Enhanced Deep Learning and Semantic-based Predictive Analytics for Reactive IoT Applications and Streaming Data

The emergence of Internet of Things (IoT) has formed a bridge that connects most of the real-world entities with the related computer entities. Its general objectives includes: Sensing critical information from the external physical environment; sampling of internal system signals and; obtaining meaningful information from sensor data to perform monitoring and proactive decision-making process.

Furthermore, the application of IoT technologies and data analytics has been found to provide opportunities for innovative applications across fields such as: Industrial IoT and cyber-physical systems, intelligent transportation systems (ITSs), smart building, and many other related areas. In these domains, data streams produced from different sensors can form meaningful insights by drawing patterns to support real-time events in reactive and Complex Event Processing systems(CEPs).

Mostly IoT streaming data comes with various quality and data heterogeneity challenges that prevents interoperability requirements of data and associated smart systems. These streaming data requires some semantic or Intelligent-driven processing to achieve data interoperability, analysis and automated inferencing to support real-time prediction and proactive management of some smart systems and safety-critical systems.

The field of Complex event Processing is known to be capable of real-time processing of IoT streaming data, but unable to provide the predictive functionalities that are readily provided the Machine Learning nd related statistical models. In addition CEP uses set of rules to support the processing IoT streaming data but does not include support for historical data, which in itself can help in drawing pattern from the data and gaining better insights.

On the contrary, Machine Learning approach has been known for its ability to support predictive analytics, but are not suitable to support data and device interoperability, semantic stream modelling and real-time reasoning of IoT streaming data.

Therefore, it is necessary to set a foundation that can form a bridge between these technologies and the semantic technology in order to be able to achieve both effective and efficient stream analysis and proactive prediction of events in real-time safety-critical systems.

The objectives of the PhD study is not limited to the following:

• Develop an adaptive Machine Learning or AI model suitable for the processing and analysis of IoT Streaming data for real-time event prediction
• Adopt a suitable approach for the combination of historical and rea-time IoT streaming data to support the continuous analysis and correlation for accurate and trusted predictions from events to support reactive applications or systems.
• Develop a prototype intelligent-driven software architecture that support IoT stream quality management and predictive analytics from integration of semantic-based processing and enhanced AI-based models, thereby forming a bridge between ML-based data analytics and semantic technologies.

Academic qualifications 

A first-class honours degree, or a distinction at master level, or equivalent achievements ideally in Computer Science/Computing, Mathematics, Data Science, Computer engineering/Electronics, Any other numerate discipline. 

English language requirement 

If your first language is not English, comply with the University requirements for research degree programmes in terms of English language. 

Application process 

Prospective applicants are encouraged to contact the supervisor, Dr Oluwaseun Bamgboye ([Email Address Removed]) to discuss the content of the project and the fit with their qualifications and skills before preparing an application.  

Contact details 

Should you need more information, please email [Email Address Removed]. 

The application must include:  

Research project outline of 2 pages (list of references excluded). The outline may provide details about 

• Background and motivation, explaining the importance of the project, should be supported also by relevant literature. You can also discuss the applications you expect for the project results. 
• Research questions or 
• Methodology: types of data to be used, approach to data collection, and data analysis methods. 
• List of references 

The outline must be created solely by the applicant. Supervisors can only offer general discussions about the project idea without providing any additional support. 

• Statement no longer than 1 page describing your motivations and fit with the project. 
• Recent and complete curriculum vitae. The curriculum must include a declaration regarding the English language qualifications of the candidate. 
• Supporting documents will have to be submitted by successful candidates. 
• Two academic references (but if you have been out of education for more than three years, you may submit one academic and one professional reference), on the form can be downloaded here. 

Applications can be submitted here. To be considered, the application must use: 

• “SCEBE1123” as project code. 
• the advertised title as project title 

All applications must be received by 3rd December 2023. Applicants who have not been contacted by the 8th March 2024 should assume that they have been unsuccessful. Projects are anticipated to start on 1st October 2024. 

Download a copy of the project details here.