Master of Research (MRes) Technology is a postgraduate course that will allow you to focus your research interests on one or two areas of technology and work towards translating your learning into research related outputs – such as a submission for a peer-reviewed publication; a peer reviewed research/knowledge transfer grant application, or a presentation.

MRes Technology can be studied either full time (1-year) or part time (2-years), with start dates in September and January each year. You will develop a wide variety of skills, experience and competence on this course, and the MRes will provide a thorough grounding for students moving towards Doctoral (PhD) studies, or pursuing research related activities as a career.

The course is taught within the Faculty of Technology and many of the projects listed on this page are linked to research that is undertaken in our School of Computing. If you'd like to propose your own idea for a research project in the fields of computing and technology, email Dr Alice Good to discuss feasibility and potential supervisors.

AI and Machine Learning techniques for Assisted Living

Supervisors: Dr Rinat Khusainov

Ambient Assisted Living (AAL) explores how technological solutions and infrastructure can allow people with additional care needs to live independently in their preferred environment. Elderly people and those with long-term health conditions are two of the largest target groups for AAL systems. Due to the rapid increases in the cost of traditional care models and approaches, and the challenges presented by an ageing population, AAL is hugely important to the future of healthcare services.
 One of the main areas for AAL systems is Recognition of Activities of Daily Living (ADL), which can be used to detect common emergency situations, such as falls. Monitoring ADL has also the potential to help with more complex issues, such as medication, personal care, activity levels, and behaviour trends – all of which are essential to creating a safe independent living environment. The aim of this project is to investigate applications of AI techniques (in particular, machine learning and computer vision) to ADL recognition and analysis.

This project is part of the Computational Intelligence Research Group at the University of Portsmouth.

A novel digital forensic tool for assessing the suspect's IT competency level

Project supervisor: Dr Fudong Li

Over the last few years, the number of computer assisted crimes has increased significantly; as a result, investigators need to examine a large number of computing devices which can be time consuming.

One of the factors that could be used by the investigator to determine how much time should be spent during the triage phase is the suspect’s IT competency level, such as less time for a novice users computer and more time for an advanced users device.

With the aim of advising the investigator to allocate sufficient time when triaging a new case, this project aims to design and develop a novel forensic tool that can be used for assessing the suspect’s IT skill level based on the information collected during the device seizure phase and also the data presented at the forensic image.

A novel SDN driven Intrusion Prevention System for Smart Grids

Supervisors: Dr Stavros Shiaeles

Software Defined Networking (SDN) is a new paradigm transforming the way IT networking infrastructures are managed, controlled and configured. The SDN perspective relies on the separation of the control plane (i.e., the network intelligence) from the data plane (i.e., packet forwarding). The control plane then comes under the responsibility of a centralised controller that takes all flow forwarding decisions in the network.

The communication between the two planes is achieved through the OpenFlow protocol specified by the Open Networking Foundation (ONF). The Idea of this research project is to deliver a machine learning SDN Intrusion Detection System (IDS) to protect critical infrastructures. 

This project is part of the Network and Security Research Group at the University of Portsmouth.

An advanced analysis tool for digital forensics

Project supervisor: Dr Fudong Li

Over the past 15 years, digital forensics has experienced increased challenges, including expanding data storage, the prevalence of embedded flash storage, the need to analyse multiple devices, and the use of encryption.

These are an extra burden on the work of the human investigator who carries out the manual and time consuming analysis process, resulting many outstanding cases. This project will investigate the existing analysis tools of digital forensics and develop a novel advanced analysis tool that aims to remove some of the human cognitive load and offer informed decisions.

Automatic Gift Aid: Domain Specific Visualisation for the Charity Sector

Supervisors: Dr David M Williams

Do you want to help a revolution in charitable donations be visualised? This research shall provide a realistic visualisation front-end to enable end users to interact with a mathematical model of a software architecture/design as if it were the final implementation.

The existing model is of Swiftaid, a system designed by Streeva to automate the Gift Aid process. Donors register their bank card such that Gift Aid is automatically added to every contactless donation they make, enabling charities to address the £560million of Gift Aid that goes unclaimed each year.

To create an interactive visualisation of the Event-B models, you will be using BMotionWeb, a tool built on top of the ProB Java API.

