Authors: Prof. Jyothi Patil, Shambhavi V, Sneha N T, Sweta Jadhav, Tahura Sadaf
Certificate: View Certificate
The goal of this project is to create a time table generator for colleges. The creation of schedules is a very common issue that affects all educational institutions. The conflict between staff members\\\' preferences is precisely where the issue arises. Every semester, colleges are required to create time tables, which used to be an extremely time-consuming task. Once the timetables are set for a given semester, the student is allowed to access them. Once the timetables are established for a particular semester, employees are also permitted to check the class allotment schedule. The Time Table Assignment for Any Department project\\\'s goal was to create an application that would allow staff and student allotment subject to classes. Following information was added by the administrator for Add the student, the staff, the subject, enter the timetable, and update the timetable. The majority of colleges offer a variety of programmes, each of which has a number of disciplines. There are now a limited number of faculties, each of which teaches many disciplines. Therefore, the timetable now has to include the instructors at the appropriate times. the timetable schedule, which makes the most use of all faculty subject demands, slots so that their timings do not cross. For this, a genetic algorithm is employed. We suggest using a timetable object in our method for creating timetables. This object consists of classroom objects, their respective schedules, and a fitness rating for the schedule. Additionally, in order to further describe the imperatives, we used a composite configuration design that is easily expandable to include or uproot as many duties. Every obligation class now checks the condition found in our investigation between two timetable objects. In the unlikely event that the requirement is met, the score is raised by one if a crash is available.
Every semester, colleges are required to create time tables, which used to be an extremely time-consuming task. The "Time Table Generator" project is created with HTML and CSS for the front end and Python and MySQL 3 for the back end. This method for creating timetables connects with numerous modules and processing. The most crucial area for college efficiency is frequently automation and control.
The use of information technology for quicker and simpler forms of communication is widespread. Following information was added by the administrator for Add the student, the staff, the subject, enter the timetable, and update the timetable. Staff and students can see the details of the timetable. Python is being used to implement this system for the time table generator. Since HTML & CSS make up our front-end, the online application has a far more effective and secure appearance. A project for a very helpful for Students to read the time table details in this website is the time table generator system.
This undertaking Python and SQLite have been used in the development of the online automatic timetable generator. A programme written in Python called Automatic Timetable Generator is used to create timetables automatically. The timetable is currently manually handled. It will facilitate automatic management of all Periods and make timetables available to instructors. Additionally, it will control the schedule when a teacher is tardy or early. For the purpose of creating a schedule effectively, the maximum and minimum workloads for each faculty member will be set for each day, week, and month. In the current system, the issue arises when a teacher is absent and is unable to notify the school or does so too late, making the manual assignment of a substitute teacher an extremely challenging task.
There is a scenario when the department head wants to make some adjustments to the lectures while the schedule tracker is made manually. Because it is impossible for one teacher to remember every task that was completed in the past, the likelihood that the teachers' periods or assignments would overlap will rise in this case. The manual upkeep of item databases and scheduling tracker processing takes time and is in some ways inaccurate. Consequently, the new system is required to address these issues.
II. LITERATURE SURVEY
III. PROBLEM STATEMENT
The existing system produces or generates a series of timetables, however it frequently struggles to provide a timetable that is conflict-free and complete. The bottlenecks in this situation are the laborious chores of data introduction and adjustment of frequently partial solutions (Luisa et.al, 2006). The majority of educational institutions still manually create their timetables, which according to statistics takes far longer to accomplish and is less efficient. There are still some conflicts in the manually generated timetable, even at its best point, and it is the lecturer who is taking the conflicting course that arranges the course's logistics in order to resolve the conflict.
Despite the fact that human scheduling takes a lot of time and is unreliable, tiny colleges have found ways to construct their schedules. It will be vital to use computer approaches to streamline timetabling as academic complexity rises. It should be noted that the number of constraints grows, leading to an exponential increase in the computational time, making it an NP-complete operation as the student population with diverse interests and requirements grows and the teaching programmes become more complex with the expansion of universities.
