BIOS : Jurnal Teknologi Informasi dan Rekayasa Komputer

Sistem Deteksi Dini Stunting Pada Balita Menggunakan Teknik Klasifikasi Dengan Algoritma C4.5 Sebagai Upaya Penekan Angka Kasus Stunting Di Puskesmas Sumberjambe Kabupaten Jember

2025-07-02T21:15:32+07:00

Stunting is a condition of impaired growth in toddlers caused by chronic malnutrition, characterized by a height that is not appropriate for their age. According to SSGI 2022 data, Jember Regency has the highest stunting rate in East Java at 34.9%, exceeding the WHO standard (<20%). This study aims to design and develop an early detection system for stunting in toddlers at Sumberjambe Public Health Center using the C4.5 algorithm method. The type of research used is quantitative research with a data mining approach using the C4.5 algorithm and the prototyping method. The object of this study is secondary data obtained from maternal cohort books and Excel-based nutrition data from Sumberjambe Health Center, which includes data on children categorized as stunted and normal. The initial dataset consisted of 1,798 entries, and after going through a pre-processing stage, 130 clean data entries were obtained and used for analysis. The data mining process resulted in a Confusion Matrix accuracy of 83.33% and produced 34 rules that were used as knowledge for the early stunting detection system. The system was developed using the prototyping method, which includes several stages from initial planning and design to testing and user evaluation. In the construction of prototype stage, the system was built using PHP programming language with the Laravel 10 framework and tested using the black-box testing method. In the deployment, delivery & feedback stage, the system was directly tested by the nutrition team at Sumberjambe Health Center and received very positive responses. Users were satisfied with the appearance and performance of the system, with no revision requests, and fully approved the proposed prototype.

Implementasi Virtual Reality dalam Visualisasi Arsitektur Kampus Menggunakan Game Development Life Cycle (GDLC)

2025-07-23T08:11:31+07:00

Campus promotions often still rely on conventional media such as brochures, mockups, or 2D videos which are less attractive to the digital generation. This presents a challenge in effectively conveying the university's image and excellence to prospective students, especially high school students. To overcome these problems, this research aims to develop a campus architectural visualization system based on Virtual Reality (VR) technology as a promotional media for Muhammadiyah University. This system was developed using the Game Development Life Cycle (GDLC) method, which includes initiation, pre-production, production, testing, and post-production stages. 3D models of the campus buildings were created using Blender and integrated into Unity to build an interactive VR environment. Key features include virtual campus navigation, detailed 3D visualizations, and interactive information presentation. Testing was conducted using the black-box method and usability evaluation. The results show that the VR application is able to provide an interesting and informative campus exploration experience. This system is expected to be an effective and modern promotional media, and is able to increase prospective students' interest in the campus.

Systematic Literature Review : Perbandingan Algoritma Round Robin dan Shortest Job First dalam Penjadwalan CPU

2025-09-03T09:00:52+07:00

The Central Processing Unit (CPU) scheduling is a crucial aspect of operating systems that significantly impacts overall system efficiency. Round Robin (RR) and Shortest Job First (SJF) are two commonly used scheduling algorithms, each with distinct characteristics. Although numerous studies have compared these algorithms, a clear consensus on the superiority of either algorithm across various workload scenarios remains elusive. This systematic literature review aims to analyze and synthesize empirical evidence from prior research (2020-2024) comparing the performance of RR and SJF algorithms. Literature searches on four major databases and study selection using the PRISMA framework with strict inclusion criteria (empirical comparative studies from 2020-2024) yielded eight articles for analysis. The synthesis of results indicates that the SJF algorithm, particularly its preemptive variant (SRTF), consistently excels in efficiency, with an Average Waiting Time (AWT) that can be over 50% lower than RR in some scenarios. Conversely, RR demonstrates superiority in response time and fairness in CPU allocation, though its performance is highly dependent on the time quantum size. The selection of an optimal algorithm is highly contingent upon system performance metric priorities, and these findings provide a foundation for the future development of hybrid algorithms.

Analisis User Experience pada Aplikasi Linkedln dengan Menggunakan Metode SUS

2025-09-22T07:38:00+07:00

LinkedIn is one of the professional social media platforms that is widely used for job searching and building a digital personal image. Although its usage is quite extensive, there are still several obstacles in user experience, such as features that are not yet fully understandable and difficulties in understanding the application's usage flow, especially for new users. This situation is the reason LinkedIn was chosen as the research object to evaluate user usability. This research aims to assess the user experience of the Linkedin application using a descriptive quantitative approach and the System Usability Scale (SUS) instrument. Data were obtained from 110 active respondents of Linkedin users through the distribution of online questionnaires. The results of the validity and reliability tests indicate that all question items are valid and consistent. The average SUS score obtained is 62.85, which falls into the 'Marginal' category. which indicates that this application is rated reasonably well by users, but still requires improvements in some aspects to provide a better experience.

Analisis Kerentanan Website SMK Muhammadiyah 2 Bontoala Makassar Menggunakan Metode OWASP (Open Web Application Security Project)

2025-09-28T12:44:37+07:00

The official website of SMK Muhammadiyah 2 Bontoala Makassar plays a crucial role as a medium for information and services. However, its significance is often not matched by a verified security posture. The primary problem addressed in this study is the potential for unidentified cybersecurity vulnerabilities on the website, which malicious actors could exploit. To address this problem, a systematic vulnerability analysis was conducted based on the Open Web Application Security Project (OWASP) Top 10 framework. The testing process combined automated scanning using the OWASP ZAP tool with manual validation via penetration testing to ensure the accuracy of the findings. The assessment successfully identified several critical security flaws, primarily in the categories of Cross-Site Scripting (XSS) (A03:2021), Security Misconfiguration (A05:2021), and Vulnerable and Outdated Components (A06:2021). These vulnerabilities directly expose the website to risks of data breaches, unauthorized content modification, and service disruption. This study concludes by providing concrete technical recommendations for administrators to mitigate the identified vulnerabilities and strengthen the website's overall security posture.

Ensemble Learning dengan Soft Voting Classifier untuk Klasifikasi Pasien Tifus di Puskesmas Balung

2025-09-30T14:39:44+07:00

Typhoid fever remains a significant public health problem in Indonesia, particularly in areas with limited medical facilities. This study aims to develop an automatic classification model for typhoid diagnosis using an ensemble learning approach based on the Soft Voting Classifier. The model combines three base algorithms, Logistic Regression, Random Forest, and Gradient Boosting, to enhance predictive accuracy. The dataset was obtained from Balung Primary Health Center, Jember Regency, consisting of 510 patient records with typhoid symptoms. Experimental results show that the ensemble model achieved an accuracy of over 92%, outperforming individual models. Furthermore, adequate precision and recall indicate the model’s potential to support rapid and accurate medical diagnosis. These findings demonstrate that the Soft Voting Classifier can serve as an effective tool to assist healthcare workers, especially in resource-limited settings, in improving the quality of typhoid fever diagnosis.