Mrindoko Rashid Nicholaus

Mrindoko Rashid Nicholaus

Auto-generated profile, based on publicly available information

Mrindoko Rashid Nicholaus

Mbeya University of Science and Technology

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 September 2025 in Journal of Information Systems and Informatics
Verified
Journal Article
Open access
PDF file
JAJosephat Benard Agostino
Josephat Benard Agostino
NMNicholaus Mrindoko
Nicholaus Mrindoko
Vehicle breakdowns are a growing problem worldwide, often caused by overheating, oil leaks, battery problems, flat tires, fuel system failures, and other issues. These incidents frequently result in delays, safety hazards, and costly repairs. Existing systems mainly focus on locating nearby mechanics but lack self-diagnostic capabilities. This study presents a mobile-based expert system that offers step-by-step repair instructions, troubleshooting flowcharts, and safety guidelines. The system integrates ensemble machine learning models and rule-based inference to empower users to independently diagnose and resolve minor vehicle faults. The system is designed with offline capability and a user-friendly interface, this tool ensures accessibility and reliability, especially in remote areas. Initial testing demonstrated a classification accuracy of 88% in diagnosing common faults, confirming the system’s effectiveness and potential for real-world deployment.

1 January 2026 in Mathematics Open
Verified
Journal Article
Open access
PDF file
BTBuberwa M. Tibesigwa
Buberwa M. Tibesigwa
MNMrindoko Nicholaus
Mrindoko Nicholaus
IKIsack Ephraim Kibona
Isack Ephraim Kibona
Integer factorization has raised concerns, particularly in the digitalization era, based on the fact that positive integers can be employed in the safety of information in cryptography. This study introduced a square table that is instrumental in the analysis of all positive integers concerning their prime factors. The systematic arrangement of triangular and nontriangular numbers in this table leads to formulas and instructions useful for factorization.

31 December 2025 in Applied Computer Science
Verified
Journal Article
Open access
PYPascal Yamakili
Pascal Yamakili
MNMrindoko Rashid Nicholaus
Mrindoko Rashid Nicholaus
KGKenedy Aliila Greyson
Kenedy Aliila Greyson
The architectural design of deep learning models significantly influences their predictive capabilities in environmental monitoring tasks. This paper investigates the individual and collective effects of residual learning and feature fusion mechanism to improve the performance of soil moisture estimation on the designed architecture of the deep learning model. In this study, the data fusion mechanism was used to integrate Normalized Difference Water Index (NDWI), Synthetic Aperture Radar (SAR), and satellite imagery datasets containing Red, Green, and Blue (RGB) color channels, which consist of images or data collected by a radar system that uses microwaves to produce images of the Earth's surface. Three model variants were developed, each selectively omitting one or more of these architectural elements, and their performance was evaluated using three standard metrics, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2). The results of the final proposed model architecture showed that while each component contributes to accuracy improvements, the combination of residual learning and feature fusion yields the most significant gains. Improved results of RMSE = 0.0117, R²=0.814 and Mean Absolute Error=0.0148 were obtained. These performance indicators were superior to the results of most of the baseline models after comparative analysis. Thus, this study provides insights into model component selection for deep learning soil moisture prediction applications.

2 February 2025 in Journal of Applied Sciences and Environmental Management
Verified
Journal Article
Open access
PDF file
OMO. D. Mbita
O. D. Mbita
MNM. R. Nicholaus
M. R. Nicholaus
KKKazema Kazema
Kazema Kazema
This paper aims to evaluate the efficiency and reliability of fertilizer subsidy systems in the Mbeya Region of Tanzania, while exploring the role of blockchain technology in driving enhancements to these systems. The research presents a blockchain-based e-voucher system as the innovative solution to these challenges, providing a robust framework that incorporates architectural design and algorithmic solutions to enhance efficiency within the distribution process. The findings demonstrate significant improvements in addressing the identified challenges, including streamlined application processing, voucher issuance and redemption, reimbursement procedures, and increased transparency and traceability. The proposed hybrid architecture integrates well-structured algorithms to improve operational efficiency and ensure a more secure and fair distribution system. These findings underscore the urgent need for novel approaches to improve agricultural productivity and food security, advocating for the widespread adoption of blockchain technology within the agricultural sector.

25 September 2025 in International Journal of Intelligent Computing and Information Sciences
Verified
Journal Article
Open access
PDF file
MNMrindoko Rashid Nicholaus
Mrindoko Rashid Nicholaus
Recently, localization systems tailored for indoor environments have been introduced, leveraging the existing wireless local area network (WLAN) infrastructure. These systems utilize position fingerprinting methods rather than direction-based or time-of-arrival approaches to determine the spatial positions of mobile users. Nevertheless, experimental studies on these systems indicate that factors such as signal attenuation and scattering caused by the higher density of walls significantly impact the accuracy and performance of indoor positioning. Furthermore, the accuracy of indoor positioning systems (IPS) may be compromised by variations in environmental factors, including alterations in height, the introduction or removal of a WLAN Access Point (AP), or modifications to AP power settings. This paper analyses the impact of AP power through a probabilistic analytical model that exclusively utilizes high signal relations to mitigate the effects of low signal relations on WLAN fingerprinting-based IPS, thereby enhancing accuracy performance. Through comprehensive experimental evaluations, the proposed algorithm demonstrates an improvement in the accuracy of the IPS by an average of 15.794 % as measured by the Root Mean Square Error (RMSE). The findings suggest that the integration of AP power and high signal relations can substantially enhance the accuracy performance of WLAN fingerprinting-based IPS.

23 April 2024 in The Indonesian Journal of Computer Science
Verified
Journal Article
Open access
PDF file
PYPascal Yamakili
Pascal Yamakili
MNMrindoko Nicholaus
Mrindoko Nicholaus
Effective radio network planning requires understanding an area's radio propagation characteristics. This investigation uses dependable techniques to examine the movement of wireless signals in Tanzania's rural locations. Propagation characteristics in selected rural Tanzanian communities (South Chunya) are examined as a case study, and recommendations are made based on the findings, particularly for wireless service providers or researchers looking to improve wireless connectivity in rural communities. Important radio parameters such as Pathloss, Signal to Noise ratio, Bandwidth throughput, Spectral efficiency and Spectral band were examined. This was done after simulating signal transmission from the Base station transmitter to the Base station receiver and observing power and attenuation. Their corresponding results are discussed and evaluated. The general observation of the pass loss results for both operating frequencies 800MHz and 2000MHz have shown that only few areas are experiencing strong signal after initial signal power transmission, large areas served by these macro sites are experiencing huge path loss. This is evidently affected by the terrain of an area and the carrier frequency of operators.