Jurnal Teknoinfo https://publikasi.teknokrat.ac.id/index.php/teknoinfo <p>Jurnal Teknoinfo is a peer-reviewed scientific Open Access journal that published by Universitas Teknokrat Indonesia. This Journal is built with the aim to expand and create innovation concepts, theories, paradigms, perspectives and methodologies in the sciences of Informatics Engineering. The articles published in this journal can be the result of conceptual thinking, ideas, innovation, creativity, best practices, book review and research results that have been done. Jurnal Teknoinfo publishes scientific articles twice a year in January and July. The Jurnal Teknoinfo already has P-ISSN: 1693-0010 and E-ISSN: 2615-224X .<br><br>Jurnal Teknoinfo is Accredited “Rank 4”(Peringkat 4) as a scientific journal under the decree of the Ministry of Research, Technology and Higher Education of the Republic of Indonesia, Decree No 0173/C3/DT.05.00/2025, March 21th 2025 .</p> <p><img src="/public/site/images/setiawansyah/teknoinfo2.jpg"></p> <p>The study of other sciences that examine topics related to Informatics Engineering is not limited to: Mobile Application, Technopreneur, Cloud Computing, Customer Relationship Management, Database Management, Web Application, Semantic, E-Learning, Game Development, Multimedia Application, Industrial Engineering, Cluster Computing, Intelligent System, Data Mining, Expert System, Software Engineering, Operating System, Data Center, Bioinformatics, Network and Security, Computer Network, Human Computer Interaction, Computer Vision, Decision Support System, Neural Network, Paralel Processing, Animation, Computer Graphic, Information Security.</p> <p><br>The submitted paper will be reviewed by reviewers. Review process employs Double-Blind Peer Review. In this system authors do not know who the reviewer is, and the reviewers do not know whose work they are evaluating.<br>Before submission, please make sure that your paper is prepared using the journal Paper Template.</p> en-US setiawansyah@teknokrat.ac.id (Setiawansyah, M.Kom.) Thu, 10 Jul 2025 07:41:26 +0700 OJS 3.1.2.4 http://blogs.law.harvard.edu/tech/rss 60 NEXT-GEN LOGISTIC MANAGEMENT: RANCANG BANGUN SISTEM DENGAN LARAVEL DAN MYSQL https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/60 <p>In the increasingly complex and competitive logistics industry, optimizing freight management is crucial for enhancing operational efficiency. This study develops a web-based freight management system utilizing the Laravel framework and MySQL database, aiming to improve operational effectiveness at PT. Tunas Mendayung Group. The system development follows the Waterfall methodology, encompassing requirements analysis, system design, implementation, and testing phases. System evaluation was conducted through black-box testing, achieving an average success rate of 98.6%, with authentication accuracy of 100% for administrators and 98% for users, CRUD operations at 95%, shipment status validation at 100%, and pricing evaluation accuracy at 97%. The system demonstrated an average response time of 2 seconds and full compatibility across major web browsers. The primary contribution of this research lies in the development of an integrated freight management system that not only incorporates real-time shipment tracking and robust authentication mechanisms but also optimizes data processing efficiency through a modular architecture that is adaptable to logistics industry demands. Unlike previous studies that primarily focused on data optimization without considering interactive user features, this system offers a comprehensive solution that enhances operational transparency and the accuracy of shipment information. Consequently, the proposed system has the potential to serve as a model for logistics companies seeking to adopt web-based technologies to improve competitiveness and overall industry efficiency.