Coccidiosis, Salmonella, and Newcastle are the common poultry diseases that curtail poultry production if they are not detected early. In Tanzania, these diseases are not detected early due to limited access to agricultural support services by poultry farmers. Deep learning techniques have the potential for early diagnosis of these poultry diseases. In this study, a deep Convolutional Neural Network (CNN) model was developed to diagnose poultry diseases by classifying healthy and unhealthy fecal images. Unhealthy fecal images may be symptomatic of Coccidiosis, Salmonella, and Newcastle diseases. We collected 1,255 laboratory-labeled fecal images and fecal samples used in Polymerase Chain Reaction diagnostics to annotate the laboratory-labeled fecal images. We took 6,812 poultry fecal photos using an Open Data Kit. Agricultural support experts annotated the farm-labeled fecal images. Then we used a baseline CNN model, VGG16, InceptionV3, MobileNetV2, and Xception models. We trained models using farm and laboratory-labeled fecal images and then fine-tuned them. The test set used farm-labeled images. The test accuracies results without fine-tuning were 83.06% for the baseline CNN, 85.85% for VGG16, 94.79% for InceptionV3, 87.46% for MobileNetV2, and 88.27% for Xception. Finetuning while freezing the batch normalization layer improved model accuracies, resulting in 95.01% for VGG16, 95.45% for InceptionV3, 98.02% for MobileNetV2, and 98.24% for Xception, with F1 scores for all classifiers above 75% in all four classes. Given the lighter weight of the trained MobileNetV2 and its better ability to generalize, we recommend deploying this model for the early detection of poultry diseases at the farm level.

School dropout is absenteeism from school for no good reason for a continuous number of days. Addressing this challenge requires a thorough understanding of the underlying issues and effective planning for interventions. Over the years machine learning has gained much attention on addressing the problem of students dropout. This is because machine learning techniques can effectively facilitate determination of at-risk students and timely planning for interventions. In order to collect, organize, and synthesize existing knowledge in the field of machine learning on addressing student dropout; literature in academic journals, books and case studies have been surveyed. The survey reveal that, several machine learning algorithms have been proposed in literature. However, most of those algorithms have been developed and tested in developed countries. Hence, developing countries are facing lack of research on the use of machine learning on addressing this problem. Furthermore, many studies focus on addressing student dropout using student level datasets. However, developing countries need to include school level datasets due to the issue of limited resources. Therefore, this paper presents an overview of machine learning in education with the focus on techniques for student dropout prediction. Furthermore, the paper highlights open challenges for future research directions.

Predicting student dropout is a challenging problem in the education sector. This is due to an imbalance in student dropout data, mainly because the number of registered students is always higher than the number of dropout students. Developing a model without taking the data imbalance issue into account may lead to an ungeneralized model. In this study, different data balancing techniques were applied to improve prediction accuracy in the minority class while maintaining a satisfactory overall classification performance. Random Over Sampling, Random Under Sampling, Synthetic Minority Over Sampling, SMOTE with Edited Nearest Neighbor and SMOTE with Tomek links were tested, along with three popular classification models: Logistic Regression, Random Forest, and Multi-Layer Perceptron. Publicly accessible datasets from Tanzania and India were used to evaluate the effectiveness of balancing techniques and prediction models. The results indicate that SMOTE with Edited Nearest Neighbor achieved the best classification performance on the 10-fold holdout sample. Furthermore, Logistic Regression correctly classified the largest number of dropout students (57348 for the Uwezo dataset and 13430 for the India dataset) using the confusion matrix as the evaluation matrix. The applications of these models allow for the precise prediction of at-risk students and the reduction of dropout rates.

Presumptive treatment and self-medication for malaria have been used in limited-resource countries. However, these approaches have been considered unreliable due to the unnecessary use of malaria medication. This study aims to demonstrate supervised machine learning models in diagnosing malaria using patient symptoms and demographic features. Malaria diagnosis dataset extracted in two regions of Tanzania: Morogoro and Kilimanjaro. Important features were selected to improve model performance and reduce processing time. Machine learning classifiers with the k-fold cross-validation method were used to train and validate the model. The dataset developed a machine learning model for malaria diagnosis using patient symptoms and demographic features. A malaria diagnosis dataset of 2556 patients’ records with 36 features was used. It was observed that the ranking of features differs among regions and when combined dataset. Significant features were selected, residence area, fever, age, general body malaise, visit date, and headache. Random Forest was the best classifier with an accuracy of 95% in Kilimanjaro, 87% in Morogoro and 82% in the combined dataset. Based on clinical symptoms and demographic features, a regional-specific malaria predictive model was developed to demonstrate relevant machine learning classifiers. Important features are useful in making the disease prediction.

Maize is one of the most important staple food and cash crops that are largely produced by majority of smallholder farmers throughout the humid and sub-humid tropic of Africa. Despite its significance in the household food security and income, diseases, especially Maize Lethal Necrosis and Maize Streak, have been significantly affecting production of this crop. This paper offers a dataset of well curated images of maize crop for both healthy and diseased leaves captured using smartphone camera in Tanzania. The dataset is the largest publicly accessible dataset for maize leaves with a total of 18,148 images, which can be used to develop machine learning models for the early detection of diseases affecting maize. Moreover, the dataset can be used to support computer vision applications such as image segmentation, object detection and classification. The goal of generating this dataset is to assist the development of comprehensive tools that will help farmers in the diagnosis of diseases and the enhancement of maize yields thus eradicating the problem of fod security in Tanzania and other parts in Africa.