AJASA ABIODUN AFIS

Electronics and Computer Engineering

At the Electronics And Computer Engineering department office

Appointment on Visitation important

Topic: DESIGN AND IMPLEMENTATION OF PRECISION AGRICULTURE SYSTEM USING IoT DEVICES

Description: Introduction:The Precision Agriculture System utilizes IoT devices such as soil moisture sensors, weather stations, and drones to monitor and optimize agricultural operations. This project involves collecting data from the field, analyzing it to make informed decisions regarding irrigation, fertilization, and pest control.Aims/Objectives:Deploy IoT devices for monitoring soil moisture levels, weather conditions, and crop health.Collect and analyze data to optimize irrigation schedules and fertilizer application.Implement predictive algorithms for early detection and prevention of pest infestations.Utilize drones for aerial imaging and surveillance of agricultural fields.Contribution to Knowledge or Society:This project contributes to the advancement of precision agriculture technology, enabling farmers to make data-driven decisions for optimizing crop yields and minimizing resource usage. By leveraging IoT devices and predictive analytics, it facilitates sustainable farming practices that conserve water, reduce chemical inputs, and enhance crop quality.Expected Results:Improved crop yields through optimized irrigation and fertilization practices.Reduced environmental impact with targeted pest management strategies.Enhanced farm productivity and profitability through data-driven decision-making.Potential for scalability and adaptation to different agricultural settings and crops.

#	Certificate	School	Year
1.	Ph.D (ELECTRICAL ENGINEERING)	DEPARTMENT OF CONTROL, ROBOTICS AND MECHATRONICS ENGINEERING, FACULTY OF ELECTRICAL ENGINEERING, UNIVERSITI TEKNOLOGI MALAYSIA, JOHOR, MALAYSIA	2023

Performance Evaluation of Human Motion Tracking and Prediction Using Kalman Filter and Extended Kalman Filter with Hybridized Optimization Techniques

Advancements in biometric identification technology have spurred the development of sophisticated intelligent monitoring systems, enhancing security measures. While past research has made strides in this arena, none have explored Kalman filtering (KF) or Extended Kalman filtering (EKF) for human motion tracking with hybrid optimization techniques. This study introduces new variants of Cuckoo Search Optimization (CSO) - Synchronous-CSO (S-CSO), Asynchronous-CSO (A-SCO), and Synchronous-Asynchronous CSO (SA-CSO) - to enhance particle updating in conjunction with Grey Wolf Optimization (GWO). These hybrid techniques, SCSO-GWO, ACSO-GWO, and SACSO-GWO, are then integrated into KF and EKF methods to optimize error parameters. Additionally, Particle Swarm Optimization (PSO) is employed for error parameter benchmarking, offering automated adjustments for enhanced estimation accuracy and efficiency compared to manual tuning. The study utilizes an IoT platform for human motion tracking data collection, developing ten 2D models including traditional KF, EKF, and optimized variants. Evaluation across ten human datasets with 100 samples each reveals performance differences based on accuracy analysis (Mean Square Error - MSE), computational, and time complexities. MATLAB is employed for sensor dataset analysis using developed algorithms. Results highlight the EKF-SACSO-GWO model's superior accuracy albeit with increased computational and time complexities. Conversely, the KF-PSO model, while less accurate, demonstrates efficiency in computation and time. Despite minor tracking errors, the study successfully achieves its objectives, delivering high-quality results.

AJASA ABIODUN is a Lecturer II at the Department of Electronics and Computer Engineering

AJASA has a Ph.D in ELECTRICAL ENGINEERING from DEPARTMENT OF CONTROL, ROBOTICS AND MECHATRONICS ENGINEERING, FACULTY OF ELECTRICAL ENGINEERING, UNIVERSITI TEKNOLOGI MALAYSIA, JOHOR, MALAYSIA