Garuda - Garba Rujukan Digital

Sistem Keamanan Ruang Server Rumah Sakit Swasta Berbasis Mikrokontroler Arduino dan Android Angelina Hadriani Hadriyanto; Agung Budi Susanto; Abu Khalid Rivai
IKRAM: Jurnal Ilmu Komputer Al Muslim Vol. 2 No. 1 (2023): IKRAM: Jurnal Ilmu Komputer Al Muslim
Publisher : LPPM STMIK AL MUSLIM

Show Abstract | Download Original | Original Source | Check in Google Scholar

The security of the server room is very important, considering that a lot of important data is stored in it, the server room door locking system which still uses conventional keys is very vulnerable to break-ins into the server room because conventional keys are very easy to duplicate, besides that the use of conventional keys is very risky of human error because It's human nature to forget to put keys all over the place. Besides that, maintenance work that is usually done by IT staff to check the condition of the server room is also hampered by having to go back and forth to security to borrow and return keys before and after carrying out routine maintenance activities. By utilizing the development of Android and Arduino smartphone technology in this study, the authors aim to make SK applications and SMS alarms to replace the current server room security system which is still manual using conventional keys. With this new system, the unlocking process can be through an application embedded in an Android smartphone. by pressing the buttons provided in the application. The research method used is the Prototype method. The way this security system works is that the user or users must open the application on Android and then connect it to the Bluetooth module. After the application and the Bluetooth module are connected, the user only has to choose whether to open or lock the door according to the options in the image in the application, and for the workings of the security system. sms alarm if the PIR sensor detects the movement of people in the server room then the PIR sensor will forward the command to GSM module to send sms to smartphone user.

Optimization of Employee Burnout Prediction Using Explainable Boosting Machine, Long Short-Term Memory, and Extreme Gradient Boosting Methods in Human Resource Management at PT. XYZ Syahrul Kahfi; Sudarno Wiharjo; Abu Khalid Rivai
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5772

- Employee burnout threatens organizational sustainability through reduced productivity, compromised mental health, and elevated turnover rates. Early detection remains critical for maintaining workforce stability. We address burnout prediction optimization at PT. XYZ through three advanced machine learning models: Explainable Boosting Machine (EBM), Long Short-Term Memory (LSTM), and Extreme Gradient Boosting (XGBoost). Our methodology incorporates structured data preprocessing, model construction, training protocols, and rigorous performance evaluation. We assessed models using MAE, RMSE, and R² for regression tasks, alongside Accuracy, Precision, Recall, F1-score, Confusion Matrix, Feature Importance, and ROC curves for classification. Cross-validation ensured robust evaluation, with burnout labels derived from established psychosocial factor assessments. Results reveal LSTM's superior performance at 0.99 accuracy, followed by EBM (0.96) and XGBoost (0.95). LSTM demonstrates exceptional capability in identifying subtle burnout patterns, while EBM delivers high interpretability regarding causal factors. These findings offer a data-driven framework for human resource management, enabling precise, proactive intervention through evidence-based decision-making.

PROGRAM PENGABDIAN KEPADA MASYARAKAT: OPTIMASI PENGGUNAAN ARTIFICIAL INTELIGENT DAN PENCEGAHAN ADIKSI DIGITAL Muhammad Farras Ma’ruf; Ahmad Fauzi; Andrey Gustaph Setiawan; Defri Salsabila Oktaviani; Desi Sihamita; Luki Handoko; Risa Nur Aisiyah; Abu Khalid Rivai; Mardiyanto
Abdi Jurnal Publikasi Vol. 4 No. 6 (2026): Juni
Publisher : Abdi Jurnal Publikasi

Show Abstract | Download Original | Original Source | Check in Google Scholar

The Industrial Revolution 4.0 has brought digital transformation that drives a shift from automated systems toward interconnected intelligent systems. In this context, Generative Artificial Intelligence (Gen AI) plays a significant role across various sectors, including education, through its ability to process multiple data types and deliver rapid analysis. Although Gen AI has been widely utilized by academic communities, its application in the learning process requires careful supervision. A study conducted by Kosmyna et al. found that students who continuously rely on Gen AI for problem-solving in learning experience a cumulative decline in their learning abilities. Based on these findings, a community service initiative was conducted at SMP Putra Pertiwi using two main approaches: first, providing counseling to students and educators regarding the negative impacts of uncontrolled Gen AI usage; second, designing a Gen AI-based system blueprint that continues to promote effective learning while granting schools full control over the management of learning resource access. This initiative is expected to serve as a model for the responsible implementation of AI technology in educational environments.

