You are not logged in
Time stamp: 19:25:01-7/12/2022


2012 | 2013 | 2014 | 2015 | 2016 | 2017 | 2018 | 2019 | 2020 | 2021 | 2022

Projects from 2022

Aaron JamesVizDoom AI via Deep Reinforcement LearningFrank C LangbeinSteven Schockaert2021-CM3203
In this paper, I will adapt an existing algorithm to the ViZDoom visual deep reinforcement learning library and try to find optimal algorithmic settings for some default scenarios provided by the library under the PPO and A2C algorithms. I will attempt to further this into playing The Ultimate DOOM once these settings are found. I will follow existing novel methodologies such as transfer learning, curriculum learning, and reward shaping to allow the machine learning algorithm to develop an under...[more]
Adekoyejo CokerCardiff Youth Service – Digital Youth Club (Discord)Catherine TeehanVíctor Gutiérrez Basulto2021-CM3203
Over the past 18 months Cardiff Youth Service has needed to offer a range of digital services and opportunities to young people in the city. Moving into a Covid recovery model we still want to offer these services and opportunities as some young people prefer accessing our service online. Young people have told us they would like to engage with our service through discord and we now have a young person steering group to tell us how it should look, what it should include and what should be on off...[more]
Alexander JonesCyber Security Education Online PortalYulia CherdantsevaOktay Karakus2021-CM3203
The aim of this project is to develop a web-application for hosting cyber security educational material for audiences of different ages starting from primary school and up to the MSc level, and beyond. The application will have must allow access to educational material, allow filtering of material based on different criteria. User roles in the application will include: Admin, Educator, and Participant. The access permissions will vary based on the role. The material stored will vary by type and ...[more]
Alex Hayman Creating Cyber Security Training Exercises for DevelopersYulia CherdantsevaFernando Loizides2021-CM3203
Web applications are often a point of interest for cyber criminals as they are publicly available online and contain personal data, user credentials and financial information. Once the application is compromised, hackers can pivot around the network where the website is being hosted and target more machines. It is essential for developers to have good security practices when developing websites. There is also a growing market in gamification of cyber security learning. Websites such as HackTheB...[more]
Andrei CojocariuGenerating fake travel source and destination location pairsPadraig CorcoranMatthew J W Morgan2021-CM3203
Route planning services, such as Google Maps, require users to submit their source and destination location pairs. For example, if I want a route from my home to the cinema, I submit the location of my home and the location of the cinema. If a user is concerned about their privacy, they may wish to obfuscate or hide the true locations in question. This can be achieved by submitting to the service provider a set of fake source and destination location pairs along with the true location pair. If t...[more]
Anthos KountourisAnalysing the discourse related to electrical vehicles on social media.Padraig CorcoranAmir Javed2021-CM3203
The UK government has committed to transitioning from fossil fuel to electrical vehicles. Many people support this goal because it will result in a more sustainable world. However, many others have concerns about the transition. These concerns include not being able to afford the cost of expensive new electrical vehicles and not being able to charge their vehicles. The aim of this project is to perform an analysis of the discourse related to electrical vehicles on social media and specifical...[more]
Astrid Rickaby-PrattCardiff University Staff Web-AppYulia CherdantsevaSylwia Polberg2021-CM3203
Universities' academic staff, Cardiff included, have been subject to overwork without compensation consistently for over a decade. The aim of this project is to develop a staff-focused web application similar to the Cardiff University student app, but meeting staff needs and expectations. It focuses on both requirements gathering and specification as well as prototype implementation, and pays homage to possible cyber-security threats as a standalone online program that may be subject to attack.[more]
Chilli GoodmanUsing Minecraft for Education to Teach about the Impact of Rising Sea Levels on Welsh Coastal RegionsCatherine TeehanLouise Knight2021-CM3203
Wales Coastal Monitoring Centre - A Welsh Government funded organisation based in the Vale of Glamorgan, focusing on the monitoring of Welsh coastlines with regard to erosion, flood risk and coastal defences. As part of their programme, they are currently developing a series of lessons to be delivered within Primary schools across Wales educating children on the impacts of climate change, coastal erosion and flooding. To support the project, you will build a Minecraft for Education world that wi...[more]
Dan LawAutomatic analysis of music performance styleAndrew JonesFederico Liberatore2021-CM3203
One of the fundamental problems in computational music is the analysis and modelling of performance style. The aims of this project are as follows: (1) Investigate what relevant performance features (e.g. variations in dynamics, tempo, timbre) can be reliably extracted from audio recordings. (2) Provide a means of exploring which of these features are relevant to the perception of performance style. (3) Investigate what operations can be applied to styles, e.g. interpolation between styles, styl...[more]
Devaang MisraHuman Robot Interaction in Healthcare: supporting everyday taskCarolina Fuentes ToroYulia Cherdantseva2021-CM3203
As the title suggests, the problem being tackled here is supporting everyday tasks in a Healthcare environment with the help of robots. The robot being used here is Pepper, a semi-humanoid robot that was manufactured by SoftBank Robotics. In a healthcare environment, Pepper can perform a myriad of everyday tasks, involving greeting hospital visitors, carrying small talks with patients or their families and keeping them entertained, communicating with nurses to provide instructions, Pepper can al...[more]
Dominyque MohammedImplementation of a data privacy protection method for transaction dataJianhua ShaoJames Osborne2021-CM3203
As an increased amount of transaction data being gathered and stored, how to protect the private information contained within such data sets becomes an important issue. This project aims to implement one of the exisiting algorithms for anonymizing transaction data. The system is expected to be developed in Python.[more]
Emima VaipanSSID Stripping Attack: From Vulnerability to Tangible ThreatEirini S AnthiPadraig Corcoran2021-CM3203
This project aims to research and develop hardware tooling that can enable a range of attacks, including a phishing attack, against IEEE 802.11-compliant devices. This attack was recently detected in iPhones and can have lots of severe consequences such as a leak of sensitive data. More specifically, this vulnerability enables SSIDS to be crafted and allows for unintended behaviour in phones whey they ingest them. This project will involve creating a hardware rogue Access Point that will imple...[more]
Ethan CaldeiraCreating an Interactive Virtual Companion to Support and Enhance Mental WellbeingNervo Verdezoto DiasNeetesh Saxena2021-CM3203
This project aims to create a mobile application that will make users aware of their mental wellbeing and help users deal with any stress they might face. The application will guide users through becoming more mindful via a variety of different means. Simplifying these methods by using a virtual companion to increase user engagement, so that all are able to get the benefits.[more]
Eun-Kyul KoWhen is the best time to exchange your money?Parisa EslambolchilarSylwia Polberg2021-CM3203
The foreign exchange market is so unpredictable; you never know when is the best time to exchange your money. Especially with current political problems such as Brexit and COVID-19 it makes the currency fluctuate even more. As an international student I often face problems regarding fluctuating exchange rates. With the same amount of money you send over from abroad, one day you can get a few percent more, and the next day you get a few percent less. Although the percentages are less than 1%, dep...[more]
Finn MillinerSecurity Analysis in SMS-based ApplicationsNeetesh SaxenaBailin Deng2021-CM3203
This project aims to analyse the security level of the applications and services that are either based on Short Message Service (SMS) (such as SMS-based mobile-banking) or do use SMS to provide some sort of service, such as in One-time Password (OTP). Outcome will reflect research-based advantages and limitations with quantitative information about the security level of the application and services used. The work will also provde recommendations to address the existing/found security issues.[more]
Francesco ZucchelliDetecting DDoS attack on a networkAmir JavedJose Camacho Collados2021-CM3203
Using Cyber range to simulate DoS attack on a network – Within the project student will work on already collected dataset. They will then pre-process the data and build supervise/unsupervised machine learning model to detect an ongoing attacks.[more]
George GraingerDeveloping a web application to Visualise IoT Data for Abacws BuildingCharith PereraMartin Caminada2021-CM3203
The Internet of Things (loT) is a recent emerging technology that provides substantial amounts of data previously inaccessible to humanity. The aim of this project is to develop a system to make it easier to access the data produced by/for the Cardiff University Computer Science Abacws building. Making this data more accessible opens the door to a range of possible applications and people wishing to access, process and utilise sensor data for the building. During this report I will explain the t...[more]
George Haddon-GillGenerating fake GPS trajectoriesPadraig CorcoranHiroyuki Kido2021-CM3203
Many location based services (LBS), such as Strava, require users to submit their GPS trajectory which may come from a smartphone or Sat Nav system. If a user is concerned about their privacy, they may wish to obfuscate or hide their true trajectory. This can be achieved by submitting to the LBS a set of fake trajectory along with the true trajectory. If the LBS cannot differentiate between the true and fake trajectories, they can determine which is the actual true trajectory. The goal of this p...[more]
