Publikasi Universitas Mercu Buana
Not a member yet
7303 research outputs found
Sort by
Pengembangan Peta Interaktif Layanan Puskesmas Nasional melalui Integrasi Open Data dengan Streamlit dan Folium
No full textKetersediaan dan keterbukaan data layanan publik, khususnya di sektor kesehatan, memainkan peran penting dalam mewujudkan sistem pelayanan yang merata dan responsif. Penelitian ini bertujuan untuk mengembangkan peta interaktif layanan Puskesmas nasional dengan mengintegrasikan data terbuka (open data) pemerintah menggunakan teknologi Streamlit dan Folium. Sumber data berasal dari portal data kesehatan dan administrasi wilayah yang tersedia untuk publik dan memiliki informasi yang dapat diekstrak untuk kebutuhan peta interaktif. Data tersebut diproses melalui tahapan pembersihan dan geocoding untuk memperoleh koordinat geografis. Aplikasi yang dibangun memungkinkan pengguna untuk menjelajahi peta interaktif, menyaring informasi berdasarkan wilayah atau kecamatan, dan mengakses detil masing-masing Puskesmas secara langsung. Hasil pengembangan menunjukkan bahwa dari 333 data Puskesmas, sebanyak 299 entri berhasil divisualisasikan pada peta dan 34 entri gagal diproses karena kendala geocoding. Selain itu, pengujian performa menggunakan Firefox DevTools menunjukkan bahwa untuk memanggil dan memuat sebuah halaman peta interaktif rata-rata memakan waktu 1,278 hingga 1,291 detik dengan ukuran data yang ditransfer sekitar 3105 kB. Hasil ini menunjukkan bahwa integrasi open data dalam visualisasi berbasis web dapat dilakukan untuk meningkatkan transparansi, memperluas akses informasi, serta mendukung pemangku kepentingan dalam pengambilan keputusan berbasis data di sektor kesehatan
Evaluation of the Effectiveness of Sewage Treatment Plant Performance in GKM Green Tower Building
No full textWastewater or wastewater is the remaining water that is disposed of, originating from households, industries, offices, and other public places. A sewage treatment plant (STP) is a process of reusing wastewater and removing contaminants from wastewater. This study evaluates the Sewage Treatment Plant system in the GKM Green Tower Building. This study aims to analyze the performance of the Sewage Treatment Plant (STP) in the GKM Green Tower building and to determine the effectiveness of the performance of the Sewage Treatment Plant (STP) in the GKM Green Tower building. The parameters used in this study were pH (acidity), COD, BOD, TSS, oil and grease, Total Coliform, and Ammonia, which complies with Domestic Wastewater Quality Standards Based on the Regulation of the Minister of Environment and Forestry of the Republic of Indonesia Number: P.68/ Menlhk-Setjen/2016. Recycled water in the GKM Green Tower building is used to flush closed urinals and water plants. It was found that the results of clean wastewater management in the GKM Green Tower building still look cloudy and smelly. Based on the results of domestic wastewater monitoring tests at GKM Green Tower in August / prior to analysis, several parameters exceeded the quality standards, namely TSS and Total Coliform. The maintenance carried out so far on the Sewage Treatment Plant (STP) system in the GKM Green Tower Building is still not good, which is the cause of the ineffectiveness of the wastewater that has been managed so far. The results of the second test conducted in November showed a decrease in the numbers between the TSS 4 and Total Coliform parameters between 1100. So that they were in accordance with the quality standards set by the government Ministry of Environment
Enhancing Homogeneity and Particle Size Reduction in Coffee–Creamer Mixtures Using Fluidized Bed Mixer
No full textThis study investigates the application of a fluidized bed mixer to improve the homogeneity, particle size distribution, and moisture reduction of coffee and creamer powder mixtures. The research focuses on three types of coffee particles—Type A (145 μm), Type B (100 μm), and Type C (50 μm)—which were mixed with creamer in a weight ratio of 1:0.7. The mixing process was conducted using a prototype fluidized bed mixer with a capacity of 1,000 grams and a blower speed range of 2,800–3,000 rpm. After 10 minutes of mixing, significant reductions in particle size were observed: Type A decreased by 20–30%, Type B by 10–15%, and Type C by 5–10%, with creamer particles also experiencing a 15% reduction. Moisture content dropped from 10.63% to 8.5%, demonstrating the system’s dual function of mixing and drying. Microscopic analysis revealed a uniform particle distribution with minimal agglomeration or segregation, confirming the effectiveness of the fluidized bed mixer in achieving a homogeneous blend. These findings underscore the potential of fluidized bed technology in improving the quality, stability, and handling properties of powder-based products. The results have important implications for instant beverage production, food formulation, and broader powder processing industries, where consistent product performance is essential
Peningkatan Kreativitas Anak dengan Implementasi Augmented Reality Pembelajaran Hewan Berbasis Android
