1,720,980 research outputs found
Architectural Analysis of the Repository Pattern in Web-Based Credit Score Conversion Assessment System Based on PermenPAN-RB No. 1 of 2023
Full text linkPermenPAN-RB Regulation No. 1 of 2023 introduced a major shift in functional position assessment by emphasizing performance predicate conversion in credit score evaluation, which increases architectural demands on supporting information systems. In practice, many assessment systems remain tightly coupled and difficult to evolve when regulatory rules, integration sources, or reporting formats change. This paper presents an architecture-oriented analysis of a web-based credit score conversion assessment information system that applies the Repository Pattern as a core architectural mechanism to decouple business logic from persistence, integration, and document-generation concerns. The analysis adopts a scenario-based evaluation approach inspired by the Architecture Tradeoff Analysis Method (ATAM) and is grounded in the ISO/IEC 25010 software quality model, focusing on maintainability, modifiability, testability, scalability, and reliability. Architectural evaluation is conducted by examining layered boundaries, repository abstractions, and dependency injection mechanisms under representative regulatory-driven change scenarios, including rule adjustments, data integration extensions, and reporting modifications. The results demonstrate consistent change localization across architectural layers, where rule changes are confined to service modules, integration changes are absorbed by repository adapters, and reporting changes remain isolated within document-generation components. These findings show that repository-based architectures significantly reduce coupling, improve change isolation, and support the sustainable evolution of government information systems operating under dynamic regulatory environments
Skyline Query untuk Rekomendasi Ekowisata Berdasarkan Sentimen Menggunakan Apache Spark
No full textEkowisata adalah jenis pariwisata yang memiliki daya tarik tersendiri seperti adanya pemandangan alami, flora dan fauna yang langka atau wahana edukasi yang berkaitan dengan alam. Sebagian besar penyedia layanan wisata online saat ini tidak menyediakan pertanyaan spesifik seperti dalam persyaratan ekowisata. Sehingga dirasa perlu untuk mengusulkan fitur knowledge discovery yang efektif untuk mendukung bisnis ekowisata tersebut, terutama dalam layanan online.
Dengan banyaknya transaksi teks dan sumber daya yang tersedia dari berbagai lembaga saat ini, skyline query berbasis text mining diusulkan untuk memberikan rekomendasi ekowisata secara online sesuai dengan preferensi pengguna. Misalnya, destinasi ekowisata dengan jarak yang dekat dan rating yang tinggi. Analisis sentimen diterapkan pada komentar pengunjung untuk mengetahui kelas sentimennya, apakah positif, negatif atau netral. Banyaknya preferensi yang dipertimbangkan, ukuran data yang besar, dan proses analisis sentimen yang dilakukan menyebabkan kompleksitas yang tinggi. Metode konvensional dengan komputasi tunggal akan membutuhkan waktu yang lama untuk memproses rekomendasi tersebut. Oleh karena itu, penelitian ini menerapkan komputasi klaster untuk menghasilkan rekomendasi ekowisata menggunakan skyline query pada banyak komputer secara paralel melalui framework Apache Spark.
