EANSO East African Nature and Science Organization Journals
Not a member yet
3828 research outputs found
Sort by
Comparison of Deep Learning Models in Predicting Water Deficits in Semi-Arid Regions: A Case Study of Dodoma, Tanzania
Get PDFThe escalating global freshwater shortage is driven by socio-economic development, changing consumption patterns, and systemic inefficiencies, with semi-arid regions like Dodoma, Tanzania, being especially vulnerable. Traditional statistical and regression-based models for predicting water deficits have proven insufficient in capturing the complex, nonlinear interactions among climatic, hydrological, and anthropogenic factors. To address this gap, this study proposes a deep learning-based predictive framework utilising advanced algorithms, Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Deep Neural Networks (DNN) to improve the forecasting of water deficits. Using a thirteen-year (13) dataset collected from the semi-arid climate region of Dodoma, encompassing meteorological, hydrological, and socioeconomic variables. The models were trained and evaluated using performance metrics such as Root Mean Square Error (RMSE) and R-squared (R²). The DNN model demonstrated superior performance with an RMSE of 0.049 and an R² of 1.000, significantly outperforming other models. LSTM, CNN, and RNN models showed moderate to weak predictive accuracy, particularly in handling long-term dependencies and extreme deficit events. The key finding of this study is that the DNN model provides highly reliable and accurate water deficit predictions, making it the most effective among the tested deep learning approaches. This result highlights the value of incorporating deep learning into water resource planning, especially in data-scarce, semi-arid regions. The study concludes that DNN-based models should be prioritised for operational deployment in early warning systems and decision-making platforms. Future work should explore hybrid architectures, hyperparameter tuning, and integration with real-time data sources to enhance robustness and applicabilit
Effects of Employee-Hotel Information System Interaction Rate on Service Innovation Levels in Star-Rated Hotels in Nyeri County, Kenya
Get PDFDeveloped countries have integrated people and technology into their hotel systems, but many developing countries lack sufficient information on this integration. Developing countries like Kenya have mainly focused on the determinants of technology adoption and installing well-established technological systems. While the interaction between people and technology is reported to improve overall operations in Kenyan hotels, research has not adequately shown their specific impacts on service innovation. The study's objective was to determine the effects of Employee-Hotel Information System interaction on service innovation in Nyeri County Star-Rated Hotels. The theory of people-technology interaction guided this study. A descriptive cross-sectional research design was used, targeting 335 employees from the human resource data. Purposive and convenience sampling techniques selected a sample of 178 employees. Primary data was collected using closed-ended questionnaires administered to employees. The data’s reliability was tested with Cronbach’s alpha at α ≥ 0.70. Data analysis was conducted using SPSS version 25, incorporating descriptive statistics such as percentages. Categorical regression and exploratory factor analysis were used to quantify the variables for precise estimates and to test their relationships. Significance levels were set at α ≤ 0.05. Results indicated that the usage of the Electronic Point of Sale System (p=0.001) greatly influenced service innovation in Nyeri County. Conversely, the usage of the Reservation System (p=0.771), Rooms Management System (p=0.447), Mobile Device Technology (p=0.717), Biometric Technology (p=0.600), and Virtual Reality (p=0.136) had an insignificant impact. The study concludes that most hotel managements had invested in the Electronic Point of Sale System, which significantly contributed to service innovation. The findings demonstrate that hotels in Nyeri have adopted a certain level of technology for their operations, leading to increased service innovation, such as timely delivery and the development of additional features for food and beverage products
Genetic-Based Algorithms Towards Effective Stock Price Prediction: Case Study of Dar es Salaam Stock Exchange
