Article Per Year (5 Year)
p-Index From 2021 - 2026
1.583
P-Index
This Author published in this journals
All Journal SOSIOLOGI NUSANTARA Jurnal Teknologi Terpadu Technologia: Jurnal Ilmiah Jurnal Pengembangan Sistem Informasi dan Informatika Djtechno: Jurnal Teknologi Informasi Kharisma Tech Jurnal Inovasi Teknologi Terapan JURNAL FLOBAMORATA MENGABDI Dharma Nusantara: Jurnal Ilmiah Pemberdayaan dan Pengabdian kepada Masyarakat
Zain, M Syafrizal
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Arts Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Mechanical Engineering Social Sciences Other

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 10 Documents
Search

 1 
A GAN-Based Approach for Identifying Fake Accounts on Twitter Zain, M Syafrizal; Swengky, Better; Wisesa, Bradika Almandin; Putri, Vivin Mahat
Jurnal Pengembangan Sistem Informasi dan Informatika Vol. 6 No. 1 (2025): Jurnal Pengembangan Sistem Informasi dan Informatika
Publisher : Training & Research Institute - Jeramba Ilmu Sukses

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47747/jpsii.v6i1.2671

Abstract

The multiple security threats on the network make the need for robust security measures a major concern. The increasing presence of fake accounts and malicious actors on online platforms poses significant challenges, requiring sophisticated detection techniques to maintain network integrity. To address these issues, we propose a novel method for detecting fake accounts by leveraging Generative Adversarial Networks (GANs). By analyzing data extracted from platform APIs, our approach leverages the unique characteristics of GANs to improve the accuracy and efficiency of the detection process. In this study, we develop a GANs-based model specifically designed to detect fake accounts. The model is built through several key stages: first, we collect a comprehensive dataset, then perform data processing and preprocessing to make it suitable for machine learning applications. Next, the model is trained using various hyperparameters to optimize accuracy, thus learning the underlying patterns associated with fake accounts. After the training stage, the model is tested on previously unseen data to evaluate its generalization and performance in real-world scenarios. Experimental results show that our model achieves a threshold value of 0.0054779826. This value plays a crucial role in determining the accuracy of the detection system. The smaller the threshold value, the higher the model accuracy, as it shows a lower error rate in distinguishing between real and fake accounts. The ability of GANs-based models to adaptively learn from data during the training process contributes to high precision in detecting anomalies as well as minimizing false positives.
Prediksi Harga Saham Malindo Feedmill Tbk. (MAIN) Menggunakan Jaringan Saraf Tiruan Long Short-Term Memory (LSTM) Putri, Vivin Mahat; Zain, M Syafrizal; Darma, Satria Agus
Jurnal Pengembangan Sistem Informasi dan Informatika Vol. 6 No. 3 (2025): Jurnal Pengembangan Sistem Informasi dan Informatika
Publisher : Training & Research Institute - Jeramba Ilmu Sukses

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47747/jpsii.v6i3.2789

Abstract

Stock price prediction presents a significant yet intricate challenge in financial forecasting, primarily due to volatile market dynamics and the nonlinear nature of data. This study investigates the efficacy of the Long Short-Term Memory (LSTM) model, a specialized Recurrent Neural Network (RNN), for forecasting the stock price of PT. Malindo Feedmill, Tbk., a publicly listed agribusiness firm on the Indonesia Stock Exchange. A five-year historical dataset of daily stock prices (open, high, low, close, volume) was utilized. Pre-processing involved data normalization, the application of a sliding window approach, and partitioning the data into training and testing subsets. The LSTM model was trained on sequential closing prices to effectively learn and model long-term dependencies inherent in stock price movements. The model's predictive performance was rigorously assessed using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics. Our results reveal that the LSTM model adeptly captures price trends, yielding a low MAPE of 3.47% on the test set. Comparative analysis against traditional models like linear regression confirms that LSTM provides superior accuracy and robustness, especially under volatile market conditions. This research highlights the significant potential of deep learning models in facilitating smarter investment decisions within the Indonesian agricultural sector. Subsequent work will aim to integrate sentiment analysis and macroeconomic indicators to further improve real-time predictive accuracy.
Pelatihan Membuat Aplikasi Tanpa Coding Bagi Siswa SMK Yapensu Sungailiat Bradika Almandin Wisesa; Vivin Mahat Putri; Indra Irawan; M. Syafrizal Zain; Putri Armilia Prayesy
Dharma Nusantara: Jurnal Ilmiah Pemberdayaan dan Pengabdian kepada Masyarakat Vol. 3 No. 2 (2025): Dharma Nusantara: Jurnal Ilmiah Pemberdayaan dan Pengabdian kepada Masyarakat
Publisher : LPPM Universitas Bhinneka Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/dharma.v3i2.2154

