University of Lusaka

This study presents an AI-powered framework for predictive maintenance and prognostic health management (PHM) based on edge-enabled predictive algorithms to support intelligent fault diagnosis in industrial operations. The proposed framework is designed to monitor system conditions, detect early fault signatures, and anticipate degradation patterns using high-frequency operational data collected from two large industrial plants between 2024 and 2025. By leveraging edge computing, the approach enables localized anomaly detection with low latency, allowing deviations in system behavior to be identified close to the data source. The methodology integrates edge-based anomaly detection with predictive modeling techniques to estimate future system health states and fault-related risk dynamics. Anomalies identified at the edge level are aggregated and processed through forecasting models to infer degradation trends and support prognostic assessment. A health-oriented evaluation layer translates predictive outputs into actionable indicators that support maintenance planning and system recovery decisions. The framework is evaluated using standard predictive performance metrics, including MAPE, RMSE, and R², together with a health-related improvement measure reflecting system stability and recovery capability. The results demonstrate high predictive reliability, with the models explaining approximately 98.9% of the observed variability in system risk indicators and achieving measurable improvements in operational stability through early fault mitigation. This research contributes a scalable algorithmic framework that links data-driven condition monitoring, intelligent fault diagnosis, and PHM within an edge computing environment, strengthening maintenance decision accuracy in dynamic industrial settings.

Background: Healthcare waste management is a critical component of infection prevention and control within health facilities, however, it still remains a global public health challenge. The purpose of this paper was to assess the healthcare waste management practices among health workers at Samfya District Hospital. Methods: A descriptive cross-sectional study design and quantitative approach was employed. Simple random sampling was used, 65 healthcare workers participated in the study. Data was collected through structured questionnaire and analyzed using STATA version 14.2. Descriptive statistics were used to summarize socio-demographic characteristics and Healthcare waste management practices, while Fishers exact and chi square tests were applied to determine associations between variables. At 95% confidence Interval, a p value <0.05 was considered statistically significant. Results: The study findings revealed that healthcare waste management practices were significantly associated with the presence of properly labelled waste bins (p<0.05, 95% CI), indicating that the availability and proper labelling of bins greatly influenced correct waste segregation and disposal. Furthermore, the profession of healthcare workers showed a statistically significant relationship with healthcare waste management practices (p<0.05, 95% CI), suggesting that knowledge and adherence to waste management protocols varied across professional categories. Conclusions: The study concluded that while awareness of healthcare waste management practices among healthcare workers was high, actual compliance was influenced by structural factors such as the availability of properly labelled bins and professional background.

Small and Medium Enterprises (SMEs) are crucial to Zambia’s economic growth but continue to face challenges in sustaining profitability. This study examined the effect of firm characteristics on SME profitability, aiming to (i) identify the most influential characteristic and (ii) analyse their relationships with profitability. The characteristics assessed included firm size, firm age, debt finance, liquidity, and sales growth. Data were collected from 270 SMEs registered with the Patents and Companies Registration Agency (PACRA) across seven urban centres: Livingstone, Lusaka, Kabwe, Ndola, Kitwe, Chingola, and Chililabombwe, using structured, face-to-face questionnaires. Systematic random sampling was employed, and data were analysed using factor analysis, Pearson correlation, regression, and Chi-square tests. Results showed that firm characteristics collectively have a significant effect on SME profitability, though individual relationships were weak and statistically insignificant. Among the characteristics, sales growth had the strongest influence. However, regression results (R² = 0.002, F = 0.237, p = 0.790) indicated very weak predictive power, suggesting that firm characteristics explain only 0.2% of profitability variance. This implies that SME profitability in Zambia is influenced by the combined interaction of factors rather than individual characteristics. The study contributes new insights by identifying sales growth as the most influential factor, highlighting that sales growth drives SME profitability even in resource-constrained contexts like Zambia. Policymakers should prioritise integrated strategies that foster sales growth through innovation, market diversification, and digital marketing, while enhancing liquidity through accessible, low-interest financing. Financial policy reforms should prioritize accessible, low-interest financing mechanisms that enhance liquidity and sustainable debt utilisation.

