cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Hindarto
Contact Email
jurnal@umsida.ac.id
Phone
-
Journal Mail Official
jurnal@umsida.ac.id
Editorial Address
Jl. Mojopahit No. 666B, Sidoarjo, Jawa Timur
Location
Kab. sidoarjo,
Jawa timur
INDONESIA
Indonesian Journal of Innovation Studies
Published by Universitas Muhammadiyah Sidoarjo
ISSN : -     EISSN : 25989936     DOI : https://doi.org/10.21070/ijins.v17i
Core Subject : Science, Education, Social, Engineering,
Computer Science & IT Education Engineering Law, Crime, Criminology & Criminal Justice
Indonesian Journal of Innovation Studies (IJINS) is a peer-reviewed journal published by Universitas Muhammadiyah Sidoarjo four times a year. This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.This journal aims is to provide a place for academics and practitioners to publish original research and review articles. The articles basically contains any topics concerning new innovation on all aspects. IJINS is available in online version. Language used in this journal is Indonesia or English.
Arjuna Subject : Umum - Umum
Articles 923 Documents
 89   90   91   92   93 
Automatic Classification of Artificial Intelligence Generated Question Difficulty Levels: Klasifikasi Otomatis Tingkat Kesulitan Soal Hasil Kecerdasan Buatan Najahah, Vina; Pujianto, Utomo
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1880

Abstract

General Background: Determining question difficulty is a fundamental requirement in educational assessment to support valid evaluation and systematic question curation. Specific Background: The increasing use of artificial intelligence for automatic question generation produces large volumes of linguistically diverse items, making manual difficulty labeling time-consuming and subjective. Knowledge Gap: Despite extensive research on text-based difficulty prediction, lightweight and reproducible pipelines for multi-level difficulty classification of AI-generated questions remain limited. Aims: This study aims to develop and evaluate an automatic classification pipeline for three difficulty levels of AI-generated multiple-choice questions using TF-IDF text representation and a Random Forest classifier. Results: The proposed pipeline achieved a test accuracy of 70.98%, exceeding the random guessing baseline, with the highest F1-score observed in the easy class (78.45%) and the lowest in the medium class (65.32%), indicating greater ambiguity in intermediate difficulty questions. Novelty: This study presents a reproducible and interpretable classification workflow specifically applied to expert-labeled AI-generated questions with high inter-rater reliability. Implications: The findings support the use of lexical feature–based classification as an initial pre-curation and difficulty filtering tool in AI-assisted educational assessment systems. Highlights • The classification pipeline distinguishes three difficulty levels using only textual features• Medium difficulty questions exhibit the highest classification ambiguity• Lexical patterns contribute consistently to difficulty level separation Keywords Question Difficulty Classification; AI Generated Questions; TF-IDF Representation; Random Forest Classifier; Educational Assessment
Generative Artificial Intelligence Label Reliability in Programming Assessment: Reliabilitas Label Kecerdasan Buatan Generatif pada Asesmen Algoritma Pemrograman Khairunnisa, Raissa Araminta; Pujianto, Utomo
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1881

Abstract

General Background: The integration of Generative AI in educational assessment enables rapid construction of large-scale question banks, particularly in programming education, yet raises concerns regarding content validity. Specific Background: In algorithm and programming domains, Generative AI models frequently assign Higher Order Thinking Skills and Lower Order Thinking Skills labels automatically, creating potential discrepancies with Bloom’s Taxonomy classifications. Knowledge Gap: Empirical evidence validating the reliability of AI-generated cognitive labels and comparing statistical and transformer-based classification methods on small, domain-specific Indonesian datasets remains limited. Aims: This study aims to audit the reliability of cognitive labels generated by the Gemini model through expert validation and to compare TF-IDF–SVM and IndoBERT–SVM classifiers under class-imbalanced conditions. Results: Expert validation revealed substantial mislabeling, with a claimed balanced dataset becoming skewed toward LOTS. Classification experiments using five-fold cross-validation showed that TF-IDF–SVM achieved a slightly higher macro F1-score than IndoBERT–SVM. Novelty: The study demonstrates that simple lexical representations with stemming can outperform transformer-based embeddings when data are limited and domain-specific. Implications: These findings emphasize the necessity of human validation in AI-generated assessments and support the use of lightweight statistical text classification for automated cognitive level evaluation in constrained educational contexts. Highlights • Generative AI cognitive labels showed substantial inconsistency after expert validation• Lexical feature representation yielded higher macro-level classification balance• Human-in-the-loop validation remained essential for programming assessment datasets Keywords HOTS; LOTS; Generative AI; Text Classification; TF-IDF
Web-Based Priority Program Recommendation Using Collaborative Filtering: Rekomendasi Program Prioritas Berbasis Web Menggunakan Collaborative Filtering Pesik, Luisa Maria; Tinambunan, Medi Hermanto; Santa, Kristofel
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1882

