Journal of Technology and Informatics (JoTI)

K-Means Clustering untuk Analisis Tren Peminjaman Buku di Perpustakaan

Lidya Rosiana, Imam Yuadi — Mon, 28 Apr 2025 00:00:00 +0700

This study aims to analyze book borrowing trends in libraries using the K-Means Clustering algorithm in Orange Data Mining. The data used in this research includes historical book borrowing records, such as borrowing frequency, book categories, and borrowing times. The study clusters the data to identify significant patterns and trends. The analysis process begins with data preprocessing, including data cleaning, normalization, and transformation. Subsequently, the K-Means algorithm is applied to divide the data into several clusters based on similarities in borrowing patterns. The results show that books in certain categories, exhibit distinct borrowing patterns. The generated clusters provide insights into the characteristics of groups of book titles with high borrowing intensity and book titles that tend to be borrowed at specific times. These insights can be utilized for more effective book collection management, the development of library promotion strategies, and the creation of book recommendation systems. This study demonstrates that the K-Means Clustering algorithm is an effective tool for library data analysis, enabling libraries to understand user needs and improve the services they provide.

Pengembangan Sistem Prediksi Harga dan Rekomendasi Mobil Bekas Berbasis Machine Learning

Mon, 28 Apr 2025 00:00:00 +0700

The used car sales business in Indonesia has been experiencing rapid growth, driven by increasing market demand. However, determining the price of used cars remains a challenge due to various influencing factors such as the year of production, mileage, and vehicle specifications. This research develops a web-based used car price prediction system using the XGBoost Regressor algorithm. The data used undergoes preprocessing and hyperparameter tuning to produce a high-performance model (R²: 97.79% on training data and 89.90% on testing data, MSE: 2.3129, RMSE: 1.5208). Additionally, the system provides a car recommendation feature using a Rule-Based Method, allowing users to filter vehicles based on specific criteria. The results demonstrate that this system effectively assists both buyers and sellers in making more informed, efficient, and transparent decisions in used car transactions.

UI/UX Design of a Web-Based Student Organizations System Using the Design Thinking Method Approach

Adlan Nugroho, Joko Purwanto, Muhammad Abdul Muin Muin, Fajar Mahardika — Mon, 28 Apr 2025 00:00:00 +0700

A web-based Student Organization System (Student organizations) is a platform used to manage activities and information about student organizations in higher education institutions. However, in many cases, many existing systems lack an intuitive user interface (UI) and adequate user experience (UX), which causes difficulties in usage and a lack of user engagement. Therefore, this research aims to design a web-based Student organizations system using the Design Thinking method consists of five main stages: Empathize, Define, Ideate, Prototype, and Test. In this study, the first stage was conducted through interviews and surveys with users to understand their problems and needs. The next stage involved defining the identified issues, followed by brainstorming and generating design ideas that fit the requirements. The developed interface prototype was then tested through user testing to evaluate user experience and system functionality. The results of this study were a user interface design that is simpler, easier to navigate, and meets the specific needs of users. Testing of the prototype showed significant improvements in terms of ease of use and user satisfaction. Thus, the Design Thinking approach has proven to be effective in designing a web-based Student organization’s UI/UX system that better aligns with user expectations. The hypothesis test accepted the application with a user reception rate of 86%. Thus, the system falls into the "very strong" category, who stated that a result percentage between 81% and 100% indicates a very high level of strength in testing. Therefore, the developed system is considered feasible for implementation.

Perancangan Aplikasi EMKASADA untuk Penjadwalan Kegiatan Perkuliahan Program Studi Sains Data UPN Veteran Jawa Timur

Mon, 28 Apr 2025 00:00:00 +0700

The development of information technology has encouraged innovation in various fields, including education. Lecture scheduling is one important aspect that requires special attention to ensure efficient and effective use of resources. The EMKASADA application improves efficiency in lecture scheduling by automating the process of preparing schedules, thus reducing the time and manual effort in managing schedules. With features such as dashboards, lecturer data, courses, days, sessions, rooms, lecturers, and automatic scheduling, this system is able to speed up the schedule preparation process and optimize the allocation of available resources. In terms of effectiveness, the EMKASADA application ensures that scheduling is more optimal by minimizing the possibility of clashes between lecturer schedules, courses, and rooms. With the waterfall method approach, the system is developed in a structured and systematic manner, following the stages from requirements analysis to maintenance. Testing was conducted using the black box testing method to ensure all application features, such as dashboards, lecturer data, courses, days, sessions, rooms, lecturers, and scheduling, function properly. The test results show that the features in the EMKASADA application function properly and are able to increase efficiency in scheduling lectures.

Challenge and Opportunity of Mobile Banking in Afghanistan

Mohammad Fahim Naseri, Qurban Ali Frugh, Qamaruddin Shamsi — Wed, 30 Apr 2025 00:00:00 +0700

Mobile banking is a major advancement in information technology, transforming the banking system by enabling users to conduct transactions anytime, anywhere. In Afghanistan, it was first introduced in 2017 by Azizi Bank, leading the way in accessible banking. However, several challenges remain. This study examines the challenges and opportunities of mobile banking in Afghanistan using a mixed-methods approach. Data was collected through surveys and interviews. Findings show that only 12% of respondents see mobile banking as secure and convenient, while 88% express concerns over cybersecurity risks, network reliability, weak internet infrastructure, unstable income, and lack of trust in banking services. The study also highlights key barriers such as low digital literacy, regulatory challenges, limited infrastructure, low income levels, public distrust after political transitions, and poor internet access. Despite its potential, overcoming regulatory, infrastructural, and socio-economic challenges is crucial for the growth of mobile banking in Afghanistan. The result is mobile banking in Afghanistan is currently facing major problems that investment in this sector has not been made and what is needed, mobile banking services in Afghanistan have not grown.

Pemanfaatan Machine Learning dalam Prediksi Rating: Studi Kasus pada Data Abstrak Publikasi Ilmiah

Wed, 30 Apr 2025 00:00:00 +0700

As the volume of scientific publications increases, the need for automated approaches to evaluate and analyze abstracts becomes increasingly important. This research not only aims to predict the abstract rating of scientific publications using machine learning algorithms, but also offers a unique approach by integrating regression and classification analysis to evaluate the relevance of abstracts more comprehensively. Four main models, namely XGBoost Regressor, Random Forest Regressor, Support Vector Regressor (SVR), and K-Nearest Neighbors Regressor (KNN), are evaluated for this task. The dataset is processed through preprocessing stages which include removing duplications, text representation using TF-IDF, handling data imbalances with Synthetic Minority Oversampling Technique (SMOTE), and dimension reduction using Truncated Singular Value Decomposition (SVD). The research results show that SVR provides performance the best with the lowest Mean Absolute Error (MAE) value of 0.4980, Mean Squared Error (MSE) of 0.5237, and the highest R² of 0.7321. XGBoost and Random Forest show competitive performance with advantages in computational efficiency and prediction stability respectively, while KNN provides varying results depending on the data distribution. Dimensionality reduction using Truncated SVD successfully preserves more than 70% of the initial variance, enabling higher computational efficiency without losing important information. This research makes a significant contribution in supporting machine learning-based decision making, especially in the analysis of abstracts of scientific publications. This approach can be further developed through exploration of ensemble or hybrid models, as well as testing on larger datasets to improve generalization and accuracy.

Implementation of UAT and Blackbox Methods in the Android-Based Prayer Collection and News Portal Application of PP El-Bayan

Nur Moniroh, Rafiq Chasnan Habibi — Wed, 30 Apr 2025 00:00:00 +0700

PP El-Bayan is a pesantren located in Cilacap. One of the books taught at this pesantren is Aurod, which contains a collection of prayers, poems, and guidelines for worship. Despite being in the digital age, PP El-Bayan does not yet have an application that includes Aurod and a pesantren news portal, so students are still required to bring the physical Aurod book in order to practice the prayers. This situation also indicates that the pesantren does not yet have a dedicated digital platform to share Islamic news and articles. This study employs the prototype method, which consists of six steps: first, gathering requirements and analyzing the existing system; second, quickly designing a model; third, creating a prototype; fourth, presenting the prototype; fifth, making revisions to the prototype if necessary based on feedback during the presentation and finally. The goal of this research is to develop an application that presents the prayers taught at PP El-Bayan and provides access to the latest news and Islamic articles related to the pesantren. This study resulted in the Bayanian application, an Android application containing a collection of prayers and news from Islamic boarding schools along with various additional features, which are expected to provide greater benefits to its users. The hypothesis of testing this material was accepted from the application with a user acceptance test, namely Good. with a result of 87.7%, so that the system is categorized as very strong according to Riduwan (2008), if the percentage results obtained reach 81% -100% then the test results can be said to be very strong so that the system that has been created can be implemented.

