Cocoa-Hazelnut Spread Jar Contaminant Detection via Microwave Sensing at 11.0 GHz

2400 instances of scattering parameter measurements for detecting contaminants in packaged cocoa-hazelnut spread jars using microwave sensing at 11.0 GHz. The dataset, created by Luca Urbinati, contains 1200 uncontaminated and 1200 contaminated samples across 11 classes of contaminants like metal, glass, and plastic. Each sample consists of 30 scattering parameters measured at five different microwave frequencies.

Use Cases

• Training binary classifiers to detect the presence of contaminants based on 30 scattering parameters.
• Developing multi-class models to identify specific contaminant types and positions (surface vs. middle).
• Benchmarking microwave sensing techniques for food packaging inspection across different frequency bands.
• Researching the scattering behavior of different materials (metal, glass, plastic) in a food matrix.

Strengths

• Contains 2400 total instances with a balanced set of 1200 contaminated and 1200 uncontaminated samples.
• Includes 11 distinct, physically defined contaminant classes with specific instance counts per class.
• Measurements are taken at five specific microwave frequencies (9.0, 9.5, 10.0, 10.5, 11.0 GHz), though this specific dataset is for 11.0 GHz.

Limitations

• Column-level documentation is absent; field semantics for the 30 scattering parameters must be inferred after download.
• Last update date is unknown; freshness unverified.
• The dataset is one of a series of five; analysis may require combining datasets from different frequencies for a complete view.

Provenance

Source

OpenML, author Luca Urbinati.

Collection Method

Microwave sensing measurements of scattering parameters from a network of antennas, target object (jar), and air medium.