Jean Pierre Nyakuri

Mr. Jean Pierre Nyakuri


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
2 July 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JNJean Pierre Nyakuri
Jean Pierre Nyakuri
CNCelestin Nkundineza
Celestin Nkundineza
OGOmar Gatera
Omar Gatera
KNKizito Nkurikiyeyezu
Kizito Nkurikiyeyezu
GMGervais Mwitende
Gervais Mwitende
Climate change exacerbates the challenges of maintaining crop health by influencing invasive pest and disease infestations, especially for cereal crops, leading to enormous yield losses. Consequently, innovative solutions are needed to monitor crop health from early development stages through harvesting. While various technologies, such as the Internet of Things (IoT), machine learning (ML), and artificial intelligence (AI), have been used, portable, cost-effective, and energy-efficient solutions suitable for resource-constrained environments such as edge applications in agriculture are needed. This study presents the development of a portable smart IoT device that integrates a lightweight convolutional neural network (CNN), called Tiny-LiteNet, optimized for edge applications with built-in support of model explainability. The system consists of a high-definition camera for real-time plant image acquisition, a Raspberry-Pi 5 integrated with the Tiny-LiteNet model for edge processing, and a GSM/GPRS module for cloud communication. The experimental results demonstrated that Tiny-LiteNet achieved up to 98.6% accuracy, 98.4% F1-score, 98.2% Recall, 80 ms inference time, while maintaining a compact model size of 1.2 MB with 1.48 million parameters, outperforming traditional CNN architectures such as VGGNet-16, Inception, ResNet50, DenseNet121, MobileNetv2, and EfficientNetB0 in terms of efficiency and suitability for edge computing. Additionally, the low power consumption and user-friendly design of this smart device make it a practical tool for farmers, enabling real-time pest and disease detection, promoting sustainable agriculture, and enhancing food security.

1 June 2023 in European Journal of Technology
Verified
Journal Article
Open access
PDF file
JNJean Pierre Nyakuri
Jean Pierre Nyakuri
IVIshimwe Viviane Ishimwe Viviane
Ishimwe Viviane Ishimwe Viviane
ULUwimana Lambert
Uwimana Lambert
IVIshimwe Viviane
Ishimwe Viviane
ISIrakora Shadrack
Irakora Shadrack
HTHabiyaremye Theogene
Habiyaremye Theogene
Purpose: Unpredictable and rapid change in weather patterns has great impact on agricultural activities, especially for precision agriculture that results in worsened water resources availability, decreased soil fertility, use of pesticide as well as decreased yield productivity. In attempt to alleviate these challenges, this study aims at developing a real-time weather and farm field data driven Artificial Intelligence (AI) and Internet of Things (IoT) system that analyze, manage and schedule irrigation and fertigation as well as enabling farmers to interact with their farms via Smart phone or PCs to optimize energy and water resources. Methodology: The system employs weather condition monitoring sensors such as atmospheric pressure, air temperature, air humidity and wind speed for collecting real-time farm field data and uses Fuzzy Inference System (FIS) to predict rainfall rate at farm area for 24 hours period. The system also gathers field data such as soil moisture content and soil nutrient content and uses the Machine Learning (ML) algorithms to predict the time for irrigation and fertigation. By combining weather and farm field data, the system schedules the irrigation and fertigation activity. In addition, the mobile application is developed for the farmers to interact, control and monitor the farming activities and the data is presented to the farmers in both graphical and numerical formats. Findings: The system prototype deployed and tested in the two hectors Maize farm proved that 55% of water, 51% of energy and 20% of fertilizer were saved as well as increases in 20% of Maize yield production compared to previous season. Recommendations: Since the current irrigation and fertigation practices are based on predetermined time of the day and threshold values for automatic irrigation, this solution introduced the new concept of real-time and short-term weather forecasting that enables farmers to balance the irrigation period and weather pattern for water and fertilizer resources optimization.

