Faculty of Computing ,Library and Information Science (FCLIS).

Permanent URI for this collection

http://hdl.handle.net/20.500.12493/8

Browse

Browsing Faculty of Computing ,Library and Information Science (FCLIS). by Subject "Artificial Intelligence"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Application Of ArtifiCial Intelligence in E-Governance: A Comparative Study of Supervised Machine Learning and Ensemble Learning Algorithms on Crime Prediction.
    (Kabale University, 2024) Niyonzima, Ivan; Muhaise, Hussein; Akankwasa, Aureri
    In the developing world, the daily activities of humans’ social, political and economic life make it vital and easy to encounter the phenomenon of crime. Crime is an unnecessary evil in society and for any economic, social and political activities to run smoothly, criminal offenses must be completely eliminated from society. Advancement in information and communications technology enables law enforcement agencies to collect a huge amount of crime data, and the data collected by these organizaions have been doubling every two years. It has been found out that only 17% of the collected crime data is used in their operations today and several studies have noted that Law Enforcement Agencies are data rich but information poor. Machine learning, a subfield of artificial intelligence, has been used by government agencies in developed countries in different operations like face recognition, computer forensics, image and video analysis to identify criminals and crime predictions. It is therefore time for developing countries to leverage such technologies in order to reduce crimes. Therefore, this study proposes the application of supervised machine learning techniques in the prediction of crimes basing on the past crime data. During this study, we used open-source crime data from the UCI Machine learning repository to train and validate our algorithms. The performance of supervised machine learning and ensemble learning algorithms was done using crime data. The supervised machine learning algorithms used include K-Nearest Neighbor (KNN), decision tree classifier (CART), Naïve Bayes (NB) and Support vector machine (SVM). The ensemble learning algorithms used include AdaBoost (AD), Gradient Boosting Classifier (GBM), Random Forest (RF) and Extra Trees (ET). We used an accuracy metric to measure the performance of the algorithms. Python 3 was used in all the experiments using windows 10 laptop with 8GB RAM and 2.0GHZ processor. The performance of the supervised machine learning algorithms using the original datasets includes 60.33%, 56.24%, 57.01% and 59.06% for KNN, CART, NB, and SVM respectively. The performance of ensemble learning algorithms using the original datasets includes 58.58%, 59.81%, 55.23% and 55.74% for AD, GBM, RF and ET respectively. Experimental results revealed that KNN generally performed better when compared to the rest of the algorithms. we then developed a crime prediction model based on KNN and its prediction accuracy was 66% on our test dataset. The use of Artificial Intelligence has the potential to ameliorate several existing structural inefficiencies in the discharge of governmental functions. Machine learning, a subfield of artificial intelligence, has been used by government agencies in developed countries in crime analysis and predictions. It is therefore time for developing countries to leverage such technologies in order to reduce crimes.
  • Thumbnail Image
    ItemOpen Access
    Diagnosis and Classification of Tuberculosis Chest X-ray Images of Children Less Than 15 years at Mbarara Regional Referral Hospital Using Deep Learning.
    (Kabale University, 2024) Kawuma, Simon; Kumbakumba, Elias; Mabirizi, Vicent; Nanjebe, Deborah; Mworozi, Kenneth; Mukama, Adolf Oyesigye; Kyasimire, Lydia
    Tuberculosis (TB) is an underestimated cause of death in children, with only 45% of cases correctly diagnosed and reported. It is estimated that 1.12 million TB cases occurred among newborns, children, and adolescents aged less or equal 14 years. In Uganda, TB prevalence is 8.5% in children and 16.7% in adolescents. Treatment and diagnosing TB is challenging and its high mortality rate is due to many lacks in the diagnosis of this illness especially among children. As a strategy to curb TB mortality rate in children, there exists a need to improve and expedite the screening for TB among children. Chest X-ray (CXR) is commonly used in TB burdened countries like Uganda to diagnose TB patients but interpretation of the patient’s radiograph needs skilled radiologists who are few. To this end, this research aims to close the TB mortality gap in children by applying AI, primarily deep learning techniques, to detect TB in children. The study created five models, one from scratch and four pre-trained Transfer Learning (TL) and were trained and verified using digital CXR radiograph images of children who visit the TB clinic at Mbarara Regional Referral Hospital. The model classifies clinical images of patients into normal or Tuberculosis. TL models; VGG16, VGG19, Inception V3, and ResNet50 outperformed scratch model with validation accuracy of 79.91%, 69.21%, 53.0%, 51.09% and 50.01% respectively. We hope that once the deep learning models are implemented and adopted by the radiologist, it will reduce the time spent by radiologist while analysing CXR images.