Robust chemical analysis with graphene chemosensors and machine learning

Area of Science:

• Materials Science
• Analytical Chemistry
• Computer Science

Background:

• Ion-sensitive field-effect transistors (ISFETs) are crucial for converting chemical variations into electrical signals.
• ISFETs find applications in environmental monitoring, healthcare, and industrial control.
• Recent ISFET advancements include functionalized arrays and data analytics.

Purpose of the Study:

• To demonstrate the integration of machine learning with ISFET sensor data for enhanced classification and quantification.
• To explore how machine learning can provide deeper insights into ISFET functionality.
• To address practical challenges like sensor variability for commercial ISFET adoption.

Main Methods:

• Utilizing extensive datasets generated by non-functionalized graphene-based ISFET arrays.
• Training artificial neural networks with ISFET data.
• Applying predictive models for classification and quantification tasks.

Main Results:

• Machine learning models accurately discern food fraud, spoilage, and safety concerns using ISFET data.
• The integration mitigates cycle-to-cycle, sensor-to-sensor, and chip-to-chip variations.
• Developed predictive models offer insights beyond human expertise.

Conclusions:

• The fusion of graphene-based ISFETs and machine learning offers a powerful platform for detecting chemical and environmental changes.
• This approach enables swift, data-driven insights for a wide range of applications.
• The technology holds potential to revolutionize sensing by overcoming current limitations.