Abstract

General Background: Recess activities of regional legislative members function as a formal mechanism for collecting diverse public aspirations related to regional development programs. Specific Background: In Minahasa Regency, the determination of priority programs derived from recess activities has traditionally relied on manual procedures that are prone to subjectivity and inconsistency. Knowledge Gap: Despite extensive studies on collaborative filtering in various domains, its application for managing and prioritizing legislative recess programs within local government contexts remains limited. Aims: This study aims to design and implement a web-based priority program recommendation system for DPRD recess activities using an Item-Based Collaborative Filtering algorithm. Results: The system was developed using the Waterfall method and implemented with PHP and MySQL, incorporating modules for aspiration management, rating, authentication, and recommendation generation. Black box testing across core functionalities confirmed that the system operated according to specifications and supported structured priority ranking of programs. Novelty: The research introduces the application of Item-Based Collaborative Filtering to DPRD recess aspiration management, replacing a previously manual and subjective process. Implications: The proposed system provides a structured, transparent, and data-driven approach to supporting legislative decision-making in prioritizing public programs at the regional level. Highlights• The developed system organizes recess aspirations into measurable program priorities• Item-based recommendation logic supports consistent ranking of proposed programs• Web-based architecture enables structured management of legislative aspiration data KeywordsCollaborative Filtering; Recommendation System; DPRD Recess; Priority Program; Web-Based Application
Comparison Of Random Forest and Neural Network for Portable Executable Malware Classification: Perbandingan Random Forest dan Neural Network pada Klasifikasi Malware Portable Executable Nugroho, Agung; Umam, Chaerul
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1883

Abstract

General Background: The rapid growth of information technology has increased the complexity of cyber threats, with malware attacks posing significant risks to computer systems, particularly those based on the Windows operating system. Specific Background: Portable Executable files contain structured statistical attributes that can be utilized to distinguish malware from benign software using machine learning techniques. Knowledge Gap: Despite extensive use of machine learning in malware detection, comparative evidence using identical Portable Executable statistical features and consistent evaluation settings remains limited. Aims: This study aims to compare the classification performance of Random Forest and Neural Network models in malware detection based on Portable Executable statistical features. Results: Using the ClaMP Integrated Dataset comprising 5,184 samples and 70 static features, Random Forest achieved an accuracy, precision, recall, and F1-score of 99.14%, while the Neural Network obtained consistent scores of 98.18% across all evaluation metrics. Novelty: This research presents a direct and controlled comparison of ensemble and neural-based classifiers using identical preprocessing pipelines, default model configurations, and balanced Portable Executable datasets. Implications: The findings demonstrate that ensemble-based approaches provide stable and reliable performance for Portable Executable malware classification and offer a practical foundation for automated machine learning–based cybersecurity systems. Highlights • Random Forest Achieved The Highest Classification Scores Across All Metrics• Portable Executable Statistical Features Provided Clear Malware Separation• Ensemble Learning Demonstrated Strong Stability On Structured PE Data Keywords Malware Detection; Portable Executable; Random Forest; Neural Network; Machine Learning
Asynchronous Fetching and Periodic Polling for Web-Based Staffing Dashboards: Asynchronous Fetching dan Periodic Polling pada Dashboard Kepegawaian Berbasis Web Rompas, Parabelem Tino Dolf; Saroinsong, Samuel
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1884

