Name: Dr Georgina Cosma
Type: User
Company: Loughborough University, Department of Computer Science
Bio: Data Science, Computational Intelligence, Machine Learning, AI, Deep Learning, Information Retrieval, neural and traditional NLP
Twitter: gcosma1
Location: Loughborough, UK
Blog: https://datascienceplus.blog/
Dr Georgina Cosma's Projects
ACO Feature Selection
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.
Bias Auditing & Fair ML Toolkit
Official FIRE 2020 Authorship Identification of SOurce COde (AI-SOCO) task repository containing dataset, evaluation tools and baselines
AI ethics sources of info
Search with BERT vectors in Solr, Elasticsearch, OpenSearch and GSI APU
code for BHI missing data paper
A Hybrid Model for Classification of Biomedical Data using Feature Filtering and a Convolutional Neural Network
Clan-based Cultural Algorithm for Feature Selection
NeverFindMe
Deep-Feature Selection
Hand gesture recognition using an adapted convolutional neural network with data augmentation
Deep Learning Tutorials in Colab
Extended Binary Cuckoo Search for Feature Selection
On-line voltage stability monitoring using an Ensemble AdaBoost classifier
A abstractive news summary generator. Taking the latest news from the internet and creating summary based on that.
Genetic Algorithm for Feature Selection
Generalisation Power Analysis for finding a stable set of features using evolutionary computation feature selection algorithms
Hands On Natural Language Processing with Python, published by Packt
PacKt NLP Book
Code for the I-SIRch summarisation and topic modelling papers
Python code for the paper entitled "Feature Extraction and Classification using Leading Eigenvectors: Applications to Biomedical and Multi-Modal mHealth Data", IEEE Access
Inquisitive Parrots for Search
Learn OpenCV : C++ and Python Examples
Interrogate the performance of machine learning models using instance hardness measures and difficulty-based incremental evaluations.
A simple interface to inspect, improve and add concepts to biomedical NER+L -> MedCAT.
Baseline model for the MedSecId paper
MIMIC Code Repository: Code shared by the research community for the MIMIC-III database