Fadillah, Ahmad Hoerul (2025) PERBANDINGAN AKURASI ALGOTIMA KLASIFIKASI DECISION TREE DAN K-NEAREST NEIGHBOR PADA DATA INDEKS STANDAR PENCEMAR UDARA (ISPU) JAKARTA. S1 thesis, Universitas Mercu Buana Menteng.
|
Text (Cover)
41520010207-Ahmad Hoerul Fadillah-01 Cover_removed - Ahmad Hoerul Fadilah.pdf Download (1MB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
41520010207-Ahmad Hoerul Fadillah-02 Bab 1 - Ahmad Hoerul Fadilah.pdf Restricted to Registered users only Download (465kB) |
|
|
Text (BAB II)
41520010207-Ahmad Hoerul Fadillah-03 Bab 2 - Ahmad Hoerul Fadilah.pdf Restricted to Registered users only Download (344kB) |
|
|
Text (BAB III)
41520010207-Ahmad Hoerul Fadillah-04 Bab 3 - Ahmad Hoerul Fadilah.pdf Restricted to Registered users only Download (463kB) |
|
|
Text (BAB IV)
41520010207-Ahmad Hoerul Fadillah-05 Bab 4 - Ahmad Hoerul Fadilah.pdf Restricted to Registered users only Download (923kB) |
|
|
Text (BAB V)
41520010207-Ahmad Hoerul Fadillah-06 Bab 5 - Ahmad Hoerul Fadilah.pdf Restricted to Registered users only Download (334kB) |
|
|
Text (Datar Pustaka)
41520010207-Ahmad Hoerul Fadillah-08 Daftar Pustaka - Ahmad Hoerul Fadilah.pdf Restricted to Registered users only Download (287kB) |
|
|
Text (Lampiran)
41520010207-Ahmad Hoerul Fadillah-09 Lampiran - Ahmad Hoerul Fadilah.pdf Restricted to Registered users only Download (1MB) |
Abstract
Kualitas udara di Jakarta menjadi isu lingkungan yang signifikan akibat tingginya tingkat polusi yang berdampak negatif pada kesehatan masyarakat. Penelitian ini bertujuan untuk membandingkan akurasi dua algoritma machine learning, yaitu Decision Tree dan K-Nearest Neighbor (KNN), dalam mengklasifikasikan data Indeks Standar Pencemar Udara (ISPU) di DKI Jakarta. Data yang digunakan adalah data ISPU tahun 2023 yang bersumber dari Portal Satu Data Indonesia, dengan parameter polutan meliputi PM10, SO2, CO, O3, dan NO2. Metodologi penelitian ini mencakup beberapa tahapan, yaitu pengumpulan data, pra-pemrosesan data yang meliputi pembersihan, penanganan data yang hilang, dan normalisasi menggunakan Min-Max Scaling, pembagian data menjadi data latih dan data uji, pelatihan model, serta evaluasi menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma Decision Tree memiliki tingkat akurasi yang lebih unggul, yaitu sebesar 99%, dibandingkan dengan algoritma K-Nearest Neighbor yang mencapai akurasi 94%. Berdasarkan hasil tersebut, dapat disimpulkan bahwa Decision Tree merupakan model yang lebih baik dan akurat untuk klasifikasi data ISPU di DKI Jakarta. Air quality in Jakarta has become a significant environmental issue due to high levels of pollution that have a negative impact on public health. This study aims to compare the accuracy of two machine learning algorithms, namely Decision Tree and K-Nearest Neighbor (KNN), in classifying Air Pollution Standard Index (ISPU) data in DKI Jakarta. The data used is the 2023 ISPU data sourced from the Satu Data Indonesia Portal, with pollutant parameters including PM10, SO2, CO, O3, and NO2. This research methodology includes several stages, namely data collection, data pre-processing which includes cleaning, handling missing data, and normalization using Min-Max Scaling, dividing data into training data and test data, model training, and evaluation using accuracy, precision, recall, and F1-score metrics. The results show that the Decision Tree algorithm has a superior accuracy rate, which is 99%, compared to the K-Nearest Neighbor algorithm which achieves 94% accuracy. Based on these results, it can be concluded that Decision Tree is a better and more accurate model for ISPU data classification in DKI Jakarta.
Actions (login required)
 |
View Item |
