Computing and Information Technology

Permanent URI for this collection


Recent Submissions

Now showing 1 - 5 of 16
  • Item
    (Journal of Applied Sciences, Information and Computing (JASIC), 2023-07) Nabulongo Ali, V. S. Manjula and Fatou Marega
    Uganda has made outstanding progress in agricultural output, which is crucial for preserving the safety of the country's food supply. The role of technology and digitization in promoting sustainable agriculture practices in Uganda. The case study will focus on various innovative initiatives and solutions that have been implemented in the country to enhance agricultural productivity, reduce environmental impact, and improve livelihoods. By examining the current state of technology adoption in Ugandan agriculture, analyzing successful case studies, and identifying challenges and opportunities, this research will provide valuable insights into the potential of technology and digitization to drive sustainable agricultural development in Uganda."
  • Item
    Design and implementation of an android based automatic phase selector and overload protector using GSM
    (Kampala International University, 2021-01) Umaru, Kalyankolo; Gabriel, Aguto. A; Zaina, Kalyankolo; Enerst, Edozie
    In this century, the demand for electricity is increasing at an alarming rate that has caused pressure on the existing transmission and distribution networks. This has led to power cuts affecting sensitive facilities such as hospitals, industries and schools. This project is designed to automatically supply continuous power to the load through one or all of the three sources of supply that are: solar, mains grid & generator. In case their availability; an android app is used to select the source of choice and when the amount of load demand increases beyond what can be handled by one source, a mobile app is used to bring on board either of the remaining two sources so as to meet the load demand. The output of either source is connected to a voltage stabilizer which stabilizes the voltage to 220Vac by means of an auto-transformer with many taps and then the load is connected through an overload protector circuit which monitors the amount of current drawn. Once the current exceeds normal values, the last load connected is automatically isolated from the source leaving the critical loads connected. At the same time a message is sent to the operator by means of GSM, notifying of the overload. The operator can decide to operate the loads by sending a text message “normal” to restore the system operation to use an android app.
  • Item
    Design and implementation of three phase PWM inverter
    (Kampala International University, 2021-02) Umaru, Kalyankolo; Abdunulu, Lawrence; Kavuma, Kigenyi; William, Isabirye; Enerst, Edozie; Zaina, Kalyankolo
    This paper presents an advanced three phase inverter topology the Z-Source Inverter and its control using microcontroller Atmega 328P. Z-Source Inverter employs second order filter network at front end which provides unique buckboost feature for inverter. Z-Source inverter can be controlled by any traditional PWM method. Here the modified maximum constant boost PWM method is utilized for Z-Source inverter control. The microcontroller Atmega 328P is used to generate PWM pulses and to control operation of Z-Source inverter. The complete hardware is designed to drive the three phase induction motor. The hardware design involves the design of control circuit, driver circuit, Z-Source network, main inverter bridge, power supply etc. The Z-Source inverter is implemented and tested to verify the Z-Source inverter concept. The desired three phase PWM signals are generated by using control circuit and detailed hardware results are presented.
  • Item
    Corona Virus Disease (COVID 19): Analysis and Design of an Alert and Real-time Tracking System
    (Warse, 2020-05) Umezuruike, Chinecherem; Nwankwo, Wilson; Tibenderana, Prisca; Assimwe, John Patrick; Muhirwa, Ronald
    Microscopic agents such as viruses, protozoa, bacteria, fungi, etc. are common aetiologic agents in most infections affecting man. Whereas some infectious diseases are localized owing to the unique geospatial and biochemical characteristics of the aetiologic agents, others are not bound by such restrictions hence their manifest tendencies towards evolving an epidemic or even a pandemic. CoVID-19 sprang up in Wuhan China in November 2019 and was declared a pandemic by the in January 2020 World Health Organization (WHO). Like the Spanish flu of 1918 that claimed millions of lives, the COVID-19 has caused the demise of thousands with China, Italy, Spain and the USA having the highest statistics on infection and mortality rates. Regardless of existing sophisticated technologies and medical science, the spread has continued to surge high. Tracking of suspected carriers (cases) has been difficult, thereby increasing the risk of spread. As a novel infection, real-time information management beyond national geographical borders is vital to the success of any disease management campaign. Currently, information on the Covid-19 and applicable management procedures in most countries is limited thus creating a knowledge and management gap among the populace and even health management personnel especially in areas susceptible to the pandemic. In response to the aforementioned, this paper proposes an Alert and Tracking System (CVATS) that enhances information dissemination, disease management, tracking of cases, and management of confirmed cases. The system follows an object-oriented approach in articulating the various actors and evolves a model that could be implemented on both web and mobile platforms. On mobile platform, it employs google maps and could be used to track persons as well as geographical areas with prevalence of infections.
  • Item
    Hybrid Methods for Credit Card Fraud Detection Using K-means Clustering with Hidden Markov Model and Multilayer Perceptron Algorithm
    (SCIENCEDOMAIN international, 2016-12-10) Fashoto, Stephen Gbenga; Owolabi, Olumide; Adeleye, Oluwafunmito; Wandera, Joshua
    The use of credit cards is fast becoming the most efficient and stress-free way of purchasing goods and services; as it can be used both physically and online. Hence, it has become imperative that we find a solution to the problem of credit card information security and also a method to detect fraudulent credit card transactions. Over the years, a number of Data Mining techniques have been applied in the area of credit card fraud detection. The focus of this paper is to model a fraud detection system that would attempt to maximally detect credit card fraud by generating clusters and analyzing the clusters generated by the dataset for anomalies. The major objective of this study is to compare the performance of two hybrid approaches in terms of the detection accuracy.We employed hybrid methods using the K-means Clustering algorithm with Multilayer Perceptron (MLP) and the Hidden Markov Model (HMM) for this study. Our tests revealed that the detection accuracy of “MLP with K-means Clustering” is higher than the “HMM with K-means Clustering” for 80% percentage split but the reverse is the case when the “MLP with K-means Clustering” is compared with the “HMM with K-means Clustering” for 10 fold cross-validation but the accuracy is the same in the two hybrid methods for percentage split of 66%. More extensive testing with much larger datasets is however required to validate theses results.