PATS2
You are not logged in
Time stamp: 14:43:59-22/8/2019

[Login]

2012 | 2013 | 2014 | 2015 | 2016 | 2017 | 2018 | 2019
[PDF/Print]

Projects from 2019

StudentTitleSupervisorModeratorModule
Alexander StantonDematerialisation of Share Certificate with BlockchainGeorge TheodorakopoulosFederico Cerutti1819-CM3203
Currently when a person has purchased shares in a company, they are issued a share certificate. Dematerialisation is the process of taking these physical certificates and putting them into an online system. This project aims to create a prototype blockchain application to dematerialise physical share certificates onto a blockchain ledger with the ability to trade them between members of the system.[more]
Austen WellsPrivate Browsing ForensicsMichael DaleyXianfang Sun1819-CM3203
The aim of this project is to investigate if Private Browsing on the web is truly private. A thorough investigation will be conducted to uncover any left-over data/information after a Private Browsing session across the five major web browsers: Internet Explorer, Microsoft Edge, Safari, Google Chrome, and Mozilla Firefox. This research will be used to highlight which Private Browser is most private. The five privacy modes that were probed in this project were: ‘InPrivate Browsing’ in Inter...[more]
Benjamin HughesReinforcement learning for autonomous drivingKirill SidorovMatthias Treder1819-CM3203
As you probably know, engineering Cardiff Racing team have successfully competed in Formula Student UK for the past 12 years. Recently, Formula Student Germany have pioneered a new class in this competition: driverless racing. Our engineering students are now looking to build a team towards participating in this driverless class in the future years. This project would look into developing certain components of the software for a future driverless race car. There are many interesting tasks to be...[more]
Caleb StrideCreating a dataset of 3D deformed shapes for evaluating 3D model registration techniquesPaul L RosinYukun Lai1819-CM3203
3D scanned data has become increasingly popular with the advent of low-cost devices such as the Kinect. There are many applications of 3D data, such as gaming, cinematography special effects, 3D printing, etc. Due to unavoidable occlusion, multiple scans of an object are usually required to reconstruct the full shape. Many surface registration techniques have been developed to align multiple scans. However, so far, techniques for evaluating the registration techniques are still very limited. T...[more]
Craig WinfieldMachine learning: Deep Learning to predicting Age and Cognitive Ability from MRIsMatthias TrederFrank C Langbein1819-CM3203
The average age of the population is steadily increasing; therefore, we need to look for earlier signs of deterioration in cognitive ability. The earlier that abnormalities are spotted, the sooner and better they can be treated, and MRIs can spot early signs of disease before any symptoms become visible. An MRI is a 3-dimensional medical imaging technique used in radiology to form pictures of the anatomy and the physiological processes of the body in both health and disease. MRI scanners use str...[more]
Daniel HarborneTowards a Best Practices Approach to Dataset Image Augmentation in Deep Learning Image Classifier TrainingDave MarshallKirill Sidorov1819-CM3203
It is well established that one weakness of the widely adopted deep learning approach to image classification is the large volumes of labelled training data required to produce a robust model. This can be particularly challenging if instances of some classes within the classification task are rare within the task domain and thus, making finding example data to train with difficult. Further to this, even when example data is available for all classes, annotating large volumes of data usually requ...[more]
Daniel HendryImplementation of a data privacy protection tool for transaction dataJianhua ShaoVíctor Gutiérrez Basulto1819-CM3203
As an increased amount of data being gathered and stored, how to protect the private information contained within such data sets becomes an important issue. One of the recent approach to addressing this issue is called k-anonymisation, which attempts to make any record in a data set identical to at least k-1 other records (hence no individual could be identified). This project aims to implement a software tool based of a version of k-anonymisation in the form of k^m-anonymisation, where this is ...[more]
Daniel HuntleyLocation-based services with MongodbAlia I AbdelmotyChris B Jones1819-CM3203
MongoDB is a powerful nosql database that is being adopted by many businesses worldwide. It offers some powerful functions to store and search for geo-referenced data. You will write an interface to the database to allow users to express and customise location-based queries (where is the nearest post office, which is the nearest Pizza restaurant to my location, etc. ) to simulate realistic functions that underpins location-based services on mobile applications. The project will provide you wit...[more]
Daniel MorganDelineating regions of interest in MRI/S prostate scans for cancer diagnosisFrank C LangbeinJing Wu1819-CM3203
Prostate cancer is the second most common cancer in men worldwide. Earlier diagnosis combined with better staging and treatment has lead to a decrease in death rates for most developed countries. Magnetic resonance imaging and spectroscopy (MRI/S) plays an important role in differentiating malignant from benign prostate tissue. We are working on a project utilising machine learning techniques to devise an assistant to the radiologist to help in this differentiation. The aim of this project is t...[more]
