Where-Got-Time - An NUS timetable generator which uses a genetic algorithm to optimise timetables to suit the needs of NUS students

Overview

Where Got Time(table)?

A timetable optimsier which uses an evolutionary algorithm to "breed" a timetable suited to your needs.



Try it out here!

Inspiration

Planning the best fit timetable to suit our needs can be an absolute nightmare. Different sets of modules can result in a seemingly limitless combinations of timetable. Comparing and choosing the best timetable can take hours or even days. The struggle is real

Having chanced upon an article on genetic algorithm, we thought that this would be the best approach to tackling an optimization problem involving timetabling/scheduling. This project aims to provide the most optimized timetable given a set of pre-defined constraints.

What It Does

Users can input the following:

  • Modules codes for the particular semester
  • Adjustable start and end time
  • Select free days
  • Maximize lunch timings
  • Determine minimum hours of break between classes

Based on user inputs, the most optimized timetable is generated.





Why It Works

A Genetic Algorithm mimics the process of natural selection and evolution by combining the "elite" timetables to form the "next generation" of timetables.

The evolutionary process:

  1. Extracting, cleaning and generating our own data structure from NUSMods API
  2. Initialise the first generation which includes a population of timetables
  3. Grading each timetable with a fitness score
  4. Cross-over fittest "parents" to generate 2 "child" timetables with mutations
  5. Assign these timetables to the next generation
  6. Repeat this process until the fitness score across a generation converges
  7. If the soft and hard constraints were not met after reaching the generation limit, the most optimised timetable is returned to the user

How We Built It

Our main algorithm was written with Python. It utilizes NUSMods API to fetch the relevant module data. Some filtering and cleaning up of the data grants us a workable data structure. Implementation of the genetic algorithm returns a link that is sent to the web page which generates an image for the user.

Firstly, we generate a population of timetables. Using a scoring algorithm, we rate the fitness of each timetable. Timetables with a better fitness score gets to produce the next generation of timetables through cross-overs and mutation.

We repeat this process until the average fitness score of the entire generation converges to within a tolerance range. The fittest timetable from the final generation is returned to the user.

Challenges We Ran Into

Managing large data structures comes with confusing errors that are hard to pinpoint. NUS offers more than 6000 modules, some classes are fixed while others are variable. This results in multiple varying data structures for different modules. As such, our code needs to be robust enough to handle the unique data structures. Integration of front and backend code was much harder than expected.

Accomplishments We're Proud Of

We are proud to have come up with a minimum viable product.

What We Learned

As this is our first group project, we learnt how to work on Git Flow, how to push and pull information via Git and version control. One of us even deleted a whole file and had to rewrite from scratch We also learnt how to approach optimization problems and how to use the NUSMods API for parsing data into our program.

What's Next For Where Got Time(table)?

Improve the UI/UX of the landing page to facilitate better user experience. Allow more user constraints such as "Minimal Time Spent in School". We will further fine-tune the program which could possibly be used as an extension for the official NUSMods. A possible feature that can be added includes a GIF of the user's timetable evolving across generations from start to finish.

Try It Out

Where Got Time(table)?

Credits/Reference

Using Genetic Algorithm to Schedule Timetables

Owner
Nicholas Lee
Nicholas Lee
Use your Philips Hue lights as Racing Flags. Works with Assetto Corsa, Assetto Corsa Competizione and iRacing.

phue-racing-flags Use your Philips Hue lights as Racing Flags. Explore the docs » Report Bug · Request Feature Table of Contents About The Project Bui

50 Sep 03, 2022
Patch SVDD for Image anomaly detection

Patch SVDD Patch SVDD for Image anomaly detection. Paper: https://arxiv.org/abs/2006.16067 (published in ACCV 2020). Original Code : https://github.co

Hong-Jeongmin 0 Dec 03, 2021
Network Pruning That Matters: A Case Study on Retraining Variants (ICLR 2021)

Network Pruning That Matters: A Case Study on Retraining Variants (ICLR 2021)

Duong H. Le 18 Jun 13, 2022
Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite and .pb from .tflite.