Georgios PsevdiotisMyBookChoice - A reading books recommender algorithm and websiteDr Daniela TsanevaHantao Liu2021-CM3203
Sometimes people find it difficult to decide what book to read next or are unaware what new books have been printed. The aim of this project is to create a recommender system in the form of a web site, which uses a recommendation algorithm returning the results of recommended books to the user depending on the criteria they have selected. The website would have to provide visual selection of the desired book features and easy to use, as well as responsive, while also being efficient in recommend...[more]
Gregor WebsterFirst Person Shooter Bots Via Reinforcement LearningFrank C LangbeinYulia Cherdantseva2021-CM3203
This project's focus was the building of better FPS bots through the use of reinforcement learning, and specifically the area of sample biassing as a means of achieving that improvement. To find out if sample biassing was a useful improvement, data needed to be gathered on both unbiased and biassed programs. To that end, a simple reinforcement learning algorithm was adopted and adapted to generate the data needed. After six runs, three unbiased and three with varying levels of bias, sufficient d...[more]
Harvey AllenSentiment Analysis of Financial News Headlines with Market ComparisonIrena SpasicMartin J Chorley2021-CM3203
This project is based on the following Kaggle dataset: Scraped from CNBC, the Guardian, and Reuters official websites, the headlines in these datasets reflects the overview of the U.S. economy and stock market every day for the past year to 2 years. Data scraped from CNBC contains the headlines, last updated date, and the preview text of articles from the end of December 2017 to July 19th, 2020. Data scraped from the Guardian Business ...[more]
Henrijs PrincisExplainable SAT Proofs for Social Choice and Argumentation TheoryRichard BoothHiroyuki Kido2021-CM3203
The aim of this project is to implement the workflow described by Geist and Peters [1] for generating concise human-readable mathematical proofs for theorems via the use of SAT solvers. Initially the focus will be on theorems in the area of social choice, before potentially branching out into argumentation theory or matching theory. The project will involve research on automated theorem proving, SAT solvers, explainable AI (XAI). Possible project outputs include: - Comparison of the performanc...[more]
Jake HarkinsPredict Animal Movements using Collar data Help Fight Poaching and Save AnimalsCharith PereraYulia Cherdantseva2021-CM3203
This project suits for a student who is highly motivated to make an impact on wildlife conservation activities, support climate change mitigation and fight against poaching activities. The student will be supported and advised by a team including academics and PhD students. This project is a collaboration between Cardiff University’s Danau Girang Field Centre (DGFC) (, School of Bioscience and the School of Computer Science. Your project is ...[more]
James Goodrick-ClarkeMusic makes you run faster...Martin J ChorleySylwia Polberg2021-CM3203
Both Spotify and Last.FM allow you to access a list of a user's recently played tracks. Multiple services exist for tracking exercise (Strava, Fitbit, Runkeeper, ...) and associated data (heartrate, pace, ...). I'd like to create an app that allows you to compare your exercise data with your recently played music over a large time period to determine whether the music you were listening to has any impact on your performance in the exercise. This could be created as a secure web application acc...[more]
Joseph Wilson-HallNon-Photorealistic Rendering with Spot ColourPaul L RosinYukun Lai2021-CM3203
In a previous paper I developed a method (using traditional computer vision techniques) to add "spot colour" to images: That is, colour is added to region (or regions) of a black and white image to make it look more attractive or interesting. The aim of this project is to tackle this problem, but using the power of deep learning![more]
Juncheng ChenExplainable machine learning for exploiting technical and fundamental indicators in stock tradingYuhua LiYipeng Qin2021-CM3203
The aim of this project is to use machine learning to combine technical analysis and fundamental analysis in stock trading. Technical analysis and fundamental analysis are two commonly employed investment tools for timing the market and select stocks. Technical analysis often relies on daily price or trading volume, and is usually applied for short-term trading, while fundamental analysis focuses on financial ratios and more suitable for long-term investing. Hedge fund managers have argued that,...[more]
Kalvin WillisModelling Cyber-Attacks on Modbus TCP Protocol in ICSNeetesh SaxenaYuhua Li2021-CM3203
This project designs, develops and implements cyber-attacks on Modbus TCP protocol in ICS. You really need strong interest in programming (Python), you will be given the code which you need to understand and alter to mount cyber-attacks and obtain results/impact.[more]
