TRIAGANTARA, RAGA (2025) IMPLEMENTASI HYBRID GWO-SCA DENGAN SUPPORT VECTOR MACHINE DAN K-NEAREST NEIGHBOR UNTUK MENGKLASIFIKASI INDEKS POLUSI UDARA PROVINSI DKI JAKARTA. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (563kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (88kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (251kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (84kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (532kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (77kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (146kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (1MB) |
Abstract
Air pollution is a significant environmental and health challenge in the DKI Jakarta Province, Indonesia. Accurate classification of the Air Quality Index (AQI) is crucial for effective monitoring and policy formulation. This study implements a combination of the Hybrid Grey Wolf Optimizer-Sine Cosine Algorithm (GWOSCA) integrated with Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) to classify AQI data in the DKI Jakarta Province. The study evaluates four models—HGWOSCA+SVM, HGWOSCA+KNN, SVM, and KNN—based on performance metrics such as accuracy, precision, recall, and F1-score. The results show that the HGWOSCA+KNN model achieves the highest performance, with an accuracy of 98.774%, precision of 98.774%, recall of 98.775%, and an F1-score of 98.774%. The HGWOSCA+SVM model also improves, achieving an accuracy of 98.36% compared to 94.97% for the non-hybrid SVM model. Additionally, while SVM outperforms KNN in both hybrid and non-hybrid schemes, the GWO-SCA combination significantly enhances the accuracy and reliability of both models. These findings confirm the effectiveness of hybrid optimization techniques in improving machine learning models for environmental data classification. Kata kunci: Hybrid GWO-SCA, SVM, KNN, Optimization , Classification, Air Pollution Index Pencemaran udara merupakan tantangan lingkungan dan kesehatan yang signifikan di Provinsi DKI Jakarta, Indonesia. Klasifikasi yang akurat terhadap Indeks Kualitas Udara (AQI) sangat penting untuk pemantauan yang efektif dan perumusan kebijakan. Penelitian ini menerapkan kombinasi algoritma Hybrid Grey Wolf Optimizer-Sine Cosine Algorithm (GWO-SCA) yang terintegrasi dengan Support Vector Machine (SVM) dan K-Nearest Neighbor (KNN) untuk mengklasifikasikan data AQI di Provinsi DKI Jakarta. Penelitian ini mengevaluasi empat model, yaitu HGWOSCA+SVM, HGWOSCA+KNN, SVM, dan KNN, berdasarkan metrik performa seperti akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model HGWOSCA+KNN mencapai performa tertinggi dengan akurasi sebesar 98,774%, presisi 98,774%, recall 98,775%, dan F1-score 98,774%. Model HGWOSCA+SVM juga meningkatk dengan mencapai akurasi sebesar 98.36%, dibandingkan dengan 94.97% pada model SVM tanpa hybrid. Selain itu, meskipun SVM mengungguli KNN baik dalam skema hybrid maupun tanpa hybrid, kombinasi GWO-SCA secara signifikan meningkatkan akurasi dan keandalan klasifikasi kedua model tersebut. Temuan ini menegaskan efektivitas teknik optimasi hybrid dalam meningkatkan model pembelajaran mesin untuk klasifikasi data lingkungan. Kata kunci: Hybrid GWO-SCA, SVM, KNN, Optimisasi, Klasifikasi, Indeks Polusi Udara.
Actions (login required)
 |
View Item |