Abstract

General Background: Timely information flow is a critical requirement in public administrative systems, particularly in environments with limited server infrastructure. Specific Background: At the Agricultural Modernization Implementation Center of North Sulawesi, manual staffing administration processes have caused high information latency and scheduling conflicts, motivating the adoption of a web-based staffing dashboard. Knowledge Gap: Fully real-time architectures are often resource-intensive and unsuitable for local government infrastructures, while alternative lightweight synchronization strategies remain underexplored in this context. Aims: This study aims to implement and evaluate the integration of Asynchronous Data Fetching and Client-Side Periodic Polling algorithms within a web-based staffing dashboard developed using the Rapid Application Development method. Results: Performance evaluation using Google Lighthouse recorded a Total Blocking Time of 160 ms, indicating minimal main-thread disruption, while comparative analysis showed a 99.5% reduction in information latency compared to manual procedures. Novelty: The study demonstrates a practical combination of asynchronous data loading and periodic polling as a stable and lightweight solution for administrative dashboards under server constraints. Implications: The findings indicate that government institutions with limited infrastructure can adopt similar client-side optimization strategies to achieve responsive and stable web-based administrative services without increasing server capacity. Highlights • The dashboard architecture minimizes browser main-thread workload through parallel asynchronous data loading• Periodic polling at a 15-second interval maintains stable notification synchronization under limited server resources• Administrative information latency is substantially reduced compared to conventional manual workflows Keywords Asynchronous Data Fetching; Periodic Polling; Web-Based Staffing Dashboard; Information Latency; Public Administration Systems
Hyperparameter Optimization of Light Gradient Boosting Machine for Microcirculation Detection Wearable Data: Optimasi Hyperparameter Light Gradient Boosting Machine untuk Deteksi Mikrosirkulasi Data Wearable Pramudita, Tatya Hanum; Arifin, M. Zainal
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1888

Abstract

General Background: Microcirculation disorders represent an early marker of chronic health conditions, yet existing detection approaches predominantly rely on invasive and resource-intensive procedures. Specific Background: Recent advances in wearable technology enable noninvasive microcirculation monitoring through Laser Doppler Flowmetry and Fluorescence Spectroscopy signals, which generate complex, nonstationary, and high-dimensional data that challenge conventional analytical methods. Knowledge Gap: Despite the proven capability of Light Gradient Boosting Machine models for wearable physiological data, limited studies have systematically combined feature selection, Bayesian hyperparameter optimization, and cohort-based validation for microcirculation condition detection using LDF-FS data. Aims: This study aims to optimize LightGBM performance for microcirculation condition detection by integrating feature importance–based selection and Bayesian hyperparameter tuning within a Stratified Group K-Fold validation framework. Results: Feature dimensionality was reduced from 34 to 22 informative variables, resulting in improved classification performance, with the optimized model achieving a ROC-AUC of 0.8632, accuracy of 88.04%, and recall of 80.00%. SHAP-based analysis identified age, body mass index, and skin temperature as dominant physiological predictors. Novelty: The study presents an integrated optimization pipeline combining feature selection, Bayesian optimization, and subject-level validation on wearable LDF-FS data. Implications: The findings support the potential of optimized LightGBM models as interpretable and reliable components of noninvasive wearable-based microcirculation monitoring systems. Highlights • Feature selection reduced dimensionality while maintaining robust classification performance• Bayesian optimization improved sensitivity in detecting microcirculation conditions• SHAP analysis revealed dominant demographic and physiological predictors Keywords Bayesian Optimization; Microcirculation Detection; Feature Selection; LightGBM; Wearable LDF-FS
Eco-Pesantren Program Shaping Islamic Character and Environmental Awareness: Program Eco-Pesantren dalam Pembentukan Karakter Islami dan Kesadaran Lingkungan Makrufah, Nurul Ilmiyah Al; Abror, Sirojuddin
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1889

