Abstract:
Livestock keeping is considered one of the main sources of both domestic and commercial
products which plays a crucial role in the household and national economies in the respective
country of Rwanda. The lack of equipment to monitor the quality of the best environment for
animals makes animal caregivers continue to use local methods in their livestock-keeping
activities. This leads to an increase in outbreaks of diseases in animals and makes its products
decrease its quality in the market. With the current improvement in the development of the Internet
of Things in the agricultural sector, the Internet of Thing Animal Healthcare (IoTAH) using the
spread of computing is considered a fundamental approach through sensing and actuating
technologies in assessing animal health. IoT devices in different forms such as wearable devices,
sensors deployed units, and Unmanned Aircraft Vehicle (UAV) moving devices have been used
to track the stimuli of husbandry activities, thus present a gap in precision to manage health
assessment parameters of the quality of Napier leaves for animal food.
Internet of things (IoT) nowadays is based on the smart farming system as a solution for monitoring
animals. This involves IoT-based technologies to enable farmers to control animals based on such
as movement control, weather detection, disease detection, and other parameters of treating those
animals such as the safety of clean water.
Within the previous research, the use of sensors in animal investments has not sufficiently provided
the optimized solution for better food selection for animals to be improved. Therefore, there is still
a need to improve the existing methods of examining the quality of leaves that can give animals
vii
better health. which is an important need, and the system could be able to help collect data to
support future studies processing and optimize decision-making.
In this research work, we introduce a Quality-Leaf-IoT Assessment System (QLIAS) for
examining the quality of leaves for the best animal feed. Firstly, the primary intention of QLIAS
is to evaluate the quality of the leaves, based on the basic colour of Red, Green, and Blue (RGB)
appearance using a colour sensor to assess the solid colour of the leaf. Secondly, QLIAS will track
the weather level in the leaf nest areas to check the possible source of the bad growth of the leaves.
In addition, we will develop a Leave-Pack Quality Accessing Kit (LPQAK) a portable kit mounted
with sensors, the low-cost best tool, and easy to use in assessing the quality leaves. LPQAK will
be the best-fit tool for collecting Napier leaves parameters and storing data in the cloud platform.
Furthermore, the tool is configured with an Machine Learning (ML) model and gives results of an
assessed leave of Full nutritional, moderate, and unhealthy leaves.
