cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Aufa Rizka Azzumi
Contact Email
garuda@apji.org
Phone
+6285156704080
Journal Mail Official
aufa.r.azzumi@stikes-ibnusina.ac.id
Editorial Address
Jalan Raya Ajibarang Km 1 Banyumas, Jawa Tengah, Kab. Banyumas, Provinsi Jawa Tengah, 53163
Location
Kab. banyumas,
Jawa tengah
INDONESIA
Saber: Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Published by Sekolah Tinggi Ilmu Kesehatan Ibnu Sina Ajibarang
ISSN : 30252776     EISSN : 3025342X     DOI : 10.59841
Core Subject : Science,
Computer Science & IT
hasil penelitian mengenai Ilmu bidang Teknik Informatika, Sains dan Ilmu Komunikasi, sebagai media bagi para dosen, guru, peneliti dan para praktisi dalam bidang teknologi informasi dari seluruh Indonesia
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 296 Documents
 24   25   26   27   28 
Klasifikasi Perilaku Berbagi Informasi Generasi Z di Media Sosial Menggunakan Decision Tree Berbasis Web Sri Dewi Rahmawati; Cherlina Helena P P; Tantik Sumarlin
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.3883

Abstract

The swift expansion of social media utilization has positioned Generation Z among the primary demographics in acquiring and disseminating information. The substantial frequency of social media engagement along with the standard of information obtained impacts information-sharing behaviour, rendering a classification model essential for determining behavioural patterns. This research seeks to apply the Decision Tree algorithm to classify the information-sharing behaviour of Generation Z according to the variables of Information Quality (X1) and Social Media Usage Intensity (X2), as well as to deploy the classification model within a web-based system. The inquiry utilized a quantitative methodology adopting the CRISP-DM framework, comprising Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. The empirical data were gathered via questionnaires administered to 113 Generation Z participants actively engaging with social media across Semarang Regency. The classification model was constructed utilizing RapidMiner, whereas its effectiveness was assessed employing a Confusion Matrix. The findings demonstrated that the Decision Tree algorithm attained an accuracy rate of 82.61% and produced 13 decision rules capable of classifying information-sharing behaviour into three tiers: high, moderate, and low. The constructed model was effectively integrated into a web-based application built with PHP and MySQL, allowing the classification procedure to operate automatically according to user entries. These outcomes reveal that the Decision Tree algorithm not merely delivers a classification model with robust performance, but also admits effective integration into a web-based system to assist the classification of Generation Z's information-sharing behaviour.
Evaluasi Komparatif Kinerja Varian Model Whisper Melalui Hyperparameter Tuning pada Sistem Input Transaksi Keuangan UMKM Berbasis Suara Zulfikar Yusya Mubarak; Yuni Anggraeni
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.3902

Abstract

Voice based transaction input offers a practical alternative for reducing delayed and inaccurate financial recording in micro, small, and medium enterprises (MSMEs), particularly when owners record transactions while serving customers. This study empirically evaluates three Whisper automatic speech recognition variants for a voice driven financial transaction input system. The research workflow includes audio preparation, utterance segmentation, manual ground truth transcription, transaction field labeling, parameter efficient fine tuning using Low Rank Adaptation (LoRA), and hyperparameter tuning of learning rate and training epochs. The dataset comprises 28 transaction recordings from MSMEs in the Cilacap area, segmented into 140 short utterances containing local product names, transaction intents, and monetary values. Whisper tiny, Whisper base, and Whisper small are evaluated under zero shot and LoRA fine tuning settings using Word Error Rate (WER), Character Error Rate (CER), transaction field accuracy, and inference latency. The results show that Whisper small with a learning rate of 2e 4 and 20 epochs provides the best overall performance, achieving a WER of 5.86%, CER of 2.64%, field accuracy of 92.86%, and average latency of 1.36 seconds. Whisper base remains a practical alternative when lower latency is prioritized. These findings indicate that Whisper can support voice based transaction recording for MSMEs, particularly when nominal validation and user confirmation are incorporated before financial data are stored.
Karakterisasi Fitur dan Deteksi URL Phishing pada Dataset Indonesia Menggunakan LASSO+ dan Random Forest Wendy Sarasjati; Edy Winarno; Faiq Madani
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.3904