A. Problem Objective
The major objective of a college timetable generator is to create an efficient and effective schedule for classes and other activities in a college or university. This objective is achieved by taking into account various constraints and criteria, such as
The college timetable generator may produce a schedule that satisfies the requirements of the students, teachers, and administrators while maximising efficiency and effectiveness by meeting these goals. This may lead to better academic achievement, greater student satisfaction, and less work for administrators and professors.
B. Existing System
Each operation must be completed manually under the current system, and processing is a time-consuming effort as well. In the prior method, institutions had to manually manage their timetable information on paper and ink, which took time and money. The organisation can't meet its demands in a timely manner, and the outcomes might not be reliable. Numerous issues and shortcomings with the system are caused by manual upkeep.
C. Proposed System and Solution
The purpose of this work is to illustrate how effectively evolutionary algorithms can be used to find the best solutions for scheduling timetables in general. Despite the abundance of commercial scheduling software, its lack of generality makes it difficult for it to satisfy the needs of varied institutions. The main challenge to overcome is the demand of particular coding as per the distinct colleges. An institute must deal with a number of restrictions when constructing a schedule. These constraints can be categorised as either "hard" or "soft" based on whether they are necessary or desirable.
D. System Specifications
2 Software Requirements
IV. DESIGN METHODOLOGY
A. Block Diagram Of The System
The software can simply be compared to a schedule computing tool that accepts simple data sets as input and produces organised results. Using the straightforward input-process model We fill out the form with all the information, and a genetic algorithm applies it to the data on the backend to create class schedules.
B. Genetic Algorithm
Natural selection, a process in biological evolution, is a process that the genetic algorithm mimics. The best way to visualise the repeating process is through a flowchart. Instead of using the term "person," the term "chromosome" is used in genetic algorithms. The fundamentals of a genetic algorithm are depicted in the diagram below. However, in actual use, the system adds an additional phase known as environment modification following evaluation. A strong programming tool for issue solving is the genetic algorithm (GA). It belongs to the class of evolutionary algorithms, which is a subset of artificial intelligence's evolutionary computation. Professor John Holland of the University of Michigan created it in 1960. In the 1970s, his book Adaptation in Natural and Artificial Systems helped launch the field of genetic algorithm (GA) study. The Darwinian theory of natural evolution, which holds that species in the world multiply in geometric proportions resulting to a battle for life mostly owing to a lack of food and space, served as the inspiration for this technique. The strongest will prevails in this conflict. The variants that are most suited to survival are those whose accumulation led to the evolution of species. Organisms with harmful mutations have very little chance of surviving. Natural selection is the mechanism that leads to evolution.
A random beginning point will be chosen for the population generation, and a mixture of greedy and random approaches will be used to fill the table with any suitable entities. All rigid restrictions must be adhered to throughout population generation. While soft constraints are completely disregarded, medium requirements will go through several tries to be followed
The whole method of scheduling based on genetic algorithm is explained in detail in this section. A scheduling procedure is divided into several important modules are as follows,
The initial step before beginning a Genetic Algorithm is data encoding. To obtain a straightforward value, such as a string, it converts a solution into a chromosome. It is used to increase the algorithm's speed. Making the data into a binary string is a simple technique to accomplish this. A gene is a component of a chromosome and can also be transformed into a binary string. The algorithm can be treated more easily by converting the data to this kind. Side-by-side gene strings make up the chromosomal string.
2. Initial Population
It is the initial phase of GA. It involves producing a large number of randomly chosen people under strict limits. The user's needs determine the population choice. Due to evolution, a tiny population will eventually become even smaller and exterminate the entire population. On the other side, a huge population will produce better outcomes but will be slower and need more resources. A set can be used to represent the population.
3. Evaluation of Population
A solution's fitness is an assessment of its quality made utilising soft restrictions. The answer is appropriate for this range. The core of the genetic algorithm is population evaluation. In this stage, a fitness function is used to determine which solution is superior to others. The fitness can be expressed using a range from 0 to 1, with 1 being the population's best estimate, and using the other individuals to range them. There will always be a solution where the fitness is 1 in this situation, and a solution where the fitness is 0.
