eJournal Komunitas Dosen Indonesia
Not a member yet
1406 research outputs found
Sort by
Applying Importance-Performance Analysis to Identify Strategic Factors Enhancing User Satisfaction in Dana
Get PDFThe use of digital wallets in Indonesia has grown significantly alongside increasing public demand for fast, secure, and practical financial transactions. One of the widely used applications is Dana. However, user satisfaction with its services still requires a comprehensive evaluation to ensure continued usage. This study aims to measure and analyze user satisfaction with the Dana application by integrating the End User Computing Satisfaction (EUCS) model and the Importance-Performance Analysis (IPA) method. This research employed a quantitative approach by distributing online questionnaires to 403 respondents. The research instrument was tested for validity and reliability, and the data were analyzed using IPA to map service attributes based on their perceived importance and performance. The results show that attributes such as system security, content completeness, and information accuracy fall into the high-priority quadrant (Quadrant I), indicating that they are highly important but currently underperforming. Meanwhile, attributes like content format and timeliness meet user expectations and should be maintained. The study concludes that Dana’s development team should prioritize improvements in the aspects that most significantly affect user satisfaction. These findings are expected to serve as a strategic foundation for decision-making in enhancing service quality, while also contributing to the academic literature on evaluating digital financial applications.The use of digital wallets in Indonesia has grown significantly alongside increasing public demand for fast, secure, and practical financial transactions. One of the widely used applications is Dana. However, user satisfaction with its services still requires a comprehensive evaluation to ensure continued usage. This study aims to measure and analyze user satisfaction with the Dana application by integrating the End User Computing Satisfaction (EUCS) model and the Importance-Performance Analysis (IPA) method. This research employed a quantitative approach by distributing online questionnaires to 403 respondents. The research instrument was tested for validity and reliability, and the data were analyzed using IPA to map service attributes based on their perceived importance and performance. The results show that attributes such as system security, content completeness, and information accuracy fall into the high-priority quadrant (Quadrant I), indicating that they are highly important but currently underperforming. Meanwhile, attributes like content format and timeliness meet user expectations and should be maintained. The study concludes that Dana’s development team should prioritize improvements in the aspects that most significantly affect user satisfaction. These findings are expected to serve as a strategic foundation for decision-making in enhancing service quality, while also contributing to the academic literature on evaluating digital financial applications
Decision Tree and Reinforcement Learning Approaches in Adapting Math Problems Based on Student Ability
Get PDFMathematics learning often faces challenges in adjusting the difficulty level of questions to match individual students' abilities. Traditional methods, which apply a uniform difficulty across all students, are less effective as they fail to account for differences in comprehension and learning speed. This study introduces an adaptive learning system utilizing Decision Tree and Reinforcement Learning approaches to dynamically adjust the difficulty of mathematics questions based on real-time student performance. The Decision Tree model classifies questions into easy, moderate, and difficult categories by analyzing the distribution of correct and incorrect student answers, achieving a classification accuracy of 71.33% and an F1-score of 80.02%. Reinforcement Learning, particularly the Q-Learning algorithm, adjusts the difficulty level of subsequent questions based on continuous student performance feedback, with a success rate of 65.96% and a total reward of 626,885. This dual approach significantly enhances the learning process by providing personalized and adaptive experiences, ensuring each student is challenged at an appropriate level. Implemented as a web-based system, it facilitates real-time adjustments and continuous adaptation to student needs. By continuously analyzing student responses, the system maintains engagement and supports effective mastery of mathematical concepts. This personalized feedback mechanism fosters a dynamic and interactive learning environment that is more responsive to individual needs, improving both student engagement and conceptual understanding.Mathematics learning often faces challenges in adjusting the difficulty