Kriti ShewaramaniComparative Analysis of Tree-Based Machine Learning Models and Neural Networks for Malware PredictionYuhua LiSandy Gould2021-CM3203
In the age of technology, malware attacks are occurring every day around the world. These attacks involve a malicious software that can lock up essential files, spam you with ads, or redirect you to malicious websites which can result in anything from data theft to the destruction of entire systems or devices. Cybercriminals use different types of malware like trojans, ransomware, spyware, or worms to infect individuals or organizations. Machine learning is a credible technology in today’s day...[more]
Laura ChoyVirtual Reality educational puzzle using logic gates and 3d space limitationsParisa EslambolchilarJing Wu2021-CM3203
The project aims to introduce logic gates and truth tables in an educational game. The project will use Unity with the SteamVR plugin to create a Virtual Reality environment and Blender for 3D models. The puzzle space consists of a small cube with multiple input and output points on the surface area and a truth table. The user then selects appropriate logic gates and wires to connect the input and output gates inside the cube to match a given truth table . The challenge is to reverse engineer t...[more]
Lida WenCreating Othello AI Players Combining Heuristic Evaluation And Reinforcement LearningBailin DengHantao Liu2021-CM3203
This project aims to explore possible ways of creating AI players that are capable to make sensible decisions in the board game Othello. The complexity and interactivity make this topic particularly interesting. To achieve the aim, the project starts with analysing the background, rulesets and advanced strategies used in the game. A GUI has then been designed with Pygame to visualise the game. Four types of intelligent agents are created, which are Heuristics, Minimax, MCTS and DQN. Another thr...[more]
Malaika MiahDo people know what emoji ‘really’ mean?Sandy GouldStuart M Allen2021-CM3203
Billions and billions of emoji are sent around the world every day. The Unicode Consortium defines which emoji exist and assigns a text description to each pictogram. But in reality we find emoji are used in many different ways. Sometimes consciously, sometimes not. In this project, you will try to understand whether people’s understanding of emoji matches the definition given by the Unicode consortium. If not, how do these understandings vary? For this project you will make use of web-program...[more]
Marley SudburyDetecting metastatic tissue in lymph nodes with deep learningPaul L RosinDave Marshall2021-CM3203
To track the spread of a tumour, pathologists examine lymph nodes in the surrounding area for metastatic growths. This is done by looking at high resolution scans of slides with tissue taken from the lymph nodes. Deep learning systems have demonstrated a great ability to classify images, and so researchers have looked at applying these techniques to the problem of tissue classification, including lymph node classification, with the aim of creating a system which can aid pathologists. In this pro...[more]
Matthew HarrisHow we can elevate our storytelling to better invest our audience in a modern world.Nervo Verdezoto DiasHiroyuki Kido2021-CM3203
Following from my CM3116 Design Thinking module, I'm hoping to continue my research into how writers can elevate their stories to better engage their audience in a modern world. This project aims to solve the issue of a general lack of engagement within stories being told in modern media. The aim of this project is to find the most effective methods of engaging audiences in different forms of media, and to identify the ways that writers are able to take advantage of these methods, to elevate th...[more]
Matthew Hermanautomated testing of Web Applications courseworkMartin CaminadaBailin Deng2021-CM3203
One of the coursework assignments of Web Applications is to build a site that calculates the date of Easter for a particular year. Currently, much of the testing (and marking) is done automatically. However, with student numbers on the rise, we are interested in having a way to automatically test and evaluate some of the aspects. The difficulty, however, is that this testing needs to work on a wide variety of designs that the students come up with. In particular, we are interested in testing whe...[more]
Matthew LarbyTheatre Company Website and BackendDr Daniela TsanevaChris B Jones2021-CM3203
Custom Website Features for a Client Client: Silchester Players – Amateur Theatre Group IMDB style show history page •Over 130 shows spanning over 45+ years •Searchable/Filterable by cast or crew member •Also shows photos from each show (see next item.) Custom Image Gallery Widget •Photos are already stored on Google Photos but theres no embeddable gallery for including it on the website since Google bought out and discontinued the Picasa galleries in 2016. Blog page •(Partially Star...[more]
Mingrui FangChinese Chess AI PlayerYukun LaiOktay Karakus2021-CM3203
The project aims to investigate different AI techniques for building an automatic game player for Chinese chess and then evaluate and discuss their performance and strength through a series of tests and data comparisons.[more]
Naomi DavidsonApplying Route Optimisation to Rota Generation for Home-Help ServicesRichard BoothNatasha Edwards2021-CM3203