Dean BaleSports Scheduling Problems with Entertainment MaximisationRichard BoothVíctor Gutiérrez Basulto1819-CM3203
Sports scheduling (i.e., the problem of deciding which teams should play each other in which week) provides a rich problem to attack in the area of integer linear programming. Typical constraints would take the form: - teams 1 and 4 can't play each other in week 4. - teams 4 and 5 can't play each other in the same week as teams 2 and 3. - Attendance objectives: given a projected attendance for each game and each week, maximise the total projected attendance. This project will be about implemen...[more]
Deeon RoyDeep Learning Guitar TuningsDave MarshallBailin Deng1819-CM3203
Guitars can be tuned to a a variety of tunings. This is especially common in certain genres of music, notably folk music and heavy metal, for example. The basic idea here is to take recordings on music played in known guitar tunings. I have database of known songs in know tunings by a variety of artists and have the associated recordings. A deep learning system can then be trained with input samples (many short snippets from every recording) and trained to classify the tunings. New music can t...[more]
Dimosthenis AntypasTracking Beliefs and Trust in Social NetworksRichard BoothIrena Spasic1819-CM3203
In a social network, people receive information about the world from people they are "friends" with. These friends are in turn influenced by their friends, and so on. Furthermore we trust some friends more than others with regard to certain topics, e.g., I might have one friend who I trust regarding financial matters, but not regarding medical matters. This project will be about taking an exisiting java program that simulates propagation of information in a social network, and augmenting it to t...[more]
Dominic RoutleyCloud Engineering University ModulePadraig CorcoranDavid W Walker1819-CM3203
I intend to create a proof-of-concept university module focusing on Cloud engineering/operations. This is not intended to be fully fleshed out as I believe that to do so would probably be beyond the scale of a three month project. I do intend however that everything is at least described and any software that has to be used (either from an admin point of view or student point of view) is at least mocked up to show its potential usage. Items that may be created: - 2 Example coursework assignm...[more]
Eloise CollingsA personal diary appAlia I AbdelmotyJames Osborne1819-CM3203
A lot of people may be interested in a simple way of keeping a diary of events in their day- whom they met, they talked to, where they went, how they felt. Some of this information can be extracted automatically from their location traces on their phones and from their activity on social web sites. You will build an app that will automatically track and record some of these personal information and present it to the user in the form of a browsable diary. You will be able to build upon/make u...[more]
Evdokia MinaFinding the Optimal Job Assignment for a Home-Help ServiceRichard BoothLuis Espinosa-Anke1819-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]
George GoodallSmart contracts with Blockchain (multiple projects)George TheodorakopoulosDavid W Walker1819-CM3203
Blockchain is the technology that underpins Bitcoin, but there are many more applications for Blockchain, with potentially large business and societal impact. One of the recently proposed applications is smart contracts https://en.wikipedia.org/wiki/Smart_contract. The aim of this project is to implement a smart contract prototype. To undertake this project, you will need to understand the basics of cryptography and to have programming experience.[more]
Haya AlsultanEvaluating Intrusion Detection Systems in IoTPhilipp ReineckeCharith Perera1819-CM3203
This project will focus on evaluating Intrusion Detection Systems in an IoT environment. Metrics for evaluation will be defined regarding the quality of detection and performance of the system, then investigations will be run on Intrusion Detection Systems such as Bro and Snort to evaluate their detection with smart devices. Based on the results, an attempt to automate the evaluation technique will be made. Finally, Analysis of the systems will be done in order to judge and compare their perform...[more]
Jack CorscaddenMulti-player game with AI and networking [multiple projects, must be specialised in discussion]Frank C LangbeinMatthew J W Morgan1819-CM3203
For this project you may choose an arbitrary game that is played between at least two people based on the players taking turns. The aim of this project is to implement a user interface and game engine to run this game and add artificial intelligence and/or networking capabilities to the game (depending on the specific nature of the game). There should be a core interface to the game engine for any player-decisions where the player decisions can either come from some AI program, a local or remote...[more]
James GrantInvestigating Security vulnerabiities in Internet of Things DevicesEirini S AnthiPhilipp Reinecke1819-CM3203
The popularity of Internet of Things (IoT) devices (e.g. amazon echo, smart bulbs, smart cameras, smart sensors) has significantly increased over the past few years. This is due to their ubiquitous connectivity, allowing them to exchange information with other technologies and their decision-making capabilities to invoke actions. This provides seamless user experiences which significantly enhance people's everyday lives and is demonstrated by how prominent IoT is today. Nevertheless, although th...[more]
