Jurnal Nasional Teknik Elektro dan Teknologi Informasi https://jurnal.ugm.ac.id/v3/JNTETI <p><strong><img style="display: block; margin-left: auto; margin-right: auto;" src="/v3/public/site/images/khanifan/HEADER_JNTETI_2020_1200x180_Background_baru_tanpa_list1.jpg" width="600" height="90" align="center"></strong></p> <p><strong>Jurnal Nasional Teknik Elekto dan Teknologi Informasi</strong>&nbsp;is an international journal accommodating research results in electrical engineering and information technology fields.<br><br><strong>Topics cover the fields of:</strong></p> <ul> <li class="show">Information technology: Software Engineering, Knowledge and Data Mining, Multimedia Technologies, Mobile Computing, Parallel/Distributed Computing, Data Communication and Networking, Computer Graphics, Virtual Reality, Data and Cyber Security.</li> <li class="show">Power Systems: Power Generation, Power Distribution, Power Conversion, Protection Systems, Electrical Material.</li> <li class="show">Signal, System and Electronics: Digital Signal Processing Algorithm, Robotic Systems, Image Processing, Biomedical Engineering, Microelectronics, Instrumentation and Control, Artificial Intelligence, Digital and Analog Circuit Design.</li> <li class="show">Communication System: Management and Protocol Network, Telecommunication Systems, Antenna, Radar, High Frequency and Microwave Engineering, Wireless Communications, Optoelectronics, Fuzzy Sensor and Network, Internet of Things.</li> </ul> <p><strong>Jurnal Nasional Teknik Elekto dan Teknologi Informasi is published four times a year: February, May, August, and November.<br></strong><strong><br>Jurnal Nasional Teknik Elektro dan Teknologi Informasi has been accredited by Directorate General of Higher Education, Ministry of Education and Culture, Republic of Indonesia, </strong>Number 28/E/KPT/2019 of September 26, 2019 (<strong>Sinta 2</strong>),&nbsp;<strong>Vol. 8 No. 2 Year 2019 up to Vol. 12 No. 2 Year 2023<br></strong><strong><br>Publisher<br></strong>Department of Electrical and Information Engineering, Faculty of Engineering, Universitas Gadjah Mada<br>Jl. Grafika No 2. Kampus UGM Yogyakarta 55281<br>Website&nbsp; :&nbsp;&nbsp;<a href="https://jurnal.ugm.ac.id/v3/JNTETI">https://jurnal.ugm.ac.id/v3/JNTETI</a><br>Email&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; :&nbsp;&nbsp; jnteti@ugm.ac.id<br>Telephone&nbsp;&nbsp; :&nbsp; +62 274 552305</p> en-US <p style="text-align: justify;">© <span style="font-weight: 400;">Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the</span><a href="https://creativecommons.org/licenses/by-sa/4.0/"> <span style="font-weight: 400;">Creative Commons Attribution-ShareAlike 4.0 International License</span></a><span style="font-weight: 400;">.</span></p> jnteti@ugm.ac.id (Sekretariat JNTETI) jnteti@ugm.ac.id (Sekretariat JNTETI) Fri, 16 May 2025 00:00:00 +0700 OJS 3.1.2.0 http://blogs.law.harvard.edu/tech/rss 60 Comparative Analysis of MVVM and MVP Patterns Performance on Android Dashboard System https://jurnal.ugm.ac.id/v3/JNTETI/article/view/18985 <p class="JNTETIIntisari"><span lang="EN-US">The rapid growth of the Android market in various developing countries has driven the demand for higher-quality applications. Developing Android-based applications presents specific challenges, such as the need for responsive designs and optimization for devices with diverse specifications. Design patterns like model-view-controller (MVC), model-view-presenter (MVP), and model-view-viewmodel (MVVM) have become popular approaches to address these issues. However, studies on the performance of design patterns in Android applications, especially in modern programming languages like Kotlin, remain limited. This research aims to compare the performance of the MVP and MVVM design patterns in an Android-based boarding house management application, KosGX. This application utilized Kotlin and featured an interactive dashboard requiring significant device resources. Testing was conducted by measuring performance across three key aspects: central processing unit (CPU) usage, memory usage, and system response