Abstract

Phishing URL detection using machine learning often achieves high performance, but feature relevance may vary across datasets and collection contexts. This study analyzes the characteristics of an Indonesian phishing URL dataset and evaluates a compact detection model that prioritizes phishing recall. The dataset contains 2,054 balanced phishing and legitimate URLs represented by 70 lexical, structural, domain/WHOIS, infrastructure, and reputation features. Interquartile Range (IQR) was used to identify statistically extreme values, while Pearson correlation and Mutual Information were used to examine feature-target associations. LASSO+ was applied to reduce redundant features, and Random Forest with uncertainty-weighted bootstrap sampling was evaluated using stratified 10-fold cross-validation. The results show that 92.84% of the URLs contain at least one statistically extreme feature value. Response time, IP information, domain reputation, and hyperlink-related features show prominent associations with the target. LASSO+ reduces the feature set by approximately 36.3% without reducing Random Forest performance. The complete model achieves the highest recall of 0.9942 ± 0.0050 and the lowest false-negative count of six. These findings show that feature relevance needs to be validated for the target dataset and that a compact feature representation can support recall-oriented phishing detection.
Pengembangan Sistem Digitalisasi dan Agregasi Berita Budaya Melayu Kepulauan Riau Sherly Agustini; Andi Amin Amirul Mukminim; Muhammad Ilham Wijaya
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.3909

Abstract

Malay culture in the Riau Islands, is vulnerable to displacement due to the high heterogeneity of society, while digital media specifically collecting Malay cultural news is still very limited. This study aims to design a Digitization and Aggregation Application for Malay Cultural News in the Riau Islands as an integrated information platform for the community. The research is software engineering in nature so it does not use statistical hypotheses, but instead applies the Waterfall model that includes Requirements Analysis, System Design, Implementation, Testing, Deployment, and Maintenance, supported by modeling theories of Data Flow Diagrams and Entity Relationship Diagrams. The research input is in the form of secondary data from literature studies and web scraping from several news portals, including articles, categories, events, media, and user data. The system is implemented using Laravel 11, PHP 8, MySQL, and Bootstrap 5, then tested using Black Box Testing on ten main feature scenarios and all tests are declared successful. The results of the study show that the application is able to display and aggregate Malay cultural news automatically from various sources into one platform. Further development is recommended at the operational deployment stage, adding news portal sources, and conducting non-functional and usability testing. These results are important as a reference for an automated aggregation-based local cultural digitization model that supports the preservation of Malay identity amidst urban social dynamics.
Dinamika Batasan Privasi Komunikasi Pengguna Judi Online dalam Relasi Keluarga dan Interaksi Sosial di Kabupaten Pasuruan Muhammad Slamet Basofi; Nurma Yuwita
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.3922

Abstract

This study is motivated by the development of digital technology, which has contributed to the increasing practice of online gambling conducted personally and concealed from family members and the social environment. This condition is closely related to communication privacy management, particularly when individuals attempt to conceal information that may lead to stigma and interpersonal conflict. This study aims to analyze how online gambling users establish privacy rules, manage privacy boundaries, and deal with boundary turbulence in family and social relationships. The study employed a qualitative method with a descriptive approach. The informants consisted of five online gambling users in Pasuruan Regency selected through purposive sampling. Data were collected through semi-structured interviews, observation, and documentation, and were analyzed using the interactive model of Miles, Huberman, and Saldaña, which involved data reduction, data display, and conclusion drawing and verification. The findings indicate that online gambling users selectively apply privacy rules by concealing their activities from family members while being more open with trusted friends or individuals with similar experiences. Privacy boundaries are maintained by restricting device access, deleting browsing history, and concealing activities and transactions. When the information is disclosed, boundary turbulence occurs in the form of anger, arguments, disappointment, anxiety, and strained relationships. Privacy management is dynamic and influenced by trust, stigma, and the risk of conflict. Open family communication and a nonjudgmental approach are necessary to reduce interpersonal conflict.
Pengaruh Variasi Filter Udara terhadap Emisi dan Performa Yamaha NMax 155 cc Buang Turasno; Dimas Aril Pratama; Aziz Kurniawan; Bagus Febriyana
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.3931

