Computing, Informatics and Applications Research Group

Close-up of IT equipment

Our Computing, Informatics and Applications (CIA) research group has a wide remit that includes scientific data processing, smart technology and web/internet technologies. We are particularly interested in how computational and artificial intelligence (AI) methods can be used to improve people's lives and increase productivity.

The group has specific expertise in AI, Machine Learning (ML) and Deep Learning (DL) algorithms and applications, image and signal processing, data visualisation, mobile devices, 2D/3D modelling, distributed computing, wireless environments, the application of sound and imaging technology in healthcare and assisted living, AI in climate change and sustainability, the Internet of Things (IoT), and sensor technology.

Much of the research the group undertakes is applied/collaborative, and includes links with industrial partners.

Our work is primarily focussed in the research areas below:

Imaging Technologies, Vision, Acoustics and Digital Systems

Dr Ian van der Linde, Prof Lakshmi Babu Saheer, Dr Mahdi Maktabdar Oghaz, Dr Silvia Cirstea, Dr Domenico Vicinanza, Dr Jin Zhang, Dr Marcian Cirstea, Dr Ashim Chakraborty, Dr Raj Shukla, Dr Oliver Faust, Dr Otilia Mihaela Boaghe.

Our Imaging Technologies and Acoustics team focuses on AI-based navigation, image and signal processing systems, 2D/3D image modelling, neural networks, inverse problems, numerical modelling of physical processes (electromagnetics, acoustics, psychoacoustics, quantum mechanics), statistical methods, ray-tracing, architectural acoustics, data sonification, data visualisation, auditory display, sound synthesis, remote sensing and satellite image processing, (LiDAR) aerial image terrain identification, tree localisation, tree species identification, mobile devices and technologies for supporting visual impairment.

It also looks at computer aided design (CAD) tools and methods applied to digital systems modelling and rapid prototyping using VHDL and FPGAs.

Artificial Intelligence, Machine Learning, Data Science and Applications

Prof Lakshmi Babu Saheer, Dr Mahdi Maktabdar Oghaz, Dr Ian van der Linde, Dr Silvia Cirstea, Dr Domenico Vicinanza, Dr Jin Zhang, Dr Cristina Luca, Dr Arooj Fatima, Dr Stiphen Chowdhury, Dr Vanessa Ng, Dr Man-Fai Leung, Dr Raj Shukla, Dr Chung-Man Tang, Dr. Faraz Janan, Dr Ashim Chakraborty, Dr Imran Ahmed, Dr Oliver Faust.

Our AI, Machine Learning, Data Science and Applications team has a wide range of research interests that include: data analysis and machine learning techniques; up-to-date theoretical and practical developments and hardware platforms for AI; signal processing; remote sensing for the IoT and how these converge in the emergence of intelligent systems; advanced statistics; machine learning for structured data and graphs; data integration, probabilistic systems; algorithms for massive datasets; large-scale optimisation.

IoT, Machine Learning and Cloud Computing

Dr Mahdi Maktabdar Oghaz, Prof Lakshmi Babu Saheer, Dr Razvan-Ioan Dinita, Dr Imran Ahmed, Dr Raj Shukla, Dr Oliver Faust.

Our IoT, Machine Learning and Cloud Computing team is interested in IoT, smart environments, pervasive healthcare, Human Computer Interaction (HCI), adaptive computational systems, advanced internet and mobile technologies, AI, smart sensors and advanced spectral analysis in biomechanics and biomedical sciences.

Semantic Web and Educational Technologies

Dr Cristina Luca, Dr Razvan-Ioan Dinita, Dr Arooj Fatima, Dr George Wilson.

Our Semantic Web and Educational Technologies team investigates business information systems, open linked data, intelligent internet search and knowledge modelling, online virtual environments, image processing and data visualisation.

AI for Sustainability

Prof Lakshmi Babu Saheer, Dr Mahdi Maktabdar Oghaz, Dr Cristina Luca, Dr. Mahmud Hassan, Dr Raj Shukla.

Our sustainability group focuses on use of data analysis and machine learning techniques to aid climate change related problems of air quality, natural disasters, vegetation, food supply chain, healthcare, transportation, net zero policy, climate adaptation, agricultural and industrial sustainability.

The sustainability group looks at various problems to propose sustainable solutions in different domains with the help of AI, data science, IoT, and emerging technologies such as digital twins, blockchain and federated learning.

The group also looks at internet of medical things (IoMT) based sustainable care for all in the healthcare domain; smart farming, precision agriculture and precision livestock farming in the agricultural domain; and urban green space planning, net zero policy visualisation/planning, climate adaptation techniques and public awareness in the climate change domain.

PhD researchers

Our current postgraduate research students and their projects include:

Burrows, H. IoMT-based respiratory healthcare monitoring. 1st supervisor: Mahdi Maktabdar.