time. The results of the study showed that MVVM outperformed in CPU efficiency, with an average usage of 8.92% compared to 11.15% for MVP. In terms of memory usage, MVVM was also slightly more efficient, with an average usage of 121.48 MB compared to 121.55 MB for MVP. However, MVP excelled in response time, averaging 236.88 ms, whereas MVVM reached 252.68 ms. This study underscores that the choice of design pattern affects application performance. MVVM is more efficient in CPU and memory usage, while MVP offers better response times. These findings provide valuable insights for developers in selecting the optimal design pattern based on the specific needs of their applications.</span></p> Fajar Pradana, Raziqa Izza Langundi, Djoko Pramono, Nur Ida Iriani Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/18985 Fri, 16 May 2025 09:56:15 +0700 Detecting Fraudulent Transaction in Banking Sector Using Rule-Based Model and Machine Learning https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17410 <p>This research aims to develop an effective fraud detection model in banking transactions using the rule-based model (RBM) approach and the isolation forest (IF) machine learning algorithm. Based on data from the Ministry of Communication and Information Technology, there were more than 405,000 online fraud cases during the 2019–2022 period, indicating the need for a reliable fraud detection system to protect customers. The research method involves collecting banking transaction data for four months through channels such as ATM, internet banking, and mobile banking. The RBM model was used as an initial approach, detecting suspicious transaction patterns based on defined rules. However, it has limitations in detecting transactions that are not defined in the rules. To complement this shortcoming, this research implemented IF, an effective unsupervised learning model for detecting anomalies using the isolation tree (iTree) technique to identify suspicious transactions. The results showed that the IF model could detect anomalous patterns not covered by RBM, thereby improving the accuracy of fraud transaction identification. The precision data of 99% indicates that the model’s predictions of anomalies are indeed anomalies, while a recall value of 1.0 shows that the model successfully identified all anomalies in the dataset. In conclusion, the combination of RBM and IF provides a comprehensive approach to fraud detection in the banking sector. IF’s ability to detect anomalies more dynamically and accurately can reduce fraud losses in the industry.</p> Cut Dinda Rizki Amirillah Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17410 Tue, 27 May 2025 11:09:21 +0700 Advancing Indonesia’s Energy Transition: Coal-to-Nuclear (C2N) Simulation Study https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17426 <p>Indonesia’s ambitious net-zero emissions (NZE) target for 2060 necessitates a transformative shift from coal-dependent power systems to nuclear energy sources. Although previous studies have explored various aspects of energy transitions, limited attention has focused on the possibility of replacing existing coal-fired boilers with nuclear reactors while maintaining the input and output parameters of the current infrastructure. This paper presents an approach to facilitating Indonesia’s nuclear energy transition by a coal-to-nuclear (C2N) simulation study. Specifically, the focus is on the 400 MW coal-fired power plant (CFPP), which relies on coal combustion. This study was designed to model the conversion process of the coal combustion system to a modular nuclear reactor setup while preserving the existing steam turbine and generator infrastructure. The foundation of this study was that the replacement of the nuclear reactor-based heat source must meet the requirements of the pre-existing water and steam cycle design. Various configurations for substituting the current boiler with a nuclear reactor were analyzed in this study, by considering engineering, operational, and modeling aspects. Results from model simulations for nine different operating conditions showed a deviation of the main-steam temperature of about 3% of the design value, starting at 120 MWe and above. Nevertheless, all other parameters of the conversion simulation results demonstrated a very small deviation. The deviation was close to the actual existing operational conditions of the previous CFPP. This paper highlights how the simulation demonstrated a promising integration of legacy infrastructure with emerging nuclear technology.