Dams dynamic attendance management system

IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308
_______________________________________________________________________________________
Volume: 04 Issue: 03 | Mar-2015, Available @ http://www.ijret.org 417
DAMS-DYNAMIC ATTENDANCE MANAGEMENT SYSTEM
Anita Lahane1
, Tejaswi Rohit Anupindi2
, Vishal Badrinarayanan3
, Ipshita Dutta4
1
Assistant Professor, Computer Engineering, Rajiv Gandhi Institute of Technology, Maharashtra, India
2
Student (B.E), Computer Engineering, Rajiv Gandhi Institute of Technology, Maharashtra, India
3
4
Abstract
This paper describes a project which aims at the implementation of an online student teacher attendance management system
which can act as an efficient means in maintaining proper correct and updated records. With the amalgamation of the various
tools and techniques in data base, data mining and web technologies we can implement an online attendance management system.
Attendance can be accessed anytime and personalized reports can be generated for each student or teacher. This project can also
double as a student teacher portal to share assignments, results and other important notices. An educational institution needs to
have an approximate prior knowledge of enrolled students to predict their performance in future academics. This helps them to
identify promising students and also provides them an opportunity to pay attention to and improve those who would probably get
lower grades. This system which can predict the performance of students from their previous performances using concepts of data
mining techniques under Classification. It tracks all the details of a student from the day one to the end of his course which can be
used for all reporting purpose, tracking of attendance, progress in the course, completed semesters years, coming semester year
curriculum details, exam details, project or any other assignment details, final exam result; and all these will be available for
future references too. This can facilitate us to know which teacher / faculty is assigned to which batch, the current status of a
batch, attendance percentage of a batch and upcoming requirements of a batch.
Keywords: Attendance, Data Mining and Web
--------------------------------------------------------------------***----------------------------------------------------------------------
1. INTRODUCTION
People have always been concerned about attendance
management in big organization. Since attendance plays a
very important role in the working of the organization.
People have used paper and pen to mark the attendance.
This method is very tedious, time consuming and not
interactive. For over decades people have been dreaming
about a better way to manage and view attendance, which is
easily accessible and usable. The goal of DAMS (Dynamic
Attendance Management System) is to bring computer
technologies into attendance management. This would make
the organization’s job for managing attendance more
efficient and easier. DAMS is highly dynamic and easy to
access in nature, any person can access it any time from the
centralized database system and generate required report.
In this project database is used to keep a record of
attendance and also use data mining to generate attendance
management report for individual students. The ability of
updating attendance live makes the system more robust to
check ones attendance.
To provide interaction with a user, we can use a database
server and web interface to mark the attendance of students
for various lectures. This application would also help in
updating the attendance dynamically right when the changes
are made i.e. if attendance of a student is changed by the
teacher, student can view the update right away from his/her
account. With the help of a web site with an easy to use GUI
and all necessary functions with an industrial standard
database system as the backbone to store and process all the
required data for this system, we can achieve great results.
The object under consideration in the project is to identify
areas in the Education System which can be compiled
together with the help of data mining techniques to
determine trends which can be used to improve student
performance.
2. RELATED RESEARCH
Data mining is an exploratory data analysis [12].
[1] This paper gave us insights into how the process of data
mining can be used to gain valuable insights in the
educational sector. Predicting the performance of a student
is a great concern to the higher education managements
[2] This paper helped us in judging the criteria which are
useful and important to determine their usefulness in using
them in our data collection process.
[3] The following paper gave us insights into the various
techniques and algorithms which are effective in classifying
and clustering our data into useful format for our use.
[4] This paper also helped us in gaining more knowledge
and familiarity with the whole process of result prediction
from data mining and generating results for our processing.
3. IMPLEMENTED SYSTEM
With help of good UI and proper database management we
can make attendance management easier to view and
manage. Our System maintains a centralized database for