Joseph SingletonImplementation and Analysis of Truth Discovery AlgorithmsRichard BoothFederico Cerutti1819-CM3203
With the vast amount of data available in today's world, particularly on the web, it is common to find conflicting information from different sources. Given an input consisting of conflicting claims from multiple sources of unknown trustworthiness and reliability, truth discovery algorithms aim to evaluate which claims should be believed and which sources should be trusted. The evaluations of trust and belief should cohere with one another, so that a claim receives a high belief ranking if it is...[more]
Joshua Hornsby3D Engine and Turn-Based Strategy Game with AIFrank C LangbeinMatthew J W Morgan1819-CM3203
Adjust description for specific project, as discussed. For this project you may choose an arbitrary game that is played between at least two people based on the players taking turns. The aim of this project is to implement a user interface and game engine to run this game and add artificial intelligence and/or networking capabilities to the game (depending on the specific nature of the game). There should be a core interface to the game engine for any player-decisions where the player decisions...[more]
Karan JujTracking Poachers using the Internet of Things [BLE Beacons]Charith PereraJing Wu1819-CM3203
In this project, you will use IoT technologies to develop a solution to track poachers. This is a real-world project, where we expect to deploy the solution in the Lower Kinabatangan Wildlife Sanctuary in Sabah, Malaysia in collaboration with Danau Girang Field Centre (https://www.cardiff.ac.uk/danau-girang-field-centre)[more]
Luke JonesPizzaBox: Studying Internet Connected Physical Object Manipulation based Food OrderingCharith PereraHantao Liu1819-CM3203
This paper presents the designing and testing of PizzaBox, a 3D printed, interactive food ordering system that aims to differ from conventional food ordering systems and provide an entertaining and unique experience when ordering a pizza by incorporating underlying technologies that support ubiquitous computing. The PizzaBox has gone through both low and medium fidelity testing while working collaboratively with participants to co-design and refine a product that is approachable to all age group...[more]
Markuss BaumgartsSystem for downloading up to date webpages for offline viewingPadraig CorcoranLuis Espinosa-Anke1819-CM3203
The aim of this project is to develop a system which will automatically download one's favourite webpages when free Wi-Fi networks are available so that they may be viewed offline at a later time when such networks are not available. The system should check if a webpage has changed since the last time it was downloaded and if so download the current version. This project requires good web programming and database skills.[more]
Nashalung RaiMachine analysis of where people look in images and videosHantao LiuPaul L Rosin1819-CM3203
Do you know where you are looking at while watching online videos? Do you know where the computers think you are looking at? Modelling visual saliency - predicting where human eyes pay attention to in visual content - has been a very active research area over the past few years in both academia and industry. This project aims to investigate saliency modelling in emerging applications in image and vision computing, such as computer rendered images, high-dynamic-range (HDR) imaging, medical imagin...[more]
Nathan MellyActivity monitoring AppAlia I AbdelmotyCharith Perera1819-CM3203
People willingly give their location tracks, activity records and other health indicators when using smartphones and fitness bracelets. This project will examine the sort of personal information that can be collected with a Fitbit HR tracker and develop an app that stores and anlayses this data for personal use. Data mining of this data to extract a user profile is possible which then allows the application to alert the user if their behaviour deviates from their "normal" profile (for example, ...[more]
Nicole KanAssessment timetable and scheduling systemHelen R PhillipsPaul L Rosin1819-CM3203
Currently the School of Computer Science & Informatics provides students with a coursework timetable that is developed by each year tutor. The fact that there is a variety of people producing the timetables means that they are inconsistent and take time for several staff members to produce. This timetable is as generally just a excel spreadsheet. These timetabes are also not dynamic, ao if there are changes to coursework handin handout dates the timetabes have to be manually altered. Stud...[more]
Nojus LenciauskasLocation-based services with MongodbAlia I AbdelmotyNatasha Edwards1819-CM3203
MongoDB is a powerful nosql database that is being adopted by many businesses worldwide. It offers some powerful functions to store and search for geo-referenced data. You will write an interface to the database to allow users to express and customise location-based queries (where is the nearest post office, which is the nearest Pizza restaurant to my location, etc. ) to simulate realistic functions that underpins location-based services on mobile applications. The project will provide you wit...[more]
Patricia BoothForensic analysis of Smart WatchesHelen R PhillipsBailin Deng1819-CM3203
Forensic analysis of 2 common smart watches, analysing the watch itself and when it is synchronised to a users phone. With the increasing number of users of smart watches, it is ideal to analyse the data being stored in these devices. Experimenting with methods on how to physically acquire data. If the results indicate that the data that held on these devices are of forensic value then it should be further studied.[more]