</p> Irfan Eko Budiyanto, Sinta Uri El Hakim Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17426 Wed, 28 May 2025 09:11:00 +0700 Evaluasi Pengukuran Semantik Sinonim KBBI Menggunakan Pendekatan Word Embedding https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17117 <p>Kamus Besar Bahasa Indonesia (KBBI) ialah salah satu sumber utama penyedia data dalam penelitian menentukan kemiripan makna kata dalam bahasa Indonesia. Penelitian ini membahas cara metode <em>word embedding</em> dan teknik pembobotan <em>term frequency-inverse document frequency </em>(TF-IDF) mengukur tingkat kemiripan pasangan makna kata sinonim, dengan tujuan mengukur kemiripan pasangan makna kata sinonim dalam KBBI menggunakan <em>cosine similarity </em>dengan memanfaatkan teknik pembobotan TF-IDF dan beberapa model<em> word embedding </em>serta menerapkan<em> latent semantic analysis </em>(LSA). Metodologi penelitian ini dimulai dengan pengumpulan data, kemudian prapemrosesan teks yang terdiri atas <em>case folding</em>, <em>stopword removal</em>, <em>stemming</em>, dan <em>tokenization</em>. Selanjutnya, data yang telah diproses direpresentasikan ke dalam bentuk vektor menggunakan model <em>word embedding</em>, seperti Word2Vec, fastText, GloVe, <em>bidirectional encoder representations from transformers </em>(<em>Sentence-BERT</em>, S-BERT), dan teknik pembobotan TF-IDF. Lalu, LSA diterapkan untuk mereduksi dimensi vektor sebelum dilakukan uji kesamaan dengan <em>cosine similarity</em> dan diakhiri dengan evaluasi hasil. Hasil penelitian menunjukkan bahwa penggunaan fastText berhasil meningkatkan nilai kesamaan antara makna dua kata sinonim dengan nilai rata-rata yang diperoleh pada uji kesamaan dari 30 pasang makna kata sinonim adalah 0,901, dengan hasil evaluasi menunjukkan akurasi 0,88, <em>recall</em> 1,00, presisi 0,81, dan <em>F</em>1<em>-score</em> 0,90. Dengan temuan ini, dapat disimpulkan bahwa penggunaan fastText lebih efektif dalam meningkatkan akurasi pengukuran kemiripan makna kata sinonim. Rekomendasi untuk penelitian selanjutnya melibatkan perluasan korpus data dan eksplorasi lebih lanjut terhadap <em>word embedding</em> dalam uji kesamaan makna kata. Penelitian ini memberikan kontribusi pada pengembangan pemrosesan bahasa alami dan berpotensi menjadi dasar untuk aplikasi berbasis pemrosesan bahasa yang lebih akurat dalam mengukur kemiripan makna kata dalam KBBI.</p> Muhammad Rafli Aditya H., Muhammad Ilham, Dewi Fatmarani Surianto, Abdul Muis Mappalotteng Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17117 Wed, 28 May 2025 09:11:44 +0700 5G Network Planning Using Macrocell and Piccocell Technology https://jurnal.ugm.ac.id/v3/JNTETI/article/view/16830 <p>The city of Pontianak is projected to experience substantial growth in network demand, driven by the expansion of commercial hubs, educational institutions, tourism destinations, and essential public services. Under the current status quo, Pontianak lacks 5G network coverage, underscoring the necessity of implementing a comprehensive 5G network plan to support its urban development. This research conducted a detailed analysis of 5G network coverage and capacity planning, utilizing macrocell and picocell technologies to address the connectivity demands of an urban environment. Operating within the 3.5 GHz frequency band with a 100 MHz bandwidth, this research examined network requirements in the medium band spectrum. The results revealed that macrocell technology required 18 uplink and 23 downlink sites to cover an area of 107.8 km², while picocell technology demanded a denser infrastructure, comprising 351 uplink and 364 downlink sites across 90.72 km². Based on a five-year