Seleksi Fitur dengan Artificial Bee Colony untuk Optimasi Klasifikasi Data Teh menggunakan Support Vector Machine

https://doi.org/10.22146/ijeis.63902

Suhaila Suhaila(1*)

(1) Universitas Gadjah Mada
(*) Corresponding Author

Abstract


Teh dapat dikenal kualitasnya melalui aroma yang dihasilkan. Penelitian klasifikasi teh menggunakan e-nose umumnya hanya mendeteksi kualitas aroma menggunakan general sensor gas. Namun, adanya redundansi fitur sensor dapat menyebabkan penurunan performa sistem e-nose. Oleh karena itu diperlukan sebuah sistem yang dapat menyeleksi fitur sehingga performa klasifikasi menjadi lebih optimal. Pada penelitian ini dibentuk sistem perangkat lunak yang mampu menyeleksi fitur untuk mengoptimalkan performa klasifikasi. Data input untuk sistem adalah respon sensor e-nose terhadap 3 kualitas teh hitam dengan jumlah sampel 300. Fitur yang diseleksi berupa sensor-sensor pada instrumen e-nose. Proses seleksi fitur dilakukan dengan pendekatan wrapper, algoritma ABC digunakan untuk seleksi fitur, kemudian hasil fitur yang terpilih dievalusi dengan klasifikasi menggunakan SVM. Hasil sistem ABC-SVM kemudian dibandingkan dengan sistem SVM tanpa seleksi fitur. Hasil penelitian menunjukkan bahwa dari 12 sensor e-nose, sensor yang paling mencirikan teh hitam kualitas 1-3 yaitu sensor TGS 2600, TGS 813, TGS 825, TGS 2602, TGS 2611, TGS 832, TGS 2612, TGS 2620 dan TGS 822. Sedangkan untuk sensor MQ-7, TGS 826 dan TGS 2610 merupakan sensor yang redundant pada sistem dikarenakan gas yang dideteksi oleh 3 sensor tersebut dapat diwakili oleh sensor lainnya. Dengan berkurangnya fitur menjadi 9, performa akurasi klasifikasi meningkat 16,7%.

Keywords


Electronics; Instrumentation

Full Text:

PDF


References

N. Bhattacharyya, B. Tudu, R. Bandyopadhyay, M. Bhuya, and R. Mudi, “Aroma characterization of orthodox black tea with electronic nose,” IEEE Reg. 10 Annu. Int. Conf. Proceedings/TENCON, vol. B, pp. 427–430, 2004, doi: 10.1109/tencon.2004.1414623. https://ieeexplore.ieee.org/abstract/document/1414623 [Accessed: 23-Nov-2020]

A. Dutta, B. Tudu, R. Bandyopadhyay, and N. Bhattacharyya, “Black tea quality evaluation using electronic nose: An artificial bee colony approach,” 2011 IEEE Recent Adv. Intell. Comput. Syst. RAICS 2011, no. 2, pp. 143–146, 2011, doi: 10.1109/RAICS.2011.6069290. https://ieeexplore.ieee.org/document/6069290 [Accessed: 23-Nov-2020]

R. Banerjee, P. Chattopadhyay, B. Tudu, N. Bhattacharyya, and R. Bandyopadhyay, “Artificial flavor perception of black tea using fusion of electronic nose and tongue response: A Bayesian statistical approach,” J. Food Eng., vol. 142, pp. 87–93, 2014, doi: 10.1016/j.jfoodeng.2014.06.004. https://www.sciencedirect.com/science/article/abs/pii/S0260877418304102?casa_token=WUzxSYUrZmEAAAAA:oZMha9xUU95Oj0w_EJo2AEBAtURTPYyPrETeZ8Np3i6yfZddyNjGsn0rAoHsboAXHmaGpzZuaQ [Accessed: 14-Nov-2019]

R. Dutta, E. L. Hines, J. W. Gardner, K. R. Kashwan, and M. Bhuyan, “Tea quality prediction using a tin oxide-based electronic nose: An artificial intelligence approach,” Sensors Actuators, B Chem., vol. 94, no. 2, pp. 228–237, 2003, doi: 10.1016/S0925-4005(03)00367-8. https://www.researchgate.net/publication/223495802_Tea_Quality_Prediction_Using_a_Tin_Oxide-based_Electronic_Nose_an_Artificial_Intelligence_Approach [Accessed: 26-Des-2020]

B. Santosa and D. R. Hanum, “Studi komparasi metode klasifikasi dua kelas,” Pros. Semin. Nas. Manaj. Teknol. V, 2007. https://adoc.pub/studi-komparasi-metode-klasifikasi-dua-kelas.html [Accessed: 27-Sep-2019]