Abstract

Kegiatan pengabdian masyarakat berbentuk pelatihan pembuatan aplikasi mobile berbasis no-code sukses digelar untuk siswa SMK Yapensu Sungailiat dengan memanfaatkan Glide Apps—platform yang dipilih berkat kemudahan penggunaan dan fitur gratisnya yang cukup untuk aplikasi sederhana tanpa perlu coding. Prosesnya meliputi persiapan administratif, survei pra-pelatihan melalui kuesioner, penyuluhan disertai demonstrasi dan praktik langsung, hingga evaluasi pasca-pelatihan; peserta berhasil mengembangkan Aplikasi Siswa Yapensu menggunakan Glide Tables dengan antarmuka mirip Excel. Evaluasi menunjukkan rata-rata 80 % responden memberikan penilaian “sangat baik” dan “sangat sesuai”, menandakan respons positif serta kemampuan peserta menyelesaikan seluruh tahap pengembangan aplikasi secara mandiri.
PENERAPAN METODE PROTOTYPE DALAM PENGEMBANGAN SISTEM PERPUSTAKAAN DIGITAL DI POLMAN BABEL affani, khairunnisa shabira; Rindri, Yang Agita; Zain, M Syafrizal
Technologia : Jurnal Ilmiah Vol 17, No 1 (2026): Technologia (Januari)
Publisher : Universitas Islam Kalimantan Muhammad Arsyad Al Banjari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31602/tji.v17i1.20944

Abstract

Perkembangan teknologi digital telah membawa dampak besar terhadap inovasi di dunia pendidikan, salah satunya dalam penyediaan layanan perpustakaan. Di Polman Babel, penggunaan sistem perpustakaan digital masih menghadapi kendala karena belum terintegrasi secara menyeluruh dan belum mendukung pengelolaan informasi secara optimal. Untuk mengatasi hal tersebut, penelitian ini mengembangkan sistem perpustakaan digital menggunakan metode prototype, yang memungkinkan proses pengembangan dilakukan secara bertahap dengan melibatkan partisipasi pengguna pada setiap fase. Berdasarkan hasil black box testing, seluruh fungsi utama sistem berjalan sesuai rancangan, sedangkan hasil User Acceptance Testing (UAT) dari 31 responden menunjukkan tingkat penerimaan sebesar 88,4%. Dengan hasil tersebut, sistem perpustakaan digital ini dinyatakan layak digunakan serta berpotensi meningkatkan efisiensi dan akses layanan informasi di Polman Babel.
Penanaman Karakter Peduli Lingkungan Pada Siswa Kelas 4 SD Melalui Kegiatan Penanaman Sukulen dalam Implementasi Pembelajaran P5 Lesta, Lesta; Ningsih, Riski Meliya; Ali, Hendrik; Wathan, Muhammad Hizbul; Zain, Muhammad Syafrizal
Jurnal Flobamorata Mengabdi Vol. 3 No. 2 (2025): JURNAL FLOBAMORATA MENGABDI
Publisher : Program Studi Pendidikan Guru Sekolah Dasar, Fakultas Keguruan dan Ilmu Pendidikan, Universitas Muhammadiyah Kupang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51494/jfm.v3i2.2788

Abstract

Permasalahan lingkungan seperti berkurangnya kepedulian terhadap lingkungan, polusi udara, penumpukan sampah plastik, dan berkurangnya ruang hijau mendorong pentingnya pendidikan lingkungan sejak dini pada siswa SD. Pengabdian ini bertujuan menganalisis efektivitas kegiatan penanaman sukulen sebagai media pembelajaran berbasis proyek untuk menanamkan karakter peduli lingkungan pada 25 siswa kelas 4 SDN 3 Sungailiat melalui implementasi Proyek Penguatan Profil Pelajar Pancasila (P5). Metode partisipatif mencakup edukasi jenis dan manfaat sukulen, persiapan alat-bahan, simulasi penanaman, pelatihan perawatan, serta observasi perilaku dan keterampilan siswa. Hasil menunjukkan 85% siswa antusias mengikuti seluruh tahapan dengan banyak pertanyaan yang mencerminkan rasa ingin tahu terhadap alam, 100% membawa tanaman pulang, dan 68% berkomitmen merawat secara mandiri, sementara 44% sangat terampil serta 56% terampil dalam teknik penanaman. Tantangan utama adalah konsistensi perawatan yang memerlukan kolaborasi pengabdi, guru, dan orang tua. Model hands-on dengan sukulen ini dapat direplikasi di sekolah lain untuk memperluas penghijauan rumah tangga dan membentuk kebiasaan peduli lingkungan berkelanjutan, sekaligus memperkuat kurikulum P5 melalui program pengabdian rutin yang melibatkan komunitas.
Strategi Pengembangan Kampung Adat Gebong Memarong (Kampung Adat Gebong Memarong) sebagai Destinasi Pariwisata Berbasis Masyarakat (CBT) Budaya di Kabupaten Bangka Muhamad Galy Njoman Ari Pribowo; M Syafrizal Zian; Redi Alamsyah; Ganif Nur Annafi
Jurnal Sosiologi Nusantara Vol 11 No 2 (2025): Vol 11 No.2
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsn.11.2.238-261

