Cocoa-Hazelnut Spread Jar Contaminant Detection via Microwave Sensing at 9.5 GHz

2400 instances of scattering parameters measured at 9.5 GHz for detecting contaminants in packaged food jars. The dataset was created by Luca Urbinati and contains 1200 uncontaminated and 1200 contaminated samples across 11 classes of contaminants like metal, glass, and plastic. It is part of a series of five datasets each measured at a different microwave frequency.

Use Cases

• Classifying contaminant types (e.g., metal, glass, plastic) based on 30 scattering parameters.
• Training models to distinguish between contaminated and uncontaminated food jars using microwave scattering data.
• Analyzing the effect of contaminant placement (surface vs. middle) on microwave scattering signatures.

Strengths

• Contains 2400 total instances with a balanced set of 1200 contaminated and 1200 uncontaminated samples.
• Includes 11 distinct classes of contaminants with specific instance counts per class, such as 200 for 'air_surface' and 100 for 'glass_fragment_middle'.
• Data is part of a controlled series acquired at five specific microwave frequencies, with this subset measured at 9.5 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 description is generic to a series of five datasets, which may cause confusion if the specific 9.5 GHz data is sought.

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.