level of questions to match individual students' abilities. Traditional methods, which apply a uniform difficulty across all students, are less effective as they fail to account for differences in comprehension and learning speed. This study introduces an adaptive learning system utilizing Decision Tree and Reinforcement Learning approaches to dynamically adjust the difficulty of mathematics questions based on real-time student performance. The Decision Tree model classifies questions into easy, moderate, and difficult categories by analyzing the distribution of correct and incorrect student answers, achieving a classification accuracy of 71.33% and an F1-score of 80.02%. Reinforcement Learning, particularly the Q-Learning algorithm, adjusts the difficulty level of subsequent questions based on continuous student performance feedback, with a success rate of 65.96% and a total reward of 626,885. This dual approach significantly enhances the learning process by providing personalized and adaptive experiences, ensuring each student is challenged at an appropriate level. Implemented as a web-based system, it facilitates real-time adjustments and continuous adaptation to student needs. By continuously analyzing student responses, the system maintains engagement and supports effective mastery of mathematical concepts. This personalized feedback mechanism fosters a dynamic and interactive learning environment that is more responsive to individual needs, improving both student engagement and conceptual understanding
Comparison of Adam, RMSprop, and SGD on DenseNet121 for Tomato Leaf Disease Classification
Get PDFDiseases affecting tomato leaves can severely impact agricultural productivity, as they can reduce crop yields and quality significantly. A swift and dependable identification of these diseases is vital for ensuring prompt interventions and the successful implementation of disease control strategies. This study focus on evaluating and comparing the efficiency of three separate optimizers, such as Adam, RMSProp, and SGD on the pretrained Convolutional Neural Network (CNN) architecture DenseNet121. There has been no previous research that directly compares the performance of Adam, RMSProp, and SGD optimizers on the DenseNet121 model for classifying tomato leaf diseases using the Plant Village dataset. These optimizers are crucial in the training process by influencing the model’s ability to converge and generalize well on new, unseen data. Experimental procedures were performed using a labeled dataset of tomato leaf images, which included healthy leaves and various disease classes. Out of the three optimization techniques tested, the DenseNet121 model trained with the Adam optimizer consistently outperformed the others. It achieved the highest evaluation metrics, with an accuracy of 0.9800, precision of 0.9807, recall of 0.9800, and F1-score of 0.9800 on the test set. These outcomes suggest that the model has a strong and balanced classification performance, capable of correctly identifying disease conditions with minimal errors. Based on these findings, the DenseNet121 architecture combined with the Adam optimizer is considered the optimal model used to recognize various tomato leaf diseases in this study
Dynamic Depth Cues: Mengoptimalkan Alur Pemetaan Paralaks Multi-Lapisan dalam RPG Maker MV/MZ
No full textParallax mapping is a visual rendering technique that creates the illusion of three-dimensional (3D) depth in two-dimensional (2D) game environments by shifting background layers relative to camera movement. While widely supported in advanced game engines such as Unity and Godot, its application in RPG Maker MV/MZ—a platform favored by indie developers for its accessibility—has not been adequately explored in existing game development literature. This study addresses that gap by introducing a custom five-layer parallax mapping pipeline optimized for RPG Maker’s PIXI.js-based renderer, which is not natively designed to support complex depth effects.The proposed system introduces performance-conscious features, including grouped texture loading, dynamic layer visibility (adaptive culling), and a logarithmic depth-scaling method that enhances realism without overwhelming system resources. To evaluate its effectiveness, the study adopts a sequential explanatory mixed-methods approach consisting of two phases: quantitative benchmarking across three hardware tiers (low-end, mid-range, and high-end), and qualitative feedback collection from 20 participants comprising both players and developers. Findings reveal that the system consistently achieves over 46 frames per second (FPS) on low-end devices while improving perceived depth and spatial realism by 38%. Additionally, 85% of users expressed a preference for the parallax-enhanced visuals due to increased immersion and aesthetic quality. These results demonstrate that cinematic visual depth is achievable in RPG Maker with proper optimization, offering practical guidance for developers working under technical constraints.te