This project is part of the Network and Security Research Group at the University of Portsmouth.

Bio Inspiring Intrusion Prevention System (IPS) system for Smart Cities

Supervisor: Dr Stavros Shiaeles

This project is focused on studying cyber threats to Smart Cities, and how these threats can be mitigating using Intrusion Prevention Systems (IPS) models inspired by nature, such as swarm intelligence and ant colonies.

The project requires good knowledge of Python and an understanding of machine learning in order for the model to be implemented and evaluated.

This project is part of the Network and Security Research Group at the University of Portsmouth.

Blockchain-based Trust Model for Cloud Identity Management

Supervisor: Dr Stavros Shiaeles

Secure and reliable management of identities has become one of the greatest challenges facing cloud computing today, mainly due to the huge number of new cloud-based applications generated by this model, which means more user accounts, passwords, and personal information to provision, monitor, and secure.

Currently, identity federation is the most useful solution to overcome the aforementioned issues and simplify the user experience by allowing efficient authentication mechanisms and use of identity information from data distributed across multiple domains.  This project aims on building upon existing work [1] proposed and enhance it.

  1.  Bendiab, K., Kolokotronis, N., Shiaeles, S., & Boucherkha, S. (2018, August). WiP: A novel blockchain-based trust model for cloud identity management. In 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech) (pp. 724-729). IEEE

Blocks-based program construction for a textual language

Supervisor: Dr Matthew Poole

Blocks-based programming languages such as Scratch are attractive environments in which to learn to program. Chunking of code into blocks reduces cognitive load, and drag-and-drop program construction avoids syntax errors. However, many learners need to program with traditional textual languages. Some recent work exists on a blocks-based environment for introductory procedural programming in Python.

This project will investigate design ideas to enable object-oriented programming (for example, in Python) using blocks. Core issues to be investigated include visual representations of objects and block-based structuring of classes. Design ideas will be prototyped and evaluated. Candidates should be familiar with Python and JavaScript.

This project is part of the Computational Intelligence Research Group at the University of Portsmouth.

Clinical outcome modelling

Supervisors: Professor Jim Briggs and Professor David Prytherch

The Centre for Healthcare Modelling and Informatics (CHMI) at the University of Portsmouth is a long-established health informatics research and innovation group.

In collaboration with Portsmouth Hospitals and other partners, our work in clinical outcome modelling has supported the development of the VitalPAC vital signs collection system and the National Early Warning Score (NEWS), which recommended by the Royal College of Physicians, among many other projects.

We offer several projects involving applying statistical or data science techniques to clinical data sets in order to derive new clinical knowledge or improve clinical practice.

Context-Sensitive Information Retrieval and Service in Mobile Ad Hoc Societies

Supervisors: Dr Linda Yang

This project aims at providing intelligent context-sensitive information searching and services in Mobile Ad Hoc Societies. The challenge is to use information coming from different sources to provide proactive information services adapted to the user’s context such as activities or location. In many cases, this involves dealing with large amounts of sensor and location data and information resources that are distributed across multiple sites.

This research focuses on developing new search, classification and context-sensitive recommendation technologies that will allow mobile information systems to be truly usable and valuable. The project will apply and evaluate the proposed theory in the practical settings towards end-users scenarios, expecting to deliver exploitable and ready-to-use products and services.

This project is part of the Network and Security Research Group at the University of Portsmouth.

Data mining methods for risk prediction in intensive care units

Supervisor: Dr Mohamed Bader

This study aims to investigate the development of data mining methods for analysing large-scale medical data.

The study will focus on the Intensive Care Unit (ICU) as it is one of the most data-intensive units in the healthcare system. The study will be based on the Philips eICU and Mimic database, which contains more than 3 million ICU stays and billions of medical measurements collected from more than 400 hospitals.

Research students will join an existing team working on risk and mortality prediction in ICUs. The team has access to an existing preprocessed ICU database that is compatible with several data mining and data analytics tools.

Deep fuzzy modelling

Supervisor: Dr Alexander Gegov

Deep learning has gained significant attention within the computational intelligence community over the recent years. Its success has been mainly due to the increased capability of modern computers to collect, store and process large volumes of data. This has led to a substantial increase in the effectiveness and efficiency of data management. As a result, it has become possible to achieve high accuracy for some benchmark learning tasks such as object classification and image recognition within a short time frame.

