cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Indah Purnama Sari
Contact Email
indahpurnama@umsu.ac.id
Phone
+6282276837886
Journal Mail Official
ibchanifjournal@gmail.com
Editorial Address
Jl. Batang Kuis - Lubuk Pakam Gg. Cempaka Dusun III No. 3, Tanjung Sari, Batang Kuis, Kab. Deli Serdang Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
Hanif Journal of Information Systems
Published by Ilmu Bersama Center
ISSN : -     EISSN : 30252342     DOI : https://doi.org/10.56211/hanif
Core Subject : Science,
Computer Science & IT Library & Information Science
Hanif journal of Information Systems aims to provide scientific literatures specifically on studies of applied research in information systems (IS)/information technology (IT) and public review of the development of theory, method and applied sciences related to the subject. Hanif Journal of Information Systems accepts manuscripts on the topics: E-Business/E-commerce E-Government E-Health E-learning Human-Computer Interaction Information Assurance & Intelligent Information Security & Risk Management IS/IT Operations Management IS/IT Organization & Human Resource Management IS/IT Strategic Planning IT Governance IT Investment Analysis IT Project Management Web Science Social Media in Business Multimedia Application Big Data Research New Technology Acceptance and Diffusion Green Information Systems Innovation Management/Technopreneurship Data Science And other topics relevant to Information Systems.
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 41 Documents
 1   2   3   4   5 
Implementation of Multi-Room Computer Laboratory Network Infrastructure Based on Star Topology in an Educational Environment Andi Zulherry; Al-Khowarizmi
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/hanif.v3i2.68

Abstract

Reliable network infrastructure is essential to support digital-based learning activities in educational institutions, particularly in computer laboratories that require stable and simultaneous internet access for a large number of devices. This study aims to implement a multi-room computer laboratory network infrastructure consisting of 160 PCs distributed across four laboratory rooms, each containing 40 computers. The network architecture is designed using a star topology, where each PC connects to an access switch within its respective room, and all switches are connected to a central modem acting as the primary gateway and Dynamic Host Configuration Protocol (DHCP) server. The infrastructure follows a peer-to-peer model without centralized server deployment or bandwidth management configuration. The implementation process includes physical network installation, structured cabling, automatic IP configuration through DHCP, and connectivity testing to ensure proper communication and internet accessibility. The results show that all 160 PCs successfully obtained IP addresses without conflicts and were able to access the internet simultaneously under normal operating conditions. The star topology provided ease of installation, simplified troubleshooting, and effective fault isolation. These findings indicate that the implemented infrastructure operates reliably as a foundational network system and provides a baseline for future development, including network segmentation, bandwidth management, and centralized service integration.
Implementation of the Least Significant Bit (LSB) Method for Data Security in a Mandailing Language Dictionary Zulkifli Hasibuan
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

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

Abstract

The development of information technology has encouraged the digitalization of various forms of information, including regional language dictionaries. The Mandailing Language Dictionary in digital form makes it easier for people to learn and preserve regional languages. However, digital data storage also poses risks to data security, such as theft, duplication, or modification of data by unauthorized parties. Therefore, a method is needed to improve data security in digital dictionary systems. This study aims to implement the Least Significant Bit (LSB) method as a steganographic technique to hide text data within digital images in the Mandailing Language Dictionary system. The LSB method works by embedding text data into the least significant bit of digital image pixels so that the existence of the data is not easily detected visually. This research produces a web-based system capable of performing encoding (data embedding) and decoding (data extraction) processes on digital images. The encoding process is carried out by converting text into binary form and embedding it into the red color channel of each image pixel using the LSB method. In the decoding process, the system reads the LSB bits from the image to retrieve the embedded text data. The testing results show that the embedded data can be accurately extracted without any changes, and the image quality before and after the embedding process does not show significant differences. Therefore, the LSB method can be used as a solution to improve data security in the Mandailing Language Dictionary system.
SEO (Search Engine Optimization) Finding Growth Opportunities in Organic Traffic on the KAIA Media.id Website Yoga Pramana; Halim Maulana
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