Proses analisis sentimen yang dilakukan menggunakan algoritme SentiStrength berhasil memperoleh skor akurasi sebesar 78.3% dan F-measure sebesar 84.5%. Hal ini mengindikasikan bahwa sistem rekomandasi yang diusulkan berhasil mendeteksi respon positif melalui komentar pengunjung dengan baik. Adapun penerapan metode komputasi klaster Apache Spark dengan tiga node komputer berhasil meningkatkan kecepatan proses pemeringkatan objek rekomendasi dibandingkan dengan metode komputasi tunggal, yakni 213.7 kali lebih cepat pada data correlated, 240 kali lebih cepat pada data independent, dan 288.1 kali lebih cepat pada data anti-correlated. Sebagai prototipe untuk akses pengguna, telah dikembangkan sebuah aplikasi mobile Android. Melalui aplikasi tersebut, pengguna hanya perlu memilih preferensinya dan selanjutnya sistem akan memberikan rekomendasi destinasi ekowisata terbaik dengan sentimen positif
Predicting Potential Car Buyers using Logistic Regression Algorithm
Full text linkThis research aims to develop a predictive model to identify individuals with a high potential to become car buyers, employing logistic regression algorithm. The primary objective is to support the automotive industry in devising more efficient and focused marketing strategies. The choice of logistic regression is based on its superiority in handling categorical dependent variables and its practicality in result interpretation. The data processed in this study derive from demographic information, consumption habits, brand preferences, and various other factors that influence car buying decisions. The main data source is the outcome of online surveys participated in by individuals predicted to have the potential to buy a car within the next 12 months. The analysis results indicate that factors such as income, age, previous vehicle ownership status, gender and marriage status play significant roles in predicting the likelihood of someone becoming a car buyer. The developed model achieved an accuracy and precision of 95%, proving its significant capability in identifying potential car buyers with a high success rate. These findings provide valuable insights for the automotive industry in formulating more targeted and efficient marketing strategies, as well as contributing to the academic literature on the application of logistic regression in consumer behavior prediction
Digitalization of Legal Information Management in Primary Schools Based on the JDIH Application: Digitalisasi Manajemen Informasi Hukum Sekolah Dasar Berbasis Aplikasi JDIH
Full text linkThe rapid development of science and technology in the education sector has prompted institutions like the elementary school to improve the efficiency and effectiveness of information and legal management. This study aims to develop a Legal Documentation and Information Network (JDIH) application to facilitate the publication of school regulations. The primary objective of this research is to create an application that simplifies the management of student and school information, ensuring compliance with educational laws, and fostering an adaptive educational environment. The research used the System Development Life Cycle (SDLC) methodology, utilizing the Waterfall Model approach, which includes planning, analysis, design, implementation, testing, and maintenance. Data was gathered through observation, interviews, and literature studies, ensuring comprehensive insights into the existing regulatory management practices at the school. The JDIH application was successfully developed and implemented at the elementary school. It improved the accessibility of school regulations, ensuring better legal compliance and enhancing transparency. Positive feedback was received from respondents, with an average satisfaction level of 83.3%. This study demonstrates the effectiveness of the JDIH application in streamlining regulatory management. It is expected that the application will be expanded to other schools, further improving the management of legal information and promoting a more transparent and efficient educational environment.Perkembangan pesat ilmu pengetahuan dan teknologi di sektor pendidikan mendorong lembaga seperti SD Inpres 7 Labuan Baru untuk meningkatkan efisiensi dan efektivitas pengelolaan informasi dan regulasi. Penelitian ini bertujuan untuk mengembangkan aplikasi Jaringan Dokumentasi dan Informasi Hukum (JDIH) untuk mempublikasikan peraturan sekolah. Tujuan utama dari penelitian ini adalah menciptakan aplikasi yang mempermudah pengelolaan informasi siswa dan sekolah, memastikan kepatuhan terhadap peraturan pendidikan, dan menciptakan lingkungan pendidikan yang adaptif. Penelitian ini menggunakan metode System Development Life Cycle (SDLC) dengan pendekatan Waterfall Model, yang mencakup perencanaan, analisis, desain, implementasi, pengujian, dan pemeliharaan. Data dikumpulkan melalui observasi, wawancara, dan studi literatur, untuk mendapatkan pemahaman menyeluruh tentang praktik pengelolaan regulasi yang ada di sekolah. Aplikasi JDIH berhasil dikembangkan dan diimplementasikan di SD Inpres 7 Labuan Baru. Aplikasi ini meningkatkan aksesibilitas peraturan sekolah, memastikan kepatuhan hukum yang lebih baik, dan meningkatkan transparansi. Umpan balik positif diterima dari responden, dengan tingkat kepuasan rata-rata sebesar 83,3%. Penelitian ini menunjukkan efektivitas aplikasi JDIH dalam memperlancar pengelolaan regulasi. Diharapkan aplikasi ini dapat diperluas ke sekolah-sekolah lain, untuk meningkatkan pengelolaan informasi hukum dan menciptakan lingkungan pendidikan yang lebih transparan dan efisien
Ecotourism Recommendations based on Sentiments Using Skyline Query and Apache-Spark
