Article Per Year (5 Year)
p-Index From 2021 - 2026
7.687
P-Index
This Author published in this journals
All Journal Informatika Mulawarman: Jurnal Ilmiah Ilmu Komputer RABIT: Jurnal Teknologi dan Sistem Informasi Univrab JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Jurnal Teknovasi : Jurnal Teknik dan Inovasi Mesin Otomotif, Komputer, Industri dan Elektronika JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Sisfokom (Sistem Informasi dan Komputer) Jurnal Informatika Kaputama (JIK) Jurnal Informasi dan Teknologi Vocatech : Vocational Education and Technology Journal JTIK (Jurnal Teknik Informatika Kaputama) JOURNAL OF INFORMATICS AND COMPUTER SCIENCE G-Tech : Jurnal Teknologi Terapan Journal of Computer Science, Information Technology and Telecommunication Engineering (JCoSITTE) Jurnal Pengabdian kepada Masyarakat Nusantara JINAV: Journal of Information and Visualization International Journal of Engineering, Science and Information Technology MALLOMO: Journal of Community Service Journal of Renewable Energy, Electrical, and Computer Engineering Sisfo: Jurnal Ilmiah Sistem Informasi Jurnal Teknologi Terapan and Sains 4.0 Jurnal Pengabdian Masyarakat Bangsa MEUSEURAYA : JURNAL PENGABDIAN MASYARAKAT Jurnal Informatika: Jurnal Pengembangan IT Jurnal Malikussaleh Mengabdi Journal of Advanced Computer Knowledge and Algorithms JuTISI (Jurnal Teknik Informatika dan Sistem Informasi) Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Proceedings of Malikussaleh International Conference on Multidisciplinary Studies (MICoMS)
Yesy Afrillia
Universitas Malikussaleh
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Nursing Physics Public Health Social Sciences Transportation Other

Published : 58 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 58 Documents
Search

 2   3   4   5   6 
PENGEMBANGAN MODEL DETEKSI BERITA PALSU PADA PLATFORM BERITA ONLINE MENGGUNAKAN METODE BIDIRECTIONAL ENCODER REPRESENTATIONS FROM TRANSFORMERS (BERT) Farhan Dika; Wahyu Fuadi; Yesy Afrillia
Jurnal Teknologi Terapan and Sains 4.0 Vol 6 No 3 (2025): Jurnal Teknologi Terapan & Sains
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/tts.v6i3.26167

Abstract

Penyebaran berita palsu pada platform berita online telah menjadi tantangan serius yang mengancam integritas informasi dan stabilitas sosial di era digital. Penelitian ini bertujuan untuk mengembangkan model deteksi berita palsu yang akurat menggunakan metode Bidirectional Encoder Representations from Transformers (BERT) dengan pendekatan fine-tuning pada dataset berita berbahasa Indonesia. Dataset penelitian terdiri dari 248 artikel berita yang dikurasi dari berbagai platform media online, kemudian diseimbangkan menjadi 196 artikel dengan distribusi 50:50 antara berita asli dan berita palsu. Metodologi penelitian mencakup text preprocessing, tokenisasi menggunakan IndoBERT tokenizer dengan panjang maksimal 128 token, dan pembagian data dengan stratified train-test split 80:20. Model IndoBERT di-fine-tune selama 3 epoch dengan konfigurasi batch size 4, learning rate 2e-5, dan gradient accumulation steps 2. Hasil penelitian menunjukkan performa yang sangat baik dengan akurasi 85.0% pada data testing, macro average F1-score 0.8485, dan evaluation loss 0.3669. Model menunjukkan precision 0.9375 dan recall 0.75 untuk deteksi berita palsu, serta precision 0.7917 dan recall 0.95 untuk berita asli. Validasi menggunakan confusion matrix menunjukkan 34 prediksi benar dari 40 sampel testing, dengan karakteristik model yang cenderung konservatif dalam melabeli berita sebagai palsu. Pengujian pada kasus nyata menunjukkan kemampuan model dalam mengidentifikasi indikator linguistik berita palsu seperti kata "SALAH", "PENIPUAN", dan "HOAX" dengan tingkat kepercayaan 65.50%-88.51%. Penelitian ini membuktikan bahwa metode BERT efektif untuk deteksi berita palsu berbahasa Indonesia dan dapat diimplementasikan sebagai sistem moderasi konten otomatis pada platform berita online. Kata kunci: BERT, Deteksi Berita Palsu, Natural Language Processing, Klasifikasi Teks, Deep Learning.
Implementation of VRRP for Internet Optimization at Class I Sultan Iskandar Muda Meteorological Station - Banda Aceh Kasihan Muhammad Fajar; Wahyu Fuadi; Yesy Afrillia
Journal of Renewable Energy, Electrical, and Computer Engineering Vol. 4 No. 1 (2024): March 2024
Publisher : Institute for Research and Community Service (LPPM), Universitas Malikussaleh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/jreece.v4i1.15812