Abstract

This study investigates the effect of air-filter variation on exhaust emissions and engine performance of a 155 cc Yamaha NMax motorcycle. An experimental method was applied using three filter configurations: original, canvas, and racing. Engine performance was measured using a chassis dynamometer, while exhaust emissions were measured using a gas analyzer. Each filter was tested repeatedly under controlled conditions using Pertamax RON 92, standard engine condition, engine temperature of 60–70 °C, and tire pressure of 30–32 psi. Performance measurements were conducted at engine speeds of 3,000–8,000 rpm and repeated three times for each filter; emission measurements were repeated five times for each filter at idle. The results show that filter characteristics affected the power and torque curves, particularly at medium-to-high engine speeds. The racing filter produced the highest average peak power of 9.47 HP and peak torque of 10.52 Nm based on the three repeated measurements, while the canvas filter showed the lowest peak power. For emissions, the original, canvas, and racing filters produced average CO concentrations of 0.300%, 0.280%, and 0.112%, respectively, while HC concentrations were 64.4, 51.6, and 35 ppm. Compared with the original filter, the racing filter reduced CO by 62.7% and HC by 45.7%. The findings indicate that a lower intake-flow restriction can support engine performance while reducing incomplete-combustion indicators under the tested conditions.
Pengaruh Data Quality dan Analytics Capability terhadap Kualitas Keputusan Manajerial: Peran Mediasi Data-Driven Culture pada Organisasi Perkantoran Febri Adi Prasetya; Cheesya Siska Adhiati; Indra Ava Dianta
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.3968

Abstract

The growing use of information systems and analytical technologies has encouraged organizations to adopt data-driven approaches to managerial decision-making. However, the availability of high-quality data and analytical tools does not automatically produce better decisions when data use has not become part of organizational routines. This study examines the effects of Data Quality and Analytics Capability on Managerial Decision Quality and investigates the mediating role of Data-Driven Culture in office-based organizations. A quantitative explanatory design was employed involving 220 respondents who routinely use data, information systems, digital reports, dashboards, spreadsheets, or analytical tools in their work. The research model was tested using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results show that Data Quality and Analytics Capability have positive and significant effects on Data-Driven Culture. Analytics Capability and Data-Driven Culture also positively and significantly affect Managerial Decision Quality, whereas the direct effect of Data Quality on Managerial Decision Quality is not significant. Furthermore, Data-Driven Culture mediates the relationship between Data Quality and Managerial Decision Quality through an indirect-only mediation mechanism and mediates the relationship between Analytics Capability and Managerial Decision Quality through complementary mediation. These findings indicate that reliable data alone is insufficient to improve managerial decisions unless organizations institutionalize data use in their working culture. The study highlights the importance of integrating data quality, analytical capability, and a data-driven culture to strengthen evidence-based managerial decision-making and provides practical guidance for organizations seeking to improve the managerial value of their information resources
Kerangka Ekosistem Teknologi Cerdas Berbasis AI melalui Konvergensi Teknik Elektro dan Informatika Ananto Tri Sasongko
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.3971

Abstract

The rapid development of Artificial Intelligence (AI), the Internet of Things (IoT), edge–cloud computing, and cyber-physical systems has increased the need for an integrated architecture capable of connecting physical sensing with intelligent decision-making and real-world actions. This study aims to formulate an AI-based smart technology ecosystem framework through the convergence of Electrical Engineering and Informatics. A descriptive qualitative approach was employed through a conceptual literature review and qualitative synthesis of recent scientific publications related to AIoT, IoT, edge–cloud computing, smart cities, digital twins, cyber-physical systems, and cybersecurity. The findings identify five interdependent functional layers, formulated as the Sensing–Connectivity–Computing & Data–Intelligence–Action (SCCIA) framework. Sensing transforms physical phenomena into digital data; connectivity enables reliable and timely data transmission; computing and data services provide scalable data management and processing; intelligence transforms data into predictions, recommendations, and decisions; while action closes the cyber-physical loop by translating decisions into physical or organizational responses. The study further identifies cybersecurity, interoperability, human oversight, and responsible AI governance as cross-layer requirements. The proposed SCCIA framework provides an integrative conceptual model for designing, evaluating, and developing reliable, interoperable, secure, and responsible AI-based smart technology ecosystems.
Strategi Komunikasi Digital Lembaga Publik melalui Instagram: Analisis 4C pada Akun @lps_idic Medo Maulianza; Odilia Siringo Ringo; Nur Asni Gani
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.3990

