Department of Information Technology

V R Siddhartha Engineering College

EDUSLOT:LAB AND CLASS SLOT BOOKING PLATFORM

Software Development, Machine Learning

B.Tech in Information Technology

MINI-1 Project Review Presentation

Presented by
Ms. Keerthi Koneru (218W1A1222)
Mr. Ede Prashanth (218W1A1210)

Under the guidance of

Dr K.Sita Kumari, Associate Professor
 Introduction:

 In educational institutions, ensuring optimal use of resources and efficient

scheduling is crucial for smooth operations. However, the absence of a
centralized system often results in scheduling conflicts and uncertainties
regarding resource availability.

 To address these challenges, we propose the development of a comprehensive

booking system tailored specifically for educators. This solution aims to
streamline the process of reserving classrooms and laboratory facilities
efficiently, thereby enhancing operational effectiveness.
Problem Statement:

The current lack of a robust scheduling system leads to frequent instances of double-
booking and scheduling discrepancies among teachers. This not only causes confusion
but also disrupts academic activities, resulting in wasted time and resources.
Consequently, there is a pressing need for a centralized solution that alleviates these
issues and provides clarity regarding resource availability.
Objectives:

• To create a Mobile Application for the teachers to book a slot and a lab/class.
• To implement 2 different algorithms for recommendation.
• To integrate recommendation system to suggest classes/labs for a teacher based on their previous
searches and bookings into the mobile application.

Outcomes:
• To provide a Mobile application to the IT department to provide convenience in terms of slot
booking.
• Optimized Resource Use: Efficient use of classrooms/labs with reduced conflicts.
• Reduced Disruptions: Real-time availability info leading to confident planning.
• To recommend classes/lab slots through a notification to the teacher’s mobile .
Literature Review:
Title of the Publication Details Algorithms / Summary
Paper Technologies
Used
The research emphasizes the use of Cosine
Similarity and Content-Based Filtering in a deep
Movie International Journal of
learning framework to predict movie
Recommendation Engineering and
KNN , Cosine recommendations. It details the mathematical
System using Advanced Technology
Similarity aspects of Cosine Similarity in measuring movie
Cosine Similarity (IJEAT)
similarities and the implementation of the KNN
and KNN 2020
algorithm to find the nearest neighbors for
recommendations.

design and implementation of an android and web

BOOKiiIT - IEEE Sixth application, BOOKiiIT, it is developed using Flutter
Flutter,Google
Designing a International and is intended to facilitate the booking and
Calendar, GPS
Venue Booking Conference on management of spaces in the institution .It
technology ,QR code
System (Technical Multimedia Big Data addresses the challenges faced in the existing
scanning
Demo) 2020 manual booking system, such as lack of knowledge
of available spaces, communication failures
Title of the Publication Details Algorithms / Summary
Paper Technologies
Used
The research delves into the technical aspects of
Career Fifth International recommendation systems, including the use of
Recommendation Conference on
Communication and KNN , cosine similarity cosine similarity and KNN algorithms to predict
Systems using
Electronics Systems , Content-based filtering recommendations. It discusses the mathematical
Content
2020 principles behind cosine similarity and its
based Filtering
application in measuring similarities between items

eReserba Development of an online room reservation system

International
Cardinal: An to optimize the scheduling of room reservations in a
Conference on
Integrated Room web-based Technologies higher education institution in the Philippines. This
Industrial Engineering
Reservation , Data base management system, aims to facilitate ease of room
and Operations
System for Higher Systems management, provide real-time information, and
Management
Education offer a convenient manner of room reservation for
2020
Institutions students, faculty,
Title of the Publication Details Algorithms / Summary
Paper Technologies
Used

Developing and
Implementing The online facilities reservation system for
International Journal of MySQL ,Unified Modeling
Web-based Online Imam Abdulrahman Bin Faisal University (IAU)
Applied Engineering Language (UML) , Visual
University is designed to allow users to reserve university
Research Basic Programming
Facilities facilities such as halls, stadiums, theaters, and
2019 Language (VB)
Reservation swimming pools.it uses UML, MySQL, and VB.
System

Java programming
language, JSP (a Web
Design and
platform development
Implementation of The paper addresses the imbalanced use of
MATEC Web of technology), MySQL
Online Booking university sports venues by designing an online
Conferences 100 database processing
System of booking system based on the table tennis hall of
2021 technology, JDBC data
University Sports Zhengzhou University.
access model, MyEclipse
Venues
development platform, and
Tomcat server
 Literature Summary:
 Research paper focuses on designing and implementing online reservation systems tailored to the
specific needs of higher education institutions, ranging from room bookings to venue and sports
facility reservations.

