Penerapan Machine Learning Untuk Klasifikasi Tingkat Kesegaran Udang Vaname Berdasarkan Data Sensor

Ruhi, Sendy Aryan (2026) Penerapan Machine Learning Untuk Klasifikasi Tingkat Kesegaran Udang Vaname Berdasarkan Data Sensor. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2039221021-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Udang vaname (Litopenaeus vannamei) merupakan salah satu komoditas perikanan bernilai ekonomi tinggi dan memiliki permintaan pasar yang luas, namun mudah mengalami penurunan kualitas akibat proses biokimia dan aktivitas mikroorganisme. Penurunan mutu tersebut menghasilkan berbagai senyawa volatil yang dapat dijadikan sebagai indikator tingkat kesegaran udang. Penilaian tingkat kesegaran umumnya masih dilakukan secara tradisional menggunakan indra penciuman manusia sehingga bersifat subjektif dan kurang konsisten karena dipengaruhi oleh pengalaman serta kondisi fisik penilai. Untuk mengatasi permasalahan tersebut, penelitian ini menerapkan metode Artificial Neural Network (ANN) untuk mengklasifikasikan tingkat kesegaran udang vaname berdasarkan data sensor yang diperoleh dari sistem electronic nose. Data hasil pembacaan sensor terlebih dahulu melalui tahap prapemrosesan sebelum digunakan untuk membangun model ANN, kemudian performa model dievaluasi menggunakan confusion matrix. Hasil penelitian menunjukkan bahwa model ANN mampu mengklasifikasikan tingkat kesegaran udang vaname dengan akurasi sebesar 90,56%, presisi 91,72%, recall 90,56%, dan F1-score 90,49%. Hasil tersebut menunjukkan bahwa model yang dikembangkan memiliki kemampuan klasifikasi yang sangat baik dalam membedakan tingkat kesegaran udang berdasarkan pola respons sensor. Penelitian ini menunjukkan bahwa penerapan machine learning berbasis ANN berpotensi menjadi metode yang objektif dan akurat untuk mendukung pengawasan mutu produk perikanan, sehingga dapat meningkatkan efektivitas pengendalian mutu dan keamanan pangan. Selain itu, hasil penelitian ini diharapkan dapat menjadi referensi dalam pengembangan sistem identifikasi kesegaran produk perikanan berbasis electronic nose dan kecerdasan buatan pada penelitian selanjutnya.
============================================================
=========================================================================
Whiteleg shrimp (Litopenaeus vannamei) is a fishery commodity with high economic value and has a wide market demand, but it is easily degraded due to biochemical processes and microorganism activity. This quality degradation produces various volatile compounds that can be used as indicators of shrimp freshness. Freshness assessment is generally still carried out traditionally using the human sense of smell so it is subjective and less consistent because it is influenced by the experience and physical condition of the assessor. To overcome this problem, this study applies the Artificial Neural Network (ANN) method to classify the freshness level of whiteleg shrimp based on sensor data obtained from the electronic nose system. The sensor reading data first goes through a preprocessing stage before being used to build the ANN model, then the model performance is evaluated using a confusion matrix. The results show that the ANN model is able to classify the freshness level of whiteleg shrimp with an accuracy of 90,56%, a precision of 91,72%, a recall of 90,56%, and an F1-score of 90,49%. These results indicate that the developed model has excellent classification capabilities in distinguishing shrimp freshness levels based on sensor response patterns. This research demonstrates that the application of ANN-based machine learning has the potential to be an objective and accurate method to support fishery product quality control, thereby increasing the effectiveness of quality control and food safety. Furthermore, the results of this study are expected to serve as a reference in the development of an electronic nose and artificial intelligence-based fishery product freshness identification system in future research.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Udang Vaname, Electronic Nose, Machine Learning, ANN, Confusion Matrix
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7871.674 Detectors. Sensors
Divisions:	Faculty of Vocational > Mechanical Industrial Engineering (D4)
Depositing User:	Sendy Aryan Ruhi
Date Deposited:	30 Jul 2026 06:36
Last Modified:	30 Jul 2026 06:36
URI:	http://repository.its.ac.id/id/eprint/139769

Actions (login required)

View Item