Claim Missing Document
Check
Articles

Comparison of Text Classification Techniques in Fake News Detection in the Digital Information Age Ilham, Dimas Muhammad; Mujiyono, Sri
International Journal of Advances in Data and Information Systems Vol. 6 No. 1 (2025): April 2025 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v6i1.1365

Abstract

A comparison of text classification techniques for detecting fake news in the digital information age has been discussed in this study, with a focus on the application of Deep Learning methods, specifically Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The increasing spread of fake news through digital platforms emphasizes the importance of developing effective methods for identifying inaccurate information. In this study, a news dataset was collected from various sources, and both models were applied for text classification analysis. The performance of the model was then measured based on accuracy, precision, recall, and F1-score. The results showed that although both have their own advantages, better results in terms of processing speed and classification accuracy were found in CNN compared to RNN. These findings provide important insights for the development of more efficient and effective fake news detection systems in the digital age.
Prediksi Fluktuasi Berat Badan Berdasarkan Pola Hidup Menggunakan Model XGBoost dan Deep Learning Mujiyono, Sri; Sanjaya, Ucta Pradema; Wibisono, Iwan Setiawan; Setyowati, Heni
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2253

Abstract

The global obesity rate has tripled since 1975, driving the development of technology-based solutions for predicting body weight to mitigate disease risks. This study implements three models—Decision Tree Regressor, XGBoost Regressor, and Deep Learning—to project final body weight based on physiological variables (age, gender, BMR), nutritional factors (caloric intake, surplus/deficit), and lifestyle factors (physical activity, sleep, stress). The multidimensional dataset from community health posts includes TDEE calculations and BMR estimates using the Harris-Benedict Equation. Evaluation using RMSE and R² indicates XGBoost as the best-performing model (RMSE: 5.65; R²: 0.974), outperforming the Decision Tree (RMSE: 10.68; R²: 0.908) and Deep Learning (RMSE: 10.4; R²: 0.913) models. Key challenges include overfitting in the Decision Tree and Deep Learning's inability to capture outliers due to vanishing gradients. The analysis identifies energy balance, representation of extreme data, and regularization as critical factors for model stability. Hyperparameter optimization (learning rate, max\_depth) and data augmentation are recommended to enhance generalization. These findings offer an innovative framework for data-driven health technologies, reinforcing the role of artificial intelligence in precision public health interventions. Practically, the study advocates for the adoption of optimized predictive models integrating multidimensional variables for high accuracy, while highlighting the need for outlier handling and further clinical validation to ensure relevance in real-world scenarios.
Sistem Pendukung Keputusan Untuk Menentukan Kualitas Beras Dengan Menggunakan Metode WP (Weighted Product) Syarifudin, Nanang Irfan; Mujiyono, Sri
MEANS (Media Informasi Analisa dan Sistem) Volume 9 Nomor 1
Publisher : LPPM UNIKA Santo Thomas Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54367/means.v9i1.3767

Abstract

Beras adalah komoditas makanan utama bagi hampir setiap negara di Asia, khususnya negara-negara Asia Tenggara. Tingginya permintaan konsumen untuk makanan berbasis beras membuat produsen beras kesulitan menentukan kualitas beras yang baik. Maka diperukan sebuah sistem pendukung keputusan untuk menentukan kualiatas beras yang terbaik dengan menggunakan metode Weighted Product (WP). Metode ini menggunakan perkalian untuk menghubungkan rating atribut, dimana setiap rating atribut harus dipangkatkan dahulu dengan bobot atribut yang bersangkutan. Metode ini hanya menghasilkan nilai terbesar yang akan dipilih sebagai alternatif terbaik. Perhitungan akan sesuai dengan metode jika alternatif yang terpilih memenuhi persyaratan yang telah diterapkan. Adapun kriteria yang terlah direkomendasikan pakar berdasarkan permasalahan yang terjadi yaitu warna, ukura, aroma, dan tekstur sehinga menghasilkan peringkat terhadap pemilihan kualitas beras terbaik yang pertama terbaik Beras Rojolele dengan nilai Vector = 0,23215, kedua terbaik Beras IR 64 dengan nilai Vector = 0,2178, ketiga terbaik Beras IR 42 dengan nilai Vector = 0,20015, keempat terbaik Beras Pandan Wangi dengan niali Vector = 0,18214, dan rangking terbaik yang terakhir yaitu Beras Methik Susu dengan nilai Vector = 0,16776.
Decision Support System for Inventory Prediction using Fuzzy Tsukamoto Method (Case Study: UMKM Bayou Indonesia) Galih Agil Febri Hidayatullah; Sri Mujiyono
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 3 (2025): November
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/sfyymk96

