Claim Missing Document
Check
Articles

Found 16 Documents
Search

ANALISIS DAN PENERAPAN TRACER STUDY BERBASIS WEB DENGAN MENGGUNAKAN METODE RAPID APPLICATION DEVELOPMENT DI BAGIAN UNIT K2UIBA IKEST MUHAMMADIYAH PALEMBANG Fadillah, Arif; Rudiansyah, Rudiansyah
JUTIM (Jurnal Teknik Informatika Musirawas) Vol 10 No 1 (2025): JUTIM (Jurnal Teknik Informatika Musirawas) JUNI
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v10i1.2619

Abstract

Abstrak Tracer Study metode yang sering digunakan untuk melacak keberadaan alumni dan mengevaluasi keberhasilan mereka dalam memasuki dunia kerja, termasuk relevansi pendidikan yang mereka terima dengan pekerjaan yang mereka lakukan. Bagi Universitas Muhammadiyah Ahmad Dahlan Palembang, khususnya di bagian Unit Puskema, penerapan tracer study penting untuk memantau keberlanjutan karier alumni di bidang kesehatan serta untuk meningkatkan kualitas layanan pendidikan dan pelatihan. Namun, saat ini pemantauan alumni belum sepenuhnya terstruktur sehingga kurang efektif dalam mengumpulkan data jangka panjang. Tujuan dari penelitian ini adalah untuk menganalisis dan menerapkan sistem tracer study berbasis web di Puskema Universitas Muhammadiyah Ahmad Dahlan Palembang. Metode dalam penelitian ini adalah studi kasus, yang melibatkan pengumpulan data melalui observasi, wawancara, dan melakukan analisis penilaian menggunakan Framework PIECES. Kemudian rancangan metode menggunakan Metode RAD, dengan menggunakan metode RAD diharapan dapat meningkatkan pengelolaan data alumni serta memberikan informasi yang akurat dan real-time untuk pengambilan keputusan dalam pengembangan kualitas pendidikan dan layanan kesehatan.
Penerapan Sistem Informasi E-Document Akreditasi Program Studi Dengan Penggunakan Metode Rapid Application Development Di Bagian Unit Lembaga Penjamin Mutu Ikest Muhammadiyah Palembang Fadillah, Arif; Apriansyah, Apriansyah
Jurnal Digital: Telnologi Informasi Vol 8, No 1 (2025): Jurnal Digital Teknologi informasi
Publisher : Universitas Muhammadiyah Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32502/digital.v8i1.9500

Abstract

Penerapan sistem informasi e-document dalam proses akreditasi program studi di Unit Lembaga Penjamin Mutu (LPM) IKesT Muhammadiyah Palembang diharapkan dapat meningkatkan efisiensi, akurasi, dan transparansi dalam pengelolaan dokumen akreditasi yang selama ini dilakukan secara manual. Penelitian bertujuan untuk merancang Sistem Informasi E-Document berbasis web yang mengoptimalkan akreditasi dalam 9 standar dengan menerapkan 2 metode yaitu pengambilan record  melalui  database  sistem  yang  terintegrasi  dengan  unit  lain,  dan  input  upload dokumen prodi. Metode dalam penelitian ini adalah studi kasus, yang melibatkan pengumpulan data melalui observasi, dan wawancara. Kemudian rancangan metode menggunakan Metode RAD. Kesimpulan Penelitian adalah penerapan sistem e-document dengan metode RAD di LPM IKesT Muhammadiyah Palembang memberikan kontribusi signifikan terhadap perbaikan manajemen dokumen akreditasi program studi. Selain itu, diharapkan dapat menjadi referensi bagi institusi pendidikan lain dalam penerapan sistem serupa untuk mendukung proses akreditasi yang lebih efisien dan efektif. 
Enhancing Intrusion Detection Using Random Forest and SMOTE on the NSL‑KDD Dataset Saputra, Febri Hidayat; Ilham, Ilham; Rizal, Muhammad; Wisda, Wisda; Wanita, First; Mursalim, Mursalim; Fadillah, Arif
Journal of System and Computer Engineering Vol 6 No 3 (2025): JSCE: July 2025
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v6i3.2056

