Improved Maturity and Ripeness Classifications of Magnifera Indica cv. Harumanis Mangoes through Sensor Fusion of an Electronic Nose and Acoustic Sensor
Date
2012-05-10Author
Ammar, Zakaria
Ali Yeon, Md Shakaff, Prof. Dr.
Maz Jamilah, Masnan
Fathinul Syahir, Ahmad Saad
Abdul Hamid, Adom, Prof. Dr.
Mohd Noor, Ahmad, Prof. Dr.
Mahmad Nor, Jaafar, Assoc. Prof. Dr.
Abu Hassan, Abdullah
Latifah Munirah, Kamarudin
Metadata
Show full item recordAbstract
In recent years, there have been a number of reported studies on the use of non-destructive techniques to evaluate and determine mango maturity and ripeness levels.
However, most of these reported works were conducted using single-modality sensing
systems, either using an electronic nose, acoustics or other non-destructive measurements. This paper presents the work on the classification of mangoes (Magnifera Indica cv. Harumanis) maturity and ripeness levels using fusion of the data of an electronic nose and an acoustic sensor. Three groups of samples each from two different harvesting times (week
7 and week 8) were evaluated by the e-nose and then followed by the acoustic sensor.
Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were able to discriminate the mango harvested at week 7 and week 8 based solely on the aroma and
volatile gases released from the mangoes. However, when six different groups of different maturity and ripeness levels were combined in one classification analysis, both PCA and LDA were unable to discriminate the age difference of the Harumanis mangoes. Instead of six different groups, only four were observed using the LDA, while PCA showed only two distinct groups. By applying a low level data fusion technique on the e-nose and acoustic data, the classification for maturity and ripeness levels using LDA was improved. However, no significant improvement was observed using PCA with data fusion technique. Further
work using a hybrid LDA-Competitive Learning Neural Network was performed to validate
the fusion technique and classify the samples. It was found that the LDA-CLNN was also improved significantly when data fusion was applied.