Claim Missing Document
Check
Articles

Found 2 Documents
Search

Analisis Interaksi Populasi, Kasus Kebakaran, Ruang Terbuka Hijau, dan Kadar Karbonmonoksida Terhadap Polusi Udara PM2.5 di DKI Jakarta Alfarisi, Salman; Prayogo, Arif Zidan; Dani, Wa Ode Dianita Putri Suaiba
Jurnal Sumberdaya Alam dan Lingkungan Vol 11, No 3 (2024)
Publisher : Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

ABSTRAK  Buruknya kualitas udara menjadi salah satu masalah yang serius untuk kota-kota besar, khususnya Jakarta. Salah satu indikator dalam polusi udara adalah Particulate Matter (PM). Penelitian ini mengkaji pengaruh populasi penduduk, kasus kebakaran, luas ruang terbuka hijau (RTH), dan kadar karbonmonoksida (CO) terhadap kadar PM 2.5 di Jakarta menggunakan metode linear mixed model (LMM). Hasil penelitian menunjukkan bahwa luas RTH memiliki pengaruh signifikan terhadap penurunan kadar PM 2.5 dengan koefisien negatif, artinya semakin luas RTH, semakin rendah tingkat polusi udara. Kadar CO juga berpengaruh signifikan terhadap PM 2.5 secara mandiri. Populasi penduduk, meskipun tidak signifikan secara langsung, menunjukkan pengaruh signifikan ketika diinteraksikan dengan variabel lain terhadap PM 2.5. Di sisi lain, kasus kebakaran tidak berpengaruh signifikan terhadap polusi udara, bahkan interaksinya dengan variabel lain juga tidak menunjukkan pengaruh signifikan. Penelitian ini dapat menjadi acuan bagi pemerintah DKI Jakarta dalam menyusun regulasi dan kebijakan untuk mengendalikan polusi udara, terutama dengan memperhatikan pentingnya memperluas RTH dan mengendalikan kadar CO sebagai upaya mengurangi PM 2.5, serta mencegah dampak buruk kualitas udara terhadap kesehatan masyarakat seperti penyakit pernapasan. Kata kunci: kebakaran, kualitas udara, LMM, pernapasan, polusi ABSTRACT Poor air quality is a serious problem for big cities, especially Jakarta. This study examines the effect of population, fire cases, green open space (GOS) area, and carbon monoxide (CO) levels on PM 2.5 levels in Jakarta using the linear mixed model (LMM) method. The results showed that the area of green space has a significant effect on reducing PM 2.5 levels with a negative coefficient, meaning that the wider the green space, the lower the level of air pollution. CO levels also have a significant effect on PM 2.5 independently. Population, although not significant directly, shows a significant effect when interacted with other variables on PM 2.5. On the other hand, fire cases do not have a significant effect on air pollution, and even their interaction with other variables also does not show a significant effect. This research can serve as a reference for the DKI Jakarta government in developing regulations and policies to control air pollution, especially by paying attention to the importance of expanding green spaces and controlling CO levels as an effort to reduce PM 2.5, as well as preventing adverse effects of air quality on public health such as respiratory diseases. Keywords:  air quality, breathing, fire, LMM, pollution
Comparative Performance of U-Net CNN in Multi-Class Aircraft Segmentation and Classification Using Polygon and Bounding Box Annotations Sitanggang, Rivilyo Mangolat Rizky; Dani, Wa Ode Dianita Putri Suaiba; Setiadi, Bambang; Kuntjoro, Yanif Dwi
Indonesian Journal of Aerospace Vol. 23 No. 1 (2025): Indonesian Journal Of Aerospace
Publisher : BRIN Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55981/ijoa.2025.8155

Abstract

Recent advancements in deep learning have revolutionized image processingtasks such as segmentation and classification. This study investigates theperformance of U- Net-CNN models in multi-class aircraft segmentation andclassification using polygon and bounding box annotations. Military aircraftclassification is crucial for defense applications, as it aids in rapid and accuratedecision-making during critical missions. This study investigates howthese annotation methods affect training time, segmentation accuracy, andclassification performance in multi-class segmentation and classification tasksinvolving military aircraft. The research compares polygon and bounding boxmethods to evaluate their effectiveness in capturing object details and computationalefficiency. While polygon annotations achieved superior precision witha mean test accuracy of 0.987 and lower loss of 0.041, bounding boxes excelledin computational efficiency. Future research should expand datasets and exploreadditional annotation techniques to further generalize these findings.