30 April 2023 in Journal of Appropriate Technology
Verified
Journal Article
Open access
PDF file
BSBikorimana Sefu
Bikorimana Sefu
SVSefu Venuste
Sefu Venuste
MDMirembe Jean D’aMour
Mirembe Jean D’aMour
KDKanyarwanda Daniel
Kanyarwanda Daniel
JNJean Pierre Nyakuri
Jean Pierre Nyakuri
HFHarerimana Felix
Harerimana Felix
The COVID-19 preventive measurements restrict farm-workers from travel to their farms, social distancing and lockdown to prevent them from getting infected. Consequently, farming and irrigation activities are dramatically reduced due to shortage of farm-workers and reduction of crops production. To find solutions, various technologies have been adopted to remotely connect farmers with their farm-fields from their homes and perform the same work as they are in the farm. An Internet of Things (IoT) approach, modern sensor technologies, and smart irrigation equipment are coupled to allow the collection of the field data for automatic irrigation of the field. This paper presents the IoT system based on Fuzzy logic controller that assists farmers to receive and monitor necessary irrigation data from the farm field through their smart phones and PCs. The Wireless Sensor Networks (WSNs) are deployed in the field to measure the water content in the soil and water used for plants by measuring the soil moisture dynamics throughout the entire duration of the crop growing season in the Maize crop farm. The Fuzzy logic controller was used for data analytics and intelligent decision making as well as Fuzzy logic toolbox in MATLAB to simulate irrigation scheduling process. The system saves 50% of water and energy consumption for irrigation, 80% reduction of farm-workers and increase in 20% of crop production.

27 February 2023 in American Journal of Computing and Engineering
Verified
Journal Article
Open access
PDF file
JNJean Pierre Nyakuri
Jean Pierre Nyakuri
FHFelix Harerimana
Felix Harerimana
FKFrancois Karanguza
Francois Karanguza
NGNiyomufasha Ghadi
Niyomufasha Ghadi
JMJean D’aMour Mirembe
Jean D’aMour Mirembe
JBJudith Bizimana
Judith Bizimana
Purpose: Since the breakout of COVID-19 pandemic, various preventive measures have been put in place by WHO to prevent the spread of this disease. However, some people are unaware or less likely to follow rules regarding hygiene, physical distancing, properly wearing of face mask and body temperature measurement. One of the best solutions to this challenge is the introduction of the internet of things (IoT) technology to assist in implementation of the preventive measures. This paper presents an IoT-enabled solution that uses Fuzzy logic controller to assess the risks of being COVID-19 infected and monitor environment conditions in the public hall to limit the spread of the coronavirus. Methodology: The proposed model employed sensors to measure in real-time the body temperature, hand sanitization, wearing of face mask, room ventilation and IP camera controlled by Fuzzy logic controller for decision making. In addition, it uses raspberry-pi for processing and data transmission to the cloud, liquid crystal display (LCD) for displaying data and web application was developed for user interface. The resulting sensor measurements were simulated using MATLAB software and the system made automatic decisions. Findings: A prototype was implemented effectively and the results obtained from the system were fast, accurate, efficient and cost effective when compared to other commercially available systems. Unique Contribution to Practice: The actual practice for implementing the preventive measures require the presence of the health care personnel (HCP) which is time consuming and risky for HCP. Therefore, this system works autonomously and effectively in monitoring and controlling the implementation of the COVID-19 preventive measures in the public hall.

26 May 2026 in Scientific Reports
Verified
Journal Article
Open access
JNJean Pierre Nyakuri
Jean Pierre Nyakuri
CNCelestin Nkundineza
Celestin Nkundineza
OGOmar Gatera
Omar Gatera
KNKizito Nkurikiyeyezu
Kizito Nkurikiyeyezu
GMGervais Mwitende
Gervais Mwitende
Invasive pests pose a significant threat to agricultural production, particularly maize crops, with severe implications for food security. Timely detection of pest development stages and accurate prediction of outbreak risks are essential for effective management. This study introduces a hybrid model combining Explainable Artificial Intelligence (XAI), a lightweight Convolutional Neural Network (CNN), and Fuzzy Logic (FL) for Fall Armyworm (FAW) detection and weather-based risk prediction. The model uses Tiny-MobileNet-SE for image classification, Grad-CAM for interpretability, and FL inference based on environmental parameters. Tiny-MobileNet-SE achieved 98.6% accuracy, 98.5% F1-score, 98.6% recall, a compact size of 0.72 MB, and 80 ms latency on Raspberry Pi 5, outperforming state-of-the-art lightweight models including EfficientNetB0, SqueezeNet, MobileNet-v2, MobileNet-v3, and ShuffleNet. The proposed system delivers a power-efficient, scalable, and user-friendly solution for precision agriculture, providing actionable insights for pest management and supporting sustainable crop protection strategies.