_______________________________________________________________________________________
the attendance of all students. As the data is readily
available at any time, reports can be easily generated in an
organized form using data mining techniques on the
available data.
 User Friendly: The proposed system is going to be
highly user friendly. The system follows a hierarchal
flow of data hence the process seems more organized
and easy to use
 Better UI: The User Interface of the proposed system
is seamlessly simple and unique, shows the right info
at the right time. With a better UI we can achieve
better usability.
 Notification System: In the proposed system in case
the student’s overall attendance drops below a certain
percentage an email will be sent to the student
reporting his/her current attendance levels in each
subject. Which helps in managing their attendance
better. The system can also be used to send
notification and upload assignments by the professors
even if they aren’t present in the college.
 Computer Operated: Since the whole process is
managed by the computer there will be a minimal
instance of error generation during attendance
calculation and report creation.
 Report Generation: This system can be used to
generate reports on different authorization levels to
judge and evaluate the trends and performance in the
different aspects.
Fig -1: Home page of DAMS system
Fig -2: Features of DAMS system
4. DATA MINING APPLICATIONS IN THE
PROJECT
Data Mining is used as an important tool to determine trends
and helps in characterizing data into suitable format to be
used in the application.
In this project the major applications of Data Mining will
be:
 Identifying student attendance trends: By analyzing
the data obtained from the attendance we can
determine the number of students present for a
particular lecture at a particular time of the day. This
can help in generating better schedules so as to
improve both student performance and attendance in
the specified subject.
 Predicting the possible result of the students in a
particular subject: Our database collects all the
information of the student regarding the previous
performance of the student and by comparing it
against the present performance it can help us predict
the possible outcome of the student and hence
develop strategies to combat the outcome.
 Constructing Student Profile: This can be used by
teachers in scheduling extra tutorials and extra
guidance to be provided to students who are expected
to show poor results. It can also be used to develop
various assessment procedures too.
5. DATA MINING TECHNIQUES
Prediction of the outcome of the student in the academic
scenario requires the analysis of various different parameters
and criteria. The model which is to be created after the
analysis requires the inclusion of a variety of variables
involving the academic, social and psychological factors.
Due to current project constraints we have decided to work
only with the academic variables.
Through the extensive research and study of various
literatures and discussions with academic professionals a
few key factors were identified as the most important in the
analysis process. Table I lists out the various attributes
shortlisted for the study to be conducted.
These factors were categorized as input variables for the
data set to be considered for the data mining model. On the
other hand the output variables or the rank values represent
the possible outcomes of the criteria after the classification
algorithm (i.e. ID3 or C4.5) has been implemented on it.
For this experiment before the actual calculations could be
finalized, data from our college was collected. The data set
consisted of students from all branches from all the
semesters over the span of two annual academic sessions.
In the actual project the data collection is done through the
web interface itself in the form of Student Registration form
Fig. 2b. The information to be processed was reviewed by
the academic professionals assisting us with the project.

_______________________________________________________________________________________
The secondary data which involved the variables such as
Attendance and Mid-term marks were obtained by the
teachers who are assigned the particular subject and the
specified class of students under observation. The results
obtained were tabulated in the data base and further
processing was conducted on it.
The domain values of Table 1 of the various attributes are
defined as follows:
 Student Attendance (ATT): This criteria is selected
for the evaluation of student interest in the particular
subject which will be directly proportional to the
number of lectures attended by the student. This
value will also allow us to substantiate weightage to
the student interest and performance and help us in
predicting the outcomes.
This value will be collected in our database against each
student when the teacher takes the daily attendance for her
subject. These values will then combined together for all the
subjects for each student and hence evaluated.
 Midterm Marks (MT): This attribute refers to the
assessment tests conducted by colleges on a regular
basis. This criteria will help us determine the current
progress of the student in the particular subject.
This value will be collected in the format of average of the
test marks and then converted into percentages which will
then be assigned rank values for further evaluation.
 Previous Semester Marks (PS): The value in this
attribute will help us judge the temperament of the
student in the current course of education and give us
another aspect for the evaluation of the student.
 Senior Secondary Exam Marks (SSC): This criteria
has been selected for the benefit of students who
have been inducted into the program recently and
don’t have sufficient values in the other criteria.
This would also help in again predicting future result based
on past performance.
 Higher Secondary Exam Marks (HSC): This criteria
will help us determine the dedicated approach of the
student on his particular interest by helping us
evaluate the interest in the chosen stream of higher
education.
Table 1
Sr
.
N
o.
Data Attributes to be used for mining
Criteria
Variab
les Grade
1. StudentAttendance ATT
{>90% -- 10
75% - 90% --
8
60% - 75% --
6
40% - 60% --
4
<40% --1 }
Sr
.
N
o.
Data Attributes to be used for mining
Criteria
Variab
les Grade
2. Midterm Marks MT
{>90% -- 10
70% - 90% --
8
55% - 70% --
6
40% - 55% --
4
<40% --1 }
3.
Previous Semester
Marks
PS
{>80% -- 5
70% - 80% --
4
60% - 70% --
3
50% - 60% --
2
<50% --1 }
4. Senior Secondary Exam SSC
{>90% -- 5
75% - 90% --
4
60% - 75% --
3
35% - 60% --
2
<35% --1 }
5. Higher Secondary Exam HSC
{>90% -- 5
75% - 90% --
4
55% - 75% --
3
35% - 55% --
2
<35% --1 }
Table 2
Sr.
No.
Rank values of attributes to be used in the
Mining Model
Criteria Rank Values
1. ATT 0.42
2. MT 0.28
3. PS 0.19
4. SSC 0.05
5. HSC 0.06