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

Abstract

The rapid growth in digital marketing highlights the importance of Search Engine Optimization (SEO) in enhancing website visibility and attracting organic traffic. This research focuses on SEO optimization for Kaia Media.id by developing a dedicated Keyword Tool Suggestion application. The primary goal is to identify opportunities to increase organic traffic to the Kaia Media.id website by efficiently targeting relevant keywords. The developed tool helps discover high-potential keywords that align with the interests and search behavior of the target audience. The Keyword Tool Suggestion application provides an easy-to-use interface to generate effective keyword suggestions based on current trends and search engine algorithms. By integrating this tool into Kaia Media.id's SEO strategy, the website can improve its search engine ranking, attract more visitors, and ultimately enhance its online presence. The application is tested to ensure that it provides accurate and actionable keyword suggestions, facilitating more effective content creation and marketingstrategies. By leveraging the Keyword Tool Suggestion application, Kaia Media.id aims to position itself as a leading digital marketing agency, offering high-quality SEO and online marketing solutions to its clients. The findings of this research affirm the value of targeted keyword optimization in achieving sustainable growth in organic traffic.
Machine Learning-Based Phishing Email Detection: A Comparative Study of Support Vector Machine and Random Forest nurkumalalubis; Mulkan Azhari
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

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

Abstract

Information and communication technology has now developed very rapidly, bringing significant changes to our daily lives. With the advancement of information and communication technology, access to information has become very easy and fast. However, this convenience also brings its own challenges, especially in terms of personal data security. As technology users, we are required to be wise and vigilant in safeguarding our personal data so that it is not misused by irresponsible parties. One example of cybercrime that often occurs is phishing emails. In this attack, the perpetrator uses a link containing a virus to encrypt the user's data or device, then asks for a ransom to restore access to the data. Phishing emails usually look like official emails from trusted sources, so recipients are often unaware of the dangers lurking. Therefore, to minimize the losses that can occur, we can also take advantage of technology so that we can automatically classify phishing emails. Therefore, this research will carry out the process of building a machine learning model which can automatically classify phishing emails. So that with the model built in this research, it is hoped that it can help in anticipating phishing emails. In this research, the construction of machine learning models will use data with a total of 18650 data which consists of 11322 non-phishing email data and 7328 phishing email data. The model that will be built in this research is a model using the Support Vector Machine and Random. Forest algorithms. In the model building process, to find the optimal parameters, the hyperparameter tuning process is carried out using CV gridsearch, so as to produce optimal parameters. After testing the model to classify phishing emails, the results show that using the Support Vector Machine algorithm produces a test accuracy of 97.27%, while using the Random Forest algorithm produces an accuracy of 96.51%.
Design and Development of an Internet of Things (IoT)-Based Real-Time Tide Monitoring System for Coastal Water Level Observation Muhammad Ari Juanda; Mhd. Basri
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/hanif.v3i2.71

Abstract

Sea tides are a phenomenon of the periodic rise and fall of sea level caused by a combination of gravitational force and the attractive force of astronomical objects, especially the sun, earth and moon. Every day the tidal phenomenon occurs and information about tides is very useful for human activities related to the marine sector such as fishing and other activities. There is a need for intelligent tool concept technology that can help and alleviate this problem, so an instrumentation tool has been created that can provide tidal information at any time that can be accessed via the internet network using the Android system. Decisions can match human thought patterns. The electronic components used in implementing the system are nodeMCU as a controller and internet of things (IOT) communication, ultrasonic sensors function as a medium for measuring sea water height. This research produces a system that can monitor the ebb and flow of sea water. In the system, a notification system is implemented for system users so they can monitor the ebb and flow of sea water. The application used is the blynk application which is integrated with the internet.
Application of Data Mining to Analyze BPJS Patient Satisfaction Levels Regarding the Service Attitude of PTPN II Tanjung Selamat General Hospital Using the K-Means Clustering Algorithm Yohanni Syahra; Natasya Nabaceva
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

