Recruiting 4 Research Associates in AI and Data Science
DECODE project (2 FT posts for 30 months each) – https://www.jobs.ac.uk/job/CMS217/research-associate-in-artificial-intelligence – clinical records, temporal data, feature selection, predictive modelling, healthcare data
I-SIRch (1 FT post for 2 years) – https://www.jobs.ac.uk/job/CMW146/research-associate-in-artificial-intelligence – Natural Language Processing, Named Entity Recognition, feature selection, predictive modelling
Themis.AI (1 FT post for 1 year) – https://www.jobs.ac.uk/job/CMW143/research-associate-in-data-science – preparation of noisy data for machine learning, predictive modelling
Papers published in December 2021!
Our paper is published! Prostate Cancer: Early Detection &Assessing Clinical Risk Using Deep #MachineLearning of High Dimensional Peripheral Blood Flow Cytometric #Phenotyping Data. Link to Paper: https://frontiersin.org/article/10.3389/fimmu.2021.786828… Link to Data: https://data.mendeley.com/datasets/wmgtzw2w8f/1… #DeepLearning #DataScience #FlowCytometry
Published! Our paper on Predicting surgical outcomes for chronic exertional compartment syndrome using Machine Learning with embedded trust by interrogation strategies, is in Nature Scientific Reports https://nature.com/articles/s41598-021-03825-4… Link to GitHub: https://github.com/gcosma/Machine-Learning-Model-Interrogation…#DataScience#AI@andrewhouston95
Media articles about our newly funded project!
Loughborough news – New Loughborough research will use Artificial Intelligence to help reduce maternal harm amongst mothers from black ethnic groups.
Awarded funding as part of the NHS AI Lab Initiative “AI and Racial and Ethnic Health Inequalities/ Optimising AI to improve the health and care outcomes of minority ethnic communities” competition
I-SIRch – Using artificial intelligence to improve the investigation of factors contributing to adverse maternity incidents involving Black mothers and families
Dr Patrick Waterson and Dr Georgina Cosma at Loughborough University
Aims to use AI to improve the investigation of factors contributing to adverse maternity incidents amongst mothers from different ethnic groups. This research will provide a way of understanding how a range of causal factors combine, interact and lead to maternal harm, and make it easier to design interventions that are targeted and more effective for these groups.
September 2021: Journal Paper Acceptance in Knowledge-Based Systems
Our article “Generalisation Power Analysis for finding a stable set of features using evolutionary algorithms for feature selection” has been published in Elsevier Knowledge-Based Systems (I.F 8.038).
Click on link before November 02, 2021 for the final version of the article. No sign up, registration or fees are required https://authors.elsevier.com/a/1dkqB3OAb91XON
Publicity! New AI system predicts building energy rates in less than a second
Our work on artificial intelligence system that can predict building emissions rates (BER) – an important value used to calculate building energy performance – of non-domestic buildings.
This research was carried out with from Cundall
Publicity! Our work on wind turbine blade defect detection…
Our work on wind turbine blade defect detection has got a lot of publicity, and well deserved too (not that I am biased 😉 ). Here are some of the news articles:
To read the research paper in its entirety, click here.
This research is funded through the EPSRC Centre for Doctoral Training in Embedded Intelligence, with industrial support from Railston & Co Ltd.
January 2021: Journal Paper Acceptance in Information Sciences
Salesi, S, Cosma, G, Mavrovouniotis, M (2021) TAGA: Tabu Asexual Genetic Algorithm embedded in a filter/filter feature selection approach for high-dimensional data, Information Sciences, ISSN: 0020-0255. GitHub – MATLAB code
Accepting sponsored/self-funded PhD students
If you are a self-funded/sponsored student seeking a PhD in A.I and Data Science then take a look at my project topics. If you are interested in any of these then get in touch.
Glad to be back in my office at the beautiful Loughborough University campus!
July 2020: eLife journal paper has been published 🙂
June 2020: eLife Journal Paper acceptance
Hood, S, Cosma, G, A, GF, Johnson, C, Reeder, S, E, SM, Khan, M, A, GP (Accepted for publication) Identifying prostate cancer and its clinical risk in asymptomatic men using machine learning of high dimensional peripheral blood flow cytometric natural killer cell subset phenotyping data, eLife. To Appear.
March 2020: WCCI’20 paper acceptance
March 2020: Three papers accepted at the IEEE Computational Intelligence Society with two at the International Joint Conference on Neural Networks (IJCNN 2020); and one at the 2020 IEEE Congress on Evolutionary Computation (IEEE CEC 2020).
Turabee, G, Cosma, G, Madonna, V, Giangrande, P, Khowja, MR, Vakil, G, Gerada, C, Galea, M (Accepted for publication) Predicting Insulation Resistance of Enamelled Wire using Neural Network and Curve Fit Methods Under Thermal Aging. In IEEE World Congress on Computational Intelligence (WCCI) 2020), Glasgow, Scotland.
Alani, AA, Cosma, G, Taherkhani, A (Accepted for publication) Classifying Imbalanced Multi-modal Sensor Data for Human Activity Recognition in a Smart Home using Deep Learning. In IEEE World Congress on Computational Intelligence (WCCI) 2020, Glasgow, U.K.
Ogun, O, Enoh, M, Cosma, G, Taherkhani, A, Madonna, V (Accepted for publication) Enhancing Prediction in Cyclone Separators through Computational Intelligence. In IEEE World Congress on Computational Intelligence (WCCI) 2020, IEEE Congress on Evolutionary Computation (IEEE CEC), Glasgow, U.K.
March 2020: Neurocomputing Journal paper Acceptance
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.
Source-code available from: https://github.com/gcosma/adaboostCNN