Implementasi Backpropagation Neural Network pada Sistem Electronic Nose untuk Klasifikasi Aroma Teh
Abstract
Conventional tea aroma quality assessment is subjective and slow. This study aims to design and implement an Arduino Uno-based automatic Electronic Nose (e-nose) system with a TGS sensor array (880, 826, 822, 825) combined with a Backpropagation Neural Network (BPNN) for tea aroma classification. The method includes signal acquisition, normalization, feature extraction, and sensor correlation analysis to form a chemical fingerprint before modeling. Testing with a confusion matrix on three types of tea (black, green, and jasmine) showed performance with an accuracy of 0.71, precision of 0.71, recall of 0.72, and f-measure of 0.71. The results of this study provide an objective, fast, economical, and non-destructive aroma evaluation method and contribute to the development of smart sensor technology to support the competitiveness of Indonesian tea products. The main novelty of this study is the integration of sensor correlation analysis into the modeling pipeline with an end-to-end classification system that combines sensor correlation analysis to optimize the performance of the BPNN model on the tea aroma dataset.
Keywords: Arduino; Tea Aroma; Backpropagation; Electronic Nose; TGS Sensor
Abstrak
Penilaian mutu aroma teh secara konvensional bersifat subjektif dan lambat. Penelitian ini bertujuan merancang dan mengimplementasikan sistem Electronic Nose (e-nose) otomatis berbasis Arduino Uno dengan array sensor TGS (880, 826, 822, 825) yang dikombinasikan Backpropagation Neural Network (BPNN) untuk klasifikasi aroma teh. Metode mencakup akuisisi sinyal, normalisasi, ekstraksi fitur, dan analisis korelasi sensor untuk membentuk chemical fingerprint sebelum pemodelan. Pengujian dengan confusion matrix pada tiga jenis teh (hitam, hijau, wangi melati) menunjukkan performa dengan akurasi 0,71, presisi 0,71, recall 0,72, dan f-measure 0,71. Hasil penelitian memberikan metode evaluasi aroma yang objektif, cepat, ekonomis, dan non destruktif, serta berkontribusi pada pengembangan teknologi sensor cerdas untuk mendukung daya saing produk teh Indonesia. Kebaruan utama penelitian ini adalah pada integrasi analisis korelasi sensor ke dalam pipeline pemodelan dengan sistem klasifikasi end-to-end yang menggabungkan analisis korelasi sensor untuk mengoptimalkan performa model BPNN pada dataset aroma teh.
Kata kunci: Arduino; Aroma Teh; Backpropagation; Electronic Nose; Sensor TGS
References
A. A. Br Barus and Irsal, “Pengaruh Iklim terhadap Produktivitas Tanaman Teh (Camellia sinensis L.) di Perkebunan Bah Butong Tahun 2017-2021,” JURNAL AGROTEKNOLOGI, vol. 12, no. 1, pp. 7–13, Jan. 2024, doi: 10.32734/ja.v12i1.20566.
B. Rifai, “Implementasi Arduino Uno dan ATmega328P Untuk Perancangan Alat Keamanan Sepeda Motor,” JSAI (Journal Scientific and Applied Informatics), vol. 2, no. 2, pp. 144–148, Jun. 2019, doi: 10.36085/jsai.v2i2.235.
Y. izzah Sutita and H. Irwan, “Perancangan Arduino Uno pada Design Mesin Pick and Place Sorting Colour Automation untuk Meningkatkan Produktivitas,” Journal of Manufacturing in Industrial Engineering & Technology, vol. 3, no. 2, pp. 72–82, Dec. 2024, doi: 10.30651/mine-tech.v3i2.23987.
A. Sitompul, B. H. Iswanto, and W. Indrasari, “Analisis cluster bahan herbal berdasarkan fitur respon e-nose,” in Prosiding Seminar Nasional Fisika (SNF), 2020, pp. 2339-0654, doi: 10.21009/03.SNF2020.01.FA.22.