Rural roads are frequently promoted as a tool for increasing smallholder agricultural productivity, yet evidence from real-world, climate-stressed contexts remains mixed. This paper examines how rural road rehabilitation under the Zambia Improved Rural Connectivity Project has affected agricultural productivity and resilience among small-scale farmers in Nyimba and Chibombo districts. Using a concurrent mixed-methods design, the study combines survey data from 372 households, stratified by district and distance from rehabilitated roads, with qualitative interviews, focus group discussions, and key informant interviews. The analysis focuses on land ownership and activation, cropping patterns and yields for maize, sunflower, soya beans and groundnuts over two recent agricultural seasons, including the climatically adverse 2023/24 season. Results show that land ownership is widespread in both districts and that improved roads have supported land activation and crop diversification, particularly in previously more peripheral parts of Nyimba. Maize cultivation remains entrenched, but participation in commercial oilseed and legume crops has expanded or been sustained along rehabilitated corridors. However, yield outcomes are highly volatile: maize and soya yields contracted sharply in 2023/24 season, particularly in Chibombo, despite improved physical access to depots and markets, and sunflower and groundnut yields are uneven across distance bands and local agro-ecologies. Interpreted through the Spatial Development Theory and the Sustainable Livelihoods Framework, the findings support a “necessary but not sufficient” interpretation: Improved Rural Connectivity Project roads raise the ceiling of feasible productivity and help farmers stay engaged in key value chains, but realised productivity gains depend critically on climate, agronomy, liquidity and local market and service ecosystems. Policy implications emphasise integrating rural road investments with climate-smart agriculture, timely input systems and rural finance.

The main aim of the study was to analyze the effects of microfinance on the performance of SMEs in Kitwe. SMEs in Kitwe face significant challenges, particularly limited access to formal financing, which constrains their growth and sustainability. A mixed research (qualitative and quantitative) approach was adopted, with 38 SMEs selected through purposive sampling. Primary data were collected using a questionnaire, and data analysis was done using Megastat. This study addresses the gap in empirical evidence regarding the long-term effect of microfinance on the profitability and growth of SMEs in Kitwe, where previous research has been limited. Using the mean vs hypothesized value we found that microfinance has got a statistical significance effect on the profitability of the SMEs. About 13.2% and 73.7% of SMEs reported that net profit increased significantly and increased moderately respectively with the p-value = 1.58e-15 which is less than 0.05. A test to verify if the effect on revenue and profit was different, the result showed that there was no difference significantly and ANOVA confirmed the results. Results also show that job creation increased as result of access to microfinance loans by SMEs and using the hypothesized value we established the statistical significant test results because the p-value = 8.03e-15 is less than 0.05. Hence we conclude that microfinance institutions are doing a very significant task to help SMEs. It is therefore recommended that both SMEs and microfinance institutions be supported at a regular level.

Abstract Botswana adopted IFRS for listed companies to raise comparability and attract investment. Despite adoption, compliance levels vary between firms. This suggests corporate governance may be an important influence, yet local evidence is limited. This quantitative descriptive–explanatory study used a structured questionnaire administered to officers across publicly listed companies on the Botswana Stock Exchange (BSE). Descriptive statistics, Pearson correlation and multiple regression were used to examine the relationship between governance mechanisms (board independence, audit committees, internal controls, ownership structure) and IFRS compliance. The response rate was 80%. Descriptive results show most firms rated their IFRS compliance as moderate to high (75%). Pearson correlations showed audit committee expertise had the strongest positive relation with IFRS compliance (r = 0.68, p < 0.01), followed by board oversight (r = 0.66) and board independence (r = 0.64). Regression analysis produced R² = 0.62; audit committee expertise (β = 0.26, p < 0.01) and board oversight (β = 0.24, p < 0.05) were the strongest predictors. Strong governance mechanisms especially audit committee expertise and active board oversight are associated with higher IFRS compliance. However, weak regulatory enforcement reduces the full effect of governance.

