Module Title: Artificial Intelligence

Module Code: CS3AI18

Lecturer responsible: Muhammad Shahzad

Type of Assignment (coursework / online test): Coursework

Individual / Group Assignment: Individual

Weighting of the Assignment: 50%

Page limit/Word count: 4 pages excluding title page(s), references and appendices Expected hours spent for this assignment: 10 hours

Items to be submitted: A single zip archive containing :

1) report (PDF or Word file)

2) dataset(s)

3) Python script(s) (PY or IPYNB files)

Work to be submitted on-line via Blackboard Learn by: 21st March 2023 noon Work will be marked and returned by: 15 working days after the above deadline

NOTES

By submitting this work, you are certifying that it is all your sentences, figures, tables, equations, code snippets, artworks, and illustrations in this report are original and have not been taken from any other person's work except where explicitly the works of others have been acknowledged, quoted, and referenced. You understand that failing to do so will be considered a case of plagiarism. Plagiarism is a form of academic misconduct and will be penalised accordingly. The University’s Statement of Academic Misconduct is available on the University web pages.

If your work is submitted after the deadline, 10% of the maximum possible mark will be deducted for each working day (or part of) it is late. A mark of zero will be awarded if  your  work  is  submitted  more  than  5  working  days  late.  You  are  strongly recommended to hand work in by the deadline as a late submission on one piece of work can impact on other work.

If you believe that you have a valid reason for failing to meet a deadline then you should make an Exceptional Circumstances request and submit it before the deadline, or as soon as is practicable afterwards, explaining why. To make such a request log on

to  RISIS  and  on the Actions tab  select  Exceptional  Circumstance:  as  explained  at

https://www.reading.ac.uk/essentials/The-Important-Stuff/Rules-and- regulations/Exceptional-Circumstances

1. Assignment description

You are required to find a dataset, formulate a problem you want to address with the dataset  (e.g.,  predict  whether  a  mushroom  is  poisonous  or  not  based  on  its characteristics), build, evaluate and compare two different machine learning models that would address the problem, and draw conclusions and recommendations based on  your  findings. One of the two models must be based on a deep learning architecture implemented using the Keras Python library . The  submission  should include your report, dataset(s) and Python scripts with comments, all included in one zip-file. Your work should be original and produced by you. Copying whole tutorials, scripts or images from other sources is not allowed. Any material you borrow from other sources to build upon should be clearly referenced (use comments to reference in  Python  scripts);  otherwise,  it will  be treated  as  plagiarism, which  may  lead to investigation and subsequent action.

You can use any open data, e.g. :

https://ieee-dataport.org/topic-tags/artificial-intelligence

https://archive.ics.uci.edu/ml/datasets.php

https://www.kaggle.com/datasets

https://data.gov.uk/

Some examples:

Optical Image data:

1.   Building Detection and Roof Type Classification

https://ieee-dataport.org/competitions/2023-ieee-grss-data-fusion-contest- large-scale-fine-grained-building-classification

2.   So2Sat LCZ42 Dataset for land cover classification

https://mediatum.ub.tum.de/1483140

3.   DOTA: A Large-Scale Benchmark and Challenges for Object Detection in Aerial

Images

https://captain-whu.github.io/DOTA/dataset.html

Weather and Climate Data:

4.   Daily 0900 GMT observations from the university weather stations (back to

1908; there was a site change in 1968):

https://metdata.reading.ac.uk/cgi-bin/climate_extract.cgi

5.   Five-minute/hourly data from our automatic weather station back to 1 Sept

2014 (has a few missing dates):

https://metdata.reading.ac.uk/cgi-bin/MODE3.cgi

http://www.met.reading.ac.uk/~sws09a/MODE3_help.html

For some further inspiration (visualisation of current data) and information

around     the     above     two     data     sources,     check     these     resources:

https://www.met.reading.ac.uk/weatherdata/wall_display.html