Pradana, Ilham Akbar (2024) Pengembangan Aplikasi Pendeteksi Keretakan Jalan Berbasis Android dengan Implementasi Algoritma Hybrid CNN-LSTM. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
Cover.pdf Download (1MB) |
|
Text (BAB I)
BAB I.pdf Download (452kB) |
|
Text (BAB II)
BAB II.pdf Restricted to Repository staff only until 19 July 2026. Download (824kB) |
|
Text (BAB III)
BAB III.pdf Restricted to Repository staff only until 19 July 2026. Download (841kB) |
|
Text (BAB IV)
BAB IV.pdf Restricted to Repository staff only until 19 July 2026. Download (1MB) |
|
Text (BAB V)
BAB V.pdf Download (374kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf Download (287kB) |
|
Text (Lampiran)
Lampiran.pdf Restricted to Repository staff only Download (1MB) |
Abstract
High-quality road infrastructure plays a critical role in the economic growth of a country. However, with increasing vehicle volume and environmental factors, road damage becomes an unavoidable issue that requires serious attention. Traditional methods for detecting road damage often involve manual inspections, which are not only time-consuming but also tend to be subjective and less accurate. This study proposes the development of an innovative Android application that utilizes Deep Learning technology for accurate and efficient road damage detection. The application incorporates a Convolutional Neural Network (CNN) for visual feature extraction from images and Long Short-Term Memory (LSTM) to understand the sequential context of the output data from the CNN layers. The dataset used in developing this model is sourced from a collection of road damage images representing various urban road conditions in Indonesia. Through the training process, this CNN-LSTM model is integrated into the application using TensorFlow Lite. The development of the Android application is done with consideration of good and efficient application architecture, ensuring that the application is not only responsive and intuitive but also resource-efficient. Through the integration of advanced technology and a focused development approach, this application has the potential to become an essential tool in road infrastructure maintenance efforts, providing a practical and innovative solution for quickly and accurately detecting road damage.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T385 Computer Graphics |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Ilham Akbar Pradana | ||||||||||||
| Date Deposited: | 22 Jul 2024 02:32 | ||||||||||||
| Last Modified: | 22 Jul 2024 02:32 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/26763 |
Actions (login required)
 |
View Item |