capacity projection for a population of 673,400, the macrocell technology will require 10 uplink and 22 downlink sites. On the contrary, picocell technology, which is more suitable for densely populated areas, will require 261 uplink and 263 downlink sites to serve a population of 423,881. Simulation results indicated that synchronization signal reference signal received power (SS-RSRP) and secondary synchronization signal received power (SS-SINR) values met or surpassed the established key performance indicators (KPI) for both technologies. This 5G network plan aligns with Pontianak’s smart city vision by enhancing connectivity, optimizing coverage, and delivering seamless user experiences, highlighting the adaptability of macrocell and picocell solutions in varied urban settings.</p> Rivan Achmad Nugroho, Redy Ratiandi Yacoub, Herry Sujaini, Dedy Suryadi, Eva Faja Ripanti Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/16830 Wed, 28 May 2025 09:12:02 +0700 Studi Komparasi Kinerja Object-Relational Mapping Berdasarkan Implementasi Data Source Architectural Pattern https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17315 <p><em>Object-relational mapping</em> (ORM) merupakan teknik <em>mapping</em> antara <em>in-memory objects</em> dan tabel pada basis data. ORM mengimplementasi <em>data source architectural patterns </em>(DSAP), di antaranya <em>Data Mapper</em> dan <em>Active Record</em>. Komparasi kinerja kedua <em>pattern </em>perlu dilakukan karena adanya indikasi perbedaan kinerja serta mengingat perannya yang signifikan terhadap proses bisnis sebuah sistem. Studi ini bertujuan melakukan komparasi dan analisis terhadap kinerja durasi eksekusi dan konsumsi memori secara kuantitatif serta fungsi-fungsi yang memengaruhinya pada ORM yang mengimplementasi <em>Data Mapper</em> dan <em>Active Record</em>. Doctrine (<em>Data Mapper</em>) dan Eloquent (<em>Active Record</em>) dijadikan sebagai objek studi. <em>Profiling</em> kinerja pada ORM dilakukan dalam bentuk <em>library</em>, tidak dibundel dalam <em>framework</em>. <em>Profiling</em> mencakup operasi <em>create, read, update, and delete</em> (CRUD) dan <em>lookup</em> berdasarkan metrik ukur tertentu serta dilakukan dengan variasi jumlah <em>database</em> <em>record</em>. Proses <em>profiling </em>diotomatisasi melalui <em>script</em> yang memanfaatkan kombinasi Xdebug dan Apache Benchmark. Analisis dilakukan dengan Kcachegrind dan <em>Big-O Notation</em>. Analisis menghasilkan grafik kinerja dan <em>relative percentage difference</em> serta kontribusi fungsi-fungsi terhadap kinerja. Hasil menunjukkan kinerja konsumsi memori <em>Active Record</em> unggul atas <em>Data Mapper</em>. <em>Data Mapper</em> unggul dalam kinerja durasi eksekusi pada sebagian besar kombinasi operasi dan metrik. Kelompok fungsi <em>database transaction</em>, <em>object serialization</em>, dan <em>record retrieval </em>merupakan kontributor terbesar terhadap kedua kinerja serta tambahan kelompok fungsi <em>object and database synchronization</em> untuk <em>Active Record</em>. Kompleksitas fungsi-fungsi kontributor terbesar pada <em>Data Mapper</em> lebih tinggi dibandingkan <em>Active Record</em>. Studi berikutnya dapat memanfaatkan konsep otomatisasi pada proses <em>profiling</em> dan mensubstitusi Xdebug sesuai kebutuhan bahasa pemrograman yang digunakan oleh ORM.</p> Muhammad Rezy Anshari, Redi Ratiandi Yacoub, Herry Sujaini, Bomo Wibowo Sanjaya, Eva Faja Ripanti Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17315 Wed, 28 May 2025 09:12:29 +0700 Deteksi Duplikasi Data pada Sistem Pemantauan Kualitas Udara Berbasis IoT https://jurnal.ugm.ac.id/v3/JNTETI/article/view/16272 <p class="JNTETIIntisari" style="line-height: 105%;"><span lang="EN-US">Peningkatan volume data pada sistem berbasis <em>internet of things</em> (IoT) telah mendorong kebutuhan akan efisiensi dalam pengelolaan data, khususnya dalam konteks sistem pemantauan kualitas udara. Salah satu pendekatan untuk mengatasi tantangan ini adalah deteksi duplikasi data, yang berfungsi mengeliminasi data redundan guna mengurangi kebutuhan penyimpanan dan konsumsi