cover
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)
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
Articles 272 Documents
Development of an ISP Partnership Business Model Using Business Model Canvas, SWOT, and AHP Deni Kurniawan; Rahma Wahdiniwaty; Rano Khamidovna Nosirova
International Journal of Research and Applied Technology Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i1.20672

Abstract

The growth of the internet service provider industry has intensified competition in partnership-based business, necessitating the use of more structured and organized business partnership strategies. Although previous studies have combined the Business Model Canvas (BMC), SWOT analysis, and the Analytical Hierarchy Process (AHP), only a few have applied the concept of an internet service provider partnership business. This study aims to design a partnership business model for an internet service provider company by integrating the BMC, SWOT, and AHP methods. The mixed method that will be used in the study involves interviewing, observation, company documentations, and comparison questionnaires. The role of the Business Model Canvas (BMC) is to aid in analysis of the current business model, SWOT will be utilized in order to create strategic alternatives, and AHP will be used to rank the alternatives. From the research, the two main areas which need attention are increasing the ISP Network by developing new marketing/community partnerships (SO1), and enhancing the service improvement using integrated digital services (SO2). The two areas will be developed further into a Business Model Canvas. In this research, a framework of decision making that integrates BMC, SWOT analysis, and AHP is suggested to effectively transform the organization’s strategy into a BMC for ISPs. This framework could be used theoretically as a reference for integrating the strategy and business modelling and practically for designing the collaborative business model
Designing a Digital Business Model for Private Tutoring in Bandung Using Business Model and Value Proposition Canvases Mochamad Yoga Adijaya; Irfan Dwiguna Sumitra; Khurvalieva Tarmiza Latipovna
International Journal of Research and Applied Technology Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i1.20673

Abstract

Nowadays, Educational Technology (EdTech) is becoming increasingly more significant for the process of modern instruction, assisting students and parents in many processes. However, local private tutoring providers across Bandung face commercial pressures from expanding national EdTech firms. Because small tutoring micro-enterprises rely on manual administrative workflows and rigid face-to-face instruction, it creates the issue where they struggle to keep pace with changing parent and student preferences. This study examines the baseline (As-Is) operations connected to a local private tutoring enterprise, Les Ngaji Bandung. This is done for the purpose of identifying operational bottlenecks and constructing a scalable digital business model (To-Be). For this purpose, a qualitative case study was applied. This was carried out by means of data collection including semi-structured interviews across internal and external stakeholders, field observations, as well as internal record audits. Empirical validity was cross-checked through source triangulation. In this study, the Business Model Canvas (BMC) and Value Proposition Canvas (VPC) served as analytical tools to enable classification of operational failures. These failures are paper-based administration, hyper-localized customer recruitment, rigid session scheduling, and absent student progress tracking. Based on these findings, a lightweight hybrid digital business model is proposed. This model incorporates WhatsApp Business API, QRIS payment settlement, hyper-local SEO, and a streamlined Learning Management System (LMS). As results, this paper presents an empirical conceptual blueprint. In turn, this gives practical insights for educational micro-enterprises to improve operational efficiency and market relevance.
Analysis of Barriers to PoS application users in MSMEs based on Google play store review Wildan Zulfikar Djunaedi; Adam Mukharil Bachtiar; Akhrarova Shoira Batirovna
International Journal of Research and Applied Technology Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i1.20691

