Rudianto, Ricky and , Fajar Suryawan, S.T, M.Eng.Sc.,Ph.D. (2026) Rancang Bangun Sistem Klasifikasi Kesegaran Daging Sapi Menggunakan Neural Network Terkompresi Pada Mikrokontroler ESP32 Dengan Sensor Gas MQ Dan Sensor Warna RGB. Skripsi thesis, Universitas Muhammadiyah Surakarta.
![[img]](https://eprints.ums.ac.id/style/images/fileicons/application_pdf.png) |
PDF (Naskah Publikasi)
NASKAH PUBLIKASI.pdf Download (1MB) |
|
PDF (Surat Pernyataan Publikasi)
Surat pernyataan publikasi .pdf Restricted to Repository staff only Download (577kB) |
Abstract
Beef segarness is an important factor that affects food quality and safety. Segarness assessment performed manually through visual observation and odor evaluation is still subjective and may lead to inaccurate judgments. Therefore, this study aims to design and develop a beef segarness classification system using an MQ-135 gas sensor and a TCS3200 color sensor combined with a Neural Network method implemented on an ESP32 microcontroller. Sensor data were processed through several preprocessing stages, including the application of an Infinite Impulse Response (IIR) filter to reduce noise, RGB-to-HSV color space conversion, and data normalization before being used as model inputs. The input features consisted of R, G, B, Saturation (S), Value (V), and MQ values. The Neural Network model was developed using TensorFlow and converted into TensorFlow Lite format to enable deployment on the ESP32 microcontroller. The evaluation results showed an accuracy of 91.10% with a weighted average F1-score of 0.91. Direct testing of the system achieved an accuracy of 83.3%, with a 100% success rate in identifying spoiled beef samples. The results indicate that the combination of gas sensing, color sensing, and Neural Network methods is capable of accurately classifying beef segarness levels. Furthermore, the implementation on ESP32 enables real-time classification without requiring an external server, making the system suitable for embedded applications.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Uncontrolled Keywords: | Neural Network, TensorFlow Lite, Beef Segarness Classification, MQ Gas Sensor, RGB Color Sensor,ESP32 |
| Subjects: | R Medicine > General Medicine T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Fakultas Teknik > S1 Teknik Elektro |
| Depositing User: | RICKY DWI RUDIANTO |
| Date Deposited: | 21 Jul 2026 01:03 |
| Last Modified: | 21 Jul 2026 01:04 |
| URI: | http://eprints.ums.ac.id/id/eprint/146184 |
Actions (login required)
 |
View Item |