</p> Mega Wahyu Rhamadani, Abdullah Ardi Copyright (c) https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/60 Thu, 10 Jul 2025 00:00:00 +0700 PENERAPAN METODE SIMPLE ADDITIVE WEIGHTING UNTUK PEMILIHAN KEAKTIFAN DIVISI DALAM LAPORAN PENGAWASAN BIDANG https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/39 <p>Bogor Class IA Religious Court is a government institution responsible for carrying out the mandate of the law based on religious law. Currently the supervision process is still carried out manually, so it takes a long time in terms of supervision and is not monitored in the activeness of each division. Therefore, it is recommended to develop a decision support system for division activeness in field supervision reports by supervisory judges. This system is designed web-based using the Simple Additive Weighting (SAW) method to evaluate division performance scores based on criteria, namely processing time, follow-up, evidence, number of completed tasks and final results. Supervision data is taken from the fourth quarter of 2023. The evaluation results show that the Judicial Administration division is ranked first with the highest score of 0.934, then for rank two is occupied by General Administration with a score of 0.895, for rank three is occupied by Trial Administration with a score of 0.741 and for rank four is occupied by two divisions namely Case Administration and General Services with the same score of 0.247. After that, a system accuracy test was carried out on the SAW algorithm using the Mean Absolute Percentage Error (MAPE) method, which resulted in an average prediction error value of 19.18%, indicating that the ability of the forecasting model was classified as good. The developed system is expected to improve the efficiency and effectiveness of the supervision process at the Bogor Class IA Religious Court.</p> Intan Gya Agisti, Lita Karlitasari, Dini Suhartini Copyright (c) 2025 Intan Gya Agisti, Lita Karlitasari, Dini Suhartini https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/39 Thu, 10 Jul 2025 00:00:00 +0700 MODEL REFERENSI OPEN SYSTEMS INTERCONNECTION (OSI) DAN TRANSMISSION CONTROL PROTOCOL/INTERNET PROTOCOL (TCP/IP) DALAM TANTANGAN ERA INDUSTRI https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/101 <p>Tujuan penelitian ini adalah mengeksplorasi peran serta adaptasi yang diperlukan oleh Model Referensi OSI dan TCP/IP dalam menghadapi tantangan era Industri 4.0. Penelitian ini menggunakan pendekatan <em>Systematic Literature Review (SLR) </em>untuk memberikan gambaran yang komprehensif tentang analisis literatur dalam konteks Industri 4.0. Sumber data dari jurnal ilmiah, buku referensi, dan publikasi terkait lainnya akan menjadi sumber informasi utama. Data sekunder juga dapat digunakan untuk mendukung temuan dan argumen yang dihasilkan dalam penelitian. Hasil penelitian bahwa model referensi OSI dan TCP/IP tetap relevan dalam era industri 4.0. OSI membantu dalam memahami fungsi jaringan secara rinci dengan tujuh lapisannya, sedangkan TCP/IP fokus pada konektivitas end-to-end dengan empat lapisan. Penerapan protokol TCP/IP memungkinkan komunikasi yang mulus di seluruh dunia sesuai dengan standar ISO dan OSI. Temuan penelitian ini memberikan pemahaman yang lebih baik tentang kedua model dan relevansinya dalam era industri 4.0, memberikan pandangan baru untuk pengembangan jaringan komputer yang efisien dan aman di masa depan. Dengan pemahaman yang mendalam tentang keduanya, organisasi dapat mengembangkan infrastruktur jaringan yang kokoh sesuai dengan perkembangan teknologi saat ini. Model OSI terdiri dari tujuh lapisan, masing-masing memiliki peran khusus dalam proses komunikasi jaringan. Mulai dari lapisan fisik yang mengatur transmisi bit-data hingga lapisan aplikasi yang menyediakan antarmuka untuk aplikasi pengguna, model ini membantu dalam memahami konsep dasar komunikasi jaringan dan membagi fungsi jaringan menjadi bagian yang lebih terkelola. Sementara itu, model TCP/IP, meskipun hanya terdiri dari empat lapisan, efektif dalam mengelola konektivitas dari ujung ke ujung dan pengiriman data antara perangkat dalam jaringan. Protokol ini juga mengikuti standar ISO dan OSI, memungkinkan komunikasi yang lancar antara berbagai platform di seluruh dunia. Di era di mana teknologi seperti Internet of Things (IoT), komputasi awan, dan big data semakin penting, pemahaman yang kuat tentang kedua model ini sangatlah vital. Mereka membantu dalam merancang, menerapkan, dan mengelola jaringan yang efisien dan aman, memfasilitasi komunikasi yang lancar antara berbagai perangkat dan sistem dalam lingkungan yang semakin terhubung. Dengan menggunakan model-model ini sebagai panduan, organisasi dapat mengembangkan infrastruktur jaringan yang tangguh yang dapat beradaptasi dengan perubahan teknologi yang terjadi di era industri 4.0.