Nita Merlina
Nusamandiri University

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Integrating MLOps for Monitoring, Drift Detection, and Adaptive Retraining in Sensor Systems Novia Heriyani; Nita Merlina
Computer Science (CO-SCIENCE) Vol. 6 No. 2 (2026): July 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i2.12409

Abstract

Machine learning models deployed in sensor-based production environments are prone to performance degradation due to evolving data distributions, commonly known as data drift. In gas sensor systems, such drift often arises from environmental variability and sensor aging, which can significantly reduce predictive reliability if left unaddressed. This study presents an integrated Machine Learning Operations (MLOps) framework that combines performance monitoring, distribution-based drift detection, and adaptive retraining within a unified production pipeline. Experiments are conducted using the Gas Sensor Array Drift Dataset, organized into sequential batches to emulate real-world deployment conditions. Data drift is quantified using Population Stability Index (PSI) and Kullback–Leibler Divergence (KL), which serve as decision thresholds for triggering retraining. The proposed adaptive retraining strategy is systematically compared with baseline (no retraining) and periodic retraining approaches. The results indicate that the adaptive strategy maintains more stable performance across data batches while minimizing unnecessary retraining processes. Additionally, the use of containerization and experiment tracking ensures reproducibility and supports full lifecycle traceability. Overall, this study demonstrates that integrating MLOps practices into sensor-based machine learning systems is essential for improving robustness and ensuring long-term operational sustainability in dynamic environments.
PENERAPAN PSO UNTUK SENTIMEN ANALISIS PADA REVIEW MATA UANG KRIPTO MENGGUNAKAN METODE NAÏVE BAYES Nita Merlina; Ade Chandra; Nissa Almira Mayangky
INTI Nusa Mandiri Vol. 18 No. 2 (2024): INTI Periode Februari 2024
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i2.4982

Abstract

In the digital age emerging currencies using digital technology called currency crypto money. Many people use cryptocurrencies to invest. This triggered the sentiment in society on social media twitter, there are positive opinions and there are negative opinions. The purpose of this study is to determine the public sentiment regarding the review of crypto currency and then classify it into two sentiments, namely positive and negative sentiments. The classifier method used is Naïve Bayes, Naïve Bayes is a good classifier method but has shortcomings in the selection of features therefore Particle Swarm Optimization (PSO) is applied as a feature selection in order to improve the accuracy value. After conducted experiments using Naïve Bayes method, obtain accuracy value of 66% with AUC 0.482 and after Applied Particle Swarm Optimization (PSO) as feature selection in Naïve Bayes obtain accuracy value of 85% with AUC 0.716 has increased accuracy .