cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Yuhefizar
Contact Email
ephi.lintau@gmail.com
Phone
+628126777956
Journal Mail Official
ephi.lintau@gmail.com
Editorial Address
Jalan Jati Padang Raya No. 41 Jati Padang Pasar Minggu Jakarta Selatan Kode Pos 12540
Location
,
INDONESIA
Prosiding Seminar Nasional Sisfotek (Sistem Informasi dan Teknologi Informasi)
Published by Ikatan Ahli Informatika Indonesia
ISSN : -     EISSN : 25973584     DOI : -
Core Subject : Science,
Computer Science & IT
Seminar Nasional Sistem Informasi dan Teknologi (SISFOTEK) merupakan ajang pertemuan ilmiah, sarana diskusi dan publikasi hasil penelitian maupun penerapan teknologi terkini dari para praktisi, peneliti, akademisi dan umum di bidang sistem informasi dan teknologi dalam artian luas.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 471 Documents
 44   45   46   47   48 
Perancangan Sistem Informasi Manajemen Gudang Spare Part Berbasis Website Qosdu Sabil; Dian Ade Kurnia; Irfan Ali
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

The rapid growth of information technology has significantly influenced industrial operations, including the petrochemical sector, where efficient spare part management is crucial to ensure continuous production. This study aims to design a web-based spare part warehouse management information system capable of managing inventory data in real-time and reducing operational inefficiencies. The system was developed using the waterfall model through several stages: requirement analysis, system design, implementation, testing, and maintenance. The application was built using PHP programming language with the Laravel framework and MySQL database. The developed system features user authentication, role-based access control, equipment and part management, stock monitoring, issue and receipt transactions, and report generation in PDF format. Testing using the black box method indicates that all functionalities perform as expected. The system enhances efficiency in spare part tracking, minimizes delays in equipment maintenance, and supports accurate stock recording. Therefore, the proposed system can be an effective solution for improving warehouse management performance within the petrochemical industry.
Integrasi Data Science dan AI untuk Optimalisasi Layanan Pemerintahan: Literatur Review Kadek Dwi Mahardika Adnyana; I Made Oka Widyantara; NMAED Wirastuti; Ida Bagus Gede Manuaba
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

Indonesia’s digital government agenda establishes a policy backbone for data-driven and AI-enabled public services through the national Electronic-Based Government System (SPBE) and the One Data policy, while the Personal Data Protection Law (PDP) frames privacy-by-design obligations for public institutions. Building on international guidance (OECD’s G7 Toolkit; World Bank’s GovTech Maturity Index), this review synthesizes how Data Science (DS)—via reliable feature engineering and descriptive–predictive analytics—can be aligned with Artificial Intelligence (AI) for automation and decision support under public-sector accountability requirements. We identify recurrent enablers (interoperable data architecture, data governance, civil service capabilities, and MLOps) and barriers (data silos, legacy constraints, skills gaps, and explainability/ethics demands), and propose evaluation indicators that link model performance to service performance: service latency reduction, service quality, model fairness, and explainability. The contribution is a systems view that connects SPBE/Satu Data/PDP compliance to DS–AI operations across the lifecycle (governance ? pipeline/feature store ? training/validation ? deployment ? MLOps & audit), and a graduate-level research agenda on causal impact and federated collaboration across agencies.
Comparative Analysis of Deep Learning Models for Predicting Undernourishment Prevalence in Indonesia Sukma Evadini; Nadya Satya Handayani
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

Undernourishment constitutes a critical public health challenge in Indonesia with significant impacts on human resource quality and economic productivity. Accurate prediction of undernourishment prevalence is essential for supporting early warning systems and evidence-based food security policy planning. This study conducted comprehensive comparative analysis of three deep learning architectures—Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Transformer—for predicting Prevalence of Undernourishment (PoU) using longitudinal data from 38 Indonesian provinces spanning 2018-2024 with 242 observations. Methodology encompasses systematic preprocessing with minmaxscaler normalization, 70:15:15 dataset split, implementation of three models with hyperparameter tuning via grid search, and evaluation using RMSE, MAE, R², and MAPE. Results demonstrate Transformer achieves superior performance with RMSE 286.02, MAE 217.79, R² 0.8822, and MAPE 48.11%, outperforming GRU (RMSE 315.19, R² 0.8570) and LSTM (RMSE 356.81, R² 0.8167). Learning curves analysis reveals Transformer exhibits faster convergence and smaller training-validation gap (0.075) compared to LSTM (0.10) and GRU (0.105), indicating superior generalization. Although Transformer exhibits higher computational complexity (125,248 parameters), the accuracy-efficiency trade-off remains favorable with inference time of 8.6ms per sample. Transformer superiority stems from its multi-head self-attention mechanism effectively capturing long-term temporal dependencies and complex non-linear patterns. Findings provide evidence-based recommendations for implementing Transformer in food security early warning systems, supporting targeted resource allocation, and contributing to Sustainable Development Goals achievement related to zero hunger.
Perbandingan Kinerja Machine Learning Perekomendasi Tanaman Berdasarkan Data Iklim dan Kondisi Tanah Zidan Fahreza; Arwin Datumaya Wahyudi Sumari; Mila Kusuma
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

