cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Agis Abhi Rafdhi
Contact Email
agis@email.unikom.ac.id
Phone
+62222504119
Journal Mail Official
injuratech@email.unikom.ac.id
Editorial Address
Jl. Dipati Ukur No.112-116, Lebakgede, Kecamatan Coblong, Kota Bandung, Jawa Barat 40132
Location
Kota bandung,
Jawa barat
INDONESIA
International Journal of Research and Applied Technology (INJURATECH)
Published by Universitas Komputer Indonesia
ISSN : 28100662     EISSN : 28077229     DOI : https://doi.org/10.34010/injuratech.v1i2.5902
Core Subject : Science, Engineering,
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering
INJURATECH cover all topics under the fields of Computer Science, Information system, and Applied Technology. Scope: Computer Based Education Information System Database Systems E-commerce and E-governance Data mining Decision Support System Management Information System Social Media Analytic Data visualization Cloud computing platforms Distributed file systems and databases Big data technologies Data capture and storage Computer Architecture and Embedded Systems Geographic information system (GIS) Remote Sensing Software Engineering Internet and Web Applications Mobile Computing Hardware and physical security Mobile Computing Security management and policies Block chain Technology
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 266 Documents
 23   24   25   26   27 
Blockchain-Enabled Cryptography for Intelligent Healthcare Systems. Aniru Abudu Muhammed; Hibah Imuentinyanose Muhammed
International Journal of Research and Applied Technology (INJURATECH) Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

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

Abstract

The ongoing digital transformation of healthcaredriven by artificial intelligence (AI), Internet of Things (IoT), and cloud-based serviceshas led to unprecedented volumes of sensitive health data and novel pathways for care delivery and analytics. However, the highly distributed, heterogeneous and mission-critical nature of modern health systems exposes them to elevated risks of data breaches, tampering, and privacy-erosion. In this paper we present a comprehensive exploration of how blockchain technology, combined with advanced cryptographic frameworks, can serve as the cryptographic backbone of intelligent healthcare ecosystems. We present the architectural foundations, identity and access control models, smart contractenabled compliance, federated learning integration, interoperability and auditability mechanisms. We then examine practical case studies and evaluate performance implications. Finally, we discuss the technical, operational and regulatory challenges and highlight avenues for future researchincluding post-quantum cryptography and hybrid architectures. Our findings demonstrate that blockchain-enabled cryptography offers a promising pathway toward secure, privacy-preserving, interoperable and trustworthy healthcare systems but realising this potential requires careful design, standardisation, and empirical validation.
A Comprehensive AI-Driven Predictive Maintenance Framework with Multi-Layer Architecture, Advanced Signal Processing, and RUL Modeling for Oil Palm Processing Systems Aniru Abudu Muhammed; Hibah Imuentinyanose Muhammed
International Journal of Research and Applied Technology (INJURATECH) Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

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

Abstract

This study presents a comprehensive artificial intelligence–driven predictive maintenance framework tailored to the operational complexities of oil palm processing systems. The proposed architecture integrates Internet of Things (IoT) sensing, edge computing, advanced signal processing, and machine learning within a multi-layer structure comprising data acquisition, preprocessing, AI analytics, decision support, and maintenance execution with continuous feedback. High-frequency sensor data collected from critical equipment such as sterilizers, screw presses, turbines, and digesters are transformed into meaningful representations through time-domain, frequency-domain, and time–frequency feature extraction techniques, including Fourier transforms, wavelet analysis, and statistical descriptors. These features form the basis for robust predictive modeling using both supervised and unsupervised learning approaches, enabling accurate fault detection, anomaly identification, and Remaining Useful Life (RUL) estimation. The framework incorporates advanced prognostic models, including stochastic degradation processes, survival analysis, and deep learning architectures such as Long Short-Term Memory networks, to capture complex temporal dependencies in equipment behavior. To ensure reliability and interpretability, model outputs are complemented with explainable AI techniques and evaluated using rigorous statistical metrics and cost-sensitive optimization strategies. Deployment considerations such as edge inference, model quantization, latency optimization, and system redundancy are integrated to support real-time operation in resource-constrained industrial environments. Furthermore, a closed-loop feedback mechanism enables continuous learning, model adaptation, and performance improvement through data-driven retraining and human-in-the-loop validation.  This scalable, production-ready framework transitions oil palm processing to intelligent, condition-based maintenance. Aligned with Industry 4.0, it bridges advanced analytics with practical application to improve predictive accuracy, minimize unplanned downtime, optimize schedules, and drive overall cost savings and sustainability.
Ubuntu-principled multi-layered AI-Guardrails Framework for promoting sustainable integrity practices in Higher Education Institutions Micheal van Wyk
International Journal of Research and Applied Technology (INJURATECH) Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

