ELECTRONIC NOSE SYSTEM FOR FRUIT SPOILAGE DETECTION USING IOT-BASED ARTIFICIAL NEURAL NETWORK

Putra, Faturochim (2024) ELECTRONIC NOSE SYSTEM FOR FRUIT SPOILAGE DETECTION USING IOT-BASED ARTIFICIAL NEURAL NETWORK. Tugas Akhir thesis, University of Technology.

[img] Text
5200711084_Faturochim Putra.pdf
Download (77kB)

Abstract

ABSTRACT Detection of fruit rot presents a significant challenge within the agricultural sector, particularly in preserving fruit quality throughout distribution. This study introduces an electronic nose (E-Nose) system that leverages Artificial Neural Networks (ANN) and the Internet of Things (IoT) to facilitate real-time detection of fruit rot. The E-Nose employs gas sensors, specifically TGS 2600, TGS 2602, and TGS 822, to identify variations in gas compounds indicative of rot. The data collected from these sensors are analyzed using an ANN implemented in MATLAB software, with the results transmitted via IoT for remote monitoring. This study utilized a dataset comprising 2,176 samples to train the ANN utilizing the backpropagation method. The dataset was partitioned into Training, Validation, and Testing. Specifically, 80% of the data (1,740 samples) was allocated for training, while 10% (218 samples) was designated for validation, and the remaining 10% (218 samples) was reserved for testing. The findings of this research demonstrate that the proposed system can detect fruit rot with a high degree of accuracy, thereby enabling prompt preventive measures and minimizing fruit waste. The study categorizes the results based on fresh and rotten fruit. The tests conducted within the fruit detection system yielded Accuracy, Precision, Sensitivity, and Specificity levels of 100%. This outcome was derived from a total of 48 tests, including 16 tests on training data, 16 on untested data, and 16 on new data. Keywords: Matlab, Artificial Neural Network, Electronic smell.

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Sains Dan Teknologi > S1 Teknik Elektro
Depositing User: Kaprodi Teknik Elektro
Date Deposited: 28 Nov 2024 03:07
Last Modified: 28 Nov 2024 03:07
URI: http://eprints.uty.ac.id/id/eprint/16731

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.