cover
Contact Name
Farid Wahyudi
Contact Email
faridstifler@gmail.com
Phone
+6285755817853
Journal Mail Official
faridstifler@gmail.com
Editorial Address
Fakultas Sains dan Teknologi Universitas Islam Raden Rahmat, Malang Office: C 2.1 Lantai II, Gedung KH. Tolchah Hasan Jalan Raya Mojosari No. 02, Kepanjen - Malang, Jawa Timur
Location
Kota malang,
Jawa timur
INDONESIA
JUSIFOR : Jurnal Sistem Informasi dan Informatika
ISSN : 28303393     EISSN : 28302443     DOI : https://doi.org/10.33379/jusifor.v1i2.1444
JUSIFOR adalah jurnal akses terbuka di bidang Informatika dan Sistem Informasi. Jurnal ini tersedia bagi para peneliti yang ingin meningkatkan pengetahuan mereka dibidang tertentu dan dimaksudkan untuk menyebarkan pengalaman hasil studi. JUSIFOR merupakan Jurnal penelitian ilmiah bidang informatika dan system informasi. Terbuka bagi siapa saja yang ingin mengembangkan ilmu pengetahuan berdasarkan penelitian yang berkualitas dibidang apapun. Artikel penelitian yang dikirimkan ke jurnal online ini akan di-peer-review. Jurnal ini diterbitkan oleh Prodi Sistem Informasi dan Teknik Informatika Fakultas Sains dan Teknologi, Universitas Islam Raden Rahmat. Jurnal ini diterbitkan sebanyak 2 kali dalam satu tahun, yaitu di bulan Juni dan Desember.
Articles 87 Documents
Algoritma LightGBM untuk Deteksi Aktivitas Cyber Espionage Melalui Dataset Serangan Siber Wulandari, Tasya; Yudisthira, Yasyfi Farhan; P.H, Kayla Chika; Wibowo, Muhammad Afriza; Andrew, Chistofer
JUSIFOR : Jurnal Sistem Informasi dan Informatika Vol 4 No 2 (2025): JUSIFOR - Desember 2025
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/jusifor.v4i2.8489

Abstract

Cyber espionage is a type of cyberattack where hackers try to secretly and continuously steal important information through computer networks. This study suggests using the Light Gradient Boosting Machine (LightGBM) algorithm to spot early signs of digital espionage. The data used comes from the Cybersecurity Intrusion Detection dataset available on Kaggle. The research includes steps like cleaning and organizing the data, dividing it into 80% for training and 20% for testing, and training the model with carefully chosen settings for learning rate and number of leaves. The results show that the LightGBM model performed well, with an accuracy of 89%, an AUC of 0.874, and an average precision of 0.9064. For the attack class, the model had a precision of 1.00 and a recall of 0.75. The most important features that helped identify suspicious behavior were ip_reputation_score, session_duration, and network_packet_size. Early detection happens by looking at unusual patterns in the data to find network activities that look like cyber espionage. When compared to other methods like SVM and Random Forest, LightGBM works better and is faster. Based on these results, the LightGBM model is seen as a good tool for an early warning system to detect cyber espionage.
Komparasi Kinerja Algoritma XGBoost dengan Reduksi Dimensi PCA pada Klasifikasi Diabetes Nusa, Rivale Belano; Indahsari, Rina Dewi
JUSIFOR : Jurnal Sistem Informasi dan Informatika Vol 4 No 2 (2025): JUSIFOR - Desember 2025
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/jusifor.v4i2.8563

Abstract

Diabetes is one of the most prevalent chronic diseases worldwide and requires accurate early detection to prevent long-term complications. In the field of medical data analysis, the application of machine learning algorithms such as XGBoost has proven effective in classifying disease risk. This study aims to compare the performance of the XGBoost algorithm before and after applying Principal Component Analysis (PCA) in diabetes risk classification using the Early Stage Diabetes Risk Prediction Dataset. The research stages include data preprocessing involving missing value checking, label encoding, outlier removal, normalization, and followed by the application of PCA with a 90% variance retention threshold. The experimental results show that the XGBoost model without PCA achieved the highest accuracy of 99.04%, while the model with PCA achieved 98.08%. Although the application of PCA slightly reduced accuracy, this technique successfully decreased the number of features and improved computational efficiency without losing important information. Therefore, PCA is proven to be effective in simplifying data complexity while maintaining optimal model performance.
Perancangan Sistem Informasi Absensi Siswa Berbasis Mobile pada SMK Pemda Lubuk Pakam Alda, Muhamad; Utami, Yulia; Chairullah, Andry; Kumala, Winda; Husaini, Adam
JUSIFOR : Jurnal Sistem Informasi dan Informatika Vol 4 No 2 (2025): JUSIFOR - Desember 2025
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/jusifor.v4i2.8593