Abstract

General Background: Environmental degradation has increasingly positioned education and religious institutions as strategic arenas for cultivating ecological responsibility. Specific Background: Islamic boarding schools hold distinctive potential to integrate Islamic teachings with daily environmental practices, particularly within child-friendly pesantren contexts. Knowledge Gap: Existing studies tend to address environmental education in pesantren partially, without simultaneously integrating eco-pesantren programs, Islamic character formation, and child-friendly educational principles. Aims: This study aims to analyze the implementation of the Eco-Pesantren program in forming Islamic character and environmental awareness among students at the child-friendly At-Tahdzib Islamic Boarding School in Jombang. Results: Using a qualitative case study approach through participatory observation, in-depth interviews, and documentation, the findings show that integrating Islamic values with environmental conservation activities—such as Green Friday programs, automatic water faucets, tree planting, 3R-based waste management, and energy conservation—contributes to observable changes in students’ ecological behavior and character, including reduced ablution water use, decreased electricity consumption, increased waste sorting consistency, reduced plastic waste, and improved understanding of environmental jurisprudence. Novelty: The novelty of this study lies in its holistic integration of eco-pesantren practices, Islamic character education, and child-friendly pesantren principles within a contextual Islamic education model. Implications: These findings provide empirical and conceptual contributions for developing sustainable Islamic education models that align spiritual values with environmental responsibility. Highlights • Integration of Islamic values with daily environmental practices within pesantren life• Observable behavioral changes in water use, energy conservation, and waste management• Holistic Islamic education model aligned with child-friendly pesantren principles Keywords Eco-Pesantren; Islamic Education; Islamic Character; Environmental Awareness; Child-Friendly Pesantren
Micro Small and Medium Enterprises and Socioeconomic Welfare in Bayah Barat Village: Usaha Mikro Kecil dan Menengah dan Kesejahteraan Sosial Ekonomi Desa Bayah Barat Zaky, Ahmad; Padillah, Teja Amhar; Saputra, Dimas; Oktavia, Salwa; Akhdam, Nasywa Fawwaz; Delfiza, Yandri; Daeng, Amalina Adani Putri; Pidreansyah, Syarifah Khansa
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1890

Abstract

General Background: Micro, Small, and Medium Enterprises are widely recognized as a fundamental pillar of rural economic systems in Indonesia, particularly in supporting household livelihoods and local economic circulation. Specific Background: In Bayah Barat Village, Lebak Regency, MSMEs based on banana processing and home industries represent dominant community economic activities rooted in local resources and traditional knowledge. Knowledge Gap: Despite their persistence, limited empirical studies have documented how these MSMEs contribute to socio-economic welfare while simultaneously facing constraints related to capital access, marketing reach, and digital literacy at the village level. Aims: This study aims to analyze the contribution of MSMEs to socio-economic welfare in Bayah Barat Village and to formulate a digital-based strengthening strategy grounded in community participation. Results: Using a Participatory Rural Appraisal approach, the findings indicate that MSMEs contribute to employment absorption, household income generation, and local economic strengthening, while encountering structural challenges including limited financing, raw material stability, and conventional marketing practices. Novelty: The study highlights a community-based perspective that integrates traditional production systems with participatory analysis to identify digital marketing and alternative financing pathways. Implications: These findings imply the need for inclusive financing access, entrepreneurial capacity building, digital literacy improvement, product standardization, and strengthened village institutional collaboration to support sustainable community-based MSME development. Highlights • MSMEs support employment and household income through banana-based home industries• Participatory Rural Appraisal reveals capital and marketing constraints at village level• Community-based digital strategies align local resources with economic sustainability Keywords Micro Small And Medium Enterprises; Socioeconomic Welfare; Participatory Rural Appraisal; Digital Marketing; Bayah Barat Village
Theory of Constraint and Drum Buffer Rope Increase Shoe Production Throughput: Teori Kendala dan Drum Buffer Rope Meningkatkan Produktivitas Produksi Sepatu Rahmawati, Dea; Rochmoeljati, Rr.
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1891