Abstract

Kampung Adat Gebong Memarong in Bangka Regency represents a cultural heritage of the Bangka Malay community and holds significant potential as a cultural-based tourism destination. However, tourism management in this area remains suboptimal due to low community involvement and the absence of an integrated development strategy. This study aims to formulate development strategies for Kampung Adat Gebong Memarong as a sustainable Community-Based Tourism (CBT) destination that empowers the local community. A qualitative approach with a case study design was employed, integrating the Participatory Rural Appraisal (PRA) method to explore community perspectives and aspirations in a participatory manner. Data were collected through in-depth interviews, participatory observations, focus group discussions (FGDs), and community mapping. The data were analyzed using descriptive SWOT analysis, along with Internal Factors Analysis Summary (IFAS) and External Factors Analysis Summary (EFAS). The findings reveal that community involvement is still symbolic and limited to ceremonial activities. However, the PRA method proved effective in fostering a sense of ownership and collective responsibility among the community. The SWOT analysis identified strengths in cultural authenticity and community solidarity, while weaknesses were found in human resource and institutional capacity. The conclusion of this study emphasizes the importance of strengthening community capacity, establishing multi-stakeholder partnerships, and integrating cultural narratives into digital promotion. This study contributes to the development of an inclusive and sustainable tourism model based on local wisdom.
INTEGRASI GAME LITERASI PADA SISTEM PERPUSTAKAAN DIGITAL POLMAN BABEL khairunnisa affani; Yang Rindri; Syafrizal Zain
KHARISMA Tech Vol 21 No 1 (2026): KHARISMATech Journal
Publisher : STMIK KHARISMA Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55645/kharismatech.v21i1.659

Abstract

Layanan perpustakaan di perguruan tinggi memerlukan inovasi digital yang tidak hanya menyediakan akses informasi, tetapi juga mampu meningkatkan keterlibatan pengguna secara interaktif. Penelitian ini dilaksanakan untuk mengembangkan sistem perpustakaan digital yang terintegrasi dengan literasi permainan sebagai solusi terhadap rendahnya partisipasi siswa dalam memanfaatkan koleksi digital di Polman Babel. Sistem yang dirancang telah memadukan akses konten perpustakaan dengan mekanisme permainan yang menampilkan tantangan, perolehan poin, dan umpan balik langsung sebagai pemicu motivasi pengguna. Metode pengembangan yang diterapkan adalah prototipe, meliputi analisis kebutuhan, perancangan, pembuatan antarmuka, dan implementasi fitur utama. Pengujian sistem dilakukan melalui User Acceptance Test kepada pelajar sebagai pengguna akhir. Hasil pengujian menunjukkan bahwa seluruh fungsi bekerja sebagaimana direncanakan dan menghasilkan tingkat penerimaan sebesar 83%. Temuan ini mengumumkan bahwa integrasi game literasi memberikan pengalaman penggunaan yang lebih menarik dan berpotensi mendukung peningkatan literasi digital melalui layanan perpustakaan berbasis teknologi.
Evaluasi Usability Sistem Reservasi Ruang Kelas dan Laboratorium Berbasis Web dengan Pendekatan System Usability Scale Insyirah Hulul Aini; Yang Agita Rindri; M. Syafrizal Zain
Jurnal Teknologi Terpadu Vol 12 No 1 (2026): Juli, 2026
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v12i1.2575