Abstract

Bayou Indonesia, an MSME engaged in acrylic product manufacturing, faces overproduction issues due to manual production planning, leading to stockpiling and wasted resources. This study aims to develop a decision support system using the Fuzzy Tsukamoto method to predict production quantities more accurately by analyzing historical data such as orders, shipments, and final stock. Data processing is performed with fuzzy logic to generate reliable production forecasts for the upcoming periods. The novelty of this research lies in the real-world integration of the Fuzzy Tsukamoto method within a CodeIgniter-based web application, which is directly implemented in the MSME environment, moving beyond the purely theoretical simulations of prior studies. The system significantly improves production planning accuracy, reducing manual errors (MAPE) from 21.5% to 8.7%, with an RMSE of 11.2 units. Furthermore, it helps decrease excess production discrepancies by up to 30% per month, raises prediction precision to 85%, and accelerates the decision-making process from two to three days to real-time. The resulting operational efficiency gains are estimated at 60–70%. These findings indicate that the system provides a practical solution for MSMEs to minimize overproduction risks, optimize resource usage, and enhance production planning through data-driven methods.
Analisis Klasifikasi Resign Karyawan dengan Random Forest Pratama, Ade; Mujiyono, Sri; Sanjaya, Ucta Pradema
JURNAL UNITEK Vol. 18 No. 1 (2025): Januari - Juni 2025
Publisher : Sekolah Tinggi Teknologi Dumai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52072/unitek.v18i1.1415

Abstract

Tingginya employee turnover (18,4% global) menimbulkan gangguan operasional dan kebocoran finansial kronis. Penelitian ini mengimplementasikan pipeline analitik berbasis Random Forest Classifier untuk memprediksi attrition karyawan melalui ekstraksi pola non-linier dalam ruang fitur SDM. Hasilnya mengungkap “sebagai prediktor” dominan, sementara Surat Peringatan muncul sebagai paradoks prediktif  melalui interaksi tersembunyi dengan variabel tekanan kerja. Fenomena yang hanya terkuak berkat kapasitas ensemble learning dalam menangkap high-dimensional decision boundaries. Model menunjukkan asimetri kinerja (recall kelas minoritas: 67,3%) akibat ketidakseimbangan data (rasio 1,9:1), memerlukan strategi cost-sensitive learning untuk mitigasi false negative. Temuan ini mentransformasi kebijakan SDM: dari retensi generik berbasis senioritas menuju paket personalisasi berbasis risk profiling dan competency micro-skilling, sekaligus menggeser fungsi HR dari administratif reaktif menjadi strategic predictive core.  
Pendampingan Penggunaan Aplikasi Smartdle Untuk Meningkatkan Karakter Kreatif Siswa Sekolah Dasar Purwanti, Kartika Yuni; Putra, Lisa Virdinarti; Mujiyono, Sri
Jurnal Masyarakat Madani Indonesia Vol. 2 No. 3 (2023): Agustus
Publisher : Alesha Media Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59025/js.v2i3.105

