Open CV (View a picture)
To read an image, use the function cv2.imread(). The image
must be in the working directory or have a complete path
specified.
A flag serving as the second input designates how the image
should be read.
A color image is loaded using cv2.IMREAD_COLOR. Any
image transparency will be disregarded. Thisisthestandard
flag.
• cv2.IMREAD_GRAYSCALE loads the image in grayscale
• cv2.IMREAD_UNCHANGED: Loads the image as is, with the
alpha channel included.
Open CV(Show a picture)
To display an image in a window, use the function
cv2.imshow(). The window automatically adjusts to the size
of the image.
The window name, which is a string, is the first argument.
Our image is the second defense. You can make as many
windows as you'd like, but each one will have a different
look. A keyboard binding function is ncv2.waitKey(). The
time in milliseconds is its main point. The function waits a
predetermined amount of time for any keyboard event. The
programme keeps running if you press any key during that
time. If 0 is passed, it continuously waits for a keystroke.
Additionally, as we will discuss below,itcanbeconfigured to
recognize particular keystrokes, such as if key A is pressed.
Simply put, cv2.destroyAllWindows() eliminates every
window we've created.
Temperature Sensor: A temperature sensor is a device
designed specifically to tells how hot or cold an object is.
The output of the accurate IC temperature sensor LM35 is
proportional to the temperature reading (in °C). The LM35
can monitor temperature more precisely than a thermistor.
It also has capable of minimal self-heating and only slightly
slights the temperature of still air, by no more than 0.1 °C.
The range of operating temperature is between -55°C and
150°C.The LM35 is exceptionally easy to interface with
reading or control circuitry due to its low outputimpedance,
linear output, and perfect internal calibration.
Fig-4 Temperature Sensor

Fig-5 Software Architecture
Automation Will happen based on input from camera. Using
camera we will detect studentsinside the class.
5.ALGORITHM
5.1Haar Classifier:
This framework for object detection aims to deliver
competitive object detection rates in real-time, such as face
detection in an image. A person can accomplish this
effortlessly, but a computer need specific guidelines and
limitations. Full view frontal upright faces arenecessary for
Viola-Jones in order to make the task more feasible.
Therefore, the full face must face the camera and cannot be
slanted in any direction in order to be recognized. Since the
detection stage is typically followed by a recognition step,
these limitations on pose look like they wouldslightlyreduce
the algorithm's utility, but in actuality they are fairly
acceptable the qualities
The Viola-Jones technique is a powerful detection algorithm
because it has the qualities listed below:
a) Robust – Very high true-positive detection rate and very
low false-positive detection rate at all times.
b) Real time – At least two frames per second must be
processed for practical applications.
c) Only face detection, not face recognition – Since detection
comes before recognition, the objective is to tell faces from
other objects.
Features
 An approach of detecting object with Machine
Learning is called Haar cascade.
 A situation where a cascade function is trained
using a sizable number of both positive and
negative images.
 Then, using the training data, it is used to identify
objects in the other images.
 They are large individual.xml files with numerous
feature sets, and each one of them relates to a very
unique kind of use case. This is how it works.
5.2 Histogram of oriented gradients (HOG)
It is a feature descriptor used to identify objectsincomputer
vision and image processing. Using a detection window or
region of interest (ROI), the HOG descriptor technique
counts instances of gradient orientation in targeted regions
of a picture.
The HOG descriptor algorithm is implemented as follows:
1. Calculate for each cell in the image by dividingit
into small, connected areas called cells.
2. A cell's pixel histogram showing the gradientaxes
or edge orientations.
3. Weighted gradient is contributed by each cell's
pixel to the associated angular bin.
4. Blocks are thought of as spatial entities that
consist of a collection of contiguouscells.Histogramsare
normalized and grouped on thebasisofthearrangement
of cells into blocks.
6.IMPLEMENTATION
The implementation of the Hardware and Software. Using
machine learning and IoT, there are various processes
involved in creating the software components for a smart
classroom monitoring system.
6.1 Hardware Implementation:
The hardware includes an LDR sensor for sensing light,
which means that when the humidity is higher or when it is
darker outside, the device will turn on and off as needed.
Other devices, like as a temperature sensor, are used to turn
on and off fans. A few more include an Arduino Uno
microcontroller board, a relay, a power source, an LCD, an
LED, and a fan. The following actions are taken in order to
implement the hardware architecture:
Compile the necessary hardware parts.

