cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Imam Asrowardi
Contact Email
imam@polinela.ac.id
Phone
+6281369739001
Journal Mail Official
routers@polinela.ac.id
Editorial Address
Jl. Sukarno Hatta No. 10 Bandar Lampung
Location
Kota bandar lampung,
Lampung
INDONESIA
ROUTERS: Jurnal Sistem dan Teknologi Informasi
Published by Politeknik Negeri Lampung
ISSN : -     EISSN : 29621224     DOI : https://doi.org/10.25181
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Library & Information Science
ROUTERS: Jurnal Sistem dan Teknologi Informasi includes research in the field of Computer Science, Computer Networks and Engineering, Software Engineering and Information Systems, and Information Security. Editors invite research lecturers, reviewers, practitioners, industry, and observers to contribute to this journal. ROUTERS is a national scientific journal that is open to seeking innovation, creativity, and novelty. Either letters, research notes, articles, supplemental articles, or review articles. ROUTERS aims to achieve state-of-the-art theory and application in this field. ROUTERS provides a platform for scientists and academics across Indonesia to promote, share, and discuss new issues and the development of systems and information technology.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 47 Documents
 1   2   3   4   5 
Digitalisasi Sistem Absensi Real-Time Berbasis QR Code Dengan Validasi Lokasi Untuk Meningkatkan Akuntabilitas Kehadiran Personel Pamungkas, Bayu; Iswahyudi, Raden Teddy; Anwar, Nizirwan; Ariessanti, Hani Dewi
ROUTERS: Jurnal Sistem dan Teknologi Informasi Vol. 4 No. 1, Februari 2026
Publisher : Program Studi Teknologi Rekayasa Internet, Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/rt.v5i1.4781

Abstract

Digital transformation has encouraged organisations to adopt information systems that are more efficient, accurate, and transparent, including in the management of personnel attendance. Conventional manual attendance systems still present significant limitations, such as high susceptibility to human error, data duplication, manipulation, and inefficiency in data processing and reporting. This study aims to design and develop a QR code–based attendance system as a digital solution to improve the reliability and accountability of attendance records. The software development process follows the Waterfall methodology, encompassing requirement analysis, system design, implementation, and testing stages. System modelling is conducted using unified modeling language (UML) diagrams and an entity relationship diagram (ERD) to clearly define system structure and operational workflows. The implemented system enables attendance recording through QR code scanning integrated with a centralised database in real-time, supported by QR validity checks, location validation based on location name or GPS radius, prevention of duplicate scans within a five-minute interval, and automatic determination of attendance status as PRESENT or LATE. System testing is performed using the Black Box Testing method to verify functional compliance from the user’s perspective without examining internal code structures. The testing results demonstrate that all core system functions operate in accordance with the specified requirements and business rules, responding appropriately to both valid and invalid input scenarios. Furthermore, each successful transaction consistently generates attendance records and activity logs, ensuring data integrity, traceability, and accountability. Overall, the proposed QR code–based attendance system effectively enhances efficiency, accuracy, and transparency in attendance management and is considered suitable for operational implementation and further development.
Peningkatan Akurasi Sistem Rekomendasi Film Menggunakan TF-IDF dan Cosine Similarity dengan Metode Hybrid Feature Engineering Aryono Prihandito; Sri Lestari; Fitria; Ketut Artaye
ROUTERS: Jurnal Sistem dan Teknologi Informasi Vol. 4 No. 2, Juli 2026 (In Progress)
Publisher : Program Studi Teknologi Rekayasa Internet, Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/rt.v4i2.4929

Abstract

Content-based filtering movie recommendation systems are widely used to help users find relevant movies. However, most studies still rely on a single feature such as a synopsis, resulting in a less informative feature representation that impacts the quality of recommendations. This study aims to improve the accuracy of movie recommendation systems using TF-IDF and Cosine Similarity through the application of Hybrid Feature Engineering, which combines synopsis, genre, and keywords. Evaluation was conducted using the TMDb 5000 Movie Dataset with Precision, Recall, and F1-Score metrics in a Top-10 Recommendation scenario. The results showed that the hybrid model increased Precision from 0.7600 to 0.9600 (26.3%), Recall from 0.0048 to 0.0060 (25.0%), and F1-Score from 0.0095 to 0.0120 (26.3%) compared to the baseline model. The system was also successfully implemented as a Streamlit-based web application. These results indicate that combining multiple features through Hybrid Feature Engineering can produce a more informative feature representation and improve the quality of recommendations in content-based filtering systems
Perbandingan Algoritma Long Short-Term Memory (LSTM) Dan XGBoost Dalam Memprediksi Kualitas Udara Di Jakarta Luthfi radyansyah; Nizirwan; Riya Widayanti; Rahmat Budiarsa
ROUTERS: Jurnal Sistem dan Teknologi Informasi Vol. 4 No. 2, Juli 2026 (In Progress)
Publisher : Program Studi Teknologi Rekayasa Internet, Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/rt.v4i2.5013

Abstract

This study compares the Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) algorithms in predicting air quality in Jakarta using the Air Pollution Standard Index (ISPU) dataset. The dataset consists of 2,874 observations collected from January 1, 2024, to July 31, 2025. The results show that both models are capable of producing accurate predictions; however, XGBoost demonstrates superior performance. XGBoost achieves an RMSE of 1.9704, MAE of 1.0509, MAPE of 1.54%, and an R² of 0.9913. In contrast, LSTM produces an RMSE of 3.0667, MAE of 2.0968, MAPE of 3.71%, and an R² of 0.9790. These findings indicate that XGBoost has lower prediction error and a stronger ability to explain data variability. Additionally, particulate pollutants such as PM2.5 and PM10 are identified as the dominant factors influencing air quality. Overall, XGBoost proves to be more effective, stable, and efficient in modeling air quality data.
Analisis Komparatif Kinerja Algoritma KNN, SVM, dan Neural Network dalam Klasifikasi Kanker Paru-paru Abwabul jinan; Manatur Pandapotan Siregar; Dede Fika Suryani; Tar Muhammad Raja Gunung; Abdul Muis
ROUTERS: Jurnal Sistem dan Teknologi Informasi Vol. 4 No. 2, Juli 2026 (In Progress)
Publisher : Program Studi Teknologi Rekayasa Internet, Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/rt.v4i2.5058

Abstract

Lung cancer is one of the leading causes of cancer-related deaths worldwide, making accurate classification methods essential to support early diagnosis. Although various machine learning algorithms have been applied to lung cancer classification, their reported performance remains inconsistent across different studies. Therefore, a comparative analysis using the same dataset is needed to provide a more objective evaluation of algorithm performance. This study aims to compare the performance of the K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Neural Network (NN) algorithms for lung cancer classification. The dataset was obtained from Kaggle and consists of 309 instances with 16 attributes. The research process included data preprocessing, classification, and model evaluation using Orange Data Mining. The performance of each algorithm was evaluated using a confusion matrix based on accuracy, precision, and recall metrics. The experimental results indicate that the Neural Network algorithm achieved the best performance, with an accuracy of 92.3%, a precision of 95.4%, and a recall of 95.9%, followed by Support Vector Machine with an accuracy of 89.9% and K-Nearest Neighbor with an accuracy of 89.1%. These findings demonstrate that the Neural Network algorithm is more effective in learning the underlying patterns of the dataset than the other two algorithms. The results of this study are expected to serve as a reference for selecting appropriate classification algorithms in the development of machine learning-based lung cancer diagnosis support systems.
Analisis Sentimen Ulasan Pengguna TikTok Shop pada Google Play Store Menggunakan Metode IndoBERT Putri Dewintari
ROUTERS: Jurnal Sistem dan Teknologi Informasi Vol. 4 No. 2, Juli 2026 (In Progress)
Publisher : Program Studi Teknologi Rekayasa Internet, Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/rt.v4i2.5068

Abstract

TikTok Shop has become one of the largest social commerce platforms in Indonesia; however, user perceptions of its shopping features have not been systematically studied. Star rating assessments alone are insufficient to deeply understand user satisfaction and complaints, necessitating a more comprehensive text analysis approach. This study aimed to analyze the sentiment of TikTok Shop user reviews on Google Play Store using IndoBERT, with a contribution of a keyword-based filtering approach to extract shopping-related reviews from general TikTok application reviews. Review data were collected through automated extraction from Google Play Store, filtered using shopping-related keywords, and preprocessed before classification using IndoBERT. Evaluation was conducted using a confusion matrix with accuracy, precision, recall, and F1-score metrics. Results showed a dominance of positive sentiment, with positive reviews centered on shopping convenience and live shopping satisfaction, while negative reviews were dominated by technical complaints and delivery issues. The model achieved adequate performance on positive and negative classes, although the neutral class was undetected due to class imbalance. This study demonstrates that IndoBERT effectively analyzes sentiment in Indonesian-language social commerce reviews, and the findings serve as empirical evidence for platform developers and digital business actors in formulating service improvement strategies.
Analisis Komparatif Decision Tree, Random Forest, dan Naive Bayes untuk Deteksi Website Phishing Menggunakan K-Fold Cross Validation dan Evaluasi Multi-Metrik Nasir Usman; Muhammad Faisal; Alvina Felicia Watratan; Emil Agusalim Habi Talib; Nurahmad
ROUTERS: Jurnal Sistem dan Teknologi Informasi Vol. 4 No. 2, Juli 2026 (In Progress)
Publisher : Program Studi Teknologi Rekayasa Internet, Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/rt.v4i2.5082

Abstract

Phishing websites remain difficult to detect because attackers can create new domains faster than blacklist systems can update. This study compares Decision Tree, Random Forest, and Naive Bayes for phishing website classification using 11,055 records with 30 technical features. The models were evaluated with Stratified 10-Fold Cross-Validation and five metrics: accuracy, precision, recall, F1-score, and ROC-AUC. Random Forest produced the best and most stable performance, with 97.23% accuracy, 97.70% precision, 96.02% recall, 96.85% F1-score, and 99.58% ROC-AUC. Decision Tree also performed strongly, while Naive Bayes showed very high recall but many false positives. Feature importance analysis identified SSLfinal_State and URL_of_Anchor as the most influential predictors, supporting lightweight technical-feature screening for phishing detection.
Perbandingan Algoritma Random Forest, Decision Tree, dan K-Nearest Neighbor untuk Penentuan Model Klasifikasi Gaya Belajar VARK Hefri Juanto; M Said Hasibuan; Sriyanto
ROUTERS: Jurnal Sistem dan Teknologi Informasi Vol. 4 No. 2, Juli 2026 (In Progress)
Publisher : Program Studi Teknologi Rekayasa Internet, Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/rt.v4i2.5086

Abstract

The mismatch between teaching methods and individual learning style preferences in e-learning platforms often hinders the effectiveness of information absorption for students. The primary issue lies in the one-size-fits-all learning approach and the inefficiency of identifying learning styles through manual questionnaires, which are subjective and time-consuming. This study aims to evaluate the performance of Random Forest, Decision Tree, and K-Nearest Neighbor (KNN) algorithms in automating VARK (Visual, Auditory, Read/Write, Kinesthetic) learning style classification. The novelty of this research lies in the implementation of the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance in the Read/Write modality, which initially accounted for only 14.2% of the total population. Following the CRISP-DM framework, a balanced dataset of 1,410 records was utilized. Experimental results show that Random Forest and KNN achieved the highest identical accuracy of 97.87%. However, based on stability evaluation through 10-Fold Cross Validation, Random Forest proved to be the most optimal model with the highest Mean CV score of 0.9592, outperforming KNN (0.9503). These findings provide a precise scientific foundation for developing adaptive recommendation systems to deliver personalized and effective instructional materials.

Page 5 of 5 | Total Record : 47

 1   2   3   4   5 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 2, Juli 2026 (In Progress) Vol. 4 No. 1, Februari 2026 Vol. 3 No. 2, Juli 2025 (In Progress) Vol. 3 No. 1, Februari 2025 Vol. 2 No. 2, Juli 2024 Vol. 2 No. 1, Februari 2024 (Dalam Proses) Vol. 1 No. 2, Juli 2023 Vol. 1 No. 1, Februari 2023