Ehsaniamrei, S. Modelling and optimizing carbon emission factors in food supply chain using artificial intelligence. 1st supervisor: Lakshmi Babu Saheer.

Garbagna, L. Urban green routing and micro-climate modelling. 1st supervisor: Lakshmi Babu Saheer.

O'Reilly, J. Artificial Intelligence‐Based Navigation Aid for Indoor and Low‐Light Environments. 1st supervisor: Silvia Cirstea.

Payne, P. Intelligent Control System Development for Electric Powered Wheelchairs. 1st supervisor: Erika Sanchez-Velazquez.

Sanaei, A. A Novel Multisensory System with an Original Predictive Algorithm to Provide Auditory Feedback of Multidimensional Advanced Coordination and Gait Movement. 1st supervisor: Domenico Vicinanza.

Shaikh, A. An Intelligent Real-Time Anti-Phishing System to Protect Internet Users. 1st supervisor: Michael Cole.

Wamambo, T. Predictive Product Review Analysis Using Sentiment Analysis and Machine Learning. 1st supervisor: Cristina Luca.

Mkpa, A. Dynamic Configurable Model for Addressing Trust, Security, and Privacy in Ubiquitous IoT Network. 1st supervisor: George Wilson.

David, E. A model for decision-making on the priority of requirements for software product lines with multiple target markets and business stakeholders. 1st supervisor: Cristina Luca.

Read more about phd researchers.

Members of our research group have participated in the following projects and partnerships:

  • Green and NetZero policies in collaboration with Colchester Borough Council, ARU Sustainable Futures research theme funds, Jan 2022 – August 2022. £5k.
  • Green routing in collaboration with Colchester Borough Council, ARU QR Funds, Jan 2022 – August 2022. £10k.
  • A Data-driven Health Monitoring Ecosystem Using Artificial Neural Networks and Internet of Medical Things (IoMT) devices and sensors for Proactive Respiratory Care and Diagnoses, ARU QR Next steps, Jan 2022 – August 2022. £10k.
  • Internet of Medical Things (IoMT) for Proactive Elderly Care, ARU Health, Performance and Wellbeing theme award, Mar 2022 – July 2022. £12k.
  • Development of pre-emptive decision making on clinical and operational issues, and apply AI algorithms to identify parties (people) at risk, KTP with AT Medics, October 2019 – March 2022. £200k.
  • Development of large anti-reflection coated lenses for passive (sub)millimetre-wave science instruments, European Space Agency funded, led by Cardiff University, in collaboration with University College London (UCL), Mullard Space Science Laboratory (MSSL), Anglia Ruskin University (ARU) and Stockholm University. November 2019 – November 2021. 51.4k of 600k euros.
  • BIMformed – Adaptive learning for zero-defects in buildings (development of a data collection and machine learning framework to predict and prevent errors in the construction industry), Innovate UK project with TR Control Solutions, February 2019 – April 2020, £120K.
  • Development of a ‘real time’ web-based software platform to replace the current, legacy costing and warehousing program, KEEP+ with Prime Accounting Software Ltd, May 2018 – September 2019, £69k.
  • Development of a secure Instant Messaging social media app for healthcare professionals, KEEP+ with Lana Data Solutions, September 2017 – September 2018, £54k.
  • Urban Living: Integrated Products and Services CR&D, "Hyperlocal Rainfall", 2015-2017, InnovateUK, £33.81k of £230,566.00.
  • Development of a new high performance low cost acoustic absorber for use in new and existing buildings, 2014, Echo2Eco – total 1.1 million for three universities and five companies across Europe.
  • We have also undertaken other KTPs or Knowledge East of England Partners up to £130k with many local and national companies including Sovereign Installations Ltd, Glazing Vision, LMK Thermosafe, Papershrink Ltd, Calex Electronics, I-Dash Ltd.

    Members of our research group have also organised the following:

    • NPAPW2019 – The international conference on network and technology applied to performing arts, Prague 2-4 April 2019.
    • ISIE 2017 – the 26th IEEE International Symposium on Industrial Electronics, Edinburgh, June 2017. Professor Marcian Cirstea was General Chairman.
    • INDIN 2015 – the 13th IEEE International Conference on Industrial Informatics in Cambridge in July 2015. Professor Marcian Cirstea was General Chairman.
Read more about read more about activities, projects and partnerships.

BIMformed: Machine learning framework for predicting and preventing defects in buildings

Funded by Innovate UK, Silvia Cirstea, Razvan Dinita and Javad Zarrin from the School of Computing and Information Science worked with industry partner TR Control Solutions to tackle the challenge of reducing errors in the construction industry.

Availability of data in the construction industry is a major barrier, as most building workers do not get their instructions via digital devices and records of errors are not kept in digital form linked to the construction specification.