This project is about developing and implementing an algorithm to solve a particular real-world problem. You are the boss of a company that organises home-help visits for elderly patients. Your staff is made up of a fixed number of support workers who must visit a fixed number of homes, spending a set amount of time at each home. Each patient has preferences about the number and timings (e.g., "not before 10am", "between 1pm and 2pm") of the visits they receive each day. You must assign staff to...[more]
Nomair ShahzadDigital Learning – Education of the futureNatasha EdwardsCharith Perera2021-CM3203
The COVID-19 pandemic resulted in world-wide disruption to life. Whilst all industries have been negatively affected by the pandemic, some have been hit harder than most. Arguably the most important area affected by the pandemic is the education sector. A joint report published by UNESCO, UNICEF and the World Bank states that COVID-19 pandemic-related school closures affected more than 1.6 billion learners and the current generation of students now risk losing $17 trillion in lifetime earnings (...[more]
Pablo Stutt CastroAutomated Region-of-Origin Classification of Traditional Music from Peninsular SpainAndrew JonesStuart M Allen2021-CM3203
In recent years, interest in the field of Music Information Retrieval (MIR) has grown significantly, particularly in the field of Music Genre Classification (MCR). However, these studies often focus on contemporary musical genres, and traditional music is entirely absent from relevant datasets such as the GTZAN dataset. This project attempts to carry out some initial research in the field of automated classification of audio recordings of traditional music, and to research the challenges that th...[more]
Peter SnookDrone forensics investigationShancang LiPadraig Corcoran2021-CM3203
You will be provided with a few Drone images that can be used to conduct drone foresnic investigation, including evicence extraction from cameras, GPS, connectivities, geolocation match, etc.[more]
Rachael HansonDesigning an Interactive Application to Promote Healthy Ageing among Older Adults at HomeNervo Verdezoto DiasJames Osborne2021-CM3203
Prerequisites: -Basic knowledge of Human-Computer Interaction and user-centered and/or participatory design methods -Experience developing mobile and/or web applications in several platforms (e.g., Android, HTML5 & Javascript, etc.) -Desirable experience with Spanish (not mandatory) Digital health technologies are becoming increasingly prevalent to support and enhance the everyday experiences of older adults. However, their potential to promote healthy ageing practices has been limited. T...[more]
Rhys ConnorAnalysing The Raspberry Pi as a Cost Effective Solution for SMEsMartin CaminadaCrispin Cooper2021-CM3203
The objective of this is to analyse Raspberry Pi’s as a low energy and low cost solution for small enterprises and start-ups. This would look at the Raspberry Pi and analyse it when compared to a more traditional server set up.[more]
Ruslan LevondDevelop an IoT Edge device to Capture and Classify Species using Sounds to Support Wildlife Conservation ActivitiesCharith PereraVíctor Gutiérrez Basulto2021-CM3203
Wildlife has been in danger for quite some time from various kinds of human activities, ranging from directly destroying habitat to impact from climate change caused by human's unsustainable way of living. Many organisations have established conservation projects and activities to try to mitigate the effects and save wildlife, one of the most important activities of which is monitoring species. Automatic sound recognition systems have proven to be an effective tool used during conservation activ...[more]
Rytis DerzinauskasUtilising technology to improve the shopping experience in grocery stores of customers with dietary restrictionsNervo Verdezoto DiasFederico Liberatore2021-CM3203
My topic area is 'Customers with dietary restrictions'. Whether that would be because of their allergies, ethical beliefs, religion, or health condition. My aim is to find an easier everyday solution for customers to quickly access information whether a product in a grocery store has any ingredients that they cannot consume. This will help both customers and businesses avoid misfortunes where a person consumes a product that has ingredients they are allergic to or do not want to consume. My ...[more]
Safah AhmedThe Role of Technology on Women's SafetyCarolina Fuentes ToroNatasha Edwards2021-CM3203
I have started work on this topic area in the Design Thinking and prototyping module, where I have conducted initial interviews to get more insight around the problem and began to identify the solution. I want to develop this project further by doing more research and interviews to create a prototype of the solution, this is likely to be wearable technology such as a smart watch with GPS tracking features.[more]
Samantha HughesSpelling Practice / Spelling Test - tailored toward students with Dyslexia.Helen R PhillipsYulia Cherdantseva2021-CM3203