Abstract

This study aims to analyze the management strategy of the @lps_idic Instagram account as a publication medium for the Indonesia Deposit Insurance Corporation (LPS) using the 4C framework, comprising context, communication, collaboration, and connection. The study employed a qualitative approach within a constructivist paradigm. Data were collected through observation of Instagram account activities, interviews with five informants directly involved in communication management and content production, and documentation. The data were examined using thematic analysis through transcription, coding, categorization, and interpretation. The findings indicate that, in terms of context, LPS delivers financial literacy and institutional information by following current trends, using semi-formal language, and maintaining content originality. Regarding communication, LPS develops two-way interaction by responding to comments, direct messages, and various forms of audience feedback. In collaboration, LPS engages Key Opinion Leaders to expand publication reach and increase audience engagement. In connection, relationships with followers are maintained through polls, quizzes, giveaways, live broadcasts, and the distinctive audience designation “Sahabat LPS.” These strategies contribute to increasing account visibility and public understanding of the roles and functions of LPS. The study highlights the importance of adaptive, interactive, collaborative, and relationship-oriented content management in strengthening public institutional communication.
Evaluasi Aksesibilitas Website Layanan Publik Kabupaten Kudus Berdasarkan WCAG 2.1 AA Menggunakan aXe DevTools Muhammad Sholikhan; Fujiama Diapoldo Silalahi; Richma Hidayati
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v4i3.4092

Abstract

Digital public services require websites that are not only informative but also accessible to all citizens, including persons with disabilities. This study aims to evaluate the accessibility of public service websites in Kudus Regency based on the Web Content Accessibility Guidelines (WCAG) 2.1 Level AA using aXe DevTools. A descriptive evaluative approach was applied to eight public service websites: the official Kudus Regency Government portal, PPID Kudus, Population and Civil Registration Office, Social Affairs Office, Health Office, Communication and Informatics Office, SIMPONI/Complaint Service, and Pro InvestKu/DPMPTSP. Five key pages were examined from each website, resulting in 40 audited pages. The data were analyzed based on the number of issues, average issues per page, risk category, and dominant accessibility violation patterns. The audit identified 1,090 accessibility issues across 40 pages, with an average of 27.25 issues per page. The highest number of issues was found on the official Kudus Regency Government portal with 270 issues, followed by SIMPONI/Complaint Service with 207 issues. The lowest number was found on the Health Office website with 66 issues. The most frequent issues included insufficient color contrast, missing alternative text for images, non-descriptive links, buttons without accessible names, frames without accessible names, inadequate form labels, and improper ARIA structures. Based on the POUR principles, the dominant problems were related to perceivable, operable, and robust aspects. These findings indicate that local public service websites require systematic improvements in visual design, semantic structure, assistive technology compatibility, and periodic accessibility audits.

Page 26 of 30 | Total Record : 296

 24   25   26   27   28 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 4 (2026): Oktober: Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 3 (2026): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 2 (2026): April : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 4 No. 1 (2026): Januari : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 3 No. 4 (2025): Oktober: Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 3 No. 3 (2025): Juli : SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 3 No. 2 (2025): April : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 3 No. 1 (2025): Januari : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 2 No. 4 (2024): Oktober : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 2 No. 3 (2024): Juli : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 2 No. 2 (2024): April : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 2 No. 1 (2024): Januari : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 1 No. 4 (2023): Oktober : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi More Issue