Pendeteksian Jumlah Bangunan Berbasis Citra Menggunakan Metode Deep Learning

Radhinka Bagaskara(1*), Alya Khairunnisa Rizkita(2), Rivaldo Fernandes(3), Winda Yulita(4),


(1) Institut Teknologi Sumatera
(2) Institut Teknologi Sumatera
(3) Institut Teknologi Sumatera
(4) Institut Teknologi Sumatera
(*) Corresponding Author

Abstract


Counting residential houses is one of the problems faced when determining population density level in Indonesia, therefore it’s required to find a method that’s able to solve said problem. Deep learning method is capable of creating a prediction model for detecting the number of buildings from an image. The deep learning prediction model is created with MobileNetv2 application. The prediction model is trained by using a dataset from Kaggle. The prediction model is tested using satellite photos taken from Way Kandis-Sukarame, Bandar Lampung. The result is a deep learning prediction model with accuracy of 91.30% for SenseFly and 10.34% for Way Kandis dataset. The research can be further improved by using a better training and testing dataset

Full Text:

PDF

References


Badan Pusat Statistik. “Hasil Sensus Penduduk 2020”, 2021.

Singga, Siprianus, and Wanti Wanti. "Hubungan Jumlah Anggota Keluarga, Kepadatan Rumah dan Mobilitas dengan Kejadian Demam Berdarah Dengue di Kota Kupang.", Prosiding Semnas Sanitasi, 212-217, 2019.

Hariyanto, Hendri. "Kejadian Pneumonia pada Anak Usia 12-59 Bulan.", HIGEIA (Journal of Public Health Research and Development) 4, no. Special 3, 549-560, 2020.

Ikbar, Iffat Nabila, Ahmad Ghiffari, and Rista Silvana. "Identifikasi Faktor Sosial Ekonomi Dan Lingkungan Yang Berhubungan Dengan Kerentanan Terhadap Covid-19 Di Kota Palembang.", MESINA (Medical Scientific Journal) 2, 28-39, 2021

Schmidhuber, J. "Deep Learning in Neural Networks: An Overview", Neural Networks. 61, 85–117, 2015.

Sandler, Mark, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. "Mobilenetv2: Inverted residuals and linear bottlenecks.", Proceedings of the IEEE conference on computer vision and pattern recognition, 4510-4520, 2018.

Rácz, Anita, Dávid Bajusz, and Károly Héberger. "Effect of dataset size and train/test split ratios in QSAR/QSPR multiclass classification.", Molecules 26.4, 1111, 2021




DOI: http://dx.doi.org/10.30645/j-sakti.v6i1.428

Refbacks

  • There are currently no refbacks.



J-SAKTI (Jurnal Sains Komputer & Informatika)
Published Papers Indexed/Abstracted By:


Jumlah Kunjungan :

View My Stats