tflite2tensorflow Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite and .pb from .tflite. 1. Supported Layers No. TFLite Layer TF

Katsuya Hyodo 214 Dec 29, 2022
U-Net Implementation: Convolutional Networks for Biomedical Image Segmentation" using the Carvana Image Masking Dataset in PyTorch

U-Net Implementation By Christopher Ley This is my interpretation and implementation of the famous paper "U-Net: Convolutional Networks for Biomedical

Christopher Ley 1 Jan 06, 2022
Image Captioning on google cloud platform based on iot

Image-Captioning-on-google-cloud-platform-based-on-iot - Image Captioning on google cloud platform based on iot

Shweta_kumawat 1 Jan 20, 2022
Repository for the NeurIPS 2021 paper: "Exploiting Domain-Specific Features to Enhance Domain Generalization".

meta-Domain Specific-Domain Invariant (mDSDI) Source code implementation for the paper: Manh-Ha Bui, Toan Tran, Anh Tuan Tran, Dinh Phung. "Exploiting

VinAI Research 12 Nov 25, 2022
Details about the wide minima density hypothesis and metrics to compute width of a minima

wide-minima-density-hypothesis Details about the wide minima density hypothesis and metrics to compute width of a minima This repo presents the wide m

Nikhil Iyer 9 Dec 27, 2022
improvement of CLIP features over the traditional resnet features on the visual question answering, image captioning, navigation and visual entailment tasks.

CLIP-ViL In our paper "How Much Can CLIP Benefit Vision-and-Language Tasks?", we show the improvement of CLIP features over the traditional resnet fea

310 Dec 28, 2022
A new benchmark for Icon Question Answering (IconQA) and a large-scale icon dataset Icon645.

IconQA About IconQA is a new diverse abstract visual question answering dataset that highlights the importance of abstract diagram understanding and c

Pan Lu 24 Dec 30, 2022
Implementation of Convolutional LSTM in PyTorch.

ConvLSTM_pytorch This file contains the implementation of Convolutional LSTM in PyTorch made by me and DavideA. We started from this implementation an

Andrea Palazzi 1.3k Dec 29, 2022
Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Models

Explainable_FIQA_WITH_AMVA Note This is the official repository of the paper: Explainability of the Implications of Supervised and Unsupervised Face I

3 May 08, 2022
Supplementary materials for ISMIR 2021 LBD paper "Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes"

Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes Supplementary materials for ISMIR 2021 LBD submission: K. N. W

Karn Watcharasupat 2 Oct 25, 2021
Applying PVT to Semantic Segmentation

Applying PVT to Semantic Segmentation Here, we take MMSegmentation v0.13.0 as an example, applying PVTv2 to SemanticFPN. For details see Pyramid Visio

35 Nov 30, 2022
An updated version of virtual model making

Model-Swap-Face v2   这个项目是基于stylegan2 pSp制作的,比v1版本Model-Swap-Face在推理速度和图像质量上有一定提升。主要的功能是将虚拟模特进行环球不同区域的风格转换,目前转换器提供西欧模特、东亚模特和北非模特三种主流的风格样式,可帮我们实现生产资料零成

seeprettyface.com 62 Dec 09, 2022
Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU)

DocFormer - PyTorch Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for t

171 Jan 06, 2023
A Distributional Approach To Controlled Text Generation

A Distributional Approach To Controlled Text Generation This is the repository code for the ICLR 2021 paper "A Distributional Approach to Controlled T

NAVER 102 Jan 07, 2023
Semantic similarity computation with different state-of-the-art metrics

Semantic similarity computation with different state-of-the-art metrics Description • Installation • Usage • License Description TaxoSS is a semantic

6 Jun 22, 2022
A Pytorch implementation of CVPR 2021 paper "RSG: A Simple but Effective Module for Learning Imbalanced Datasets"

RSG: A Simple but Effective Module for Learning Imbalanced Datasets (CVPR 2021) A Pytorch implementation of our CVPR 2021 paper "RSG: A Simple but Eff

120 Dec 12, 2022