Rhys BeckettIoT Skullfort: Exploring the Impact of Internet Connected CosplayCharith PereraRichard Booth1819-CM3203
In this paper, we explore the potential impact of Internet of Things (IoT) technology may have on the cosplay community. We developed a costume (an IoT Skullfort) and embedded IoT technology to enhance its capabilities and user interactions. Sensing technologies are widely used in many different wearable domains including cosplay scenarios. However, in most of these scenarios, typical interaction pattern is that the costume responds to its environment or the player’s behaviour (e.g., colour of...[more]
Samuel MantleInvestigating Radio Frequency vulnerabilities in the Internet of Things using HackRFEirini S AnthiKirill Sidorov1819-CM3203
The significant increase in Internet of Things (IoT) devices, which routinely collect sensitive information, is demonstrated by their prominence in our daily lives. Although such devices have simplified and automated every day tasks, they have also introduced tremendous security flaws. The insufficient security measures that are currently being employed to defend these smart devices make IoT the 'weakest' link to breaking into a secure infrastructure, and therefore an attractive target for cyber...[more]
Samuel WilliamsLogic circuit builderDavid W WalkerPhilipp Reinecke1819-CM3203
The aim is to develop a software environment for building computer logic circuits from simpler circuits. At the lowest level the simplest circuits are NAND, NOR, NOT, AND, OR, and XOR gates. The environment must include a graphical user interface allowing circuits to be dragged, dropped, and connected to build more complex circuits. These circuits can then be stored and subsequently used to build yet more complex circuits. The environment should also be able to generate truth tables for circuits...[more]
Sara AldossaryCredit Card Fraud Detection using novelty detection techniquesYuhua LiGeorge Theodorakopoulos1819-CM3203
See https://www.kaggle.com/mlg-ulb/creditcardfraud/home for description of the problem. Talk to me if you want to know novelty detection techniques before you choosing this project.[more]
Scott HulbertSecure votingGeorge TheodorakopoulosYuhua Li1819-CM3203
The aim of this project is to implement a client-server voting application. The client should be able to vote anonymously, but no unauthorized party should be able to vote on behalf of an authorized voter. The server should be able to properly authorize legitimate voters and reject everybody else. The implementation could be on mobile devices or on regular computers. This project requires experience with programming and understanding of cryptography at the level of CM3110.[more]
Sean TomlinsonEvaluating Deep Learning Techniques for Automated Sleep Stage Scoring of EEG DataMatthias TrederPaul L Rosin1819-CM3203
We will be evaluating the use of different neural network architectures with the purpose of developing a classifying deep learning system. This system should be capable of automatically sleep stage scoring human sleep data from a multivariate EEG source. We will be working with Cardiff University’s NaPS Laboratory (Neuroscience and Psychology of sleep) and CUBRIC (Cardiff University Brain Research Imaging Centre) with the hopes of providing a system that can aid in the scoring of their data to...[more]
Sebastian GolosData analysis of where people look in videosHantao LiuBailin Deng1819-CM3203
Do you know where you are looking at while watching online videos? Do you know where the computers think you are looking at? Modelling visual saliency - predicting where human eyes pay attention to in visual content - has been a very active research area over the past few years in both academia and industry. This project aims to analyse visual attention data in emerging applications in image and vision computing, such as computer rendered images, high-dynamic-range (HDR) imaging, medical imaging...[more]
Timothy BirdActivity Recognition on Body dataFrank C LangbeinMatthias Treder1819-CM3203
Obtain data from wearable sensors to recognize data. Tasks 1) Create Sensor system 2) Gather Data 3) categorize Data 4) Evaluate Data 5) Create simple Front end if time[more]
Wei TehGenerating Differentially Private Datasets Using Deep Learning (in collaboration with: Office for National Statistics)George TheodorakopoulosLuis Espinosa-Anke1819-CM3203
Government organisations, businesses, academia, members of the public and other decision-making bodies require access to a wide variety of administrative and survey data to make informed and accurate decisions. However, the collecting bodies are often unable to share sensitive data without risking breaking the confidentiality and consent checks required to obtain this data. Therefore, researchers have proposed many methods for generating synthetic data to replace the raw data for the purposes o...[more]
William CooterGame with a purposeIrena SpasicAngelika Kimmig1819-CM3203
A game with a purpose (GWAP) is a human-based computation game developed to address the problem of creating difficult metadata (https://en.wikipedia.org/wiki/ESP_game). The idea behind the game is to use the computational power of humans to perform a task that computers cannot (originally, image recognition) by packaging the task as a game. Rules of the game Once logged in, a user is automatically matched with a random partner. The partners do not know each other's identity and they cannot com...[more]