Analisis Transaksi Fraud QRIS pada Industri Perbankan Switching dengan Data Mining Metode Klasifikasi menggunakan Aplikasi Orange Astried Nirmala Safitri; Agung Budi Susanto; Abu Khalid Rivai
Jurnal Unggul Teknologi dan Informatika (JUTIKA) Vol 1 No 1 (2025): Jurnal Unggul Teknologi dan Informatika - Desember
Publisher : YAYASAN KAYYIS MULIA JAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar

Perkembangan sistem perbankan semakin besar sejalan dengan banyaknya sebagian orang yang memanfaatkan hal tersebut. Banyaknya transaksi mencurigakan di sistem perbankan yang mengindikasi adanya kriminalitas, maka bisnis perbankan memerlukan pengecekan semua data yang ada. QRIS menjadi channel transaksi paling banyak digunakan saat ini. Seiring dengan berkembangnya UMKM dan penjual yang menggunakan QRIS sebagai media pembayaran membuat berkembangnya transaksi QRIS di sistem perbankan switching. Tujuan peneitian ini untuk melakukan pengecekan dari transaksi mencurigakan di sistem perbankan yang mengindikasi adanya transaksi fraud. Banyaknya transaksi setiap harinya membuat sistem yang sudah ada harus dapat menyediakan data yang cepat, tepat dan real time. Keterbatasan SDM dan waktu yang diperlukan untuk pengecekan data transaksi yang cukup banyak sehingga dibutuhkan metode pengecekan yang cepat dan akurat agar pengecekan lebih efektif dan efisien. Data mining dengan aplikasi orange digunakan untuk menyediakan data-data yang dibutuhkan dengan metode klasifikasi yang dapat mengidentifikasi data fraud berdasarkan pola-pola dari sekumpulan data transaksi QRIS yang cukup besar. Metode penelitian digunakan algoritma Naive Bayes Classifier, K-Nearest Neighbors dan Decision Tree untuk mempermudah user mendapatkan data yang dibutuhkan. Dengan membuat matriks (pola) terkait indikator transaksi anomali yang diperlukan, pengecekan dengan menggunakan beberapa metode ini bertujuan sebagai pilihan analisa yang dapat dipilih untuk proses deteksi data-data yang terindikasi fraud. Pada penelitian ini didapatkan hasil penelitian menunjukkan tingkat akurasi maksimal pada penggunaan metode algoritma K-Nearest Neighbors dengan nilai 0,991. Untuk hasil dari algoritma Naive Bayes Classifier dengan nilai 0,961 dan algoritma Decision Tree dengan nilai 0,990 Hasil penelitian ini dapat digunakan pada perusahaan switching untuk membantu tim operasional dalam mendapatkan data untuk kebutuhan laporan perusahaan.

Analisis Tren Dan Topik Populer Tugas Akhir Mahasiswa Teknik Informatika Menggunakan Bertopic Dan Lda Studi Kasus: Universitas Mercu Buana Suharyadi; Sajarwo Anggai; Abu Khalid Rivai
Jurnal Informatika dan Komputer Vol 16 No 1 (2026): April
Publisher : Sekolah Tinggi Ilmu Komputer PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55794/jikom.v16i1.349

In recent years, there has been little systematic mapping of trends and popular topics in student final projects, particularly in the field of Information Technology at Mercu Buana University. This is important because identifying trends can provide insight into the direction of scientific development and student research interests. This study aims to analyze the dominant trends and topics of the past few years in the final projects of Information Technology students at Mercu Buana University. The research object consists of a collection of titles and abstracts of student final projects from 2019 to 2024, totaling 1677 datasets. The data was collected through internal faculty documentation and compiled into a text-based dataset. The analysis process included the stages of preparation, text pre-processing, feature extraction, and the application of two topic modeling methods with BERTopic and LDA. BERTopic uses transformer-based representation and semantic clustering, while LDA utilizes a probabilistic distribution approach. The evaluation was conducted by comparing topic coherence and prediction accuracy to assess the quality and relevance of the results produced by each method. The results showed that there were 15 main topics. Model evaluation was conducted using a coherence score of 0.4 for LDA with an accuracy rate of 100%, while BERTopic had a coherence score of 0.39 with an accuracy rate of 86.01%.

STUDI IMPLIMENTASI SNI ISO/IEC 27001:2022 UNTUK MANAJEMEN RISIKO DATA CENTER BBMKG WILAYAH II Nunuk Irawati; Agung Budi Susanto; Abu Khalid Rivai
INTECOMS: Journal of Information Technology and Computer Science Vol. 9 No. 1 (2026): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/n7pjjt56

Sesuai dengan PP No.95 Tahun 2018 (SPBE) dan Peraturan BMKG No.4 Tahun 2020, informasi merupakan aset krusial bagi BBMKG Wilayah II. Sebagai institusi yang bertanggung jawab atas data meteorologi, klimatologi, dan geofisika, (seperti info gempa dan tsunami) akurasi dan keamanan data sangat vital bagi keselamatan publik. Berbagai ancaman yang terjadi seperti terjadinya web defacement, sering terjadinya gangguan kelistrikan yang merusak server sehingga dapat menghambat layanan yang harus real time dan kurangnya kesadaran keamanan informasi dikalangan pegawai. Penelitian ini bertujuan untuk menganalisis kesiapan dan keandalan aset serta dokumen Data Center BBMKG Wilayah II, mengidentifikasi ancaman risiko keamanan informasi keberlangsungan yang harus dimitigasi dan dikontrol, serta melakukan implementasi kerangka kerja SNI ISO/IEC 27001:2022 dalam manajemen risiko keamanan informasi. Metode yang digunakan dengan pengumpulan data melalui wawancara, observasi, studi dokumen, dan Focus Group Discusion (FGD). Penelitian ini menghasilkan 30 risiko yang harus dimitigasi dengan sistem pengendalian dari SNI ISO/IEC 27001:2022 yang meliputi 3 (tiga) kategori risiko, yaitu keamanan, infrastruktur, dan sumberdaya manusia (SDM), dimana salah satu terindikasi adalah belum adanya kebijakan SMKI dan kebijakan operasional keamanan informasi yang melanggar Klausul 5.2 - Kebijakan. Setelah dilakukan penanganan risiko selama 3 bulan diantaranya dengan pembuatan dokumen SMKI dan dokumen operasional keamanan informasi, hasil pengujian menunjukkan sejumlah 0 NC mayor, 4 NC minor, dan 9 OFI, yang menggambarkan sangat baik untuk status SMKI di Data center BBMKG Wilayah II.

PREDIKSI SUHU MAKSIMUM BERBASIS DEEP LEARNING DENGAN MODEL LONG SHORT-TERM MEMORY DAN GATED RECCURENT UNIT (STUDI KASUS WILAYAH CIPUTAT) Hesti Rahayuningsih; Tukiyat Tukiyat; Abu Khalid Rivai
INTECOMS: Journal of Information Technology and Computer Science Vol. 9 No. 1 (2026): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/f9e1d633

