iLearning Journal Center (IJC)
Not a member yet
591 research outputs found
Sort by
Human Centered AI Integrating Ethical Psychological and Computational Perspectives for Inclusive Innovation
No full textThe rapid evolution of Artificial Intelligence (AI) has reshaped social, economic, and cultural landscapes, yet its development often prioritizes technical efficiency over human values. This study proposes the Human-Centered AI Integration Framework, a multidisciplinary model that unites ethical, psychological, and computational perspectives to promote inclusive and responsible AI innovation. Employing a mixed-method and Design Science Research (DSR) approach, data were gathered from literature studies, user surveys, and AI system analyses to identify gaps between ethical principles, user perception, and algorithmic design. The proposed framework consists of three interrelated layers: the Ethical Layer, emphasizing fairness, accountability, and transparency; the Psychological Layer, focusing on trust, empathy, and human experience; and the Computational Layer, ensuring algorithmic integrity through bias mitigation and explainability. Evaluation results from interdisciplinary experts confirm that the model effectively bridges human values with technical implementation, enhancing trust, inclusivity, and transparency across AI systems. This research contributes to the growing discourse on responsible AI by providing a holistic foundation for designing systems that are not only intelligent and efficient but also empathetic, equitable, and aligned with human well-being
Sistem Informasi Pengelolaan Sampah Kabupaten Bantul Berbasis Website Menggunakan Model Modified Waterfall: Bantul Regency Waste Management Information System Based on Website Using Modified Waterfall Model
Full text linkWaste management that is carried out conventionally or not integrated and coordinated between the government, the community, and the private sector creates new, increasingly complex problems. The Bantul Regency Government has established a Waste Management program based on Village-Owned Enterprises (the BumKal), which involves the synergy of all stakeholders. This research aims to develop and evaluate a web to optimize data management and monitoring: waste shodaqoh; waste bank; waste management place; and other BumKal programs. The process of developing a web applies the Software Development Life Cycle principles with the modified Waterfall model, which consists of stages: requirements definition; system and software design; implementation and unit testing; integration and system testing; as well as operation and maintenance. This research succeeded in developing a web to optimize BumKal program services. Efforts to evaluate web pages from unit level to overall functional integration through black box tests succeeded in achieving 100% conformity to functional aspects. The final stage of this research is to submit a web to the Environmental Service in Bantul Regency to optimize the BumKal program.Pengelolaan sampah yang dilakukan secara konvensional atau tidak terintegrasi dan terkoordinasi antara pihak pemerintah, masyarakat, dan swasta mewujudkan permasalahan baru yang semakin kompleks. Pemerintah Kabupaten Bantul membentuk program Pengelolaan Sampah Berbasis Badan Usaha Milik Kelurahan (BumKal) yang melibatkan sinergi seluruh pemangku kepentingan. Penelitian ini bertujuan membangun dan mengevaluasi suatu laman web dalam mengoptimalkan pengelolaan serta pemantauan data: shodaqoh sampah, bank sampah; tempat pengelolaan sampah; dan program BumKal lain. Proses membangun laman web menerapkan prinsip Software Development Life Cycle dengan model modified Waterfall yang terdiri dari tahap: requirements definition; system and software design; implementation and unit testing; integration and system testing; serta operation and maintenance. Penelitian ini berhasil membangun suatu laman web untuk mengoptimalkan layanan program BumKal. Upaya evaluasi laman web mulai level unit sampai integrasi keseluruhan fungsional melalui black box test berhasil mencapai 100% kesesuaian aspek fungsional. Tahap akhir penelitian ini yaitu menyerahkan laman web kepada Dinas Lingkungan Hidup di Kabupaten Bantul untuk mengoptimalkan program BumKal
Penerapan Algoritma K-Means Clustering Dalam Pengelompokkan Kepadatan Penduduk: Application of K-Means Clustering Algorithm in Population Density Grouping
