Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

The Effect of LAB Color Space with NASNetMobile Finetuning on Model Performance for Crowd Detection

Advance Sustainable Science, Engineering and Technology (ASSET) · Vol. 6 No. 1 (2024)

DOI
10.26877/asset.v6i1.17821
ISSN
2715-4211, 2715-4211
Terbit
2024-01-02
Penerbit
Universitas PGRI Semarang
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

In the COVID-19 pandemic, computer vision plays a crucial role in crowd detection, supporting crowd restriction policies to mitigate virus spread. This research focuses on analyzing the impact of using the RGB LAB color space on the performance of NASNetMobile for crowd detection. The fine-tuning process, involving freezing layers in various NASNetMobile base model variations, is considered. Results reveal that the model with LAB color space outperforms model with RGB color space, with an average accuracy of 94.68% compared to 94.15%. From all the test iterations, it was found that the highest performance for the NASNetMobile model occurred when freezing 10% of the layers from the back for both model LAB and RGB color spaces, with the LAB color space achieving an accuracy of 95.4% and the RGB color space achieving an accuracy of 95.1%.

Kata kunci

Jaringan kolaborasi para penulis

17 penulis · 40 tautan kepenulisan bersama · 7 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Universitas Dian Nuswantoro
  • Politeknik Negeri Samarinda
  • Institut Teknologi Sepuluh Nopember
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Kiswanto -Politeknik Negeri Samarinda1
SurahmanAfiliasi tidak diketahui1
Amiril AzizahPoliteknik Negeri Samarinda1
Ahyar Muhammad DiahPoliteknik Negeri Samarinda1
Sri WinarnoUniversitas Dian Nuswantoro1
Julius Immanuel Theo KrisnaUniversitas Dian Nuswantoro1
Leno Dwi CahyaUniversitas Dian Nuswantoro1
Adhitya NugrahaUniversitas Dian Nuswantoro1
Muljono MuljonoUniversitas Dian Nuswantoro1
Pulung Nurtantio AndonoUniversitas Dian Nuswantoro1
Sari Ayu WulandariUniversitas Dian Nuswantoro1
Harun Al AziesInstitut Teknologi Sepuluh Nopember1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) http://journal.upgris.ac.id/index.php/asset/oai, pertama di-harvest 8 Nov 2026, terakhir terlihat 8 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">The Effect of LAB Color Space with NASNetMobile Finetuning on Model Performance for Crowd Detection</dc:title>
	<dc:creator>Rafid, Muhammad</dc:creator>
	<dc:creator>Luthfiarta, Ardytha</dc:creator>
	<dc:creator>Naufal, Muhammad</dc:creator>
	<dc:creator>Al Fahreza, Muhammad Daffa</dc:creator>
	<dc:creator>Indrawan, Michael</dc:creator>
	<dc:subject xml:lang="en-US">literacy; local wisdom; natural and social science; wordwall</dc:subject>
	<dc:description xml:lang="en-US">In the COVID-19 pandemic, computer vision plays a crucial role in crowd detection, supporting crowd restriction policies to mitigate virus spread. This research focuses on analyzing the impact of using the RGB LAB color space on the performance of NASNetMobile for crowd detection. The fine-tuning process, involving freezing layers in various NASNetMobile base model variations, is considered. Results reveal that the model with LAB color space outperforms model with RGB color space, with an average accuracy of 94.68% compared to 94.15%. From all the test iterations, it was found that the highest performance for the NASNetMobile model occurred when freezing 10% of the layers from the back for both model LAB and RGB color spaces, with the LAB color space achieving an accuracy of 95.4% and the RGB color space achieving an accuracy of 95.1%.</dc:description>
	<dc:publisher xml:lang="en-US">Universitas PGRI Semarang</dc:publisher>
	<dc:contributor xml:lang="en-US"></dc:contributor>
	<dc:date>2024-01-02</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.upgris.ac.id/index.php/asset/article/view/17821</dc:identifier>
	<dc:identifier>10.26877/asset.v6i1.17821</dc:identifier>
	<dc:source xml:lang="en-US">Advance Sustainable Science, Engineering and Technology; Vol 6, No 1 (2024): November-January; 02401014</dc:source>
	<dc:source>2715-4211</dc:source>
	<dc:source>2715-4211</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.upgris.ac.id/index.php/asset/article/view/17821/pdf</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2024 Advance Sustainable Science, Engineering and Technology (ASSET)</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>