This study uses the Food and Agricultural Organization (FAO) Penman-Monteith equation to develop a crop water algorithm needed to automate the supply of specific amount of water to crops, depending on their different crop water requirements. This was done to deviate from the practice of supplying the same amount of water to different crops during irrigation practices which could lead to over-irrigation or under-irrigation resulting in pest infestation and eventually low yield. The crop water requirement for cocoyam, spinach and tomatoes were estimated using data from FAO. A microcontroller-based smart irrigation device incorporated with real-time clock was developed to supply the right amount of water to crops at the right time and duration daily. The implementation was done using a laboratory-scale irrigation test bed and experimental results reveal the effectiveness of the developed system in the automation of crop-specific irrigation systems and in line with their Crop Water Requirement (CWR). Possible applications include greenhouses where researchers have to apply a specific amount of water to crops for experiments; horticultural gardens and nurseries to mention a few.

In this paper, an Automatic Load Shedding module is developed for teaching and research. The module uses an Arduino microcontroller combined with a switching circuit to implement a load shedding plan in four settlements of a laboratory-scale urban settlement. The switching plan, in line with the power Distribution Company (DISCO) approval, is done to ensure optimal usage of the available 7.5MW as against the 10MW power demand. The developed module is useful as a teaching aid for illustrating power system automation among undergraduates..

The challenges faced by managers of transportation systems in developing nations such as Nigeria are numerous. These include driver scheduling, which, in many cases, is still being done manually; diversion of vehicles to unauthorized routes by drivers for selfish reasons results in illegal use of fuel meant for official duties, causing the organization lose considerable revenue. In its drive to reduce its carbon footprint, Elizade University, Nigeria, is embarking on the development and use of electric vehicles (EV) as a means of transportation within the university campus. This research is geared towards supporting this initiative by developing an EV tracking system that combines tracking of EV drivers with vehicle position and battery power (energy) tracking in order to mitigate the challenges outlined above. Personnel tracking was achieved using an RFID-enabled staff identity card that authenticates authorized drivers before activating the vehicle ignition system, position tracking was achieved using a geographical positioning system (GPS), and current and voltage sensors were used for tracking of electric vehicle power. Tests revealed that the EV system administrator operated through a personal computer was able to track the EV driver, position and power through a web interface/Google Maps and e-mail in real time. Whereas previous studies either considered tracking of vehicle position or power without personnel, others tracked personnel with less emphasis on the vehicle position or energy. In this study, we combined different technologies such as RFID, GPS and power sensors to consider EV administration in a holistic manner, thereby providing intervention in an infrastructurally deficient setting.

Farmers in sub-Saharan Africa are plagued with the challenges of climate change, farmers-headers clash, resulting in low production. Greenhouse farming is seen as a way out due to small space required and ability to control microclimate. Tropical Greenhouses are usually very hot in the afternoon resulting in water and heat stress. This work develops an automated system that monitors microclimate in real-time, regulate temperature and provides prediction of future water needs to aid future management. A data acquisition system using Atmega 382 microcontroller and a DHT22 was used for monitoring and control while Raspberry Pi was used for future temperature prediction. At a threshold temperature of 30 ℃, the microcontroller activates a fogging pump to release mist into the greenhouse to cool the heat-stressed leaves thus enhancing photosynthesis. Irrigation is also activated using drip system. Raspberry Pi combined with DHT22 is used to collect temperature and humidity measurement which were used to train a machine learning algorithm and stored Google sheets in the cloud. The experimental result reveals the ability of the system to perform greenhouse automation, monitoring, and control of fogging and irrigation remotely as well as temperature prediction. Machine learning models: linear regression (LR), support vector regression (SVR) and random forest regression (RFR) were trained with acquired data and the results were compared. The results revealed accuracy (RFR: 98.43%, SVR: 98.54%, LR: 98.57%), and MAE (RFR: 0.47, SVR: 0.44, LR: 0.43). The developed system will enhance greenhouse agriculture and boost food production, especially in the tropics.

The main challenge of the well-celebrated Levenberg-Marquardt algorithm (LMA) is the selection of the searching direction and adaptation parameters. Secondly, the implementation of the LMA for online model identification has faced challenges as it is a batch optimization. As a third challenge, the solution of the Levenberg-Marquardt based on the full-Newton nonlinear optimization (FNNO) for online applications have been limited due to its unguaranteed positive definiteness. This paper presents two versions of the modified Levenberg-Marquardt algorithm (MLMA) for neural network model identification and adaptive predictive control for the online dynamic model identification and adaptive control of a self-balancing two-wheel LEGO Mindstorms NXTway-GS robot. The first version is the online-window-approach of the modified Levenberg-Marquardt algorithm (OWA-MLMA) based on approximate Guass-Newton algorithm (AGNA) for training neural network model predictor. The second version is a neural network-based adaptive predictive control (APC) algorithm based on the full-Newton nonlinear optimization of the modified Levenberg-Marquardt algorithm (FNNO-MLMA) for online adaptive control. A NNARMAX model predictor for the NXT robot is first trained and validated using the OWA-MLMA based on AGNA. The validated NNRAMAX model is then used for the design of the NN-APC based on FNNO-MLMA. Finally, the model identification based on OWA-MLMA and APC based on FNNO-MLMA schemes are simulated in closed-loop for online NNARMAX model identification and adaptive predictive control of the NXT robot. The comparison of the proposed OWA-MLMA based on AGNA shows superior performance over the recursive incremental back-propagation algorithm (INCBPA) while the proposed NN-APC based on FNNO-MLMA shows excellent control and good tracking performances over a discrete-time fixed-parameter proportional-integral-derivative (PID) controller for the NXT robot control. The simulation results show that the developed OWA-MLMA based on AGNA and the APC based on FNNO-MLMA can be adapted for the online dynamic modeling, automation, control and robotics applications.