ALFAJR, ACHMAD YUNEDA (2023) KLASIFIKASI PENGEMUDI TERGANGGU MENGGUNAKAN METODE SUPPORT VECTOR MACHINE BERBASIS PCA REDUKSI FITUR CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, UNIVERSITAS PEMBANGUNAN NASIONAL "VETERAN" JAWA TIMUR.
|
Text (Cover)
19081010128-cover.pdf Download (1MB) | Preview |
|
|
Text (BAB I)
19081010128-bab1.pdf Download (142kB) | Preview |
|
![[img]](http://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (BAB II)
19081010128-bab2.pdf Restricted to Repository staff only until 19 November 2026. Download (1MB) | Request a copy |
|
|
Text (BAB III)
19081010128-bab3.pdf Restricted to Repository staff only until 20 November 2026. Download (927kB) | Request a copy |
|
|
Text (BAB IV)
19081010128-bab4.pdf Restricted to Repository staff only until 20 November 2026. Download (3MB) | Request a copy |
|
|
Text (BAB V)
19081010128-bab5.pdf Download (13kB) | Preview |
|
|
Text (Daftar Pustaka)
19081010128-daftar-pustaka.pdf Download (138kB) | Preview |
|
|
Text (Lampiran)
19081010128-lampiran.pdf Restricted to Repository staff only until 20 November 2026. Download (882kB) | Request a copy |
Abstract
The increasing use of road transportation has raised concerns about the high incidence of accidents. The rising traffic density is a consequence of the widespread use of transportation tools. One of the main causes of accidents is driver distraction, often caused by disruptive activities such as texting, calling, and eating while driving. A potential solution is to employ image classification technology to assess whether the driver's attention is compromised. To address the issue of recognizing distracted driving conditions, image processing techniques can be applied. One approach involves extracting features from specific objects for identification purposes. This research implements feature extraction using the Convolutional Neural Network method, feature reduction using Principal Component Analysis, and Support Vector Machine for the classification process. Based on testing results on the test data, the highest accuracy was obtained with a 60%:40% data split, a parameter C value of 10, a maximum iteration parameter of 20, a tolerance parameter of 0.01, and a feature reduction result of 1024, yielding an accuracy of 97.60%, precision of 97.58%, recall of 97.53%, and an f1-score of 97.55%.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Achmad Yuneda Alfajr | ||||||||||||
| Date Deposited: | 20 Nov 2023 07:33 | ||||||||||||
| Last Modified: | 22 Nov 2023 02:19 | ||||||||||||
| URI: | http://repository.upnjatim.ac.id/id/eprint/18721 |
Actions (login required)
 |
View Item |