Abstract:Abstract: M2M Futsal is one of the futsal field rental service providers that still conducts its operational management manually, such as scheduling, customer data recording, and transaction processing. This manual process…
ss has several drawbacks, including the risk of data loss, recording errors, and limitations in data retrieval and reporting. Therefore, this study aims to design and develop a web-based futsal field management information system to support more effective and efficient business processes. The system is developed using the Laravel framework due to its ability to streamline the development process, high level of security, and support for the Model-View-Controller (MVC) architecture. The system development method used is the waterfall model, which includes stages such as requirement analysis, system design, implementation, testing, and maintenance. The developed features include rental management, customer data, field schedules, payments, and revenue reports. The implementation results show that the system improves the rental management process, reduces data entry errors, and facilitates report generation. Additionally, the system has been successfully implemented online, allowing access anytime and anywhere via the internet. This system makes a significant contribution to the digitalization of M2M Futsal’s services and serves as a potential technological solution for managing similar businesses in the future.
Â
Keyword: Information System, Laravel, Field Rental, Web, Futsal, Digitalization, Online Access
Â
Abstrak: M2M Futsal merupakan salah satu penyedia layanan penyewaan lapangan futsal yang masih menjalankan proses manajemen operasional secara manual, seperti pencatatan jadwal, data pelanggan, dan transaksi. Proses manual tersebut memiliki berbagai kekurangan, antara lain risiko kehilangan data, kesalahan pencatatan, serta keterbatasan dalam pencarian dan pelaporan data. Oleh karena itu, penelitian ini bertujuan untuk merancang dan membangun sistem informasi manajemen lapangan futsal berbasis web guna mendukung proses bisnis yang lebih efektif dan efisien. Sistem dikembangkan menggunakan framework Laravel karena kemampuannya dalam menyederhanakan proses pengembangan, keamanan yang tinggi, serta dukungan struktur arsitektur Model-View-Controller (MVC). Metode pengembangan sistem yang digunakan adalah waterfall, yang meliputi tahapan analisis kebutuhan, desain, implementasi, pengujian, dan pemeliharaan. Fitur-fitur yang dikembangkan dalam sistem ini meliputi manajemen penyewaan, data pelanggan, jadwal lapangan, pembayaran, serta laporan pendapatan. Hasil implementasi menunjukkan bahwa sistem mampu mempercepat proses manajemen penyewaan, mengurangi kesalahan pencatatan, serta mempermudah penyusunan laporan. Selain itu, sistem ini telah berhasil diimplementasikan secara online, sehingga dapat diakses kapan saja dan di mana saja melalui jaringan internet. Sistem ini memberikan kontribusi nyata terhadap digitalisasi layanan M2M Futsal dan dapat menjadi solusi teknologi bagi pengelolaan usaha serupa di masa mendatang.
Â
Kata kunci: Sistem Informasi, Laravel, Penyewaan Lapangan, Web, Futsal, Digitalisasi, Online Access
Abstract:Abstract: Mental health issues such as depression are prevalent among students and significantly impact both academic performance and psychological well-being. While machine learning techniques have been widely employed…
to predict mental health conditions, single-model approaches often suffer from limited generalizability and interpretability. This study proposes a Stacked Ensemble Learning framework that integrates three heterogeneous base classifiers—Logistic Regression (LR), Support Vector Machine (SVM) with RBF kernel, and Random Forest (RF)—combined with a meta-learner to enhance the accuracy and robustness of depression prediction among students. Experiments were conducted on a large-scale student mental health dataset comprising 27,901 records, with preprocessing steps including feature standardization, class balancing using SMOTE, and stratified cross-validation. Performance evaluation utilized Confusion Matrix, F1-Score, Recall, Precision, and the Area Under the ROC Curve (AUC-ROC). The proposed ensemble model achieved a classification accuracy of 84%, an AUC of 0.911, and an average precision of 0.89, consistently outperforming individual baseline classifiers. These results validate that combining margin-based, non-linear, and tree-based models can yield more reliable and interpretable predictions. The proposed architecture presents a promising and explainable tool for early detection of mental health issues within educational settings.
