Abstract
Ripeness is a key metric in the growth, distribution and sale of fruits. Present methods to determine a given fruit’s ripeness rely on slow, labour intensive and destructive methods that only provide an indication of crop-wide ripeness. A digital, low-cost and non-destructive method would provide instant access to accurate ripeness data whenever required. In this paper a methodology is proposed for estimation of banana ripeness using an array of lowcost sensing modalities including cameras, spectrometers, Volatile Organic Compound and environmental sensors. Data was collected over 5 periods, each 35 days long (on average), using a setup designed for this systematic data collection. The banana’s ripeness is classified into one of 5 stages using a range of Machine Learning algorithms such as Support Vector Machines, Random Forest, K-Nearest Neighbours, Gradient Boosting Classifiers & Artificial Neural Networks, which were trained and tested against datasets constructed from different combinations of sensor data. Random Forest and Gradient Boosting Classifiers were found to be the most accurate at 99.95% each when using data from all available sensors arrays.
Original language | English |
---|---|
Number of pages | 10 |
Journal | IEEE Sensors Journal |
Early online date | 16 Jan 2025 |
DOIs | |
Publication status | E-pub ahead of print - 16 Jan 2025 |
Data Availability Statement
Data created in this research work is openly availablefrom the University of Bath Research Data Archive at
https://doi.org/10.15125/BATH-01459
Funding
Engineering and Physical Sciences Research Council (Grant Number: EP/V051083/1)
Funders | Funder number |
---|---|
Engineering and Physical Sciences Research Council |
Keywords
- Classification
- Computational Intelligence
- Fruit Ripeness
- Multimodal Sensing
ASJC Scopus subject areas
- Instrumentation
- Electrical and Electronic Engineering
Fingerprint
Dive into the research topics of 'Low-Cost, Multi-Sensor Non-Destructive Banana Ripeness Estimation Using Machine Learning'. Together they form a unique fingerprint.Datasets
-
Dataset for "Low-Cost, Multi-Sensor Non-Destructive Banana Ripeness Estimation Using Machine Learning"
Callaghan, K. (Creator) & Martinez Hernandez, U. (Creator), University of Bath, 16 Jan 2025
DOI: 10.15125/BATH-01459
Dataset