Research Interest

Dr Otebolaku's research focuses on :

Past and current Research Projects

CAMR: Context-Aware Personalization for Mobile Multimedia(2015)

Goal: CAMR proposed to investigate advanced forms of realizing context-aware personalization by taking advantage of mobile devices’ inbuilt sensors to acquire information concerning usage contexts, monitoring user’s consumptions to build innovative and implicit user profiles. With such gathered data and employing data mining and semantic-based techniques to derive additional knowledge, CAMR provides an innovative solution that can seamlessly or on-demand take decisions to deliver a set of recommendations to mobile users, adapted to their current usage context (e.g. activities that users perform; characteristics of their devices; time of the day; location; network connections; environmental conditions, etc.). Additionally, it proposes the ability to decide whether the resource selected by users from the recommended set of items needs to be adapted to satisfy network or terminal constraints.

Wise-IoT(2018)

Goal: Wise-IoT is a collaborative project between Europe and Korea. From the EU side, it is funded under the H2020 framework program for research of the European Commission. It aims at deepening the interoperability and interworking of IoT existing systems. Use case driven, the project uses the experiences available in the consortium to build a comprehensive mediation framework that can be used between various IoT systems.

Swarms-EU(2016)

Goal: The oceans are considered to host a substantial part of human and industrial resources, namely oil and gas, whose industry will move to ever deeper waters, and where renewable energy continue to be harvested from the seas in offshore wind farms, but also increasingly through tidal, currents and wave energy converters. Furthermore, minerals such as cobalt, nickel, and copper, rare earths, silver and gold will be mined from the seafloor (deep sea mining). To this end, new offshore and port infrastructure will need to be built, monitored and maintained or repaired. The goal is to expand the use of AUV/ROVs and facilitate the creation, planning and execution of maritime and offshore operations to reduce operational cost and improve safety of tasks assigned to divers.


The Overhead Lines(OHL)Collision Avoidance(to start in 2023)

His participation among others will include the use of mobile phones’ in-built sensory data to design mobile app for tracking variability of magnetic field, which will be used to determine the proximity to the OHL with increasing loud alerts to warn users. 

AESSEAL Project(on hold)

1) Improving the rotating shaft running speed estimation of the machinery. Currently the expert system uses a range of analysis techniques in conjunction with c. 150 rules. The accuracy of results from some of those analysis techniques are severely hampered by inaccurate shaft speeds and would benefit from more accurate determination / estimation of this running speed. 

 

2) Using machine learning (ML) / artificial intelligence (AI) to perform zero auxiliary knowledge fault detection (i.e. just using the raw time series vibration waveform). Ideally this would produce a score as to how close the bearing is to failure (e.g., 1 (bearing is like new) - 5 (bearing is at end of life)).  

 

3) Trend analysis of bearing state deterioration. Using multivariate statistical modelling techniques such as Principal Component Analysis (PCA) and Partial Least Squares (PLS), more accurate prediction models for the speed of bearing deterioration may be achievable (e.g. based on historical observations, how long does a given bearing have before complete failure?). 

Prospective Research Projects

AI As Microservices for emerging IoT applications

As data-driven decision-making services are being infused into IoT applications, especially at the Edge-Cloud continuum, Artificial Intelligence (AI) algorithms such as deep learning, reinforcement learning, etc. are being deployed as monolithic application services for autonomous decision processes based on data from IoT devices. However, for latency-sensitive IoT applications such as health-monitoring or emergency-response applications, it is inefficient to transmit data to the cloud data centers for storage and AI-based processing. In this project, an integrated architecture for intelligent Internet of Things based on the concepts of AI as a microservice for the Internet of Things applications, and integration of the concepts Roof, Fog, and Cloud computing and microservices is proposed. Key components, including their functionality, of the architecture, are identified. The architecture is conceived to support the design and development of AI services as microservices, which can be deployed on the federated and integrated edge-cloud platform to provide autonomous units of intelligence at the edge of Things, as opposed to the current monolithic IoT-Cloud services. The proposed system is envisioned as a platform for effective design, deployment of scalable, robust, and intelligent cross-platform for IoT applications that can be deployed to provide improved quality of experience in scenarios where real-time processing, ultra-low latency, and intelligence are key requirements. 

Leveraging Context-awareness to Support Intelligent Decisions in the IoT-Edge-Cloud Computing Continuum

The Internet of Things(IoT) is pushing the boundaries of distributed computing as heterogeneous devices with sensing capabilities are wirelessly connected not only to each other but also to the cloud giving rise to the decentralization of various kinds of intelligent applications and micro/macro datacenters. The need for latency-sensitive applications due to resource-hungry computations and security has led to the emergence of Edge and Fog computing where IoT based computation can be supported close to the edge of networks such as Smart grids. The orchestration of AI-based data analytics and intelligent services in such a scenario requires automated support, allowing context-awareness to help decide where in the Edge/Fog-Cloud continuum data analytics or computation should occur: in the edge/ the cloud or on which edge devices such should happen. Context-awareness can also help to decide where data can be stored for computational purposes. The research to be carried out will focus on how to use context awareness to engineer seamless intelligent services from Edge to Cloud or vice versa to minimize latency especially when real-time data analytics and intelligent decisions are required in the Smart Grid use cases.

Trust based Intelligent Service recommendations in the edge.

Research Collaboration

He's actively seeking research collaborators.

Prospective PhD students are welcome to contact him. 

If you are interested in working with him as a postgrad student(Masters or PhD), drop him an email. a.otebolaku{at}shu.ac.uk