Browsing by Author "Fue, Kadeghe G."

Now showing 1 - 6 of 6

Deep learning based Real-time GPU-accelerated tracking and counting of cotton bolls under field conditions using a moving camera
(2018 ASABE Annual International Meeting, 2018-08) Fue, Kadeghe G.; Porter, Wesley; Rains, Glen
Robotic harvesting involves navigation and environmental perception as first operations before harvesting of the bolls can commence. Navigation is the distance required for a harvester’s arm to reach the cotton boll while perception is the position of the boll relative to surrounding environment. These two operations give a 3D position of the cotton boll for picking and can only be achieved by detection and tracking of the cotton bolls in real-time. It means detection, tracking and counting of cotton bolls using a moving camera allows the robotic machine to harvest easily. GPU-accelerated deep neural networks were used to train the convolution networks for detection of cotton bolls. It was achieved by using pretrained tiny yolo weights and DarkFlow, a framework which translates YOLOv2 darknet neural networks to TensorFlow. A method to connect tracklets using vectors that are predicted using Lucas-Kanade algorithm and optimized using robust L-estimators and homography transformation is proposed. The system was tested in defoliated cotton plants during the spring of 2018. Using three video treatments, the counting performance accuracy was around 93% with standard deviation 6%. The system average processing speed was 21 fps in desktop computer and 3.9 fps in embedded system. Detection of the system achieved an accuracy and sensitivity of 93% while precision was 99.9% and F1 score was 1. The Tukey’s test showed that the system accuracy and sensitivity was the same when the plants were rearranged. This performance is crucial for real-time robot decisions that also measure yield while harvesting.
Experimenting open agricultural extension service in Tanzania: A case of Kilosa Open Data Initiative (KODI)
(Journal of Scientific and Engineering Research, 2016) Sanga, Camilius A.; Masamaki, Joseph Phillipo; Fue, Kadeghe G.; Mlozi, Malongo R.; Tumbo, Siza D.
This paper presents results from the application of Open Data System to improve coverage of agricultural extension services using web-based and mobile-based farmers‘ advisory information Ushaurikilimo in Kilosa District. The research adopted a participatory action research method to develop the interventions. The findings from this study show that farmers and other actors get timely, relevant and personalized advisory services. The user interface of the Open System hosting Open Data is in Swahili language, a language widely spoken in the study area, which enhanced adoption of the system. The Open System did not require farmers and other actors to pay for the services, which motivated to attract farmers and actors to adopt the system. In order to lower the cost of implementing the project, agricultural extension officers in study villages were used to receive questions from farmers and provided answers, and sent difficulty questions to experts from Sokoine University of Agriculture to answer via their mobile phones.
Modeling the electrical conductivity relationship between saturated paste extract and 1:2.5 dilution in different soil textural classes
(Department of agricultural engineering, 2024-12) Omar, Moh’d M.; Shitindi, Mawazo J.; Massawe, Boniface H. J.; Pedersen, Ole; Meliyo, Joel L.; Fue, Kadeghe G.
Regression models were developed to estimate the electrical conductivity of saturated paste extract (ECe) from the electrical conductivity of soil-water ratio (EC1:2.5) for different soil textural classes. ECe is a crucial parameter used to indicate the presence, type, and distribution of salinity in soils. However, determining ECe is demanding, time-consuming, requires considerable skill to accurately identify the correct soil saturation point, and is not routinely performed by soil testing laboratories. Many laboratories, instead, commonly measure the electrical conductivity of soil-water extracts at various dilutions, such as EC1:1, EC1:2.5, or EC1:5. In this study, 706 soil samples were collected from depths of 0 - 30 cm across three rice irrigation schemes to determine EC1:2.5, with 50% analyzed for ECe. ECe values were grouped based on soil textural classes. The results showed a strong linear relationship between EC1:2.5 and ECe values, with a high coefﬁcient of determination (R² > 0.95). The Root Mean Square Error values were low (1.4 < RMSE), and the Mean Absolute Error values were similarly low (0.85 < MAE). Therefore, the regression models developed provide a practical means of estimating ECe for various soil textural classes, thereby enhancing soil salinity assessment and management strategies
A simple convolutional neural network architecture for monitoring Tuta absoluta (Gelechiidae) infestation in tomato plants.
(Sokoine University of Agriculture, 2021-05) Mourice, Sixbert K.; Mlebus, Festo Joseph; Fue, Kadeghe G.