Keywords: depression detection; student mental health; ensemble learning;machine learning.
Abstrak: Permasalahan kesehatan mental seperti depresi kerap dialami oleh siswa dan berdampak pada performa akademik serta kesejahteraan psikologis mereka. Meskipun pendekatan pembelajaran mesin telah banyak digunakan untuk prediksi kondisi ini, model tunggal kerap menghadapi keterbatasan dalam hal generalisasi dan interpretabilitas. Studi ini mengusulkan kerangka kerja Stacking Ensemble Learning yang mengintegrasikan tiga model dasar—Logistic Regression (LR), Support Vector Machine (SVM) dengan kernel RBF, dan Random Forest (RF)—yang dikombinasikan dengan meta-learner untuk meningkatkan akurasi dan stabilitas prediksi depresi pada siswa. Eksperimen dilakukan pada dataset berskala besar yang mencakup 27.901 entri, dengan penerapan preprocessing, standardisasi, penyeimbangan kelas menggunakan SMOTE, dan validasi silang stratifikasi. Evaluasi performa menggunakan metrik Confusion Matrix, F1-Score, Recall, Precision, serta AUC-ROC Curve. Hasil menunjukkan bahwa model ansambel yang diusulkan mencapai akurasi 84%, AUC 0,911, dan rata-rata precision 0,905, yang secara konsisten melampaui performa model individual. Temuan ini menegaskan bahwa kombinasi antara model berbasis margin, non-linear, dan pohon keputusan mampu menghasilkan prediksi yang lebih andal dan dapat dijelaskan, sehingga potensial untuk diimplementasikan dalam sistem pemantauan kesehatan mental berbasis institusi pendidikan.
Kata kunci: deteksi depresi, kesehatan mental siswa, stacking ensemble, machine learning.
Abstract:Abstract: Coffee bean classification is a crucial step in ensuring the quality and selling value of coffee products. Manual sorting methods are often inefficient and error-prone, necessitating a technology-based automated…
d approach. This study proposes a combination of the Inception V3 architecture as an image feature extraction method and the random forest algorithm as a classifier to distinguish good and defective coffee beans. The dataset used consists of 986 images, divided into training and test data. The processing was carried out using the Orange Data Mining platform, which includes pre-processing, feature extraction, model training, and performance evaluation. The evaluation results show that the model produces an accuracy of 96.4% on the training data and 96.8% on the test data. In addition, other performance metrics such as AUC (1.000), F1-score (0.967), precision (0.968), recall (0.968), and MCC (0.922) strengthen the model's excellent classification performance. Thus, the combined approach of Inception V3 and random forest is proven effective and has the potential to be implemented in a digital image-based coffee bean classification system.
Â
Keywords: Coffee Bean Classification, Random Forest, Inception V3, Feature Extraction, Digital Imagery
Abstrak: Klasifikasi biji kopi merupakan langkah penting dalam menjamin mutu dan nilai jual produk kopi. Metode manual dalam penyortiran sering kali tidak efisien dan rentan kesalahan, sehingga dibutuhkan pendekatan otomatis berbasis teknologi. Penelitian ini mengusulkan kombinasi arsitektur Inception V3 sebagai metode ekstraksi fitur citra dan algoritma random forest sebagai klasifikator untuk membedakan biji kopi bagus dan rusak. Dataset yang digunakan terdiri dari 986 gambar, terbagi menjadi data latih dan data uji. Proses pengolahan dilakukan menggunakan platform Orange Data Mining, yang meliputi tahap pra-pemrosesan, ekstraksi fitur, pelatihan model, dan evaluasi kinerja. Hasil evaluasi menunjukkan bahwa model menghasilkan akurasi sebesar 96,4% pada data latih dan 96,8% pada data uji. Selain itu, metrik performa lain seperti AUC (1.000), F1-score (0.967), precision (0.968), recall (0.968), dan MCC (0.922) memperkuat bahwa model ini memiliki kinerja klasifikasi yang sangat baik. Dengan demikian, pendekatan kombinasi Inception V3 dan random forest terbukti efektif dan berpotensi diimplementasikan dalam sistem klasifikasi biji kopi berbasis citra digital.
Â
Kata kunci: Klasifikasi Biji Kopi, Random Forest, Inception V3, Ekstraksi Fitur, Citra Digital
Abstract:Abstract: Coffee is one of the most important commodities in the global agricultural sector. However, the manual sorting process of coffee beans, which is still widely applied in the Small and Medium Industry (IKM) sector,…
r, tends to be time-consuming and often results in inconsistent quality assessments. This study aims to classify coffee bean quality using the DenseNet-201 deep learning architecture, optimized with the GridSearch method to obtain the best combination of hyperparameters. The dataset used consists of 450 images of coffee beans divided into two classes: good-quality and defective beans. The model was trained for 20 epochs using a transfer learning approach and evaluated using performance metrics such as accuracy, precision, recall, and F1-score. The test results show that the model before optimization achieved an accuracy of only 78.67%, while the model optimized with GridSearch reached a high accuracy of 99.47% with a low loss value. These findings indicate that the application of DenseNet-201 with hyperparameter tuning is capable of producing accurate and stable classification results, and can be relied upon as an automated solution for sorting coffee beans based on their quality.
Â
Keywords: Deep Learning, DenseNet201, Hyperparameter, GridSearch, Coffee Bean Classification
Abstrak: Kopi merupakan salah satu komoditas penting dalam sektor pertanian global. Namun, proses pemilahan biji kopi secara manual yang masih banyak diterapkan pada sektor Industri Kecil dan Menengah (IKM) cenderung memakan waktu dan menghasilkan penilaian kualitas yang tidak konsisten. Penelitian ini bertujuan untuk mengklasifikasikan kualitas biji kopi menggunakan arsitektur Deep Learning DenseNet-201 yang dioptimalkan dengan metode GridSearch untuk memperoleh kombinasi hyperparameter terbaik. Dataset yang digunakan terdiri dari 450 gambar biji kopi dengan dua kelas: biji kopi bagus dan biji kopi rusak. Model dilatih selama 20 epoch dengan pendekatan transfer learning dan dilakukan evaluasi terhadap performa model menggunakan metrik akurasi, precision, recall, dan f1-score. Hasil pengujian menunjukkan bahwa model sebelum optimasi hanya mencapai akurasi sebesar 78,67%, sedangkan model dengan optimasi GridSearch mampu mencapai akurasi tinggi sebesar 99,47% dan nilai loss yang rendah. Hal ini menunjukkan bahwa penerapan DenseNet-201 dengan tuning hyperparameter mampu menghasilkan klasifikasi yang akurat dan stabil, serta dapat diandalkan sebagai solusi otomatis dalam proses sortasi biji kopi berdasarkan kualitasnya.
Â
Kata kunci: Deep Learning, DenseNet201, Hyperparameter, GridSearch, Klasifikasi Biji Kopi
Abstract:Abstract: This research aims to design and build a Tourism Potential Information System for Kota Pari Village, located in Pantai Cermin District, Serdang Bedagai Regency, using the Waterfall Method approach. The problem…
faced is the lack of accessibility of information on the tourism potential of Kota Pari Village online, which hinders the promotion and development of local tourism potential. The purpose of this research is to overcome these obstacles by designing and developing a web-based platform that can provide comprehensive information about the tourism potential of Kota Pari Village to the general public and potential tourists. The research method used is the Waterfall Method, which consists of five main stages: needs analysis, system design, implementation, testing, and maintenance. The needs analysis stage involves identifying user needs, required features, and the structure of information to be presented in the system. Furthermore, system design was conducted to design an intuitive and systematic user interface, as well as a robust and scalable system architecture. The result of this research is a web-based Kota Pari Village Tourism Potential Information System, which allows users to access information about tourism objects, facilities, activities, and location maps of Kota Pari Village easily and quickly. It is expected that the implementation of this system will improve the promotion and tourism attractiveness of Kota Pari Village, as well as facilitate the growth of the tourism sector in the area.
