A

SYNOPSIS REPORT

On

Automated Diploma Result Evaluation System (ADRES)

Submitted in partial fulfilment of the requirements of the

Diploma in Engineering
In
Information Technology
To

Maharashtra State Board of Technical Education,Mumbai

Submitted By :-

Yogesh Chandrakant Kamankar (23)

Pranit Rajendra Adhangle (2)
Aaryan Rakesh Ahirrao (6)
Darshan Vijay Aher (3)

Under the Guidance of

Prof. M.P.Bhandakkar

Department of Information Technology

Matoshri Education Society’s
Matoshri Aasarabai Polytechnic, Eklahare, Nashik
DECEMBER 2024
 Maharashtra State Board of Technical Education,
Mumbai
Matoshri Aasarabai Polytechnic, Eklahare, Nashik

CERTIFICATE

This is to certify that following students of Fifth Semester Diploma Engineering

Program in IT Department have successfully completed the Project-Synopsis Report
" Automated Diploma Result Evaluation System (ADRES) "
under my supervision, in the partial fulfillmentof Course Capstone Project Planning
(22058) for Academic Year 2024-2025 as per prescribed in the MSBTE “ I-Scheme”
curriculum.

Roll No Name Sign

Roll no.02 Pranit Rajendra Adhangle

Roll no.03 Darshan Vijay Aher

Roll no.06 Aaryan Rakesh Ahirrao

Roll no.23 Yogesh Chandrakant Kamankar

Date:- Place:- Nashik.

Signature of Guide Signature of HOD

(Prof. M.P.Bhandakkar) (Prof. M.P.Bhandakkar)
 Index

Ch.No Details Page No.

1 Abstract 1

2 Introduction 2

3 Problem Of Statement 3

4 Objective and scope of the project 4

5 Literature Survey 5-6

6 Hardware & Software to be used 7

7 Methodology 8

8 Application and Future Scope of the Project 9

9 Conclusion 10

10 References/ Bibliography 11
1. Abstract

The objective of this project is to develop an automated system that extracts student
marks from PDF files, organizes the data into a structured format, and performs various
analyses, including calculating the overall passing percentage, identifying toppers, and listing
students who scored above 75%. This system aims to streamline the result analysis process for
educational institutions by automating data extraction, analysis, and report generation.

The system will be developed using a combination of modern web technologies. The
frontend will be built using React.js to ensure a dynamic and user-friendly interface. The
backend logic, responsible for handling API requests and processing the data, will be
developed using Java or Node.js/Express. Student result data will be stored in a MySQL or
PostgreSQL database, allowing efficient data storage and retrieval.

1
2. Introduction

In the academic environment, the process of result analysis is critical for understanding the
performance of students. However, this task is often a time-consuming and labor-intensive process,
especially for teachers. When examination results are declared, teachers are typically required to manually
enter student marks into spreadsheets, perform various calculations to determine overall performance
metrics, and generate reports. This involves not only a high risk of human error but also detracts from the
teachers' primary role of focusing on the educational development of students.

The Automated Result Analysis System aims to alleviate these challenges by automating the entire
result processing workflow. Teachers can upload student result PDFs into the system, which will
automatically extract and organize the data into a structured format. This extracted data will be used to
perform real-time calculations, such as identifying class toppers, calculating the overall pass percentage,
and determining students who scored more than 75%. The system will further generate detailed reports
that can be downloaded and shared.

This project uses a combination of modern web technologies and tools to achieve automation. The
frontend of the system will be developed using React.js, which provides a dynamic and responsive user
interface. The backend will be powered by Node.js/Express or Java, ensuring efficient handling of API
requests and business logic. The data extracted from the PDF files will be stored in a MySQL or
PostgreSQL database, which enables efficient data management and retrieval for further analysis.

For PDF parsing, libraries like PDF.js or PyMuPDF will be employed, allowing the system to
accurately extract text and data from uploaded PDFs. This data will then be mapped to specific students
and subjects. Once the data is organized, the system will enable teachers to filter and segregate results
based on various performance criteria such as top students, those who passed with distinction, and those
who failed. To make the process even more efficient, customizable reports will be generated using
PDFKit, offering users the ability to download reports based on different filters, such as subject-wise or
class-wise performance.This project ultimately serves the dual purpose of reducing the administrative
burden on teachers while improving the accuracy and efficiency of result analysis. By automating
repetitive tasks and ensuring precise calculations, the system allows educational institutions to manage
their result analysis more effectively. The automated process not only saves time but also reduces the
chances of errors, providing a reliable and scalable solution for managing academic performance data.
The Automated Result Analysis System represents a significant leap forward in enhancing the
productivity of teachers and improving the overall educational experience.

2
3. Problem of Statement

• Educational institutions, particularly teachers, face a significant challenge when processing

student results after they are declared. Traditionally, teachers are required to manually enter the
marks of each student, perform time-consuming calculations to identify toppers, determine
students who scored above certain thresholds (e.g., 75%), and analyze overall class
performance. This manual process is not only tedious and error-prone but also reduces the
productive time that teachers could otherwise dedicate to educational activities.

