BA (Hons) Music: Production, Performance and Enterprise — First Class Honours

Final Major Project (73%): Early version of DedAI — AI-driven music composition system using real-time EEG signal processing.
Research Project (74%): Quasi-experimental EEG study on emotional processing of music in musicians vs non-musicians (supervisor: Dr Jasmine Taylor).
Relevant modules: Advanced Audio Production, Music Production Studio and Live, Recording Techniques, Creative Identities and Making Digital Content, The Freelance Music Professional.
Self-directed study: Digital Signal Processing, Computational Neuroscience, Machine Learning, Neural Resonance Theory.

DedAI-Neurodynamics — Founder & Lead Researcher

Developed a computational framework bridging Neural Resonance Theory and deep learning to build AI systems that perceive temporal structure through oscillatory dynamics. The project implements biophysically-grounded models for rhythm perception and translates EEG-derived emotional states into generative music synthesis.

• Implemented ASHLE (Adaptive Synchronisation with Hebbian Learning and Elasticity) and GrFNN (Gradient Frequency Neural Network) models for oscillatory entrainment and beat perception
• Trained a Temporal Convolutional Network (TCN) surrogate with physics-informed loss achieving 94.37% Phase-Locking Value retention, enabling real-time inference while preserving neural entrainment dynamics
• Built a closed-loop Brain-Computer Music Interface (BCMI) using Emotiv EPOC X (14-channel EEG), mapping cognitive biomarkers to oscillator parameters in real-time (<50ms latency)
• Developed PyNRT — an open-source Python toolkit for simulating Hopf oscillators, gradient frequency neural networks, and adaptive oscillator models
• Extended framework to cross-modal visual perception, demonstrating video-to-audio entrainment where motion energy drives ASHLE rhythm synthesis (r=0.91 correlation for periodic stimuli)
• Created digital twin simulations of EEG hardware for algorithm prototyping without physical sensors

EEG Study: Musicians vs Non-Musicians — Primary Investigator

Conducted a mixed-methods quasi-experimental study examining differential emotional processing of music between musicians and non-musicians using EEG. Grounded in Meyer's Expectancy Theory and Juslin & Västfjäll's BRECVEMA model of music-induced emotions.

• Collected and analysed 14-channel EEG data from 6 participants using Emotiv EPOC X in naturalistic listening conditions; processed with MNE-Python, ICA artifact rejection, and FFT band power analysis
• Found significant beta wave (12–30 Hz) differences in frontal regions (AF3, AF4, F3, F4, F7, F8) indicating heightened cognitive engagement in musicians during musical expectation violation (p=0.0158)
• Created visualisations including topographical brain maps, radar graphs, and hierarchical edge bundling diagrams using PyVis and Matplotlib
• Consulted with Dr Marcus Pearce (QMUL) on methodology and theoretical framework; discussion informed integration of schematic and dynamic expectation mechanisms
• Obtained full ethics approval (ETH2324-0744) from the University of Westminster Research Ethics Committee

Pinnacle Crew — Freelance AV Crew / Technical Assistant

Assisted with AV setup, signal routing, and system configuration for live events at London venues. Worked under tight turnaround times across multiple cross-functional crews, gaining practical exposure to live sound, staging, and event production workflows.

Macoral Services — AI & Web Development Consultant

Developed and deployed a custom AI chatbot and quote calculator, achieving approximately 30% reduction in client response time. Translated complex technical requirements into accessible business tools for non-technical stakeholders.