Full text linkUneven population density will have a negative impact if not considered. One way to tackle this problem is with population equity management planning policies. This research focuses on clustering population density areas, which is the ratio between population and area in Central Sulawesi Province. This research clustering is applied with data mining techniques, namely K-Means Clustering. The research stages are data collection, data understanding, data processing, clustering, clustering review, dashboard analysis, and accuracy testing with the tableau application in providing visualization of population density in the region. Based on the results of the algorithm calculation, it produces three clusters, cluster 0 being low population density, cluster 1 being high population density, and cluster 2 being medium population density. Cluster formation is based on the visualization produced by the research dataset through Sum Of Square Error analysis, silhouette coefficient, and elbow method. Clustering is formed, followed by dashboard visualization with the tableau application. The clustering results, based on the SSE calculation, produce a value of 4324505738.747303, meaning the determination of the number of clusters with a significant difference with the calculation of the number of previous groupings. Then the results of the silhouette analysis provide the highest average silhouette value at the number of clusters, namely 3 with a value of 0.6144435666457168, and the elbow method gives the result that the elbow point is at point 3, meaning the optimum number of clusters with 3 clusters.Kepadatan penduduk yang tidak merata akan memberikan dampak buruk jika tidak diperhatikan. Salah satu cara untuk menanggulangi masalah ini dengan kebijakan perencanaan pengelolaan pemerataan kependudukan. Penelitian ini berfokus dalam mengelompokkan wilayah kepadatan penduduk yang merupakan rasio antara jumlah penduduk dan luas wilayah di Provinsi Sulawesi Tengah. Pengelompokkan penelitian ini diterapkan dengan teknik data mining, yakni K-Means Clustering. Tahapan penelitian yakni pengumpulan data, data understanding, data processing, clustering, cluster review, analisa dashboard dan uji akurasi dengan aplikasi tableau dalam memberikan visualisasi kepadatan penduduk di wilayah tersebut. Berdasarkan hasil perhitungan algoritma tersebut, menghasilkan tiga cluster dengan cluster 0 merupakan kepadatan penduduk rendah, cluster 1 merupakan kepadatan penduduk tinggi, dan cluster 2 merupakan kepadatan penduduk sedang. Pembentukan cluster berdasarkan visualisasi yang dihasilkan dataset penelitian melalui analisa Sum Of Square Error, silhouette coefficient, serta elbow method. Clustering yang dibentuk, dilanjutkan visualisasi dashboard dengan aplikasi tableau. Hasil clustering tersebut, berdasarkan perhitungan SSE menghasilkan nilai 4324505738.747303 berarti penetapan jumlah cluster dengan perbedaan signifikan dengan perhitungan jumlah pengelompokkan sebelumnya. Lalu hasil analisa silhouette memberikan nilai rata-rata silhouette paling tinggi pada jumlah cluster yakni 3 dengan nilai 0.6144435666457168, dan metode elbow memberikan hasil bahwa elbow point berada di titik 3, berarti jumlah cluster yang optimum dengan 3 cluster
Advancing Management Strategies with AI and IoT for Operational Excellence and Competitive Edge
No full textAs organizations face increasing competition and technological advancements, optimizing operations and managing resources efficiently is crucial for maintaining a competitive edge. The integration of emerging technologies like Artificial Intelligence (AI) and the Internet of Things (IoT) enhances efficiency, improves resource allocation, and drives growth. This study explores how AI and IoT adoption optimizes business processes, improves decision-making, and fosters a competitive advantage Using a quantitative approach, data from 200 executives in AI and IoT-implemented industries were analyzed. The analysis, conducted using Partial Least Squares Structural Equation Modeling (PLS-SEM), indicates that AI and IoT significantly enhance efficiency, resource utilization, and overall performance. Real-time monitoring and predictive analytics improve market alignment and operational trends The findings suggest that organizations adopting AI and IoT can better navigate dynamic business environments, enhance productivity, and sustain growth. Moreover, fostering innovation and continuous technological improvement is essential. This research underscores AI and IoT’s transformative potential in reshaping business operations and securing a competitive edge. Future research should explore these technologies\u27 industry-specific impacts and broader innovation potential
AI-Driven Makeup Suggestions Leveraging Mediapipe Face Landmarks For Eye Shape Detection: Rekomendasi Tampilan Riasan Mata Berbasis AI Menggunakan Landmark Wajah Mediapipe Untuk Mendeteksi Bentuk Mata