Q. Chen, J. Zhao, Z. Chen, H. Lin, and D. A. Zhao, “Discrimination of green tea quality using the electronic nose technique and the human panel test, comparison of linear and nonlinear classification tools,” Sensors Actuators, B Chem., vol. 159, no. 1, pp. 294–300, 2011, doi: 10.1016/j.snb.2011.07.009. https://www.sciencedirect.com/science/article/abs/pii/S0925400511006393 [Accessed: 4-Okt-2019]

S. Jenicka and A. Suruliandi, “Comparative study of classification algorithms with modified multivariate local binary pattern texture model on remotely sensed images,” Int. Conf. Recent Trends Inf. Technol. ICRTIT 2011, pp. 848–852, 2011, doi: 10.1109/ICRTIT.2011.5972312. https://ieeexplore.ieee.org/abstract/document/5972312 [Accessed: 27-Sep-2019]

R. Prakash, V. P. Tharun, and S. Renuga Devi, “A Comparative Study of Various Classification Techniques to Determine Water Quality,” Proc. Int. Conf. Inven. Commun. Comput. Technol. ICICCT 2018, no. Icicct, pp. 1501–1506, 2018, doi: 10.1109/ICICCT.2018.8473168. https://ieeexplore.ieee.org/document/8473168 [Accessed: 17-Sep-2019]

Y. T. Liu and K. T. Tang, “A Minimum Distance Inlier Probability (MDIP) Feature Selection Method to Improve Gas Classification for Electronic Nose Systems,” IEEE Access, vol. 8, pp. 133928–133935, 2020, doi: 10.1109/ACCESS.2020.3010788. https://ieeexplore.ieee.org/abstract/document/9145749 [Accessed: 27-Des-2020]

Y. Lu, I. Cohen, X. S. Zhou, and Q. Tian, “Feature selection using principal feature analysis,” in Proceedings of the 15th international conference on Multimedia - MULTIMEDIA ’07, 2007, p. 301, doi: 10.1145/1291233.1291297. https://ieeexplore.ieee.org/document/5640135 [Accessed: 4-Nov-2019]

D. Karaboga and B. Basturk, “A powerful and efficient algorithm for numerical function optimization: Artificial bee colony (ABC) algorithm,” J. Glob. Optim., vol. 39, no. 3, pp. 459–471, 2007, doi: 10.1007/s10898-007-9149-x. https://www.researchgate.net/publication/225392029_A_powerful_and_efficient_algorithm_for_numerical_function_optimization_Artificial_bee_colony_ABC_algorithm [Accessed: 5-Apr-2019]

B. Basu and G. K. Mahanti, “A comparative study of modified particle swarm optimization, differential evolution and artificial bees colony optimization in synthesis of circular array,” ICPCES 2010 - Int. Conf. Power, Control Embed. Syst., pp. 1–5, 2010, doi: 10.1109/ICPCES.2010.5698614. https://www.researchgate.net/publication/251987264_A_comparative_study_of_Modified_Particle_Swarm_Optimization_Differential_Evolution_and_Artificial_Bees_Colony_optimization_in_synthesis_of_circular_array [Accessed: 10-Sep-2019]

M. Meguellati, F. Srairi, F. Djeffal, and L. Saidi, “Performance analysis of swimming microrobot using GA, ABC and PSO based-optimization techniques,” 2015 4th Int. Conf. Syst. Control. ICSC 2015, pp. 310–314, 2015, doi: 10.1109/ICoSC.2015.7153277. https://ieeexplore.ieee.org/document/7153277 [Accessed: 13-Sep-2019]

D. Lelono, “Pengembangan Instrumentasi Sistem Electronic Nose untuk Uji Teh Hitam Lokal. Universitas Gadjah Mada,” Universitas Gadjah Mada, 2017.

M. Monirul Kabir, M. Monirul Islam, and K. Murase, “A new wrapper feature selection approach using neural network,” Neurocomputing, vol. 73, no. 16–18, pp. 3273–3283, 2010, doi: 10.1016/j.neucom.2010.04.003. https://www.sciencedirect.com/science/article/abs/pii/S0925231210001979 [Accessed: 11-Des-2020]



DOI: https://doi.org/10.22146/ijeis.63902

Article Metrics

Abstract views : 248 | views : 388

Refbacks

  • There are currently no refbacks.




Copyright (c) 2022 IJEIS (Indonesian Journal of Electronics and Instrumentation Systems)

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.



Copyright of :
IJEIS (Indonesian Journal of Electronics and Instrumentations Systems)
ISSN 2088-3714 (print); ISSN 2460-7681 (online)
is a scientific journal the results of Electronics
and Instrumentations Systems
A publication of IndoCEISS.
Gedung S1 Ruang 416 FMIPA UGM, Sekip Utara, Yogyakarta 55281
Fax: +62274 555133
email:ijeis.mipa@ugm.ac.id | http://jurnal.ugm.ac.id/ijeis



View My Stats1
View My Stats2