The Novel Combination of Nano Vector Network Analyzer and Machine Learning for Fruit Identification and Ripeness Grading
Fruit classification is required in many smart-farming and industrial applications. In the supermarket, a fruit classification system may be used to help cashiers and customer to identify the fruit species, origin, ripeness, and prices. Some methods, such as image processing and NIRS (near-infrared...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/2/952 |
| _version_ | 1797437248267878400 |
|---|---|
| author | Van Lic Tran Thi Ngoc Canh Doan Fabien Ferrero Trinh Le Huy Nhan Le-Thanh |
| author_facet | Van Lic Tran Thi Ngoc Canh Doan Fabien Ferrero Trinh Le Huy Nhan Le-Thanh |
| author_sort | Van Lic Tran |
| collection | DOAJ |
| description | Fruit classification is required in many smart-farming and industrial applications. In the supermarket, a fruit classification system may be used to help cashiers and customer to identify the fruit species, origin, ripeness, and prices. Some methods, such as image processing and NIRS (near-infrared spectroscopy) are already used to classify fruit. In this paper, we propose a fast and cost-effective method based on a low-cost Vector Network Analyzer (VNA) device augmented by K-nearest neighbor (KNN) and Neural Network model. S-parameters features are selected, which take into account the information on signal amplitude or phase in the frequency domain, including reflection coefficient <i>S</i><sub>11</sub> and transmission coefficient <i>S</i><sub>21</sub>. This approach was experimentally tested for two separate datasets of five types of fruits, including Apple, Avocado, Dragon Fruit, Guava, and Mango, for fruit recognition as well as their level of ripeness. The classification accuracy of the Neural Network model was higher than KNN with 98.75% and 99.75% on the first dataset, whereas the KNN was seen to be more effective in classifying ripeness with 98.4% as compared to 96.6% for neural network. |
| first_indexed | 2024-03-09T11:16:06Z |
| format | Article |
| id | doaj.art-9d8f0e2b7f9c48f6b3a22363452c1892 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T11:16:06Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9d8f0e2b7f9c48f6b3a22363452c18922023-12-01T00:30:21ZengMDPI AGSensors1424-82202023-01-0123295210.3390/s23020952The Novel Combination of Nano Vector Network Analyzer and Machine Learning for Fruit Identification and Ripeness GradingVan Lic Tran0Thi Ngoc Canh Doan1Fabien Ferrero2Trinh Le Huy3Nhan Le-Thanh4Universite Cote d’Azur, LEAT, CNRS, 06903 Sophia Antipolis, FranceThe University of Danang—University of Economics, Danang 55000, VietnamUniversite Cote d’Azur, LEAT, CNRS, 06903 Sophia Antipolis, FranceFaculty of Computer Engineering, University of Information Technology, Ho Chi Minh City 721400, VietnamUniversite Cote d’Azur, LEAT, CNRS, 06903 Sophia Antipolis, FranceFruit classification is required in many smart-farming and industrial applications. In the supermarket, a fruit classification system may be used to help cashiers and customer to identify the fruit species, origin, ripeness, and prices. Some methods, such as image processing and NIRS (near-infrared spectroscopy) are already used to classify fruit. In this paper, we propose a fast and cost-effective method based on a low-cost Vector Network Analyzer (VNA) device augmented by K-nearest neighbor (KNN) and Neural Network model. S-parameters features are selected, which take into account the information on signal amplitude or phase in the frequency domain, including reflection coefficient <i>S</i><sub>11</sub> and transmission coefficient <i>S</i><sub>21</sub>. This approach was experimentally tested for two separate datasets of five types of fruits, including Apple, Avocado, Dragon Fruit, Guava, and Mango, for fruit recognition as well as their level of ripeness. The classification accuracy of the Neural Network model was higher than KNN with 98.75% and 99.75% on the first dataset, whereas the KNN was seen to be more effective in classifying ripeness with 98.4% as compared to 96.6% for neural network.https://www.mdpi.com/1424-8220/23/2/952VNAKNNneural networkfruit classification |
| spellingShingle | Van Lic Tran Thi Ngoc Canh Doan Fabien Ferrero Trinh Le Huy Nhan Le-Thanh The Novel Combination of Nano Vector Network Analyzer and Machine Learning for Fruit Identification and Ripeness Grading Sensors VNA KNN neural network fruit classification |
| title | The Novel Combination of Nano Vector Network Analyzer and Machine Learning for Fruit Identification and Ripeness Grading |
| title_full | The Novel Combination of Nano Vector Network Analyzer and Machine Learning for Fruit Identification and Ripeness Grading |
| title_fullStr | The Novel Combination of Nano Vector Network Analyzer and Machine Learning for Fruit Identification and Ripeness Grading |
| title_full_unstemmed | The Novel Combination of Nano Vector Network Analyzer and Machine Learning for Fruit Identification and Ripeness Grading |
| title_short | The Novel Combination of Nano Vector Network Analyzer and Machine Learning for Fruit Identification and Ripeness Grading |
| title_sort | novel combination of nano vector network analyzer and machine learning for fruit identification and ripeness grading |
| topic | VNA KNN neural network fruit classification |
| url | https://www.mdpi.com/1424-8220/23/2/952 |
| work_keys_str_mv | AT vanlictran thenovelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading AT thingoccanhdoan thenovelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading AT fabienferrero thenovelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading AT trinhlehuy thenovelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading AT nhanlethanh thenovelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading AT vanlictran novelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading AT thingoccanhdoan novelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading AT fabienferrero novelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading AT trinhlehuy novelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading AT nhanlethanh novelcombinationofnanovectornetworkanalyzerandmachinelearningforfruitidentificationandripenessgrading |