1. Attach the power supply, Arduino Uno
microcontrollerboard,andtemperaturesensorandLDR.
Connect the proper pins on the power supply and
microcontroller board with jumpers.
2. In order to display the values that
indicate the changing temperature and humidity,
connect an LCD display to the microcontroller and
power supply.
3. To control a circuit with a separate low-
power signal, connect the relay to the power source, the
LED, and the fan.
4. The Fan now turns on automatically as
the temperature rises and vice versa.
5. The light itself automatically turns on
when the humidity is high and vice versa.
6.2.Software Implementation:
The software component entailscreating an applicationthat
gathers student information, displays thenumberofpresent
and absent students aswell asany lingering questions about
the subject matter of the class. Thesoftwareimplementation
involves following steps.
1. Install the necessary software tools, such as the
OpenCV, Arduino, and Anaconda libraries.
2. The system is broken down into three modules:
database building, dataset training, testing, and
alarm message sending as an addition.
6.2.1.Building Database
a) Restore the camera's default settings and turn on
the alert message to get the students' attention.
b) Obtain the user ID.
c) make the image grayscale and find the face.
d) Store the given input in the database using it as a
label for up to 20 frames.
6.2.2.Training
a) Set up LBPH face recognizer.
b) Use the database file to retrieve faces andIDs for
the LBPH face detect.
c) Hold the learned data as an xml or yml file.
6.2.3.Testing
The Haar classifier and LBPH face recognizer should be
loaded along with trained data from an xml or yml file.
a) Snap the photo using the camera,
b) Change it into gray scale,
c) Recognize the face in it and
d) Using the aforementioned recognizer, predictthe
face.
6.2.4.For raising the doubts :
a) Create a server using telegram app.
b) By using Bot father create a channel.
c) Send the doubts related to the topic covered using
the smart phone through the channel in the
telegram app.
d) The raised questions will get displayed on the
screen or on the projector screen.
6.2.5. Indoor Navigation:
a) Create a server using telegram app.
b) By using Bot father create a channel.
c) Insert a picture related to the place through a
Microsoft word though mapping.
d) As the text arises as to rise the doubt
immediate an option will be provided to selectthe
required location or the place.
e) After giving the option or after selecting the
option the route will be obtained automatically.
Fig-6 Hardware Components

Fig-7 Database Creation
Fig-8 Database entry
Fig-9 Image trained
Fig-10 Doubts Raising.
Fig-11 Creation of the channel.

