Perbandingan Akurasi Algoritma Naïve Bayes dan Support Vector Machine Untuk Pencemaran Udara Di DKI Jakarta

HAIKAL, MUHAMMAD IKHSAN (2022) Perbandingan Akurasi Algoritma Naïve Bayes dan Support Vector Machine Untuk Pencemaran Udara Di DKI Jakarta. S1 thesis, Universitas Mercu Buana.

Preview	Text (HAL COVER) 01 Cover.pdf Download (1MB) | Preview
Preview	Text (ABSTRAK) 02 Abstrak.pdf Download (23kB) | Preview
	Text (BAB 1) 03 Bab 1.pdf Restricted to Registered users only Download (369kB)
	Text (BAB 2) 04 Bab 2.pdf Restricted to Registered users only Download (984kB)
	Text (BAB 3) 05 Bab 3.pdf Restricted to Registered users only Download (358kB)
	Text (BAB 4) 06 Bab 4.pdf Restricted to Registered users only Download (372kB)
	Text (BAB 5) 07 Bab 5.pdf Restricted to Registered users only Download (530kB)
	Text (BAB 6) 08 Bab 6.pdf Restricted to Registered users only Download (595kB)
	Text (DAFTAR PUSTAKA) 09 Daftar Pustaka.pdf Restricted to Registered users only Download (333kB)
	Text (LAMPIRAN) 10 Lampiran.pdf Restricted to Registered users only Download (419kB)

Abstract

Air pollution is a decrease in air quality so that the air experiences a decrease in quality in its use which ultimately can no longer be used as it should according to its function. This study aims to determine the application of the Naïve Bayes algorithm and Support Vector Machine to obtain good accuracy results in predicting the level of air pollution in DKI Jakarta. With the application of the Naïve Bayes algorithm and Support Vector Machine for predicting the level of air pollution, it is hoped that it can reduce casualties and other losses caused by this air pollution. And can facilitate the DKI Jakarta provincial government in making decisions on the right steps to solve air pollution problems in the DKI Jakarta area. The Support Vector Machine algorithm has better results with an average accuracy rate of 98.5% with an average level of precision, recall and f1-score of 92.58%, 98.75%, 95%. Meanwhile, the Naïve Bayes algorithm only obtained an accuracy of 87.75% with an average level of precision, recall, and f1-score of 73.5%, 91.16%, 77.6%. The results produced by the two algorithms are also influenced by the large amount of training data and test data. Key words: Naïve Bayes, SVM, Classification, Air pollution Pencemaran udara adalah turunnya kualitas udara sehingga udara mengalami penurunan mutu dalam penggunaannya yang akhirnya tidak dapat digunakan lagi sebagaimana mestinya sesuai fungsinya. Penelitian ini bertujuan untuk mengetahui penerapan algoritma Naïve Bayes dan Support Vector Machine untuk mendapatkan hasil akurasi yang baik dalam memprediksi tingkat pencemaran udara di DKI Jakarta. Dengan adanya penerapan algoritma Naïve Bayes dan Support Vector Machine untuk prediksi tingkat pencemaran udara, diharapkan dapat mengurangi korban jiwa dan kerugian-kerugian lain yang disebabkan oleh penecemaran udara ini. Serta dapat memudahkan pemerintah provinsi DKI Jakarta dalam pengambilan keputusan langkah yang tepat untuk menyelesaikan masalah penceraman udara di wilayah DKI Jakarta. Algoritma Support Vector Machine memiliki hasil yang lebih baik dengan tingkat akurasi rata-rata sebesar 98.5% dengan tingkat rata-rata precision, recall dan f1-score sebesar 92,58%, 98,75%, 95%. Sedangkan algoritma Naïve Bayes hanya memperoleh akurasi sebesar 87.75% dengan tingkat rata-rata precision, recall, dan f1-score sebesar 73.5%, 91,16%, 77,6%. Hasil yang dihasilkan oleh kedua algoritma juga di pengaruhi oleh besarnya jumlah data latih dan data uji. Kata kunci: Naïve Bayes, SVM, Klasifikasi, Pencemaran Udara

Actions (login required)

View Item