Computational Neuroscience and Cognitive Robotics

Computational Neuroscience and Cognitive Robotics (CNCR) is dedicated to research into computational intelligence, taking inspiration from, and learning from, biology, psychology, medicine and neuroscience. The work of the Centre is directed at achieving a greater understanding of how the biological brain processes information, particularly sensory information, and the translation of critical aspects of that knowledge into smart computational systems that can perform in a way that humans would consider "intelligent". Current research includes work on visual, auditory and tactile processing. The research finds application in medical devices and cognitive robotics, as well as data analytics and big data in medicine, among other areas. The strengths of the group arise from its multidisciplinary ethos and expertise, and the fact that it exploits both software modelling and hardware emulations in its work. Furthermore, its links into neuroscience on the one hand and cognitive robotic applications on the other positions it well for EU, Research Council and industrial funding. Current projects are related to modelling of visual, auditory and tactile sensing and their implementations in hardware (Field Programmable Gate Arrays - FPGAs) and in software; deep learning using big data (funded by Leverhulme), activity recognition using machine learning and applications of AI in risk identification for premature babies.

Areas of strength:

• computational intelligence
• computational neuroscience
• modelling of biological information processing
• biologically-compatible computational modelling of auditory signal processing, in particular tinnitus; modelling of retinal ganglion cells and human visual processing in general
• modelling of tactile devices for human-like sensing

Areas of growing activity: computational modelling are implemented in both software and reconfigurable (FPGA) hardware. The work finds potential applications in medical / healthcare applications and cognitive robotics

Research areas:

• Si Elegans Project – The Si Elegans Project aims at developing a hardware-based computing framework that accurately mimics the nematode C. elegans in real time and enables complex and realistic behaviour. The project replicates the C. elegans nervous system using individual field-programmable gate arrays (FPGAs).
• Hand-Eye coordination – How visual cues and stimulus guides the muscles of the hand, arm and shoulder for interaction with objects. This research uses visual input, which is followed image processing and object recognition analysis, to guide the robot arm and hand into a specific movement, taking into consideration the surroundings and objects it's dealing with.
• Human-Robot Interaction – How human actions produce behaviours in robots, which in turn learn how to move and act around people.
• Robotics for disaster rescue - How robots can be controlled to assist and help in rescue missions where human interaction may be too dangerous.

Recent major grants:

• Leverhulme - Novel approaches for constructing optimised multimodal data spaces
• EU FP7

• Dr João Filipe Ferreira
• Dr Georgina Cosma
• Dr Andreas Oikonomou
• Dr Richard Gault
• Dr Eiman Kanjo
• Mr Pedro Machado,
• Professor Saeid Sanei

• ANTONIADES, A., SPYROU, L., MARTIN-LOPEZ, D., VALENTIN, A., ALARCON, G., SANEI, S. and CHEONG TOOK, C., 2017. Detection of interictal discharges with convolutional neural networks using discrete ordered multichannel intracranial EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25 (12), pp. 2285-2294. ISSN 1534-4320
• COSMA, G., JOY, M., SINCLAIR, J., ANDREOU, M., ZHANG, D., COOK, B. and BOYATT, R., 2017. Perceptual comparison of source-code plagiarism within students from UK, China, and South Cyprus higher education institutions. ACM Transactions on Computing Education, 17 (2), pp. 1-16. ISSN 1946-6226
• COSMA, G., MCARDLE, S.E., REEDER, S., FOULDS, G.A., HOOD, S., KHAN, M. and POCKLEY, A.G., 2017. Identifying the presence of prostate cancer in individuals with PSA levels <20 ng ml−1 using computational data extraction analysis of high dimensional peripheral blood flow cytometric phenotyping data. Frontiers in Immunology, 8, p. 1771. ISSN 1664-3224
• COSTALAGO-MERUELO, A., MACHADO, P., APPIAH, K., MUJIKA, A., LESKOVSKY, P., ALVAREZ, R., EPELDE, G. and MCGINNITY, T.M., 2018. Emulation of chemical stimulus triggered head movement in the C. elegans nematode. Neurocomputing. ISSN 0925-2312
• KANJO, E., YOUNIS, E.M.G. and SHERKAT, N., 2018. Towards unravelling the relationship between on-body, environmental and emotion data using sensor information fusion approach. Information Fusion, 40, pp. 18-31. ISSN 1566-2535
• KERR, D., COLEMAN, S. and MCGINNITY, T.M., 2018. Biologically inspired intensity and depth image edge extraction. IEEE Transactions on Neural Networks and Learning Systems, PP (99), pp. 1-10. ISSN 2162-237X
• KUSS, D.J., KANJO, E., CROOK-RUMSEY, M., KIBOWSKI, F., WANG, G.Y. and SUMICH, A., 2018. Problematic mobile phone use and smartphone addiction across generations: the roles of psychopathological symptoms and smartphone use. Journal of Technology in Behavioral Science. ISSN 2366-5963
• PROCHÁZKA, A., KUCHYŇKA, J., VYŠATA, O., SCHÄTZ, M., YADOLLAHI, M., SANEI, S. and VALIŠ, M., 2018. Sleep scoring using polysomnography data features. Signal, Image and Video Processing. ISSN 1863-1703
• WINGFIELD, B., COLEMAN, S., MCGINNITY, T.M. and BJOURSON, A., 2018. Robust microbial markers for non-invasive inflammatory bowel disease identification. IEEE/ACM Transactions on Computational Biology and Bioinformatics. ISSN 1545-5963 (Forthcoming)