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
 42   43   44   45   46 
Comparison Of Machine Learning Algorithms For Rice Production Prediction In Sumatra Abdul Karim; Yuwaldi Away; Syahrial; Roslidar; Jeperson Hutahaean; William Ramdhan; Yessica Siagian
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

Rice production prediction is a crucial aspect in agricultural planning and food security. This study compares the performance of four regression algorithms in predicting rice production based on agronomic and climatological variables. The algorithms used are Random Forest Regression, XGBoost Regression, Support Vector Regression (SVR), and Artificial Neural Network (ANN). The evaluation results showed that Random Forest performed best with an R² of 0.963, followed by XGBoost with an R² of 0.959, indicating that these two models were able to explain more than 95% of the data variation. In contrast, SVR performed poorly with an R² of -0.064, while ANN had the worst result with an R² of -2.417, indicating the model's unsuitability for the dataset used. Thus, it can be concluded that Random Forest and XGBoost are the best options for rice production prediction, while SVR and ANN require further optimization to be used effectively in this context.
Perancangan Sistem Informasi Berbasis Website Pada Toko Pualam Untuk Meningkatkan Efisiensi Layanan Akmil Maulana Ramadhan; Kartini
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 aims to design and implement an e-commerce-based sales information system for Toko Pualam to enhance operational efficiency and expand marketing reach. The system was developed using the Prototype method, allowing iterative collaboration between developers and users to ensure that the final product meets real-world requirements. The research stages included requirement analysis, system design, implementation, and testing. The results indicate that the developed system supports online sales activities with key features such as product management, transactions, automated financial reporting, and real-time inventory control. Functional testing using Black Box Testing confirmed that all features operated as expected, while the System Usability Scale (SUS) test showed good usability levels. The implemented system effectively accelerates data processing and improves sales accuracy while providing customers with easy access to product information anytime and anywhere.
Pengembangan Media Pembelajaran Digital Bertema Transportasi Dua Bahasa (Bahasa Indonesia–Arab) untuk Anak Usia Dini menggunakan model R&D Sekar Wulandari; Rudi Budi Agung; Siti Chodijah; Zahra Aidid
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

Language is the most important medium of communication for humans, useful as a tool to convey messages from one person to another. One of the popular languages ????among Indonesian people is Indonesian and Arabic. Language learning can be in schools or in science assemblies, in addition to independent memorization methods. With the presence of current technology can assist learning so that learning can be converted into a digital format with the hope of learning being more practical and interesting. This method is an alternative learning method that can encourage children to feel enthusiastic about learning languages ????for early childhood. In this study, we will create a digital learning media for introducing transportation tools in Indonesian and Arabic to broaden children's insight and education about transportation tools in Indonesian and Arabic. The method developed is the EDDIE model, an acronym for Analysis, Design, Development, Implementation and Evaluation. As well as conducting testing of the application that has been created. The results of this digital learning media are expected to help children in learning the names of transportation tools in Indonesian and Arabic.
Integrasi Deep Learning Multimodal Untuk Peramalan Penjualan Toko Menggunakan Keras Functional API Khaerul Anam; Dadang Sudrajat; Saeful Anwar; Rudi Kurniawan
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

Store sales forecasting based on historical data has been widely studied; however, most conventional approaches remain limited to single time series data and are less capable of capturing the complex influence of external factors. Existing knowledge suggests that deep learning can improve forecasting accuracy compared to traditional statistical methods, but what remains unclear is the extent to which multimodal integration—combining time series, economic, and categorical data—can enhance predictive performance in a dynamic retail context. This study aims to develop and evaluate a multimodal deep learning model using the Keras Functional API for store sales forecasting. The methodology involves collecting and processing daily transaction data, oil prices, holidays, and store information, followed by preprocessing, feature engineering, normalization, and time-window construction stages. Four architectures were tested—LSTM, 1D CNN, CNN+RNN, and Multiscale CNN—with performance evaluation conducted using Mean Absolute Error (MAE). The results indicate that multimodal integration yields a significant improvement compared to single-source data, with the 1D CNN model achieving the best performance at an MAE of 57,4318. The discussion highlights that integrating external variables such as oil prices and holidays enhances the robustness of predictions, while the main challenges remain in high computational requirements and limited model interpretability. This study concludes that the multimodal deep learning approach provides a scientific contribution by enriching the literature on sales forecasting while offering practical implications for the retail sector in inventory management, promotional planning, and data-driven decision-making.
Peningkatan Akurasi Prediksi Performa Akademik Siswa Menggunakan Model Stacking Ensemble Ari Nugroho Putro; Much. Aziz Muslim
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