Abstract

Higher education institutions play a strategic role in producing high-quality graduates and must therefore remain committed to providing adequate facilities and infrastructure for all members of the academic community. Effective facility management is crucial to ensuring the smooth delivery of educational activities, including the use of classrooms and laboratories, which are closely tied to lecture scheduling. At the State Manufacturing Polytechnic of Bangka Belitung, room management and scheduling have thus far been handled by individual departments. To keep pace with technological advancements, the campus has adopted the SEVIMA Edlink system, a platform designed to support various academic needs such as room scheduling, course scheduling, and campus announcements. However, the system has not yet fully addressed sudden schedule changes and class substitutions. This limitation creates difficulties for lecturers and students in locating replacement rooms due to the lack of real-time information on room availability. To address this issue, SIRUANGKU Polman Babel was developed as a dedicated solution. This research applies usability testing using the System Usability Scale (SUS) through questionnaires distributed to lecturers, administrative staff, and students. The results indicate a usability score of 82, classified as excellent, showing that the system performs well and is well accepted by users.
KLASIFIKASI BINER TINDAK PIDANA MENGGUNAKAN DECISION TREE DAN RANDOM FOREST DENGAN SMOTE PADA DATA SISTEM INFORMASI PENELUSURAN PERKARA PENGADILAN NEGERI KEBUMEN Rahmat Hidayat; Weri Sirait; M. Syafrizal Zain; Firdaus Firdaus; David Nugroho
Djtechno: Jurnal Teknologi Informasi Vol 7, No 2 (2026): Agustus
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/djtechno.v7i2.9299

Abstract

Kriminalitas merupakan salah satu permasalahan yang memengaruhi keamanan dan ketertiban masyarakat. Pemanfaatan data historis perkara melalui pendekatan machine learning dapat mendukung penyusunan strategi pencegahan kejahatan yang lebih terarah. Penelitian ini bertujuan mengembangkan model klasifikasi tindak pidana menggunakan data Sistem Informasi Penelusuran Perkara (SIPP) Pengadilan Negeri Kebumen periode 2021–2025. Permasalahan utama yang dihadapi adalah ketidakseimbangan distribusi kelas dan rendahnya performa klasifikasi pada data dengan banyak kategori tindak pidana. Untuk mengatasinya, sembilan rumpun tindak pidana direkonstruksi menjadi dua kategori, yaitu Kejahatan Kekerasan dan Kejahatan Non-Kekerasan. Penyeimbangan data dilakukan menggunakan Synthetic Minority Over-sampling Technique (SMOTE), sedangkan proses klasifikasi menggunakan algoritma Decision Tree dan Random Forest dengan skema stratified split 80:20. Hasil pengujian menunjukkan bahwa Decision Tree memberikan performa terbaik dengan akurasi 73,81%, presisi 79,08%, recall 73,81%, dan F1-score 75,45%, sedangkan Random Forest memperoleh akurasi 65,48%. Analisis feature importance menunjukkan bahwa tingkat pendidikan, pekerjaan, dan lokasi kejadian merupakan faktor yang paling berkontribusi dalam membedakan kategori tindak pidana. Hasil penelitian menunjukkan bahwa pendekatan yang diusulkan berpotensi mendukung pengambilan keputusan dalam penyusunan strategi pencegahan kejahatan berbasis data.
Aplikasi Hallotem Platform Konsultasi Dan Layanan Pengaduan Teknisi Elektro Medis Berbasis Mobile Syahrun Mubarok; Linda Fujiyanti; M. Syafrizal Zain
Jurnal Inovasi Teknologi Terapan Vol. 4 No. 2 (2026): Jurnal Inovasi Teknologi Terapan
Publisher : Politeknik Manufaktur Negeri Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33504/jitt.v4i2.394

Abstract

The advancement of information and communication technology has driven digital transformation across various sectors, including healthcare. RSUD Dr. Ir. H. Ibnu Saleh, MM, in Bangka Belitung faces challenges in managing medical equipment due to a limited number of technicians and a manual reporting system for equipment malfunctions. This leads to delays in repairs and impacts the quality of healthcare services. This study aims to design and develop the HalloTEM mobile application using the Prototipe method to address these issues. The application enables real-time reporting of medical equipment malfunctions, direct consultation with technicians, and efficient management of complaint data by administrators. Developed using the Flutter framework and supported by Laravel and MySQL technologies, the application offers features such as real-time notifications via WhatsApp or in-app, complaint status tracking, and periodic reporting. The results demonstrate that HalloTEM significantly improves efficiency, accuracy, and documentation in the medical equipment repair process, thereby enhancing the overall quality of healthcare services in the hospital.
Co-Authors affani, khairunnisa shabira Ali, Hendrik Better Swengky Bradika Almandin Wisesa Darma, Satria Agus David Nugroho Firdaus Firdaus Ganif Nur Annafi Indra Irawan Insyirah Hulul Aini khairunnisa affani Lesta, Lesta LINDA FUJIYANTI M. Hizbul Wathan Muhamad Galy Njoman Ari Pribowo Putri Armilia Prayesy Rahmat Hidayat Redi Alamsyah Riski Meliya Ningsih Syahrun Mubarok Vivin Mahat Putri Weri Sirait Yang Agita Rindri Yang Rindri