This paper investigates the quality management practices (QMPs) adopted by manufacturing companies in Zambia, synthesizing evidence from existing empirical studies and practitioner reports. The analysis describes commonly used practices, adoption drivers, and implementation gaps, while also examining the key dimensions and strategic emphasis in response to a competitive and challenging business environment. Since 2018, the emergence of successful local conglomerates like TradeKings and Savenda has significantly influenced the industry's quality landscape, pushing the adoption of global best practices in a local context. Key QMPs that significantly impact performance include benchmarking, people management, and top leadership commitment. Crucially, the paper identifies that financial and capability constraints create a significant adoption barrier through a self-reinforcing causal cycle, a challenge severely exacerbated by macro-level contextual issues in Zambia's unreliable infrastructure and limited institutional support. The findings, which are supported by a hypothetical performance model to quantify impact, lead to practical recommendations for a phased roadmap, SME certification support, and supplier development, explicitly linking firm-level quality behaviour to broader industrial policy.

The Par-4 Delta parallel robot is a powerful candidate in most pick and place applications which requires high speed, high acceleration and high precision. The control design is the key for improving the tracking accuracy of parallel robots. The PID controller, includes proportional, integral and derivative terms for tuning the controller. However, optimal tuning process of PID controller is cumbersome unless optimization techniques are proposed. In this study, Whale Optimization Algorithm (WOA) and Fuzzy logic controller are proposed to tune the parameters of controller. The objective of these methods is to optimally tune the parameters of PID controller towards global minimum of tracking errors. Using the Root Mean Square of Error (RMSE) as the metric of evaluation, the numerical results showed that the Fuzzy PID controller with WOA optimized parameters by 77.3% on the xaxis and 66.7% on the z-axis as compared to the other implemented methods.

Family dynamics play a significant role in adolescent substance abuse. Various factors within the family environment can influence the likelihood of adolescents engaging in substance use. The study employed a mixed-methods research because the research questions could best be answered through a combination of quantitative and qualitative data focusing on the role of family dynamics and adolescent substance abuse. The study population for this study involved an estimated population of 100 youths aged between 18-35 years and parents of Mphwere Village. The first objective was to examine how lohmweh cultural norms influence family dynamics and adolescent substance abuse in Mphwere Village. The findings clearly demonstrate that Lohmweh cultural norms significantly shape family dynamics and adolescent substance use in Mphwere Village. Cultural practices influence decision-making, discipline, and attitudes toward alcohol, with fathers and grandparents holding dominant authority in households, reflecting patriarchal and extended family structures that guide how families operate. Disciplinary practices rooted in tradition ranging from corporal punishment to involvement of community elders show the role of cultural values in shaping parenting approaches. The second objective was to assess the effect of parental supervision on adolescent substance abuse within extended families in Mphwere Village. The study revealed that while 43% of adolescents believed it was very likely and 26% somewhat likely that their parents or guardians would notice any changes in behaviour related to alcohol or drug use, a notable minority (32%) felt it was unlikely or very unlikely that such behaviours would be detected. This suggests that limited or inconsistent parental supervision may increase adolescents’ vulnerability to peer pressure and substance use, whereas attentive and engaged parenting acts as a protective factor, discouraging experimentation with substances. The third objective was to investigate how parental education contribute to adolescent substance abuse in Mphwere Village. The finding that addresses the second objective assessing the effect of parental supervision on adolescent substance abuse within extended families in Mphwere Village relates to the reported patterns of parental monitoring and involvement. Specifically, respondents indicated varying levels of parental oversight, with some parents consistently supervising their children’s activities and school performance, while others provided minimal or irregular guidance. This variation in supervision suggests that adolescents with limited parental oversight may be more susceptible to experimenting with substances, whereas those experiencing regular monitoring and guidance are likely better protected against substance use. Based on findings of study, it was commendations that Mphwere Village should designing substance abuse prevention programs that respect Lohmweh cultural norms, engaging elders and community leaders to align interventions with local traditions and authority structures. The study also recommends Mphwere Village should encourage parents and guardians to consistently monitor adolescents’ activities and behaviours, providing guidance and support to reduce susceptibility to substance use