Â
Keywords: Information System; Waterfall; Tourism potential; Kota Pari; Web;
Abstrak: Penelitian ini bertujuan untuk merancang dan membangun sebuah Sistem Informasi Potensi Wisata Desa Kota Pari, yang berlokasi di Kecamatan Pantai Cermin, Kabupaten Serdang Bedagai, dengan pendekatan Waterfall Method. Masalah yang dihadapi adalah kurangnya aksesibilitas informasi potensi wisata Desa Kota Pari secara online, yang menghambat promosi dan pengembangan potensi wisata lokal. Tujuan penelitian ini adalah untuk mengatasi kendala tersebut dengan merancang dan mengembangkan sebuah platform berbasis web yang dapat memberikan informasi yang komprehensif tentang potensi wisata Desa Kota Pari kepada masyarakat umum dan calon wisatawan. Metode penelitian yang digunakan adalah Waterfall Method, yang terdiri dari lima tahap utama: analisis kebutuhan, perancangan sistem, implementasi, pengujian, dan pemeliharaan. Tahap analisis kebutuhan melibatkan identifikasi kebutuhan pengguna, fitur-fitur yang dibutuhkan, dan struktur informasi yang akan disajikan dalam sistem. Selanjutnya, perancangan sistem dilakukan untuk merancang antarmuka pengguna yang intuitif dan sistematis, serta arsitektur sistem yang kokoh dan scalable. Hasil penelitian ini adalah sebuah Sistem Informasi Potensi Wisata Desa Kota Pari yang berbasis web, yang memungkinkan pengguna untuk mengakses informasi tentang objek wisata, fasilitas, aktivitas, dan peta lokasi Desa Kota Pari secara mudah dan cepat. Diharapkan bahwa implementasi sistem ini akan meningkatkan promosi dan daya tarik wisata Desa Kota Pari, serta memfasilitasi pertumbuhan sektor pariwisata di wilayah tersebut.
Â
Kata kunci: Sistem Informasi; Waterfall; Potensi wisata; Kota Pari; Web;
Â
Abstract:Abstract: SMKS 1 Pembangunan of Bengkulu City is one of the Private Vocational High Schools in Bengkulu City, Bengkulu Province. In the process of managing student administrative data at school, especially the administration…
tion of tuition payments, it uses an office application package, namely Microsoft Excel. The administration system at SMKS 1 Pembangunan Bengkulu City using Two Tier Architecture can simplify the process of managing administrative data at school, especially the payment of tuition fees and student development fees, can provide information on which students have not paid tuition fees and student development fees, and can facilitate the school in giving warnings to students in the form of letters to make payments. Two Tier architecture is built to allow the administration system at SMKS 1 Pembangunan to be accessed by more than 1 laptop/ client on the same network. Based on the tests that have been carried out, it is found that the administration system at SMKS 1 Pembangunan Bengkulu City using two tier architectures has run well and as expected and the application can facilitate the process of managing administrative data in schools, especially payment of tuition fees and student development fees.
