Some of the possible PhD research topics and descriptions are given below.

If you are a potential PhD student, please email me at and express your interest :).
For Northumbria University admission requirements, click here.


Topic: Machine Learning in Network Security

Description: As network applications are increasingly being used with the popularity of broadband networks, network security is very important. The smartphones and computers use various applications for banking and online purchases, and the user needs to use it securely. To perform network attacks like spoofing, flooding, eavesdropping, etc. is so easy with some research. An intrusion detection system looks for different kind of network attacks in the incoming packets. Can we use machine learning to differentiate the attack packet flows, classify attacks and eventually stop them? Can we allow the learning algorithm to understand new kind of attacks and grow in intelligence? Can we use multi-agent approach to tackling this? There is a need for intelligent intrusion detection system that could detect different and dynamic attack patterns, and this research will develop such a system.

Topic: Intelligent Analysis of Qualitative reports

Description: To manually analyse a qualitative document can be time-consuming. For example, a corporate sustainability report is a report that is published by an organisation about the economic, environmental and social impacts caused by its daily activities. These reports can help organisations to measure, understand and communicate the economic, environmental, social and governance performance. A manual analysis can be challenging when the report has hundred or more pages and when there are hundreds of such reports it can be even more challenging. In this research, we will use machine learning techniques along with natural language processing to do automated text analysis of (any) qualitative documents, in relation to their adherence to standard guidelines.


Topic: Intelligent Wireless Sensor Network Application in Healthcare

Description: Wireless inertial sensor network in conjunction with machine learning can be used in healthcare to work with elderly people to monitor their walk pattern and to alert a caregiver or relative when they have an unobtrusive fall. This will be more like an unobtrusive fall detection and alert system. The technology can also be used to monitor less critical patient's behaviour in a care home environment and can alert when an accident happens. The research will involve attaching wearable electronic sensors (depending on what is being monitored) on patients, collecting data wirelessly, analysing the data intelligently and taking action when anything abnormal occurs.


Topic: Artificial Intelligence in Wireless Sensor Network Security
Description: This work will focus on mobile sensor security based on mobile agents (MA). We will review the security requirements, attacks, preventive measures using Mobile Agents on Wireless Sensor Networks (WSN) when applied in a large scale industry. In the face of jamming attacks or other security attacks against the WSN, we will modify the itineraries of the mobile agents to avoid the attack area(s) while not harming the efficient data dissemination from working sensors.  We will explore the use of ant colony, bee colony, swarm intelligence or other nature-inspired algorithms, and its possible modifications. We will thus develop an effective framework that will identify the problematic nodes, execute queries and will know when they resume function.


Topic: Use of Machine Learning in Twitter Feed Analysis

Description: There are many tweets surrounding an event. Many events have an important outcome like in the case of an election, mass protest or a football match. In this research, we will analyse the Twitter feeds surrounding an event using machine learning and will do sentiment analysis and/or behaviour prediction based on our analysis, along with other inputs surrounding that event. But there is also the question of demographics and whether tweets truly represent the intentions and activity of the population as a whole. For example, we can consider tweets pertaining to specific teams and games in the football season and use them alongside statistical game data to build predictive models for future game outcomes.


Topic: Real-time Malicious Behaviour Detection on Mobile Devices 
Description: A smartphone may look innocent, but when compromised by malware it can illegally watch and impersonate the owner, participate in botnet activities, capture personal data and even steal one's money. There can be application based threat, web-based threat and network threats apart from the physical threats of a lost or stolen device. Machine learning techniques can significantly improve the performance of malicious detection, but the existing ones cannot be applied on resource-constrained mobile devices, such as mobile phones, smart watches, etc. In this project, we will optimise the machine learning based malicious detection methods, and enable real-time processing on mobile devices. NOTE: This work will be done along with my colleague Dr Bo Wei.


Topic: Mobility and Resource Management for Wireless Networks

Description: The objective of this research is to propose a mobility and resource management scheme for wireless networks. The whereabouts of the wireless users will be estimated, and accordingly, resources will be granted. This management will be conducted to overcome wireless channel related issues, such as fading and shadowing, and improve Quality of Service (QoS) performance along the entire user’s path of movement with increased bandwidth utilisation. These goals will be achieved by employing state-of-the-art networking features: software-defined networking (SDN), network function virtualization (NFV), and cloud computing (CC). SDN will serve the purpose of separating the control plane from the user plane and abstracting the control functions to separate servers. NFV facilitates the decoupling of the functions’ software from their hardware components, and thus, they can be implemented on any platform. Eventually, mobility and resource management related network functions, services and entities will be implemented in the cloud by taking advantage of SDN and NFV. 


Topic: The Diagnosis of Retinal Vein Occlusion using Machine Learning

Description: This project uses image processing and machine learning. Retinal Vein Occlusion (RVO) is the second most popular reason for vision loss after Diabetic Retinopathy. Among different types of RVO, Central Retinal Vein Occlusion (CRVO) and Branch Retinal Vein Occlusion (BRVO) occurs frequently and the prime cause of visual impairment. Depending on the severity, RVO can be ischemic or non-ischemic. The main cause of vision loss in RVO is the formation of macular edema. A Computer Aided Diagnosis (CAD) system to detect the RVO and its severity can be developed. Instead of emphasizing on the complete vein structure, the central retinal vein can be identified using morphological operations. The different features like hemorrhages, bright lesions and vein tortuosity will be extracted using pixel based operations. Then, using machine learning algorithms Convolutional Neural Network (CNN) or similar can be trained to classify the RVO types viz. CRVO, BRVO and HRVO. This is a current PhD work.


Computer and Information Sciences

Northumbria University
Newcastle, UK

  • Twitter Clean Grey
  • LinkedIn Clean Grey