Get PDFPredicting the movement of stock prices in financial markets has become a challenging task. This is due to the fact that stock prices are dynamic and volatile, exhibiting a stochastic behaviour. Hence, it requires a well-constructed predictive model capable of determining the probable cause of the price of a stock in the future. In an attempt to address the challenge, this study has explored prediction parameters and proposed a Genetic Algorithm (GA) approach. The proposed predictive model is capable of determining future stock price trends. The proposed approach involves identifying patterns using statistical concepts and predicting stock prices. The approach has been deployed and evaluated using the dataset (2014–2018) collected from the Dar es Salaam Stock Exchange (DSE). The evaluation results proved that the proposed Genetic Algorithm (GA) approach achieved a prediction accuracy of 94.86% when used as a natural selection algorithm to find the optimal stock price. Hence, the effectiveness of the proposed algorithm has been confirmed, and this study is a milestone towards the improvement of stock price prediction in the Stock Exchange financial marke
Development of Pavement Condition Prediction Model for Airport Runway to Enhance Operational Availability: The Case of Mtwara Airport
Get PDFAirport runway pavements constitute critical infrastructure components requiring systematic maintenance management to ensure operational safety and efficiency. This study developed a pavement condition prediction model for airport runways to enhance operational availability, using Mtwara Airport as a case study. The research employed a mixed-methods approach involving comprehensive surveys of 70 aviation professionals, including civil engineers, technicians, managers, artisans, and pilots, to identify and quantify factors affecting runway pavement deterioration. Using Relative Importance Index (RII) analysis, twelve critical factors were systematically evaluated and ranked based on their impact on pavement condition. Construction quality emerged as the most significant factor (RII = 0.726), followed by aircraft weight (RII = 0.714) and subgrade strength (RII = 0.703). A multiple regression model was subsequently developed, incorporating the eight highest-importance factors, achieving strong predictive capability with R² = 0.828, explaining 82.8% of the variance in pavement condition. The model equation demonstrated statistical significance (F = 33.756, p < 0.001). Key limitations identified include systematic upward bias for poor to moderate pavement conditions, indicating the model's optimal performance for good to excellent conditions and highlighting areas requiring future calibration enhancement. Despite these limitations, comprehensive validation results confirm the model's practical utility for proactive maintenance planning. The study provides airport managers with a quantitative tool for data-driven decisions regarding resource allocation and improving runway operational availability, representing a significant advancement in pavement management for tropical developing country contexts
Design and Development of an AVR Microcontroller-Based Industrial Programmable Logic Controller
Get PDFThis script presents the design and implementation of an industrial Programmable Logic Controller (PLC) developed using the AVR ATmega2560 microcontroller and tailored for educational and industrial automation applications. This PLC integrates 15 digital inputs, 10 digital outputs, 10 analogue voltage inputs, 6 current loop analogue inputs (4–20 mA via precision shunt resistors), and 8 analogue voltage outputs generated through a DAC60508 over SPI, scaled for 0 –10 V operation using a precision op-amp circuit, utilising a compact design. Furthermore, the controller supports Modbus RTU communication over RS232, RS485, and USB interfaces, enabling interoperability with SCADA platforms such as ScadaBR. In addition to that, the firmware is developed using OpenPLC runtime, offering IEC 61131-3 compliant programming in ladder logic. Moreso, the system also supports I2C-based EEPROM for data retention, I2C-based expansion, and its real-time performance is validated through sequential process control and SCADA visualisation tests. This low-cost, flexible PLC platform provides an ideal foundation for teaching automation principles, prototyping industrial control logic, and exploring Industry 4.0 integration. In this context, this script aims to design and develop a low-cost, programmable logic controller based on the AVR microcontroller, providing versatile I/O options and multiple communication interface
Development of an Internal Corrosion Maintenance Management System to Enhance the Operational Availability of Natural Gas Midstream Pipeline Systems: A Case Study of Gasco's Mtwara to Dar Es Salaam Pipeline System