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

Abstract

This study employed a systematic literature review (SLR) to synthesize the existing literature and examine how an Ubuntu-informed, multilayered AI guardrails framework can be conceptualized to promote sustainable integrity in higher education. The SLR approach is suitable for mapping emerging evidence, clarifying key concepts, and identifying research gaps. The first step was to define eligibility criteria for the types of scholarly works to be included in the SLR, with a focus on the research questions. This approach was adopted to ensure transparency and replicability. Findings indicated that existing scholarship on AI guardrails, which focuses on the ethical, technical, and procedural dimensions of the responsible use of AI and sustainable integrity in higher education, is limited. Existing AI guardrail frameworks in higher education are misaligned with ethical, relational, and community-oriented principles of Ubuntu philosophy. Finally, the Ubuntu principles were integrated with current AI guardrail frameworks to strengthen sustainable integrity practices in teaching, learning, and institutional governance. The contribution of this framework moves beyond compliance-based guardrails towards ethically internalized practices, integrates African philosophy (Ubuntu) into AI governance, and balances technology, pedagogy, and humanity to support long-term sustainability, not just the detection of misconduct.  
Enhancing A Universal Acquisition and Analysis Tool: A Scalable and Interoperable Forensic Tool for Internet of Things (IoT) Pjorn Muriuki Njue; Dennis Kaburu; David Muchangi Mugo
International Journal of Research and Applied Technology (INJURATECH) Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

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

Abstract

Digital forensics artifacts created by the Internet of Things (IoT) environment are highly fragmented, originating from diverse devices, gateways, message brokers and cloud platforms using various protocols and logging formats thus creating non-comparable logs. Modern forensic software solutions presently available do not provide adequate support for these diverse ways that IoT devices communicate with one another. The proposed Universal Acquisition and Analysis Tool (UAAT) creates a single comprehensive forensic environment in which IoT evidence can be collected, analyzed regarding the specific protocols with which the evidence was created, tracked through a cryptographic chain-of-custody, threat analyzed through machine learning techniques, and have reports generated automatically within a single deployable Java-based application (i.e., can run on any machine irrespective of OS and Hardware). The UAAT was developed using a Design Science Research (DSR) methodology and tested using the IoT-23 and CICIDS2017 benchmarks within a laboratory setting. Native and/or parallel support for the widely used IoT communications protocols of MQTT, CoAP, HTTP and TCP was added via the use of the Kafka streaming platform, as well as a protocol-based parser engine; results indicate that the UAAT was able to achieve 95% protocol compatibility, maintain an ingest throughput of 6.8 logs/second, and produced an F1 score of 96.38% for the random forest during the classification of simulated threats test case. The SHA-256 chain-of-custody engine for the UAAT identified all simulated evidence tampering instances across 1,423 records.
Geospatial As-built Drawing Management Techniques in Building Practice: A Framework for Facility Management in Nigerian Universities Rasheed Busari; Jubril Jimoh; Amos Ayoola; Najeem ADERIBIGBE
International Journal of Research and Applied Technology (INJURATECH) Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

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

Abstract

Geospatial as-built drawing management is increasingly vital in modern building practice as it enhances efficiency, performance, and facility lifecycle management. This study explores the deployment of a geospatial technology for managing as-built drawings within a Nigerian university campus. It assesses the current state of documentation, staffing capacity, and digital infrastructure required for effective implementation. Spatial data were collected using GPS and satellite imagery, processed in ArcGIS 10.8. Attribute data on buildings and staff were sourced from the university’s establishment and records office. Analyses included simple percentages and spatial hyperlinking in ArcGIS. Findings reveal that as-built drawings exist mainly in fragmented formats—paper archives and standalone digital files—with minimal geospatial referencing and limited integration into centralized systems. This fragmentation hinders efficient data retrieval, maintenance planning, and informed decision-making. Significant staffing gaps were identified, as most personnel are traditional built environment professionals lacking expertise in Geographic Information Systems (GIS), Building Information Modelling (BIM), and digital data management. Digital infrastructure deficiencies further constrain progress, including inadequate computing systems, absence of dedicated geospatial platforms, lack of centralized databases, and poor network connectivity. These limitations collectively hinder the transition to integrated geospatial as-built management. The study concludes that successful implementation requires accurate and standardized documentation, skilled interdisciplinary personnel, and robust digital infrastructure. It recommends strategic investment in training, technology, and system integration to achieve efficient geospatial as-built drawing management.
Digital Business Model Innovation for Manufacturing MSMEs Using the Business Model Canvas Approach Risqi Windu Harjono; Eddy Soeryanto Soegoto; Maripova Nodira Xamidovna
International Journal of Research and Applied Technology (INJURATECH) Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