Abstract

Class I Sultan Iskandar Muda - Banda The Aceh Meteorological Observatory is an environmental engineering implementing agency for observation and data processing, under the responsibility of the Meteorology, Climatology and Geophysical Agency. When using a government agency`s Internet network, failures such as unstable connections, failures, errors, and broken main routers often occur. If the main router goes down, no backup is available. To avoid this, a backup router must exist. Therefore, in this study, we apply an implementation of the virtual redundant router protocol to optimize the Internet network. The reseacrh aims explore to investigate the quality of WiFi network services. Researchers use her QoS analysis using packet loss, delay, and jitter parameters. Testing was conducted using Wireshark software during peak office hours in January and February 2023. The latency parameter findings were 3.49 ms in January and 4.89 ms in February on the main router (very good). The average jitter parameter was 3.49ms in January and 4.89ms in February (very good). The packet loss parameter is 2.05% (good) in February, while the overall average value in January is 0.83%. Overall, the calculation of the three parameters according to the TIPHON standardization is within a good range. His implementation of VRRP at the Sultan Iskandar Muda Weather Observatory proves the effectiveness of his VRRP in improving network availability and reliable backup systems.
Comparison of Random Forest Algorithm Classifier and Naïve Bayes Algorithm in Whatsapp Message Type Classification Abdul Hadi; Mukti Qamal; Yesy Afrillia
Journal of Renewable Energy, Electrical, and Computer Engineering Vol. 5 No. 1 (2025): March 2025
Publisher : Institute for Research and Community Service (LPPM), Universitas Malikussaleh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/jreece.v5i1.21227

Abstract

This study compares the effectiveness of Random Forest and Naïve Bayes algorithms in classifying WhatsApp messages into three categories: normal, promotional, and fraudulent messages. With over 2.78 billion active users worldwide and 90% of Indonesian internet users utilizing WhatsApp, the platform's end-to-end encryption creates challenges for automatic spam detection, necessitating machine learning approaches. A dataset of 300 messages, equally distributed across the three categories, underwent preprocessing including cleansing, case folding, stopword removal, normalization, and stemming before being converted to numerical form using TF-IDF vectorization. Experimental results demonstrated that Naïve Bayes outperformed Random Forest with higher accuracy (88.67% vs. 86.00%), precision (89.64% vs. 88.95%), recall (88.67% vs. 86.00%), and F1-score (88.61% vs. 85.99%). Cross-validation analysis with 10-fold validation further confirmed Naïve Bayes' superior consistency and stability across all evaluation metrics. Additionally, Naïve Bayes exhibited remarkable computational efficiency, requiring only 0.13 seconds for training compared to Random Forest's 3.65 seconds. Confusion matrix analysis revealed Naïve Bayes' particular effectiveness in distinguishing between normal and fraudulent messages, crucial for preventing users from falling victim to scams. The model successfully identified key fraud indicators such as "claim," "account," and "verification" while demonstrating precision in ambiguous cases. These findings contribute significantly to developing more effective spam detection systems for encrypted messaging platforms where traditional filtering mechanisms cannot be applied, ultimately enhancing user safety and experience through automated identification of potentially harmful content.
Sistem Informasi Manajemen Laundry Berbasis Web Intan Putri Dinanti; Rizky Putra Fhonna; Yesy Afrillia
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 6 No. 1 (2022): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2022
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v6i1.7987

Abstract

Bisnis laundry merupakan bisnis jasa keperpercayaan sehingga tidak lepas dari peminatnya dan tanpa disadari bahwa bisnis ini telah menjadi bagian penting dari kehidupan manusia dan akan terus ada. Aktivitas sehari-hari yang sibuk seringkali memakan waktu lama sehingga tugas yang seharusnya dilakukan sendiri harus diserahkan kepada penyedia layanan. OkeLaundry merupakan salah satu perusahaan jasa laundry yang sedang berkembang. Pengelolaan data laundry dilakukan secara manual sehingga sering terjadi kesalahan karena human error dalam pengelolaan data dan tidak jarang record hilang membutuhkan waktu yang lama dalam pencatatan data. Begitu juga dengan konsumen yang ingin mengetahui hasil cuciannya harus bertanya langsung ke pihak pengelola karena akan sangat tidak efisien dan membuang waktu. Maka lahirlah aplikasi sistem informasi untuk mengatasi permasalahan tersebut. Sistem informasi ini dibuat berbasis web dengan menggunakan PHP framework Codeigniter 3 dan juga menggunakan framework Bootstrap. Untuk bagian menyimpan data digunakan database Mysqli. Dengan adanya aplikasi laundry berbasis web ini, kasir dapat melakukan proses input data, baik data konsumen, data paket maupun data transaksi, mengubah data, menghapus data dan mencetak laporan. Disamping itu, kasir dapat men filter periode laporan yang akan dicetak sehingga memudahkan pengecekan data baik perhari, perbulan bahkan pertahun. Keuntungannya bagi konsumen, konsumen dapat mengecek status dari laundryan mereka dengan memasukkan kode transaksi yang telah tercetak di invoice. Sistem informasi manajemen laundry dibuat dengan tujuan menjadikan pengelolaan data, pencatatan transaksi, pembuatan laporan menjadi teratur serta pengecekan status laundryan lebih mudah dan tepat, sehingga pemilik mudah dalam mengontrol bisnisnya, konsumen mudah dalam mengecek laundryannya.
Integrated Emergency Communication System for Disaster Areas Using Long Range Mahadika Luqman; Muhammad Fikry; Yesy Afrillia
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12753

