Peningkatan Akurasi Klasifikasi Kemurnian Daging Sapi Berbasis Electronic Nose Dengan Menggunakan Ensemble Method

Ulhaq, Azzam Jihad (2021) Peningkatan Akurasi Klasifikasi Kemurnian Daging Sapi Berbasis Electronic Nose Dengan Menggunakan Ensemble Method. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 05111740000132-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (2MB) | Request a copy

Abstract

Daging sapi merupakan salah satu jenis daging yang sering dikonsumsi oleh manusia. Namun, pencampuran jenis daging sapi dengan daging lainnya seperti daging babi dilakukan dalam praktik jual beli dalam rangka mendapatkan keuntungan yang lebih. Hal ini tidak hanya mengurangi kepercayaan publik tentang keaslian daging juga membahayakan kesehatan dan melanggar aturan-aturan agam tertentu. Dalam penelitian ini, kami merancang dan mengusulkan sistem yang lebih akurat dalam melakukan klasifikasi kemurnian daging sapi berdasarkan data sampel aroma yang ditangkap oleh electronic nose.
Sistem ini dibangun melalui tujuh tahap: pengambilan sampel data menggunakan electronic nose yang dibuat dari sensor gas dan Arduino; praproses data sensor; ekstraksi fitur statistik; hyperparameter tunning; seleksi fitur menggunakan ANOVA; klasifikasi menggunakan metode SVM, LDA dan MLP; dan peningkatan akurasi menggunakan ensemble method.
Hasil penelitian menunjukkan bahwa sistem ini dapat membedakan daging sapi yang dicampur dengan daging babi dengan perbandingan 0%, 10%, 25%, 50%, 75%, 90%, dan 100% dengan akurasi 89,71% menggunakan Bagging MLP.
======================================================================================================
Beef is a type of meat that is often consumed by humans.
However, mixing types of beef with other meats such as pork is
carried out in buying and selling to get more profit. The
adulteration undermines public belief in meat's authenticity and
harms health, and violates specific religious rules. In this study, we
designed and proposed a more accurate system for classifying beef
purity based on the aroma sample data captured by the electronic
nose.
This system has seven stages: data sampling using an
electronic nose made from the gas sensor and Arduino;
preprocessing sensor data; statistical feature extraction;
hyperparameter tunning; feature selection using ANOVA;
classification using the SVM, LDA, and MLP methods; and
improved accuracy using the ensemble method.
The results showed that this system could distinguish beef
mixed with pork with a ratio of 0%, 10%, 25%, 50%, 75%, 90%,
and 100% with an accuracy of 89.71% using Bagging MLP.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	electronic nose, klasifikasi, ensemble method, optimasi, classification, ensemble method, optimization
Subjects:	T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > T Technology (General) > T58.62 Decision support systems
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Mr Azzam Jihad Ulhaq
Date Deposited:	03 Aug 2021 01:59
Last Modified:	03 Aug 2021 01:59
URI:	http://repository.its.ac.id/id/eprint/84701

Actions (login required)

View Item