4. Crossover Evolution
A technique for creating a new population based on an older population is crossover evolution. The two-chromosome simple crossover evolution allows for the creation of X additional chromosomes. The two chromosomes are divided into pieces, and new chromosomes are made from various pieces. Mutation: The algorithm is made to move by means of mutation. By randomly altering a gene's values, a novel, unexpected solution is produced. These solutions present the fitness function from a fresh perspective. Only the chromosome is altered by the mutation; other solutions are unaffected.
5. New Population
The crossover and the mutation permit to create a new population of original solutions.
V. ADVANTAGES AND DISADVANTAGES
Large applicability in an institution where different class schedules are necessary. Within minutes, automatically establish and maintain student academic calendars. You can quickly construct a different timetable for each class and subject using an automated timetable management system.
There exist a lot of diverse timetable problems such as:
All of the timetables can be created easily and productively using genetic algorithm.
VII. RESULT AND DISCUSSION
This system generates separate timetables for each class, faculty member, and lab automatically. The project is designed to prevent slot conflicts and provides tools for customising the schedule as needed. The project employs a genetic algorithm to meet the scheduling-related limitations. The following restrictions are met by the programme:
Unique class timing
classes are allotted according to section requirements
Course.students <= room. seating capacity and Teachers are allocated to their course accordingly
All courses are according to their department
Two classes don’t have same room and Class timing for each teacher is unique
Even distribution of course in a section per week
Models were employed to test the artificial intelligence's capabilities. Despite the constraints put forth by the setting of the algorithm, it is reasonable to claim that the system has operated within its capabilities. The final output screens, which include several options for adding instructor details, adding course details with a department, and adding room and time details, are as shown in the figures below. On the home page, we can create the schedule.
VIII. FUTURE SCOPE
This project will be very beneficial to the university because managing numerous faculties and assigning courses to them simultaneously by hand is a very challenging task that this project will assist in managing effectively. This faculty timetable can be readily controlled while taking into account the maximum and lowest workload. The faculty data in the database can also be used to keep track of the faculty's expertise in specific fields. Attribute The accuracy of the project will allow for a more corrective approach to the creation of this schedule. This project will produce output that is mostly corrective and error-free. The project's potential future improvement is the creation of a master schedule for the departments and the entire college. Further adjustments can be made while maintaining the project's approach and methods to accomplish this improvement. Additionally, it can be utilised to assign a certain time slot that the instructor prefers. The university website may incorporate this timetable maker, making it more useful. The implementation of a time table management system can make it simpler for the schools to assign a teacher to a class in the event of an absent teacher.
VIII. CONCLUSION By removing some of the problem\\\'s dimensions and putting those dimensions into constraints, the original timetabling problem with its enormous number of binary variables has been shrunk to an appropriate size. The size of the individual was greatly decreased by combining numerous binary variables into a single gene value. The full-size problem (the problem of the entire FER schedule) can now be attempted to be solved using a genetic algorithm approach. Small size problems are resolved in tens of seconds when the scheduling problem is represented in this way, which reaches the acceptable method speed. Using intelligent operators has resulted in significant benefits. The intelligent algorithm converges significantly more quickly than the fundamental algorithm, and it serves as a suitable foundation for fully resolving the original problem. We have made significant progress, and we can say with confidence that it is highly fulfilling. We gained a solid understanding of the fundamentals of web construction as well as how evolutionary and genetic algorithms can be combined to get the best goal-finding performance in terms of time and space complexity. Regarding our comprehension of Python. Exceptional chance to understand the framework and the advantages it offers. We have made a wonderful find here. Our method of creating an automated timetable system is effective in resolving the lecture-course scheduling issue in institutions. We\\\'ve also demonstrated how our timetabling system can be integrated into a rich web-based desktop environment. The graphical user interface used in this system provides an easy way in understanding how system works and also makes ease in providing the input.