Abstract

Transformation to digital through Point of Sale (POS) software can offer a lot of operational efficiency for MSMEs but the adoption is still not optimal because of the limitations of the users themselves. In this research, we will seek to explore, categorize, and prioritize the main operational challenges faced by MSME entrepreneurs using the Kasir Pintar app. Using the quantitative approach in text mining, the data collection process used a total of 10,000 user reviews from the Google Play Store on 13 July 2026. Filtering out low ratings (1 & 2) provided 421 reviews and after preprocessing (folding, cleaning, tokenizing, normalization, preserving stopwords for negation semantics, and Sastrawi stemming), we had 395 cases. Based on the results, the most frequent words or tokens include “tidak” (229 times), “daftar” (61), “data” (55), “masuk” (51), “akun” (50), and “barang” (45). The above complaints have been systematically synthesized to formulate a new barrier taxonomy consisting of four categories: technical and system barriers (failure of authentication and OTP), integration and data barriers (data loss and failure of receipt printer connection), customer service barriers (non-responsive helpdesk support) and commercial barriers (re-registration issues and price sensitivity). In practice, it emerges from this study that the instability of the software causes a vicious multiplier effect, forcing the merchants to rely on their inefficient manual record keeping during peak sales time, and losing customer trust and increasing application churn. In the context of PoS application development, these insights provide strategic priorities in the form of developing multi-channel OTP authentication (whatsapp and email) and offline first local synchronization to avoid data loss, along with SLA based customer support
A Digital Platform Ecosystem for Circular Economy Implementation: Design and Development of the Toraja Coffee Cascara Value Chain Management System Belo Tarran; Eddy Soeryanto Soegoto; Farmonov O'ktam Ne'matovich
International Journal of Research and Applied Technology Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i1.20732

Abstract

Toraja coffee pulp, typically wasted in post-harvest processing, presents untapped economic potential as a premium cascara tea product. This study develops a comprehensive digital business framework to transform this agricultural byproduct into a sustainable commodity. Employing a descriptive qualitative strategy grounded in Design Science Research Methodology (DSRM), the research constructed novel artifacts addressing practical challenges in cascara commercialization: a digital platform eliminating supply chain intermediaries, a Triple Layer Business Model Canvas balancing economic, environmental, and social dimensions, and a mobile-based farmer education system. The DSRM approach emphasized iterative development of these models and systems through stakeholder engagement, including in-depth interviews with farmers and processors, focus group discussions with cooperatives, and pilot implementation with selected farmer groups. Qualitative data were analyzed using thematic coding and content analysis. Results demonstrate significant synergy between digital platform technology and circular business models, with the digital platform reducing supply chain inefficiencies, improving farmer profit margins, and enhancing transparency, while structured farmer education standardizes coffee pulp quality according to international hygiene criteria. These findings reveal that integrating digital innovation, circular economy principles, and targeted farmer education generates substantial value-added benefits across economic, environmental, and social dimensions. The study concludes that this integrated approach, developed through rigorous design science methodology, creates viable pathways for establishing a sustainable cascara tea ecosystem in Toraja, simultaneously maximizing economic opportunity for farmers while minimizing environmental impact.
Comparative Analysis of Machine Learning Regression Algorithms for Predicting Social Media Addiction Levels Among University Students Daris Rifaldi Setiana; Hidayat; Rifaldi Maulana; Daffa Wirdiyan Hassan; Dostnazar Ximmataliyev
International Journal of Research and Applied Technology Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i1.20743

Abstract

An increased use of social media platforms by university students has raised some concerns about their possible addiction, which might result in negative effects on their mental health, sleep and academic achievement. Addiction assessment to social media can be done through questionnaire-based tools that cannot effectively capture the interrelations between variables. In this study, the development and evaluation of machine learning regression models for predicting social media addiction of university students will be discussed. The dataset comprises the survey data having the dependent variable, Addicted Score, and three independent variables: Average Daily Usage Hours, Mental Health Score, and Sleep Hours per Night. Three regression algorithms, including Linear Regression, Decision Tree Regression and Support Vector Machine (SVM) have been compared using Orange Data Mining software. Models have been evaluated based on the fivefold cross-validation with five performance metrics: MSE, RMSE, MAE, MAPE and R². Based on the experiment, it was found that Linear Regression had the highest accuracy with R² of 0.915, MSE of 0.215, and RMSE of 0.464. The R² score of Decision Tree Regression was found to be 0.907, while for SVM it was 0.879. It can be seen from these results that there is linearity amongst the relationships between the different variables in the dataset which made Linear Regression give superior generalization performance over other regressors. This paper has shown that the use of regression using machine learning gives an efficient way of predicting the level of social media addiction amongst university students.
Business–IT Strategic Alignment as a Driver of Integrated E-Service Delivery in Public Institutions: A PLS-SEM Approach Ayoub M Mswahili; Simon S Msanjila; Fridric Chali
International Journal of Research and Applied Technology Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i1.20766