The most common implementation of deep learning has been through neural networks due to the ability of their layers to perform multiple functional composition as part of a multistage learning process. In spite of the significant recent advances in deep learning discussed above, there are still some open problems and serious limitations.

In particular, effectiveness is usually adversely affected when the data is not well defined due to inherent noise, uncertainty, ambiguity, vagueness and incompleteness. This has an adverse impact on efficiency due to the necessity to define the data better by means of additional collection, analysis and cleaning. The reduced effectiveness and efficiency undermines the ability of deep learning to address real life tasks that are safety critical or time critical.

Besides this, deep learning has been used mainly in a passive manner for the purpose of observing the environment. But its not been used to change the environment in an active manner as much. Finally, deep learning models often have poor transparency which makes them difficult for understanding and interpretation by non-technical users.

The aim of this project is to address some of the problems and limitations discussed above with the help of deep fuzzy models. The latter have been around in different forms and under different names such as hierarchical fuzzy systems and fuzzy networks. These models are well suited for performing multiple functional composition at both crisp and linguistic level. Moreover, they have the potential of handling effectively and efficiently data that is not well defined due to the use of a fuzzy approach. Also, deep fuzzy models can be used in both passive and active manner with regard to the environment due to their generic structure. Finally, these models have a high level of transparency due to their rule based nature.

This project is part of the Computational Intelligence Research Group at the University of Portsmouth.

Emerging darknets

Supervisor: Dr Gareth Owenson 

Darknets are often championed as places of freedom and liberty, but the reality is that they more often than not provide a safe place for criminals to trade and publish their wares.

Darknets are designed to make it difficult for law enforcement to understand what is going on and where actors are located. In this project, you will examine new and emerging darknets to analyse them for vulnerabilities and develop attacks that can be utilised by law enforcement.

You will have experience programming in a language such as C or Java, understand networking concepts like TCP and UDP, and have at least a basic understanding of cryptographic primitives (for example, public/private key, block cipher, etc).

Formal Behaviour Driven Development

Supervisors: Dr David M Williams

Do you know your gherkin from your cucumber? This research aims to unite Formal Modelling with Behaviour Driven Development. Business stakeholders write acceptance tests in collaboration with the development team to capture the desired behaviour of the system. These can be understood at both a technical and non-technical level, thus act as both system requirements and acceptance criteria.

When formal modelling is also required within a rigorous software engineering development process and alongside this there is a desire to use behaviour driven development then there may be duplication of effort or conflicts between the approaches.

This research shall identify and demonstrate circumstances in which the two approaches can be united; you will be writing gherkin specifications and Event-B models.

This project is part of the Network and Security Research Group at the University of Portsmouth.

Hashgraph Analysis

Supervisors: Dr David M Williams

Is a graph stronger than a chain? Hashgraphs are proposed as an alternative to typical blockchain platforms as a means of establishing distributed consensus. The platform is designed for speed, fairness and security and avoids the need for proof-of-work.

However, unlike the more common platforms, this alternative distributed ledger technology has not undergone significant rigorous analysis. In this research you shall implement or simulate a demonstration hashgraph and use this to analyse the system against its system requirements. 

This project is part of the Network and Security Research Group at the University of Portsmouth.

Image-based Authentication

Supervisors: Dr Linda Yang

The project is aimed to support existing research in authentication. Textual passwords have been the most widely used authentication method for decades. However, a strong textual password is hard to memorise and recollect. Image-based passwords were proven to be easier to recollect.

As a result, users can set up a complex authentication password and are capable of recollecting it after a long time even if the memory is not activated periodically. In this project the student will be expected to implement an authentication system based on the graphic images, which will protect users from becoming victims of shoulder surfing attacks.

This project is part of the Network and Security Research Group at the University of Portsmouth.

Impact of virtual communities on health outcomes

Supervisor: Dr Alice Good

With rapidly evolving technological communications, virtual communities are transcending many aspects of our lives, including commercial, social, education, health and wellbeing.

Health related virtual communities and Electronic Support Groups (ESGs) offer a peer to peer community support forum that enables people to seek and offer advice and support relating to specific health areas.