Full text linkIn the world of beauty, makeup is not only a form of self expression but also a creative skill that requires precision and an understanding of facial structures. Among all facial features, the eyes play a crucial role in defining makeup styles. Each individual has unique eye shapes such as round, monolid, upturned, almond, and downturned, which require different makeup techniques to enhance their appearance. However, many individuals struggle to identify their eye shape, leading to suboptimal makeup results. This research aims to develop an intelligent system for eye shape classification using image processing and artificial intelligence technologies. MediaPipe, a robust and lightweight framework for facial landmark detection, was employed to extract key features from the eye region, including Eye Aspect Ratio (EAR), Eye Corner (angle), and Eye Distance. A total of 1,250 images were used from various datasets including personal archives, Kaggle, and GitHub MUCT. The classification process used a Support Vector Machine (SVM) with a non-linear RBF kernel, and its performance was validated using K-Fold Cross Validation with 10 folds. The system demonstrated high accuracy for almond, downturned, monolid, and round eyes. However, classification for upturned eyes showed less optimal results, likely due to limitations in the current feature set. This study also introduces an integrated open camera interface that detects eye shape in real time and recommends suitable eye makeup styles. This research contributes to inclusive beauty technology by providing personalized makeup suggestions based on eye shape, aligning with SDG 5 (Gender Equality) and SDG 9 (Industry, Innovation, and Infrastructure). Future work will focus on improving accuracy, particularly for upturned eye classification.Dalam dunia kecantikan, riasan bukan hanya bentuk ekspresi diri, tetapi juga keterampilan kreatif yang membutuhkan ketelitian serta pemahaman terhadap struktur wajah. Di antara semua fitur wajah, mata memegang peranan penting dalam menentukan gaya riasan. Setiap individu memiliki bentuk mata yang unik seperti bulat, monolid (sipit), naik (upturned), almond (ideal), dan menurun (downturned), yang masing-masing memerlukan teknik riasan berbeda agar tampil optimal. Namun, banyak individu yang masih kesulitan dalam mengidentifikasi bentuk mata mereka, sehingga hasil riasan menjadi kurang sesuai. Penelitian ini bertujuan untuk mengembangkan sistem cerdas untuk klasifikasi bentuk mata menggunakan teknologi pengolahan citra dan kecerdasan buatan. Framework MediaPipe digunakan untuk mendeteksi titik landmark pada area mata, yang mencakup fitur Eye Aspect Ratio (EAR), Eye Corner (sudut), dan Eye Distance (jarak). Total 1.250 gambar digunakan dari berbagai sumber, termasuk dokumentasi pribadi, Kaggle, dan GitHub MUCT. Proses klasifikasi dilakukan menggunakan algoritma Support Vector Machine (SVM) dengan kernel non-linear RBF, dan divalidasi menggunakan teknik K-Fold Cross Validation sebanyak 10 fold. Sistem menunjukkan akurasi tinggi pada bentuk mata almond, downturned, monolid, dan round, namun masih kurang optimal untuk bentuk mata upturned karena keterbatasan fitur. Penelitian ini juga menghadirkan antarmuka kamera terbuka yang mendeteksi bentuk mata secara real-time dan memberikan rekomendasi gaya riasan yang sesuai. Penelitian ini mendukung pengembangan teknologi kecantikan yang inklusif dan personal, sejalan dengan SDG 5 (Kesetaraan Gender) dan SDG 9 (Inovasi Industri dan Infrastruktur). Penelitian selanjutnya akan difokuskan pada peningkatan akurasi klasifikasi, khususnya untuk bentuk mata upturned
Reinterpreting Brand Experience Stimuli through Virtual Space Avatars and Metaverse Co-Creation
No full textThe transformation of digital spaces into three-dimensional virtual ecosystems, widely known as the metaverse, has fundamentally reshaped the paradigm of brand experience from traditional visual narrative communication into participatory, immersive, and multisensory engagement. This study aims to reinterpret and extend the conventional understanding of brand experience by identifying the key stimuli that shape user interactions within virtual environments. Employing a qualitative exploratory approach based on the AEIOU framework (Activities, Environments, Interactions, Objects, and Users) and reflective thematic analysis, the research examined eight major metaverse platforms across five categories: game-based, social playground, VR-based, NFT-based, and event-based. The analysis revealed five primary