Jurnal ICT: Information Communication & Technology

Analisis Pemanfaatan Teknologi Informasi & Digital Bisnis Dalam Usaha Mikro Kecil dan Menengah (UMKM) di Wilayah Kerja BPSDMP Kominfo Bandung

2026-01-01T10:34:36+00:00

Evaluating the benefits of social media, digital wallets, marketplaces, and the Government's efforts in providing digital training to MSMEs for product marketing can be conducted through observation, interviews, and documentation. The purpose of this research is to analyze the benefits of Information Technology and Digital Business for MSMEs in the working area of BPSDMP Kominfo Bandung. The qualitative descriptive research method interprets the results using Data Triangulation. The research design begins with a literature review, followed by the development of research instruments. Subsequently, interviews are conducted and analyzed to derive conclusions. The research results prove a positive impact on MSME performance in terms of marketing effectiveness, operational efficiency, and customer communication.

Optimalisasi Model Logistic Regression untuk Prediksi Diabetes Menggunakan Seleksi Fitur Berbasis Korelasi

2026-01-01T10:45:35+00:00

Diabetes Mellitus is a pressing global health challenge, making early detection a key component of effective intervention. Machine learning has shown great potential in predicting diabetes risk. Among various models, Logistic Regression (LR) is often favored in a medical context due to its high interpretability, although its accuracy frequently lags behind more complex black-box models. LR performance is known to be highly sensitive to the quality and relevance of input features. This study aims to quantitatively evaluate the impact of a strict correlation-based feature selection strategy on the accuracy of the Logistic Regression model. Using the "Diabetes Health Indicators" dataset (N=100,000), this study compares two scenarios: (1) a baseline LR model using all features (All Input) and (2) an optimized LR model using only a subset of features (including engineered features) that have a high absolute correlation with diabetes diagnosis (Correlated Input). The results demonstrate a significant performance improvement. The All Input baseline model achieved an accuracy of 80.45%, while the Correlated Input model achieved an accuracy of 85.67%. This +5.22% absolute increase demonstrates that correlation-based feature selection effectively eliminates noise from irrelevant features, thus drastically improving the predictive power of the LR model. This study concludes that an optimized Logistic Regression with feature selection offers a strong balance between improved accuracy and the interpretability essential for clinical applications.

Sistem Cerdas Untuk Meningkatkan Prestasi Siswa Dengan Analisis Rapor Menggunakan Algoritma K-Means Clustering Berbasis Web

2026-01-04T04:00:59+00:00

SMA Negeri 1 Aek Songsongan faces problems in managing and analyzing student academic data, where historical report card data has not been optimally utilized to support appropriate educational decision-making. This study aims to develop a web-based intelligent system using the K-Means Clustering algorithm to automatically analyze patterns of student academic achievement and generate targeted learning recommendations. The research method uses a Mixed Method approach with Knowledge Discovery in Databases stages, including data collection, preprocessing, clustering with K-Means, evaluation using the Davies-Bouldin Index, and provision of intelligent system recommendations. The research data consisted of 1,384 student report card scores from three academic years, which after preprocessing resulted in 1,075 valid data with 8 subject attributes. The clustering results identified three groups of students with a Davies-Bouldin Index score of 0.9678, indicating excellent separation quality. Cluster 0 contained 317 students (29.5%) with high achievement, Cluster 1 contained 706 students (65.7%) with moderate to good performance, and Cluster 2 included 52 students (4.8%) with uneven score patterns. The system generates specific recommendations for each group, ranging from acceleration programs, regular tutoring, to intensive remedial programs, thereby helping schools design more effective and targeted learning strategies.

Fire Detection Berbasis Computer Vision Menggunakan YOLOv8 Secara Real-Time

2026-01-04T04:30:58+00:00

This study presents the development of a fire detection system using image processing techniques based on the YOLOv8 object detection algorithm to achieve fast, accurate, and real-time performance. A dataset of fire images with various visual characteristics was preprocessed, converted into YOLO annotation format, and used to train the model for 30 epochs. Evaluation results demonstrate that the YOLOv8 model performs effectively, achieving an mAP50 of 0.646, a precision of 0.889, and an inference speed of 282.5 ms per frame. The system is integrated with OpenCV to process webcam input and display bounding boxes and confidence scores in real time. The implementation confirms that YOLOv8 is a reliable solution for early fire detection, offering faster and more adaptive responses compared to conventional sensor-based methods. This approach can be applied to modern safety monitoring systems to enhance fire prevention efforts.