Abstract

This study investigates organisational and technological factors influencing Business–IT Strategic Alignment (BITSA) towards designing and implementation of integrated e-service delivery within public institutions, addressing the persistent challenge of siloed, non-interoperable platforms that undermine citizen-centric digital transformation. Grounded in the Strategic Alignment Model (SAM), a cross-sectional survey of 411 respondents from 16 Tanzanian public institutions was conducted, with data analysed using Partial Least Squares Structural Equation Modelling (PLS-SEM) to test relationships between alignment constructs and integrated e-service outcomes. The findings reveal that BITSA is a significant positive predictor of integrated e-service delivery (β = 0.196, p < .001), with IT Strategy–Infrastructure/Processes Alignment (β = 0.265, p < .001), Strategic Performance Measures Alignment (β = 0.153, p = .002), and IT–Business Functional Alignment (β = 0.093, p = .047) emerging as key drivers. Conversely, E-services Strategic Collaboration, Communication, and Business Infrastructure Alignment exerted negative effects, reflecting coordination difficulties and structural rigidities. The model explains a moderate portion of the variance in BITSA (R² = 16.9%) but only a small share in integrated e-service delivery (R² = 3.8%). This study extends alignment theory to the public sector by empirically demonstrating BITSA’s enabling role in integrated e-services, while highlighting that successful integration requires enhanced cross-agency collaboration, organisational flexibility, and supportive policies and leadership. Practically, the findings underscore the need for governments to complement technical competence with strategic leadership, collaborative governance, and policy frameworks to achieve sustainable e-service integration.
Consumer Behavior in Payment Failures and Retry Attempts in Online Ticket Purchasing Dmitrii Khaiurov
International Journal of Research and Applied Technology Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i1.20734

Abstract

A declined payment interrupts the purchase of an event ticket at the moment of highest commitment, yet the behavioral response of the buyer to this interruption has received limited attention. This study examines how consumers respond to payment failures and how often interrupted orders are resolved successfully. The analysis draws on 2 anonymized transaction datasets from the Russian ticketing industry: 25,811 acquiring operations from a ticket marketplace and 199,635 orders from 3 ticketing companies within 1 holding, covering January 2024 to June 2026. The study applies transaction-level behavioral analysis to operational payment records and triangulates consumer responses after a failure through the combination of operation-level and order-level evidence. Declines affected 23.0% of payment attempts. A retry followed 55.7% of initially declined orders, the median pause before a repeated attempt equaled 3 minutes, and 43.7% of such orders ended in a completed payment. Recovery depended on the cause of the failure: orders declined for reasons a buyer can correct, such as an incorrect CVV code or insufficient funds, and recovered at close to twice the rate of orders interrupted by processing errors. Retries made after a pause of 5 to 15 minutes succeeded in 74.8% of cases, while immediate repetition succeeded in 25.0% of cases. Among recovered orders, 80.1% kept the original payment instrument. At the order level, 27.6% of purchases expired before any payment method was selected. The findings describe retrying as a mass consumer response, quantify the recoverable share of failed revenue, and provide platforms with guidance on designing retry prompts and payment method switching at checkout. The results extend checkout abandonment research into the interior of the payment stage, add the interpretability of the failure cause to models of service failure recovery, and document consumer persistence under the time pressure of an expiring seat reservation.
Building and Implementing SME Landing Page Website as Promotional and to Strengthen the Brand Identity of Croccante Chips using AGILE Method Nurjandi Abdillah; Rahma Wahdiniwaty; Mukhlisa Omonova
International Journal of Research and Applied Technology Vol. 6 No. 2 (2026): December, 2026 (Issue in Progress)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i2.20744