</p> Tri Wahyudi Copyright (c) 2025 Tri Wahyudi https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/101 Thu, 10 Jul 2025 00:00:00 +0700 ANALISIS PENERIMAAN MARKET PLACE FACEBOOK MENGGUNAKAN TECHNOLOGY ACCEPTANCE MODEL (TAM) https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/135 <p>Dengan banyaknya alternatif marketplace online yang lebih terstruktur dan memiliki sistem perlindungan konsumen yang lebih ketat, seperti Shopee, Tokopedia, dan Bukalapak dan lain-lain yang menjadi saingan <em>Marketplace Facebook</em>. Selain itu Fitur <em>Market Place</em> di <em>Facebook</em> di luncurkan sejak tahun 2016 namun belum di ketahui tingkat penerimaannya. Preferensi penjual dan pembeli rata-rata penjual memilih menggunakan group <em>Facebook</em> atau media social lain untuk berjualan di bandingkan dengan <em>Market place</em> <em>Facebook</em>, dari segi kesadaran atau pemahaman juga mengenai fitur dan manfaat fitur <em>Marke tplace Facebook</em> masih kurang. Penelitian ini mengadopsi pendekatan eksplanatori dengan tujuan menjelaskan hubungan sebab-akibat antara variabel penelitian serta menguji hipotesis yang telah dirumuskan untuk memahami fenomena yang diteliti, penelitian ini menggunakan <em>Technology Acceptance Model (TAM</em>) sebagai kerangka konseptual utama. Model ini membantu dalam mengidentifikasi variabel penelitian yang berkaitan dengan konsep-konsep utama dalam <em>Technology Acceptance Model (TAM),</em> seperti Persepsi Kemanfaatan (<em>Perceived Usefulness</em>), Persepsi Kemudahan Penggunaan (<em>Perceived Ease of Use</em>), Penggunaan Aktual Sistem (<em>Actual System Use),</em> serta Sikap terhadap Penggunaan (<em>Attitude Toward Using</em>). Metode analisis PLS 3 dipilih karena fleksibilitasnya dan dapat menangani banyak variabel sekaligus tanpa memerlukan asumsi yang kompleks, serta mampu mengatasi masalah multikolinieritas antar variabel. Disimpulkan bahwa penggunaan dan manfaat yang dipersepsikan <em>Market place</em> <em>Facebook </em>secara signifikan mempengaruhi sikap dan niat pengguna dalam menggunakan platform tersebut. Meskipun sebagian pengguna merasa cukup memahami cara penggunaannya, masih ada beberapa faktor yang menyebabkan ketidakpuasan dan sikap penolakan. Oleh karena itu, diperlukan upaya yang lebih efektif dalam mensosialisasikan fitur-fitur dan manfaat <em>Marketplace Facebook</em> serta meningkatkan&nbsp; aspek-aspek yang masih kurang memuaskan, seperti frekuensi penggunaan yang belum optimal dan kekurangan fitur dalam proses jual-beli</p> <p>Keyword : Analisis, Penerimaan , Marketplace , Facebook , TAM</p> <p><br><strong><br></strong></p> Yuliana Sangka, Jennis Tanopa, Engelberth Worabai Copyright (c) 2025 Yuliana Sangka, Jennis Tanopa, Engelberth Worabai https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/135 Thu, 10 Jul 2025 00:00:00 +0700 PERANCANGAN VIDEO PROMOSI WISATA RELIGI MAKAM DATU QABUL DENGAN PENDEKATAN CINEMATIC INFOGRAFIS https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/145 <p>Wisata religi Makam Datu Qabul merupakan salah satu destinasi yang memiliki potensi besar untuk dikembangkan, khususnya di Kabupaten Tapin, tepatnya di Desa Baulin, Kecamatan Candi Laras Selatan. Saat ini, masih terdapat keterbatasan dalam strategi promosi yang menyebabkan destinasi ini belum dikenal secara luas oleh masyarakat. Oleh karena itu, diperlukan upaya yang lebih efektif dalam memperkenalkan wisata religi ini agar mampu menarik lebih banyak pengunjung, baik untuk keperluan wisata maupun ziarah.&nbsp;Penelitian ini bertujuan untuk mendukung pengembangan wisata religi Makam Datu Qabul dengan strategi promosi berbasis media digital, khususnya melalui platform media sosial Instagram. Dengan adanya publikasi yang efektif, diharapkan daya tarik wisata religi ini dapat meningkat serta mampu memberikan kontribusi terhadap sektor pariwisata lokal.&nbsp;Dalam penelitian ini, digunakan metode Multimedia Development Life Cycle (MDLC) sebagai pendekatan pengembangan sistem. MDLC terdiri dari enam tahap utama, yaitu: Konsep (Concept), yang melibatkan perencanaan awal untuk menentukan tujuan dan target promosi; Perancangan (Design), yang berfokus pada pembuatan konsep visual dan sketsa awal; Pengumpulan Bahan (Material Collecting), yang mencakup pengambilan data berupa gambar, video, dan informasi relevan mengenai destinasi wisata; Pembuatan (Assembly), yang merupakan tahap produksi dan pengeditan video promosi menggunakan perangkat lunak seperti Adobe Premiere Pro CC dan Adobe Photoshop; Pengujian (Testing), yang bertujuan untuk mengevaluasi kualitas video sebelum dipublikasikan; serta Distribusi (Distribution), yaitu penyebaran video melalui platform Instagram agar dapat menjangkau audiens yang lebih luas.&nbsp;Hasil penelitian menunjukkan bahwa video promosi dengan durasi 5 menit 23 detik dinilai menarik serta informatif dalam menyampaikan keunggulan wisata religi Makam Datu Qabul. Selain itu, penggunaan media sosial sebagai sarana promosi terbukti efektif dalam meningkatkan keterjangkauan informasi bagi masyarakat. Oleh karena itu, strategi pemasaran digital berbasis konten multimedia dapat menjadi salah satu solusi dalam mengembangkan dan memperkenalkan potensi wisata daerah secara lebih luas.</p> Jiki Romadoni, Haji Ahmad Makie, Muhammad Taufik Rahman Copyright (c) 2025 Jiki Romadoni, Haji Ahmad Makie, Muhammad Taufik Rahman https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/145 Thu, 10 Jul 2025 00:00:00 +0700 ANALISIS KLASTERISASI DAFTAR PEMILIH KABUPATEN MANOKWARI MENGGUNAKAN METODE K-MEANS CLUSTERING BERBASIS ELBOW METHOD https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/163 <p>General Elections (Pemilu) are a crucial pillar in Indonesia's democratic system, ensuring public representation in government. As voter data becomes increasingly complex due to population growth and community mobility, electoral data management requires more efficient analytical approaches to support accurate decision-making. Therefore, methods capable of accurately grouping voters based on specific characteristics are needed. This study aims to cluster voter registration data in Manokwari Regency based on age and neighborhood unit (RT) using the K-Means algorithm. A total of 16,871 entries obtained from the General Election Commission of Manokwari Regency were used, but two outliers due to input errors were removed, leaving 16,869 valid entries analyzed using Jupyter Notebook. The Elbow Method was applied to determine the optimal number of clusters by calculating the Sum of Squared Errors (SSE) from K = 2 to K = 9. The most significant drop in SSE occurred from K = 2 to K = 3 and K = 3 to K = 4, with gradual decreases afterward, indicating the elbow point lies between K = 3 and K = 4. Considering data density and segmentation, K = 4 was chosen with an SSE value of 347,575. The K-Means algorithm then clustered the data based on age and RT through random centroid initialization, Euclidean distance calculation, reassignment, and iterative centroid updates until convergence. The results showed four clusters: Cluster_0 with 6,332 young voters aged 17–29 years (RT 0–17), Cluster_1 with 3,478 productive-age voters aged 43–56 years (RT 0–14), Cluster_2 with 1,768 elderly voters aged 57–93 years (RT 0–14), and Cluster_3 with 5,291 voters aged 30–42 years (RT 0–15). The broad RT distribution across clusters indicates diverse voter age groups across the region. These findings can help the Manokwari General Election Commission (KPU) and related institutions in planning effective voter education, outreach, and logistics distribution strategies.</p> Marselinda Rante Uma, Christian Dwi Suhendra, Josua Josen A. Limbong Copyright (c) 2025 Marselinda Rante Uma, Christian Dwi Suhendra, Josua Josen A. Limbong https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/163 Thu, 10 Jul 2025 00:00:00 +0700 ANALISIS PENGARUH THRESHOLD PADA METODE CANNY DAN SOBEL DALAM DETEKSI TEPI CITRA CABAI https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/162 <p><strong>Abstract</strong></p> <p><em>The utilization of digital image processing technology in agriculture has developed rapidly, particularly for identifying and classifying horticultural commodities such as chili peppers. Chili peppers possess diverse visual characteristics, including color changes based on ripeness levels and irregular shapes. Misidentification can lead to losses during harvest, making accurate automatic detection essential. One of the key approaches in image processing is edge detection, which functions to extract object contours from the image background. However, the results of this process are highly influenced by the threshold parameters used. Inappropriate thresholds can result in the loss of important details or the appearance of disruptive noise, thereby reducing detection accuracy. Therefore, this study was conducted to analyze the effect of threshold parameter variations on the performance of two commonly used edge detection methods: Canny and Sobel. The edge detection process was carried out by applying the Canny and Sobel methods using the Kaggle Notebook platform. Canny edge detection involves Gaussian blur to reduce noise, calculation of intensity gradients, and the use of two threshold values. Meanwhile, Sobel calculates gradients along the X and Y axes to highlight pixel intensity changes.