A complete list of my publications can be found here and via my Google Scholar account.

I have organised a selection of my publications around topics.

Selected Journal papers on Cancer Predictive Modelling. A topic of my work focuses on the development of prostate cancer prediction models. The key driver of this work is in the identification of biomarkers for diagnosing prostate cancer (PCa) stages. The focus is on the development of combinatorial methods to identify a unique immune cell phenotypic profile (‘signature’) of features which are incorporated into interpretable machine learning models.

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
[DOI] https://doi.org/10.3389/fimmu.2017.01771

COSMA, G., ACAMPORA, G., BROWN, D., REES, R.C., KHAN, M. and POCKLEY, A.G., 2016. Prediction of pathological stage in patients with prostate cancer: a neuro-fuzzy model.PLOS ONE, 11 (6), e0155856. ISSN 1932-6203

COSMA, G., BROWN, D., ARCHER, M., KHAN, M. and POCKLEY, A.G., 2017. A survey on computational intelligence approaches for predictive modeling in prostate cancer.Expert Systems with Applications, 70, pp. 1-19. ISSN 0957-4174
https://doi.org/10.1016/j.eswa.2016.11.006

SEYMOUR-SMITH, S., BROWN, D., COSMA, G., SHOPLAND, N., BATTERSBY, S. and BURTON, A., 2016. “Our people has got to come to terms with that”: changing perceptions of the digital rectal examination as a barrier to prostate cancer diagnosis in African-Caribbean men. Psycho-Oncology, 25 (10), pp. 1183-1190. ISSN 1057-9249

Novel Deep Learning algorithms, methods and applications. The focus of this topic is the development of algorithms for overcoming the limitations of existing deep learning algorithms. Particular focus is on multi-modal data fusion, imbalanced and limited data classification using deep learning.

Taherkhani, A, Cosma, G, McGinnity, M (2020) AdaBoost-CNN: an adaptive boosting algorithm for convolutional neural networks to classify multi-class imbalanced datasets using transfer learning, Neurocomputing, 404, pp.351-366, ISSN: 0925-2312. DOI: 10.1016/j.neucom.2020.03.064.

TAHERKHANI, A., COSMA, G. and MCGINNITY, T.M., 2018. Deep-FS: a feature selection algorithm for deep Boltzmann machines. Neurocomputing, 322, pp. 22-37. ISSN 0925-2312

TAHERKHANI, A., COSMA, G., ALANI, A.A. and MCGINNITY, T.M., 2019. Activity recognition from multi-modal sensor data using a deep convolutional neural network. In: K. ARAI, S. KAPOOR and R. BHATIA, eds., Intelligent computing. Proceedings of the 2018 Computing Conference, volume 2.Advances in intelligent systems and computing. (857). Chaim: Springer, pp. 203-218. ISBN 9783030011765

SALESI, S., ALANI, A.A. and COSMA, G., 2018. A hybrid model for classification of biomedical data using feature filtering and a Convolutional Neural Network. In: 2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS), Valencia, Spain, 15-18 October 2018.[Piscataway, N.J.]: Institute of Electrical and Electronics Engineers, pp. 226-232. ISBN 9781538695883

ALANI, A.A., COSMA, G., TAHERKHANI, A. and MCGINNITY, T.M., 2018. Hand gesture recognition using an adapted convolutional neural network with data augmentation. In: 2018 4th International Conference on Information Management (ICIM2018), 25-27 May 2018, Oxford, UK. IEEE, pp. 5-12.ISBN 9781538661482

Spiking and Deep Spiking Neural Networks for image and video classification.

TAHERKHANI, A., COSMA, G. and MCGINNITY, T.M., 2019. Optimization of output spike train encoding for a spiking neuron based on its spatiotemporal input pattern. IEEE Transactions on Cognitive and Developmental Systems. Accepted and To Appear.

MACHADO, P., OIKONOMOU, A., COSMA, G. and MCGINNITY, T.M., 2018. Bio-inspired ganglion cell models for detecting horizontal and vertical movements. In: 2018 International Joint Conference on Neural Networks (IJCNN 2018), Rio de Janeiro, Brazil, 8-13 July 2018. (Forthcoming)

Source-code Similarity Detection. This topic of work involves developing information retrieval and computational intelligence algorithms for detecting semantic similarities in source code for plagiarism detection, authorship detection and source-code categorisation (based on semantic similarity). This work is undertaken in collaboration with Professor Mike Joy and other academics from the University of Warwick.

