Evariste Twahirwa

Dr. Evariste Twahirwa

A.Lecturer University of Rwanda-College of Science and Technology-Dept of Computer Science
+2
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
24 December 2021 in Sustainability
Verified
Journal Article
Open access
PDF file
ETEvariste Twahirwa
Evariste Twahirwa
JRJames Rwigema
James Rwigema
RDRaja Datta
Raja Datta
A novel computing paradigm, called the Internet of things emerged a few years ago. IoT is materialized by connecting both real and digital worlds together. The deployment of IoT in vehicular networks has introduced a new vehicular communication technology-themed vehicular internet of things (V-IoT). With the introduction of miniaturized sensors and actuators, V-IoT has demonstrated the ability to improve the level of urban transport systems through the development and deployment of low-cost but powerful technologies which seamlessly upgrade the level of smart transportation in urban environments. In this research article, we have presented the features of V-IoT that encompass both the benefits and potential challenges of the technology. Low-cost IoT prototypes have been built and tested for numerous functions in vehicular environments. The monitored parameters include air, road conditions such as traffics flow sizes, air quality, weather parameters, and signal status in terms of Received signal strength indicator, and Signal noise ratio for both road and intra-vehicular environments. Devices are implemented at every IoT architectural layer and tested on a web-based IoT front-end application using different protocols like LoRaWAN. Two LoRa sensors have been deployed in the public bus to monitor some of the mentioned parameters on a real-time basis and historical data could be retrieved through the developed web-based dashboard. Simplistic algorithms are implemented for both real-time and historical data demonstration.

10 May 2021
Verified
Conference Paper
Closed access
ETEvariste Twahirwa
Evariste Twahirwa
Kambombo MtongaKambombo Mtonga
Kambombo Mtonga
NDNgabo Desire
Ngabo Desire
SKSanthi Kumaran
Santhi Kumaran
Keeping key air pollutants below the World Health Organization recommended limits is important for combating the ever-increasing deaths resulting from the associated health problems. This is especially true for indoor environments where poor ventilation can magnify the effects of air pollution. Having Knowledge about the level of pollutants in the air would serve as a stepping stone to take mitigation measures. In this work, a domesticated air pollution monitoring system over the LoRa enabled Internet of Things framework is proposed. Two sensors for CO 2 and PM 2.5 that are important for air quality monitoring with compensated weather monitoring capabilities were deployed in the cafeteria kitchen and laboratory room of the University of Rwanda, College of Science and Technology. The sensed parameter readings are then sent to the cloud via LoRaWAN protocol supported gateway that interfaces the sensors and the cloud part of the network. The end users can query the system and access the data together with the analytic information via the developed Web-based user interface dashboard. An analysis of the data over a period of eleven (11) months is carried out and results show high parts per million of CO 2 of over 800 ppm and PM 2 . 5 concentration of over 100 ppm in the kitchen environment. Whilst a concentration of 500 ppm for CO 2 and zero ppm for PM 2 . 5 were observed in the laboratory room. Baseline algorithms that facilitate setting of triggers for each sensing node and pushing of notifications for when a measured parameter exceeds a certain threshold value are proposed and implemented.

16 July 2022 in Tanzania Journal of Engineering and Technology
Verified
Journal Article
Closed access
PDF file
WSWaheed Sanya
Waheed Sanya
GBGaurav Bajpai
Gaurav Bajpai
Omar Haji KomboOmar Haji Kombo
Omar Haji Kombo
ETEvariste Twahirwa
Evariste Twahirwa
Rising electricity bills as a result of climate variability and new home electrical and electronic appliances are becoming a major source of concern for most end users. Consumers are typically unaware of their household electricity consumption patterns and the costs associated with them, making proper planning and budgeting difficult. Monitoring and controlling energy consumption on appliances can reduce energy costs for end-users. The Internet of Things (IoT) has the potential to provide remote monitoring and control of devices via automated monitoring and control. In this study, we propose an IoT-enabled system for monitoring and controlling energy consumption in homes to save money and make electricity more affordable to low-income people. Autonomous sensor nodes attached to power outlets collect and route power consumption data to the GSM-enabled gateway. Data aggregation is performed by the gateway for data received from all end-nodes within its coverage area. The gateway sends the data to the cloud, where real-time data analytics is performed. We also developed an algorithm that enables users to not only understand their usage patterns but also remotely control their appliances at any time. Mobile phones are used to remotely turn on and off household appliances via a machine-to-machine interface, as well as to provide real-time visualization of household energy consumption patterns.