</em></p> <p><em>The data used in this study consists of 11 images of various types of chili peppers, captured using a smartphone camera, then resized and converted to grayscale to simplify color information. The results from both methods were analyzed visually and quantitatively using metrics such as the number of edge pixels, PSNR (Peak Signal-to-Noise Ratio), and SSIM (Structural Similarity Index). The results of the study show that the Canny method is capable of producing clearer edges with less noise compared to Sobel, especially in images with low lighting. However, the Sobel method excels in processing speed and implementation simplicity. These findings highlight the importance of selecting the appropriate threshold values to enhance edge detection accuracy and efficiency. Consequently, the results of this study can serve as a reference in the development of more accurate and reliable automated systems for chili pepper identification and classification based on digital image processing.</em></p> <p>&nbsp;</p> <p><strong>Keyword:</strong> <em>Canny, Chili, Edge Detection Image Processing, Sobel.</em></p> <p>&nbsp;</p> <p><strong>&nbsp;</strong></p> <p><strong>Abstrak</strong></p> <p>Pemanfaatan teknologi pengolahan citra digital dalam bidang pertanian telah berkembang pesat, khususnya untuk mengidentifikasi dan mengklasifikasi komoditas hortikultura seperti cabai. Cabai memiliki ciri visual yang beragam, seperti warna yang berubah sesuai tingkat kematangan dan bentuk yang tidak seragam, jika salah mengidentifikasi maka akan menyebabkan kerugian pada saat panen sehingga deteksi otomatisnya membutuhkan metode yang tepat. Salah satu pendekatan yang penting dalam pengolahan citra adalah deteksi tepi (<em>edge detection</em>), yang berfungsi untuk mengekstraksi kontur objek dari latar belakang gambarnya. Namun, hasil dari proses deteksi ini sangat dipengaruhi oleh parameter <em>threshold</em> yang digunakan. <em>Threshold</em> yang tidak sesuai dapat menyebabkan hilangnya detail penting atau munculnya <em>noise</em> yang mengganggu, sehingga menurunkan akurasi deteksi. Oleh karena itu, penelitian ini dilakukan untuk menganalisis pengaruh variasi parameter <em>threshold</em> terhadap performa dua metode deteksi tepi yang umum digunakan, yaitu <em>Canny</em> dan <em>Sobel</em>. Proses deteksi tepi dilaksanakan dengan menerapkan metode <em>Canny</em> dan <em>Sobel</em> dalam platform <em>Kaggle Notebook</em>. <em>Canny edge</em> <em>detection</em> melibatkan proses <em>Gaussian blur</em> untuk mengurangi noise, perhitungan gradien intensitas, dan penggunaan dua nilai <em>threshold</em>. Sedangkan <em>Sobel</em> melakukan perhitungan gradien pada sumbu X dan Y untuk menyoroti perubahan intensitas piksel. Data yang digunakan dalam penelitian ini berasal dari 11 gambar cabai berbagai jenis yang diambil menggunakan kamera ponsel, kemudian melalui proses <em>resizing</em> dan konversi ke <em>grayscale</em> guna menyederhanakan informasi warna. Hasil dari kedua metode dianalisis baik secara visual maupun kuantitatif menggunakan metrik seperti jumlah piksel tepi, PSNR (<em>Peak Signal-to-Noise Ratio</em>), dan SSIM (<em>Structural Similarity Index</em>). Hasil penelitian menunjukkan bahwa metode <em>Canny</em> mampu menghasilkan tepi yang lebih jelas dan minim <em>noise</em> dibandingkan <em>Sobel</em>, terutama pada gambar dengan pencahayaan rendah. Namun, metode <em>Sobel</em> memiliki keunggulan dalam kecepatan pemrosesan dan kesederhanaan implementasi. Temuan ini menegaskan pentingnya pemilihan nilai <em>threshold</em> yang tepat dalam meningkatkan akurasi dan efisiensi deteksi tepi. Dengan demikian, hasil penelitian ini dapat dijadikan acuan dalam pengembangan sistem otomatisasi identifikasi dan klasifikasi cabai berbasis pengolahan citra digital yang lebih akurat dan andal.&nbsp;</p> <p>&nbsp;</p> <p><strong>Kata Kunci:</strong> pengolahan citra deteksi tepi, Canny, Sobel, Cabai.