Tomato leaf miner (Tuta absoluta (Gelechiidae)) is a serious tomato insect pest in Tanzania, and its management or control still posess significant challenge. If left uncontrolled, the loss inflicted by the miner can be as high as 100%. Successful management of the pest may leverage on an integrated pest management (IPM) approach which, requires high throughput data on damage signs over space and time. This needs, in turn, a robust technique for pest monitoring. This study uses a deep learning technique to detect infestation symptoms of T. absoluta on tomato plants. The technique is rapid, automated and doesn’t require trained or experienced personnel. An experiment was carried out at Sokoine University of Agriculture (SUA), where two sets of tomato plants (cv. Asila F1) were planted in a screen house and in an open field. High-quality images of the tomato leaves were captured from both sets at seven days intervals for 70 days following transplanting. More images were collected from tomato gardens around Morogoro town. Collected images were labeled as being infested or non-infested. A simple convolution neural network (CNN) architecture with four convolution layers, three pooling layers, one flat layer and one dense layer, powered by Keras library and python’s Tensorflow backend, was developed in R-Software. The model accuracy was 90% on training and 82% on test data sets. This study suggests that the model can accurately identify T. absoluta infestation in tomato plants to a considerable extent. An in-depth discussion of the technique is provided in the paper.
The use of participatory approaches in developing ICT-based systems for disseminating agricultural knowledge and information for farmers in developing countries: the case of Tanzania
(The Electronic Journal of Information Systems in Developing Countries, 2017) Barakabitze, Alcardo Alex; Fue, Kadeghe G.; Sanga, Camilius Aloyce
This paper provides an insight on the use of various participatory approaches to develop ICTs to the rural farming communities. The paper shows how collective groups of farmers can be empowered through involvement of different stakeholders in a participatory action research. The paper also discusses how participatory action research will help the farming community in adopting ICT-based solutions for agriculture. This in turn will contribute in solving problems as well as assisting decision making in identifying technological and agricultural needs. In this study, a total of 64 researchers and extension workers and 320 rural farmers were involved. Primary data were collected using a self-administered questionnaire and interviews. Data were analyzed using descriptive statistics tool. The results indicate that many ICT- based solutions for agriculture are not adopted by farmers and other stakeholders in various agricultural value chains because those ICTs were developed without using participatory approaches. Moreover, the results from study indicate that participatory action research approaches such as Participatory Communication (PV), Participatory Video (PV), Participatory Learning and Action Research (PLAR), Farmer Participatory Research (FPR), Informal-Mobile Learning Research (IMLR) have a significant impact on the effective use of ICTs in rural farming community and the agricultural domain in general. Among of these participatory approaches, the IMLR and PLAR have shown to be more effective because of availability and interactive mobile learning environments that excite interests, commitments and encourages participatory attitudes among famers and researchers. This study provides an evident that ICTs has a dominant position to alleviate rural poverty and strengthen the agriculture productivity through participatory approaches. We recommend that a strong commitment of all actors in agriculture value chain is needed so that they can collaborate to identify the problem, analysis and design possible solutions and finally, implement and later on use those developed ICTs to increase agriculture productivity.
Web-based examination results release information system for cost effective strategies in academic institutions
(2014) Fue, Kadeghe G.; Mahenge, Michael P.J.; Busagala, Lazaro S.P.
In past eras, a variety of results release approaches and systems have been proposed. And as technology keeps improving every day and night, numerous of them have been transformed from traditional paper to computerized and web-based format in recent years. Higher learning institutions with large number of students like Sokoine university of Agriculture face challenges in handling and releasing examination results leading to high cost and delay accessibility by students. Sokoine University of Agriculture and many other universities in East Africa particularly Tanzania have been using the computerized format of processing exams using Microsoft Excel which in turn leads to many complications and mostly notably excel formulas which are unknown to most of them. This paper proposes the web-based examination results release information system for cost effective strategies in East African academic institutions. It is urgent to come up with a solution that will cater short term demands of institutions like SUA and many others. Though, the proposed system involves only results releasing module but it’s urgent for the institutions that have a significant financial constraints. The proposed system is able to display results for each student and is able to accept the results from the examination officers. The system is intended to make sure that each student gets his/her results on-line without any hassle. Since, the system is proposed for financial constraints institution; hence it is not suitable for long term solution. Instead, this is recommended to be used for temporary services only.