Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Proceeding Applied Business and Engineering Conference

PERANCANGAN SISTEM MANAJEMEN PERUBAHAN JADWAL PERKULIAHAN DI LABORATORIUM DENGAN PENERAPAN METODE DevOps Elvi Rahmi; Eva Yumami; Kasmawi; Wiwin Saputra
ABEC Indonesia Vol. 11 (2023): 11th Applied Business and Engineering Conference
Publisher : Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Optimal laboratory availability holds utmost importance in the pursuit of educational and research objectives at Politeknik Negeri Bengkalis. Confronting the global challenges and competition in today's digital age, Politeknik Negeri Bengkalis finds it imperative to ensure the effective and efficient utilization of its academic resources. Through observations, it has been noted that instances of suboptimal laboratory usage are not uncommon due to instructors' absence from the laboratory as per the designated schedule. This circumstance renders the laboratories unused, consequently disrupting the teaching and learning process. The focal point of this research is to craft academic administration software at Politeknik Negeri Bengkalis, enabling the real-time monitoring of laboratory availability and seamless adjustment of laboratory usage schedules. This ambitious task is undertaken using the innovative DevOps application development methodology. The adoption of the DevOps application development approach yields significant advantages throughout the stages of development, testing, and eventual implementation of this application.
The Role of SMOTE in Enhancing Naive Bayes Classification for Major Choice Prediction Rahmi, Elvi; Yumami, Eva
ABEC Indonesia Vol. 12 (2024): 12th Applied Business and Engineering Conference
Publisher : Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study examines the application of the Synthetic Minority Oversampling Technique (SMOTE) to addressclass imbalance within a dataset used for predicting high school major selection. The dataset comprises 468 traininginstances, including 306 labeled as 'IPA' and 162 labeled as 'IPS'. Despite the implementation of SMOTE, the results revealno significant enhancement in the predictive performance of the models, as both the SMOTE and non-SMOTE modelsachieved an accuracy of 100%, an F1-score of 100%, and a recall of 100%. This finding suggests that other factors, suchas the selection of relevant features, hyperparameter tuning, and model complexity, may have a more substantial impact onprediction performance. Additionally, the study proposes several recommendations for future research, includingconducting a more in-depth feature analysis, exploring alternative classification algorithms with advanced class imbalancehandling mechanisms, and performing meticulous hyperparameter optimization to improve overall model performance.