Analisis Penerapan Metode Moora dalam Seleksi Penerimaan Beasiswa Mahasiswa

2026-01-08T07:44:51+00:00

Scholarship acceptance is an important instrument in supporting the success of higher education, both to motivate outstanding students and to help those who are less fortunate. However, the selection process is often constrained by the objectivity, transparency, and complexity of decision-making because it involves various criteria. This research offers a solution by applying the Multi-Objective Optimization based on Ratio Analysis (MOORA) method, which is able to process multicriteria data by distinguishing benefit and cost criteria so as to produce an objective ranking. The purpose of this study is to analyze the application of the MOORA method in the selection of student scholarship admissions and assess its effectiveness in supporting decision-making. The study used five criteria, namely GPA, parental income, achievement, number of family dependents, and organizational activeness. The calculations are done using the Python programming language. The results of the study show that Rina Amelia ranks first with the highest MOORA score. These findings prove that the MOORA method is effective, transparent, and can be an alternative solution for universities in the scholarship selection process.

Sistem Informasi Bank Sampah Berbasis Web Untuk Meningkatkan Pengelolaan Sampah di Kelurahan Padasuka

2026-01-08T01:00:16+00:00

Abstrak- Perkembangan teknologi informasi mendorong transformasi digital di berbagai sektor, termasuk pengelolaan sampah melalui bank sampah. Di Kelurahan Padigital di berbagai sektor, termasuk pengelolaan sampah melalui bank sampah. Di Kelurahan Padasuka, proses pengelolaan masih dilakukan secara manual menggunakan pencatatan tertulis, sehingga menimbulkan masalah ketidakakuratan data, kesulitan monitoring, dan rendahnya transparansi bagi nasabah. Penelitian ini bertujuan merancang dan mengembangkan sistem informasi bank sampah berbasis web untuk meningkatkan akurasi operasional dan partisipasi masyarakat. Metode pengembangan yang digunakan adalah prototyping, yang memungkinkan keterlibatan pengguna secara langsung dalam proses evaluasi dan penyempurnaan sistem. Fitur utama sistem mencakup manajemen data nasabah, pencatatan transaksi, penjadwalan dan pengajuan penjemputan, serta pelaporan digital. Pengujian dilakukan dengan metode Black Box terhadap tiga peran pengguna, yaitu Super Admin (petugas kelurahan), Admin RW, dan Nasabah. Hasil pengujian menunjukkan seluruh fungsi sistem berjalan sesuai kebutuhan pengguna tanpa kendala berarti. Dengan demikian, sistem informasi ini dapat meningkatkan efisiensi operasional, memperkuat transparansi, serta mendukung partisipasi masyarakat dalam pengelolaan sampah anorganik.

Analisis Perbandingan Algoritma BM25 dan TF-IDF untuk Temu Kembali Metadata Jurnal Indonesia pada Temujurnal.com

2026-01-08T13:44:13+00:00

Peningkatan volume publikasi ilmiah di Indonesia melalui sistem jurnal elektronik menuntut adanya mekanisme pencarian yang efisien bagi para peneliti. Temujurnal.com merupakan platform agregator yang mengelola kumpulan jurnal nasional, Temujurnal memiliki fitur pencarian dan kategori mencakup variabel tekstual seperti nama, singkatan, penerbit, dan deskripsi, serta filter seperti peringkat Sinta, periode terbit dan biaya publikasi. Penelitian ini bertujuan untuk melakukan analisis perbandingan performa antara algoritma Term Frequency-Inverse Document Frequency (TF-IDF) dan Best Matching 25 (BM25) dalam sistem temu kembali informasi jurnal Indonesia. Metodologi yang digunakan mencakup tahap pra-pemrosesan teks menggunakan algoritma Stemming dan penerapan logika Hybrid Retrieval. Pengujian dilakukan terhadap 100 metadata jurnal dengan 20 kueri uji yang diukur melalui metrik Precision, Recall, F1-Score, dan Mean Average Precision (MAP). Hasil penelitian menunjukkan bahwa algoritma BM25 mengungguli TF-IDF dengan perolehan nilai MAP sebesar 0,74 berbanding 0,59. BM25 mencapai nilai Precision sebesar 0,78, menunjukkan stabilitas yang lebih baik dalam menangani variasi panjang metadata melalui parameter normalisasi b=0,75 dan saturasi k₁=1,2. Penelitian ini merekomendasikan implementasi BM25 pada platform Temujurnal untuk meningkatkan akurasi dan efisiensi penemuan literatur ilmiah nasional.

Implementasi Kombinasi Algoritma Kriptografi Menggunakan Atbash dan Caesar Cipher Pada Nilai Rapot Akhir Siswa MA Berbaur di Wonosobo

2025-12-22T04:18:00+00:00

The development of information technology demands an improvement in data security systems, especially in the world of education which stores a lot of sensitive information such as student report card grades. This study aims to design and implement a cryptographic system combining the Caesar Cipher and Atbash Cipher algorithms to improve protection of students' final report card data at Madrasah Aliyah (MA) Berbaur Wonosobo. The Caesar Cipher method is used to encrypt letter-based data through a fixed character shift, while the Atbash Cipher is applied to numeric data with digit substitution based on the vertical position in the number sequence. The combination of these two methods produces a more complex and secure layered encryption system. This study uses a software engineering approach with implementation methods and system testing. The implementation results show that the combination of algorithms is able to maintain the integrity and confidentiality of student report card data effectively, and can be used as an applicable and efficient academic data security solution.