Abstract

Pengabdian ditujukan kepada Siswa Kelas 4 SDN Jubelan 01 Kecamatan Sumowono Kabupaten Semarang. Masalah yang dihadapi mitra adalah belum adanya penguatan pendidikan karakter pada siswa, kurangnya karakter kreatif siswa, serta guru belum menggunakan media berbasis aplikasi yang mampu meningkatkan karakter kreatif siswa. Metode yang digunakan adalah sosialisasi,demonstrasi dan praktik penggunaan aplikasi smartdle, pendampingan penerapan aplikasi smartdle dalam pembelajaran, serta monitoring dan evaluasi. Hasil dari pelatihan ini peserta kegiatan telah mengalami peningkatan pengetahuan danketerampilan dengan rata-rata 92%, yaitu penguatan pendidikan karakter siswa sebesar 98%, peningkatan karakter kreatif siswa sebesar 85% serta kemampuan guru dalam mengembangkan media pembelajaran berbasis digital sebesar 93%. Oleh karena itu, hasil kegiatan pendampingan penggunaan aplikasi smartdle ini dapat dikatakan berhasil dalam kategori sangat baik. Program pengabdian berupa penguatan pendidikan karakter perlu terus diupayakan. Melalui penerapan pembiasaan literasi di sekolah, maka penguatan karakter siswa akan terbentuk dengan sendirinya
Implementasi Aplikasi Perpustakaan Berbasis Website Menggunakan Framework Codeigniter 4 di Sekolah Dasar Nugroho, Aventura Suryo; Mujiyono, Sri
ELSE (Elementary School Education Journal) : Jurnal Pendidikan dan Pembelajaran Sekolah Dasar Vol 9 No 2 (2025): AUGUST
Publisher : UNIVERSITAS MUHAMMADIYAH SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30651/else.v9i2.24242

Abstract

The use of information technology is increasingly essential in data processing and storage, including library management in schools. The library at SD Negeri Candirejo 02 still applies a manual system for recording borrowings, returns, and book collection management. This condition creates several problems such as delays in data retrieval, recording errors, and inefficiency in library services. This study aims to implement a web-based library application to improve the effectiveness and efficiency of data management at SD Negeri Candirejo 02. The research method employed the waterfall model, which consists of system requirements analysis, system design, implementation, testing, and maintenance. The application was developed using PHP programming language with the CodeIgniter 4 framework and MySQL as the database, and it was equipped with a QR code scanning feature. The implementation results show that the application, named PerpusKu, can assist library staff in managing borrowing, returning, member data, book categories, book racks, and fine reports more quickly and accurately. Testing using black-box methods indicated that all features functioned as expected. Therefore, this application can serve as an effective solution for elementary school libraries in overcoming the limitations of manual systems and supporting sustainable collection management.
Inovasi Sistem Informasi Sekolah Menggunakan CodeIgniter 3 untuk Optimalisasi Layanan di Sekolah Dasar Aripin, Ahmad Nurul; Mujiyono, Sri
ELSE (Elementary School Education Journal) : Jurnal Pendidikan dan Pembelajaran Sekolah Dasar Vol 9 No 2 (2025): AUGUST
Publisher : UNIVERSITAS MUHAMMADIYAH SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30651/else.v9i2.24245

Abstract

Elementary schools as educational institutions require an information system that is fast, transparent, and easily accessible to the public. However, many schools still do not have a website-based information system, including SD Negeri X, which until now has relied on manual methods for delivering information. This condition creates limitations in disseminating information related to school profiles, teacher data, learning activities, and academic achievements. This study was conducted to address this need by developing a school information system based on a website using the CodeIgniter 3 framework and the Waterfall development method. The system was built with the PHP programming language and MySQL database, and tested using Black-Box Testing to ensure that all features functioned according to user requirements. The results showed that the developed application facilitates schools in providing information to the community, expands the school’s promotion reach, and improves the efficiency of data management, which can be accessed anytime via digital devices.   Keywords: School Information System; Website; CodeIgniter 3; Waterfall; Black-Box Testing; Education Digitalization
Simulasi Smart Home IoT dengan Aplikasi Cisco Packet Tracer Iwan Setiawan Wibisono; Sri Mujiyono
Jurnal Informatika dan Kesehatan Vol. 1 No. 1 (2024): IKN : Jurnal Informatika dan Kesehatan
Publisher : Universitas Ngudi Waluyo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35473/ikn.v1i1.3046

