Peach Maturity Dataset (Redhaven)
Fuente:
Zenodo
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Recurso digital |
| Langue: | anglais |
| Publié: |
Zenodo
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866902152779137024 |
|---|---|
| author | Ljubobratović, Dejan Vuković, Marko Matetic, Maja Brkic Bakaric, Marija Jemrić, Tomislav |
| author_facet | Ljubobratović, Dejan Vuković, Marko Matetic, Maja Brkic Bakaric, Marija Jemrić, Tomislav |
| contents | <p>This dataset contains measurements of 701 peach fruit samples (<em>Prunus persica</em>, cv. 'Redhaven') collected at a single orchard location under uniform agronomic conditions. Each sample is annotated with a categorical maturity label derived from established firmness-based harvest thresholds. The dataset includes 58 variables encompassing a wide spectrum of physicochemical, colorimetric, morphometric, and electrical attributes relevant for maturity assessment.</p> <p>Physical and morphometric measurements comprise fruit mass, volume, and firmness. Biochemical variables include soluble solids content and titratable acidity. Colorimetric descriptors are recorded from multiple regions of the fruit surface (additional color, ground color, petiole-insertion area), expressed through L*, a*, b*, C*, h°, and several derived color indices. Electrical impedance properties (Zs and Ts components) are measured in two orthogonal orientations using a handheld LCR meter at 10 kHz.</p> <p>All samples were measured individually, and the complete dataset is stored in CSV format with clearly defined variable names and metadata. Due to its multimodal structure and the inclusion of both destructive and non-destructive measurements, the dataset is well suited for applications in machine learning, maturity classification, and the development of predictive models for automated or real-time fruit quality assessment.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17669848 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Peach Maturity Dataset (Redhaven) Ljubobratović, Dejan Vuković, Marko Matetic, Maja Brkic Bakaric, Marija Jemrić, Tomislav Peach maturity Redhaven Tabular data Fruit quality Dielectric properties Colorimetric features Machine learning Machine learning dataset Agricultural sensing Horticulture Non-destructive measurement <p>This dataset contains measurements of 701 peach fruit samples (<em>Prunus persica</em>, cv. 'Redhaven') collected at a single orchard location under uniform agronomic conditions. Each sample is annotated with a categorical maturity label derived from established firmness-based harvest thresholds. The dataset includes 58 variables encompassing a wide spectrum of physicochemical, colorimetric, morphometric, and electrical attributes relevant for maturity assessment.</p> <p>Physical and morphometric measurements comprise fruit mass, volume, and firmness. Biochemical variables include soluble solids content and titratable acidity. Colorimetric descriptors are recorded from multiple regions of the fruit surface (additional color, ground color, petiole-insertion area), expressed through L*, a*, b*, C*, h°, and several derived color indices. Electrical impedance properties (Zs and Ts components) are measured in two orthogonal orientations using a handheld LCR meter at 10 kHz.</p> <p>All samples were measured individually, and the complete dataset is stored in CSV format with clearly defined variable names and metadata. Due to its multimodal structure and the inclusion of both destructive and non-destructive measurements, the dataset is well suited for applications in machine learning, maturity classification, and the development of predictive models for automated or real-time fruit quality assessment.</p> |
| title | Peach Maturity Dataset (Redhaven) |
| topic | Peach maturity Redhaven Tabular data Fruit quality Dielectric properties Colorimetric features Machine learning Machine learning dataset Agricultural sensing Horticulture Non-destructive measurement |
| url | https://doi.org/10.5281/zenodo.17669848 |