No full textThis study aims to address challenges in early childhood education, which are often caused by regulations, limited educator readiness, and inadequate interactive learning media. Augmented Reality (AR) technology offers a solution by integrating the virtual and real worlds, enabling children to experience 3D objects immersively using smartphones. The research was conducted at SD Bedahan 01 with third-grade students learning Natural Science (IPA) topics about animals, including their characteristics, classifications, habitats, and benefits. Initial observations showed the average student score was 78, meeting the Minimum Competency Criteria (KKM) but requiring improvement to optimize learning outcomes. To address this, an AR-based learning media application for Android was developed using the Multimedia Development Life Cycle (MDLC) method, integrating 3D visuals, audio, and interactive features to create an engaging and immersive learning experience. The results demonstrated that the use of AR technology increased students’ interest and understanding of the material, as well as their ability to recall and apply concepts. This study highlights the potential of AR as an effective educational tool and contributes to the development of innovative and interactive learning media for elementary education, particularly in subjects requiring visualization. Future research may explore expanding AR features to include gamification and advanced interactivity for broader educational applications
Sistem Otomatis Ringkasan Laporan Keuangan Berbasis PDF Menggunakan Metode NLP Transformer
No full textKompleksitas dan volume laporan keuangan perusahaan yang terus meningkat menjadi tantangan bagi analis dan pemangku kepentingan dalam menginterpretasikan informasi secara cepat dan akurat. Analisis manual cenderung memakan waktu lama dan rentan terhadap kesalahan. Penelitian ini mengusulkan sistem otomatis untuk melakukan peringkasan laporan keuangan berbasis PDF dengan menggunakan metode Natural Language Processing (NLP) berbasis Transformer. Sistem dikembangkan menggunakan Python serta memanfaatkan PyPDF2/pdfplumber untuk ekstraksi teks, NLTK untuk prapemrosesan, dan model BART/T5 dari Hugging Face Transformers untuk menghasilkan ringkasan. Evaluasi dilakukan pada laporan tahunan perusahaan multinasional dengan panjang 50–200 halaman. Hasil pengujian menunjukkan sistem mampu mereduksi teks hingga 10–15% dari panjang asli, dengan nilai rata-rata ROUGE-1 = 0,72; ROUGE-2 = 0,62; dan ROUGE-L = 0,70. Ringkasan yang dihasilkan mempertahankan informasi penting seperti tren pendapatan, laba bersih, beban operasional, dan arus kas. Pendekatan ini dapat mempercepat analisis keuangan, mengurangi beban kognitif analis, serta menghasilkan ringkasan yang konsisten. Ke depan, penelitian dapat dikembangkan dengan fine-tuning model pada korpus keuangan serta integrasi analisis sentimen untuk memperkaya interpretasi manajerial
Evaluasi Pengalaman dan Keterlibatan Pengguna Pada Aplikasi Pembelian Tiket Bioskop M-Tix dengan Metode UEQ+ dan UES
No full textCineplex 21 Group yang dimiliki oleh PT Nusantara Sejahtera Raya Tbk adalah perusahaan yang berfokus pada industri bioskop di Indonesia dan juga menjadi pelopor jaringan Cineplex di negara ini. Sejak 2015, perusahaan ini telah melakukan digitalisasi pada sistem penjualan tiket dengan meluncurkan aplikasi M-Tix. Aplikasi tersebut telah diunduh lebih dari 10 juta kali dan mendapatkan rating 3,8 pada September 2023. Untuk menilai kualitas pengalaman dan tingkat keterlibatan pengguna, pengukuran yang akurat diperlukan untuk meningkatkan aplikasi tersebut. Penelitian ini bertujuan untuk mengukur pengalaman dan keterlibatan pengguna, serta untuk mengidentifikasi apakah terdapat korelasi antara keduanya. Dalam penelitian ini, metode yang digunakan adalah User Experience Questionnaire Plus (UEQ+) dan User Engagement Scale (UES) untuk mengevaluasi pengalaman dan keterlibatan pengguna aplikasi M-Tix. Hasil penelitian menunjukkan bahwa aplikasi M-Tix mendapatkan evaluasi positif secara keseluruhan terkait pengalaman pengguna dan juga menunjukkan tingkat keterlibatan pengguna yang baik. Selain itu, penelitian ini menemukan adanya hubungan yang bervariasi antara pengalaman pengguna dan tingkat keterlibatan mereka, yang mengindikasikan adanya saling pengaruh antara keduanya. Temuan ini memberikan informasi yang berguna untuk pengembangan lebih lanjut aplikasi tersebut, guna meningkatkan kualitas layanan bagi penggunanya
Penerapan Machine Learning untuk memprediksi Resiko Pengidap Penyakit Jantung menggunakan Algoritma decision tree