dimensions that collectively construct brand experience in the metaverse: immersive presence, virtual space, avatar-mediated interaction, personalized virtual goods, and dynamic co-creation. These dimensions redefine the brand experience from a stimulus–response perspective into a participatory, socially driven relationship in which users actively co-create meaning, identity, and value with brands. The findings highlight how digital stimuli and multisensory interactions within metaverse spaces foster emotional attachment and brand engagement, offering both conceptual and managerial implications. From a theoretical standpoint, this research provides an initial framework for understanding brand experience in immersive digital environments, while practically, it guides marketers and brand strategists to design interactive, personalized, and community-oriented branding initiatives. Ultimately, the study opens new opportunities for future research to empirically examine the link between metaverse-based experiences, user perception, and brand outcomes such as trust, attachment, and loyalty within the evolving digital ecosystem.The transformation of digital spaces into three-dimensional virtual ecosystems, widely known as the metaverse, has fundamentally reshaped the paradigm of brand experience from traditional visual narrative communication into participatory, immersive, and multisensory engagement. This study aims to reinterpret and extend the conventional understanding of brand experience by identifying the key stimuli that shape user interactions within virtual environments. Employing a qualitative exploratory approach based on the AEIOU framework (Activities, Environments, Interactions, Objects, and Users) and reflective thematic analysis, the research examined eight major metaverse platforms across five categories: game-based, social playground, VR-based, NFT-based, and event-based. The analysis revealed five primary dimensions that collectively construct brand experience in the metaverse: immersive presence, virtual space, avatar-mediated interaction, personalized virtual goods, and dynamic co-creation. These dimensions redefine the brand experience from a stimulus–response perspective into a participatory, socially driven relationship in which users actively co-create meaning, identity, and value with brands. The findings highlight how digital stimuli and multisensory interactions within metaverse spaces foster emotional attachment and brand engagement, offering both conceptual and managerial implications. From a theoretical standpoint, this research provides an initial framework for understanding brand experience in immersive digital environments, while practically, it guides marketers and brand strategists to design interactive, personalized, and community-oriented branding initiatives. Ultimately, the study opens new opportunities for future research to empirically examine the link between metaverse-based experiences, user perception, and brand outcomes such as trust, attachment, and loyalty within the evolving digital ecosystem
Leveraging IPFS for Scalable and Secure Data Storage in Blockchain-Based DApps
No full textThe rapid expansion of blockchain-based Decentralized Applications (DApps) has intensified challenges related to scalable, secure, and cost-efficient data storage, as conventional on-chain storage is unsuitable for large data volumes due to high gas costs and performance limitations, while centralized off-chain solutions undermine decentralization and increase security risks. This study aims to evaluate the effectiveness of integrating the IPFS as a decentralized storage layer within an Ethereum-based DApp architecture to enhance scalability, data integrity, and operational efficiency. Using an experimental systems engineering approach, a fully functional DApp prototype was developed by integrating a React.js frontend, Ethereum smart contracts written in Solidity, and a local IPFS node for off-chain file storage. Empirical performance testing was conducted to measure file upload and retrieval latency, CID (Content Identifier) consistency, smart contract execution time, and gas consumption on the Ethereum testnet. The results demonstrate that IPFS integration significantly reduces on-chain storage load while maintaining strong data integrity, as evidenced by 100% CID consistency across all test scenarios. Although upload and retrieval times increased proportionally with file size, the system achieved success rates above 95% with stable performance, while gas costs remained low because only CIDs were recorded on-chain. These findings indicate that IPFS provides a scalable, secure, and cost-efficient decentralized storage solution for blockchain-based DApps, enabling the development of more data-intensive and resilient DApps, with future research opportunities focusing on incentive-based pinning mechanisms, advanced encryption, and cross-chain storage integration
