TY - GEN
T1 - The identification of oreochromis niloticus feeding behaviour through the integration of photoelectric sensor and logistic regression classifier
AU - Mohd Sojak, Mohamad Radzi
AU - Mohd Razman, Mohd Azraai
AU - P. P. Abdul Majeed, Anwar
AU - Musa, Rabiu Muazu
AU - Abdul Ghani, Ahmad Shahrizan
AU - Iskandar, Ismed
N1 - Funding Information:
Acknowledgement. The final outcome of this research project and the successful of development of this useful system required a lot of guidance and assistance from my project supervisor. Meanwhile, I would like to express my gratitude to lab instructors and my friends for providing practically knowledge, skills and guidance when doing the mechanical work in lab. This work is partially support by Universiti Malaysia Pahang, Automotive Engineering Centre (AEC) research grant RDU1803131 entitled Development of Multi-vision guided obstacle Avoidance System for Ground Vehicle.
Publisher Copyright:
© Springer Nature Singapore Pte Ltd. 2019.
PY - 2019
Y1 - 2019
N2 - Oreochromis niloticus or tilapia is the second major freshwater aquaculture bred after catfish in Malaysia. By understanding the feeding behaviour, fish farmers will able to identify the best feeding routine. In the present investigation, photoelectric sensors are used to identify the movement, speed and position of the fish. The signals acquired from the sensors are converted into binary data. The hunger behaviour classes are determined through k-means clustering algorithm, i.e., satiated and unsatiated. The Logistic Regression (LR) classifier was employed to classify the aforesaid hunger state. The model was trained by means of 5-fold cross-validation technique. It was shown that the LR model is able to yield a classification accuracy for tested data during the day at three different time windows (4 h each) is 100%, 88.7% and 100%, respectively, whilst the for-night data it was shown to demonstrate 100% classification accuracy.
AB - Oreochromis niloticus or tilapia is the second major freshwater aquaculture bred after catfish in Malaysia. By understanding the feeding behaviour, fish farmers will able to identify the best feeding routine. In the present investigation, photoelectric sensors are used to identify the movement, speed and position of the fish. The signals acquired from the sensors are converted into binary data. The hunger behaviour classes are determined through k-means clustering algorithm, i.e., satiated and unsatiated. The Logistic Regression (LR) classifier was employed to classify the aforesaid hunger state. The model was trained by means of 5-fold cross-validation technique. It was shown that the LR model is able to yield a classification accuracy for tested data during the day at three different time windows (4 h each) is 100%, 88.7% and 100%, respectively, whilst the for-night data it was shown to demonstrate 100% classification accuracy.
KW - Fish hunger behaviour
KW - Logistic regression
KW - Oreochromis niloticus
KW - Photoelectric sensor
UR - http://www.scopus.com/inward/record.url?scp=85065095555&partnerID=8YFLogxK
U2 - 10.1007/978-981-13-7780-8_18
DO - 10.1007/978-981-13-7780-8_18
M3 - Conference Proceeding
AN - SCOPUS:85065095555
SN - 9789811377792
T3 - Communications in Computer and Information Science
SP - 222
EP - 228
BT - Robot Intelligence Technology and Applications - 6th International Conference, RiTA 2018, Revised Selected Papers
A2 - Kim, Jong-Hwan
A2 - Myung, Hyung
A2 - Lee, Seung-Mok
PB - Springer Verlag
T2 - 6th International Conference on Robot Intelligence Technology and Applications, RiTA 2018
Y2 - 16 December 2018 through 18 December 2018
ER -