- Email: 2501065M@student.gla.ac.uk, email@example.com
- LinkedIn: https://www.linkedin.com/in/emmanuel-p-mwanga-99052a1a9/
Research title: Using machine learning & infrared spectroscopy for rapid assessment of key indicators of malaria transmission
- Vector surveillance
- Application of machine learning in parasite surveillance
- Malaria genomic data analysis
- Public health
- My research aims to use machine learning and infrared spectroscopy for rapid assessment of key entomological and parasitological indicators of malaria transmission. The focus of this work is to validate infrared-based approach to rapidly and accurately identify field collected mosquitoes that have bitten humans or are malaria-infected. I also aim to study the mechanism of the Mid-infrared spectroscopy (MIR) in detecting Plasmodium parasite, by examining the unique parasite signals in MIR spectra from packed red blood cells.
- December 2021 – December 2024: Local PI – “Infrared & AI to Diagnose and Quantify Onchocerca volvulus in Blackflies” project, Sub-award from University of Glasgow
- June 2019 – December 2021: Principal Investigator (PI) - "Using machine learning and midinfrared spectroscopy for rapid assessment of blood-feeding histories and parasite infection rates in field-collected malaria mosquitoes" (MIRS – ML Project), Wellcome Trust International master’s fellowship in public health (30 months)
- Emmanuel P. Mwanga, Halfan Ngowo, Salum Mapua, Arnold Mmbando, Hamisi Kifungo, and Fredros Okumu “Evaluation of light trap (Mosclean IW1) for sampling Anopheles arabiensis and Culex Mosquito species in South-eastern Tanzania”. 17-LB-4228-ASTMH, Presented at the American Society of Tropical Medicine and Hygiene (ASTMH). For 66th Annual Meeting November 5-9, 2017, DOI: https://doi.org/10.4269/ajtmh.abstract2017. Volume 97, Issue 5_Suppl, Nov 2017, p. 1 - 674.
- Emmanuel P. Mwanga, Joshua Mitton, Doreen J. Siria, Francesco Baldini, Fredros O. Okumu, and Simon A. Babayan. “Using transfer learning and dimensionality reduction to improve generalisability of machine-learning predictions of mosquito ages from mid-infrared spectra”. 0317-ASTMH, Presented at the American Society of Tropical Medicine and Hygiene (ASTMH). For 70th Annual Meeting November 17-21, 2021, DOI: https://www.astmh.org/getmedia/59a95de8-1a06-49ca-9fd0-286454cc241a/ASTMH-2021- Annual-Meeting-Abstract-Book.pdf