The selection of appropriate crop types according to agroclimatic conditions is a determining factor in the success of agricultural productivity. This study develops a machine learning-based crop recommendation system to classify 22 crop types based on seven agroclimatic parameters (N, P, K, temperature, humidity, pH, and rainfall). Four machine learning algorithms were compared for performance: K-Nearest Neighbors (KNN), Logistic Regression, Artificial Neural Network (ANN), and Decision Tree using a dataset of 2200 samples with an 80:20 split ratio for training and testing. Evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The research results show that KNN with k=13 achieved optimal performance with 98.18% accuracy, 98.28% precision, 98.18% recall, and 98.17% F1-score. This algorithm outperformed Logistic Regression (97.27%), ANN (96.59%), and Decision Tree (95.23%). Confusion matrix analysis identified that classification errors primarily occurred in crop pairs with similar agroclimatic characteristics such as lentil-chickpea and pigeonpeas-kidneybeans. KNN proved to be the most suitable model for implementing precision agriculture decision support systems in the Indonesian agricultural context by providing high accuracy and good generalization capability.
Prompting Adaptif pada LLM untuk Agen AI Rekomendasi Berita Generatif Bahasa Indonesia Tubagus Mohammad Akhriza; Ega Rudy Graha
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

In the era of disruptive technology, increasing reader engagement rates has become a key factor for online media industries in Indonesia, as it directly impacts advertising revenue. To address this challenge, generative AI has emerged as a critical technology that can deliver more personalized, relevant, and adaptive reading experiences. This study introduces a prototype news recommendation system based on an AI Agent designed to provide adaptive and sustainable reading experiences. The system integrates several components, including short-term and long-term memory, association, similarity, and a generative mechanism powered by Large Language Models (LLMs) at the core of the agent. The system was evaluated using two prompting approaches: static prompting, which keeps the recommendation prompt fixed, and adaptive prompting, in which generative recommendations clicked by users dynamically update the prompt fed to the LLM. The evaluation was conducted across six questionnaire-based metrics from 49 respondents: diversity, novelty, serendipity, curiosity, filter bubble, and context coherence. Six open-weight LLMs from the Ollama platform were tested and categorized as large LLMs (>100B parameters) and small LLMs (<20B parameters). The experimental results indicate that adaptive prompting consistently improves contextual coherence and reader curiosity. Large LLMs achieved the highest scores across nearly all metrics, particularly serendipity and curiosity, demonstrating their potential to deliver adaptive and sustainable reading experiences that increase reader engagement. These results provide important contributions to the development of agentic AI in news recommendation systems, paving the way for more adaptive, contextual, and personalized reader interactions.
Kategorisasi dan Visualisasi Semantik-Topik Berbasis LLM pada Refleksi Guru Koding Kecerdasan Artifisial Tubagus Mohammad Akhriza; bagus; Meivi Kartikasari; Syntia Widyayuningtias Putri Listio
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

The training program for Senior and Vocational High School teachers of the Coding and Artificial Intelligence (KKA) subject serves as a strategic effort to strengthen human resource capacity in response to digital transformation. Teachers are expected to understand the KKA learning outcomes and be able to design and implement technology-based learning in their respective schools. This study employs a Large Language Model (LLM)-based categorization technique to analyse the reflective content of SMA/SMK teachers in Malang City after attending the KKA training, aiming to identify their learning achievement levels and how they interpret their learning experiences. The dataset, consisting of presentation files in PDF and PPTX formats, was text-extracted, processed by the LLM, categorized into ten main themes in JSON format, and visualized as a mind map using Mermaid scripts. The findings demonstrate that the LLM effectively performs consistent semantic categorization on unstructured reflective data and produces visual representations that facilitate the interpretation of learning achievements. Content analysis of teacher reflections reveals strong motivation to enhance digital and pedagogical competencies, successful implementation of project-based learning, and emerging challenges related to student scepticism toward AI adoption in art and design education. Furthermore, the comparison between a general-purpose LLM (GPT-OSS) and coder-type LLMs (such as GLM-4.6:Coder and Qwen3-Coder) indicates comparable accuracy in generating JSON structures and Mermaid scripts. However, the non-coder LLM exhibits greater stability in maintaining contextual coherence and processing speed. These findings highlight the potential of LLMs in analysing reflective educational data and underscore the need for pedagogical adaptation and continued digital competence development among teachers toward AI-driven educational independence.
Development of an Explainable Deep Learning Model for Phishing Detection Sugiyatno; Mujiono Sadikin; Endang Retnosingsih
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