The aim of the project is to carry out a systematic review on the health benefits of these communities and groups when used as an adjunct support intervention.

This project is part of The Centre for Healthcare Modelling and Informatics (CHMI) at the University of Portsmouth, a long-established health informatics research and innovation group.

Internet of Things – Wireless Sensor Networks (indoor location based systems)

Project supervisor: Dr Amanda Peart

Navigating indoors is challenging as the outdoor Global Positioning System (GPS) satellites do not currently work in the indoor environment, hence the need for alternative technologies.

Wireless Sensor Networks (WSN) are capable of sensing and communicating data, and can gather and send data through the network as part of the Internet of Things. There are many challenges with ensuring the data produced is sent and received in a time critical way.

This research focuses on the challenges of indoor location based detection using WSN. This includes the accuracy, timeliness of the data transmitted and received while maintaining satisfactory Quality of Service (QoS). This is not only directing but also redirection of people or items based on key criteria.

Intelligent motion planning for the robot grasps

Supervisor: Dr Zhaojie Ju

Different shapes and colours of manipulated objects provide a challenge for dexterous robot grasps, which are crucial to many robot applications, such as home assistance, industrial robot tasks, robot entertainment and robot healthcare.

The aim of this project is to find the best way to grasp objects and hold them while moving, using machine learning algorithms. An experimental robotic arm with a gripper end-effector will be provided and used to grasp different shapes of objects.

This project is part of the Computational Intelligence Research Group at the University of Portsmouth.

Investigating the challenges, opportunities and impact AI can have on the education sector

Supervisors: Petronella Beukman and Dr Mihaela Cocea 

How will the education sector respond to Artificial Intelligence (AI)?

One of the simplest but most impactful things AI can do for the educational space, is to speed up the administrative processes for educators. Some of the more complex applications focus on the development of intelligent tutoring systems that use test responses to personalise how students navigate through materials and assessments targeting the skills that students need to develop, as well as the introduction of teaching robots to teach linguistics to young learners.

The aim of this research is to investigate the challenges, opportunities and impact for AI in a range of educational settings, from enhancing autonomous learning to improving communication and interaction between teaching robots and students.

You should have experience in the field of AI as well as an understanding/interest in pedagogy and psychology.

This project is part of the Computational Intelligence Research Group at the University of Portsmouth.

Machine learning for digital marketing

Supervisor: Dr Mohamed Bader 

With the continuous growth of e-commerce and online sales, digital media is rapidly becoming the core marketing venue for many retailers companies. This growth has allowed retailers to gather data about their customers and their shopping behaviour. However, analyzing and mining this data is still a challenge. This project aims to use machine learning and data mining methods for developing product recommender systems and analyzing the various digital marketing data. The project will be based on real-world data and will run in collaboration with industrial partners.

Mobile apps and wellbeing

Supervisor: Dr Alice Good

Mobile applications are increasingly being used to help manage wellbeing. Examples of projects in this area within the School of Computing have looked at the potential of apps in facilitating reminiscence therapy for people with Alzheimers and supporting adherence to Post Natal Depression interventions.

We recognise the importance of designing theory based apps that are specifically tailored towards the needs of the intended user group. We offer projects that evaluate the effectiveness of these apps from both practitioners’ and caregivers’ perspectives. We also offer projects that focus on providing an evaluation of mobile apps that support wellbeing from both a theoretical and usability perspective. Ideas for proposals for new mobile apps to support wellbeing are also welcome.

This project is part of The Centre for Healthcare Modelling and Informatics (CHMI) at the University of Portsmouth, a long-established health informatics research and innovation group.

Multi-agent systems for practical artificial intelligence

Supervisors: Professor Adrian Hopgoood

This project can be about either the development or application of multi-agent artificial intelligence (AI). Agent-based AI systems use multiple techniques collaboratively, e.g. neural networks, deep learning, rules, probabilistic modelling, case-based reasoning, fuzzy logic, and genetic algorithms.

Most real-world problems are multifaceted, and therefore require such a mixed-mode approach. Prior work has led to the development of a multi-agent software framework known as DARBS (Distributed Algorithmic and Rule-based Blackboard System) which can form the start point for this project.

