Browse
Recent Submissions
Item Enhancing coffee leaf rust detection using DenseNet201: A comprehensive analysis of the Mbozi and public datasets in Songwe, Tanzania(African Journal of Empirical Research, 2025) Karia, Adrian Jackob; Ally, Juma Said; Leonard, StanleyCoffee Leaf Rust (CLR) is a worldwide devastating fungal disease that threatens coffee production, upsetting economic and farmers' livelihoods. Traditional methods of detecting CLR heavily rely on using machine-learning (ML) models trained through weakly collected datasets and physical inspection, which is tedious, time-consuming, and subject to human error. This study explores the performance of the DenseNet201 model using three datasets: Mbozi, Public, and Combined (a merger of Mbozi and Public datasets). Machine Learning Theory guided this research. The study objective is to assess the influence of dataset quality on CLR detection, analyze Mbozi and Public datasets using DenseNet201, and enhance robustness by merging the two datasets. A study of CLR severity was conducted using systematic sampling techniques. Leaves from multiple coffee farms were collected, representing different levels of infection. The Mbozi dataset, sourced from high-resolution images captured from Tanzania's Songwe coffee plantations, was analyzed for quality under controlled conditions, including environmental factors, image clarity, resolution, labeling consistency, and class balance, based on data completeness, image quality score, visual inspection, and model performance. DenseNet201 was trained and validated on each dataset, achieving its highest accuracy with the Mbozi dataset at 98.72% and a validation accuracy of 97.65%, demonstrating the importance of consistent image quality and accurate annotations. In contrast, the public dataset suffered from inconsistencies in resolution and labeling, resulting in a lower training and validation accuracy of 96.86% and 96.42% respectively. The Combined dataset, which integrated the strengths of both datasets, exhibited a stronger generalization with an accuracy of 97.48% and validation accuracy of 97.49%, balancing the need for high-quality images with environmental variability. The study shows improved CLR detection speed and accuracy due to high-quality and consistently labeled images from the Mbozi dataset. It recommends that future models integrate regionally relevant and high resolution datasets for robust performance in real-world agricultural conditions, providing coffee farmers with timely disease intervention tools for better production management and economic stability in coffee-growing regions.Item Group-Based Data Offloading Techniques Assisted by D2D Communication in 5G Mobile Network(Tanzania Journal of Engineering and Technology, 2022-07-30) Ally, Juma SaidMachine type communication devices proposed as one of the substantial data collections in the 5G of wireless networks. However, the existing mobile communication network is not designed to handle massive access from the MTC devices instead of human type communication. In this context, we propose the device-to-device communication assisted a mobile terminal (smartphone) on data computing, focusing on data generated from a correlated source of machine type communication devices. We consider the scenario that the MTC devices after collecting the data will transmit to a smartphone for computing. With the limitation of computing resources at the smartphone, some data are offloaded to the nearby mobile edge-computing server. By adopting the sensing capability on MTC devices, we use a power exponential function to compute a correlation coefficient existing between the devices. Then we propose two grouping techniques K-Means and hierarchical clustering to combine only the MTC devices, which are spatially correlated. Based on this framework, we compare the energy consumption when all data processed locally at a smartphone or remotely at mobile edge computing server with optimal solution obtained by exhaustive search method. The results illustrated that; the proposed grouping technique reduce the energy consumption at a smartphone while satisfying a required completion time.Item A Comparison Review of Indoor Positioning Techniques(IJC, 2016) Mrindokoa, Nicholaus R.; Dr. Minga, Lusajo M.The advances in positioning based technologies and the expanding significance of indoor positioning led to a growing business interest in location-based services. Today, most application requirements are real-time tracking of physical possessions inside structures precisely. The demand for indoor localization services has turned into a key essential in some markets. Moreover, indoor positioning technologies address the inadequacy of global positioning system inside a closed environment. This paper aims to provide the reader with a comparison review of different parameter that affects indoor localization. The comparison review is based on three techniques known as Angle of arrival (AoA), Time of arrival (ToA) and Fingerprinting