Sensor and Laboratory Data, Image Data and Statistical Analysis Results: Integrating Sensor Data, Laboratory Analysis, and Computer Vision in Machine Learning-Driven E-Nose Systems for Predicting Tomato Shelf Life

This dataset accompanies the publication “Integrating Sensor Data, Laboratory Analysis, and Computer Vision in Machine Learning-Driven E-Nose Systems for Predicting Tomato Shelf Life” ([https://doi.org/10.3390/chemosensors13070255]) and contains all data used for the analysis, model development, and interpretation presented in the study. Contents The dataset is structured into three components: Image DataImages of tomato samples taken from three different sides across multiple storage days and conditions. The filenames encode the storage scenario, sample ID, and storage day (e.g., Trt_0501_D3.jpg). These images were used to extract color features and visually assess spoilage progression. Sensor and Laboratory DataA set of structured CSV files containing: Sample metadata (ID, storage condition, storage day) Weight measurements (minitial, mcurrent) Color values (L, a, b) averaged across the three images per sample Sensor data (Rs/R₀ values) from 12 gas sensors detecting volatile organic compounds The data is split into: A random sampling dataset, used to train and validate machine learning models A continuous sampling dataset, used to analyze time-dependent trends in individual tomatoes 3. Statistical Analysis Results Summary tables from the statistical evaluations performed in the paper.