MIRZA, O.M., JOY, M. and COSMA, G., 2017. Style analysis for source code plagiarism detection – an analysis of a dataset of student coursework. In: M. CHANG, N.-S. CHEN, R. HUANG, KINSHUK, , D.G. SAMPSON and R. VASIU, eds., 2017 IEEE 17th International Conference on Advanced Learning Technologies (ICALT), Timisoara, Romania, 3-7 July 2017. Proceedings,. Los Alamitos, Calif.: IEEE Computer Society, pp. 296-297. ISBN 9781538638705

MIRZA, O.M., JOY, M. and COSMA, G., 2017. Suitability of BlackBox dataset for style analysis in detection of source code plagiarism. In: 2017 Seventh International Conference on Innovative Computing Technology (INTECH), Luton, 16-18 August 2017. Proceedings. Institute of Electrical and Electronics Engineers (IEEE), pp. 90-94. ISBN 9781509039906

COSMA, G., and ACAMPORA, G. 2015.A Fuzzy-based approach to programming language independent source-code plagiarism detection. In: A. YAZICI, N.R. PAL, U. KAYMAK, T. MARTIN, H. ISHIBUCHI, C.-T. LIN, J.M.C. SOUSA and B. TÜTMEZ, eds., 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Istanbul, Turkey, 2-5 August 2015. Los Alamitos, California: IEEE Computer Society, pp. 1-8. ISBN 9781467374286

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

ZHANG, D., JOY, M., COSMA, G., BOYATT, R., SINCLAIR, J. and YAU, J., 2014. Source-code plagiarism in universities: a comparative study of student perspectives in China and the UK. Assessment & Evaluation in Higher Education. ISSN 0260-2938

JOY, M.S., SINCLAIR, J.E., BOYATT, R., YAU, J.Y.-K. and COSMA, G., 2013. Student perspectives on source-code plagiarism. International Journal for Educational Integrity, 9 (1), pp. 3-19. ISSN 1833-2595

COSMA, G. and JOY, M., 2012. Evaluating the performance of LSA for source-code plagiarism detection.Informatica, 36 (4), pp. 409-424. ISSN 0350-5596

COSMA, G. and JOY, M., 2012. An approach to source-code plagiarism detection and investigation using latent semantic analysis. IEEE Transactions on Computers, 61 (3), pp. 379-394. ISSN 0018-9340

JOY, M., COSMA, G., YAU, J. and SINCLAIR, J., 2011. Source code plagiarism – a student perspective. IEEE Transactions on Education, 54 (1), pp. 125-132. ISSN 0018-9359

MOZGOVOY, M., KAKKONEN, T. and COSMA, G., 2010. Automatic student plagiarism detection: future perspectives. Journal of Educational Computing Research, 43 (4), pp. 511-531. ISSN 0735-6331

COSMA, G. and JOY, M., 2008. Towards a definition of source-code plagiarism. IEEE Transactions on Education, 51 (2), pp. 195-200. ISSN 0018-9359

JOY, M.S., SINCLAIR, J.E., BOYATT, R.C., YAU, J.Y.-K. and COSMA, G., 2012. Student perspectives on plagiarism in computing. In: 5th International Plagiarism Conference, Sage Gateshead, Newcastle upon Tyne, 16-18 July 2012, Newcastle upon Tyne.

JOY, M., COSMA, G., SINCLAIR, J. and YAU, J.Y.-K., 2009. A taxonomy of plagiarism in computer science. In: EDULEARN09 International Conference on Education and New Learning Technologies, Barcelona, Spain, 6-8 July 2009, Barcelona, Spain.

COSMA, G. and JOY, M., 2006. Source-code plagiarism: a UK academic perspective. In: 7th Annual Conference of the HEA Network for Information and Computer Sciences, Trinity College, Dublin, 29-31 August 2006, Dublin.

Customer review rating prediction using natural language processing and a combination of computational intelligence and machine learning algorithms.

COSMA, G. and ACAMPORA, G., 2016. A computational intelligence approach to efficiently predicting review ratings in e-commerce. Applied Soft Computing, 44, pp. 153-162. ISSN 1568-4946

COSMA, G., BROWN, D., BATTERSBY, S., KETTLEY, S. and KETTLEY, R., 2017. Analysis of multimodal data obtained from users of smart textiles designed for mental wellbeing. In: 2017 International Conference on Internet of Things for the Global Community (IoTGC), Funchal, Madeira, Portugal, 10-13 July 2017. Proceedings. Institute of Electrical and Electronics Engineers (IEEE). ISBN 9781538620649

REDMOND, M., SALESI, S. and COSMA, G., 2017. A novel approach based on an extended cuckoo search algorithm for the classification of tweets which contain emoticon and emoji. In: Proceedings of the 2017 2nd International Conference on Knowledge Engineering and Applications (ICKEA 2017), Imperial College London, 21-23 October 2017. Piscataway, N.J.: Institute of Electrical and Electronics Engineers, pp. 13-19. ISBN 9781538621509

SALESI, S. and COSMA, G., 2017. A novel extended binary cuckoo search algorithm for feature selection. In: Proceedings of the 2017 2nd International Conference on Knowledge Engineering and Applications (ICKEA 2017), Imperial College London, 21-23 October 2017. Piscataway, N.J.: Institute of Electrical and Electronics Engineers, pp. 6-12. ISBN 9781538621509

