Zambia ICT Journal

Exploring the decomposition of epics using natural language processing

2022-11-15T15:07:52+00:00

Agile user requirements are typically givens as user stories written using natural language and they come in different forms. The most complex form of stories to work with are epics. If epics are poorly understood, they can contribute to threats regarding the sprints or projects becoming behind schedule. It can be attributed to the epic's complexity. The research aimed to explore and attempt the use of Stanza from the Stanford NLP group in the decomposition of epics by creating a text generative model. We have also utilised the chunking technique to formulate the tasks from the generated user stories by identifying the linguistic structure through the aid of a POS tagger. The obtained results illustrate that the stanza can be utilised in the requirements engineering domain such as Sprint backlog grooming. The benefits of this research work are enormous considering that sprint backlog grooming takes considerable time and is always in iterative mode. Agile teams will also benefit from this work by efficiently using sprint timeboxes with minimal sprint planning effort. This will enable agile teams to spend more time delivering the right solutions with reduced sprint planning time and effort.

Challenges of using Data Mining Techniques to Analyze and Forecast COVID-19 Pandemic in Zambia

2022-12-09T07:41:51+00:00

COVID-19 is a highly infectious respiratory disease that belongs to the SARS group of viruses that has presented a global challenge to almost everyone world-wide. During the early stages of the pandemic in Zambia, a major challenge was the limited data and datasets for COVID-19. This challenge restricted research, especially in data mining. The challenge of data and datasets is currently improving. This paper presents the challenges of using data mining techniques and models to analyze and forecast the COVID-19 pandemic in Zambia. The analysis initially presents the methodology used for creating a dataset that focuses on the pandemic at provincial scope and uses the Zambia National Public Health Institute (ZNPHI) and Ministry of Health Zambia daily situation reports. The analysis of the pandemic at country level used the COVID-19 datasets from the Humanitarian Data Exchange (HDX) and the European Center for Disease Prevention and Control (ECDC). The study finally discusses the development and evaluation of the forecasting model. The forecasting model is based on the COVID_SEIRD Python package. To evaluate the forecasting model, the research utilized a combination of correlation and the max-function from basic statistics. The analysis focuses on finding the provincial area with the most COVID-19 cases in Zambia, while the forecasting process manages to forecast the trend of the pandemic for recoveries and fatalities.

Predicting Climate Change Related Extreme Natural Disasters Using Machine Learning in Zambia

2022-11-24T11:24:06+00:00

One of the most important concerns affecting humanity today is climate change that has led to increased frequency of natural disasters that threaten social and economic stability to populations. Zambia’s vulnerability to the threat of disasters remains high because the country still lacks an effective Early Warning System (EWS). This study recognises the need to evaluate various Machine Learning (ML) algorithms, that have been successfully implemented in disaster prediction, in order to develop a model for Zambia. Six ML algorithms, namely; Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbor (KNN), Gaussian Naive Bayes (GNB), Decision Tree (DT), and Support Vector Machine (SVM), have been compared from which the best performing is chosen. The historical climate data is obtained from the Zambia Meteorological Department (ZMD) while historical natural disasters data was obtained online because it is not locally available. The study results show that LR and SVM algorithms performed better than the others, both scoring 73.0% accuracy, respectively. LR is chosen to produce the final model because it has a shorter computational time compared to SVM. The model is then incorporated in a web service and android application for deployment. However, the high number of outliers, missing values and highly imbalanced classes affect the performance of the model. ML data cleaning and feature engineering techniques, such as Data Imputation and Oversampling Techniques, are applied but certain challenges still persist because these tools have their own flaws. Therefore, the model’s performance in a real-world data environment is likely to be affected.

An Evaluation of Developing Smart Cities in Developing Countries – Challenges and Opportunities: A Systematic Literature Review

2022-12-06T10:23:26+00:00

The implementation of smart cities globally has been the subject of literature review since the twentieth century. However, the smart city concept has only become topical in the twenty first century, particularly in more recent times. While a lot of cities in
developed countries have forged ahead with the implementation of smart cities, the same cannot be said about developing countries. Following the 2015 launch of the UN Sustainable Development Goals (SDGs), among the goals the development of smart cities across the globe, many countries have stalled on the achievement of this specific goal. The 2019 covid pandemic halted the development of smart cities while for those cities that have survived the epidemic, starting the smart city programmes that may have been started before the epidemic has proved a daunting task. This study looks at the challenges and opportunities developing countries have been faced prior to and after the covid pandemic. A systematic literature review was undertaken to consider the said challenges and opportunities, particularly in developing countries. The review has revealed that other problems like climate change have changed the development focus to the extent that smart city development agenda has been hurt and pushed aside. It is evident that the enthusiasm demonstrated in mid-1915s up to 2019 has waned. Any take-up of this programme will require concerted global effort to succeed.

