Project Title: AI-MIRS: An online Platform for Malaria Vector Surveillance in Africa using Artificial Intelligence
Project Description: This project will develop a novel technology to quantify the efficacy of any control intervention targeted at malaria mosquitoes, by combining artificial intelligence and infrared-spectroscopy to obtain real-time information on mosquito populations and their disease transmission potential. However, genetic and ecological factors can affect the composition of mosquito cuticle in unexpected ways, and demographic predictions based on MIRS of laboratory mosquitoes might not accurately estimate species and age in wild mosquitoes. This grant will support... This project will develop a novel technology to quantify the efficacy of any control intervention targeted at malaria mosquitoes, by combining artificial intelligence and infrared-spectroscopy to obtain real-time information on mosquito populations and their disease transmission potential. However, genetic and ecological factors can affect the composition of mosquito cuticle in unexpected ways, and demographic predictions based on MIRS of laboratory mosquitoes might not accurately estimate species and age in wild mosquitoes. This grant will support all the activities and cover some personnel costs. Aim 1. Establish best practice to estimate ageing rates in wild mosquitoes: analyze ecological and environmental determinants of age and species prediction accuracy of wild mosquitoes to Optimize MIRS prediction performance and generalisability. Aim 2. Develop an online platform for real-time analysis of spectral data for malaria mosquito surveillance: develop a user-friendly web application to obtain real-time analysis of mosquito infrared spectra through machine learning; this platform will also allow users to contribute data for Further optimization of the machine learning algorithms. Aim 3: Training African scientists on machine learning. Year 1: Data cleaning and manipulation; performance evaluation; simple classification models (K- Nearest neighbors, decision trees, naïve Bayes, logistic regression). Year 2: Data visualization (e.g. UMAP, TSNE); more advanced ML techniques: Kernel methods (e.g. Support Vector Machines); regression approaches (including ordinal regression); ensemble methods (E.g. Gradient Tree Boosting). Year 3: Bayesian machine learning (e.g. Gaussian Processes). An introduction to deep neural Networks (e.g. Multilayer Perceptron, Convolutional Neural Nets).
Principal Investigator : Fredros Okumu
Department Name : EHES
Time frame: (2019-12-01) - (2023-11-30)
The University Court of the University of Glasgow (UoG) (Normal)
External Collaborating Partners
None added yet.