techniques to deliver a better understanding of state-of-the-art of these techniques and inspire new research endeavours in this promising field. For this purpose, three localization positions and location estimation schemes are reviewed with a conclusion and future trends.Item Anisotropic Core-Envelope Compact Star Model with Conformal Symmetry(IACS, 2025-07-09) Kowa,Y K; Jape, J W; Sunzu, J M; Maharaj,S D.In this paper, the combination of the conformal Killing vector and equations of state for double layered stars provides new solutions to the Einstein field equations in the core-envelope setting. The matter composition in the core layer obeys a linear equation of state, while in the envelope is described by a quadratic equation of state. The behavior of the matter variables in the stellar sphere is found to be well behaved, and the model satisfies stability conditions. The generated compact star model satisfies the energy and equilibrium conditions for the behavior of the natural forces. The mass, compactness, and surface redshift also fall within the required range for observed stars. Radii and masses of the stars PSRJ1903?0327, SAXJ1808.4-3658, VelaX-1, 4U1608-52, HerX-1, SMCX-1 and EXO1785-248 have been regained. This signifies the astrophysical importance of our generated class of exact solutions.Item Performance Analysis of MCSS for the Indoor BPLC Systems(International Scholarly and Scientific Research & Innovation, 2016-05-24) Justinian Anatorypower line networks are promise infrastructure for broadband services provision to end users. However, the network performance is affected by stochastic channel changing which is due to load impedances, number of branches and branched line lengths. It has been proposed that multicarrier modulations techniques such as orthogonal frequency division multiplexing (OFDM), MultiCarrier Spread Spectrum (MCSS), wavelet OFDM can be used in such environment. This paper investigates the performance of different indoor topologies of power line networks that uses MCSS modulation scheme.It is observed that when a branch is added in the link between sending and receiving end of an indoor channel an average of 2.5dB power loss is found. In additional, when the branch is added at a node an average of 1dB power loss is found. Additionally when the terminal impedances of the branch change from line characteristic impedance to impedance either higher or lower values the channel performances were tremendously improved. For example changing terminal load from characteristic impedance (85 ) to 5 the signal to noise ratio (SNR) required to attain the same performances were decreased from 37dB to 24dB respectively. Also, changing the terminal load from channel characteristic impedance (85 ) to very higher impedance (1600 ) the SNR required to maintain the same performances were decreased from 37dB to 23dB. The result concludes that MCSS performs better compared with OFDM techniques in all aspects and especially when the channel is terminated in either higher or lower impedances.Item Digital Terrestrial Broadcasting Technologies and Implementation Status(World Academy of Science, Engineering and Technology, 2013-03-25) Mvungi, Nerey H.; Anatory, Justinian; Simba, FatumaDigital broadcasting has been an area of active research, development, innovation and business models development in recent years. This paper presents a survey on the characteristics of the digital terrestrial television broadcasting (DTTB) standards, and implementation status of DTTB worldwide showing the standards adopted. It is clear that only the developed countries and some in the developing ones shall be able to beat the ITU set analogue to digital broadcasting migration deadline because of the challenges that these countries faces in digitizing their terrestrial broadcasting. The challenges to keep on track the DTTB migration plan are also discussed in this paper. They include financial, technology gap, policies alignment with DTTB technology, etc. The reported performance comparisons for the different standards are also presented. The interesting part is that the results for many comparative studies depends to a large extent on the objective behind such studies, hence counter claims are common.Item The Establishment of the School of Virtual Education at the University of Dodoma in Tanzania(International Journal of Computer Applications, 2015-04-16) Justinian AnatoryThis paper describes the personal experience and reflections of the author who was the first Dean of the School of Virtual Education (SoVE) at the University of Dodoma (UDOM) in Tanzania. It describes in detail different tactics the author used to establish SoVE. In additional, it is suggested that the best way to implement a vibrant SoVE in developing countries like Tanzania can include three departments namely Department of Content Engineering and Multimedia Technology (DoCEMT), Department of Virtual Educational Technologies and Applications (DoVETA) and Department of Virtual Education Delivery (DoVED). The first two Departments are for capacity building while the third is for technology enhanced teaching and learning, online teaching and learning and instructional design for virtual delivery.Item A Price Based Spectrum Sharing Scheme in Wireless Cellular Networks(IIST, 2013-11-08) Kalolo, Sadath; Sam, Anael; Machuve, Dina; Anatory, JustinianRadio frequency spectrum scarcity has become a high priority research area over the past few years. The huge increase of network subscribers with multimedia applications coupled with underutilization of radio frequency spectrum motivates the search for other measures to address the scarcity of radio frequency spectrum. This work investigates on a price based spectrum sharing scheme for connection-oriented traffic in wireless cellular networks as a solution to address the scarcity of radio frequency spectrum. Dynamic pricing approach is applied with traffic overflows into neighbor networks. Performance evaluations of the scheme at steady state using MATLAB simulations reveal significant gains to the quality of service. Application of the scheme to highly loaded network traffic improves both network revenue and traffic channel utilizations.Item Consumer Preferences for Mobile Carriers in Tanzania: A Case of Group, Family, Age and Gender(International Journal of Computer Applications, 2015-04-16) Anatory, JustinianThis paper investigates age, family, group and gender influence consumer preference for selection of the mobile carrier. About seventy seven students from high learning institutions in Dodoma Municipality participated in responding to prepared questionnaires. The results indicate that family members and friends are contributing in influencing consumer preferences to select mobile services provider, although at smaller margins. This paper revealed also that there is no direct relationship between selection of a mobile carrier and age or gender.Item A Review of MC-CDMA Based Broadband Power Line Communications Systems(International Journal of Computer and Information Technology, 2015-07-04) Ngondya,Daniel; Anatory ,Justinian; Abdil RashidA number of MC-CDMA-based BPLC systems have been proposed-differing in terms of complexity and performance. This work comprehensively reviews MC-CDMA-based BPLC solutions, indicating similarities, differences, advantages and disadvantages of each. The solutions have been classified into two: conventional MC-CDMA-based BPLC solutions and MC CDMA-based BPLC solutions with MAI reduction techniques. A total of 5 solutions have been summarized.Item Using Learning Analytics to Predict Students’ Performance in Moodle Learning Management System: A Case of Mbeya University of Science and Technology.(EJISDC, 2017) Mwalumbwe, Imani; Mtebe, Joel S.The past decade has seen the rapid adoption and use of various Learning Management Systems (LMS) in Africa, and Tanzania in particular. Institutions have been spending thousands of dollars to implement these systems in a bid to improve the quality of education as well as increasing students’ enrolments through distance and blended learning. However, the impact of these system on improving students’ performance has been a popular subject of research in recent years. Studies have been relying on data from users’ opinions and subjective interpretation through surveys to determine the effectiveness of LMS usage on students’ learning performance. The use of such data is normally subject to the possibility of distortion or low reliability. Therefore, this study designed and developed Learning Analytics tool and used the tool to determine the causation between LMS usage and students’ performance. Data from LMS log of two courses delivered at Mbeya University of Science and Technology (MUST) were extracted using developed Learning Analytics tool and subjected into linear regression analysis with students’ final results. The study found that discussion posts, peer interaction, and exercises were determined to be significant factors for students’ academic achievement in blended learning at MUST. Nonetheless, time spend in the LMS, number of downloads, and login frequency were found to have no significant impact on students’ learning performance. The implications of these results on improving students’ learning are discussed.Item Public Perception of Climate Risk and Adaptation in Tanzania: a Systematic Review(Sokoine University of Agriculture, 2023) Nyinondi, P.S; Sospeter,MClimate change is a pressing global challenge of the 21st century, with impacts including global warming, drought, famine, floods, tropical storms, and cyclones. One of the biggest challenges to mitigating climate change is people's perception of its risks. This study provides valuable insights on the public perception of climate risk and adaptation in Tanzania through a systematic review of peer-reviewed papers. The search was conducted using keywords related to climate change awareness, knowledge, perception, attitude, and risk adaptation from the Sokoine University of