Strengthening Web-Based Login Security Using Vigenère Cipher and AES ENCRYPT() Method in MySQL

Fri, 02 May 2025 00:00:00 +0700

As technology advances further, more crimes are being committed on social media. These days, people can connect to the internet using technological devices like PCs (Personal Computers) or portable electronic devices like smartphones or tablets. This study presents a dual-layer encryption system combining the Vigenère Cipher and MySQL’s AES_ENCRYPT() to enhance the security of web-based login systems. The system encrypts user credentials on the client side using the Vigenère Cipher and applies additional encryption on the server side with AES_ENCRYPT(). This approach ensures secure data transmission and storage, reducing risks of plaintext exposure and unauthorized access. Comparative testing demonstrated that the dual-layer encryption method significantly improves resistance to brute-force attacks and database breaches compared to conventional techniques like SHA-256. Encrypted credentials remain secure even in the event of a database compromise, as decryption requires the correct secret keys. The system’s design also highlights the importance of robust key management to maintain data confidentiality and integrity. While this method introduces minor performance overhead and requires careful implementation, its advantages in safeguarding sensitive user information outweigh these limitations. This dual-layer approach is particularly suited for applications demanding high-security standards, making it a viable solution for mitigating contemporary cyber threats effectively.

Implementasi Sistem Informasi Penghitung Berat Badan Ideal Balita (SIPEBABA) berbasis Website dengan Waterfall

Putu Agisna Fransisco Sara, I Ketut Rama Pradipta, Bella Yasinta Usman — Fri, 02 May 2025 00:00:00 +0700

The growth and development of toddlers is a very important thing for parents to pay attention to. One thing that needs to be considered is the toddler's weight. Toddler weight is an anthropometric measure used to detect growth rate and nutritional status. Posyandu is a party that plays an active role in handling toddlers starting from checking their weight, giving vaccinations, and regular visits. Posyandu XYZ is one of the Posyandu that has implemented technology in the form of a website. However, the website has not been implemented optimally for posyandu services because it cannot be used to facilitate the implementation of services for toddlers and the elderly. In this research, a website-based application for calculating the ideal weight of toddlers was designed using the Laravel framework and the Waterfall method. This research produces a website-based information system for calculating the ideal weight of toddlers (SIPEBABA) and tested using SUS with a score of 77.90. This application can be used by Posyandu XYZ to maximize the efficiency of their employees' work.

A Hybrid Framework for Securing 5G-Enabled Healthcare Systems

Alton Mabina — Tue, 06 May 2025 00:00:00 +0700

The rapid adoption of 5G technology in healthcare introduces significant challenges regarding data privacy and security. This paper proposes a hybrid framework integrating blockchain, zero-trust architecture (ZTA), and AI-driven threat detection to address these challenges. Blockchain ensures secure, tamper-proof data storage, while ZTA strengthens access control by continuously verifying users and devices. AI contributes by providing real-time threat detection and dynamic response capabilities, making the system more resilient to evolving cyber risks. A systematic literature review was conducted to analyze existing frameworks and identify gaps in 5G healthcare security. The findings reveal that while individual technologies such as blockchain and ZTA are well-established, their integration into a cohesive framework remains underexplored. The proposed hybrid solution effectively mitigates the risks associated with 5G networks by offering a multi-layered security approach. This research contributes to the field by proposing a scalable, adaptable security model suitable for 5G-enabled healthcare systems. Future research should focus on empirical validation, scalability testing, and exploring lightweight alternatives to blockchain and AI for resource-constrained environments. Additionally, investigating the integration of emerging technologies like quantum computing and 6G networks will further enhance the framework’s security capabilities. This study provides a foundation for developing secure, privacy-preserving systems for healthcare in the 5G era.