Several updates and improvements can be envisaged as the basis of an MRes project. An additional exciting possibility would be the development of a new portable version for mobile devices. An alternative project would be the application of the existing framework to any application area of interest.

This project is part of the Computational Intelligence Research Group at the University of Portsmouth.

Personal motion detection app – machine learning to achieve correct physiological positioning in fitness

Project supervisor: Dr Amanda Peart

Each year, thousands of people take up some form of fitness goals. Many of them follow exercise videos or apps without expert guidance, such as a personal trainer. This means that many people will not be undertaking the correct physiological movement for the exercise being attempted, which often results in injury.

This research will investigate whether a simple app can assess whether a person new to exercise is undertaking a particular activity correctly.

It is anticipated that communication via the app can inform the person on what they need to move to attain the correct position for the required exercise.  To achieve the aim of this research, machine learning will need to be utilised to generate the correction requirements of the movement.

Quality of service within wireless ad hoc networks

Project supervisor: Dr Amanda Peart

As the enterprise network infrastructure grows, so does the importance of achieving satisfactory Quality of Service (QoS) throughout the whole network infrastructure. This has become critical with the growth of the Internet of Things.

The aim of QoS is to ensure that the network can guarantee to run high priority applications, such as streamed media, as well as critical time dependant traffic. This must be balanced with other traditional network traffic within a finite network capacity.

This constraint leads to differentiated services handling, based on priorities of traffic which require specific bandwidth capacity within the network infrastructure. This research focuses on developing protocols to improve QoS in enterprise network infrastructures with finite network capacity.

ReDI: Restoring Deleted Images Forensics Tool

Supervisors: Dr Stavros Shiaeles

The problem of restoring deleted files from a scattered set of fragments arises often in digital forensics. File fragmentation is a regular occurrence in hard disks, memory cards, and other storage media. As a result, a forensic analyst examining a disk may encounter many fragments of deleted digital files, but is unable to determine the proper sequence of fragments to rebuild the files.

The aim of this project is to investigate the problem and produce a new tool that will be able to assist forensic examiners image reconstruction process. Candidates should have experience in machine learning and Python programming, or be willing to learn about these.  

This project is part of the Network and Security Research Group at the University of Portsmouth.

Remote dexterous robotic hand control

Supervisor: Dr Zhaojie Ju

Dexterous robotic hands are able to perform certain actions as humans do. This project is aimed at transferring human hand skills to a robotic hand, where a surface electromyography (sEMG) sensing system is used as a way to capture human hand motions. The hand motions will be analysed and recognised for the robot to perform a desired task using machine learning and pattern recognition algorithms.

This project is part of the Computational Intelligence Research Group at the University of Portsmouth.

Scalable Federated Identity Management (Single Sign-On)

Supervisors: Dr David M Williams

Have you ever used your Google account to sign into an app not developed by Google? Federated Identity Management enables users registered with the Identity Provider within one domain to access services at a partner domain, without requiring them to also register with the identity provider in the second domain.

Replacing bilateral agreements between identifiers with a network thereof provides scope to enable a large, scalable, decentralised network of users and services. This research aims to resolve the challenge of routing authentication requests and responses around such a decentralised network of identity providers.

This project is part of the Network and Security Research Group at the University of Portsmouth.

Secure Distributed Hash Tables

Supervisors: Dr David M Williams

What's your favourite peer-to-peer network? Distributed Hash Tables (DHT) are decentralised and distributed means of providing a lookup service that underlie peer-to-peer networking.

However, DHT-based systems are prone to security attacks, such as Sybil and Eclipse attacks. Existing surveys of the security issues and proposed solutions do not cover the full range of DHT algorithms nor vulnerabilities. This research shall aim to contribute to the existing literature by identifying and addressing gaps in the security analysis of DHTs.

This project is part of the Network and Security Research Group at the University of Portsmouth.

Sentiment analysis from textual data

Supervisor: Dr Mihaela Cocea

The amount of data we produce has sharply increased giving rise to the big data era. IBM has estimated that 80% of this data is “unstructured”, with text being one of the most prevalent format, yet our machine learning algorithms perform less well on textual data than other types of data, especially when focusing on tasks capturing opinions and other subjective aspects. This project will investigate different machine learning algorithms for classification of textual data, with a particular interest in fuzzy classifiers which can deal with ambiguity. Candidates should have experience in machine learning or data mining, or be willing to learn about them.