Abstract

Digital competition in present time is challenges for small and medium enterprises (SMEs) to improve their digital business model, this need a strategic shifting toward independent digital business model. However, static product catalog are not flexible toward modern consumers without a good narrative. This study aims to build and implement a landing page website and CRUD management system for Croccante Chips to strengthen the brand value and dynamic content. The Agile SDLC framework is used for the development cycle because it’s simplicity. The process of Agile for each iteration are requirement, plan and design, development, testing, development and review. The resulting platform embeds narrative product information, such as brand heritage and product profile into an intuitive visual interface featuring a responsive section, product showcase, customer and testimonials. Evaluation is qualitative briefing with Product Owner and one IT exprt. Ultimately, this landing page provides Croccante Chips with a strategic promotional tool that supporting marketplace branding, and helping communicates brand values, and digital identity.
Hybrid Oversampling and FT-Transformer-Based Classification for Imbalanced Clinical Tabular Data: A Multi-Dataset Statistical Evaluation Asaad Khaleel; Mohammed Ramadhan; Masood Abdulrahman
International Journal of Research and Applied Technology Vol. 6 No. 2 (2026): December, 2026 (Issue in Progress)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i2.21230

Abstract

Class imbalance is a problem which is not new on the clinical data, but is not well dealt with in practice. A model trained on a skewed distribution will often claim high accuracy on the skewed dataset, but will miss almost all of the minority class, typically the class that is the most important for detection — such as the class of patients who require detection the most. The three synthetic oversampling methods tested were SMOTE and ADASYN and Borderline SMOTE, alongside the three classifiers Random Forest and Gradient Boosted Trees and a Bayesian-tuned FT-Transformer, applied to three datasets: Pima Diabetes (768 records); a cardiovascular dataset (3,000 records); and Heart Failure Clinical Records (299 records, 203 survived, 96 died). All 14 resulting configurations were tested using 5-fold cross validation repeated 5 times per fold (i.e., 25-fold-pairs), and Wilcoxon Signed-Rank tests were performed to determine if the improvements are statistically significant when compared with the baseline (RF). The answer is: Yes, they were — in many instances very much so. On Pima, ADASYN together with the tuned FT-Transformer obtained F1=0.6677 and Recall=0.8209, while for the unaugmented RF it was 0.5145 and 0.4563, respectively. In the Pima ablation study specifically, the large portion of that gain (+15.6%) was due to oversampling, with hyperparameter tuning contributing another +9.2%; these percentages are specific to the Pima/RF ablation experiment and should not be interpreted as dataset-agnostic general findings. Synthetic augmentation was tested using SHAP on the RF branch only, and did not alter the variables that the model uses.
A Systematic Review of Edge Computing Architectures and Data Mining Techniques in Smart Farming Mimi Haryani Tasani; Annisa Wulan Sari
International Journal of Research and Applied Technology Vol. 6 No. 1 (2026): June 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v6i1.21293

Abstract

The rapid integration of the Internet of Things (IoT) in smart farming generates massive volumes of heterogeneous data, conventionally processed through centralized cloud computing. However, cloud-centric systems often suffer from high latency, bandwidth limitations, and intermittent connectivity in remote agricultural areas. Edge computing, coupled with lightweight data mining techniques, offers a transformative solution by processing data directly at the source. This study presents a Systematic Literature Review (SLR) aiming to synthesize current advancements in edge architectures and resource-efficient algorithms for precision agriculture. Following a rigorous 5-phase methodology, 38 primary studies published between 2021 and 2026 were extracted from five major academic databases (ScienceDirect, ACM, IEEE Xplore, Springer, and Web of Science). The findings indicate that the three-tier (IoT-Edge-Cloud) architecture is the most prevalent framework, effectively reducing transmission delays. For data processing on resource-constrained edge nodes, compressed tree-based models—particularly Lightweight XGBoost and Random Forest—demonstrate superior efficacy compared to computationally heavy neural networks. Nevertheless, the successful deployment of edge-AI faces substantial challenges, including heterogeneous data integration without traditional ETL pipelines and dynamic model updating against environmental concept drift. This review provides a consolidated roadmap for future research addressing these technical bottlenecks in agricultural IoT.