ARDIANSYAH, DWI DARMA (2021) KLASIFIKASI TANAMAN SELADA AIR HIDROPONIK LAYAK JUAL MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, UPN"VETERAN" JATIM.
|
Text (COVER)
Cover.PDF Download (928kB) | Preview |
|
|
Text (BAB 1)
1.PDF Download (100kB) | Preview |
|
![[img]](http://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (BAB 2)
2.PDF Restricted to Repository staff only Download (458kB) |
|
|
Text (BAB 3)
3.PDF Restricted to Repository staff only Download (491kB) |
|
|
Text (BAB 4)
4.PDF Restricted to Repository staff only Download (511kB) |
|
|
Text (BAB 5)
5.PDF Download (7kB) | Preview |
|
|
Text (DAFTAR PUSTAKA)
Dapus.PDF Download (149kB) | Preview |
Abstract
Indonesia is an agricultural country that produces a lot of products vegetables such as fruits and various types of vegetables. One type Vegetables that are often traded both at home and abroad are watercress. Lettuce marketing is increasing along with economic growth and quantity population. Watercress can be grown quite easily, but if you want to keep one of its nutritional richness is using the hydroponic method, namely the hydroponic method planting without using soil media and pesticides. Watercress farmer selling to the collectors to be re-sorted according to the quality indicators worth selling. At this time collectors still do manual sorting which has drawbacks such as the length of processing time and the quality of the sorting results Convolutional Neural Network (CNN) is a machine . method learning that is designed to process two-dimensional data. CNN is included in Deep Neural Network due to its deep network level and many implemented in the image data. In this study CNN was used to hydroponic watercress plant classification and can determine whether watercress worth selling or not worth selling. The dataset used in this study as many as 600 hydroponic watercress image datasets. The highest accuracy results obtained from several test scenarios by 100% using 3 pairs of layers and a 2X2 kernel. It can be concluded that the number of layer pairs and the size of the kernel are sufficient affect the test accuracy value. K-Fold Cross Validation is also used for testing in order to determine the validity of the dataset. Models already trained, deployment to the web is also carried out to facilitate testing and then it can be developed even better. Keywords: Deep Learning, Convolutional Neural Network, Plant Classification Hydroponic Watercress
| Item Type: | Thesis (Undergraduate) | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science | ||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||
| Depositing User: | Mujari Mujari | ||||||||
| Date Deposited: | 22 Jun 2021 02:57 | ||||||||
| Last Modified: | 22 Jun 2021 02:57 | ||||||||
| URI: | http://repository.upnjatim.ac.id/id/eprint/2087 |
Actions (login required)
 |
View Item |