Pengaruh Kualitas Produk, Persepsi Harga, dan Promosi Terhadap Keputusan Pembelian di Kopi Janji Jiwa Galaxy
Get PDFStudi ini bertujuan untuk mengkaji dampak dari standar produk, pandangan konsumen terhadap harga, serta strategi promosi terhadap keputusan pembelian yang diambil oleh konsumen di Kopi Janji Jiwa Galaxy. Latar belakang didasari oleh pertumbuhan industri kopi yang pesat di Indonesia, khususnya di kalangan generasi muda urban, yang mendorong pelaku usaha untuk meningkatkan kualitas serta strategi pemasarannya. Studi ini menggunakan pendekatan kuantitatif dengan teknik pengumpulan data melalui distribusi kuesioner kepada 100 responden yang dipilih secara accidental sampling. Analisis data dilakukan dengan regresi linier berganda menggunakan perangkat lunak SPSS versi 25. Hasil analisis mengindikasikan bahwa variabel kualitas produk (X1) tidak memberikan dampak yang signifikan pada keputusan pembelian (Y). Sebaliknya, variabel persepsi harga (X2) dan promosi (X3) memberikan dampak yang signifikan, baik secara bersamaan maupun secara individual, pada keputusan pembelian konsumen. Nilai koefisien determinasi (R²) sebesar 0,624 mengindikasikan bahwa ketiga variabel independen menjelaskan 62,4% variasi dalam keputusan pembelian. Promosi menjadi variabel paling dominan dengan nilai B= 0,769 dan signifikansi p < 0,001. Temuan ini menegaskan pentingnya elemen bauran pemasaran, khususnya strategi promosi dan penetapan harga yang tepat, dalam membentuk keputusan pembelian konsumen. Disarankan agar Kopi Janji Jiwa Galaxy terus meningkatkan efektivitas promosi serta menjaga persepsi harga yang sesuai agar mampu bersaing dan mempertahankan loyalitas konsumen di pasar kopi yang kompetitif
Analisa Pengaruh Live Streaming dan Costumer Review Pada Keputusan Pembelian Melalui Platform Shopee
Get PDFRiset ini diperuntukan guna menganalisis keputusan pembelian pada live streaming serta customer review di bidang fashion thrifting pada toko sm.chloting di platform shopee. Pengambilan informasi memakai google form. penelitian ini menggunakan pendekatan kuantitatif dengan teknik purposive sampling pada 106 responden. Sampel yang digunakan adalah konsumen sm.chloting. Metode pengolahan informasi memakai statistic SPSS (Statistical Product and Service Solution) versi 26. Teknik penentuan sampel menggunakan Non-Probality Sampling (purposive sampling). Penelitian juga menggunakan model analisis regresi linier berganda. Hasil dari riset ini terdapatnya kenaikan keputusan pembelian. Live Streaming memberikan dampak positif pada keputusan pembelian. Live streaming berpengaruh signifikan (p = 0.047) terhadap keputusan pembelian, Customer Review tidak berpengaruh signifikan (p = 0.876). R² model sebesar 6,8%. Customer Review tidak mempengaruhi keputusan pembelian. Fitur Live Streaming diminati karena banyaknya penawaran menarik untuk konsumen berbelanja. Penelitian ini terbatas pada satu toko dan satu jenis produk, sehingga generalisasi ke jenis produk atau platform lain memerlukan studi lanjutan
Pengaruh Locus of Control dan Iklim Organisasi Terhadap Kinerja Pegawai di RSUD Dr. Soedarso
Get PDFMutu layanan kesehatan sangat bergantung pada kinerja tenaga keperawatan yang merupakan ujung tombak pelayanan kesehatan di rumah sakit. Penelitian ini bertujuan untuk menganalisis pengaruh locus of control dan iklim organisasi terhadap kinerja pegawai, khususnya perawat, di RSUD Dr. Soedarso Pontianak. Pendekatan kuantitatif dengan metode SEM-PLS, melibatkan 70 responden perawat dari berbagai unit pelayanan. Hasil analisis memperlihatkan bahwa variabel locus of control memiliki pengaruh yang positif dan juga signifikan terhadap kinerja pegawai (t = 2,805; p = 0,005), yang mengindikasikan bahwa perawat dengan kontrol internal yang tinggi cenderung memiliki tanggung jawab dan inisiatif lebih besar dalam menjalankan tugasnya. Iklim organisasi memberikan pengaruh yang lebih kuat serta signifikan terhadap kinerja (t = 3,334; p = 0,001), hasil ini menggambarkan bahwa lingkungan kerja yang mendukung, termasuk dukungan atasan serta komunikasi yang efektif dapat meningkatkan motivasi dan produktivitas kerja. Secara keseluruhan, kedua variabel tersebut mampu menjelaskan 58,9% variasi dalam kinerja pegawai (R² = 0,589). Penelitian ini menjadi penting karena belum banyak dilakukan pada konteks RS tipe A di Kalimantan Barat, khususnya Rumah Sakit Umum Daerah Dokter Soedarso sebagai rumah sakit pendidikan dan rujukan tertinggi. Selain itu, kajian sebelumnya umumnya hanya menganalisis faktor psikologis atau struktural secara terpisah. Studi ini diharapkan memberikan pemahaman lebih komprehensif sebagai dasar peningkatan mutu layanan keperawatan. Manajemen rumah sakit disarankan untuk mengintegrasikan program pelatihan teknis dengan pendekatan psikososial guna meningkatkan kinerja tenaga keperawatan secara berkelanjutan