Agriculture Institutional repository (SUAIR) for publications between 2010 and 2022, 48 peer reviewed articles were reviewed. The review found that there is a high level of awareness (87.5%) of climate change, with many (77%) recognizing its impacts on their daily lives in terms of economic activities and gender roles. However, the perception of climate risk varies depending on factors such as gender, location, and socioeconomic status. For example, people living in rural areas perceived climate risks such as floods and drought more than those in urban areas did. Attitudes towards climate change adaptation also vary among different groups, with some people such as farmers more resilient and willing to adapt than pastoralists, people living in urban areas than people living in rural areas. The review identifies knowledge gaps in understanding the causes and impacts of climate change. Overall, this systematic review provides a comprehensive picture of current knowledge and understanding of the public perception of risk adaptation in Tanzania, highlighting areas for further research and policy action. Keywords: Climate change, Perception, Adaptation, Risk, TanzaniaItem Improving Network Security: An Intrusion Detection System (IDS) Dataset from Higher Learning Institutions, Mbeya University of Science and Technology (MUST), Tanzania.(EANSO, 2024-01-07) Sindika, Daud M.; Dr. Nicholaus, Mrindoko R.; Dr. Hamadi, Nabahani BNowadays, Internet-driven culture securing computer networks in Higher Learning Institutions (HLIs) has become a major responsibility. Intrusion Detection Systems (IDS) are crucial for protecting networks from unauthorized activity and cyber threats. This paper examines the process of improving network security by creating a comprehensive IDS dataset using real traffic from HLIs, highlighting the importance of accurate and representative data in improving the system's ability to identify and mitigate future cyber-attacks. The IDS model was created using a variety of machine learning (ML) techniques. Metrics like accuracy, precision, recall, and score were used to assess the performance of each model. The dataset used for training and testing was real-world network traffic data obtained from the institution's computer network. The results showed that the developed IDS obtained exceptional accuracy rates, with Random Forest, Gradient Boosting, and XGBoost models all achieving an accuracy of around 93%. Precision and recall values were likewise quite high across all algorithms. Furthermore, the study discovered that data quality has a substantial impact on IDS performance. Proper data preparation, feature engineering, and noise removal were found to be helpful in improving model accuracy and reducing false positives. While the IDS models performed well throughout validation and testing, implementing such systems in a production setting necessitates careful thought. As a result, the essay also examined the procedures for testing and deploying the IDS models in a real-world scenario. It underlined the significance of ongoing monitoring and maintenance in order to keep the model effective in identifying intrusions. The research aids in the progress of network security in HLI. Educational institutions can better protect their precious assets and sensitive information from cyberattacks by understanding the impact of data quality on IDS performance and implementing effective deployment techniques.Item ICT Adoption and Access Among Small-Scale Tea Growers in Rungwe, Tanzania(Mbeya University of Science and Technology (MUST), 2023) Madembwe, Peter; Kusyama, Sadiki; Minga, LusajoTanzania is known for its high-quality tea production, with Rungwe District being a major producer. Though the sector faces various challenges, including low productivity, limited market access, and poor quality, the adoption of Information and Communication Technology (ICT) is likely to solve these challenges and enhance the overall performance of the tea industry in Rungwe. However, there is a shortage of data on ICT usage in Africa, specifically in Tanzania. This paper intends to explore the extent to which ICT has been adopted among Tanzanian Small-Scale Tea Growers (SSTGs) in Rungwe district and its impact on the tea industry. The study found that SSTGs in Rungwe have been adopting various ICT tools and applications to enhance their tea production processes, access information on market trends and opportunities, and access knowledge and training. These tools include radios, television, mobile apps, the internet (online platforms and YouTube), and sensor-based technologies, which are used to monitor crop growth, soil moisture, and weather conditions. The tools have enabled farmers to make more informed decisions about their crop management and improve their yields. The adoption of ICT in small-scale tea production in Rungwe has had a positive impact on the sector, enhancing productivity and efficiency, improving market access, and increasing the income and livelihoods of SSTGs.