ARTIFICIAL INTELLIGENCE FOR BANANA'S RIPENESS DETECTION USING CONVENTIONAL NEURAL NETWORK ALGORITHM

UTAMI, MELINDA (2021) ARTIFICIAL INTELLIGENCE FOR BANANA'S RIPENESS DETECTION USING CONVENTIONAL NEURAL NETWORK ALGORITHM. S1 thesis, Universitas Mercu Buana Jakarta.

[img]
Preview
Text (HAL COVER)
01. Cover.pdf

Download (538kB) | Preview
[img] Text (BAB I)
02. BAB 1.pdf
Restricted to Registered users only

Download (72kB)
[img] Text (BAB II)
03. BAB 2.pdf
Restricted to Registered users only

Download (226kB)
[img] Text (BAB III)
04. BAB 3.pdf
Restricted to Registered users only

Download (225kB)
[img] Text (BAB IV)
05. BAB 4.pdf
Restricted to Registered users only

Download (637kB)
[img] Text (BAB V)
06. BAB 5.pdf
Restricted to Registered users only

Download (54kB)
[img] Text (DAFTAR PUSTAKA)
07. Daftar Pustaka.pdf
Restricted to Registered users only

Download (79kB)
[img] Text (LAMPIRAN)
08. Lampiran.pdf
Restricted to Registered users only

Download (2MB)

Abstract

The Industrial Era 4.0 is a continuation of the Industrial Era 3.0, which implements an online digital system for everything, or we usually call this the Internet of Things (IoT). Technology has been a major factor in achieving optimal yield and minimum waste in agriculture over the past few decades, through the use of heavy machinery in agriculture as well as digital computing. With the advent of big data and artificial intelligence, the agricultural sector has received a tremendous boost in solving most of its challenges and ensuring maximum quality in products. Artificial intelligence has been continuously used to improve agricultural yields, storage and analysis since the advent of machine learning and deep learning. Technology for the development of Artificial Intelligent can be a solution for people in developing more efficient agricultural systems. By utilizing artificial intelligence, especially deep learning, you can monitor it earlier and in real time. By using the CONVOLUTIONAL NEURAL NETWORK ALGORITHM method, it is very suitable for object detection cases in real time conditions. So that using this method can help check the quality of the fruit before the fruit is sold to consumers. At the stage of making a classification system that uses deep learning, there are several main process stages, namely data collection, system design, training, and testing. The processed dataset is a dataset of banana fruit images with 3 different skin colors. The data classes used were 5 classes ranging from human class, raw banana class, ripe banana class, rotten banana class and non-banana or other fruit class. Based on the test data done 100 times, the accuracy rate of the program is 97% in the dim room and 97% in the bright room for unripe bananas with 33 tests. And with distance, the accuracy reaches 100%. For ripe bananas, with 33 tests, the accuracy rate is 97% in dim rooms and 97% in bright rooms and with distance, the accuracy reaches 78%. For rotten bananas, the accuracy rate is 97% in dim rooms and 97% in bright rooms and with distance, the accuracy reaches 89%. Keywords : deep learning, Image Processing,Convolutional Neural Network Era Industri 4.0 merupakan kelanjutan dari Era Industri 3.0 yang mengimplementasikan sistem digital secara online ke segala hal, hal ini biasa kita sebut sebagai Internet of Things (IoT). Teknologi telah menjadi faktor utama dalam mencapai hasil optimal dan pemborosan minimum dalam pertanian selama beberapa dekade terakhir melalui penggunaan mesin berat di pertanian dan juga komputasi digital. Dengan munculnya big data dan kecerdasaan buatan, sektor pertanian telah menerima dorongan luar biasa dalam menyelesaikan sebagian besar tantangannya serta memastikan kualitas maksimum dalam produk. Kecerdasaan buatan telah terus digunakan untuk meningkatkan hasil pertanian, penyimpanan dan analisa sejak munculnya machine learning dan deep learning. Teknologi Perkembangan kecerdasan buatan (Artificial Intelligent) dapat menjadi solusi bagi masyarakat dalam mengembangkan sistem pertanian yang lebih efisien. Dengan memanfaatkan kecerdaan buatan khususnya deep learning dapat memantau secara dini dan real time. Dengan menggunakan metode CONVOLUTIONAL NEURAL NETWORK ALGORITHM sangat cocok untuk kasus pendeteksian objek dalam kondisi real time. Sehingga dengan menggunakan metode tersebut dapat membantu pengecekkan kualitas buah sebelum buah tersebut dijual kepada konsumen. Pada tahap pembuatan sistem klasifikasi yang menggunakan deep learning terdapat beberapa tahapan proses utama yaitu pengumpulan data, perancangan system, training, dan testing. Dataset yang diolah adalah dataset citra buah pisang dengan 3 warna kulit yang berbeda. Kelas data yang digunakan yaitu sejumlah 5 kelas mulai dari kelas manusia, kelas pisang mentah, kelas pisang matang, kelas pisang busuk dan kelas bukan pisang atau buah lain. Berdasarkan data pengujian yang dikerjakan sebanyak 100 kali didapat tingkat akurasi dari program adalah sebesar 97% di ruang redup dan 97% di ruang terang untuk pisang mentah dengan pengujian sebanyak 33 kali, dan bila dengan jarak akurasinya mencapai 100%. Untuk tingkat akurasi 97% di ruang redup dan 97% diruang terang untuk pisang matang dengan pengujian sebanyak 33 kali dan bila dengan jarak akurasinya mencapai 78%. Untuk tingkat akurasi 97% di ruang redup dan 97% diruang terang untuk pisang busuk dan bila dengan jarak akurasinya mencapai 89%. Kata kunci : deep learning, Image Processing,Convolutional Neural Network.

Item Type: Thesis (S1)
NIM/NIDN Creators: 41416120079
Uncontrolled Keywords: deep learning, Image Processing,Convolutional Neural Network.
Subjects: 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan
600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan
600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan > 621.3 Electrical Engineering, Lighting, Superconductivity, Magnetic Engineering, Applied Optics, Paraphotic Technology, Electronics Communications Engineering, Computers/Teknik Elektro, Pencahayaan, Superkonduktivitas, Teknik Magnetik, Optik Terapan, Tekn
Divisions: Fakultas Teknik > Teknik Elektro
Depositing User: Dede Muksin Lubis
Date Deposited: 31 Jan 2022 02:28
Last Modified: 31 Jan 2022 02:28
URI: http://repository.mercubuana.ac.id/id/eprint/54993

Actions (login required)

View Item View Item