Text

OPTIMASI ALGORITMA NAIVE BAYES DENGAN PARTICLE SWARM OPTIMIZATION UNTUK MENINGKATKAN PERFORMA KLASIFIKASI KUALITAS AIR KOTA PALEMBANG

---

Water quality is a fundamental aspect of life, particularly in regions that rely on rivers as the primary source of raw water. However, anthropogenic activities such as industrial, agricultural, and domestic processes have contributed to increasing water pollution, while the demand for clean water continues to rise in line with population growth. This study aims to develop a water quality classification model using the Naïve Bayes algorithm optimized with Particle Swarm Optimization (PSO) to improve prediction accuracy. The dataset consists of 8,000 samples with 20 features representing physical, chemical, and biological parameters, obtained from a regional water utility company. Each sample is labeled as 0 (does not meet standards) or 1 (meets standards). Before optimization, the Naïve Bayes model achieved an accuracy of 86%–87.75% with an F1-score ranging from 0.54 to 0.58. However, the imbalance between precision and recall indicates limitations in handling complex data distributions. After optimization using PSO (with parameters: population = 100, inertia weight (W) = 0.5, iterations = 300, threshold = 0.712), model performance improved significantly, reaching the highest F1-score of 0.616 with a training-testing data ratio of 70:30. The use of PSO effectively balanced precision and recall without overfitting, while also addressing the weakness of the Naïve Bayes algorithm in determining classification thresholds. The findings suggest that integrating Naïve Bayes with PSO can enhance classification accuracy for water quality assessment, making it a potential solution for sustainable water resource monitoring and management. The implementation of this method is expected to support policy formulation for clean water provision, particularly in areas facing high pollution challenges

---

Availability

Detail Information

Series Title

-

Call Number

T1840502025

Publisher

Inderalaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xi, VI-2 hlm.; ilus.; tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.307

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika, Fakultas Ilmu Komputer
software/aplikasi perangkat lunak

Specific Detail Info

-

Statement of Responsibility

NO

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment