Claim Missing Document
Check
Articles

Recruitment Classification of Security Unit PT. Satria Kencana Abadi Using Naïve Bayes Method Rilvani, Elkin; Surojudin, Nurhadi; Danny, Muhtajuddin; Yoga Pratama, Evan
Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i1.4138

Abstract

To get human resources according to company standards, the problem faced in the company is the difficulty of the selection process with a short time and the complexity of the decision making process resulting in subjective decision making. The purpose of this research is to assist the assessment process in making decisions for determining the selection of security units (SATPAM) to be more targeted so that it can help the company. In this study the data used were 697 data with 558 training data and 139 testing data. This test data was carried out using the Naïve Bayes algorithm method to classify so that it can determine accurate and efficient decision making, using Rapidminer tools which have 82 accuracy, 01%, 81.61% Precision, and 88.75% recall. This shows that the Naïve Bayes algorithm method has a good performance in determining decision making during the selection of security forces (SATPAM) at PT. Satria Kencana Abadi.
The Sentiment Analysis of Bekasi Floods Using SVM and Naive Bayes with Advanced Feature Selection Amali, Amali; Maulana, Donny; Widodo, Edy; Firmansyah, Andri; Danny, Muhtajuddin
Brilliance: Research of Artificial Intelligence Vol. 4 No. 1 (2024): Brilliance: Research of Artificial Intelligence, Article Research May 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i1.4268

Abstract

Flood management in Bekasi City poses significant challenges, necessitating strategies grounded in an understanding of community sentiment. This study aims to develop and optimize sentiment analysis of social media data related to flooding using Support Vector Machine (SVM) and advanced feature selection techniques. The primary goal is to enhance the accuracy of classifying public sentiment toward flood management efforts in Bekasi City. Data is collected from various social media platforms, preprocessed, and analyzed using SVM with feature selection techniques like Information Gain and Analysis of Variance (ANOVA). (Thoriq et al., 2023) Our findings indicate that using SVM with advanced feature selection significantly improves sentiment classification accuracy compared to standard methods. These results offer insights into public perceptions, helping policymakers improve management strategies and communication for flood events. This method assists in understanding community responses and pinpointing critical areas needing attention. Moreover, this study contributes to disaster management in urban flood-prone areas by presenting a methodological approach applicable to other disaster contexts. Integrating social media sentiment analysis with advanced machine learning techniques offers a robust framework for real-time public sentiment assessment, enhancing disaster response strategies. Furthermore, these techniques help create a more resilient urban environment by improving the efficiency and effectiveness of flood management practices. This comprehensive tool is essential for better preparedness, response, and recovery from flood events, ultimately enhancing community resilience and safety in Bekasi City. This research is part of machine learning in disaster management and a valuable asset for city planners and disaster professionals around the world.
Analisis Prediksi Resiko Diabetes Tahap Awal Menggunakan Algoritma Naive Bayes Danny, Muhtajuddin; Muhidin, Asep
Jurnal Teknologi Informatika dan Komputer Vol. 9 No. 2 (2023): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v9i2.2017

Abstract

Diabetes merupakan salah satu penyakit kronis yang diakibatkan adanya kelainan sekresi insulin pada kenaikan glukosa secara tidak teratur. Resiko penyakit stroke, penyakit jantung, kebutaan bahkan hingga resiko kematian merupakan penyakit komplikasi yang terjadi ketika adanya peningkatakn gula darah dalam tubuh pada penderita diabetes. Diabetes merupakan salah satu penyakit yang memiliki faktor resiko kematian yang tinggi. Deteksi dini penyakit diabetes perlu dilakukan sebagai upaya dalam menurukan tingkat kematian yang diakibatkan oleh faktor penyakit tersebut. Model yang diusulkan yaitu menerapkan algoritma Naive Bayes sebagai algoritma pengklasifikasi. Dataset yang dijadikan sebagai objek penelitian yaitu dataset Early Stage Diabetes Risk Prediction merupakan dataset terbuka yang bersumber dari UCI Machine Learning. Metode-metode yang digunakan dalam melakukan prediksi yaitu metode data mining. Data mining merupakan serangkaian tindakan untuk menemukan hubungan dari pola dan kecenderungan dari data yang disimpan. Desain alur sistem klasifikasi jenis pada penelitian ini, dimulai dari penentuan Dataset, Loading dan baca data, Analisis Eksplorasi Data, Data Preprocessing, membangun model data, evaluasi Confusion Matrix, dan Hyperparameter Tuning. Didapatkan nilai True Positive sebanyak 276, True Negative sebanyak 180, False Positive sebanyak 20 dan False Negative sebanyak 44. Nilai akurasi yang didapatkan dalam penelitian yaitu sebesar 87.88% dengan kategori Good Classification serta memiliki error rate yang rendah yaitu 12.12% termasuk kedalam kategori Good Error Rate. Hasil penelitian tersebut menunjukan bahwa algoritma Naive Bayes memiliki kinerja yang baik serta dapat dijadikan sebagai landasan dalam memprediksi risiko diabetes tahap awal.
Optimasi Algoritma Random Forest untuk Prediksi Eksport Kelapa Sawit Global Danny, Muhtajuddin; Muhidin, Asep
Bulletin of Computer Science Research Vol. 5 No. 5 (2025): August 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i5.744

Abstract

Palm oil production is a strategic commodity in global trade, with a trend showing an increase from year to year. This study aims to optimize the Random Forest algorithm in predicting the amount of global palm oil production based on historical data. The dataset used consists of 12,458 observations with one dependent variable (Palm_Oil_00002577_) representing the amount of palm oil production, and four independent variables: country, Code, Year, and Palm_Oil_00002577_log. The data is divided into 80% for training (9,966 observations) and 20% for testing (2,492 observations). The model optimization process is carried out by adjusting the key parameters of Random Forest using Grid Search and Cross-Validation. The initial Random Forest model (without optimization) produces a Root Mean Squared Error (RMSE) value of 115.27 and an R-squared (R²) value of 0.9824 on the test data. After optimization using Grid Search and Cross-Validation on key parameters (n_estimators, max_depth, and max_features), the optimized model showed significant performance improvements, with the RMSE decreasing to 103.54 and the R² increasing to 0.9984. The decrease in the RMSE indicates a reduction in the model's average prediction error, while the increase in R² approaching 1 indicates the model's ability to explain almost all of the variation in global palm oil production data. These results indicate that parameter optimization in Random Forest can substantially improve prediction accuracy, enabling the model to be used as a production planning tool and strategic decision-making tool in the palm oil commodity trading sector.
Prediksi Kegagalan Perangkat Industri Menggunakan Random Forest dan SMOTE untuk Pemeliharaan Preventif Muhidin, Asep; Muhtajuddin Danny; Surojudin, Nurhadi
Bulletin of Computer Science Research Vol. 5 No. 5 (2025): August 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i5.745

Abstract

Preventive maintenance is an essential strategy to minimize losses due to industrial equipment failures. This study aims to develop an equipment failure prediction model using the Random Forest algorithm with the SMOTE technique to address class imbalance. The dataset used is the AI4I 2020 Predictive Maintenance Dataset with 10,000 entries and six main input variables. Preprocessing includes normalization of numerical features, one-hot encoding for categorical features, and handling of missing values. The Random Forest model was optimized using GridSearchCV and compared with K-Nearest Neighbors. Results show that Random Forest with SMOTE achieved 97% accuracy, 0.47 precision, 0.75 recall, and 0.58 F1-score on the failure class. This model outperforms KNN in detecting failures, particularly in imbalanced data. These findings contribute to the development of an early warning system to support preventive maintenance in industrial environments.
Sistem Informasi Laporan Petugas Patroli Jalan Tol Cibitung – Tanjung Priok Berbasis Web Khris Phasarilla, Dutha; Danny, Muhtajuddin; Priyo, Basuki Edi
Jurnal Pustaka Data (Pusat Akses Kajian Database, Analisa Teknologi, dan Arsitektur Komputer) Vol 5 No 2 (2025): Jurnal Pustaka Data (Pusat Akses Kajian Database, Analisa Teknologi, dan Arsitekt
Publisher : Pustaka Galeri Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55382/jurnalpustakadata.v5i2.1342

Abstract

Penelitian ini bertujuan untuk merancang dan mengembangkan sebuah sistem informasi guna meningkatkan proses pelaporan kegiatan petugas patroli di jalan tol Cibitung–Tanjung Priok. Sistem pelaporan yang saat ini digunakan masih bergantung pada dokumentasi manual dengan tulisan tangan, yang seringkali menyebabkan ketidakefisienan, kehilangan data, dan kesulitan dalam pengambilan kembali informasi. Untuk mengatasi permasalahan tersebut, dikembangkan sebuah platform berbasis web yang memungkinkan petugas patroli mencatat dan mengirimkan laporan kegiatan mereka secara langsung melalui smartphone. Peralihan ke sistem digital ini tidak hanya mempercepat proses pelaporan, tetapi juga meningkatkan akurasi, aksesibilitas, dan ketepatan waktu dalam pengumpulan data. Sistem yang dikembangkan dirancang dengan antarmuka yang sederhana dan ramah pengguna, sehingga mudah digunakan bahkan bagi pengguna dengan keterampilan teknis minimal. Selain itu, integrasi basis data terstruktur berfungsi sebagai repositori terpusat untuk semua data yang direkam, sehingga memudahkan penyimpanan, pengambilan, dan pengelolaan data kegiatan patroli. Penelitian ini juga membahas tantangan-tantangan yang dihadapi selama tahap pengembangan dan implementasi, khususnya yang berkaitan dengan manajemen basis data, adopsi pengguna, dan aksesibilitas sistem di lapangan. Hasil penelitian menunjukkan bahwa sistem pelaporan digital yang dirancang dengan baik secara signifikan meningkatkan efisiensi operasional, integritas data, dan efektivitas pemantauan patroli di jalan tol.
Penerapan Data Mining dengan Algoritma C4.5 dan K-nearest Neighbor untuk Prediksi Penjualan Bahan Bangunan Terlaris Surojudin, Nurhadi; Danny, Muhtajuddin
Jurnal Informatika Ekonomi Bisnis Vol. 7, No. 3 (September 2025)
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/infeb.v7i3.1241

Abstract

The main problem faced by PT. Surya Kapuas Perkasa is the difficulty in accurately determining the types of building materials with the highest sales levels. Currently, stock determination still relies on manual estimates based on previous sales trends, which are prone to errors and inaccuracies. As a result, the company often faces the risk of overstocking products that are less in demand, or understocking products that are actually in high demand. This condition can impact the sales process, increase storage costs, and reduce customer satisfaction. To overcome this problem, a method is needed that can predict the sales of the best-selling building materials more objectively and based on historical data. This prediction will utilize sales data from the past three years by applying data mining classification techniques using the C4.5 algorithm and K-Nearest Neighbor (K-NN) through the RapidMiner application. With this approach, the company can accurately identify the types of building materials that are most in demand in the market, allowing for more precise and efficient stock management. Based on the research results, four types of building materials were found to be the best-selling out of a total of 16 types analyzed: Light Steel, Brick, Iron, and Cement, with a prediction accuracy rate of 87.16%.
Building Transparent and Efficient Community Administration: Agile Development of a Neighborhood Information System at Kertamukti Sakti Residence Irawan, Reza Riyaldi; Pramudito, Dendy K; Danny, Muhtajuddin
SISTEMASI Vol 15, No 1 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i1.5784