• The primary objective of this project is to reduce the administrative burden on teachers by
automating the result processing and analysis tasks. By allowing teachers to simply upload the
result PDFs, the system will automatically extract and organize the data, perform the necessary
calculations, and generate detailed reports. This automation minimizes errors, saves time, and
allows teachers to focus on their core teaching responsibilities, thereby increasing their overall
productivity.

• In essence, the need for an automated result management system stems from the inefficiency
and stress associated with manual result processing, and the aim is to provide a reliable
solution that simplifies this process while delivering accurate and insightful performance
analytics.

3
4. Objective and scope of the project

Objectives:

o To automate the extraction of student result data from PDF files.

o To store the extracted data subject-wise in a database for easy access and analysis.

o To provide users with the ability to filter and segregate data based on performance categories
(e.g., topper, distinction, fail).
o To generate detailed, customized reports in PDF format based on the analysis of the data.

Scope: The application will cater to educational institutions looking to automate their result
processing. It will allow users to:

o Upload result files in PDF format.

o Parse and store result data in a structured way.

o Provide an intuitive interface to segregate students by performance metrics.

o Enable generation of downloadable PDF reports based on different filters.

4
5. Literature Survey

1. Student Performance Management Systems:-

Existing Solutions: Current systems like LMS (Learning Management Systems) and School
Management Software offer basic result management features, but they typically lack advanced data
analysis, PDF integration, and performance segregation. Research shows that while these systems
focus on general record keeping and assessment management, they often fail to provide in-depth
analytical reports or customizable filters for student performance categories like toppers or failed
students.
2. PDF Data Extraction Techniques:-

Text Mining from PDFs: Research in natural language processing (NLP) and optical character
recognition (OCR) highlights various methods for extracting data from PDF files, which are often
structured differently. Techniques like PyMuPDF and PDF.js have been proposed as efficient tools
for extracting tabular and textual data from PDFs.
3. Database Systems for Educational

Databases such as MySQL, PostgreSQL, and MongoDB are widely used to store student records.
Research has explored efficient ways to store large volumes of educational data, focusing on the
scalability and performance of relational and non-relational databases. The key challenge highlighted
in the literature is ensuring that the database schema is flexible enough to accommodate diverse
grading structures, subject-wise marks, and performance categories.
4. Educational Data Mining (EDM) in Student Result Analysis:
Educational Data Mining (EDM) is increasingly used to predict student performance, identify at-risk
students, and provide personalized learning recommendations. Machine learning algorithms, such as
decision trees, SVMs (Support Vector Machines), and neural networks, have been employed in
various studies to analyze historical data and predict future performance trends. These systems aim to
improve the quality of education by proactively identifying students who may need extra help and
rewarding high performers.
5. Automated Reporting and Result Customization:
The generation of automated reports from educational data is another area of focus. Systems
developed in recent years emphasize basic reporting capabilities, such as generating class averages or
individual student score summaries. However, there are very few customizable options available in
most current systems, limiting the value these reports can provide to teachers and administrators.

5
 Literature Survey In Tabular format

Our Additional
Sr.No Author(s) Year Paper Title Summary Limitations
Features

Our system will

automate result
Proposes an Limited to specific extraction from
Automated System for automated system to result formats; no PDFs of different
1. Singh, P., 2016 process student results structures using
Educational Result Processing support for PDF
et al. using predefined
extraction from advanced parsing
templates.
varying layouts. techniques.

We will automate
Focuses on data extraction
Design and Development of analyzing student Manual data entry is directly from PDF
Patel, A., Student Performance performance but required before result files,
2. et al. 2018 Analytics System lacks real-time data analysis; time- ensuring real- time
extraction from consuming and prone data analysis.
result files. to errors.

Our system will

Emphasizes the enable users to
generation of real- No feature for filter and segregate
Real-Time Reporting in time reports but segregating students students by
3. Gupta, S., et 2019 Educational Result Systems lacks filtering based on performance performance
al. capabilities for metrics (e.g., toppers, categories like
student categories. failures). topper, distinction,
etc.

We will provide
Explores the use of Only basic reports are detailed,
AI for result generated; lacks customizable PDF
Khan, M., Educational Data Processing prediction and customization based reports based on
4. et al. 2020 and Result Management Using processing but lacks on user preferences. user- defined filters
AI customized reporting and analysis needs.
options.

We will design an
Develops a system User interface is not intuitive, user-
for automating result intuitive, making it friendly interface
compilation but difficult for educators that
Sharma, Automating Result
5. A., et al. 2021 lacks a user- friendly to navigate the
Compilation for allows educators to
interface for system.
EducationalInstitutions easily upload PDFs
educators.
and manage results.