 K. Nguyen, D. Nguyen, K. Trieu, and N. Tran, “Automating a real-world university timetabling problem with Tabu search algorithm,” in 2010 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future (RIVF), 2010  A. Azlan and N. M. Hussin, “Implementing graph coloring heuristic in construction phase of curriculum-based course timetabling problem,” in 2013 IEEE Symposium on Computers & Informatics (ISCI), 2013.  R. E. Febrita and W. F. Mahmudy, “Modified genetic algorithm for high school time-table scheduling with fuzzy time window,” in 2017 International Conference on Sustainable Information Engineering and Technology (SIET), 2017.  T. Elsaka, “Autonomous generation of conflict-free examination timetable using constraint satisfaction modelling,” in 2017 International Artificial Intelligence and Data Processing Symposium (IDAP), 2017.  F. D. Wihartiko, H. Wijayanti, and F. Virgantari, “Performance comparison of genetic algorithms and particle swarm optimization for model integer programming bus timetabling problem,” IOP Conf. Ser. Mater. Sci. Eng., vol. 332, p. 012020, 2018.  A. Aminu et al., “Design and implementation of an automatic examination timetable generation and invigilation scheduling system using genetic algorithm,” in 2nd International Conference on Applied Engineering (ICAE), 2019.  D. Wang, D. Tan, and L. Liu, “Particle swarm optimization algorithm: an overview,” Soft Comput., vol. 22, no. 2, pp. 387–408, 2018.  K. Y. Junn, J. H. Obit, and R. Alfred, “The study of genetic algorithm approach to solving university course timetabling problem,” in Lecture Notes in Electrical Engineering, Singapore: Springer Singapore, 2018, pp. 454–463.  E. Psarra and D. Apostolou, “Timetable scheduling using a hybrid particle swarm optimization with local search approach,” in 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), 2019.  T. W. Ekanayake, P. Subasinghe, S. Ragel, A. Gamage, and S. Attanayaka, “Intelligent timetable scheduler: A comparison of genetic, graph coloring, heuristic and iterated local search algorithms,” in 2019 International Conference on Advancements in Computing (ICAC), 2019.  A. Schaerf, Local search techniques for large high-school timetabling problems, IEEE Transactions on Systems Man. And Cybernetics, Part A, 29 (4), 368-377 (1999).  H.P. Hariyadi, T. Widiyaningtyas, et. al., Implementation of Genetic Algorithm to Academic Scheduling System, IEEE, Region 10 Conference, (2016).  S. Daskalaki, T. Birbas, E. Housos, An integer programming formulation for a case study in university timetabling, Eur. J. Oper. Res., 153, 117-135 (2004)  A.F. AbouElhamayed, A.S. Mahmodd, et. al., An Enhanced Genetic Algorithm-Based Timetabling System with Incremental Changes, IEEE, (2016).  M. Dimopoulou, P. Miliotis, An automated university course timetabling system developed in a distributed environment: A case study, Eur. J. Oper. Res., 153 136– 147 (2004).  E. Burke, K. Jackson, J. H. Kingston, R. Weare, Automated university timetabling: The state of the art, The Computer Journal, 40 (9): 565-571, (1997).  Rosen, Kenneth H. (2012). Discrete Mathematics and Its Applications (7th ed.). New York: McGraw-Hill. p. 119. ISBN 978-0-07-338309-5  D. Shiffman, The Nature of Code, Chapter 9, 2012, Creative Commons, 444 Castro Street, Suite 900, Mountain View, California 94041, USA. ISBN-13: 978-0985930806.  E. R. Pianka, Evolutionary Ecology, 6th ed. San Francisco, CA: Addison-Wesley- Longman, 2000; Deepti Gupta, Shabina Ghafir, International Journal of Emerging Technology and Advanced Engineering, 2(5), (2012).  Shraddha Thakare, Tejal Nikam, Prof, Mamta Patil, Automated Timetable Generation using Genetic Algorithm, International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181,Vol. 9 Issue 07, July-2020
Copyright © 2023 Prof. Jyothi Patil, Shambhavi V, Sneha N T, Sweta Jadhav, Tahura Sadaf. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.