K. O. Kombo et al., “Enhancing classification rate of electronic nose system and piecewise feature extraction method to classify black tea with superior quality,” Sci. Afr., vol. 24, p. e02153, Jun. 2024, doi: 10.1016/j.sciaf.2024.e02153.
Z. Hasanati and Dwiny Meidelfi, “Kajian Implementasi Jaringan Syaraf Tiruan Metode Backpropagation Untuk Deteksi Bau,” Journal of Applied Computer Science and Technology, vol. 1, no. 2, pp. 90–95, Dec. 2020, doi: 10.52158/jacost.v1i2.113.
Z. Li, Z. Gao, J. Yu, H. Shi, J. Ling, and G. Zhang, “Applications of E-nose, GC-MS, and GC-IMS in tea volatile components analysis,” Journal of Food Composition and Analysis, vol. 149, p. 108764, Jan. 2026, doi: 10.1016/j.jfca.2025.108764.
D. Yu and Y. Gu, “A Machine Learning Method for the Fine-Grained Classification of Green Tea with Geographical Indication Using a MOS-Based Electronic Nose,” Foods, vol. 10, no. 4, p. 795, Apr. 2021, doi: 10.3390/foods10040795.
K. Kaya and M. A. Ebeoğlu, “Development of a Neural Network for Target Gas Detection in Interdigitated Electrode Sensor-Based E-Nose Systems,” Sensors, vol. 24, no. 16, p. 5315, Aug. 2024, doi: 10.3390/s24165315.
S. Kaushal, P. Nayi, D. Rahadian, and H.-H. Chen, “Applications of Electronic Nose Coupled with Statistical and Intelligent Pattern Recognition Techniques for Monitoring Tea Quality: A Review,” Agriculture, vol. 12, no. 9, p. 1359, Sep. 2022, doi: 10.3390/agriculture12091359.
A. A. Br Barus and Irsal, “Pengaruh Iklim terhadap Produktivitas Tanaman Teh (Camellia sinensis L.) di Perkebunan Bah Butong Tahun 2017-2021,” Jurnal Agroteknologi, vol. 12, no. 1, pp. 7–13, Jan. 2024, doi: 10.32734/ja.v12i1.20566.
W. B. Gonçalves et al., “Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey,” Applied Sciences, vol. 13, no. 8, p. 4881, Apr. 2023, doi: 10.3390/app13084881.
Suryanto, Data Mining untuk Klasifikasi dan Klasterisasi Data. Bandung: Informatika, 2019. Accessed: Jan. 06, 2026. [Online]. Available: https://www.gramedia.com/products/data-mining-edisi-revisi
Ben Yahia, I. Kadir, A. Abdallaoui, and K. Elazhari, “Architectural optimization of a multilayer perceptron (MLP) neural network enhanced by the Levenberg–Marquardt algorithm for predicting relative humidity: Application to Tangier, Morocco,” Water SA, vol. 51, no. 3, pp. 279-287, Jul. 2025, doi: 10.17159/wsa/2025.v51.i3.4160.
K.-T. Tang, S.-W. Chiu, C.-H. Pan, H.-Y. Hsieh, Y.-S. Liang, and S.-C. Liu, “Development of a Portable Electronic Nose System for the Detection and Classification of Fruity Odors,” Sensors, vol. 10, no. 10, pp. 9179–9193, Oct. 2010, doi: 10.3390/s101009179.
B. J. Erickson and B. Bartholmai, “Computer-Aided Detection and Diagnosis at the Start of the Third Millennium,” J. Digit. Imaging, vol. 15, no. 2, pp. 59–68, Jun. 2002, doi: 10.1007/s10278-002-0011-x.
G. Adam, S. Lemaigre, A.-C. Romain, J. Nicolas, and P. Delfosse, “Evaluation of an electronic nose for the early detection of organic overload of anaerobic digesters,” Bioprocess Biosyst. Eng., vol. 36, no. 1, pp. 23–33, Jan. 2013, doi: 10.1007/s00449-012-0757-6.
How To Cite This :
Refbacks
- There are currently no refbacks.