Pengaruh Entrepreneurial Orientation dan Market Orientation Terhadap Marketing Performance Pada UMKM di Indonesia
Get PDFStudi ini menganalisis bagaimana orientasi kewirausahaan dan orientasi pasar berkontribusi terhadap kemampuan pemasaran dan kinerja pemasaran UMKM yang beroperasi di Indonesia. Fenomena yang melatarbelakangi penelitian ini adalah jumlah UMKM di Indonesia sangat besar dibandingkan dengan negara tetangga seperti Thailand dan Malaysia. Hal ini menunjukkan UMKM menyumbang sebagian besar PDB Indonesia. UMKM juga menghadapi berbagai tantangan khas dalam hal inovasi, daya saing, dan pendekatan pemasarannya. Sampel pada penelitian ini berjumlah 258 responden dengan purposive sampling. Data dianalisis dengan menggunakan SmartPLS versi 4 dengan metode PLS-SEM. Hasil penelitian menunjukkan bahwa baik Entrepreneurial Orientation maupun Market Orientation memiliki pengaruh positif dan signifikan terhadap Marketing Capabilities dan Marketing Performance. Selain itu, Marketing Capabilities terbukti secara signifikan memediasi hubungan antara kedua variabel independen tersebut terhadap Marketing Performance. Temuan ini menegaskan bahwa kemampuan UMKM dalam berinovasi, mengambil risiko, memahami pasar, serta membangun strategi pemasaran yang adaptif menjadi kunci dalam meningkatkan kinerja mereka. Secara teoritis, penelitian ini memperkuat perspektif Resource-Based View dan Dynamic Capabilities, sementara secara praktis memberikan rekomendasi bagi pelaku UMKM dan pembuat kebijakan untuk meningkatkan kapabilitas pemasaran melalui penguatan orientasi kewirausahaan dan orientasi pasar. Dengan demikian, UMKM dapat lebih siap bersaing dan berkembang dalam era ekonomi digital
Determinants of Innovative Leadership, Competence, and Motivation through Job Satisfaction to Improve School Performance in Tangerang
Get PDFThis study aims to assess the impact of innovative leadership styles, as well as competence and motivation, on job satisfaction, and how these factors can enhance school performance in Tangerang. The study also focuses on highlighting the role of job satisfaction as a mediating variable, which is expected to strengthen the relationship between these factors and school performance. A quantitative approach using Structural Equation Modeling (SEM) was employed in this research. The results indicate that innovative leadership, individual competence, and motivation have a significant positive impact on job satisfaction and institutional performance. Additionally, job satisfaction acts as a mediator in the relationship between these three factors and school performance, suggesting that job satisfaction plays a crucial role in driving overall school performance improvements. The findings provide valuable insights for education leaders to focus on the development of innovative leadership, the enhancement of competence, and motivation. By strengthening these three elements, schools can create a more productive and collaborative work environment
Proses Peningkatan Intention to Co-create Value Objek Wisata Pilgrims Walisongo di Jawa Tengah
Get PDFPenelitian ini bertujuan untuk menganalisis peran pengalaman wisatawan pilgrim yang mencakup dimensi emosional(tourist emotional experience) dan spiritual (tourist spiritual experience) dalam membentuk kepuasan (tourist satisfaction), komitmen relasional (relational commitment) serta niat untuk menciptakan nilai bersama (intention to co-create value) dalam konteks wisata ziarah (pilgrimage tourism) ke makam Walisongo di Jawa Tengah. Model penelitian dikembangkan berdasarkan Theory of Planned Behavior (TPB) dan literatur terkait perilaku wisatawan. Penelitian ini menggunakan pendekatan kuantitatif dengan penyebaran kuesioner tertutup kepada 208 responden pengunjung wisata ziarah (pilgrim tourism) Walisongo di Jawa Tengah yang memiliki pengalaman minimal satu kali melakukan wisata ziarah (pilgrimage tourism) ke makam ‘Wali Songo’. Data dianalisis menggunakan model persamaan struktural (SEM) berbasis smartPLS 4. Hasil penelitian menunjukkan bahwa tourist’ emotional experience dan spiritual memiliki pengaruh positif dan signifikan terhadap kepuasan wisatawan. Tourist’ emotional experience juga berpengaruh signifikan terhadap komitmen relasional, sedangkan pengalaman spiritual tidak berpengaruh signifikan. Selain itu, kepuasan terbukti meningkatkan komitmen relasional dan niat wisatawan untuk menciptakan nilai bersama, meskipun pengaruh langsungnya terhadap niat tersebut tergolong kecil. Sementara itu, komitmen relasional memiliki pengaruh paling kuat terhadap niat menciptakan nilai bersama. Penelitian ini diharapkan dapat berkontribusi pada pengembangan TPB dan ilmu pengetahuan di bidang pemasaran, khususnya yang berkaitan dengan wisata religi dan pilgrimage tourism, serta memberikan wawasan bagi pengelola destinasi dalam mengelola pengalaman wisata ziarah yang bermakna bagi pengunjung atau bahkan dalam pengembangan industry pariwisata religi