_______________________________________________________________________________________
5.1 Implementation of the Mining Model
WEKA is an Open Source Software which is a collection of
a variety of algorithms for use in Data Mining Applications.
From the student data set various database files are created
and from teacher data set different database files are created
which were subsequently loaded into the WEKA explorer
for analysis and generation of the required reports. A variety
of algorithms which along with rank values Table II
assigned to them were applied to the data sets to determine
which algorithms worked best and provided the most
suitable results.
6. CONCLUSION
Fig.3 shows the login page of the website wherein registered
students and teachers can access their respective dashboards
and retrieve information. They can also change update
modify the values depending upon their fixed usage.
Fig.4 shows the parts of the student dashboard or homepage
where the total aggregate of his attendance and the uploaded
assignments can be viewed.
Fig.5 displays the chart which can be used to compare the
values of attendance between selected numbers of students in
various subjects.
Fig -3: Login Page of DAMS System
Fig -4: Dashboard of Student System
Fig -5: Comparison chart of Subject and attendance
7. FUTURE SCOPE
Our application has immense scope of development in the
future. Some of the points that can be taken into account at
that point of time are:
 This project can further be developed by using a
camera based facial recognition technique for taking
the attendance of the student. This would reduce
manual work to a minimal level.
 We can add biometric scanner for taking the
attendance. It would need additional hardware to be
implemented.
 Voice recognition based attendance management.
The system will mark the student’s attendance when
he/she gives the roll call.
 We can add a GPS tracker to the student mobile
system to keep a check on his present location.
ACKNOWLEDGEMENTS
We wish to express our sincere gratitude to Dr. U. V.
Bhosle, Principal and Prof. S. B. Wankhade, H.O.D of
Computer Department of Rajiv Gandhi Institute of
Technology for providing us an opportunity to do our
Project work on “Dynamic Attendance Management
System“. We sincerely thank our guide Ms. Anita Lahane
for her guidance and encouragement in successful
completion of our work.
REFERENCES
[1]. V.Ramesh, P.Parkavi and K.Ramar, “Predicting student
performance: A statistical and data mining approach,”
International Journal of Computer Applications (IJCA), vol.
63-No.8,February 2013
[2]. P.Meena Kumari, SK.Abdul Nabi and Puppal
Priyanka,”Educational data mining and its role in
educational field,” International Journal of Computer
Science and Information Technologies(IJCSIT),vol.
5(2),2014

_______________________________________________________________________________________
[3]. P.Veeramuthu and Dr.R.Periaswamy,“Application of
higher education system for predicting student using data
mining techniques,” International Journal of Innovative
Research in Advanced Engineering(IJIRAE),vol. 1 issue
5,June 2014
[4]. Dr.Mohd Maqsood Ali,”Role of data mining in
education sector,” International Journal of Computer
Science and Mobile Computing(IJCSMC),vol 2,issue
4,April 2013
[5]. Suchita Borkar & K. Rajeswari, “Predicting Students
Academic Performance Using Education Data Mining”,
IJCSMC, Vol. 2, Issue. 7, July 2013, pg.273 – 279
[6]. Kumar, “An Empirical Study of the Applications of
Data Mining Techniques in Higher Education”. IJACSA -
International Journal of Advanced Computer Science and
Applications, 2011
[7]. Ajay Kumar Pal & Saurabh Pal,“Data Mining
Techniques in EDM for Predicting the Performance of
Students”,2009
[8]. Surjeet Kumar Yadav, “Data Mining: A prediction for
performance Improvement of Engineering students using
Classification”, World of Computer Science and
Information Technology Journal (WCSIT), 2006
[9]. J. R. Quinlan, “Introduction of decision tree: Machine
learn”, 1: pp. 86-106, 1986
[10]. Quinlan, J.R. “C4.5: Programs for Machine Learning“.
Morgan Kaufman. 1993
[11]. Lior Rokach & Oded Maimon,”Decison
Tree”,Department of Industrial Engineering,Tel-Aviv
University,2009
[12]. Olsen L.David and Delen,Dursun,”Advanced Data
Mining Technique”,2008,Springer
[13]. David McG. Squire,” The ID3 Decision Tree
Algorithm”,Monash University Faculty of Information
Technology, 2004

Dams dynamic attendance management system

More Related Content

What's hot (19)

Similar to Dams dynamic attendance management system (20)

More from eSAT Journals (20)

Recently uploaded (20)

Dams dynamic attendance management system