Electronic nose for classifying civet coffee and non-civet coffee. (English) Zbl 07814854
Summary: Several Electronic Nose (E-nose) studies on coffee classification have been conducted. The E-nose uses gas sensors to detect the aroma of coffee and generate signals. Then the signals are classified using machine learning algorithms. In this study, the E-nose used five gas sensors to classify civet coffee and non-civet coffee, and the machine learning algorithms used were SVM, KNN and Decision Tree. The coffee variant used was Arabica coffee with the types of civet coffee (kopi luwak) and non-civet coffee (kopi non-luwak) originating from Aceh, Arjuno Malang, Bengkulu. In this study, the mixture of civet coffee and non-luwak coffee was made with a percentage of \(100:0\), \(90:10\), \(10:90\), \(80:20\), \(20:80\), \(75:25\), \(25:75\), \(50:50\). The accuracy of the classification of Aceh civet coffee (LA) and Aceh non-civet coffee (NLA) was 90% (SVM), 100% (KNN), 100% (Decision Tree). The accuracy of the classification of Arjuno civet coffee (LAR) and Arjuno non-civet coffee (NLAR) was 100% (SVM, KNN, Decision Tree). The accuracy of the classification of Bengkulu civet coffee (LB) and Bengkulu non-civet (NLB) was 45% (SVM), 100% (KNN, Decision Tree). And the accuracy of coffee mixture classification (Aceh civet and Aceh non-civet) was 90% (SVM), 93.75% (KNN), and 95% (Decision Tree). The accuracy level obtained was affected by the age of coffee storage, the data collection process when detecting the coffee aroma, and the number of class attributes used.
MSC:
| 62H30 | Classification and discrimination; cluster analysis (statistical aspects) |
| 68W40 | Analysis of algorithms |
| 68Q17 | Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) |
References:
| [1] | M. I. Sofyan and T. E. Sebayang. Investigation of Coffee Export Dynamics in Indonesia. Jurnal Bisma Unesa 11 (1) (2018) 67-76. |
| [2] | S. A. W. Kristanti and R. Sutamih. Tingkat Kematangan Biji Kopi Arabika (Coffee arabica L) dalam Menghasilkan Kadar Kafein. Sain Natural 9 (1) (2019) 22-28. |
| [3] | D. R. Wijaya, R. Samo and E. Zulaika. Sensor Array Optimization for Mobile Electronic Nose: Wavelet Transform and Filter Based Feature Selection Approach. International Re-view on Computers and Software (I.RE.CO.S.) 11 (8) (2016) 659-671. |
| [4] | D. R. Wijaya, R. Samo and E. Zulaika. Information Quality Ratio as a novel metric for mother wavelet selection. Elsevier, Chemometrics and Intelligent Laboratory Systems 160 (2017) 59-71. |
| [5] | D. Giacalonea, T. D. Kreuzfeldt, N. Yang, C. Liu and I. Fisk. Common roasting defects in coffee: Aroma composition, sensory characterization and consumer perception. Elsevier (2018) 1-12. |
| [6] | J. Towaha and B. T. Eka. Kopi Luwak Budidaya Sebagai Diversifikasi Produk Yang Mem-punyai Citarasa Khas. SIRINOV 3 (1) (2015) 19-30. |
| [7] | E. Wahyuni, A. Karim and A. Anhar. Analysis of Taste Quality of Organic Arabica Coffee in Several Altitudes and Processing Techniques in Gayo Highlands. Jurnal Manajemen Sumberdaya Lahan 2 (3) (2013) 261-269. |
| [8] | A. T. Toci and M. V. Z. Boldrin. Coffee Beverages and Their Aroma Compounds. Natural and Artificial Flavoring Agents and Food Dyes, Elsevier (2018) 379-423. |
| [9] | K. C. Hsu, T. H. Fang, Y. J. Hsiao and P. C. Wu. Response and Characteristics of TiO2/Perovskite Heterojunctions for CO Gas Sensors. Journal of Alloys and Compounds 1 (1) (2019) 2-39. |
| [10] | R. Radi, S. Ciptohadijoyo, W. S. Litananda, M. Rivai and M. H. Purnomo. Electronic Nose Based on Partition Column Integrated With Gas Sensor for fruit Identification and Classification. Yogyakarta, Indonesia, 2016. |
| [11] | U. Jumhawan, S. Prama Putri, Y. T. Bamba and E. F. Application of gas chromatogra-phy/flame ionization detector-based metabolite fingerprinting for authentication of Asian palm civet coffee (Kopi Luwak). Journal of Bioscience and Bioengineering 20 (20) (2015) 1-7. |
| [12] | V. Vapnik. Support Vector Networks. Kluwer Academic Publishers, Boston. Manufactured in The Netherlands (1995) 273-297. · Zbl 0831.68098 |
| [13] | F. R. Rozak. Flowing System Design of Indirect Elektronic Nose to Tea Aroma Dedection. Universitas Gadjah Mada, Yogyakarta, Indonesia, 2015. |
| [14] | S. S. Izza, R. Sarno and J. Siswantoro. Estimating Gas Concentration using Artificial Neural Network for Electronic Nose. In: Elsevier, 4th Information Systems International Confer-ence (ISICO 2017) Bali, Indonesia, 2017. |
| [15] | H. Hanwei. Technical Data MQ135, MQ4, MQ7, MQ2 and MQ3 Gas Sensor. http://www.hwsensor.com. Hanwei Electronics Group Corporation, 1998. |