This project will consider an Automated or Semi-Automated Assessment Tool, supporting children to undertake spelling tests as part of synchronous (potentially in-class) or asynchronous learning materials. This will be tailored towards students with dyslexia as they will be able to change font colour, style and background colour. Additionally, it will allow the teacher to show more or less feedback depending on the severity of the case. My client for this project will be Matthew Moloughney.[more]
Samuel BowenNatural Language Processing (open proposal)Jose Camacho ColladosJing Wu2021-CM3203
This is a placeholder proposal for students interested in Natural Language Processing (NLP). I am open to suggestions in different areas including applications of NLP techniques in specialized domains. For this project, the student should have a clear idea of the area they want to work on (even if of course this can be further discussed and refined). Ideally, the student should have experience in Python for NLP/Machine Learning.[more]
Sam WinkworthInteractive Data Science to Help Tackle Climate ChangeCharith PereraStuart M Allen2021-CM3203
This project suits for a student who is highly motivated to make an impact on wildlife conservation activities, support climate change mitigation and fight against poaching activities. The student will be supported and advised by a team including academics and PhD students. This project is a collaboration between Cardiff University’s Danau Girang Field Centre (DGFC) (, School of Bioscience and the School of Computer Science. Danau Girang Fie...[more]
Saul OllettCardiff Youth Service Digital platform for staffCatherine TeehanBailin Deng2021-CM3203
Cardiff Youth Service are looking for a digital platform, tool or application for the workforce to be able to work digitally agile and embrace technology. The platform will allow staff and volunteers to plan youth work sessions, record reflections and view upcoming service events, a clear link to all of the above which will then be able to be viewed by a manager for sign off and then to senior management team[more]
Shaikha AlshehhiMachine learning model to identify attacks on IoT device.Amir JavedHiroyuki Kido2021-CM3203
The project aims to build a machine learning model to identify an ongoing cyberattack on IoT devices. The ML model will be built by analysing a publicly available labelled dataset . The project will be carried out in three stages : Stage 1 1.Downloading and cleaning of the dataset. This will require you to download captured pcap file of malicious traffic. 2.Transforming the dataset into a machine-readable format. Stage 2 By using a programming l...[more]
Shakur DualeWeb Application that uses algorithms to automatically identify patterns on financial charts.Federico LiberatoreParisa Eslambolchilar2021-CM3203
My final project proposal is a web application that uses custom algorithms to identify candlestick patterns on financial charts while also teaching users what they are and how each pattern works. Candlestick patterns are an essential tool in trading any financial market. Therefore, a solution like this would be educational and help newer traders be more successful and also save time for veteran traders who are analysing charts manually. A lot of potential features are still undecided.[more]
Smit JiteshBuilding energy usage predictionYuhua LiHelen R Phillips2021-CM3203
Prediction of building energy consumption is important to electricity distribution, management and environment. This project will develop a machine learning model to predict energy usage based on historic usage rates and observed weather. A relevant project can be found at This project requires good programming skills (preferably in Python), knowledge of machine learning (regression).[more]
Su LiIndustry Partners Relationship Management SystemWendy K IvinsSylwia Polberg2021-CM3203
Over the last ten years the School of Computer Science and Informatics has built up its engagement with industry and other external partners to provide meaningful opportunities to engage with students. These include: Placements – including Professional Placement Year, Summer Placements, Work Experience; International – including Study Abroad and Global Opportunities; Projects – where partners act as clients and propose project ideas; Employability– including networking events, promotin...[more]
Tapan AgarwalLearning to Detect and Recognise Road SignsYukun LaiMartin Caminada2021-CM3203
To improve driving experience, computer vision techniques are widely used for providing assistance. The project aims to develop a prototype that implements some machine learning technique to detect and recognise road signs from real world camera footage. Such technology is also an essential component for autonomous driving.[more]
Thomas ClareSimulating a Robot Swarm in a Factory settingBailin DengHelen R Phillips2021-CM3203
The purpose of this project is to develop a visualisation and planning tool for large scale robot warehouses. Allowing the user to change characteristics and see how they can affect the efficiency of the warehouse, and in doing so allow users to find optimal characteristics. In addition to this it will also act as a visualisation tool for teaching people how robots can be used for large scale automation in this style of factories. It would also serve to demonstrate the advantages of using artifi...[more]
Thomas LaffertyMedical image processing - lesionsPaul L RosinYukun Lai2021-CM3203