Get PDFInternal corrosion significantly threatens midstream natural gas pipelines' reliability, safety, and efficiency, notably Tanzania's GASCO-operated 542 km Mtwara-Dar es Salaam pipeline transporting gas from Mnazi Bay since 2015. This study identifies key corrosion drivers, develops a predictive model for operational availability, and proposes a validated Internal Corrosion Management System (ICMS) to enhance performance. Using a mixed-methods approach involving surveys from 46 of 64 professionals at GASCO, TPDC, and EWURA, chemical analyses of 2,615 SCADA records, and machine learning modeling via XGBoost, Random Forest, and Support Vector Machine algorithms, the research highlighted major factors through Relative Importance Index analysis: solid/liquid contaminants (RII=0.932), moisture (RII=0.924), infrequent pigging (RII=0.852), design/material issues (RII=0.800), microbiological activity (RII=0.752), operational conditions (RII=0.728), and inhibitors (RII=0.708). The XGBoost model achieved superior performance with 87.43% accuracy, 87.21% precision, 87.32% recall, and 87.27% F1-score, outperforming Random Forest and SVM. Feature importance analysis identified the Corrosive Index (0.23), Fe₂O₃ percent (0.19), and Cl percent (0.15) as the most influential predictors. Model validation demonstrated robust performance with 91.67% severe case detection and 86.9% temporal F1-score. The developed ICMS, integrated with SCADA systems, provides real-time monitoring, automated severity classification, and maintenance prioritisation, supporting data-driven decisions to lower costs and ensure sustainable gas supply under EWURA regulations aligned with NACE SP0110, ASME B31.8S, and API 1160 standard
Parliaments and Post-Conflict Justice: Amplifying the Voices of Children Born in LRA Captivity in Northern Uganda
Get PDFIntroduction: This paper explores the intersection of parliamentary action and post-conflict justice in Northern Uganda, with a specific focus on children born in captivity during the Lord’s Resistance Army (LRA) insurgency. Methodology: The qualitative, participatory research design was employed, with the use of In-depth oral interviews, Focus Group Discussions (FGDs), Key Informant Interviews, Document Review and Participatory Tools to collect the necessary data. Findings: Key emerging themes include existential crisis of identity, stigma and social exclusion, structural marginalisation and legal invisibility, psychological and intergenerational trauma, aspirations and the power of voice. Conclusions: The stories shared by children born in captivity, their mothers, and various community stakeholders reveal persistent exclusion and neglect. At the policy level, the voices of one of the policy makers confirm that the issue of children born in captivity remains an overlooked category in national development plans and post-conflict frameworks. Amplifying these voices is a moral and historical obligation, requiring a collective reimagining of community, policy, and tradition, one where inclusion is not conditional on lineage or legitimacy, but anchored in shared humanity. Recommendations: This paper argues that Parliament has both a moral and constitutional obligation to address the structural barriers confronting these children, targeted legislative interventions, and culturally sensitive integration programs. It further recommends psychological healing and mental health interventions, educational support and livelihood empowerment, religious engagement and faith-based support, and inclusive national dialogues that centre these children as rightful stakeholders in Uganda’s post-conflict futur
Timber Properties of Lesser-Known Toona ciliata M. J. Roemer from Agroforestry System in Moshi Rural District, Tanzania and Its Potential Substitution for Well-known Species
Get PDFThis study investigated the physical and mechanical properties of Toona ciliata (Australian Red Cedar), a lesser-known timber species grown in agroforestry farms in Moshi Rural District, Kilimanjaro Region in Tanzania, with a focus on some of its physical and mechanical properties and potential substitution for well-known timber species in various applications. Whereas the physical properties were Wood Colour and Basic Density, the mechanical properties were Static Bending (Modulus of Elasticity/Bending strength, Modulus of Rupture/Stiffness and Work to Maximum Load), Compression parallel to grain, Shear parallel to grain and Cleavage. Three defect-free sample trees were used for assessment of the properties using standard operating procedures stipulated by the International Standards Organization (ISO). Descriptive statistics were used to summarize the properties, and regression analysis explored relationships between basic density and mechanical properties. Results indicated that T. ciliata has whitish sapwood