ALFRJANI, R., OSMAN, T. and COSMA, G., 2017. Exploiting domain knowledge and public linked data to extract opinions from reviews. In: Proceedings of the 2017 2nd International Conference on Knowledge Engineering and Applications (ICKEA 2017), Imperial College London, 21-23 October 2017. Piscataway, N.J.: Institute of Electrical and Electronics Engineers, pp. 98-102. ISBN 9781538621509

ALFRJANI, R., OSMAN, T. and COSMA, G., 2016. A new approach to ontology-based semantic modelling for opinion mining. In: D. AL-DABASS, A. ORSONI, R. CANT and G. JENKINS, eds.,UKSim2016: Proceedings of the UKSim-AMSS 18th International Conference on Mathematical Modelling & Computer Simulation, Cambridge, 6-8 April 2016. Institute of Electrical and Electronics Engineers (IEEE), pp. 267-272. ISBN 9781509008872

COSMA, G. and ACAMPORA, G., 2016. Neuro-fuzzy sentiment analysis for customer review rating prediction. In: W. PEDRYCZ and S.-M. CHEN, eds., Sentiment analysis and ontology engineering: an environment of computational intelligence. Studies in computational intelligence . Cham: Springer International, pp. 379-397. ISBN 9783319303178

ACAMPORA, G. and COSMA, G., 2015. A comparison of fuzzy approaches to e-commerce review rating prediction. In: J.M. ALONSO, H. BUSTINCE and M. REFORMAT, eds., Proceedings of IFSA-EUSFLAT 2015, 16th World Congress of the International Fuzzy Systems Association (IFSA) and the 9th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT), Gijón, Asturias, Spain, 30 June – 3 July 2015. Amsterdam: Atlantis Press, pp. 1223-1230. ISBN 9789462520776

ACAMPORA, G. and COSMA, G., 2014. A hybrid computational intelligence approach for efficiently evaluating customer sentiments in e-commerce reviews. In: 2014 IEEE Symposium on Intelligent Agents (IA) [Orlando, Florida, 9-12 December 2014]: proceedings. New York, NY: IEEE, pp. 73-80.ISBN 9781479944897

ACAMPORA, G., COSMA, G. and OSMAN, T., 2014. An extended neuro-fuzzy approach for efficiently predicting review ratings in E-markets. In: 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Beijing International Convention Center, Beijing, 6-11 July 2014, Beijing.

Applications of Deep and Machine Learning. This topic includes papers originating from students PhD work, MSc and MRes student work and some paper from undergraduate students which are/were under my supervision.

PANDYA, B., COSMA, G., ALANI, A.A., TAHERKHANI, A., BHARADI, V. and MCGINNITY, T.M., 2018.Fingerprint classification using a deep convolutional neural network. In: 2018 4th International Conference on Information Management (ICIM2018), 25-27 May 2018, Oxford, UK. IEEE, pp. 86-91.ISBN 9781538661482

BHARADI, V., PANDVA, B. and COSMA, G., 2018. Multi-modal biometric recognition using human iris and dynamic pressure variation of handwritten signatures. In: 2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS), Valencia, Spain, 15-18 October 2018. [Piscataway, N.J.]: Institute of Electrical and Electronics Engineers, pp. 233-238. ISBN 9781538695883

MAAJI, S.S., COSMA, G., TAHERKHANI, A., ALANI, A.A. and MCGINNITY, T.M., 2018. On-line voltage stability monitoring using an Ensemble AdaBoost classifier. In: 2018 4th International Conference on Information Management (ICIM2018), 25-27 May 2018, Oxford, UK. IEEE, pp. 253-259. ISBN 9781538661482

ALZUBAIDI, A. and COSMA, G., 2017. A multivariate feature selection framework for high dimensional biomedical data classification. In: Proceedings of the 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB 2017), Manchester, United Kingdom, 23-25 August 2017. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), pp. 59-66. ISBN 9781467389891

ALZUBAIDI, A., COSMA, G., BROWN, D. and POCKLEY, A.G., 2016. Breast cancer diagnosis using a hybrid genetic algorithm for feature selection based on mutual information. In: Proceedings: iTAG 2016: the 2016 International Conference on Interactive Technologies and Games – EduRob in Conjuction with ITAG2016 – 26-27 October 2016, Nottingham, United Kingdom. Washington, DC: IEEE Computer Society Conference Publishing Services, pp. 70-76. ISBN 9781509037384

ALZUBAIDI, A., COSMA, G., BROWN, D. and POCKLEY, A.G., 2016. A new hybrid global optimization approach for selecting clinical and biological features that are relevant to the effective diagnosis of ovarian cancer. In: 2016 IEEE Symposium Series on Computational Intelligence (SSCI): Proceedings.Piscataway, NJ: Institute of Electrical and Electronic Engineers. ISBN 9781509042401