 By leveraging technologies such as Flutter, UML, MySQL, and VB, the projects aim to streamline
reservation processes, enhance space management, and improve overall operational
effectiveness, ultimately making it easier for students and faculty to access and book university
facilities.

 The researches delves into recommendation systems, spotlighting cosine similarity and KNN
algorithms within a deep learning framework. It discusses the mathematical principles of cosine
similarity for measuring item similarities and emphasizes content-based filtering. it details the
implementation of the KNN algorithm to find nearest neighbors for recommendations.
Datasets & Requirements:
Datasets
Timetable Data:
• Day: The day of the week on which the slot or lab is scheduled.
• Time: The time slot of the timetable entry (start and end times).
• Room/Location: The room or location where the class is scheduled.
• Class/Event: The name or ID of the class or event.
• Instructor/Teacher: The name or ID of the instructor or teacher for the class.
• Student Group: The name or ID of the student group attending the class.
• Additional Notes: Any additional information or notes related to the class.

Facility Availability Records:

• Day: The day of the week on which the facility (room, lab, etc.) is available.
• Time: The time slot of the availability record (start and end times).
• Facility ID: The ID or name of the facility.
• Status: The availability status (e.g., available, booked, under maintenance).
• Additional Notes: Any additional information or notes related to the availability.
Faculty Booking Records:
 Day: The day of the week on which the booking is made.
 Time: The time slot of the booking (start and end times).
 Room/Location: The room or location booked by the faculty.
 Faculty ID: The ID or name of the faculty member booking the room.
 Purpose: The purpose or reason for the booking.
 Additional Notes: Any additional information or notes related to the booking.
Software Requirements
 React Native
 MongoDB
 Node Js
 Wireframes: Done in Figma for UX UI Design

Algorithms Required
 Cosine Similarity
 K-Nearest Neighbours (KNN)
Architecture Diagram:
Mobile Application Database
User Past Booking
Data
Stored Time-Table
Admin Data

Feature Vector
Creation based on
Available Not-Available
Items
Check the Availability of Check
Labs, classes to book a slot

Faculty Login Slot Slot not

Booked Booked
Accept the Notification
Model Training (Cosine
Similarity )

Recommendation Machine Learning

Machine Learning
Notification System generating Model Predict the
the Notification Model Evaluation
Similar Lab
Cosine Similarity Algorithm:
function lab_recommendation(teacher_booked_slots, lab_availability):
max_similarity = -1
recommended_lab = null

for lab in all_labs:

lab_vector = create_vector(lab_availability[lab])
similarity = cosine_similarity(teacher_booked_slots, lab_vector)
if similarity > max_similarity:
max_similarity = similarity
recommended_lab = lab

return recommended_lab

function create_vector(slots):
vector = []
for slot in all_slots:
if slot in slots:
vector.append(1)
else:
vector.append(0)
return vector
Cosine Similarity Algorithm:
function cosine_similarity(vectorA, vectorB):
dot_product = 0
magnitude_A = 0
magnitude_B = 0

for i from 0 to vectorA.length - 1:

dot_product += vectorA[i] * vectorB[i]
magnitude_A += vectorA[i] * vectorA[i]
magnitude_B += vectorB[i] * vectorB[i]

magnitude_A = sqrt(magnitude_A)
magnitude_B = sqrt(magnitude_B)

if magnitude_A == 0 or magnitude_B == 0:
return 0

cosine_similarity = dot_product / (magnitude_A * magnitude_B)

return cosine_similarity

# Usage
teacher_booked_slots = [slot1, slot2, ...] # List of booked slots for the teacher
lab_availability = {lab1: [slot1, slot2, ...], lab2: [slot3, slot4, ...], ...} # Dictionary of lab availability

recommended_lab = lab_recommendation(teacher_booked_slots, lab_availability)