Pengaruh Metode Waterfall dalam Penyempurnaan Proses Pengembangan Sistem Informasi Akademik secara Sistematis: Impact of Waterfall Method on Systematic Academic Information System Development
Full text linkAcademic information systems play a crucial role in supporting the operations of educational institutions, particularly in managing complex data. The main challenge in their development is ensuring that the process is structured, efficient, and aligned with user needs. The Waterfall method, as one of the sequential and systematic development approaches, is often used in information system development projects. However, its effectiveness in the context of academic information systems requires further analysis. This study aims to analyze the impact of the Waterfall method on improving the development process of academic information systems. The research focuses on three main aspects: time efficiency, cost, and the quality of the final output. Both quantitative and qualitative descriptive approaches were employed in this study. Data were collected through in-depth interviews with system developers, surveys of users (academic administration, lecturers, and students), and case studies at educational institutions using the Waterfall method. The results show that the Waterfall method provides a clear structure in the development process of academic information systems. This has a positive impact on time efficiency and the quality of the final output. However, the main drawback of this method is its lack of flexibility in addressing changing needs that often arise during the project. In conclusion, the Waterfall method is effective for academic information system development projects with stable and well-defined requirements. This study recommends exploring a hybrid approach, such as combining Waterfall with Agile, to improve responsiveness to changes in user needs in the future.Sistem informasi akademik memiliki peran penting dalam mendukung operasional institusi pendidikan, terutama dalam pengelolaan data yang kompleks. Tantangan utama dalam pengembangannya adalah memastikan prosesnya terstruktur, efisien, dan sesuai dengan kebutuhan pengguna. Metode Waterfall, sebagai salah satu pendekatan pengembangan yang berurutan dan sistematis, sering digunakan dalam proyek pengembangan sistem informasi. Namun, efektivitas metode ini dalam konteks sistem informasi akademik memerlukan analisis lebih lanjut. Penelitian ini bertujuan untuk menganalisis pengaruh metode Waterfall terhadap penyempurnaan proses pengembangan sistem informasi akademik. Fokus penelitian terletak pada tiga aspek utama, yaitu efisiensiwaktu, biaya, dan kualitas hasil akhir. Pendekatan deskriptif kuantitatif dan kualitatif digunakan dalam penelitian ini. Data dikumpulkan melalui wawancara mendalam dengan pengembang sistem, survei kepada pengguna (admin-istrasi akademik, dosen, dan mahasiswa), serta studi kasus pada institusi pendidikan yang menggunakan metode Waterfall. Hasil penelitian menunjukkan bahwa metode Waterfall mampu memberikan struktur yang jelas dalam proses pengembangan sistem informasi akademik. Hal ini berdampak positif pada efisiensi waktu dan kualitas hasil akhir. Namun, kelemahan utama metode ini adalah kurangnya fleksibilitas dalam menghadapi perubahan kebutuhan yang sering terjadi selama proyek berlangsung. Kesimpulannya, metode Waterfall efektif untuk proyek pengembangan sistem informasi akademik dengan kebutuhan yang stabil dan terdefinisi dengan baik. Penelitian ini memberikan rekomendasi eksplorasi pendekatan hybrid, seperti kombinasi metode Waterfall dan Agile, untuk meningkatkan responsivitas terhadap perubahan kebutuhan pengguna di masa depan
Web-Based Personal Finance Management Application with Interactive Data Visualization: Aplikasi Manajemen Keuangan Pribadi Berbasis Web dengan Visualisasi Data Interaktif