6
 6. Methodology

o User Authentication:

o Admin login to manage result uploads and report generation.

o Teacher login for viewing and analyzing class-wise results.

o PDF Upload and Parsing:

o Functionality to upload student result PDF files.

o Extract text from PDFs and map it to respective subjects and students.

o Data Segregation and Filtering:

o Identify and list topper students (highest marks).

o List students who got distinctions in subjects.

o List failed students.

o Provide filters to view data class-wise, subject-wise, or overall.

o Database Management:

o Store subject-wise student marks, grades, and overall performance.

o Support for student profiles linked with their academic records.

o Report Generation:

o Allow users to generate PDF reports based on various performance filters (e.g.,
toppers, failed students).
o Custom report generation options, such as student-specific reports or class-level reports.

Fig:Architecture Digram

7
 7. Application and Future Scope of the Project

Integrate dashboards that provide detailed visual insights such as graphs, pie charts, and trend lines
for student performance across semesters or academic years.
Incorporate predictive analytics to forecast student success or failure based on current and past data.
Subject-wise or student-wise performance comparison to help identify weak and strong areas.

• Machine Learning for Performance Prediction:

For data filtering and analysis, machine learning algorithms can enhance the accuracy of extracted data.
Natural Language Processing (NLP) techniques, such as Named Entity Recognition (NER), can identify
student names and subjects from PDFs.

Support Vector Machines (SVM) or Random Forest can classify students based on performance (e.g.,
toppers, distinctions). K-Means Clustering can group students into different performance categories,
while Decision Trees can be used for automated rule-based classification (e.g., pass/fail, distinction).

• Integration with Other Academic Platforms:

Integrate with Learning Management Systems (LMS) like Moodle or Google Classroom to
automatically pull or push data.
Sync with school management systems for a holistic view of student performance, attendance, and
activities.

• Customizable Grading Schemes:

Implement flexible grading systems that can accommodate different grading structures (e.g., GPA,
percentage, or letter grades) for various institutions.
Allow users to set custom thresholds for distinction, pass, and fail grades.

• Multi-Language Support:

Provide language localization to cater to diverse user bases from different regions and countries.
Make the system more accessible to non-English-speaking students and institutions.

8
8.Hardware & Software to be used

o Frontend: React.js (for dynamic UI and better user experience).

o Backend: Java/Node.js/Express (for handling API requests and logic).

o Database: MySQL/PostgreSQL (for structured storage of student and result data).

o PDF Parsing: Libraries like PDF.js or PyMuPDF (to extract data from uploaded PDF files).

o Reporting: PDFKit (for generating PDF reports from data).

9
9.Conclusion

The Automated PDF Marks Extraction and Result Analysis System is currently in its implementation phase
and aims to significantly streamline the process of handling student results. By automating the extraction of
marks from PDF files, the system seeks to reduce manual data entry efforts, alleviate teachers' workload, and
enhance the efficiency of result management. Although the project is still under development, its integration
of modern web technologies like React.js, Node.js/Java, and MySQL/PostgreSQL lays a solid foundation for
achieving accurate, real-time analysis of student performance, including the identification of top performers
and overall class metrics. Once fully completed, this system will revolutionize result processing in
educational institutions.

10
10.References/ Bibliography

➢ Ishwank Singh,A Sai Sabitha,Abhay Bansal,Student performance analysis using

clusteringalgorithm,2016.
[online] Available: https://en.wikipedia.org/wiki/Student_information_system.

➢ J. Hipp, U. Guntzer & N. Gholamreza (2000), “Algorithm for Association Rule Mining: A
GeneralSurvey and Comparison”, ACM SIGKDD Explorations Newsletter, Vol. 2, No. 1, Pp. 58–
64.
[online] Available: https://en.wikipedia.org/wiki/Systems_analysis.

➢ GB-Zadok, A Hershkovitz, R Mintz & R Nachmias (2007), “Examining Online Learning

Processes based on Log Files Analysis: A Case Study”, Research, Reflections and Innovations in
Integrating Ict in Education, Pp. 55–59.
➢ R. M. Neal. Bayesian Learning for Neural Networks. Number 118 in Lecture Notes in
Statistics.Springer-Verlag, New York, 1996.
➢ V. Vapnik. Statistical Learning Theory. John Wiley & Sons, N.Y., 199.
➢ Singh, P., et al. (2016). "Automated System for Educational Result Processing". [online]
Available: https://ieeexplore.ieee.org/document/7502398.
➢ Patel, A., et al. (2018). "Design and Development of Student Performance Analytics System".
[online] Available: https://www.researchgate.net/publication/322345762.
➢ Gupta, S., et al. (2019). "Real-Time Reporting in Educational Result Systems". [online]
Available: https://www.springer.com/gp/book/9783319873041.
➢ Khan, M., et al. (2020). "Educational Data Processing and Result Management Using AI".
[online] Available: https://dl.acm.org/doi/10.1145/3411764.
➢ Sharma, A., et al. (2021). "Automating Result Compilation for Educational Institutions".
[online] Available: https://www.journals.elsevier.com/computers-and-education.

11