Abstract

Natural disasters disrupt communication infrastructure, hindering emergency response coordination. This study designs and evaluates an integrated emergency communication system combining LoRa for transmission, GPS for geolocation, and BLE for alternative interface. The system comprises a Field Device with a 9-state finite-state machine, a Beacon Network forming a linear multi-hop relay chain with heartbeat-based node failure detection, and a Headquarter Device connected to the Blynk platform for monitoring and notifications. A custom binary protocol with 8 message types uses packed structures. All performance was evaluated in urban area, except maximum communication direct range in urban area and rural area. PDR achieves 100% up to 1,000 m Line-of-Sight with an average end-to-end latency of 1.02 s. A single beacon relay extends communication range to 2000 m compared to maximum direct communication range, 1288 m in rural area and 1044 m in urban campus area. Outdoor GPS accuracy measures 0.945 m, while indoor accuracy 28.68 m due to building attenuation. The system successfully detected motion >5 m with 100% sensitivity within 5 s. Usability testing average completion times of 14.84 s via physical interface and 23.85 s via mobile application. BLE range reaches 16 m outdoors and 11 m indoors. Operational durations were 4.32 h for the Field Device, 9.18 h for the Beacon Network, and 8.03 h for the Headquarter Device, falling short of the 12-hour target, necessitating aggressive GPS duty cycling and Wi Fi sleep modes. This study evaluates three critical factors for emergency response: network determinism, payload efficiency, and power autonomy.
Detection of Anemia Based on Conjunctival Images Using a Convolutional Neural Network (CNN) Method Sari, Rika Yulia; Fitri, Zahratul; Afrillia, Yesy
Informatika Mulawarman : Jurnal Ilmiah Ilmu Komputer Vol 21, No 1 (2026): Informatika Mulawarman : Jurnal Ilmiah Ilmu Komputer
Publisher : Mulawarman University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/jim.v21i1.28906

Abstract

A hemoglobin level below 12 g/dL is the primary indicator of anemia, a condition commonly found in adolescent girls. Laboratory blood tests, as a conventional detection method, are invasive, time-consuming, and costly. This study developed a non-invasive classification system for anemia and non-anemia based on conjunctival images using a Convolutional Neural Network (CNN), implemented on a real-time website. A total of 433 conjunctival images were collected comprising 206 images of anemia and 227 of non-anemia sourced from smartphone cameras and the Kaggle dataset, divided in an 80:10:10 ratio for training, validation, and testing. Preprocessing included resizing to 150 150 pixels, augmentation (flip, rotation, zoom, translation, brightness), and pixel normalization. The CNN architecture consists of three convolutional layers (32, 64, and 128 filters), max pooling, dropout, and a fully connected layer with sigmoid activation, trained using the Adam optimizer and the binary cross-entropy loss function until the 43rd epoch. The model achieved an accuracy of 88.37%, precision of 0.89, recall of 0.88, and an F1-score of 0.88. The model was integrated with a Flask-based REST API and MediaPipe Face Landmarker to automatically detect the conjunctival Region of Interest (ROI) via camera or uploaded images, thereby potentially serving as a fast, practical, and easily accessible tool for the initial screening of anemia among adolescent girls in schools and primary health care facilities.
Expert System For Detecting Soil Fertility Levels for Oil Palm Cultivation Using the Fuzzy Tsukamoto Winda Yanti; Zara Yunizar; Yesy Afrillia
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.884

