Pengembangan Sistem Klasifikasi Telur Ayam Negeri Berbasis IoT

Suharsoyo, Arkaan Hilmi (2026) Pengembangan Sistem Klasifikasi Telur Ayam Negeri Berbasis IoT. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5026221140-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (16MB) | Request a copy

Abstract

Ketidakkonsistenan pada pemrosesan klasifikasi telur khususnya telur ayam negeri oleh manusia secara manual sering kali mengakibatkan ketidaksesuaian kualitas telur ayam yang diterima oleh pelanggan. Dalam skala peternakan kecil menengah, kesalahan dalam mengklasifikasi seperti keretakan pada cangkang telur, tingkat kesegaran telur, atau bobot telur yang tidak sesuai Standar Nasional Indonesia (SNI) dapat menurunkan tingkat kepercayaan pelanggan dan dapat berdampak langsung pada pendapatan peternak ayam petelur. Oleh karena itu, dibutuhkan solusi teknologi modern yang dapat mengklasifikasi telur secara konsisten dan akurat supaya kualitas telur terjamin dan pelanggan tidak mengalami kekecewaan karena variabilitas kualitas telur. Penelitian ini mengembangkan sistem klasifikasi telur ayam negeri berbasis Internet of Things (IoT) dengan dibantu Artificial Intellegence (AI) dengan menggunakan roboflow, menggunakan pemrosesan citra, dan menggunakan algoritma Support Vector Machine (SVM). Dalam pemrosesan citra gambar diolah dengan untuk diambil Region of Interest (ROI) dan diolah dengan aturan Hue, Saturation, Value (HSV). Pengambilan gambar menggunakan kamera yang memiliki infrared (IR) yakni AMG8833 untuk mengambil data termal telur dan kamera visual yakni realsense untuk mengambil data Red Green Blue (RGB). Dan untuk data berat telur diambil menggunakan load cell. Sistem dapat mengklasifikasikan telur berdasarkan kondisi cangkang, kesegaran telur, dan berat telur berdasarkan bobot SNI. Selain itu, penelitian ini juga melakukan penyesuaian terhadap kebutuhan peternak dengan aspirasi yang langsung diambil terhadap peternak agar alat mudah digunakan. Hasil pengujian model alat ini sudah cukup optimal dan desain alat ini mudah digunakan oleh peternak. Namun, peningkatan dataset dalam pengembangan alat kedepannya. Sistem ini telah diuji dan mampu bekerja dengan baik dan dapat dikembangkan untuk kebermanfaatan solusi klasifikasi telur ayam negeri bagi peternak telur ayam negeri skala kecil menengah dengan ayam <11.501 ekor.
======================================================================================================================================
Inconsistencies in the manual classification of eggs, especially domestic chicken eggs, often result in discrepancies in the quality of chicken eggs received by customers. In small to medium-sized farms, errors in classification, such as cracks in the eggshell, freshness level, or egg weight that does not meet Indonesian National Standards (SNI), can reduce customer confidence and have a direct impact on the income of egg farmers. Therefore, a modern technological solution is needed that can classify eggs consistently and accurately so that egg quality is guaranteed and customers are not disappointed due to egg quality variability. This study developed a local chicken egg classification system based on the Internet of Things (IoT) with the help of Artificial Intelligence (AI) using Roboflow, image processing, and the Support Vector Machine (SVM) algorithm. In image processing, images were taken from domestic chicken eggs at a small to medium-sized farm in Tuban, East Java, which were then processed to extract the Region of Interest (ROI) and processed using the Hue, Saturation, Value (HSV) rules. Images were captured using an infrared (IR) camera, namely AMG8833, to collect thermal data on the eggs, and a visual camera, namely Realsense, to collect Red Green Blue (RGB) data on the eggs. Egg weight data was collected using a load cell. The system can classify eggs based on shell condition, egg freshness, and egg weight based on SNI standards. Additionally, this research also made adjustments to meet the needs of farmers by directly consulting with them to ensure the device is easy to use. The results of testing this device model are quite optimal, and the device design is easy for farmers to use. However, dataset improvement are needed for future development. This system has been tested and works well and can be developed for the benefit of small to medium-scale domestic chicken egg farmers with fewer than 11,501 chickens.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Seleksi Telur, IoT, AI, Pemrosesan Digital Citra, IR Image, SVM
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	Arkaan Hilmi Suharsoyo
Date Deposited:	29 Jan 2026 08:42
Last Modified:	29 Jan 2026 08:42
URI:	http://repository.its.ac.id/id/eprint/130837

Actions (login required)

View Item