| [16] | D. W. Rahman , R. Sarno and E. Zulaika. Gas Concentration Analysis of Resistive Gas Sensor Array. International Symposium on Electronics and Smart Devices (ISESD) (2017) 337-342. |
| [17] | D. B. Magfira and R. Sarno. Classification Of Arabika and Robusta Coffee Using Elektronic Nose. In: ICOIACT Yogyakarta, Indonesia, 2018. |
| [18] | S. Baskara, D. Lelono and T. W. Widodo. Pengembangan Hidung Elektronik untuk Klasi-fikasi Mutu Minyak Goreng dengan Metode Principal Component Analysis. IJEIS 6 (2) (2016) 221-230. |
| [19] | R. Sarno and D. W. Rahman. Recent Development in Electronic Nose Data Processing for Beef Quality Assessment. Telkomnika 17 (1) (2019) 337-348. |
| [20] | F. Chamim. https://mlgcoffee.com/2014/09/19/definisi-kopi-dan-sejarah-penyebaran-kopi-di-dunia/. 27 February 2014. [Online]. [Accessed 2019]. |
| [21] | Y. W. Teniro, Z. Zulfan and H. Husaini. Perkembangan Pengolahan Kopi Arabika Gayo Mulai Dari Panen Hingga Pasca Panen Di Kampung Simpang Teritit Tahun 2010-2017. Jurnal Ilmiah Mahasiswa (JIM) Pendidikan Sejarah FKIP Unsyiah 3 (3) (2018) 52-63. |
| [22] | D. Listyati, B. Sudjarmoko and A. M. Hasibua. Farming Analysis and Marketing Chain of Robusta Coffee in Bengkulu. Jurnal of Industrial and Beverage Crops 4 (3) (2017) 145-154. |
| [23] | T. Ada. https://www.timesindonesia.co.id/read/187708/20181028/000141/kopi-arabika-arjuno-kopi-unggulan-dari-malang/. 29 April 2019. [Online]. [Accessed 2019]. |
| [24] | M. F. Marcone. Composition and properties of Indonesian palm civet coffee (Kopi Luwak) and Ethiopian civet coffee. Elsevier Canada, 2004. |
| [25] | R. Rubiyo and J. Towaha. The Effect of Fermentation on Flavor Quality of Probiotic Civet Coffee. RISTI 4 (2) (2013) 175-182. |
| [26] | T. Herlambang, H. Nurhadi, A. Muhith, A. Suryowinoto, and K. Oktafianto. Estimation of Forefinger Motion with Multi-DOF Using Advanced Kalman Filter. Nonlinear Dynamics and Systems Theory. 23 (1) (2023) 24-33. · Zbl 1524.93066 |
| [27] | A. Lukman and M. Marwana. Machice Learning Multi Klasifikasi Citra Digital. Konfrensi Nasional Ilmu Komputer (KONIK) Makassar, 2014. |
| [28] | M. Jupri and R. Sarno. Taxpayer Compliance Classification Using C4.5, SVM, KNN, Naive Bayes and MLP. ICOIATC Yogyakarta, 2017. |
| [29] | R. Sarno, J. A. Ridoean and D. Sunaryono. Classification of Music Mood Using MPEG-7 Audio Features and SVM with Confidence Interval. International Journal on Artificial Intelligence Tools, World Scientific Publishing Company 27 (5) (2018) 1-18. |
| [30] | K. Oktafianto, A. Z. Arifin, E. F. Kurniawati, T. Herlambang and F. Yudianto. Tsunami Wave Simulation in the Presense of a Barrier. Nonlinear Dynamics and Systems Theory. 23 (1) (2023) 69-78. · Zbl 1524.86028 |
| [31] | J. Gou, H. Ma, W. Ou, S. Zeng and Y. Rao. A Generalized Mean Distance-Based K-Nearest Neighbor Classifier. ELSEVIER, Expert Systems with Applications 115 (1) (2018) 356-372. |
| [32] | K. Zhao and C. Huang. Air Combat Situation Assessment for UAV Based on Improved Decision Tree. Chinese Control And Decision Conference (CCDC) Shenyang, China, 2018. |
| [33] | J. Gou, W. Qiu, Z. Yi and X. Shen. Locality Constrained Representation-Based K-Nearest Neighbor Classification. Knowledge-Based Systems 167 (1) (2019) 38-52. |
| [34] | A. Utku, I. D. Alper and M. A. Akcayol. Decision Tree Based Android Malware Detec-tion System. Signal Processing and Communications Applications Conference (SIU) Izmir, Turkey, 2018. |
| [35] | H. Elaidi, Y. Elhaddar, Z. Benabbou and H. Abbar. An Idea of a Clustering Algorithm using Support Vector Machines Based on Binary Decision Tree. International Conference on Intelligent Systems and Computer Vision (ISCV) Fez, Maroko, 2018. |
| [36] | M. Y. Anshori, I. H. Santoso, T. Herlambang, K. Oktafianto and P. Katias. Forecasting of Occupied Rooms in the Hotel Using Linear Support Vector Machine. Nonlinear Dynamics and Systems Theory. 23 (2) (2023) 129-140. |
| [37] | E. S. Sankari and D. Manimegalai. Predicting Membrane Protein Types Using Various Deci-sion Tree Classifiers Based on Various Modes of General PseAAC for Imbalanced Datasets. Journal of Theoretical Biology 435 (12) (2018) 208-217. |
| [38] | A. Luque, A. Carrasco, A. Martin and A. H. Las. The Impact of Class Imbalance in Classi-fication Performance Metrics Based on the Binary Confusion Matrix. Pattern Recognition 91 (6) (2019) 216-231. |
| [39] | S. Ruuska, W. Hamalainen, S. Kajava and M. Mughal. Evaluation of the Confusion Matrix Method in the Validation of an Automated System for Measuring Feeding Behaviour of Cattle. Behavioural Processes 148 (4) (2018) 56-62. |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