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

Abstract

The importance of the BPJS Kesehatan's role in providing affordable healthcare access to the community is undeniable. Rumah Sakit Umum PTPN II Tanjung Selamat collaborates with BPJS Kesehatan to deliver services to BPJS participants. However, patient satisfaction levels have been declining, with primary complaints including long registration processes, data recording errors, extended waiting times for doctor consultations, and inadequate hospital facilities. Understanding the factors affecting patient satisfaction is crucial for improving healthcare quality at this hospital. To address these issues, this study applies Data Mining methods, specifically the K-Means Clustering algorithm, to analyze BPJS patient satisfaction levels at Rumah Sakit Umum PTPN II Tanjung Selamat. K-Means Clustering is chosen for its ability to group data based on similar characteristics, allowing the identification of patterns influencing patient satisfaction. Utilizing a desktop application designed with Visual Basic 2010, this research provides flexibility in determining the number of clusters, aiding in more effective analysis and grouping of patient satisfaction data. The findings are expected to offer valuable insights for the management of Rumah Sakit Umum PTPN II Tanjung Selamat to enhance healthcare services for BPJS participants. By identifying patient groups based on their satisfaction levels, the hospital can take more targeted actions to improve unsatisfactory aspects. This study demonstrates that the application of Data Mining with the K-Means method can be an effective tool in evaluating and improving healthcare service quality.
Blockchain Integration in Fintech: A Framework for Secure and Transparent Digital Transactions Surya Guntur; Surya Wisada Dachi; Willy Yusnandar
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

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

Abstract

The financial technology (fintech) industry has grown rapidly in recent years, driven by the growing demand for fast, secure, and transparent digital transactions. However, data security and transaction transparency remain key challenges that must be addressed. Blockchain technology has emerged as an innovative solution by providing a decentralized system that can enhance security and transparency within the fintech ecosystem. This study aims to analyze the benefits, challenges, and factors influencing blockchain adoption in the fintech industry. The research methodology uses a qualitative approach with literature analysis from relevant national and international journals published over the past three years. The results indicate that blockchain implementation can reduce the risk of fraud, increase transaction efficiency, and strengthen consumer trust through greater transparency. However, blockchain adoption faces various barriers, including high implementation costs, a lack of clear industry standards, limited infrastructure, and the need for comprehensive regulations. Furthermore, increased awareness and education among industry players are needed to encourage broader blockchain adoption. This study provides strategic recommendations for fintech industry players and policymakers, including the need for regulatory development, infrastructure investment, and human resource training. Thus, these findings are expected to contribute to the development of academic literature as well as provide practical guidance for optimizing the application of blockchain in improving security and transparency in the financial sector.
Improving the Accuracy of Lettuce and Weed Classification Based on MobileNetV2 Features Through Segmentation Akhmad Jayadi; Kurniawan Saputra; Ahmad Rofi'i
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

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

Abstract

Automating the separation of commodity crops and weeds is a major challenge in the implementation of precision agriculture . The presence of complex backgrounds such as soil, rocks, and shadows often degrades the performance of feature extraction in computer vision classification models. This study proposes an image preprocessing approach using the GrabCut segmentation method to extract key crop objects cleanly before performing Deep Learning- based feature extraction . Representative features from the image are extracted using the lightweight and efficient MobileNetV2 architecture. Next, classification is performed by comparing three Machine Learning algorithms , namely Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Random Forest (RF). Testing is carried out on two data scenarios, namely the original dataset ( Original ) and the segmented dataset ( GrabCut ). The experimental results show that the use of original images produces an accuracy of 98.89% for all three classification models. However, after being integrated with GrabCut segmentation, the accuracy of all three models increases significantly to 100.00%. These results prove that GrabCut-based segmentation effectively eliminates background noise information , thereby improving the generalization capabilities of classification models perfectly on edge computing devices .
Predicting Student Dropout Risk Using XGBoost and Explainable AI Sumita Wardani; Sartika Mandasari; Meisarah Riandini
Hanif Journal of Information Systems Vol. 3 No. 2 (2026): February Edition
Publisher : Ilmu Bersama Center