Prediksi suhu maksimum merupakan hal yang penting dalam kajian meteorologi karena berpengaruh terhadap berbagai sektor, seperti pertanian, kesehatan masyarakat, manajemen energi, dan perencanaan wilayah. Wilayah Ciputat menjadi lokasi yang relevan untuk studi prediksi iklim lokal, karena pernah sebagai wilayah dengan suhu ekstrem sebesar 37,2 °C pada 17 April 2023. Penelitian ini bertujuan untuk membandingkan kinerja model Long Short-Term Memory (LSTM) dan Gated Recurrent Unit (GRU) dalam memprediksi suhu maksimum harian di wilayah Ciputat serta menentukan model dengan performa terbaik. Data yang digunakan meliputi suhu maksimum harian, curah hujan, kelembapan, dan tekanan udara periode 2009–2025 yang diperoleh dari BMKG Wilayah II Ciputat, sehingga merepresentasikan variabilitas musiman dan pola iklim tropis jangka panjang. Evaluasi model dilakukan menggunakan metrik Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Coefficient of Determination (R²), dan Mean Absolute Percentage Error (MAPE). Hasil evaluasi menunjukkan model LSTM dengan performa yang lebih baik dalam memprediksi suhu maksimum dibandingkan model GRU berdasarkan nilai MAE, RMSE, R² dan MAPE. Hasil penelitian ini diharapkan dapat mendukung pengembangan metode prediksi suhu berbasis deep learning yang lebih akurat serta menjadi referensi dalam pengambilan keputusan terkait mitigasi risiko iklim. Kata Kunci: Prediksi suhu maksimum, LSTM, GRU, Deep learning, Ciputat.

Optimization of Employee Burnout Prediction Using Explainable Boosting Machine, Long Short-Term Memory, and Extreme Gradient Boosting Methods in Human Resource Management at PT. XYZ Syahrul Kahfi; Sudarno Wiharjo; Abu Khalid Rivai
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5772

- Employee burnout threatens organizational sustainability through reduced productivity, compromised mental health, and elevated turnover rates. Early detection remains critical for maintaining workforce stability. We address burnout prediction optimization at PT. XYZ through three advanced machine learning models: Explainable Boosting Machine (EBM), Long Short-Term Memory (LSTM), and Extreme Gradient Boosting (XGBoost). Our methodology incorporates structured data preprocessing, model construction, training protocols, and rigorous performance evaluation. We assessed models using MAE, RMSE, and R² for regression tasks, alongside Accuracy, Precision, Recall, F1-score, Confusion Matrix, Feature Importance, and ROC curves for classification. Cross-validation ensured robust evaluation, with burnout labels derived from established psychosocial factor assessments. Results reveal LSTM's superior performance at 0.99 accuracy, followed by EBM (0.96) and XGBoost (0.95). LSTM demonstrates exceptional capability in identifying subtle burnout patterns, while EBM delivers high interpretability regarding causal factors. These findings offer a data-driven framework for human resource management, enabling precise, proactive intervention through evidence-based decision-making.

Analysis and Development of Transformer (DistilBERT)-LSTM and Reinforcement Learning Models for Adaptive Phishing Email Detection Farizal Herry Saputra; Kahfi Heryandi Suradiraja; Abu Khalid Rivai
SISTEMASI Vol 15, No 7 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i7.6432

Phishing detection faces two major challenges: performance degradation caused by domain shift and a heavy reliance on costly labeled data. This study proposes an adaptive phishing email detection model that integrates a hybrid DistilBERT–LSTM architecture with a Proximal Policy Optimization (PPO)-based Reinforcement Learning agent. The proposed methodology employs a multi-stage transfer learning framework using three datasets: Enron as the source domain, Phishing_Validation for supervised domain adaptation, and CEAS_08 to simulate an unlabeled data stream through pseudo-labeling. Experimental results demonstrate excellent performance on the source-domain dataset (Enron), achieving an F1-score of 0.9935. However, the model's performance declined on the Phishing_Validation dataset (F1-score = 0.9067), confirming the impact of domain shift. By incorporating the PPO agent, the proposed model autonomously recovered its performance on the CEAS_08 dataset, achieving an F1-score of 0.9516, an accuracy of 0.9468, and a ROC–AUC of 0.9915. The stability of the adaptation process was validated by the convergence of the Kullback–Leibler (KL) divergence to 0.000173, although a minor overconfidence of approximately 5% was observed between the model's confidence estimates and the ground-truth labels. These findings demonstrate the effectiveness of PPO in mitigating domain shift within an unsupervised adaptation environment. Future research should focus on improving model calibration and exploring multimodal feature integration to further strengthen cybersecurity defenses.

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search