Razman, Mohd Azraan and Abdul Majeed, Anwar P.P. and Musa, Rabiu Muazu and Taha, Zahari and Susto, Gian Antonio and Mukai, Yukinori
(2020)
Time-series identification on fish feeding behaviour.
In:
Machine Learning in Aquaculture:Hunger Classification of Lates calcarifer.
Briefs in Applied Sciences and Technology
.
Springer, Singapore, pp. 37-47.
ISBN 978-981-15-2236-9
Abstract
Abstract The 1 identification of relevant parameters that could describe the state of AQ1
2 fish hunger is vital for ensuring the appropriate allocation of food to the fish. The
3 establishment of these relevant parameters is non-trivial, particularly when develop4
ing an automated demand feeder system. The present inquiry is being undertaken
5 to determine the hunger state of Lates calcarifer. For data collection, a video anal6
ysis system is used, and the video was taken all day, where the fish was fed by
7 an automatic feeding system. Sixteen characteristics of the raw data set have been
8 extracted through feature engineering for 0.5 min, 1.0 min, 1.5 min and 2.0 min,
9 respectively, in accordance with the mean, peak, minimum and variability of each of
10 the different time window scales. Furthermore, the features extracted have been eval11
uated through principal component analysis (PCA) both for dimension reduction and
12 PCA with varimax rotation. The details were then categorized using support vector
13 machine (SVM), K-NN and random forest tree (RF) classifiers. The best identifica14
tion accuracy was shown with eight described features in the varimax-based PCA.
15 The forecast results based on the K-NN model built on selected data characteristics
16 showed a level of 96.5% indicating that the characteristics analysed were crucial to
17 classifying the actions of hunger among fisheries.
Actions (login required)
 |
View Item |
Download Statistics
Download Statistics