Abstract

The design of a mobile-based student attendance information system at SMK Pembangunan Daerah Lubuk Pakam is carried out as a step to improve efficiency and accuracy in managing student attendance data. The previous attendance process, which was still manual, often caused reporting delays and potential data recording errors. In its development, the Waterfall method is used, focusing on the stages of requirement analysis and system design using UML diagrams (Use Case, Activity, and Class Diagram). The result of this study is a system design that has been validated through functional scenario testing (Black Box Design). Logical testing results show that the attendance process flow using QR Code, automatic data recap, and database integration has run 100% according to the school's functional requirements. This design is projected to significantly accelerate the attendance reporting process compared to conventional methods.
Analisis Aspek Ergonomi pada Proses Pembayaran Aplikasi Klik Indomaret menggunakan Metode NASA Task Load Index (NASA-TLX) Arini, Florentina Yuni; Saputra, Gagah Suryanatha Athallah; Putri, Farah Wahida Rizkia; Milannisya, Anya Kawakibi; Pratama, Eric Vibriano Julia; Asfino, Fadli Nugraha
JUSIFOR : Jurnal Sistem Informasi dan Informatika Vol 4 No 2 (2025): JUSIFOR - Desember 2025
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/jusifor.v4i2.8619

Abstract

The development of information technology has influenced how consumers make transactions, including in the retail sector through online shopping applications. One widely used platform is Klik Indomaret, which provides various digital payment methods to facilitate users. This study aims to analyze the ergonomic aspects of the payment process in the Klik Indomaret application based on users’ mental workload. The study used the NASA Task Load Index (NASA-TLX) to look at six parts of mental workload: Mental Demand, Physical Demand, Temporal Demand, Performance, Effort, and Frustration. The data came from 50 active Klik Indomaret users who filled out an online questionnaire. The highest scores are found in the  Performance and Mental Demand sections, while Frustration has the lowest  score. This means users still need to pay attention and put in some effort  when making a payment, but they do not feel strong emotional pressure.  Overall, the payment process in the Klik Indomaret app is comfortable to use  and can be considered ergonomic for its users.
Bibliometrik Hate Speech: Tren Metode Penelitian dan Domain Implementasi Nurindah, Arrisa Aprilani; Hasanati, Nida'ul; Aini, Qurrotul
JUSIFOR : Jurnal Sistem Informasi dan Informatika Vol 4 No 2 (2025): JUSIFOR - Desember 2025
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/jusifor.v4i2.8652

Abstract

This study aims to map the development of research related to hate speech through a bibliometric analysis of scientific publications indexed in Scopus. Using the keywords “hate speech” and “analysis,” a total of 2,009 publication metadata were obtained and analyzed using R Studio, Biblioshiny, and VOSviewer. The results indicate a significant increase in the number of publications, particularly during the 2021–2024 period, reflecting the growing academic attention toward hate speech issues. Domain analysis reveals that research is predominantly focused on the fields of Technology and Social Sciences, especially in the context of automated detection, social media, and the impact of digital society. Deep learning–based methods such as BERT and LSTM are the most frequently used techniques, in line with recent trends in Natural Language Processing (NLP). Furthermore, the co-occurrence analysis reveals the formation of several thematic clusters, including artificial intelligence, deep learning, multilingual hate speech, and large language models.
Segmentasi Pelanggan E-Commerce Berdasarkan Pola Pembatalan dan Pengembalian Pesanan Menggunakan K-Means Arifin, Yulia Natasya Farah Diba; Zubair, Anis
JUSIFOR : Jurnal Sistem Informasi dan Informatika Vol 4 No 2 (2025): JUSIFOR - Desember 2025
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/jusifor.v4i2.8887

Abstract

This study examines e-commerce customer segmentation based on cancellation and return behaviors using K-Means clustering as a proof-of-concept. Using the Pakistan E-Commerce Dataset (2017), we performed preprocessing, behavioral feature engineering (Cancellation Rate, Return Rate, Average Order Value, Discount Sensitivity, Preferred Payment Method, and Total Orders), Min–Max normalization, and K-Means modeling. Cluster number validation relied on the Elbow Method, Silhouette Score, and PCA visualization. Results indicate K = 3 stable clusters: Price-Sensitive Customers (69.48%) high per-order value but price-sensitive; Loyal Customers (13.55%), high frequency and low CR/RR; and High-Risk Customers (16.97%), high return rate with low value contribution. The findings demonstrate K-Means’ effectiveness in identifying cancellation/return patterns and provide a conceptual basis for risk management and further analysis.
Perbandingan Double Exponential Smoothing, Single Exponential Smoothing dan MA terhadap Peramalan Jumlah Pelanggan Di Gendis Jowo Soetedja, Aryadhiva; Hidayati, Rahmatina; Zubair, Anis; Indana, Luthfi
JUSIFOR : Jurnal Sistem Informasi dan Informatika Vol 4 No 2 (2025): JUSIFOR - Desember 2025
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/jusifor.v4i2.8896

Abstract

Gendis Jowo experiences fluctuations in the number of nasi box customers, which lead to suboptimal stock management and operational inefficiency, thereby requiring a forecasting approach to predict customer numbers more accurately. This study applies three forecasting methods Single Exponential Smoothing (SES), Double Exponential Smoothing (DES), and Moving Average (MA)—with the aim of determining the most accurate method for forecasting the next period’s customer count. Historical data from January 2022 to August 2025 were analyzed, with SES and DES parameters optimized using the Optimal ARIMA approach, and accuracy evaluated through MAPE, MAD, and MSD. The results show that the Moving Average method with a length of 4 (MA4) provides the highest accuracy with the lowest error values, making it the best-performing model. Based on the MA4 method, the number of customers for the next period is predicted to be 1,065.88, and this result can be used to plan stock requirements, packaging needs, and operational activities more effectively.