# A novel approach for classifying monoamine neurotransmitters by applying machine learning on UV plasmonic-engineered auto fluorescence time decay series (AFTDS)

## TL;DR

This paper presents a new method combining plasmonic nanomaterials and machine learning to detect and classify neurotransmitters with high accuracy.

## Contribution

A novel hybrid system using aluminum concave nanocubes and LSTM networks for probe-free neurotransmitter classification.

## Key findings

- Aluminum concave nanocubes enhance fluorescence signals up to 12-fold for dopamine compared to silicon substrates.
- LSTM networks outperform KNN and Random Forest in classifying neurotransmitters with over 89% accuracy.
- The method enables probe-free and label-free detection of dopamine, norepinephrine, and DOPAC with high specificity.

## Abstract

This study introduces a hybrid approach integrating advanced plasmonic nanomaterials and machine learning (ML) for high-precision biomolecule detection. We leverage aluminum concave nanocubes (AlCNCs) as an innovative plasmonic substrate to enhance the native fluorescence of neurotransmitters, including dopamine (DA), norepinephrine (NE), and 3,4-dihydroxyphenylacetic acid (DOPAC). AlCNCs amplify weak fluorescence signals, enabling probe-free, label-free detection and differentiation of these molecules with great sensitivity and specificity. To further improve classification accuracy, we employ ML algorithms, with Long Short-Term Memory (LSTM) networks playing a central role in analyzing time-dependent fluorescence data. Comparative evaluations with k-nearest neighbors (KNN) and Random Forest (RF) demonstrate the superior performance of LSTM in distinguishing neurotransmitters. The results reveal that AlCNC substrates provide up to a 12-fold enhancement in fluorescence intensity for DA, 9-fold for NE, and 7-fold for DOPAC compared to silicon substrates. At the same time, ML algorithms achieve classification accuracy exceeding 89%. This interdisciplinary methodology bridges the gap between nanotechnology and ML, showcasing the synergistic potential of AlCNC-enhanced native fluorescence and ML in biosensing. The framework paves the way for probe-free, label-free biomolecule profiling, offering transformative implications for biomedical diagnostics and neuroscience research.

This study introduces a hybrid approach integrating advanced plasmonic nanomaterials and machine learning (ML) for high-precision biomolecule detection.