Phishing is one of the most prevalent and damaging cyberattacks globally, exploiting social engineering techniques to deceive users into revealing sensitive information. The increasing sophistication of phishing attacks demands detection models that are both accurate and interpretable. This study proposes an Explainable Deep Learning model that combines Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) architectures to detect phishing attacks effectively. The model is trained using datasets from PhishTank and the UCI Machine Learning Repository, with preprocessing steps involving normalization, categorical encoding, and class balancing through the Synthetic Minority Oversampling Technique (SMOTE). To enhance model transparency, the SHapley Additive Explanations (SHAP) method is integrated, providing insights into the feature contributions that influence model predictions. Experimental results demonstrate that the proposed CNN + BiLSTM model achieves superior performance with an accuracy of 98.45%, precision of 97.80%, recall of 98.60%, F1-score of 98.20%, and an AUC-ROC value of 0.992, outperforming baseline models such as Support Vector Machine and Random Forest. The SHAP analysis identifies key influencing features, including HTTPS usage, URL length, domain age, and IP address presence, which contribute significantly to classification decisions. Overall, the integration of explainability enhances the model’s transparency and user trust, offering a reliable approach for developing intelligent phishing detection systems that support cybersecurity operations and forensic audits. The findings demonstrate that integrating explainability into deep learning improves both accuracy and interpretability in phishing detection tasks.
Optimasi Deteksi Penyakit Daun Jagung Menggunakan MobileNetV2 dan CNN Kustom Berbasis Transfer Learning Yanto Supriyanto
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

The rapid development of deep learning has revolutionized plant disease detection, particularly in precision agriculture. This study aims to compare the performance of a custom Convolutional Neural Network (CNN) and MobileNetV2 in classifying corn leaf diseases into three categories: blight, rust, and healthy leaves. The dataset consists of 303 images captured directly from cornfields in Indonesia, divided into training, validation, and test sets with a 70:15:15 ratio. To overcome data scarcity, data augmentation techniques such as rotation, zoom, and flipping were applied. The custom CNN model and MobileNetV2 (fine-tuned from ImageNet weights) were trained using TensorFlow on Google Colab with a T4 GPU. Experimental results show that MobileNetV2 outperformed the custom CNN in accuracy, precision, recall, and F1-score, demonstrating its efficiency and adaptability for small agricultural datasets. The findings confirm that transfer learning and data augmentation significantly improve classification performance, making MobileNetV2 a lightweight yet accurate solution for corn leaf disease detection in real-world agricultural applications.
Model Pembelajaran Statistika dengan Pendekatan Didaktik Digital Deasy Wahyuni; Afifah Ainun Nadjla
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

This study develops a digital didactics-based statistics learning model to enhance students' 21st-century statistical abilities. Using the ADDIE framework, the research designed a model integrating pedagogical, technological, and social collaboration aspects. Expert validation yielded a high feasibility score of 4.65/5. Experimental implementation with 75 students showed significant improvements in conceptual understanding, digital tool proficiency with R, critical data thinking, and data ethics awareness compared to conventional methods. The model's novelty lies in its systematic integration of Digital Didactical Design with triple-focus learning outcomes and open-source platforms (RStudio Cloud, GitHub). Quantitative analysis revealed significant differences (p<0.05) between experimental and control groups, while qualitative findings demonstrated enhanced engagement and authentic learning experiences. The study concludes that transforming statistics education requires comprehensive learning ecology redesign rather than mere technological substitution, offering a practical framework for developing relevant digital-era statistical competencies.
Pengembangan Aplikasi Inventory Produk Masker Camille Berbasis Web Menggunakan FIFO Syifa Maulida Akmalia; Binastya Anggara Sekti; Nixon Erzed
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

Efficient inventory management plays a crucial role in store operations to prevent issues such as overstock, shortages, or product losses caused by expiration. Camille Beauty Store has faced challenges in handling stock manually, which is often inefficient and prone to human error. To address this problem, this study aims to design and implement a website-based inventory information system using the FIFO (First In, First Out) method to optimize stock management processes. The system was developed using PHP for the programming language and MySQL for database management, while the development stages followed the waterfall model, consisting of needs analysis, design, implementation, testing, and evaluation. Data collection was carried out through direct observations, interviews with the store owner, and literature studies to ensure system requirements were well-defined. The results demonstrate that the developed system successfully automates stock recording for both incoming and outgoing goods while applying the FIFO principle, ensuring older items are sold first to minimize the risk of expiration. In addition, the system provides real-time stock reporting, which supports management in making accurate and timely inventory- related decisions. The implementation of this system has proven to enhance efficiency, reduce manual errors, and accelerate reporting processes, although stable internet connectivity remains limitation.

Page 46 of 48 | Total Record : 471

 44   45   46   47   48 

Filter by Year

2017 2025


Reset
Filter By Issues
All Issue Vol 9 No 1 (2025): SISFOTEK IX 2025 Vol 8 No 1 (2024): SISFOTEK VIII 2024 Vol 7 No 1 (2023): SISFOTEK VII 2023 Vol 5 No 1 (2021): SISFOTEK V 2021 Vol 4 No 1 (2020): Vol 4 No 1 (2020): SISFOTEK 2020 Vol 3 No 1 (2019): SISFOTEK 2019 Vol 2 No 1 (2018): SISFOTEK 2018 Vol 1 No 1 (2017): SISFOTEK 2017