daya. Penelitian ini bertujuan untuk mengembangkan sistem pemantauan kualitas udara berbasis IoT yang menerapkan metode deteksi duplikasi data sebagai bagian dari upaya mendukung konsep GreenIoT. Metodologi penelitian melibatkan perbandingan antara sistem tanpa dan dengan penerapan deteksi duplikasi data serta evaluasi menyeluruh terhadap kinerja sistem. Data yang diuji meliputi ukuran data yang dikirim dan konsumsi daya perangkat selama proses transmisi. Pengujian dilakukan dalam skenario operasional nyata selama 24 jam. Hasil penelitian menunjukkan bahwa penerapan deteksi duplikasi data berhasil menurunkan ukuran data yang dikirim dari 56 byte menjadi 11-44 byte, tergantung pada tingkat redundansi data. Selain itu, konsumsi daya berhasil dikurangi sebesar 1,59% hingga 3,84% dibandingkan dengan sistem tanpa deteksi duplikasi data. Metode ini juga terbukti tidak mengurangi akurasi data yang ditampilkan, sehingga tetap memenuhi kebutuhan fungsional sistem. Kesimpulannya, implementasi metode deteksi duplikasi data pada sistem pemantauan kualitas udara berbasis IoT tidak hanya mengoptimalkan proses transmisi data, tetapi juga mendukung efisiensi energi sesuai prinsip <em>Green</em> IoT. Penelitian ini memberikan kontribusi penting dalam pengembangan sistem IoT yang lebih berkelanjutan dan hemat energi.</span></p> Dwi Ilham Maulana, Asep Andang, Ifkar Usrah, Agus Purnomo Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/16272 Wed, 28 May 2025 09:12:50 +0700 Ensemble Voting Classifier Berbasis Multi-Algoritma dan Metode SMOTE untuk Klasifikasi Penyakit Jantung https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17157 <p>Jantung adalah organ penting tubuh yang berfungsi untuk memompa darah. Gangguan pada jantung dapat mengganggu sirkulasi darah dalam tubuh dan menjadi salah satu penyebab utama kematian global. Menurut laporan World Health Organization (WHO) tahun 2021, jumlah kematian akibat penyakit jantung mencapai angka signifikan. Sementara itu, prevalensi penyakit jantung di Indonesia mencapai 1,5%. Maka, diperlukan upaya pencegahan dan deteksi dini penyakit jantung dengan memanfaatkan teknologi pembelajaran mesin. Penelitian ini bertujuan untuk mengembangkan model klasifikasi penyakit jantung menggunakan algoritma <em>naïve Bayes</em> dan <em>random forest</em> melalui pendekatan <em>ensemble voting</em> <em>classifier. </em>Data yang digunakan berasal dari Kaggle, yang terdiri atas 1.000 <em>record</em> dengan 14 variabel, satu di antaranya sebagai target klasifikasi. Ketidakseimbangan data diatasi dengan teknik <em>synthetic minority oversampling technique</em> (SMOTE), sedangkan seleksi fitur dikonsultasikan dengan dokter spesialis jantung untuk memastikan relevansi klinis. Model dilatih menggunakan algoritma <em>naïve Bayes</em>, <em>random forest</em>, serta kombinasi keduanya melalui metode <em>ensemble voting classifier</em>, berbeda dengan penelitian sebelumnya yang hanya membandingkan beberapa algoritma untuk menentukan akurasi tertinggi. Hasil pengujian menunjukkan bahwa model yang dilatih dengan <em>ensemble voting classifier</em> memiliki kinerja terbaik, dengan akurasi 98,28%, presisi 98,41%, <em>recall</em> 98,41%, dan <em>F</em>1-<em>score</em> 98,41%. Penelitian ini membuktikan bahwa penerapan metode <em>ensemble voting classifier </em>mampu mencapai akurasi yang lebih baik dibandingkan penggunaan algoritma secara terpisah. Model ini termasuk kategori <em>excellent</em> <em>classification</em> dan diharapkan dapat berkontribusi dalam bidang kedokteran serta mendukung praktisi medis dalam pengembangan sistem pendukung keputusan untuk diagnosis penyakit jantung.