Abstract

Community management in residential areas often relies on manual paper-based administration, leading to inefficiency, unclear financial records, data loss, and limited transparency, which undermine good governance and residents’ trust. This study aims to develop a web-based neighborhood (RT/RW) management information system to improve administrative effectiveness, financial transparency, and service quality. The system was built using CodeIgniter, PHP, MySQL, Bootstrap, and jQuery, applying the Agile development method to ensure flexibility and iterative improvement through continuous feedback between the developers and the community. The development process consisted of planning, design, coding, testing, and release stages, with flowcharts and wireframes supporting interface design and black box testing used for functional validation. The system was evaluated using a user-centered usability assessment (System Usability Scale – SUS), obtaining an average score of 82.5, which falls under the Excellent category. In addition, the financial reporting process time was reduced from three days to one hour, and data entry errors decreased by 90%, proving that the system significantly improves operational efficiency and transparency compared to manual methods. In conclusion, the combination of Agile methodology and lightweight frameworks such as CodeIgniter successfully delivers a responsive, transparent, and user-oriented information system that enhances trust and collaboration within the community. Future development will focus on integrating QRIS, e-wallets, and bank transfers to further streamline financial transactions and support sustainable digital transformation in community management.
Pelatihan Internet of Things (IoT) untuk Smart Home dan Smart School di SMK Garuda Nusantara Danny, Muhtajuddin; Arwan Sulaeman, Asep; Maringan Hutauruk, Basar; Damuri, Amat
VIDHEAS: Jurnal Nasional Abdimas Multidisiplin Vol. 3 No. 2 (2025): Desember 2025
Publisher : VINICHO MEDIA PUBLISINDO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61946/vidheas.v3i2.157

Abstract

The rapid development of digital technology, particularly the Internet of Things (IoT), requires vocational education institutions to align graduate competencies with the demands of Industry 4.0. SMK Garuda Nusantara has significant potential in developing technology-based human resources; however, limitations remain in teachers’ and students’ practical IoT skills as well as in the availability of supporting learning facilities. This community service program aims to enhance teachers’ and students’ competencies through IoT training integrated with smart home and smart school concepts. The implementation method consists of preparation, socialization, theoretical training, hands-on workshops, mentoring, and program evaluation. The training focuses on the use of microcontrollers, sensors, and the development of applied IoT prototypes such as automatic lighting systems, RFID-based attendance systems, and classroom environmental monitoring. The expected outcomes include improved practical skills of teachers and students, the development of IoT learning modules based on project-based learning, and the creation of simple smart home and smart school prototypes applicable in the school environment. This program also supports the implementation of the Merdeka Belajar Kampus Merdeka (MBKM) policy and contributes to the achievement of higher education Key Performance Indicators (IKU) through sustainable collaboration between universities and school partners.
Analisis Tingkat Sentimen Opini Publik Terhadap Kebijakan TV Digital di Platform X Menggunakan Multinomial Naïve Bayes Sulaeman, Asep Arwan; Naya, Candra; Danny, Muhtajuddin; Effendi, M. Makmun
Bulletin of Computer Science Research Vol. 6 No. 2 (2026): February 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i2.951

Abstract

The migration from analog to digital television broadcasting is part of the transformation of the broadcasting system aimed at improving broadcast quality and spectrum efficiency. However, the implementation of the digital television policy has generated diverse public responses, ranging from support to criticism. This study aims to analyze public opinion on the digital television policy in Indonesia using social media data from platform X. A quantitative approach was employed using text mining and supervised machine learning techniques. Data were collected through a crawling process using the keyword “tv digital”, resulting in 1,855 tweets. After data selection and cleaning, 789 tweets were obtained as the final dataset. The analysis stages included text preprocessing, feature extraction using Term Frequency–Inverse Document Frequency (TF–IDF), and sentiment classification using the Multinomial Naïve Bayes algorithm. The results indicate that positive sentiment dominates public opinion, with 478 tweets (60.58%), while negative sentiment accounts for 311 tweets (39.42%). Model performance evaluation shows an accuracy of 79.21%, precision of 82.45%, and recall of 85.06%, indicating that the model performs well and consistently in classifying sentiment. These findings demonstrate that social media–based sentiment analysis can serve as an empirical approach to understanding public perceptions of digital television policy.