</p> Sri Rahayu, Ridwansyah, Jajang Jaya Purnama Copyright (c) 2025 Sri Rahayu, Ridwansyah, Jajang Purnama https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/162 Thu, 10 Jul 2025 00:00:00 +0700 OPTIMASI KLASIFIKASI GANGGUAN TIDUR PADA DATASET TIDAK SEIMBANG MENGGUNAKAN SMOTE DAN ALGORITMA MACHINE LEARNING https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/295 <p><em>Sleep disorders are increasingly prevalent health issues that significantly affect individual’s quality of life. Timely detection and accurate classification of these disorders are essential for proper diagnosis and effective clinical intervention. However, a major challenge in classifying sleep disorders lies in the imbalance of data distribution—where majority classes have substantially more data than minority ones. This imbalance often leads to predictive models that favor the dominant class, thereby reducing overall classification accuracy. This study focuses on enhancing sleep disorder classification performance on imbalanced datasets by applying the Synthetic Minority Over-sampling Technique (SMOTE) to balance the data. It also evaluates the effectiveness of various machine learning algorithms in identifying sleep disorders. The algorithms analyzed include Random Forest (RF), Neural Network (NN), Naive Bayes (NB), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Logistic Regression (LR), tested both before and after applying SMOTE. Model performance was assessed using accuracy, precision, recall, and F1-score to ensure a comprehensive evaluation. The findings indicate that SMOTE consistently boosts the performance of all tested models. Among them, the Neural Network combined with SMOTE achieved the highest performance, with an accuracy of 92.00%, precision of 91.88%, recall of 92.00%, and an F1-score of 91.91%. Additionally, the Random Forest model with SMOTE produced the highest F1-score at 93.18%, demonstrating strong performance stability. These results highlight the effectiveness of integrating oversampling techniques like SMOTE with machine learning models to address class imbalance, leading to more accurate and reliable classification outcomes. The study offers valuable insights for developing AI-based medical decision support systems focused on sleep disorder diagnosis.</em></p> Titik Misriati, Riska Aryanti Copyright (c) 2025 Titik Misriati, Riska Aryanti https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/295 Thu, 10 Jul 2025 00:00:00 +0700 REAL TIME OBJECT DETECTION MENGGUNAKAN FAST R-CNN https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/42 <p>Teknologi komputasi cerdas telah menjadi dasar utama dalam berbagai inovasi, termasuk pengembangan sistem deteksi objek. Dalam penelitian ini, dirancang sebuah sistem deteksi objek berbasis algoritma <em>Fast Region-based Convolutional Neural Network</em> (Fast R-CNN). Metode ini dipilih karena kemampuannya yang unggul dalam kecepatan dan akurasi deteksi dibandingkan dengan algoritma sebelumnya. Dengan mengintegrasikan proses ekstraksi fitur dan klasifikasi secara langsung, metode Fast R-CNN mampu menghasilkan deteksi yang lebih efisien. Pengujian dilakukan menggunakan dataset objek dengan variasi pencahayaan, sudut pandang, dan ukuran objek. Hasilnya menunjukkan bahwa metode ini mampu mendeteksi objek dengan tingkat akurasi yang tinggi. Kecepatan pemrosesan yang dimiliki Fast R-CNN menjadikannya cocok untuk pengujian dataset secara real-time dalam aplikasi seperti keamanan, pengawasan, dan sistem otonom. Dengan pendekatan ini, penelitian ini diharapkan dapat memberikan kontribusi nyata dalam pengembangan teknologi deteksi objek yang lebih andal dan efektif di berbagai bidang kehidupan.</p> Salsabila Tsamrotul Qolbi, Fitto Martcellindo, I Wayan Ardika Chandra, Naufal Adli, Ni Putu Dela Puspita, Abdul Haris Copyright (c) 2025 Salsabila Tsamrotul Qolbi, Fitto Martcellindo, I Wayan Ardika Chandra, Naufal Adli, Ni Putu Dela Puspita, Abdul Haris https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/42 Thu, 10 Jul 2025 00:00:00 +0700 SISTEM INFORMASI SERVICE MOBIL BERBASIS WEBSITE MENGGUNAKAN METODE WATERFALL https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/198 <p>The web-based car service information system aims to provide convenience in the process of recording and managing vehicle service online. This system was developed as a solution to the problem of managing service data which is still done conventionally using recording in a ledger resulting in data accumulation and inefficiency as well as unpredictable service customer queues. With this web-based system, customers are given the convenience of accessing service information and booking service schedules without having to visit the workshop directly and officers find it easier to manage service transaction data, check car spare part stock and create reports. The development of this system uses the waterfall method which includes needs analysis, system design, design, implementation and testing. With this system, it is expected to improve the operational efficiency of the workshop for workshop employees and make it easier for customers to access service information.</p> Mely Mailasari, Monikka Nur Winnarto, Annida Purnamawati Copyright (c) 2025 Mely Mailasari, Monikka Nur Winnarto, Annida Purnamawati https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/198 Thu, 10 Jul 2025 00:00:00 +0700 IMPLEMENTASI LINEAR SEQUENTIAL MODEL DALAM PERANCANGAN WEBSITE PEMBUKAAN DEPOSITO https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/212 <p>Bank Perekonomian Rakyat Karya Kurnia Utama menyediakan berbagai produk jasa di bidang perbankan, salah satu produk yang paling banyak diminati oleh nasabah adalah pembukaan deposito karena produk ini dianggap dapat memberikan jaminan keuntungan yang memuaskan bagi nasabah. Pembukaan deposito pada PT Bank Perekonomian Rakyat Karya Kurnia Utama Sebagian telah menggunakan sistem komputerisasi akan tetapi sebagian lainnya masih dilakukan secara manual sehingga data yang ada tidak terintegrasi dengan baik. Penumpukan nasabah saat melakukan pelayanan dikarenakan keterbatasan jumlah karyawan, kesalahan pencatatan dari proses manual yang ada, proses yang cukup lama dikarenakan data yang tidak terkelola dengan baik tentunya menjadi kendala yang harus diatasi. Untuk itu pembuatan sebuah sistem baru berbasis website dapat dijadikan Solusi untuk menyelesaikan permasalahan yang ada. Website ini akan dirancang menggunakan <em>linear sequential model </em>atau yang biasa disebut dengan metode <em>waterfall </em>dengan melakukan beberapa tahapan didalamnya seperti analisis kebutuhan, desain, implementasi, testing dan maintenance<em>. </em>Dengan adanya sistem baru ini maka semua data dapat terintegrasi satu sama lain, penumpukan antrian pun bisa diatasi karena akses kedalam website bisa dilakukan Dimana saja dan kapan saja, kesalahan-kesalahan human error seperti salah pencatatan, pencarian data yang lama, proses pendaftaran yang memakan waktu dan yang lainnya dapat ditekan sedemikian rupa sehingga proses pelaporan atau pencetakan laporan deposito pun dapat berjalan dengan cepat dan kinerja karyawan pun dapat lebih efektif dan efisien. Pada website ini calon deposan dapat melakukan pengajuan pembukaan deposito, mengunggah persyaratan deposito, melihat status ajuan deposito sampai mencetak bukti pembuatan deposito. Sedangkan karyawan bisa melihat pengajuan deposito, melakukan proses verifikasi data, melakukan pembukaan deposito yang terverifikasi, melakukan validasi data dan mencetak laporan deposito.</p> Hidayanti Murtina, Nunung Hidayatun, Susafa’ati Susafa’ati Copyright (c) 2025 Hidayanti Murtina, Nunung Hidayatun, Susafa’ati Susafa’ati https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/212 Thu, 10 Jul 2025 00:00:00 +0700 IMPLEMENTASI DEEP LEARNING UNTUK IDENTIFIKASI UMUR TANAMAN BERDASARKAN CITRA DAUN PADA SMART FARMING https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/191 <p>Technology plays an important role in optimizing agricultural production, one of which is through the application of smart farming. Smart Farming is a paradigm in agriculture that utilizes information and communication technology (ICT). The case study raised in this study is the use of smart farming in determining plant age. Plant age is an important factor in determining the harvest. Plants that are harvested at the right time can produce quality products in optimal quantities. Traditional farmers determine plant age manually. This has challenges, namely the process takes a long time and a lot of energy, especially for large agricultural areas. Plant age must be identified quickly and easily, the results of plant age identification are accurate and consistent and can be applied to large agricultural areas. The urgency of this research is the creation of a deep learning model that is used to detect the optimum plant age with a high accuracy value. The importance of this research lies not only in the development of technology but also in its contribution to the farmer's economy and the progress of the agricultural sector. This study aims to implement deep learning to form a classification model for identifying plant age based on leaf images and to evaluate the classification model to produce high accuracy. The research method used follows a flow consisting of problem understanding, data understanding, data preparation, modeling, and evaluation. The deep learning method used is classification with the application of the Convolutional Neural Network (CNN) VGG architecture algorithm, which has been proven effective in image analysis. The results of this study are Research on age classification models on plant leaf images using the classification method with the CNN algorithm is carried out with the stages of data collection and class division, image resizing, data augmentation, adding keras models, convolution, max pooling, flatten, relu, and with the training of 20 epochs. The results of model formation with the CNN algorithm using VGG16 get higher accuracy than VGG19. The best accuracy value is 78% from the confusion matrix results using VGG19 with a data ratio of 60% training data, 20% validation data, and 20% testing data.