Image of KLASIFIKASI KABUPATEN KOTA DI INDONESIA BERDASARKAN TINGKAT PENGELUARAN PERKAPITA DALAM KELOMPOK MAKANAN RINGAN MENGGUNAKAN ALGORTIMA K-NEAREST NEIGHBOR MULTI OBJECTIVE PARTICLE SWARM OPTIMIZATION (K-NN MOPSO)

Text

KLASIFIKASI KABUPATEN KOTA DI INDONESIA BERDASARKAN TINGKAT PENGELUARAN PERKAPITA DALAM KELOMPOK MAKANAN RINGAN MENGGUNAKAN ALGORTIMA K-NEAREST NEIGHBOR MULTI OBJECTIVE PARTICLE SWARM OPTIMIZATION (K-NN MOPSO)

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

This study aims to classify regencies / cities in Indonesia based on the level of expenditure in the snack food group by applying the K-Nearest Neighbor (K-NN) algorithm, and K-NN which is optimized using Multi Objective Particle Swarm Optimization (MOPSO). The classification results with K-NN show that the accuracy value is 90% which is classified as good, but the f1_score value of 75.00%, precision 71.43%, and recall 78.95% are still in the sufficient category. Furthermore, calculations using the K-NN MOPSO algorithm obtained an accuracy of 96%, f1_score, precision, and recall values of 93.50%, including in the excellent category. The completion of the K-NN MOPSO algorithm was carried out using the Python programming language, with the help of the RandomizedSearchCV module to determine the best K parameter without the need to test all other parameter combinations in the classification process, as well as the Distributed Evolutionary Algorithms in Python (DEAP) module to optimally implement the MOPSO framework. The results show that combining K-NN and MOPSO can significantly improve classification performance compared to the K-NN algorithm.

Availability
Inventory Code Barcode Call Number Location Status
2507003006T173760T1737602025Central Library (Reference)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1737602025
Publisher
: Prodi Ilmu Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sriwijaya.,
Collation
xv, 67 hlm.; ilus.; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
510.07
Content Type
-
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Matematika
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment