Claim Missing Document
Check
Articles

Found 16 Documents
Search

PREDIKSI TINGKAT KELULUSAN MAHASISWA S1 UNIVERSITAS AN NUUR DENGAN METODE  DECISION TREE C4.5 Umar Haji Mussa’id; Agus Susilo Nugroho; Rahmawan Bagus Trianto
Julia: Jurnal Ilmu Komputer An Nuur Vol 4 No 1 (2024): Julia Jurnal
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/julia.v4i1.18

Abstract

One of the private universities in Purwodadi is An Nuur Purwodadi University. Many students have graduated from An Nuur Purwodadi University, but there are some students who did not graduate on time. This poses a problem and raises a significant question as to why these students did not graduate on time. A decision tree is a suitable data mining method for this research because it has the advantage of identifying and summarizing patterns in the data. The Decision Tree algorithm has an accuracy of 96.25%. The recall values for each class are 97.37% for the "Late" class and 95.00% for the "On-Time" class. Meanwhile, the precision values for each class are 94.87% for the "Late" class and 97.44% for the "On-Time" class 
ANALYSIS OF SENTIMENT ON TEACHER MARKETPLACE ISSUES USING THE LEXICON AND K-NEAREST NEIGHBOR ALGORITHMS Addien Anaba; Rahmawan Bagus Trianto; Eko Supriyadi
Julia: Jurnal Ilmu Komputer An Nuur Vol 4 No 1 (2024): Julia Jurnal
Publisher : LPPM Universitas An Nuur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35720/julia.v4i1.19

Abstract

The advancement of social media makes it easier for users to express opinions. Twitter has become one of the media that is loved by internet users, users can freely express their thoughts or opinions, apart from that they can also express everything that is being experienced. The busy issue of the Teacher Marketplace initiated by the Minister of Education, Nadiem Makarim, has invited many comments from internet users. Twitter users' tendencies in posting content can be determined by analyzing sentiment. In this research, the Lexicon and K-Nearest Neighbor (KNN) methods are proposed to analyze sentiment towards the education minister's discourse on Twitter social media on the topic of Teacher Marketplace Issue Sentiment by classifying it into positive, neutral and negative. The results of this research show that the accuracy value obtained was 91.70%, precision 90.51%, recall 71.95%. By carrying out this sentiment analysis, it is hoped that the problems contained in the Marketplace Guru topic controversy can be identified, used as input and consideration for further research.
Optimized K-Means Clustering for Web Server Anomaly Detection Using Elbow Method and Security-Rule Enhancements Trianto, Rahmawan Bagus; Muin, Muhammad Abdul; Vikasari, Cahya
Journal of Information System and Informatics Vol 7 No 4 (2025): December
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v7i4.1391

Abstract

Anomaly detection in web server environments is essential for identifying early indicators of cyberattacks that arise from abnormal request behaviors. Traditional signature-based mechanisms often fail to detect emerging or obfuscated threats, requiring more adaptive analytical approaches. This study proposes an optimized anomaly detection model using K-Means clustering enhanced with engineered security-rule features and the Elbow Method. Two datasets were used: a small dataset of 3,399 log entries from one VPS and a large dataset of 223,554 entries collected from three VPS nodes, all sourced from local production servers of the Department of Computer and Business, Politeknik Negeri Cilacap. The preprocessing pipeline includes timestamp normalization, removal of non-informative static resources, numerical feature scaling, and TF-IDF encoding of URL paths. Domain-driven security features entropy scores, encoded-payload indicators, abnormal status-code ratios, and request-rate deviations were integrated to improve anomaly separability. Experiments across five model configurations show that combining larger datasets with rule-based features significantly enhances clustering performance, achieving a Silhouette Score of 0.9136 and a Davies–Bouldin Index of 0.4712. The results validate the effectiveness of incorporating security-rule engineering with unsupervised learning to support early-warning threat detection in web server environments.
Sistem Informasi Peminjaman Alat Praktikum Laboratorium Multimedia Berbasis Website dengan Framework Laravel Kukuh Muhammad; Rahmawan Bagus Trianto; Dwi Novia Prasetyanti
Joined Journal (Journal of Informatics Education) Vol 7 No 2 (2024): Volume 7 Nomor 2 (2024)
Publisher : Universitas Ivet

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31331/joined.v7i2.3560

Abstract

Sistem Informasi Peminjaman Alat Praktikum merupakan aplikasi berbasis web yang dirancang untuk mengelola proses peminjaman alat praktikum bagi mahasiswa atau pengguna di laboratorium multimedia. Laboratorium Multimedia memiliki tanggung jawab menyediakan fasilitas peminjaman alat praktikum untuk mendukung kegiatan belajar mengajar. Diperlukan sistem untuk mempermudah dan mengefisienkan proses peminjaman alat, dengan memanfaatkan teknologi komputer. Oleh karena itu, penelitian ini bertujuan untuk menerapkan Sistem Informasi Peminjaman Alat Praktikum Berbasis Web dengan bahasa pemrograman web pada Laboratorium Multimedia menggunakan framework Laravel. Dalam pengembangan sistem ini, metode Waterfall digunakan sebagai pendekatan pembangunan. Untuk menguji kelayakan sistem, dilakukan evaluasi menggunakan metode System Usability Scale (SUS). Hasil pengujian dengan menyebarkan 30 kuisioner dengan metode SUS menggunakan skala linkert menunjukkan nilai kelayakan sebesar 85,5%, yang menempatkannya dalam kategori Excellent menurut standar usability, menunjukkan bahwa sistem ini berhasil memenuhi kriteria kemudahan penggunaan dan kepuasan pengguna.
Pengembangan Model Random Forest untuk Prediksi Kesehatan Jiwa Berbasis Data Klinis Terstruktur dan Tidak Terstruktur Muhammad, Kukuh; Trianto, Rahmawan Bagus; Purwanto, Joko
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 11, No 3 (2025): Volume 11 No 3
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v11i3.100012

Abstract

Penelitian ini mengembangkan model prediksi kesehatan jiwa menggunakan algoritma Random Forest berbasis data klinis terstruktur dan tidak terstruktur dari pasien poli kejiwaan RSUD dr. R. Goeteng Taroenadibrata Purbalingga. Dataset terdiri dari 4.432 rekam medis yang mencakup parameter fisiologis serta catatan naratif yang diproses melalui cleaning, stemming Sastrawi, dan pembobotan TF-IDF. Evaluasi model dilakukan menggunakan dua skema pembagian data (85:15 dan 80:20) serta dua kondisi preprocessing (stemming dan non-stemming). Hasil menunjukkan bahwa jumlah data berpengaruh signifikan terhadap performa model, di mana akurasi meningkat dari 0,62–0,66 pada 1.000 data menjadi 0,79–0,81 pada 4.432 data. Namun, nilai presisi, recall, dan F1-score berbasis macro masih rendah akibat ketidak seimbangan kelas. Setelah diterapkan teknik oversampling SMOTE, performa model meningkat sangat signifikan dengan akurasi mencapai 0,9490 dan F1-score macro 0,9360. Pengukuran ROC-AUC sebesar 0,9991 menunjukkan kemampuan diskriminatif yang hampir sempurna. Perbandingan dengan algoritma lain menunjukkan bahwa Random Forest menghasilkan kinerja terbaik, melampaui SVM, Naive Bayes, dan Decision Tree. Hasil penelitian menegaskan potensi Random Forest untuk prediksi kesehatan jiwa berbasis data klinis terintegrasi, serta pentingnya penanganan class imbalance untuk meningkatkan performa pada kelas minoritas.
Optimalisasi Manajemen Downtime pada SIMRS dan REM di RSUD dr. R. Goeteng Taroenadibrata Purbalingga Muhammad, Kukuh; Fajar Mahardika; Rahmawan Bagus Trianto; Joko Purwanto
Jurnal Pengabdian kepada Masyarakat Politeknik Negeri Batam Vol. 7 No. 2 (2025): Jurnal Pengabdian kepada Masyarakat Politeknik Negeri Batam
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/abdimaspolibatam.v7i2.11194

Abstract

Guidance in managing downtime in the Hospital Management Information System (SIMRS) and Electronic Medical Records (RME) is a strategic step to maintain operational continuity and the quality of healthcare services at RSUD dr. R. Goeteng Taroenadibrata Purbalingga. Recurrent downtime negatively impacts administrative processes and medical services, necessitating systematic and continuous management. This study aims to provide technical guidance in managing downtime and to enhance the understanding and skills of human resources, particularly the Information Technology (IT) team and users of SIMRS and RME. The methods employed include technical training, identification of downtime causes, development of system maintenance procedures, and capacity building for users in operating the information systems. The results indicate that structured training and technical support can reduce downtime frequency and accelerate responses to technical disruptions. These findings highlight the importance of strengthening the IT team through ongoing training, more systematic system maintenance planning, and the establishment of clear, user-friendly operational procedures. Continuous guidance is expected to improve the effectiveness of downtime management and support the smooth delivery of healthcare services. This effort is an integral part of enhancing the quality of information systems and advancing digital transformation in healthcare services.