</p> Budi Prayitno, Pritasari Palupiningsih, Farhan Muhamad Ikhsan Copyright (c) 2025 Budi Prayitno, Pritasari Palupiningsih, Farhan Muhamad Ikhsan https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/191 Thu, 10 Jul 2025 00:00:00 +0700 DECISION SUPPORT SYSTEM UNTUK PROPERTI PREMIUM: INTEGRASI AHP DAN TOPSIS DALAM MENGANALISIS PROPERTI SINAR MAS GROUP https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/372 <p>Implementation of decision support system (dss) to select the best premium property from sinar mas group in bsd city. the main problem is the complexity of decision making in the premium property segment involving various criteria such as price, location, facilities, land area, and investment potential. the aim of this study is to develop a dss that integrates the analytical hierarchy process (ahp) method to determine criteria weights and the technique for order preference by similarity to ideal solution (topsis) to rank property alternatives based on proximity to the ideal solution. the research methods include criteria identification, data collection, criteria weight calculation using ahp, normalization and preference value calculation using topsis, and result evaluation. the results show that the elyon property type is the best alternative with the highest preference value of 0.74112, followed by adora primes and terravia belova. this study demonstrates the effectiveness of integrating ahp and topsis in providing objective and measurable decision recommendations for premium property purchases. this system is expected to assist prospective buyers, developers, and property consultants in making better decisions and has the potential to be developed into a digital application.</p> Aldo Putra Ramaddan, M. Ramaddan Julianti , Nunung Nurmaesah Copyright (c) 2025 Aldo Putra Ramaddan, M. Ramaddan Julianti , Nunung Nurmaesah https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/372 Thu, 10 Jul 2025 00:00:00 +0700 PERANCANGAN HUMAN RESOURCES INFORMATION SYSTEM BERBASIS WEB MENGGUNAKAN METODE WATERFALL https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/368 <p><em>The era of digital transformation has brought significant changes to human resource management across various organizations. Manual human resource management (HRM) at PT Infico Alumindo Indonesia has resulted in several issues, such as delayed attendance recap, disorganized leave data, and time-consuming payroll processes. Therefore, this study aims to design and implement a web-based Human Resources Information System (HRIS) using the Laravel framework and the waterfall method to improve HRM efficiency at PT Infico Alumindo Indonesia. This research employs the waterfall method, which consists of five stages: requirement analysis, system design, implementation, testing, and maintenance. Data collection techniques include direct observation at the company, interviews with company representatives particularly the Operational Director, and literature studies from various academic sources. The results of this study indicate that the developed HRIS successfully automates the attendance process through facial recognition technology and real-time location tracking. The attendance feature for sales personnel is enhanced with photo geotagging, displaying timestamps and real-time locations on the captured images. The leave management module is also systematically integrated, allowing supervisors to approve leave requests quickly and in a well-documented manner. The payroll feature is now directly connected to attendance data, sales attendance, monthly and daily wages, and overtime, enabling accurate and efficient payroll calculations. Additionally, the people development module supports periodic employee development tracking, including performance evaluations and job mutations.</em></p> Muhammad Zaidan, M Fauzi Isputrawan Copyright (c) 2025 Muhammad Zaidan, M Fauzi Isputrawan https://creativecommons.org/licenses/by-nc-sa/4.0 https://publikasi.teknokrat.ac.id/index.php/teknoinfo/article/view/368 Thu, 10 Jul 2025 00:00:00 +0700