Sudarma Yudho Prayitno, . (2026) PENGEMBANGAN SISTEM IOT BERBASIS ESP8266 UNTUK DETEKSI DINI PENYAKIT SALURAN KEMIH BERBASIS PH DAN WARNA URINE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (801kB) |
|
Text
AWAL.pdf Download (4MB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (7MB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (21MB) |
|
Text
BAB 5.pdf Download (1MB) |
|
Text
DAFTAR PUSTAKA.pdf Download (1MB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (78kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
TURNITIN PENGEMBANGAN SISTEM IOT BERBASIS ESP8266 UNTUK DETEKSI DINI PENYAKIT SALURAN KEMIH BERBASIS PH DAN WARNA URINE.pdf Restricted to Repository staff only Download (27MB) |
|
Text
Karya Ilmiah_Sudarma Yudho Prayitno_2210511122.pdf Restricted to Repository staff only Download (555kB) |
Abstract
Urinary tract health can be monitored through urine parameter analysis such as pH and color. Conventional examinations that rely on visual observation and laboratory analysis are time-consuming and potentially subjective. This study aims to develop an ESP8266-based Internet of Things (IoT) system capable of detecting urine pH and color in real-time and predicting urinary tract diseases early using a machine learning approach. The system is designed by integrating pH sensors, color sensors, and turbidity sensors connected to ESP8266. The measurement data is sent to a cloud-based database and processed using Random Forest and XGBoost algorithms. The device was tested on 20 urine samples by comparing the device readings with laboratory test results as reference data. The test results showed that the system was able to detect urine parameters with patterns consistent with laboratory results, with an average pH measurement deviation of ±0.6, which is still within the tolerance limit for early detection (screening) purposes. The machine learning model was evaluated using a dataset of 301 data points, which showed that the Random Forest algorithm produced 100% accuracy and an F1-score of 1.000, while XGBoost obtained 98.4% accuracy and an F1-score of 0.984. Based on the results of the device testing and model evaluation, the developed system is capable of functioning as a real-time screening tool for urinary tract diseases, but it cannot yet replace clinical laboratory tests. Based on input from urology and clinical pathology specialists, the system still has limitations because it only uses pH and urine color parameters. Therefore, further research is recommended to add other clinical parameters, such as bacterial indicators, leukocytes, nitrites, or urine protein, to improve the accuracy and clinical relevance of the system
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511122] [Pembimbing 1: Neny Rosmawarni] [Pembimbing 2: Nurhuda Maulana] [Penguji 1: Henki Bayu Seta] [Penguji 2: Kharisma Wiati Gusti] |
| Uncontrolled Keywords: | Internet of Things; ESP8266; urine pH; urine color; machine learning. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software R Medicine > RB Pathology T Technology > TJ Mechanical engineering and machinery T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | SUDARMA YUDHO PRAYITNO |
| Date Deposited: | 17 Mar 2026 03:35 |
| Last Modified: | 17 Mar 2026 03:35 |
| URI: | http://repository.upnvj.ac.id/id/eprint/42199 |
Actions (login required)
 |
View Item |