This project is part of the Computational Intelligence Research Group at the University of Portsmouth.

Task design for an intelligent sports assistant robot

Supervisor: Dr Zhaojie Ju

Mobile robots with manipulators will be very popular in future applications, such as assistive home robots and sports robots. In this research, a robotic arm on a track base with a gripper as the end-effector will serve as an experimental sports auxiliary. This project will study a ping-pong ball collecting task, investigating both ball detection path planning with methodologies in artificial intelligence.

This project is part of the Computational Intelligence Research Group at the University of Portsmouth.

The application of augmented reality in apprenticeship training

Supervisor: Athanasios Paraskelidis

Emerging technologies such as Augmented Reality (AR) provide a unique opportunity to improve accessibility to teaching material, encourage independent learning and speed up the learning process.

This project innovates by bringing AR technology into engineering apprentice students’ teaching and learning experiences. It will demonstrate how AR technology could revolutionise the delivery of quality teaching material to students in a digital form. The use of AR in learning applications has been documented for schools and higher education but it has not been represented in apprentice training.

Exploring the possibilities of using AR in this domain is expected to benefit apprentices and their instructors alike, and to contribute to the literature on the use and effectiveness of AR learning objects. Previous experience on Augmented and/or Mixed Reality is desirable but not essential. Candidates with experience of Java/JavaScript programming are particularly welcome.

Touchscreen-optimised real programming environment

Supervisor: Dr Jacek Kopecky

One of the major limitations of mobile devices (smartphones, tablets) compared to laptops and desktop computers is that it is not easy to create real programs on touchscreen-oriented devices. This project would research ways in which interactions with hand-held devices (such as touch, voice, etc.) could substitute typing when programming, as touchscreen typing in modern programming languages is painfully slow.

Traffic flow fingerprinting

Supervisor: Dr Gareth Owenson

A range of protocols on the Internet now use encryption to hide the content of messages. Whilst encryption is principally a net-gain for society, protecting people’s information, for law enforcement it presents a difficulty in conducting authorised surveillance.

In this project, you will examine techniques of analysing timing and sizes of encrypted messages to generate fingerprints for particular types of activity and/or destination using machine learning. You will then deploy this in the real world and evaluate its efficiency.

You will have experience programming in a language such as C or Java, understand networking concepts like TCP and UDP, and have at least a basic understanding of cryptographic primitives (e.g. public/private key, block cipher, etc).

This project is part of the Network and Security Research Group at the University of Portsmouth.

Understanding patterns of inconsistent data quality in electronic healthcare records

Supervisor: Dr Philip Scott

Many hospitals have seen the use of digitised medical records (scanned paper) as a means to save money on administration and improve access to records. In the United Kingdom (UK), Government policy has repeatedly promoted the move away from paper records in health care. However, published UK experience has shown that clinical usability of the digitised hospital record can be poor and potentially have negative effects on operational processes. Even full electronic patient records (EPRs) have had detrimental impact on clinical productivity, both in the USA and recent UK implementations.

This project is part of The Centre for Healthcare Modelling and Informatics (CHMI) at the University of Portsmouth, a long-established health informatics research and innovation group.

Web accessibility audit

Supervisor: Dr Alice Good

Web accessibility continues to be an issue for many users. Despite the availability of standards and guidelines there is still a significant shortfall of compliance. Where non-compliance to design standards prevails, there will always be users who are faced with barriers. Learning potential, inclusion and empowerment are all issues that are affected by inaccessible web pages. An investigation commissioned by the Disability Rights Commission (DRC) found that 81 per cent of websites fail to meet the most basic standards for accessibility (2004). We are interested to identify how web accessibility has improved since then. The aim of this research is to carry out an audit of selected websites and evaluate their accessibility using a range of user centred methods.

This project is part of The Centre for Healthcare Modelling and Informatics (CHMI) at the University of Portsmouth, a long-established health informatics research and innovation group.

Other research projects

MRes Technology research projects are offered in the following areas:

Please note, these lists are not exhaustive and you'll need to meet and discuss the project you're interested in with a member of research staff before you apply.

This site uses cookies. Click here to view our cookie policy message.

Accept and close