This project will use a large database of images of skin lesions and attempt to perform automatic recognition of melanomas (cancer). The first step will be to segment the lesions, i.e. locate the region of interest in the image. This will be done by using rules to combine several techniques. Next, the regions are described by their shape , colour and texture to identify whether the lesion is malignant or not. The project will be based on techniques from the following paper: H. Ganster, A. Pinz...[more]
Thomas Lea-RedmondFlake8 Linter for On-going Feedback on Student CourseworkStuart M AllenXianfang Sun2021-CM3203
Based on a project I did during the Summer for the university. Project brief was a proof-of concept coursework evaluator using Flake8. The idea was to take the common coursework feedback ie dont use global; or this function should return an integer value, and make a tool that evaulated the students work and give them the tailored feedback. Continueing this work would include making this more apllicable to other settings for example other COMSC modules; and a "does this actually work" evaluation...[more]
Tian Sou Zen TanVisualizing deep reinforcement learningJing WuFederico Liberatore2021-CM3203
Reinforcement learning (RL) enables agents to learn by interacting with the environment. The agent collects experience from trail-and-error and optimises its action rules from the environment feedback. In recent years, deep reinforcement learning, such as DQN [1], has achieved superhuman performance in playing chess, Atari games, etc. However, interpreting the behaviour of a deep RL agent is challenging, due to both the 'black-box' nature with deep learning and the randomness and long-time learn...[more]
Tim LaneData Anarchy: Building A Social Media Platform Where Users Control Their DataKathryn JonesNatasha Edwards2021-CM3203
Despite the introduction of various laws and measures seeking to regulate digital data in the past few decades, there are still a huge number of issues surrounding data privacy and data control that have not been addressed. While major laws and regulations such as GDPR and PIPL do have a significant influence globally they only capture a small subset of problems surrounding data as they focus primarily upon personal data. From a technical perspective, centralised web applications are also inhere...[more]
Tom Alfano-HughesSpelling Practice / Spelling TestHelen R PhillipsFederico Liberatore2021-CM3203
This project will consider an Automated or Semi-Automated Assessment Tool, supporting children to undertake spelling tests as part of synchronous (potentially in-class) or asynchronous learning materials. This will be tailored towards students with dyslexia as they will be able to change font colour, style and background colour. Additionally, it will allow the teacher to show more or less feedback depending on the severity of the case. My client for this project will be Matthew Moloughney.[more]
Tyler JenkinsMusic makes you run faster...Martin J ChorleyCarl Jones2021-CM3203
Both Spotify and Last.FM allow you to access a list of a user's recently played tracks. Multiple services exist for tracking exercise (Strava, Fitbit, Runkeeper, ...) and associated data (heartrate, pace, ...). I'd like to create an app that allows you to compare your exercise data with your recently played music over a large time period to determine whether the music you were listening to has any impact on your performance in the exercise. This could be created as a secure web application acc...[more]
Yao XiaoGenerating and visualising realistic plantsYukun LaiSylwia Polberg2021-CM3203
Plants come with complicated structures and lots of details. They are also very common in our daily lives. In computer graphics, to render a realistic outdoor scene, plants are often needed to be constructed. In many cases, we don't need to reconstruct a specific tree, but more likely expect the tree to be realistic looking. There are a large number of literatures looking at different approaches of generating trees or other plants in the computer. Practically, you can use e.g. L-system (http://e...[more]
Yongyi WuFace image decomposition and manipulationJing WuChris B Jones2021-CM3203
The appearance of a face is a joint effect from multiple factors including the shape, texture, and environment illumination. Altering any of these factors will change the appearance presented in face photos. This project will adopt the decompose-alter-combine process to manipulate the face appearance in photos. The student is expected to 1) explore and implement existing methods to decompose a face photo into different visual cues, e.g. facial contours, shading, reflectance/texture; Candidate te...[more]
Yuechao WangStudent Learning System App——Mobile ApplicationBeryl NoeLouise Knight2021-CMT404
1、Target & Background ● Background Due to Novel coronavirus pneumonia (COVID-19), in order to protect the safety of students, schools in most countries around the world change from offline teaching to online teaching, but the current student learning system can only view course materials and course playback on the computer, it cannot be done through mobile phones or ipad. ● Target Realize that the student learning system on the mobile phone can watch the live broadcast of the cou...[more]