Machine Learning Development and Applications

Overview: Machine learning is a growing field based on computational and statistical algorithms that are trained with experimental data to give computers the ability to learn specific tasks for prediction-making. On the other hand, data assimilation algorithms can help to forecast variables of complex systems as well as interpolate sparse observation data using knowledge a mathematical model based on observed data.

State of the art: At present, the use of neural networks for modeling and learning has rapidly increased in recent years. In addition, new training algorithms have been raising with different properties to tackle complex problems.

Our research in Machine Learning and Data Assimilation aims to:

machine learning algorithms will be used for the discovery of novel biomarker signatures and gene-regulatory networks

predicting disease progression with computational approaches

develop new algorithms for data assimilation, identification, and optimization

Relevant Publications in this Field:

Advancing neural network architectures for time series forecasting: A sustainable approach to intensified biobutanol production. Chemical Engineering and Processing-Process Intensification. 2024 [PDF]

A new computational approach, based on image trajectories, to identify the subjacent heterogeneity of sperm to the effects of ketanserin. Cytometry. 2023 [PDF]

Topological data analysis of antibody dynamics of severe and non-severe patients with COVID-19. Mathematical Biosciences. 2023 [PDF]

Distinct immunological and molecular signatures underpinning influenza vaccine responsiveness in the elderly. Nature Communications. 2022 [Link]

Tracking influenza A virus infection in the lung from hematological data with machine learning. mSystems. 2022 [Link]

Cyclo(tetrahydroxybutyrate) production is sufficient to distinguish between Xenorhabdus and Photorhabdus isolates in Thailand. Environmental Microbiology. 2019. [PDF]

Discrete-time high-order neural network identifier trained with cubature Kalman filter. Neurocomputing. 2018 [PDF]

Neural inverse optimal control for discrete-time impulsive systems. Neurocomputing. 2018 [PDF]

The 2017 plague outbreak in Madagascar: data descriptions and epidemic modelling. Epidemics. 2018 [PDF]

Germinal Center Optimization Algorithm. International Journal of Computational Intelligence Systems, 12: 13-27, 2018 [PDF]

Particle swarm optimization algorithm with a bio-inspired aging model. Particle Swarm Optimizations, InTechOpen, 2018 [PDF]

Recurrent High Order Neural Networks Identification for Infectious Diseases. Proceedings in the IEEE World Congress on Computational Intelligence, Rio de Janeiro, Brazil. 2018

An Egyptian HPAI H5N1 isolate from clade 2.2.1.2 is highly pathogenic in an experimentally infected domestic duck breed (Sudani duck). Transboundary and Emerging Diseases. 1-15, 2018 [PDF]

Germinal Center Optimization Applied to Neural Inverse Optimal Control for an All-Terrain Tracked Robot. Applied Sciences. 8(1):1-16, 2017 [PDF]

A Comparative Study of Differential Evolution Algorithms for Parameter Fitting Procedures. Proceedings in IEEE World Congress on Computational Intelligence. 2016 [PDF]

Progressive contraction of the latent HIV reservoir around a core of less-differentiated CD4+ memory T Cells. Nature Communications, Vol.5, 5407, 1-8, 2014 [PDF]

Observers for biological systems. Applied Soft Computing, Vol.24, 1175–1182, 2014 [PDF]

Decentralized Discrete-Time Neural Control for a Quanser 2-DOF Helicopter. Applied Soft Computing, Vol. 12, 2462–2469, 2012 [PDF]

Dynamic optimization algorithms to mitigate HIV escape. Proceedings in the IEEE Conference on Decision Control, Atlanta, 2010 [PDF]

Discrete-time recurrent high order neural networks for nonlinear identification. Journal of the Franklin Institute, Vol. 347 (7), 1253-1265, 2010 [PDF]

Neural observer based hybrid intelligent scheme for activated sludge wastewater treatment. Chemical and Biochemical Engineering Quarterly Journal, Vol. 23 (4), 2009 [PDF]