Machine learning driven approach towards the quality assessment of fresh fruits using non-invasive sensing

Ren, A. , Zahid, A., Zoha, A. , Shah, S. A. , Imran, M. A. , Alomainy, A. and Abbasi, Q. H. (2020) Machine learning driven approach towards the quality assessment of fresh fruits using non-invasive sensing. IEEE Sensors Journal, 20(4), pp. 2075-2083. (doi: 10.1109/JSEN.2019.2949528)

Abstract

In agriculture science, accurate information of moisture content (MC) in fruits and vegetables in an automated fashion can be vital for astute quality and grading evaluation. This demands for a viable, feasible and cost-effective technique for the defect recognition using timely detection of MC in fruits and vegetables to maintain a healthy sensory characteristic of fruits. Here we propose a non-invasive machine learning (ML) driven technique to monitor variations of MC in fruits using the terahertz (THz) waves with Swissto12 material characterization kit (MCK) in the frequency range of 0.75 THz to 1.1 THz. In this regard, multi-domain features are extracted from time-, frequency-, and time-frequency domains, and applied three ML algorithms such as support vector machine (SVM), k-nearest neighbour (KNN) and Decision Tree (D-Tree) for the precise assessment of MC in both apple and mango slices. The results illustrated that the performance of SVM exceeded other classifiers results using 10-fold validation and leave-one-observation-out-cross-validation techniques. Moreover, all three classifiers exhibited 100% accuracy for day 1 and 4 with 80% MC value (freshness) and 2% MC value (staleness) of both fruits’ slices, respectively. Similarly, for day 2 and 3, an accuracy of 95% was achieved with intermediate MC values in both fruits’ slices. This study will pave a new direction for the real-time quality evaluation of fruits in a non-invasive manner by incorporating ML with THz sensing at a cellular level. It also has a strong potential to optimize economic benefits by the timely detection of fruits quality in an automated fashion.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Zoha, Dr Ahmed and Abbasi, Professor Qammer and Imran, Professor Muhammad and Zahid, Mr Adnan and Shah, Mr Syed and Ren, Dr Aifeng
• Authors: Ren, A., Zahid, A., Zoha, A., Shah, S. A., Imran, M. A., Alomainy, A., and Abbasi, Q. H.
• College/School: College of Science and Engineering > School of Engineering; College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering; College of Science and Engineering > School of Engineering > Systems Power and Energy
• Journal Name: IEEE Sensors Journal
• Publisher: IEEE
• ISSN: 1530-437X
• ISSN (Online): 1530-437X
• Published Online: 25 October 2019
• Copyright Holders: Copyright © 2019 IEEE
• First Published: First published in IEEE Sensors Journal 20(4): 2075-2083
• Publisher Policy: Reproduced in accordance with the publisher copyright policy