Â
Keywords: administration system, smks 1 pembangunan bengkulu city, two-tier
               architecture
Abstrak: SMKS 1 Pembangunan Kota Bengkulu merupakan salah satu Sekolah Menengah Kejuruan Swasta yang terdapat di Kota Bengkulu Provinsi Bengkulu. Dalam proses pengelolaan data administrasi siswa di sekolah khususnya administrasi pembayaran uang sekolah sudah menggunakan paket aplikasi office yaitu Microsoft Excel. Sistem administrasi di SMKS 1 Pembangunan Kota Bengkulu menggunakan Arsitektur Two Tier dapat mempermudah proses pengelolaan data administrasi di sekolah khususnya pembayaran uang SPP dan uang pembangunan siswa, dapat memberikan informasi siapa saja siswa yang belum membayar uang SPP dan uang pembangunan siswa, serta dapat mempermudah pihak sekolah dalam memberikan peringatan ke siswa berupa surat untuk melakukan pembayaran. Arsitektur Two Tier dibangun guna memungkinkan sistem administrasi di SMKS 1 Pembangunan dapat diakses lebih dari 1 laptop/client yang berada pada jaringan yang sama. Berdasarkan pengujian yang telah dilakukan didapatkan hasil bahwa sistem administrasi di SMKS 1 Pembangunan Kota Bengkulu menggunakan arsitektur two tier sudah berjalan dengan baik dan sesuai dengan harapan dan aplikasi dapat mempermudah proses pengelolaan data administrasi di sekolah khususnya pembayaran uang SPP dan uang pembangunan siswa
Â
Kata kunci: sistem administrasi, smks 1 pembangunan kota bengkulu, arsitektur two-tier
Â
Abstract:Abstract: Industrial waste has had a negative impact on the environment and human health. Industrial waste pollution can occur due to improperly managed waste disposal. Managing industrial waste can be one way to reduce…
the impact of environmental pollution. Checking industrial waste can be a solution for implementing oversight of waste management, but it will be difficult to implement if done in a large industrial area. Waste classification based on organic and non-organic waste categories. Convolutional Neural Networks (CNNs) and MobileNet can be applied to automatically detect organic and non-organic industrial waste systems. Researchers have conducted a comparative study between the Convolutional Neural Network (CNN) and MobileNet models, which is useful for obtaining the best model. The results of the analysis concluded that MobileNet has better accuracy, precision, and recall compared to the CNN model. The accuracy, precision, and recall generated by MobileNet are 99.5%, 99.4%, and 100%. Therefore, MobileNet is very suitable for implementation in an automatic industrial waste detection system in real-time applications.  Â
Keyword: computer vision; Â convolutional neural network (CNN); deep learning; industrial waste; mobilenet.
Â
 Abstrak: Limbah industri telah mengakibatkan dampak buruk bagi lingkungan dan kesehatan manusia. Pencemaran limbah industri dapat terjadi akibat pembuangan limbah yang tidak terkelola dengan baik. Pengelolaan limbah industri dapat menjadi salah satu cara untuk mengurangi dampak pencemaran lingkungan. Pengecekan limbah industri dapat menjadi solusi untuk menerapkan pengawasan terhadap pengelolaan limbah, namun akan sulit diterapkan jika dilakukan pada area industri yang luas. Klasifikasi limbah berdasarkan kategori limbah organik dan limbah non organik. Convolutional Neural Network (CNN) dan MobileNet dapat diterapkan untuk sistem pendeteksi limbah industri organik dan non organik secara otomatis. Peneliti telah melakukan studi komparatif antara model Convolutional Neural Network (CNN) dan MobileNet yang berguna untuk memperoleh model terbaik. Hasil analisa yang telah dilakukan menyimpulkan bahwasanya MobileNet mempunyai akurasi, precision dan recall yang lebih baik jika dibandingkan dengan model CNN. Akurasi, precision dan recall yang dihasilkan oleh MobileNet sebesar 99,5% 99,4% dan 100%. Oleh karena itu, MobileNet sangat cocok untuk diterapkan pada sistem deteksi limbah industri secara otomatis pada aplikasi real-time.
Kata kunci: computer vision; convolutional neural network (CNN); limbah industri; mobilenet; pembelajaran mendalam.
Abstract:ANNs have the ability to learn from data and recognize unstructured patterns. In face detection, ANNs can be used to recognize faces from images or videos. However, selecting the right ANN method is crucial for achieving…
optimal face detection performance. The results of this study are the highest classification accuracy value of the backpropagation artificial neural network system in recognizing student facial images with a comparison of the Learning Vector Quantization method is 96.25% (detection error = 0) with a classification architecture of the test data comparison - training data 70: 30, 20,000 iterations, calculation error tolerance 0.00001 and the number of hidden layer neurons = 5 while the lowest classification accuracy value of the backpropagation artificial neural network system in recognizing student facial images based on LVQ features is 85.42% (detection error = 34) with a classification architecture of the test data comparison - training data 70: 30, 10,000 iterations, calculation error tolerance 0.01 and the number of hidden layer neurons = 15
Abstract:The increasing volume of patient visits in primary healthcare facilities (such as community health centers and clinics) demands efficient resource management and scheduling systems. The inability to predict patient arrival…
al patterns often leads to long queues and suboptimal allocation of medical personnel. To overcome these issues, this study proposes the development of an intelligent framework based on Stacking Ensemble Learning to accurately classify and predict patient revisit frequency patterns. The proposed architecture integrates three heterogeneous base classification models (base learners), namely Logistic Regression (LR), Support Vector Machine (SVM) with non-linear Radial Basis Function (RBF) kernel projection, and Random Forest (RF). The probability predictions from these three base models are then combined into a secondary Logistic Regression based meta-learner to optimize the final decision and reduce the predictive bias of single models. Experiments were conducted using a dataset sourced from actual primary healthcare medical records, totaling 499 data entries. Given the highly imbalanced distribution of demographic data, the preprocessing stages were comprehensively designed, encompassing numerical scale feature standardization and the application of the SMOTE (Synthetic Minority Oversampling Technique) class balancing algorithm. Model testing was performed using a 5-fold stratified cross-validation scheme to ensure the robustness of the model's generalization. Comprehensive evaluation results proved that the Stacking Ensemble architecture achieved peak performance with an Accuracy of 88.4%, Precision of 85%, Recall of 90%, and an F1-Score of 0.88. Furthermore, curve analysis revealed an Area Under the Receiver Operating Characteristic (AUC-ROC) score of 0.961 and a Precision-Recall AUC of 0.95, consistently outperforming the capabilities of each individual baseline model. These findings confirm that combining hybrid machine learning models can produce highly stable and reliable predictions while minimizing false negative errors. This architecture holds massive potential for practical implementation as the foundation of a decision support system in managing operational services within primary healthcare facilities.
Abstract:The Level 2 Working at Height (TKBT) training conducted by PT Batamindo Investment Cakrawala produced 22 certified employees across four divisions. However, post-training recommendations from the HRD unit identified the…
absence of a periodic monitoring mechanism for certificate validity periods and personal protective equipment usage, while all record keeping remained paper-based and spreadsheet-driven. This condition creates a compliance risk against Minister of Manpower Regulation Number 9 of 2016, as expired certificates may go undetected before employees are assigned to work at height. This community service program aims to strengthen the partner's occupational safety competency certification governance through the design, implementation, and mentoring of a web-based information system. The implementation method consists of six stages: situation analysis, requirements analysis, system design, construction, socialisation and training, and operational mentoring. The system was developed using a three-tier architecture and comprises four core modules: certificate record management, automated validity notification, divisional recapitulation dashboard, and digital document archiving. Program effectiveness was measured using a pre-test and post-test design with a 20-item instrument covering four knowledge domains, analysed using normalized gain. Functional testing was conducted using the black box method, while user acceptance was measured using the System Usability Scale. The results show that participants' average knowledge score increased from 51.4 in the pre-test to 86.4 in the post-test, with a normalized gain of 0.72 categorised as high. Black box testing achieved a 90 percent success rate and the System Usability Scale score reached 82.5, indicating good user acceptance.