NADEAK, DAVID HASIHOLAN (2025) PENERAPAN MULTILAYER PERCEPTRON PADA SISTEM MONITORING KUALITAS AIR TANAH WILAYAH JAKARTA UNTUK MENGKLASIFIKASI KELAYAKAN AIR MINUM. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (433kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (171kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (227kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (146kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (805kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (32kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (105kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (1MB) |
Abstract
Groundwater remains one of the main sources of drinking water for the people of DKI Jakarta. However, high population density and domestic activities have led to a decline in groundwater quality. Therefore, an innovation is needed in the form of a groundwater quality monitoring system based on IoT with the integration of a Multilayer Perceptron model to classify groundwater eligibility as drinking water. This study explores the impact of applying outlier removal processes and the influence of various activation functions (ReLU, Tanh, and Sigmoid) in the hidden layer on the performance of the Multilayer Perceptron model in classifying groundwater eligibility as drinking water. The model evaluation was carried out using accuracy, precision, recall, F1-Score, confusion matrix, and classification report. The results of the study show that the application of the outlier removal process has a significant impact on the distribution of values, class balance, model learning stability, and the improvement of the Multilayer Perceptron model's accuracy. The study also shows the influence of various activation functions in the hidden layer on model performance, where the ReLU activation function provides superior performance with the highest accuracy in both scenarios (96.59% in scenario 1 and 98.09% in scenario 2), followed by Tanh (93.18% and 96.36%), and then Sigmoid (81.11% and 92.72%). The combination of outlier removal and the ReLU activation function produces the best model with an accuracy of 98.09%. This best model has been successfully implemented in the monitoring system and is capable of automatically classifying the groundwater eligibility status. Kata kunci: Groundwater Quality, Multilayer Perceptron, Classification, Monitoring System. Air tanah masih menjadi salah satu sumber air minum bagi masyarakat DKI Jakarta. Namun, tingginya kepadatan penduduk dan aktivitas domestik telah menyebabkan penurunan kualitas air tanah. Maka dari itu, diperlukan inovasi berupa sistem monitoring kualitas air tanah berbasis IoT dengan integrasi model Multilayer Perceptron untuk mengklasifikasi kelayakan air tanah sebagai air minum. Penelitian ini mengeksplorasi pengaruh penerapan proses outlier removal dan pengaruh berbagai fungsi aktivasi (ReLU, Tanh, dan Sigmoid) pada hidden layer terhadap performa model Multilayer Perceptron dalam mengklasifikasi kelayakan air tanah sebagai air minum. Evaluasi model dilakukan menggunakan akurasi, presisi, recall, F1-Score, confusion matrix, dan classification report. Hasil penelitian menunjukkan bahwa penerapan proses outlier removal berpengaruh besar terhadap persebaran nilai, keseimbangan kelas, kestabilan proses pembelajaran model, dan peningkatan akurasi model Multilayer Perceptron. Hasil penelitian juga menunjukkan pengaruh penerapan berbagai fungsi aktivasi pada hidden layer terhadap performa model, di mana fungsi aktivasi ReLU memberikan performa superior dengan akurasi tertinggi pada kedua skenario (96,59% pada skenario 1 dan 98,09% pada skenario 2), diikuti oleh Tanh (93,18% dan 96,36%), lalu Sigmoid (81,11% dan 92,72%). Kombinasi penerapan outlier removal dan fungsi aktivasi ReLU menghasilkan model terbaik dengan akurasi 98,09%. Model terbaik ini berhasil diterapkan dalam sistem monitoring dan mampu mengklasifikasi status kelayakan air tanah secara otomatis. Kata kunci: Kualitas Air Tanah, Multilayer Perceptron, Klasifikasi, Sistem Monitoring.
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/INFO. 25 110 |
| NIM/NIDN Creators: | 41521010099 |
| Uncontrolled Keywords: | Kualitas Air Tanah, Multilayer Perceptron, Klasifikasi, Sistem Monitoring. |
| Subjects: | 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 627 Hydraulic Engineering/Rekayasa Hidrolik > 627.1 Inland Waterways Engineering/Teknik Jalan Air di Pedalaman dan Air di Bawah Tanah 600 Technology/Teknologi > 640 Home Economic and Family Living Management/Kesejahteraan Rumah Tangga dan Manajemen Kehidupan Keluarga 600 Technology/Teknologi > 650 Management, Public Relations, Business and Auxiliary Service/Manajemen, Hubungan Masyarakat, Bisnis dan Ilmu yang Berkaitan > 658 General Management/Manajemen Umum > 658.6 Quality Management/Manajemen Kualitas |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | khalimah |
| Date Deposited: | 04 Aug 2025 08:22 |
| Last Modified: | 04 Aug 2025 08:22 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/96538 |
Actions (login required)
 |
View Item |