Abstract

The rapid development of technology has caused many changes in all fields. One area that is undergoing change is the industry sector. At present, the industry is racing to design electronic devices that can be communicated through the internet network. The industrial sector utilizes the concept of the Internet of Things (IoT). IoT itself is used in the benefits of communication between tools and monitoring. Based on that, this study aims to create a smart home design using the Cisco packet tracer simulator. This research consists of two stages including: smart home design and testing with a Cisco packet tracer simulator. Researchers made a smart home design with 3 main components, namely the door, fan and camera monitoring. The three components each have different protocols. The results of the test show that the smart home protocol designed can run well in accordance with the rules that have been determined. Abstrak Perkembangan teknologi yang semakin pesat menyebabkan terjadinya banyak perubahan dalam segala bidang. Salah satu bidang yang mengalami perubahan adalah bidang industri. Saat ini, industri berlomba untuk merancang perangkat elektronik yang dapat dikomunikasikan melalui jaringan internet. Sektor industri memanfaatkan konsep Internet of Things (IoT). IoT sendiri digunakan dalam manfaat komunikasi antar alat dan monitoring. Berdasarkan hal itu, penelitian ini bertujuan untuk membuat sebuah perancangan smart home dengan menggunakan simulator cisco packet tracer. Penelitian ini terdiri dari dua tahap diantaranya : desain smart home dan pengujian dengan simulator cisco packet tracer. Peneliti membuat sebuah rancangan smart home dengan 3 komponen utama yaitu pintu, kipas angin dan monitoring camera. Ketiga komponen tersebut masing – masing memiliki protocol yang berbeda. Hasil dari pengujian menunjukan bahwa protocol smart home yang dirancang dapat berjalan dengan baik sesuai dengan rules yang telah ditentukan.
Pelatihan Pembuatan Aplikasi Game Edukasi Menggunakan Mit App Inventor Bagi Guru Rizqi, Hesti Yunitiara; Rini, Zulmi Roestika; Mujiyono, Sri
Jurnal Masyarakat Madani Indonesia Vol. 3 No. 3 (2024): Agustus
Publisher : Alesha Media Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59025/nfsz9k17

Abstract

 Pengabdian ditujukan kepada Guru SDN Ungaran 01 Kecamatan Ungaran Barat Kabupaten Semarang. Masalah yang dihadapi mitra adalah guru belum dibekali pengetahuan tentang beberapa jenis game edukasi, kurangnya eksplorasi guru untuk membuat aplikasi game edukasi dan pemanfatannya,  serta  pengetahuan  guru hanya sebatas media yang secara instant dapat digunakan sehingga minimnya guru dalam membuat game edukasi. Metode yang digunakan adalah sosialisasi, demonstrasi dan praktek serta monitoring dan evaluasi. Hasil dari pelatihan ini  peserta kegiatan telah mengalami peningkatan pemahaman guru dengan rata-rata 93,2%, yaitu pengetahuan guru tentang jenis-jenis game edukasi 100%, Pengetahuan tentang game edukasi melalui mitt app inventor 92,5%, dan keterampilan guru dalam membuat game edukasi melalui mitt app inventor 87%. Oleh karena itu, hasil kegiatan  pelatihan  pembuatan aplikasi melalui mitt app inventor  ini  dapat  dikatakan  berhasil  dalam  kategori sangat baik. Mitt app inventor dapat membantu guru dalam melaksanakan pembelajaran sehingga dapat meningkatkan minat dan kemampuan siswa dalam proses belajar. Kegiatan ini diharapkan dapat menjadi salah satu program unggulan yang  dapat  menjadi  salah  satu  sumber  belajar yang dapat digunakan sekolah.