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

Abstract

CV. Jaya Logam is a ship component manufacturing company in Bogor experiencing consistent sales growth from 310 units in 2021 to 384 units in 2025, yet all core operational processes including customer ordering, raw material procurement, and transaction recording remain entirely manual, creating a serious gap between market potential and operational capacity. This study analyzes the existing business model and designs a new digital business model using the Business Model Canvas (BMC) framework. A qualitative descriptive case study approach was employed, involving in-depth interviews with four informant categories and direct observation across three main operational areas. Data analysis followed three sequential stages: As-Is BMC mapping, SWOT analysis per BMC block to identify digital weaknesses, and To-Be BMC design as the proposed future transformation model. The results point to four BMC blocks (Channels, Customer Relationships, Key Activities and Key Resources) with critical digital deficiencies, which create an interdependent vulnerability cycle that makes the current business model unscalable. The proposed redesign encompasses six of the nine BMC blocks, with key transformations including a WhatsApp Business API-based ordering system, digital CRM for proactive customer retention, revenue diversification through consulting and maintenance services, formal recognition of digital data as a strategic asset, an integrated digital workflow replacing manual recording across order intake, inventory tracking, and production scheduling, and digitalized supplier coordination through structured procurement communication. This study contributes a practical digital transformation roadmap for CV. Jaya Logam and serves as an academic reference for Indonesian MSMEs facing similar operational challenges
Mapping the Growth Potential of Culinary MSMEs in West Java Regencies and Cities Using Open Government Data-Based K-Means Clustering Leonardo Ernesto Meba; Rahma Wahdiniwaty; Satvaldiyeva Nilufar Zoyirjonovna
International Journal of Research and Applied Technology (INJURATECH) Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

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

Abstract

Culinary MSMEs play an important role in entrepreneurship and regional economic development in areas having diverse markets and tourism potentials. The development of culinary MSMEs in various regencies and cities in West Java is uneven, emphasizing the necessity of data-driven mapping in order to precisely determine the growth potential of the regions. This paper seeks to classify the growth potential of culinary MSMEs in West Java regencies and cities using K-Means Clustering based on open government data. The data used in this paper were taken from Open Data Jawa Barat and consist of the number of projected MSMEs by regency or city and business category for 2017-2023. There were six research steps carried out in this study: data selection, data preprocessing, data transformation, data normalization, clustering, and cluster result interpretation. It was found that there were 27 regencies and cities classified into three different clusters, namely 12 regions having high potential, 14 regions having moderate potential, and one region having low potential. It can be seen that there was relatively similar percentage growth in all regions, at 43.36%. This research implies that regions that have bigger MSME clusters should have strategies for competitiveness and expansion of their markets, whereas lower potential regions would benefit from having more basic entrepreneurship strategies. This paper demonstrates that using the K-Means Clustering approach and open government data can be a useful tool for making decisions.
Digital Entrepreneurship Strategy and Suburban Food Waste Mitigation Application Prototype Luthfiyah Sakinah; Adam Mukharil Bachtiar; Nafisa Burikulovna Gulyamova
International Journal of Research and Applied Technology (INJURATECH) Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

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

Abstract

The result is that suburban culinary SMEs are confronted with the dilemma of food waste, a daily spoilage of food that they often have to bear the brunt of financial loss because of it. In this paper, we propose a digital entrepreneurship business model and a location-based application prototype for food waste reduction, using the Business Model Canvas (BMC) model and the Haversine Algorithm. Based on the Design Science Research (DSR) approach, the study includes problem identification through partner interviews, quantitative consumer surveys, and IT artifact design. Validation of the business model suggests the 15% commission scheme on the 50–70% discounted products will be perceived as a reasonable and fair loss mitigation strategy by the majority of the business owners, although facing operational friction with one partner dissent. The BMC analysis aligns the value proposition of the platform to meet the needs of balancing the consumer’s economic motives and the efficiency needs of the partner. Technologically speaking, the system uses Location-Based Service (LBS) to automatically suggest the nearest partners in real-time. Simulation test with the Haversine formula verified highly reliable output with an average deviation of 0.11 km or an error percentage of 2.05% compared with the Google Maps data, yielding a practical localized computational accuracy of 97.95%. This study strengthens the contribution to an inclusive digital ecosystem in satellite regions by way of a feasible PWA approach that furthers global SDG at mitigating food waste
Design and Development of a Web-Based Production Management Information System to Support Digital Entrepreneurship in Furniture Manufacturing: A Case Study of Prima Furniture Bandung Yogi Eka Nurdiansyah; Irfan Dwiguna Sumitra; Ganieva Nasiba Shukhrat Kizy
International Journal of Research and Applied Technology (INJURATECH) Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

