Makerere University

About: Makerere University is a education organization based out in Kampala, Uganda. It is known for research contribution in the topics: Population & Public health. The organization has 7220 authors who have published 12405 publications receiving 366520 citations. The organization is also known as: Makerere University Kampala & MUK.

Machine Learning for Plant Disease Incidence and Severity Measurements from Leaf Images

Abstract: In many fields, superior gains have been obtained by leveraging the computational power of machine learning techniques to solve expert tasks. In this paper we present an application of machine learning to agriculture, solving a particular problem of diagnosis of crop disease based on plant images taken with a smartphone. Two pieces of information are important here, the disease incidence and disease severity. We present a classification system that trains a 5 class classification system to determine the state of disease of a plant. The 5 classes represent a health class and 4 disease classes. We further extend the classification system to classify different severity levels for any of the 4 diseases. Severity levels are assigned classes 1 - 5, 1 being a healthy plant, 5 being a severely diseased plant. We present ways of extracting different features from leaf images and show how different extraction methods result in different performance of the classifier. We finally present the smartphone-based system that uses the classification model learnt to do real-time prediction of the state of health of a farmers garden. This works by the farmer uploading an image of a plant in his garden and obtaining a disease score from a remote server.

Discrimination efficacy of fecal pollution detection in different aquatic habitats of a high-altitude tropical country, using presumptive coliforms, Escherichia coli, and Clostridium perfringens spores

Abstract: The performance of rapid and practicable techniques that presumptively identify total coliforms (TC), fecal coliforms (FC), Escherichia coli, and Clostridium perfringens spores (CP) by testing them on a pollution gradient in differing aquatic habitats in a high-altitude tropical country was evaluated during a 12-month period. Site selection was based on high and low anthropogenic influence criteria of paired sites including six spring, six stream, and four lakeshore sites spread over central and eastern parts of Uganda. Unlike the chemophysical water quality, which was water source type dependent (i.e., spring, lake, or stream), fecal indicators were associated with the anthropogenic influence status of the respective sites. A total of 79% of the total variability, including all the determined four bacteriological and five chemophysical parameters, could be assigned to either a pollution, a habitat, or a metabolic activity component by principal-component analysis. Bacteriological indicators revealed significant correlations to the pollution component, reflecting that anthropogenic contamination gradients were followed. Discrimination sensitivity analysis revealed high ability of E. coli to differentiate between high and low levels of anthropogenic influence. CP also showed a reasonable level of discrimination, although FC and TC were found to have worse discrimination efficacy. Nonpoint influence by soil erosion could not be detected during the study period by correlation analysis, although a theoretical contamination potential existed, as investigated soils in the immediate surroundings often contained relevant concentrations of fecal indicators. The outcome of this study indicates that rapid techniques for presumptive E. coli and CP determination may be reliable for fecal pollution monitoring in high-altitude tropical developing countries such as those of Eastern Africa.

Phylogeography and population structure of the common warthog (Phacochoerus africanus) inferred from variation in mitochondrial DNA sequences and microsatellite loci

Abstract: Global climate fluctuated considerably throughout the Pliocene and Pleistocene, influencing the evolutionary history of a wide range of species. Using both mitochondrial sequences and microsatellites, we have investigated the evolutionary consequences of such environmental fluctuation for the patterns of genetic variation in the common warthog, sampled from 24 localities in Africa. In the sample of 181 individuals, 70 mitochondrial DNA haplotypes were identified and an overall nucleotide diversity of 4.0% was observed. The haplotypes cluster in three well-differentiated clades (estimated net sequence divergence of 3.1–6.6%) corresponding to the geographical origins of individuals (i.e. eastern, western and southern African clades). At the microsatellite loci, high polymorphism was observed both in the number of alleles per locus (6–21), and in the gene diversity (in each population 0.59–0.80). Analysis of population differentiation indicates greater subdivision at the mitochondrial loci (FST=0.85) than at nuclear loci (FST=0.20), but both mitochondrial and nuclear loci support the existence of the three warthog lineages. We interpret our results in terms of the large-scale climatic fluctuations of the Pleistocene.