Abstract

General Background: Production systems frequently experience capacity imbalances that disrupt material flow and reduce throughput, particularly in small- and medium-scale manufacturing environments. Specific Background: UD Anugrah, a footwear manufacturer specializing in children’s shoes, faces recurring work-in-progress accumulation caused by unequal capacities among production workstations. Knowledge Gap: Prior studies have widely applied the Theory of Constraints, yet empirical applications integrating Drum-Buffer-Rope scheduling within the footwear manufacturing sector remain limited. Aims: This study aims to optimize production capacity at UD Anugrah by applying the Theory of Constraints integrated with the Drum-Buffer-Rope concept to identify, manage, and resolve system bottlenecks. Results: Sewing and Injection workstations were identified as primary constraints; optimization through linear programming, flow synchronization, and selective capacity elevation increased monthly throughput from IDR 88,166,810 to IDR 91,707,000, representing a 3.86% increase, while financial analysis yielded a positive Net Present Value of IDR 61,881,704 and a Payback Period of 3.41 years. Novelty: This research presents an integrated TOC–DBR application within a shoe manufacturing context, supported by quantitative throughput and investment feasibility analysis. Implications: The findings demonstrate that structured constraint management and DBR-based flow control provide a practical framework for improving production performance and investment decision-making in small- and medium-scale manufacturing enterprises. Highlights: Sewing and Injection stations were consistently identified as system constraints across multiple production periods. Linear programming supported optimal product mix allocation under limited workstation capacity. Financial evaluation confirmed that selective machine addition was economically feasible within the system lifespan. Keywords : Theory of Constraints, Drum Buffer Rope, Production Capacity, Shoe Manufacturing, Bottleneck Analysis
Relational Capital And Innovation As Drivers Of Micro Small And Medium Enterprise Sustainability: Modal Relasional Dan Inovasi Sebagai Penentu Keberlanjutan Usaha Mikro Kecil Dan Menengah Putri, Rasti Maita; Fadliyanti, Luluk; Hak, Muhamad Bai'ul
Indonesian Journal of Innovation Studies Vol. 27 No. 1 (2026): January
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21070/ijins.v27i1.1893

Abstract

General Background: MSME sustainability is increasingly shaped by the capacity to manage intangible resources and innovation within dynamic business environments. Specific Background: Intellectual capital, comprising human, structural, and relational capital, is recognized as a strategic resource for MSMEs, yet its linkage to sustainability remains underexplored when innovation is positioned as an intervening construct. Knowledge Gap: Prior studies predominantly emphasize financial performance, leaving limited empirical evidence on how intellectual capital relates to MSME sustainability measured across economic, social, and environmental dimensions. Aims: This study examines the relationships between intellectual capital components, innovation, and MSME sustainability in Indonesia, with innovation treated as an intervening variable. Results: Using SEM–PLS on data from 178 MSMEs, the findings demonstrate that relational capital shows a positive and significant relationship with innovation, while human capital and structural capital do not exhibit significant relationships. Innovation is positively and significantly associated with economic, social, and environmental sustainability dimensions. Novelty: The study introduces an integrated sustainability measurement encompassing triple-bottom-line dimensions within a single empirical model while empirically testing innovation as an intervening mechanism linking intellectual capital to sustainability. Implications: These results extend MSME sustainability literature and provide strategic insights for policymakers and practitioners to prioritize relational networks and innovation-oriented development pathways supporting long-term MSME sustainability. Highlights • Relational capital demonstrates a significant association with innovation in MSMEs• Innovation shows significant relationships with economic, social, and environmental sustainability• Sustainability is examined through an integrated triple-bottom-line empirical model Keywords Intellectual Capital; Relational Capital; Innovation; MSME Sustainability; Triple Bottom Line

Page 92 of 93 | Total Record : 923

 89   90   91   92   93 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol. 27 No. 1 (2026): January Vol. 26 No. 4 (2025): October Vol. 26 No. 3 (2025): July Vol. 26 No. 2 (2025): April Vol. 26 No. 1 (2025): January Vol. 25 No. 4 (2024): October Vol. 25 No. 3 (2024): July Vol. 25 No. 2 (2024): April Vol. 25 No. 1 (2024): January Vol. 24 (2023): October Vol. 23 (2023): July Vol. 22 (2023): April Vol. 21 (2023): January Vol. 20 (2022): October Vol. 19 (2022): July Vol. 18 (2022): April Vol. 17 (2022): January Vol. 16 (2021): October Vol. 15 (2021): July Vol. 14 (2021): April Vol. 13 (2021): January Vol. 12 (2020): October Vol. 11 (2020): July Vol. 10 (2020): April Vol. 9 (2020): January Vol. 8 (2019): October Vol. 7 (2019): July Vol. 6 (2019): April Vol. 5 (2019): January More Issue