Assisted Artificial Intelligence Medical Diagnosis System for Heart Disease

2022-11-24T11:42:48+00:00

In recent years increase of new and effective medical field applications has critical part in research. Artificial Intelligence (AI) Systems has great influence in the growth of these effective medical field applications and tools. One of the major health problems in both established and developing countries is heart disease. Therefore,
diagnosis to regulate the heart disease is very vital, so that appropriate actions can be taken. The Artificial Intelligence System uses input medical data collected from an existing dataset from Kaggle and applies this data on the artificial intelligence application developed that uses data mining algorithm and a basic model on Zambian patients to see if the model will predict correctly. From the dataset collected 80% was used as training data and 20% was used as testing data. The Bayesian data mining algorithm was used for predicting the risk level and probability of heart disease. The system uses medical parameters to predict heart disease in patients and these parameters are age, sex, blood pressure, blood sugar (mg/dl), cholesterol (mm/dl),
heart rate, exercise-induced angina, resting electrocardiogram, oldpeak, ST-slope and chest pain type. The data set collected by the system went through preprocessing which later supervised learning techniques and prediction model was conducted. Results were produced. Based on the results with the prediction accuracy of 90.97%, our results are in the same range as generated by other algorithms like KNN, Random Forest and Decision Tree algorithm.

Model for Water Quality Monitoring Based on Internet of Things

2022-11-24T10:46:31+00:00

In Lusaka, water pollution has been a problem for many decades, which has led to outbreaks of various waterborne diseases such as cholera, dysentery, and many more. In this research, we proposed a water quality monitoring system based on the Internet of Things (IoT). IoT relies on sensors to measure different parameters in water and report the results in real-time. The real-time information obtained from sensors through the IoT system can be used to warn users if there is any contamination in the water before the community gets infected. The deliverables for this research project are 1) Water quality monitoring using IoT sensors; 2) a dashboard to show water analysis from sensors, and 3) a mobile application to notify users should there be contamination of water. The results were obtained through the testing of water collected from various sources. Others results collected are dairy gold milk, undiluted Coolsplash juice and combination of other mixture. The results obtained show that IoT technology can be used to detect water quality. The model design has demonstrated to be effective based on the results obtained from the experiments. The proposed prototype can be used to help monitor water quality in Zambia.

Blockchain Technology and its Implication for the Financial Sector in Zambia

2022-11-30T14:39:22+00:00

Blockchain is the technology that underlies Crypto Currencies and it is poised to revolutionise current existing business processes and models. Its impact is being felt in many spheres of the financial industry in many jurisdictions around the world. Transactions on the blockchain are validated by a network of participating nodes using proof of work or proof of stake algorithms. Security of the data is guaranteed by the application of cryptographic hash functions. The technology has the characteristic of delivering very secure, transparent and innovative financial products. This study presents a systematic literature review of blockchain technologies and their potential application in the financial sector with the view of identifying open challenges and opportunities that it can address in the Zambian Financial Sector Context. The focus of the study was limited to the finance, banking, insurance, tax, mortgages and fintech sectors. The findings of the research showed that the Zambian financial sector can benefit from applying blockchain in its operations. Key benefits to be derived include tamper-proof customer identity validation, guaranteed security and trust, reduction of operational costs, elimination of third parties in transaction processes, reduced financial risks and reliable data sharing and verification.

Toward Locust Management: Challenges and Technological opportunities, Sikaunzwe, Zambia

2022-12-06T22:13:14+00:00

Locust invasions have proved to be a threat to the world’s food security and livelihood. Governments in locust infested areas in Africa have adopted various early warning strategies aimed at preventing and eliminating the impact of both African Migratory Locusts and Red Locusts. These measures include community sensitisation, use of eLocust3 early warning system and spraying of affected areas using recommended pesticides. Management of locusts in the study area, Sikaunzwe Agriculture Camp in Zambia, is however faced with unique challenges. The research was focused on exploring challenges faced by the ministry of agriculture in managing the spread of locust invasions using the existing early warning strategies. Focus Group Discussion (FGD) method was used in the study and NVivo 11, a qualitative data analysis software, was used to analyse the data based on thematic coding framework. The following challenges were acknowledged; failure to identify correct locust species, limited field staff and inaccessibility of infested areas. The proposed technology solutions to the above challenges include the use of machine learning, low cost drones, geospatial technology and Internet of Things.

Distributed Spatial Search Using Paillier Cryptosystem and a Distributed Ring Algorithm

2022-12-20T16:00:47+00:00

The problem of lack of anonymity and confidentiality can be experienced by those who collect statistical data online as well as those who provide the data. One end may be secure, for example, the one providing data, and yet the other end, for example, the one collecting data, may not be secure. In another scenario, both the data provider and collector may seek anonymity. Preventing the decryption of data provided while providing aggregated results is the best solution for such scenarios. To achieve this, this paper proposes a protocol that puts into application. Homomorphic Encryption and a Distributed Ring algorithm, to ensure data anonymity of both parties involved in a spatial search that is a data provider and a searcher. Firstly, we identify a Homomorphic Encryption technique that can work best for a spatial search by reviewing literature on Homomorphic Encryption techniques. Among the Homomorphic Encryption techniques reviewed were Rivest, Shamir and Adleman (RSA), El Gamal cryptosystem, Goldwasser-Micali cryptosystem, Benaloh cryptosystem, Paillier cryptosystem and Fully Homomorphic Encryption (FHE). After a comprehensive study, Paillier Homomorphic Encryption technique was identified as the best approach to be employed in securing a spatial search. Secondly, we propose a protocol for distributed spatial searching using Paillier cryptosystem and distributed ring algorithm principles. Finally, a proof of concept prototype using the proposed approach was implemented. From initial experiments conducted using the proposed approach, it is evident that the bigger cost comes from the communication over the network and less from the encryption algorithm and protocol itself. A 39.7% overhead when compared to the usefulness of the approach, is outweighed making the solution highly practical and useful.