To address this problem, the project developed a framework to collect and link up data from a number of sources, including workers’ profiles and understanding of task, captured via a web app, and construction task information extracted from specification models and design documents. AI techniques were used to devise automatic generation of questionnaires to assess operatives' knowledge and understanding of the task.

A machine learning framework, based on Support Vector Machines, was developed and shown to be able to predict the likelihood of construction defects with sufficient reliability and accuracy on a pilot data set.

Following the successful completion of this feasibility study with our partners in April 2020, collaboration continues to develop the framework into a commercial product.

Read more about bimformed: machine learning framework for predicting and preventing defects in buildings.

Selected publications since 2019.

Babu Saheer, L., Bhasy, A., Maktabdar-Oghaz, M. and Zarrin, J. (2022) 'Data driven framework for understanding and predicting air quality in urban areas', Frontiers in Big Data, 5, 822573. Available at:

Burrows, H., Zarrin, J., Babu Saheer, L. and Maktab-Dar-Oghaz, M. (2022) 'Realtime emotional reflective user interface based on deep convolutional neural networks and generative adversarial networks', Electronics, 11(1), pp. 118. Available at:

Das, T., Shukla, R.M. and Sengupta, S. (2022) 'What could possibly go wrong? Identification of current challenges and prospective opportunities for anomaly detection in Internet of Things', IEEE Network, pp. 1-7, Available at:

Shukla, R.M. and Sengupta, S. (2022) 'A novel machine learning pipeline to detect malicious anomalies for the Internet of Things', Internet of Things, 20, 100603. Available at:

Ahmed, I., Jeon, G. and Chehri, A. (2022) 'A smart IoT enabled end-to-end 3D object detection system for autonomous vehicles', IEEE Transactions on Intelligent Transportation Systems. Available at:

Monmasson, E., Hilairet, M., Spagnuolo, G. and Cirstea, M.N. (2021) 'System-on-Chip FPGA Devices for Complex Electrical Energy Systems Control', IEEE Industrial Electronics Magazine. Available at:

Zarrin, J., Phang, H., W., Babu Saheer, L. and Zarrin, B. (2021) 'Blockchain for decentralization of internet: Prospects, trends, and challenges', Cluster Computing, 24(4), pp. 2841-2866. Available at:

Ahmed, I., Ahmad, M. and Jeon, G. (2021) 'Social distance monitoring framework using deep learning architecture to control infection transmission of COVID-19 pandemic', Sustainable Cities and Society, 69, 102777. Available at:

Sapkota, R.P., van der Linde, I. and Pardhan, S. (2020) 'How does aging influence object-location and name-location binding during a visual short-term memory task?', Aging & Mental Health, 24(1), pp. 63-72. Available at:

Bright, P. and van der Linde, I. (2020) 'Comparison of methods for estimating premorbid intelligence', Neuropsychological Rehabilitation, 30(1), pp. 1-14. Available at:

Aggius-Vella, E., Kolarik, A.J., Gori, M., Cirstea, S., Campus, C., Moore, B.C.J. and Pardhan, S. (2020) 'Comparison of auditory spatial bisection and minimum audible angle in front, lateral, and back space', Scientific Reports, 10, 6279. Available at:

Hameed, N., Shabut, A., Hameed, F., Cirstea, S., Harriet, S. and Hossain, A. (2020) 'Mobile-based Skin Lesions Classification Using Convolution Neural Network', Annals of Emerging Technologies in Computing, 4(2), pp. 26-37. Available at:

Smith, L., Stubbs, B., Hu, L., Veronese, N., Vancampfort, D., Williams, G., Vicinanza, D., Jackson, S., Ying, L., López Sánchez, G.F. and Yang, L. (2019) 'Is active transport and leisure time physical activity associated with inflammatory markers in US adults: Cross-sectional analyses from NHANES', Journal of Physical Activity and Health, 16(7), pp. 540-546. Available at:

Moseley, P., Savini, G., Saenz, E., Zhang, J. and Ade, P. (2019) 'Detailed characterization of a lenster - A mm-wave flat lens', IEEE Transactions on Antennas and Propagation, 67(5), pp. 3178-3184. Available at:

Zhao, G., Savini, G., Saenz, E., Zhang, J. and Ade, P. (2019) 'A dual-port THz time domain spectroscopy system optimized for recovery of a sample's Jones matrix', Scientific Reports, 9. Available at:

Oghaz, M.M., Maarof, M.A., Rohani, M.F., Zainal, A. and Shaid, S.Z.M. (2019) 'An optimized skin texture model using gray-level co-occurrence matrix', Neural Computing and Applications, 31, pp. 1835-1853. Available at:

Read more about read more about recent publications.

Contact us

Dr Lakshmi Babu Saheer (Contact for the group):

Dr George Wilson (Contact for external income generation):

Dr Cristina Luca (Contact for postgraduate research student enquiries):