Abstract

Intrusion Detection Systems (IDS) play a crucial role in identifying suspicious activities on computer networks. However, a major challenge in developing machine learning-based IDS is the issue of class imbalance, where attacks—being minority classes—are often overlooked by classification models. This study aims to construct an intrusion detection system based on the Random Forest algorithm integrated with the Synthetic Minority Over-sampling Technique (SMOTE) to address this problem. The NSL-KDD dataset is used for evaluation, with the data split into 80% for training and 30% for testing. Experiments include Random Forest-based feature selection and performance evaluation using accuracy, precision, recall, and F1-score metrics. The results show that the Random Forest–SMOTE combination achieves an accuracy of 99.78%, precision of 99.70%, recall of 99.88%, and an F1-score of 99.79%. The confusion matrix indicates a very low rate of false positives and false negatives. Additionally, selecting the most influential features such as src_bytes and dst_bytes improves model efficiency. Thus, the integration of Random Forest and SMOTE proves to be effective in enhancing detection sensitivity toward attacks without compromising model precision. This approach offers a significant contribution to the development of adaptive, accurate, and deployable IDS in real-world network environments.
Enhancing Flood Prediction Using Hybrid LSTM-Transformer Deep Learning Approach Fadillah, Arif; Rizal H, Muhammad; Mursalim, Mursalim
Journal of System and Computer Engineering Vol 6 No 3 (2025): JSCE: July 2025
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v6i3.2083

Abstract

Flood prediction is crucial for effective disaster management, yet it remains a complex challenge due to the nonlinear nature of meteorological processes. This study develops and evaluates a novel hybrid model that integrates Long Short-Term Memory (LSTM) networks and Transformer attention mechanisms to enhance predictive accuracy for rainfall-based flood forecasting. Using extensive Australian weather data collected from 49 stations over a decade (2007-2017), the model incorporates comprehensive feature engineering, including derived meteorological indicators, rolling statistical measures, and temporal lag features. The hybrid LSTM-Transformer architecture achieved superior precision (77.69%) and high accuracy (84.57%) compared to a Random Forest baseline model. Confusion matrix analysis illustrated the hybrid model’s strength in reducing false alarms, indicating a conservative yet highly reliable predictive performance. Feature correlation analysis revealed important relationships among temperature, humidity, pressure, and rainfall, highlighting the complexity of meteorological interactions. The findings demonstrate the effectiveness of integrating sequential and global temporal modeling for flood prediction, providing valuable guidance for operational forecasting systems and disaster preparedness strategies. This research contributes significantly to existing flood forecasting methodologies and suggests promising directions for future enhancements.
ANALISIS DAN PERANCANGAN SISTEM PAKAR MENDIAGNOSA PENYAKIT DARAH TINGGI MENGGUNAKAN METODE BACKWARD CHAINING Fendri Martadinata; Arif Fadillah; Dendra; Egga Asoka
jurnal kesehatan terapan sains dan teknologi Vol 3 No 2 (2025): Journal Health Applied Science And Technology (JHAST)
Publisher : IKesT Muhammadiyah Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52523/jhast.v3i2.80

Abstract

Hypertension, commonly known as a "silent killer," requires early detection and accurate diagnosis to prevent serious complications. This is especially crucial in primary healthcare facilities like Puskesmas Abab in Penukal Abab Lematang Ilir (PALI), where access to specialists is limited. This research developed a web-based expert system for hypertension diagnosis using the backward chaining method. The goal was to expedite medical decision-making, enhance efficiency, and improve diagnostic accuracy. Using a qualitative prototyping methodology (involving observation, literature reviews, and interviews with healthcare professionals), the system was designed with a user interface, a knowledge base, and an explanation module. Testing results showed that the system accurately diagnoses hypertension based on symptoms, aligning very well with actual medical evaluations. This confirms the effectiveness of the backward chaining method in increasing diagnostic speed and accuracy. The system also has the potential for further development to include other diseases and integrate with national health information systems
IMPLEMENTATION OF THINKING DESIGN FOR OPTIMIZING THE UI/UX OF THE ORDERING CHATBOT AT WARUNG PEMPEK MANG HANIF: IMPLEMENTATION OF THINKING DESIGN FOR OPTIMIZING THE UI/UX OF THE ORDERING CHATBOT AT WARUNG PEMPEK MANG HANIF kartina, Riza; Arif Fadillah; Rudiansyah
jurnal kesehatan terapan sains dan teknologi Vol 3 No 2 (2025): Journal Health Applied Science And Technology (JHAST)
Publisher : IKesT Muhammadiyah Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52523/jhast.v3i2.91

Abstract

In the ever-growing digital era, Warung Pempek Mang Hanif faces challenges in managing an increasingly complex ordering process due to the increasing number of customers. The current manual ordering system has limitations such as recording errors, delays, and customer dissatisfaction. This research aims to optimize the UI/UX of an ordering chatbot by applying a Design Thinking approach. Design Thinking methodology is applied to understand user needs and preferences, design innovative solutions, and ensure optimal user experience. Chatbot development was carried out using the Eclipse IDE and the Java programming language, focusing on main features such as order acceptance, menu information and order status. This research shows that the application of Design Thinking can produce responsive, intuitive and efficient chatbots, thereby increasing customer satisfaction and reducing staff workload.