and reddish heartwood with a mean Basic Density of 531 kg/m³, classifying it as medium-density timber. The key mechanical properties include Modulus of Elasticity (4,935 N/mm²), Modulus of Rupture (49 N/mm²), Compression parallel to the grain (30.8 N/mm²), Shear (11.2 N/mm2) and Cleavage (18.4 N/mm - width). Density revealed strong positive correlations with Modulus of Elasticity, Modulus of Rupture and Compression strength. A one-way analysis of variance (ANOVA) showed no significant radial variation in Basic Density. Comparative analysis with Khaya anthotheca (East African mahogany) and Uapaca kirkiana (sugar plum) highlighted similarities, suggesting that T. ciliata could substitute these species in applications requiring toughness, bending strength, and stiffness. The study concluded that T. ciliata is a viable alternative in timber markets, particularly where medium-density wood is require
Climate Variability in Narok County of Kenya: A Temporal Analysis of Temperature and Rainfall
Get PDFThis study examines the temporal trends and magnitude of variability in temperature and rainfall in Narok County, Kenya. The study used in situ observation data from the Narok Meteorological Station. Non-parametric Mann-Kendal (z) and Sen Slope (Q) tests were employed on monthly, seasonal, and annual temperature and rainfall data in evaluating the trend and magnitude of change. Coefficient of Variation was calculated to assess the degrees to which seasons and annual climate parameters had been varying. Change point detection using Sequential Mann-Kendal test was performed to establish change points and shifts in the data series. Both minimum and maximum temperatures were lowly variable in all seasons. Monthly mean temperatures were notably variable, contributing to a positive significant 0.50C rise in the long-term average. Seasonal variation in rainfall was highest in October-November-December season (C.V = 69.5%) and January – February (C.V = 60.1%), while moderate in June – July – August – September (46.1%) and March – April – May (35.6%). Monthly rainfalls were equally highly variable but contributed a minimal, non-significant (2%) drop in the long-term mean. A significant rising trend in minimum temperature has been realized at the rate of 0.070C annually. The maximum temperature portrayed lacks trend and consistency. Rainfall trends were decreasing but non-significant. Seasonal rates of precipitation changes were equally varied and non-significant (p>0.05) across the four seasons. Minimum temperatures mostly recorded higher than the 50-year average, except for the period 1990 to 1993, realizing a significant shift in 2006. Maximum temperature exhibited numerous overlaps, which signifies a lack of a significant trend. A shift in the rains was noticeable in 1964, followed by a largely below normal average for the years that followed. Changes in climate patterns suggest that traditional livelihood and conservation practices may no longer be reliable; therefore, an urgent adaptation-oriented policies are needed to build resilience
Forest Ecosystems and Climate Change in Ethiopia: Challenges and Adaptive Solutions: Review Article
Get PDFThe review article, "Forest Ecosystems and Climate Change in Ethiopia: Challenges and Adaptive Solutions," explores the critical interrelations between Ethiopia's forest ecosystems and climate change. The primary objective is to assess the effectiveness of adaptive strategies, particularly community-based forest management and agroforestry, within climate resilience. A systematic literature review was conducted, encompassing 69 studies published since 2020, to evaluate the multifaceted impacts of climate change on forest health, deforestation drivers, and existing policy frameworks. The results reveal that Ethiopia's forests face severe threats from climate change, including shifts in biodiversity and an increase in deforestation driven by agricultural expansion and illegal logging. Despite initiatives like the Climate Resilient Green Economy (CRGE) strategy and the Green Legacy Initiative, challenges persist, including inadequate policy enforcement, land tenure issues, and socio-economic pressures that hinder effective conservation. The conclusion emphasises the necessity for integrated, community-focused strategies and enhanced policy coherence to address these barriers. The findings suggest that strengthening local governance, securing land rights, and exploring alternative livelihood options are essential for sustainable forest management in Ethiopia. Overall, this review provides insights that are vital for policymakers and stakeholders aiming to bolster forest resilience and contribute to global climate change mitigation efforts