Optimasi Seleksi Fitur Menggunakan Algoritma Hybrid ARO-DBSCAN untuk Meningkatkan Akurasi Model Klasifikasi K-Nearest Neighbor: Feature Selection Optimization Using the Hybrid ARO-DBSCAN Algorithm to Improve the Accuracy of the K-Nearest Neighbor Classification Model

Florentina Yuni Arini; Josephin Nova Bagaskara; Alfani Salsabilla Anwar; Muhammad Najmuddin Faqih; Prayoga Adi Brata; Nadhia Adzqiya khairunnisa; Yusuf Pandu Satrio Aji

doi:10.57152/malcom.v6i1.2129

Authors

Florentina Yuni Arini Universitas Negeri Semarang
Josephin Nova Bagaskara Universitas Negeri Semarang
Alfani Salsabilla Anwar Universitas Negeri Semarang
Muhammad Najmuddin Faqih Universitas Negeri Semarang
Prayoga Adi Brata Universitas Negeri Semarang
Nadhia Adzqiya khairunnisa Universitas Negeri Semarang
Yusuf Pandu Satrio Aji Universitas Negeri Semarang

DOI:

https://doi.org/10.57152/malcom.v6i1.2129

Keywords:

ARO-DBSCAN, K-Nearest Neighbor, Optimasi Hybrid, Pemilihan Fitur

Abstract

Penelitian ini mengusulkan metode ARO-DBSCAN, sebuah pendekatan hybrid yang menggabungkan algoritma optimasi Artificial Rabbits Optimization (ARO) dengan teknik clustering Density-Based Spatial Clustering of Applications with Noise (DBSCAN) untuk pemilihan fitur yang lebih efektif. Hasil eksperimen menunjukkan bahwa ARO-DBSCAN secara konsisten mengungguli metode ARO dan AROD, dengan peningkatan akurasi klasifikasi pada 13 dari 18 dataset (populasi 15) dan 12 dataset (populasi 30), sekaligus mampu memilih fitur lebih sedikit tanpa mengurangi kualitas model. Dibandingkan dengan algoritma hybrid lain seperti GA-DBSCAN dan PSO-DBSCAN, ARO-DBSCAN tetap lebih unggul berkat kemampuan clustering DBSCAN yang mengelompokkan solusi serupa, sehingga mempercepat pencarian solusi optimal dan menghindari terjebak di solusi lokal. Temuan ini membuktikan bahwa integrasi teknik metaheuristik dengan clustering berbasis kepadatan dapat menjadi solusi efisien untuk pemilihan fitur pada data berdimensi tinggi di era big data.

Downloads

Download data is not yet available.

References

R. Dwivedi, A. Tiwari, N. Bharill, dan M. Ratnaparkhe, "A Novel Clustering-Based Hybrid Feature Selection Approach Using Ant Colony Optimization,"Arabian Journal for Science and Engineering, vol. 48, pp. 10727–10744, 2023.

I. P. S. Almantara, N. W. S. Aryani, dan I. B. A. Swamardika, "Spatial Data Analysis using DBSCAN Method and K-NN classification,"International Journal of Engineering and Emerging Technology, vol. 5, no. 2, pp. 77–80, 2020.

R. Wibowo, M. A. Soeleman, dan A. Affandy, "Hybrid Top-K Feature Selection to Improve High-Dimensional Data Classification Using Naïve Bayes Algorithm,"Scientific Journal of Informatics, vol. 10, no. 2, 2023.

M. Rostami, K. Berahmand, dan S. Forouzandeh, "Review of Swarm Intelligence-based Feature Selection Methods," Engineering Applications of Artificial Intelligence, vol. 100, p. 104210, 2021.

F. Amini dan G. Hu, "A Hybrid Two-layer Feature Selection Method Using Genetic Algorithm and Elastic Net," arXiv preprint arXiv:2001.11177, 2021.

L. Sun et al., "Adaptive Feature Selection Guided Deep Forest for COVID-19 Classification with Chest CT," arXiv preprint arXiv:2005.03264, 2020.

T. Silwattananusarn, W. Kanarkard, dan K. Tuamsuk, "Enhanced Classification Accuracy for Cardiotocogram Data with Ensemble Feature Selection and Classifier Ensemble," arXiv preprint arXiv:2010.14051, 2020.

A. Jiménez-Cordero, J. M. Morales, dan S. Pineda, "A Novel Embedded Min-Max Approach for Feature Selection in Nonlinear Support Vector Machine Classification," arXiv preprint arXiv:2004.09863, 2021.

E. O. Abiodun et al., "A Systematic Review of Emerging Feature Selection Optimization Methods for Optimal Text Classification: The Present State and Prospective Opportunities," Neural Computing and Applications, vol. 33, no. 22, pp. 15119–15148, 2021.

Zhang et al., “Artificial Rabbits Optimization Algorithm for Engineering Problems,”IEEE Transactions on Evolutionary Computation, vol. 24, no. 5, pp. 789–803, 2020.

Wang et al., “Hybrid Metaheuristic Optimization with Rabbit-Inspired Search,” Springer Nature, Applied Soft Computing, vol. 96, 2020.

Chen & Liu, “Exploration-Exploitation Balance in Metaheuristics,” IEEE Access, vol. 8, pp. 123456–123468, 2020.

Li et al., “Adaptive Parameter Control in Swarm Intelligence,” Springer, Swarm Intelligence, 2021.

Ester et al., “A Density-Based Algorithm for Discovering Clusters,” KDD, 2020.

Sander et al., “Density-Based Clustering Validation Methods,” IEEE Transactions on Knowledge and Data Engineering, 2021.

Ahmed et al., “Efficient Euclidean Distance Computation for Clustering,” IEEE Big Data Conference, 2020.

Han et al., “An Improved K-NN Classifier with Manhattan Distance,” Springer, Expert Systems with Applications, 2021.

Zhao & Zhang, “K-NN Classification and Distance Metrics Analysis,” IEEE Transactions on Neural Networks and Learning Systems, 2022.

Kumar et al., “Data Normalization Techniques in Machine Learning,” Springer Data Science, 2021.

Huang et al., “Performance Metrics in Classification Problems,” IEEE Access, 2020.

Patel & Shah, “Evaluation Metrics for Imbalanced Data,” Springer Journal of Big Data, 2021.

Singh & Gupta, “Parameter Optimization in Metaheuristics,” IEEE Transactions on Systems, Man, and Cybernetics, 2020.

Lee et al., “Optimizing K-NN Parameters for High-Dimensional Data,” Springer Pattern Recognition Letters, 2022.

R. Kamal, E. Amin, D. S. AbdElminaam and R. Ismail, "A Comprehensive Survey on Meta-Heuristic Algorithms for Feature Selection in High-Dimensional Data: Challenges, Applications, and Future Directions," International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), 2024.

Lee et al., “Optimizing K-NN Parameters for High-Dimensional Data,” Springer Pattern Recognition Letters, 2022.