Full text linkThe selection of an ecotourism destination is a challenging service in an online transaction. The process must consider personal considerations, such as costs or distance and interesting eco-points like specific sceneries or the rare and unique picturesque landscapes. Only a few tourists have such required information for any particular local resources. A proposed recommender system is a solution for tourists to get advice on appropriate ecotourism destinations based on sentiments according to their preferences. This work proposed the skyline query method based on the Skyline Sort Filter algorithm in the Apache Spark cluster computing framework to build recommendations. The sentiment analysis process using the SentiStrength algorithm obtain an accuracy of 78.3% and F-arithmetic of 84.5%. These results indicate the proposed recommender system can detect positive responses from visitors to ensure best ecotourism recommendations with positive sentiments for tourist. Apache Spark with three computer nodes has 213.7 times faster execution time on correlated data, 240 times faster on independent data, and 288.1 times faster on anti-correlated data than a single computing method
TWITTER (X) SENTIMENT ANALYSIS OF KAMPUS MERDEKA PROGRAM USING SUPPORT VECTOR MACHINE ALGORITHM AND SELECTION FEATURE CHI-SQUARE
Full text linkMinistry of Education, Culture, Research and Technology (Kemendikbudristek) has implemented numerous policies aimed at enhancing the quality of education in the country. One of these policies is Kampus Merdeka program. The program includes various initiatives such as Teaching Campus, the Merdeka Student Exchange program, and Internship and Independent Study programs, which have gained significant popularity among students across Indonesia. However, the Kampus Merdeka program has drawn many pros and cons, with some parties supporting the initiative, but also many criticisms related to its implementation, which is considered not optimal in some educational institutions. Social media is where many of these opinions are voiced, one of the most widely used of which is twitter. In light of these circumstances, this study conducted a sentiment analysis of the independent campus program to assess public sentiment towards it. The dataset used in this research consisted of 500 tweets containing the keyword "kampus merdeka" with 250 tweets reflecting positive sentiment and 250 tweets reflecting negative sentiment. The results of the tests carried out obtained the highest increase in results in the 10:90 ratio, namely with an accuracy that increased by 14% from the previous 66% to 80%, precision also increased by 22% from the previous 67% to 89%, recall increased by 16% from the previous 58% to 79%, and the f1-score value which was previously 62% turned into 79% because it also increased by 17%
Implementation of Naive Bayes for Optimizing Asset Condition Classification in a Web-Based Information System
No full textImproving the quality of work performance is an essential aspect for employees at the Office of Investment and Integrated One-Stop Services of Central Sulawesi Province. Many challenges remain in managing asset data, especially because the recording and monitoring processes are still performed manually. This manual approach often leads to inconsistencies, inefficiencies, and difficulties in determining asset eligibility. Therefore, an information system capable of supporting accurate and efficient data management is highly needed. The main objective of this study is to apply the Naive Bayes algorithm to classify asset conditions in a web-based system, enabling faster decision-making and improving the accuracy of asset feasibility assessments within government institutions. The dataset used in this study consists of three key attributes asset functionality, asset age, and physical condition. These attributes serve as indicators for classification using the Naïve Bayes probabilistic approach. The developed web-based application was evaluated through black-box testing to ensure that all system functions performed according to expectations and produced consistent outputs. Black-box testing results show that the system successfully provides correct outputs for each test scenario, verifying that the classification and data management processes operate properly. The application is able to classify assets into feasible or non-feasible categories based on calculated probabilities. Findings indicate that implementing the Naïve Bayes algorithm significantly improves the efficiency of asset data processing and enhances data management quality. The system also supports more objective decision-making regarding asset feasibility. This study demonstrates that probabilistic classification can be effectively integrated into governmental asset management systems to optimize operational performance.Improving the quality of work performance is an essential aspect for employees at the Office of Investment and Integrated One-Stop Services of Central Sulawesi Province. Many challenges remain in managing asset data, especially because the recording and monitoring processes are still performed manually. This manual approach often leads to inconsistencies, inefficiencies, and difficulties in determining asset eligibility. Therefore, an information system capable of supporting accurate and efficient data management is highly needed. The main objective of this study is to apply the Naive Bayes algorithm to classify asset conditions in a web-based system, enabling faster decision-making and improving the accuracy of asset feasibility assessments within government institutions. The dataset used in this study consists of three key attributes asset functionality, asset age, and physical condition. These attributes serve as indicators for classification using the Naïve Bayes probabilistic approach. The developed web-based application was evaluated through black-box testing to ensure that all system functions performed according to expectations and produced consistent outputs. Black-box testing results show that the system successfully provides correct outputs for each test scenario, verifying that the classification and data management processes operate properly. The application is able to classify assets into feasible or non-feasible categories based on calculated probabilities. Findings indicate that implementing the Naïve Bayes algorithm significantly improves the efficiency of asset data processing and enhances data management quality. The system also supports more objective decision-making regarding asset feasibility. This study demonstrates that probabilistic classification can be effectively integrated into governmental asset management systems to optimize operational performance