No full textHeart disease remains a leading cause of mortality worldwide, necessitating innovative approaches to improve diagnosis and management. This study aims to enhance the prediction of heart disease risk using machine learning, particularly the Decision Tree algorithm. A publicly available dataset containing 303 entries with 14 features related to heart disease risk factors, such as age, cholesterol levels, blood pressure, and electrocardiogram results, was utilized. The data underwent preprocessing steps, including normalization, handling outliers, and standardization, to ensure optimal model performance. The Decision Tree algorithm was trained on 80% of the dataset and evaluated on the remaining 20%. The model achieved an accuracy of 80%, with a balanced F1-score of 0.82, demonstrating its effectiveness in predicting heart disease risk. Feature importance analysis revealed that cholesterol levels, age, and resting blood pressure were the most influential predictors. The Decision Tree's interpretability provides valuable insights for medical practitioners, enabling more accurate and transparent risk assessments. This study highlights the potential of machine learning in medical diagnostics, particularly in identifying high-risk individuals for early intervention and better patient outcomes
Kinerja Komparatif LSTM dan XGBoost untuk Peramalan Radiasi Matahari Perkotaan Tropis
No full textThe increasing reliance on clean energy has accelerated the development of solar energy infrastructure. However, its intermittent nature—especially in tropical urban climates—poses significant challenges to maintaining grid stability. This study compares the performance of two machine learning algorithms, Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost), for hourly solar irradiance forecasting in two climatically distinct tropical cities: Jakarta and Bogor. Using a 10-year historical dataset from NASA POWER that includes solar irradiance and relevant meteorological variables, this research addresses the gap in comparative analysis of deep learning versus ensemble models within high-granularity tropical data settings. The methodology involves data acquisition, preprocessing, feature engineering, model development, hyperparameter tuning, and evaluation using RMSE, MAE, and R² metrics. The results show that LSTM consistently outperforms XGBoost in both cities. In East Jakarta, LSTM achieved a RMSE of 29.24, MAE of 15.63, and R² of 0.9875, compared to XGBoost with RMSE of 38.65, MAE of 18.92, and R² of 0.9782. Similarly, in Bogor Regency, LSTM achieved RMSE of 30.73, MAE of 16.89, and R² of 0.9862, outperforming XGBoost which recorded RMSE of 38.41, MAE of 18.68, and R² of 0.9785. These findings highlight LSTM's superior ability to capture complex temporal dependencies and nonlinear trends in solar irradiance time-series data, especially under the fluctuating weather patterns characteristic of tropical urban environments. The results provide strong empirical support for implementing LSTM-based forecasting in solar energy management systems across similar geographic regions
Perancangan Website E-Commerce Dengan Pemanfaatan Framework Codeigniter Pada Di Chemistry Merch
No full textFacing extraordinary online-based trade in the current era requires information systems and information technology that are very adequate for the needs of suppliers, sellers or buyers. The same thing is faced by Chemistry Merch which operates in the online trading sector. Maximizing this technology is intended to facilitate interaction between companies and consumers. Apart from that, the product is widely known by the wider community and even throughout the world. Utilization of software in the form of PHP, Microsoft Visual Studio Code, Xampp and supported by the Codeigniter framework, UML and use case diagrams further clarifies procedures for selling and disseminating information in web form. The expected results start from design to input analysis, process analysis, output analysis and information technology architecture needs analysis, namely in the form of a web that contains the complete needs of consumers
Perancangan Aplikasi To-do-list "MyList"
No full text Effective task management is crucial in today’s fast-paced world, where productivity and organization are essential. Addressing this need, MyList is designed as a mobile-based to-do list application that simplifies and optimizes task organization for users. The application features task creation, editing, deletion, categorization, prioritization, reminders, and progress tracking through visual statistics, fostering motivation and efficiency. Developed using the Waterfall methodology, the design process includes requirement analysis, system design, and user interface mockups. The application employs Android Studio, Java programming, and MySQL database management to ensure compatibility, reliability, and efficiency across Android platforms. MyList is lightweight, accessible, and tailored to diverse audiences, including students and professionals seeking better time management. Its user-friendly interface prioritizes simplicity and functionality, making it a practical solution for daily task management. While this study focuses on the design phase, the proposed application demonstrates significant potential for implementation and real-world testing. The anticipated outcomes include improved productivity, enhanced time management, and seamless task organization for users. This research serves as a foundation for developing innovative and user-centric task management solutions, encouraging future advancements and practical applications in this domain