ETEvariste Twahirwa
Evariste Twahirwa
WKWillie Kasakula
Willie Kasakula
JRJames Rwigema
James Rwigema
RDRaja Datta
Raja Datta
Vehicular Ad Hoc Network (VANET) is a subclass of Mobile Ad Hoc Network that mainly consists of moving and/or stationary vehicles, connected through wireless protocols such as IEEE 802.11p and wireless access in vehicular environments (WAVE). With the evolution of the Internet of Things (IoT), ordinary VANET has turned to the Internet of Vehicles (IoV), with additional social aspects, a novel extension themed SIoV has become common in urban areas. However vehicular wireless communication paradigms exhibit short radio communication. This problem has always been approached by supplementing moving vehicles with stationary Road Side Infrastructures, commonly known as roadside units (RSUs). The penetration of such RSUs on the global market is very low; furthermore, their procurement, deployment, and maintenance costs are prohibitively very high. All mentioned challenges have discouraged the widespread deployment of roadside infrastructure especially within large urban scenarios. With this research, we leverage on-street parked vehicles to allow them to exist as temporal gateways in the case study area. A novel modeling technique is introduced to enable a specific Percentage of parked vehicles to take up the role of roadside gateways for a certain percentage of their parking time. A mobile application is implemented that manages parking duration of the vehicle, based on the arrival, and departure time frames. Two more existing strategies were discussed (road-intersection RSUs deployment approach and Inter-vehicle scheme) to validate our proposed method through comparative studies. To evaluate the network performance evaluation, we compare two performance metrics, that is, Packets success delivery rate, and overall packets throughput under numerous vehicle densities. Using parked vehicles as temporal roadside gateways has demonstrated better results in comparison to intersection based RSUs deployment approach, and free vehicle to vehicle communication approach.

7 August 2025 in IoT
Verified
Journal Article
Open access
PDF file
SOSamson Otieno Ooko
Samson Otieno Ooko
ENEmmanuel Ndashimye
Emmanuel Ndashimye
ETEvariste Twahirwa
Evariste Twahirwa
MBMoise Busogi
Moise Busogi
The activities of birds present increasing challenges in agriculture, aviation, and environmental conservation. This has led to economic losses, safety risks, and ecological imbalances. Attempts have been made to address the problem, with traditional deterrent methods proving to be labour-intensive, environmentally unfriendly, and ineffective over time. Advances in artificial intelligence (AI) and the Internet of Things (IoT) present opportunities for enabling automated real-time bird detection and repellence. This study reviews recent developments (2020–2025) in AI-driven bird detection and repellence systems, emphasising the integration of image, audio, and multi-sensor data in IoT and edge-based environments. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was used, with 267 studies initially identified and screened from key scientific databases. A total of 154 studies met the inclusion criteria and were analysed. The findings show the increasing use of convolutional neural networks (CNNs), YOLO variants, and MobileNet in visual detection, and the growing use of lightweight audio-based models such as BirdNET, MFCC-based CNNs, and TinyML frameworks for microcontroller deployment. Multi-sensor fusion is proposed to improve detection accuracy in diverse environments. Repellence strategies include sound-based deterrents, visual deterrents, predator-mimicking visuals, and adaptive AI-integrated systems. Deployment success depends on edge compatibility, power efficiency, and dataset quality. The limitations of current studies include species-specific detection challenges, data scarcity, environmental changes, and energy constraints. Future research should focus on tiny and lightweight AI models, standardised multi-modal datasets, and intelligent, behaviour-aware deterrence mechanisms suitable for precision agriculture and ecological monitoring.

24 November 2021 in Sustainability
Verified
Journal Article
Open access
PDF file
ETEvariste Twahirwa
Evariste Twahirwa
Kambombo MtongaKambombo Mtonga
Kambombo Mtonga
KJKayalvizhi Jayavel
Kayalvizhi Jayavel
WKWillie Kasakula
Willie Kasakula
Peace BamurigirePeace Bamurigire
Peace Bamurigire
The impact of COVID-19 has been felt across all sectors, from transportation, education, and public works to the daily operations of businesses like selling, retailing, and so forth. The business sector is among those badly affected, especially micro, small, and medium enterprises. The understanding of ground prevailing conditions is key in driving informed policies that would have meaningful impact on society with regard to overcoming the effects of the virus. Hence, this work is an attempt to report the real ground statistics and necessity of technological support with the goal of submitting a report of recommended policies to the concerned authorities. In this direction, this work presents the outcome of a survey conducted to assess the impact of COVID-19 on operations of micro, small, and medium enterprises and also to find out the interventions put in place around business environments so as to enforce adherence to COVID-19 health safety measures. The survey was part of a study to develop automated IoT-powered technological solutions that would help to enforce proper mask wearing in indoor environments and also observance of social distance requirements within business premises. A customized questionnaire was designed to capture data on various aspects central to the focus of the study. The study was carried out in the month of May 2021, in the Huye district of Rwanda. According to the survey findings, the major challenges faced by businesses due to COVID-19 include failure by clients to settle bills, reduced ability to expand investment, difficulty in accessing inputs domestically, lower domestic sales to consumers, and lower domestic sales to businesses. The results also reveal some positive points that most businesses were found to have: hand washing points, hand sanitizer dispensers, and mechanisms to enforce social distance between customer and customer and also customer and front desk worker. In a nutshell, this work is unique in terms of (1) the customized questionnaire about Rwanda’s needs, (2) field visit-based data collection for accurate data, and (3) including an assessment of the importance of technological intervention for better handling of public safety, especially in the MSME business sector.