PENINGKATAN PERFORMA PREDIKSI DAERAH POTENSI PENANGKAPAN IKAN DENGAN METODE THRESHOLD ADAPTIF
Penulis/Author
RIDLA KUMARA HADI (1); Dr. Ir. Rudy Hartanto, M.T., IPM. (2); Dr. Eng. Silmi Fauziati, S.T., M.T. (3)
Tanggal/Date
2020
Kata Kunci/Keyword
Abstrak/Abstract
The method for determining thermal fronts is the Single Image Edge Detection algorithm with a static thresholdof0.5 obtained from previous research. The flaw of this method is a high bias of detection accuracy because negative detection results are much more matched than the positive detection. The research aimsto improve the performance of fish location potential detection. Thermal front detection performance improvement can be made by calculating fronts using an appropriate optimal threshold for each image. Adaptive threshold value obtained from analyzing histogramson each greyscale image. To obtain an optimal threshold value, Otsu Algorithm was chosen with consideration of fast process time and moderate accuracy. Method adjustment is needed since the nature of rasterized SST data. Otsu method modification wascarried out on optimal threshold value calculation within greyscale intensities range 1-254. Geodesic buffering within the maximum range of 10 kilometers is used for overcoming the shifted first result from the noise suppression process. The result of this study is a method for detecting potential fish areas with a recall performance valueof25.42% higher than the static threshold method. A higher recall value proves that the proposed method able to produce more positive zone detection,which precise location compared with actual fishing data
Rumpun Ilmu
Teknik Elektro
Bahasa Asli/Original Language
Bahasa Indonesia
Level
Nasional
Status
Dokumen Karya
No
Judul
Tipe Dokumen
Aksi
1
03 Peningkatan Performa Prediksi Daerah Potensi Penangkapan Ikan Dengan Metode Threshold Adaptif-compressed.pdf