Implementation of Collaborative Filtering in the Salted Fish Recommendation Process
No full textThe development of e-commerce in the current era has been so rapid that buying and selling transactions are carried out online through various media, including websites and applications. With so many products available in the application, users often feel confused when choosing the product they want to buy, so it takes a long time to choose a product to avoid regret after purchasing it. In this study, a web-based recommendation system was created for the process of recommending salted fish with the aim of making it easier for customers to choose the type of salted fish. The Collaborative Filtering method was used, employing Pearson Correlation as a tool to calculate the similarity value between users, then using Weighted Sum to calculate the prediction value. Collaborative Filtering often experiences the cold start problem, where the system has difficulty providing recommendations to users who do not yet have a transaction history. Therefore, the author proposes a popularity-based strategy as a measure to overcome this problem. Based on testing, the author obtained results of MAE = 0.63 and RMSE = 0.81 based on train-test split results with a data distribution of 80:20, 80% of the dataset for training and 20% of the dataset for testing with an accuracy of 70-80%, indicating that this system works well. This system has been tested using the Blackbox method.The development of e-commerce in the current era has been so rapid that buying and selling transactions are carried out online through various media, including websites and applications. With so many products available in the application, users often feel confused when choosing the product they want to buy, so it takes a long time to choose a product to avoid regret after purchasing it. In this study, a web-based recommendation system was created for the process of recommending salted fish with the aim of making it easier for customers to choose the type of salted fish. The Collaborative Filtering method was used, employing Pearson Correlation as a tool to calculate the similarity value between users, then using Weighted Sum to calculate the prediction value. Collaborative Filtering often experiences the cold start problem, where the system has difficulty providing recommendations to users who do not yet have a transaction history. Therefore, the author proposes a popularity-based strategy as a measure to overcome this problem. Based on testing, the author obtained results of MAE = 0.63 and RMSE = 0.81 based on train-test split results with a data distribution of 80:20, 80% of the dataset for training and 20% of the dataset for testing with an accuracy of 70-80%, indicating that this system works well. This system has been tested using the Blackbox method
Performance Comparison of Multilayer Perceptron (MLP) and Random Forest for Early Detection of Cardiovascular Disease
No full textCardiovascular disease is a disorder of the heart and blood vessels that can lead to heart attacks, strokes, and heart failure, so early detection is essential. This study compares Multilayer Perceptron (MLP) and Random Forest for risk classification in a Kaggle dataset containing 70,000 samples with balanced targets. Pre-processing included age conversion, outlier cleaning, standardization, and feature selection based on feature importance. Both models were optimized using RandomizedSearchCV and evaluated using accuracy, precision, recall, F1-score, AUC-ROC, confusion matrix, and k-fold cross-validation. The results show that the accuracy of MLP is 73.90% and Random Forest is 74.23% with an AUC of 0.80 for both. Random Forest is more stable across all folds and performs better on the negative class, while MLP is slightly more sensitive to the positive class. Independent t-test and Mann-Whitney U tests show p>0.05, indicating that the difference in performance is not significant. The most influential features were diastolic blood pressure, age, cholesterol, and systolic blood pressure. The non-clinical Streamlit prototype demonstrated the model\u27s potential for education and initial decision support
Implementation of QR Code in A Student Attendance Information Based On WhatsApp Gateway
No full textThe attendance information system at Senior High School 7 Sigi, still uses a manual attendance system, namely writing on paper sheets. The problem that often occurs is the loss of student attendance books which causes the school to have difficulty in recapitulating attendance and also reporting attendance to parents. Another problem that occurs due to manual attendance is that parents cannot directly monitor their children's attendance at school which causes some students to skip school. The recommended solution is to use an attendance information system by utilizing QR Code technology so that student attendance is more practical and also the data storage is much safer. WhatsApp Gateway is used as a monitoring medium for parents because this system will send notifications via the WhatsApp application every time the lesson starts, effectively and in real-time. This attendance system uses the Waterfall method which starts from the planning, analysis, design and implementation stage
- …