Lab Recommendation Algortihm
Algorithm: LabRecommendation

function lab_recommendation(teacher_availability, booked_slots):

available_labs = get_available_labs(teacher_availability, booked_slots)
recommended_lab = recommend_lab(available_labs)
return recommended_lab

function get_available_labs(teacher_availability, booked_slots):

available_labs = []
for lab in all_labs:
if lab.is_available(teacher_availability, booked_slots):
available_labs.append(lab)
return available_labs

function recommend_lab(available_labs):
# Implement a recommendation logic here
# For example, you can use a simple algorithm like recommending the lab with the fewest bookings
recommended_lab = min(available_labs, key=lambda lab: len(lab.bookings))
return recommended_lab
 Implementation Steps:
 Requirements Analysis: Conduct a thorough analysis of requirements and system functionalities to define the
scope of the project.

 Database Design: Design and implement a centralized database schema to store timetable data, facility
availability records, and user information.

 Algorithm Implementation: Designing the Lab recommendation algorithm and implementing cosine similarity
algorithm as well which is later integrated with the mobile application

 Frontend Development: Develop a user-friendly frontend interface with intuitive navigation and interactive
features, leveraging modern web development technologies.

 Backend Development: Implement backend functionalities for managing user authentication, booking requests,
and resource allocation logic.

 Integration and Testing: Integrate frontend and backend components, conduct rigorous testing to ensure system
stability, performance, and data integrity.

 Deployment and Maintenance: Deploy the booking system on a scalable infrastructure, provide ongoing
maintenance and support to address any issues and incorporate user feedback for continuous improvement.
 Implementation Details:

The user logs in to The user creates the The user creates Teachers log in to Select dept,year and time
create timetable department details Timetable for each book a lab or class and book a available class
like labs and classes year or lab

Admin_EduSlot User_EduSlot
Results:

Cosine Similarity Algorithm Output for recommendation of lab

Lab Recommendation Algorithm Output for recommendation

of lab
Conclusion:

In conclusion, the Eduslot project has effectively tackled the challenges of resource
scheduling in educational Institutions by providing a comprehensive booking system tailored
for educators.

The system's integration of recommendation algorithms, particularly the lab

recommendation algorithm, has greatly improved user experience by offering accurate
suggestions based on past bookings. This has streamlined the reservation process and
enhanced operational efficiency.

The project's success underscores the potential of smart technology in optimizing resource
management and improving overall efficiency in educational settings. The lab
recommendation algorithm, in particular, has outperformed cosine similarity, providing
tailored
recommendations that reduce scheduling conflicts and enhance resource utilization.

This demonstrates the value of advanced algorithms in educational tools for improving user
References:
 [1] Singh, R. H., Maurya, S., Tripathi, T., Narula, T., & Srivastav, G. (2020, June 30). Movie Recommendation System using Cosine
Similarity and KNN. International Journal of Engineering and Advanced Technology, 9(5), 556–559.
https://doi.org/10.35940/ijeat.e9666.069520

 [2] H. Singh and R. R. Shah, "BOOKiiIT - Designing a Venue Booking System (Technical Demo)," 2020 IEEE Sixth International
Conference on Multimedia Big Data (BigMM), New Delhi, India, 2020, pp. 287-291, doi: 10.1109/BigMM50055.2020.00050.

 [3] T. V. Yadalam, V. M. Gowda, V. S. Kumar, D. Girish and N. M., "Career Recommendation Systems using Content based Filtering,"
2020 5th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, 2020, pp. 660-665,
doi: 10.1109/ICCES48766.2020.9137992. keywords: {natural language processing;cosine similarity;content based filtering},

 [4] Barzaga, Paz & German, Josephine & Binoya, Guiller & Bucao, Samantha & Ibe, Rarum & Yap, Dave. (2020). eReserba
Cardinal: An Integrated Room Reservation System for Higher Education Institutions.

 [5] Li, Can & Li, Junjie & Cao, Hongxiang & Meng, Zhan. (2021). Design and Implementation of Online Booking System of
University Sports Venues. MATEC Web of Conferences. 100. 02024. 10.1051/matecconf/201710002024.

 [6] Alkhaldi, Daniyah & Alkhaldi, Dhai & Aldossary, Amienah & Alsmadi, Mutasem & Almarashdeh, Ibrahim & Badawi, Usama &
Alshabanah, Muneerah & Alrajhi, Daniah. (2019). Developing and Implementing Web-based Online University Facilities
Reservation System. 6700-6708.