Bachelor of Science in Microprocessor Technology & Instrumentation
Embedded Systems Engineer | Data Scientist | Innovation Specialist
Transforming complex technical challenges into elegant solutions through advanced instrumentation, machine learning and embedded systems design. Passionate about leveraging cutting-edge technology for real-world impact.
Graduate & ICT Professional
I recently graduated with a Bachelor of Science in Microprocessor Technology and Instrumentation from the University of Nairobi. My academic journey encompassed rigorous training in advanced mathematics (from basic calculus to advanced integral calculus), quantum physics, mechanical physics and comprehensive mathematical modeling.
My final year project focused on machine learning for soil analysis, where I developed predictive models to analyze soil samples and forecast physicochemical properties. This project combined data science, instrumentation and real-world agricultural applications.
With expertise spanning hardware integration, software development, data acquisition systems and machine learning, I bring a unique multidisciplinary perspective to solving complex technical challenges in climate-health systems, IoT and community-driven digital platforms.
E-Commerce Development
University of Nairobi
ML Soil Analysis Project
Hardware & Software
IoT & Embedded Systems
Comprehensive technical education in electronics, instrumentation and computational sciences
BSc. Microprocessor Technology & Instrumentation • 2021 - 2025 | Second Class Honors Upper Division
Title: Rapid Soil Analysis Using Near Infrared Radiation (NIR) Spectroscopy for Sustainable Agriculture Using Machine Learning
Supervisor: Dr. M. I. Kaniu
Department: Physics, University of Nairobi
Year: 2025 | Grade: Second Class Honors Upper Division
Sample Size: 55 soil samples
Wavelength Range: 900-2500 nm
Key Methods: PCA, Random Forest
Best R² Score: 0.8752 (pH prediction)
Project Summary: This research developed an innovative spectroscopic analysis system combining Near-Infrared (NIR) spectroscopy with machine learning for rapid, non-destructive prediction of soil physicochemical properties. The system enables instant soil fertility predictions, eliminating time-consuming laboratory analysis.
Key Innovation: Principal Component Analysis achieved 92.4% spectral variance explanation with just 3 components, identifying critical spectral features at 1417 nm (water absorption), 1938 nm (organic matter) and 2248 nm (clay minerals).
Comprehensive skill set across hardware, software and data science
Innovative solutions combining hardware, software and machine learning
Production-ready e-commerce platform developed for electronics retail client (yuuelectronic.shop). Comprehensive full-stack solution featuring product catalog management, secure payment gateway integration, customer authentication, order processing and inventory management. Built with modern web technologies ensuring scalability, security and optimal user experience across all devices.
Final year capstone project utilizing machine learning algorithms (Random Forest, SVM, Neural Networks) to predict physicochemical properties of soil samples. Implemented comprehensive data preprocessing pipeline, feature selection and model optimization achieving 92% prediction accuracy. Applied to agricultural optimization and environmental monitoring.
Designed and implemented microprocessor-based instrumentation systems for laboratory environments. Integrated multiple sensors (temperature, pressure, humidity) with data acquisition modules, real-time monitoring dashboard and automated calibration routines. Achieved precision measurements with <0.5% error margins.
Developed comprehensive IoT system for real-time environmental data collection and analysis. Implemented wireless sensor networks with LoRa communication, cloud data storage and web-based visualization dashboard. Applied to climate-health early warning systems in rural communities with 99.7% uptime.
Implemented advanced DSP algorithms for signal filtering, noise reduction and feature extraction in instrumentation applications. Developed real-time FFT analysis tools, adaptive filtering systems and automated signal classification using embedded processors. Achieved 40dB noise reduction in industrial environments.
Ready to collaborate on innovative projects
I'm actively seeking opportunities in electronics engineering, embedded systems, data science and IoT development. Whether you need expertise in instrumentation design, machine learning solutions, or embedded system development, I'm here to help bring your vision to life.