Full text linkPersonal financial management plays a crucial role in achieving financial stability and ensuring effective control over individual finances. With the advancement of technology, more individuals are turning to digital solutions to manage their financial data more efficiently. This research focuses on the development of a web-based personal financial management application equipped with interactive data visualization tools, allowing users to easily track and analyze their income, expenses, and financial trends. Using the waterfall approach, this research includes the stages of design, development, testing, and implementation. The application is developed with Vue.js for the user interface and Highcharts for data visualization. Testing results show that the application effectively helps users understand their financial patterns and provides useful insights for financial decision-making. The testing results also indicate that the application makes it easier for users to plan their budget, identify unhealthy spending habits, and offer recommendations for savings. This application offers a more efficient solution compared to manual methods or traditional applications that only provide raw data without visual analysis. The conclusion of this research is that the developed application provides a practical and intuitive solution for personal financial management. The application helps users plan their finances wisely and make smarter decisions, thus improving financial literacy and supporting the achievement of their long-term financial goals. As a future development step, it is recommended to integrate machine learning and blockchain technology to enhance data security and transaction transparency.Pengelolaan keuangan pribadi sangat penting untuk mencapai kestabilan keuangan dan memastikan kontrol yang efektif terhadap keuangan individu. Seiring dengan perkembangan teknologi, semakin banyak individu yang beralih ke solusi digital untuk mengelola data keuangan mereka dengan lebih efisien. Penelitian ini berfokus pada pengembangan aplikasi manajemen keuangan pribadi berbasis web yang dilengkapi dengan alat visualisasi data interaktif, yang memungkinkan pengguna untuk dengan mudah melacak dan menganalisis pemasukan, pengeluaran, dan tren keuangan mereka. Menggunakan pendekatan waterfall, penelitian ini mencakup tahap perancangan, pengembangan, pengujian, dan implementasi. Aplikasi ini dikembangkan dengan Vue.js untuk antarmuka pengguna dan Highcharts untuk visualisasi data. Pengujian aplikasi menunjukkan bahwa aplikasi ini mampu membantu pengguna memahami pola keuangan mereka dengan lebih baik dan memberikan wawasan yang berguna untuk pengambilan keputusan keuangan. Hasil pengujian juga menunjukkan bahwa aplikasi ini mempermudah pengguna dalam merencanakan anggaran, mengidentifikasi kebiasaan pengeluaran yang tidak sehat, dan memberikan rekomendasi untuk penghematan. Aplikasi ini menawarkan solusi yang lebih efisien dibandingkan dengan metode manual atau aplikasi tradisional yang hanya memberikan data mentah tanpa analisis visual. Kesimpulan penelitian ini adalah aplikasi yang dikembangkan memberikan solusi praktis dan intuitif untuk pengelolaan keuangan pribadi. Aplikasi ini membantu pengguna merencanakan keuangan dengan bijak dan mengambil keputusan yang lebih cerdas, sehingga meningkatkan literasi keuangan dan mendukung pencapaian tujuan keuangan jangka panjang mereka. Sebagai langkah pengembangan selanjutnya, disarankan untuk mengintegrasikan machine learning dan teknologi blockchain untuk meningkatkan keamanan dan transparansi transaksi
The Impact of Digital Era Transformation on Human Resource Management
No full textSignificant changes have been brought about by the digital age in many areas of business, including human resource management (HRM). The significant effects of digitalization on HRM strategies, practices, and organizational dynamics are examined in this research. This study explores how technological innovations such as automation, big data analytics, and artificial intelligence have transformed traditional HRM functions and processes. Through a thorough analysis of relevant literature, the research highlights how the advent of digital technologies has reshaped recruitment and talent acquisition. The integration of digital tools enables HR managers to efficiently find, attract, and retain top talent by leveraging online platforms, social media, and data-driven insights. Moreover, HR procedures like performance management, training and development, and employee engagement have been optimized, resulting in greater efficiency and productivity in the workplace. Furthermore, the adoption of digitalization supports data-driven decision-making and enhances employee experiences through personalized solutions. This transformation aligns HRM practices with the evolving technological landscape, positioning organizations to meet the dynamic demands of the modern workforce. In conclusion, digitalization has fundamentally reshaped HRM, offering innovative strategies to manage human capital effectively in the digital era