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

Abstract

Student dropout is one of the major challenges faced by higher education institutions, as it negatively affects academic performance, institutional accreditation, and educational quality. Early identification of students at risk of dropping out is essential to support timely intervention and improve student retention rates. This study proposes a student dropout risk prediction model using the Extreme Gradient Boosting (XGBoost) algorithm combined with Explainable Artificial Intelligence (XAI) through SHapley Additive exPlanations (SHAP). The dataset consists of student academic records, including Grade Point Average (GPA), semester performance, attendance, completed credit units, and academic engagement indicators. The research methodology involves data preprocessing, feature selection, dataset partitioning, model training, and performance evaluation using Accuracy, Precision, Recall, F1-Score, and Area Under the Curve (AUC). Furthermore, SHAP is employed to provide transparent interpretations of the model's predictions and identify the most influential factors contributing to dropout risk. Experimental results demonstrate that the XGBoost model achieves high predictive performance with an accuracy of 95.2%, precision of 94.1%, recall of 93.7%, and F1-score of 93.9%. The SHAP analysis reveals that cumulative GPA, attendance rate, completed credit units, and the number of failed courses are the most significant predictors of student dropout. The integration of XGBoost and Explainable AI not only improves prediction accuracy but also enhances the interpretability of the model, enabling academic stakeholders to make informed decisions and implement effective intervention strategies. The proposed framework can serve as a decision-support tool for universities in reducing dropout rates and improving student success.
Indonesian Social Media Text Classification for Mental Health Risk Detection Using Bidirectional LSTM Arief Rahman Hakim Arief; Yuni Franciska Br. Tarigan; Khairul Fadhli Margolang
Hanif Journal of Information Systems Vol. 4 No. 1 (2026): August Edition
Publisher : Ilmu Bersama Center

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

Abstract

Mental health disorders, particularly depression and anxiety, have become increasingly prevalent in Indonesia, affecting millions of individuals across all age groups. However, limited access to mental health professionals and persistent social stigma frequently prevent timely early detection and intervention. Social media platforms serve as digital diaries where Indonesian users express their emotional states, presenting a unique opportunity for automated mental health risk screening. This study proposes a deep learning approach using Bidirectional Long Short-Term Memory (BiLSTM) for classifying Indonesian social media text into three mental health risk categories: Normal (low risk), Depression (high risk), and Anxiety (moderate risk). Unlike standard LSTM, which processes text in a single direction, BiLSTM captures contextual information from both forward and backward directions — a critical advantage for understanding nuanced expressions in Indonesian informal language. A dataset of 1,488 Indonesian text samples (500 Normal, 494 Depression, 494 Anxiety) was collected from Twitter and labeled by expert annotators with an inter-annotator agreement (Cohen's Kappa) of 0.87. Comprehensive text preprocessing was applied, including case folding, noise removal, stopword elimination using NLTK, and stemming using Sastrawi. The proposed BiLSTM model was evaluated against three baseline methods: Naïve Bayes, Support Vector Machine (SVM), and standard LSTM. Experimental results demonstrate that BiLSTM achieves superior performance with 87.5% accuracy, 86.8% precision, 86.2% recall, and 86.5% F1-score, outperforming standard LSTM by 4.2% and SVM by 12.1%. A desktop application with a graphical user interface was developed for practical deployment, featuring real-time detection, confidence scoring, and prediction history logging. This research contributes an effective, reproducible, and deployable deep learning-based screening tool for mental health risk detection from Indonesian social media text.

Page 4 of 5 | Total Record : 41

 1   2   3   4   5 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 1 (2026): August Edition Vol. 3 No. 2 (2026): February Edition Vol. 3 No. 1 (2025): August Edition Vol. 2 No. 2 (2025): February Edition Vol. 2 No. 1 (2024): August Edition Vol. 1 No. 2 (2024): February Edition Vol. 1 No. 1 (2023): August Edition