Analysis Quality of Corn Based on IoT, SSD Mobilenet Models and Histogram
Abstract
Corn is one of the main comestibles in our society. In these last few years, the production of comestible in Indonesia has decreased, including corn. For this reason, besides increasing the production of corn, it is necessary to research corn quality so that corn has a competitive advantage. The research aims to monitor the corn’s growth and classify the corn’s quality. The research was divided into two aspects: the aspect of good corn growth, with the internet of things (IoT) monitoring, and the classification of the corn quality based on the RGB intensity pattern of digital and TensorFlow using SSD Mobilenet models. On the corn growth, the research observed temperature, humidity, and plant distance based on two kinds of corn plant diseases (blight leaf and rotten knob), using a microcontroller (Arduino Uno), DHT11 sensor, VL53L0X sensor, and ESP8266 for accessing data to a website. The quality of corn was classified into three groups, namely rotten, moldy, and normal. The classification was carried out using Python programming on Raspberry Pi with open-source library TensorFlow using SSD Mobilenet models (as the primary option for classifying the quality of corn) and Delphi 7 on a computer (as an additional option). The number of samples used was 180 sample corn seeds tested ten times for each type of quality. The results showed that the recognition of normal corn quality was nine times correct, moldy corn quality was seven times correct, and rotten corn quality was six times correct with an accuracy rate of 73.3%.
References
H.K. Purwadaria, Teknologi Penanganan Pascapanen Jagung. Jakarta, Indonesia: Deptan-FAO, UNDP, 1988.
S. Mishra, R. Sachana, and D. Rajpal, “Deep Convolutional Neural Network based Detection System for Real-Time Corn Plant Disease Recognition,” Procedia Comput. Sci., Vol. 167, pp. 2003-2010, 2020.
R. Das, V. Pooja, and V. Kanchana, “Detection of Disease on Visible Part of Plant – A Review,” 2017 IEEE Technol. Innov. ICT Agriculture, Rural Develop. (TIAR), 2017, pp. 42-45.
M.A. Rahman and M.S. Sadi, “IOT Enabled Automated Object Recognition for the Visually Impaired,” Comput. Methods, Programs Biomed., Vol. 1, pp. 1-13, 2021.
J.M. Blackledge, Digital Image Processing: Mathematical and Computational Methods. Chichester, Inggris: Horwood, 2006.
Z.-Q. Zhao, P. Zheng, S.-T. Xu, and X. Wu, “Object Detection with Deep Learning: A Review,” IEEE Trans. Neural Netw. Learn. Syst., Vol. 30, No. 11, pp. 3212 - 3232, Nov. 2019.
B.B Traore, B.K. Foguem, and F. Tangars, “Deep Convolution Neural Network for Image Recognition,” Ecol. Inform., Vol. 48, pp. 257-268, Nov. 2018.
J.G.A. Barbedo, “Plant Disease Identification from Individual Lesions and Spots Using Deep Learning,” Biosyst. Eng., Vol. 180, pp. 96-107, 2019.
A.Z. Mansor, “The Use of Blog in Decision Making Skills Course,” Procedia Soc. Behav. Sci., Vol. 18, pp. 491-500, 2011.
P.S. Janardhanan, “Project Repositories for Machine Learning with TensorFlow,” Procedia Comput. Sci., Vol. 171, pp. 188-196, 2020.
L. Parisi, R. Ma, N. RaviChandran, and M. Lanzillotta, “hyper-sinh: An Accurate and Reliable Function from Shallow to Deep Leaerning in Tensorflow and Keras,” Mach. Learn. Appl., Vol. 6, pp. 1-6, 2021.
Y.N. Nabuasa, “Pengolahan Citra Digital Perbandingan Metode Histogram Equalization and Spesification pada Citra Abu-Abu,” J-ICON-J. Komput., Inform,, Vol. 7, No. 1, pp. 87-95, 2019.
S. Agrawal, R. Panda, P.K. Mishro, and A. Abraham, “A Novel Joint Histogram Equalization based Image Contrast Enchancement,” J. King Saud Univ. – Comput., Inf. Sci., Vol. 34, No. 4, pp. 1172-1182, 2019.
V. Tripathi, D. Gangodkar, A. Mittal, and V. Kanth, “Robust Action Recognition Framework Using Segmented Block and Distance Mean Histogram of Gradients Approach,” Procedia Comput. Sci., Vol. 115, pp. 493-500, 2017.
© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
1.png)