Implementasi Sistem Informasi Pengisian Rencana Studi Terintegrasi Data Nilai Mahasiswa Di Politeknik Piksi Ganesha

2025-12-23T01:18:06+00:00

The development of information technology has encouraged higher education institutions to provide academic services that are effective, transparent, and integrated. One academic process that is still largely carried out manually is the submission and approval of course selections, which often leads to delays, recording errors, and a lack of integrated information between students, academic advisors (PA), and the academic administration. This study aims to develop a Study Data Form feature based on the Grade Information System as a digital solution to automate the course submission and approval process within a centralized platform. The research uses a descriptive qualitative method through observations and interviews as the basis for needs analysis. The development method employed is the Waterfall model, which consists of analysis, design, implementation, testing, and maintenance stages. The system is designed using Flowcharts, Data Flow Diagrams (DFD), and Entity Relationship Diagrams (ERD), and implemented using the Laravel 12 framework based on the Model-View-Controller architecture. Black Box Testing is used to ensure that the system functions according to user needs. The results show that the system is capable of facilitating digital course submissions, automatically validating prerequisite grades, accelerating the approval process by academic advisors and academic administration, and improving administrative efficiency, data accuracy, and process transparency compared to previous manual methods.

Pengujian Fungsionalitas Dashboard Admin Nemo.Ai Menggunakan Black Box Testing Equivalence Partitioning

2025-12-29T21:28:34+00:00

Penelitian ini bertujuan untuk menguji fungsionalitas sistem informasi dashboard manajemen data ikan pada aplikasi Nemo.Ai menggunakan metode Black Box Testing dengan teknik Equivalence Partitioning. Sistem ini dikembangkan untuk membantu pengelola dalam mengelola data ikan dan penyakit ikan secara digital agar prosesnya lebih efisien dan terorganisir. Website terdiri atas beberapa halaman utama, yaitu Dashboard, Ensiklopedia, dan Penyakit, yang masing-masing memiliki fungsi CRUD (Create, Read, Update, Delete) untuk mendukung pengelolaan data secara interaktif. Pengujian dilakukan dengan memverifikasi kesesuaian antara input dan output berdasarkan kelas ekuivalensi tanpa menganalisis kode sumber. Hasil pengujian menunjukkan sebagian besar fungsi berjalan sesuai spesifikasi, meskipun terdapat beberapa ketidaksesuaian pada validasi unggahan gambar dan input numerik. Secara keseluruhan, tingkat keberhasilan pengujian mencapai 77%, menunjukkan bahwa sistem telah berfungsi dengan baik dan layak digunakan, dengan kebutuhan peningkatan pada mekanisme validasi untuk hasil yang lebih optimal.

Strategi Visual Berbasis AISAS untuk Meningkatkan Kesadaran Merek Collagena di Instagram

2026-01-01T10:48:23+00:00

Perkembangan teknologi digital telah merevolusi komunikasi pemasaran dan menjadikan media sosial khususnya Instagram sebagai saluran utama bagi merek untuk membangun identitas menjangkau konsumen serta memengaruhi perilaku pembelian melalui pendekatan visual dan interaktif. Collagena hadir sebagai produk susu steril dengan kandungan 1000 mg kolagen yang diposisikan sebagai solusi gaya hidup sehat sekaligus perawatan diri. Tantangan komunikasi merek masih terlihat dalam bentuk ketidakkonsistenan visual bias representasi gender serta lemahnya integrasi antara kampanye offline dan konten digital. Kondisi ini menyebabkan kesadaran merek belum terbentuk secara optimal di benak konsumen digital. Penelitian ini bertujuan merancang strategi komunikasi pemasaran digital untuk meningkatkan kesadaran merek Collagena melalui Instagram dengan menggunakan model AISAS yaitu Attention Interest Search Action Share dan kerangka SOSTAC yaitu Situation Objective Strategy Tactics Action Control. Metode penelitian menggabungkan observasi konten dengan wawancara semi terstruktur terhadap pengikut akun resmi Collagena Id. Hasil analisis menghasilkan rancangan dummy konten yang menekankan konsistensi visual narasi edukatif dan representasi inklusif. Temuan menunjukkan bahwa strategi komunikasi terstruktur dan berbasis data mampu memperkuat identitas merek meningkatkan keterlibatan audiens serta membangun koneksi emosional yang lebih mendalam. Rekomendasi praktis meliputi penerapan siklus editorial tematik kolaborasi dengan micro influencer serta pengembangan sistem pemantauan berbasis data untuk mendukung optimasi berkelanjutan.