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

Abstract

For small and medium-sized furniture makers, production management is still often done manually, with spreadsheets and instant-messaging chats, leaving order tracking, work scheduling and operator wage calculation vulnerable to delay, miscommunication and recording errors. A web-based production management information system for a made-to-order furniture factory is designed and built in this project. It handles sales order intake, work-order tracking through cutting, assembly and finishing, delivery and driver management and piece-rate salary computation and adds a natural-language analytics assistant to query production and sales data. Development was carried out using the Prototyping model. The cycle of communication, rapid planning, rapid design, prototype manufacturing and deployment with feedback was well suited to a scenario where requirements constantly changing on the factory floor rather than being fixed upfront. Requirements were extracted from direct observation and informal discussions with the owner and production operators, and were modelled as business-process (as-is/to-be), use case, and entity-relationship diagrams prior to implementation on a relational database with a web front end. The system was tested with blackbox testing of its core modules and a System Usability Scale (SUS) questionnaire filled out by five respondents representing the positions of administrator, sales, and production-supervisor. All the functions evaluated gave the desired outcome and the SUS score of 80.0 falls in the “Good” usability band. The results suggest that a prototyping-based web platform can pull scattered, manual furniture-production records into one real-time system, cutting recording effort, making order status traceable from intake to delivery, and giving the case-study business a firmer footing for continued growth as a digitally run enterprise
Predicting Student Dropout Using Transformer-Based Deep Learning with Interpretable Feature Analysis Lozan M. Abdulrahman; Nasiba M. Abdulkarim; Mohammed M. Ibrahim; Omar M. Ahmed
International Journal of Research and Applied Technology (INJURATECH) Vol. 7 No. 1 (2027): June, 2027 (Online First)
Publisher : Universitas Komputer Indonesia

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

Abstract

The dropout of students is a significant problem in the higher education sector, affecting the graduation rate and causing serious academic and financial implications for students and institutions. In this sense, the early prediction of students that are more likely to drop out of school is necessary for the development of strategies to prevent such an outcome. Here we present a deep learning model based on a transformer architecture to predict the dropout of students using structured educational data. The proposed model uses the Feature Tokenization Transformer (FTTransformer) with self-attention mechanisms. The dataset used was the Predict Students Dropout and Academic Success. To train the model, a pre-processing pipeline was built that included the standardization of features, median imputation, and the creation of new features that helped to identify deviations in academic performance and financial risk. The performance of the model was evaluated on a test dataset, with the following metrics: accuracy (0.881), F1-score (0.88), ROC-AUC (0.9349) and PR-AUC (0.9044). In addition, permutation feature importance was used to identify the most important features related to the dropout prediction. The results show that the tuition payment status and academic performance had the highest importance in the model. The results presented demonstrate the performance of transformer-based models and the use of interpretable deep learning models to support the decision making of higher education institutions.

Page 26 of 27 | Total Record : 266

 23   24   25   26   27 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 7 No. 1 (2027): June, 2027 (Online First) Vol. 6 No. 1 (2026): June 2026 Vol. 5 No. 1 (2025): Vol 5 No 1 (2025) Vol. 5 No. 2 (2025): December 2025 Vol. 4 No. 2 (2024): Vol 4 No 2 (2024) Vol. 4 No. 1 (2024): International Journal of Research and Applied Technology (INJURATECH) Vol. 3 No. 2 (2023): International Journal of Research and Applied Technology (INJURATECH) Vol 3 No 2 (2023): International Journal of Research and Applied Technology (INJURATECH) Vol. 3 No. 1 (2023): International Journal of Research and Applied Technology (INJURATECH) Vol 3 No 1 (2023): International Journal of Research and Applied Technology (INJURATECH) Vol 2 No 2 (2022): International Journal of Research and Applied Technology (INJURATECH) Vol. 2 No. 2 (2022): International Journal of Research and Applied Technology (INJURATECH) Vol 2 No 1 (2022): International Journal of Research and Applied Technology (INJURATECH) Vol 1 No 1 (2021): International Journal of Research and Applied Technology (INJURATECH) 2021 Vol 1 No 2 (2021): International Journal of Research and Applied Technology (INJURATECH) More Issue