Date of Thesis

Spring 2026

Description

This thesis investigates deep learning approaches for voltammetric analysis of brewed coffee using a low-cost electrochemical system and screen-printed electrodes (SPEs). Traditional analytical methods, such as high-performance liquid chromatography (HPLC) and gas chromatography-mass spectrometry (GC-MS), provide precise quantification of key compounds but require expensive instrumentation and specialized expertise, limiting accessibility. While SPEs offer a more accessible alternative, they yielded poor results with traditional processing; however, when combined with a neural network, the system proved more effective. In experiments with 132 coffee samples, mean errors for caffeine, CGA, and TDS predictions were 52.98 ppm, 70.48 ppm, and 0.08 %, respectively. These findings highlight the potential of low-cost electrochemical methods while emphasizing the need for improved sensor technology and data processing to enhance sensitivity and reduce variability. Finally, this thesis explores predicting subjective cupping attributes and flavor descriptors, showing limited performance due to small, narrow-range sensory datasets and motivating larger, standardized data collection for future systems that approximate human tasting.

Keywords

Voltammetry, Deep learning, Electrochemistry, Coffee quality assessment, Caffeine quantification, Chlorogenic acids quantification

Access Type

Honors Thesis

Degree Type

Bachelor of Science in Computer Science and Engineering

Major

Computer Science & Engineering

Minor, Emphasis, or Concentration

Mathematics

First Advisor

Alan Marchiori

Second Advisor

Katsuyuki Wakabayashi

Third Advisor

Brian King

Download

Share

COinS