REMOTE SENSING UNTUK MEMPREDIKSI KASUS DEMAMBERDARAH MENGGUNAKAN RANDOM FOREST

• Main Author: Bimantoro Aulia Rizky, - (Author)
• Format: Book
• Published: 2023-12-18.
• Subjects: Thesis; NonPeerReviewed
• Online Access: Link Metadata
• Notes: http://repository.upi.edu/113985/1/S_KOM_1900303_Title.pdf; http://repository.upi.edu/113985/2/S_KOM_1900303_Chapter1.pdf; http://repository.upi.edu/113985/3/S_KOM_1900303_Chapter2.pdf; http://repository.upi.edu/113985/4/S_KOM_1900303_Chapter3.pdf; http://repository.upi.edu/113985/5/S_KOM_1900303_Chapter4.pdf; http://repository.upi.edu/113985/6/S_KOM_1900303_Chapter5.pdf; http://repository.upi.edu/113985/7/S_KOM_1900303_Appendix.pdf
• Keywords: L Education (General); QA75 Electronic computers. Computer science; QA76 Computer software

Penelitian ini mengkaji penggunaan teknologi remote sensing dan algoritma random forest dalam upaya memprediksi kasus demam berdarah. Demam berdarah adalah masalah kesehatan global yang memerlukan pemantauan dan tindakan cepat. Penggunaan data citra satelit, seperti Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Water Index (NDWI), Normalized Difference Moisture Index (NDMI), data suhu permukaan, kecepatan angin, curah hujan, kelembaban, suhu, dan populasi, digunakan untuk mengidentifikasi daerah-daerah yang berpotensi tinggi terhadap penularan penyakit tersebut. Algoritma random forest digunakan untuk mengintegrasikan berbagai parameter lingkungan dan membangun model prediksi. Informasi data citra satelit diekstraksi menggunakan aplikasi google earth engine, menghasilkan data yang digunakan memprediksi demam berdarah menggunakan random forest. Hasil penelitian menunjukkan bahwa skenario terbaik menghasilkan nilai RMSE sebesar 57.912128. This research examines the use of remote sensing technology and random forest algorithm in an effort to predict dengue fever cases. Dengue is a global health problem that requires monitoring and rapid action. The use of satellite image data, such as Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Water Index (NDWI), Normalized Difference Moisture Index (NDMI), surface temperature, wind speed, rainfall, humidity, temperature, and population data, are used to identify areas with high potential for transmission of the disease. A random forest algorithm was used to integrate the various environmental parameters and build a prediction model. Satellite image data information was extracted using google earth engine application, resulting in data used to predict dengue fever using random forest. The results showed that the best scenario resulted in an RMSE value of 57.912128.