Ahmad Zikry Salam, . (2025) PREDIKSI BENSIN OPLOSAN BERBASIS DATA SPEKTROSKOPI MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (174kB) |
|
Text
AWAL.pdf Download (658kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (260kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (573kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (293kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (217kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (218kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (115kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (175kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (21MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (444kB) |
Abstract
Fraudulent practices involving the adulteration of gasoline with other substances by unauthorized sellers can significantly harm consumers, both in terms of fuel quality and the risk of engine damage. Therefore, a reliable method is needed to predict whether a gasoline sample is adulterated or not. This study utilizes the AS7265X spectroscopy sensor to capture the spectral data of pure and adulterated gasoline samples, which are then used as input for a Convolutional Neural Network (CNN) model. A total of 120 samples were used for training and testing the model. In the initial testing phase, the model achieved an R² score of 0.9270 or 92.70%. After applying hyperparameter tuning using the Random Search method, the R² score increased to 0.9643 or 96.43%, representing an improvement of 0.0373 or 3.73%. These results indicate that CNN is effective in learning complex patterns in spectroscopic data and that proper hyperparameter tuning plays a vital role in enhancing model performance. This research is expected to contribute to the accurate detection of adulterated gasoline and support quality control efforts in the fuel distribution system.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511019] [Pembimbing 1: Ridwan Raafi'udin] [Pembimbing 2: Nurul Afifah Arifuddin] [Penguji 1: Bayu Hananto] [Penguji 2: Muhammad Panji Muslim] |
| Uncontrolled Keywords: | Prediction, Adulterated Gasoline, Spectroscopy Data, Convolutional Neural Network (CNN), AS7265X Sensor. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | AHMAD ZIKRY SALAM |
| Date Deposited: | 05 Aug 2025 07:00 |
| Last Modified: | 05 Aug 2025 07:00 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37368 |
Actions (login required)
 |
View Item |