Abstract

Soil fertility is one of the critical factors that affect the productivity of oil palm plants. Inappropriate soil fertility levels can cause suboptimal plant growth and even crop failure. Low public knowledge about soil fertility is also a significant factor. This research aims to build an expert system that can detect the soil fertility level for oil palm plants using the fuzzy Tsukamoto method. This system uses three main parameters as a reference: soil acidity (pH), soil moisture, and soil texture. The fuzzy Tsukamoto method was chosen because it can handle uncertain data and provide more flexible results. The system was developed web-based using the PHP programming language and MySQL database, and tested on 49 soil data points from the Agricultural Extension Center of Matangkuli District, North Aceh Regency. The system successfully detected soil fertility levels accurately and consistently. Tests were conducted on 49 soil sample data from various villages in Matangkuli District, North Aceh Regency, where soil fertility in the Low category was found in 43 villages with a percentage of 84%, soil fertility in the Medium category was found in 6 villages with a rate of 16% and soil fertility in the High category was not found in any town of Matangkuli District with a percentage of 0% with valid fertility classification results and by expert judgment. With this system, farmers and agricultural extension workers can be helped to make the right decisions regarding the feasibility of land for planting oil palm plants.
Sentiment Analysis of Customer Satisfaction Towards Shopee and Lazada E-commerce Platform Using the Random Forest Algorithm Classifier Tursina Dewi; Asrianda Asrianda; Yesy Afrillia
International Journal of Engineering, Science and Information Technology Vol 5, No 1 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i1.692

Abstract

In the digital era, e-commerce platforms like Shopee and Lazada have become the primary channels for online transactions in Indonesia, significantly shaping consumer behaviour and business strategies. This study analyses and compares consumer sentiment towards product reviews on these platforms, focusing on three prominent stores: Skintific, Originote, and Azarine. The research utilized a dataset of 4,500 comments collected from both platforms, with 3,600 comments allocated for training and 900 comments for testing. The sentiment analysis used a lexicon-based approach and machine learning techniques to ensure accuracy and reliability. The results reveal that the Skintific store achieved 88% positive sentiment on Shopee and 84.1% on Lazada. The Originote store recorded 81.4% positive sentiment on Shopee and 91.5% on Lazada, while the Azarine store achieved 87.8% on Shopee and 77.9% on Lazada. These findings highlight variations in consumer sentiment between platforms, which platform-specific features and user demographics may influence. This study provides valuable insights for businesses to tailor their marketing strategies and improve customer engagement on different e-commerce platforms.
Co-Authors Abadi, Sabani Abdul Hadi Abil Khairi Adek, Rizal Tjut Aldo januansyah. H Ananda Faridhatul Ulva Annas, Muhammad Aqmal, Jamalul Arif, Abdul Halim Arif, M. Arif Saputra Arifa, Cut Hilma Asmi, Nurul Annisa Asrianda Asrianda Asrifan, Andi Asrillah Asrillah Aswandi, Sakti Ayu Indah Lestari Berutu, Indah Fachlira Bustami Bustami Cut Agusniar Dahlan Abdullah Dasril Dasril David Sarana Deassy Siska EDI YUSUF, EDI Effan Fahrizal Ekamaida, Ekamaida Elvina Mutiara Vina Eri Saputra eva darnila, eva darnila Fadlisyah Fadlisyah Fadlisyah Faiz Fadhilla Fakhruddin Ahmad Nasution Farhan Dika Fatika, Dian Fidyati, Fidyati Fikria, Putri Fuadi, Wahyu Gilang Ramadhan Purba Hafidh Rafif, Teuku Muhammad Harahap, Ilham Taruna Herman Fithra Hidayat, Amam Taufiq ilham - sahputra Ilsa Hidayat Intan Putri Dinanti Jamalul Aqmal Julianansa, Ririn Kasihan Muhammad Fajar Kautsar, Al Khairuni Khairuni Lidya Rosnita Mahadika Luqman Mahesa Reglisalo Muhammad Fikry Muhammad Ikhwanus Muhammad Iqbal Muhammad Muhammad Muhammad Yusuf Mukhlis Mukhlis Mukti Qamal Muzaffar Rigayatsyah Muzaffar Rigayatsyah NELI SUSANTI, NELI Nurdin Nurdin Nurqamarina Rahma, Mutiara Rahmawati, Rahmawati Rini Meiyanti Risawandi, Risawandi Riza, Saiful Rizal Rizal Rizal Rizal S.Si., M.IT, Rizal Rizky Putra Fhonna Rozzi Kesuma Dinata Safriand, Safriand Sari, Rika Yulia Sayed Fachrurrazi Selian, Riko Ardiansyah Siregar, Winda Ramadhani Sofyan Sofyan Suci Ramadani Sujacka Retno Teuku M. Arief Afwan Tursina Dewi Uliana, Lisa Ulva Ilyatin Veri Ilhadi Wahyu Fuadi Wahyu Fuadi Wardana, Ade Bagus Widari, Liz Ayu Winda Yanti Yusril Zahratul Fitri, Zahratul Zara Yunizar Zuhra, Elviza Zulfan