Electronic Nose Sensor Data for Apples Infected with Different Fungi

160 ripe Fuji apples from Gansu Province, China, were inoculated with Aspergillus niger, Penicillium expansum, or Penicillium crustosum fungi and measured with an 8-sensor electronic nose. Data includes raw sensor readings, smoothed/filtered data, and extracted features like integral and variance values from 6 active sensors. The dataset was created by Changtong Zhao and includes data after outlier removal and dimensionality reduction.

Use Cases

• Classifying apple fungal infections based on electronic nose sensor response patterns.
• Developing feature extraction methods for time-series sensor data from agricultural products.
• Training models for anomaly detection in food quality monitoring using sensor data outliers.
• Comparing dimensionality reduction techniques like PCA and LDA on multi-sensor agricultural data.

Strengths

• Includes data from 160 apples with controlled experimental conditions for fungal infection.
• Describes a detailed preprocessing pipeline including outlier removal and multiple smoothing techniques.
• Extracts six specific feature parameters (e.g., integral, variance) from the sensor response curves.

Limitations

• Row count and file sizes are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Changtong Zhao via PapersWithCode

Collection Method

Data collected from a laboratory experiment using an electronic nose on inoculated apple samples.

Geography

Apples sourced from plantations in Gansu Province, China.