</p> Dede Kurniadi, Asri Indah Pertiwi, Asri Mulyani Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/17157 Wed, 28 May 2025 09:13:08 +0700 Developing a Drowsiness Detection System for Safe Driving Using YOLOv9 https://jurnal.ugm.ac.id/v3/JNTETI/article/view/18701 <p>Drowsiness detection systems play a crucial role in safe driving, considering the high rate of traffic accidents caused mainly by drowsiness. Several drowsiness detection systems built using the eye aspect ratio (EAR), percentage of eyelid closure (PERCLOS), and convolutional neural network (CNN) methods still have limitations in terms of accuracy and response time. This study aimed to overcome these problems by applying the You Only Look Once version 9 (YOLOv9). This method has advantages in terms of speed and accuracy because it can detect objects in real-time in one processing stage. The dataset was collected independently from several sources in a real environment inside the vehicle with various lighting and viewing angles; then, labeling, preprocessing, and modeling processes were conducted. The model performance was evaluated based on precision, recall, F1 score, and mean average precision (mAP) metrics. The best model was optimized using several optimization techniques to determine the most optimal results. The results indicate that the YOLOv9 model trained using Nadam (Nesterov-accelerated adaptive moment estimation) optimization has a better image processing speed than other models. This model yielded a precision level of 99.4%, recall of 99.6%, F1 score of 99.5%, mAP@50 of 99.5%, mAP@50-95 of 85.5%, and a processing speed of 52.08 FPS. The developed model can detect drivers’ drowsiness signs, such as closed eyes, yawning, abnormal head positions, and unnatural hand movements, in real time. However, this model still has limitations in detecting drivers wearing sunglasses, so further development is needed to improve its performance in these conditions.</p> Fernando Candra Yulianto, Wiwit Agus Triyanto, Syafiul Muzid Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/18701 Wed, 28 May 2025 11:06:37 +0700 Deteksi Berita Hoaks Berbahasa Indonesia Menggunakan 1-Dimensional Convolutional Neural Network https://jurnal.ugm.ac.id/v3/JNTETI/article/view/19050 <p>Kemajuan teknologi informasi yang pesat telah memfasilitasi penyebaran informasi secara global, tetapi juga meningkatkan prevalensi berita hoaks, khususnya di Indonesia. Berita hoaks memiliki potensi untuk menciptakan disinformasi yang dapat memengaruhi opini publik, stabilitas sosial, dan keamanan. Oleh karena itu, diperlukan solusi berbasis teknologi yang efektif untuk mendeteksi dan mengidentifikasi hoaks atau berita palsu. Penelitian ini bertujuan untuk mengembangkan dan mengoptimalkan model 1<em>-dimentional convolutional neural network</em> (1D CNN) guna mendeteksi berita hoaks dengan tingkat akurasi yang tinggi. <em>Dataset</em> yang digunakan terdiri atas 12.151 artikel, yang mencakup 5.276 berita valid dan 6.875 berita hoaks, yang diperoleh dari sumber tepercaya serta platform antihoaks. Tahapan prapemrosesan teks meliputi pembersihan data, <em>case folding</em>, penghapusan tanda baca, penghapusan angka, dan penghapusan <em>stopword</em>. &nbsp;Data tekstual selanjutnya diproses melalui tahapan tokenisasi dan <em>padding</em> untuk persiapan pelatihan model. Arsitektur 1D-CNN yang diusulkan mengintegrasikan lapisan <em>embedding, conv1d, batch normalization, globalmaxpooling1d, dense</em>, dan <em>dropout layer</em>, untuk meningkatkan kemampuan generalisasi serta mengurangi risiko <em>overfitting</em>. Model dilatih menggunakan <em>optimizer </em>Adam dan&nbsp; evaluasi kinerja menggunakan 10<em>-fold cross-validation</em>. Hasil eksperimen menunjukkan bahwa model menghasilkan rata-rata akurasi 97,74%, presisi 97,75%, <em>recall</em> 97,74%, dan <em>F</em>1<em>-score</em> 97,73%. Model yang dikembangkan mampu mengungguli metode sebelumnya, seperti kombinasi <em>convolutional neural network</em>- <em>bidirectional long short – term memory neural network</em> (CNN-BiLSTM), <em>gated recurrent unit </em>(GRU), dan metode konvensional seperti <em>naïve Bayes</em> atau <em>support vector machine</em> (SVM), baik dari segi akurasi maupun efisiensi waktu pelatihan. Penelitian ini &nbsp;menunjukkan bahwa model memiliki kemampuan yang andal dalam mengidentifikasi berita hoaks, baik dari segi tingkat deteksi yang akurat maupun konsistensi kinerja.</p> Muhammad Zuama Al Amin, Muhammad Ariful Furqon, Dwi Wijonarko Copyright (c) https://jurnal.ugm.ac.id/v3/JNTETI/article/view/19050 Wed, 28 May 2025 11:06:56 +0700