The IoT-based Cloud Integrated Smart Classroom for
Smart and a Sustainable Campus is a development in the
educational environment that willlead to high efficiency and
effectiveness of the classroom teaching approach. This
technique will increase the community of students' sincerity
in completing their assignments on time. Instead,facultyand
administration may devote more time to teaching and
learning. of controlling and observing the classroom's
workflow. In order to deliver an intelligent, economical, and
environmentally sustainablecampus,theproposededucation
system model. Theautomatedattendancesystem'sobjective
is to reduce mistakes made by the current (manual)
attendance taking system. The goal is to automate and
develop a system that is advantageous to the institution or
other organization. The up-to-date, accurate replacement
for manual techniques thatcan be usedtocollectattendance
in workplaces. This approach is workable, dependable, and
sufficiently safe. Without the need for specialised hardware,
the system can be implemented in the office. It can be made
with a camera and computer. It may be said that a manual
and unreliable method for managing class attendance has
been replaced by one that is dependable, secure, quick, and
efficient. Time will be saved, less work will need to be done
by the administration, and already existing electronic
equipment will take the place of the stationery currently in
The main disadvantage of this is spoofing. In the
upcoming days one method has been brought into force to
overcome the disadvantage like eye blink detection may be
utilized to know the difference between present and still
images if face detection is made from snapshots of the
classroom. Human interventionmight be used to make the
system error-free based on the system's overall efficiency,
which is83.1%. Therefore, a module make a list of all the
unrecognized pictures and enables the teacher to himself
check the attendance. In the future, several organized
attendance registers for each class as well as the ability to
generate itself monthly absents and presents reports and
automatically email them to the necessary employees for
evaluation may be introduced.
Indoor navigation and raising doubts in the conference hall
is also the updated method inside the campus. Where an
unknown person can easily find the route to the location he
has to visit within the short period of time.
Raising doubts lets every student to represent their doubts
without hesitating and also makes the interactionvery easy
between the teacher and the student.
REFERENCES
[1] W. Zhao, R. Chellapra, P.J. Phillips, A. Rosenfeld,
“Face Recognition: A Literature Survey,” ACM
Computing Surveys, Vol. 35, No. 4, December 2003,
pp. 399-458.
[2] M.A. Turk, A.P. Pentland. “Face Recognition Using
Eigenfaces,” IEEE Conference on Computer Vision
and Pattern Recognition, pp.586--591, 1991.
[3] M.S. Bartlett, J.R. Movellan, T.J. Sejnowski, “Face
Recognition by Independent ComponentAnalysis”,
IEEE Trans. on Neural Networks, Vol. 13, No. 6,
November 2002, pp. 1450-1464.
[4] Gottumukkal R., and Asari K.V., “System Level
Design of Real Time Face Recognition Architecture
Based on Composite PCA,” Proc. GLSVLSI 2003,
2003, pp. 157-160.
[5] Hau T. Ngo, Rajkiran Gottumukkal, Vijayan K.
Asari. "A Flexible and Efficient Hardware
Architecture for Real-Time Face RecognitionBased
on Eigenface", isvlsi, pp. 280-281, Proc. IEEE
Fig-12 Showing the route map of selected option.
7. CONCLUSION
use. The system only requires a computer and a camera for
installation, therefore no specialised hardware is required.
Since the camera is necessary for the system to function, it
is crucial to test the image quality and camera performance
in real-world situations ,when the system is connected to
the camera. This type of system can also be used in highly
reputed schools and colleges and also in the home.
VLSI:New
Frontiers in VLSI Design, 2005.
Computer Society Annual Symposium on

[6] P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman,
“Eigenfaces vs. Fisherfaces Recognition using class
specific linear projection,” IEEETrans.PatternAnal.
Machine Intell., vol. 19, pp. 711–720, May 1997.
[7] Moritoshi Yasunaga, Taro Nakamura, and Ikuo
Yoshihara, “A Fault-tolerant Evolvable Face
Identification Chip,” Proc. Int. Conf. on Neural
Information Processing, pp.125-130, Perth,
November 1999.
[8] In Ja Jeon, Boung Mo Choi, Phill Kyu Rhee.
"Evolutionary Reconfigurable Architecture for
Robust Face Recognition," ipdps, p. 192a,
International Parallel and Distributed Processing
Symposium (IPDPS'03), 2003.
BIOGRAPHIES
NIVEDITHA S
HOD & Assistant Professor, Dept. of
Computer Science and Engineering.
ANUSHREE N D
B.E Student, Department of
CHAITHRA SHREE A V
B.E Student, Department of
LIKHITHA M C
B.E Student, Department of Computer
Science and Engineering.
YOGITHA R
B.E Student, Department of Computer
Science and Engineering.

Smart Classroom Monitoring using Machine Learning and IoT

More Related Content

Similar to Smart Classroom Monitoring using Machine Learning and IoT (20)

More from IRJET Journal (20)

Recently uploaded (20)

Smart Classroom Monitoring using Machine Learning and IoT