Educational data mining has become an effective tool for exploring and predicting student academic performance. Various studies have shown its potential in developing early detection systems for students at risk of dropping out of school. However, the main challenge in such prediction systems is the low performance of conventional classification algorithms in producing high accuracy. This study aims to improve the accuracy of student performance predictions by applying a stacking ensemble model that combines several algorithms. The model developed uses two base learners, namely XGB, LGBM, SVM, and LR, which are then combined through the meta learner LR to produce a final decision. The experiment was conducted using a dataset predicting student dropout and academic success, which included academic paths, demographics, socioeconomic status, and academic performance of students in their first and second semesters. Model validation was performed using 10-fold cross validation to ensure the stability and generalization ability of the model. The test results showed that the stacking ensemble model achieved an accuracy of 0.9168, superior to the single classification model. These findings prove that the stacking ensemble approach is effective in improving student performance predictions.
Pembangunan Sumber Daya Manusia Sektor Teknologi di Papua Pegunungan Teguh Priyantoro; Esibius Irwan Hisage; Manuel Gombo
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

Human resource development is an integral part of the development of a region or area. As a new autonomous region, Papua Pegunungan requires various effective regional development strategies to align development and equitable distribution of community welfare in accordance with the objectives of regional expansion. Rapidly developing technology currently demands the availability of competent human resources, especially in the technology sector. This study aims to analyze the need for these human resources, tailored to the types of jobs in the technology sector that are predicted to be highly needed in regional development in Papua Pegunungan. The results of the study indicate that there are at least eight areas of focus in human resource development in the technology sector in Papua Pegunungan.
Pengaruh Augmentasi Data Back-Translation terhadap Kinerja Analisis Sentimen dalam Bahasa Indonesia Jusuf Junior Athala; Windy Gambetta
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

Sentiment analysis is a field of natural language processing (NLP) that aims to classify emotions or opinions contained in a text. When training a machine learning model for sentiment analysis, a problem commonly encountered is imbalanced datasets or datasets with uneven class distributions. This study investigates Back Translation’s effect on improving machine learning performance using an imbalanced dataset. The imbalanced dataset to be used is the NusaX Sentiment Analysis dataset. Experiment results show that Support Vector Machine (SVM) models give notable improvement in scores, especially with Back Translation using Javanese as the intermediate language, which provides the best F1 macro score improvement of 1.89% and the best F1 weighted score improvement of 1.52%. On the other hand, Naive Bayes models do not show any notable improvements. The findings indicate Back Translation can adjust class distribution and can boost certain models' sentiment analysis accuracy.
Klasifikasi Penyakit Citra Daun Tebu Berbasis Web Menggunakan EfficientNetB7–Support Vector Machine Patrisia Cindy Paskariana; Anastasia Rita Widiarti
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

Sugarcane is one of the important agricultural crops in Indonesia, playing a strategic role in maintaining national food security as well as serving as a raw material for the sugar industry. However, plant diseases such as mosaic, rust, red rot, and yellow can significantly reduce sugarcane productivity. This study aims to develop a web-based system capable of classifying diseases in sugarcane leaf images using EfficientNet-B7 as a feature extractor and Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel as the classifier. The research method includes preprocessing steps such as resizing, cropping, and image augmentation, followed by feature extraction and classification using Stratified K-Fold Cross Validation. Research results indicate that the model achieved optimal performance with a C value of 10 and a Gamma value of 0.001 resulting in an accuracy of 93.33%. Furthermore, alpha testing showed that the application operated without errors, while beta testing with 35 respondents resulted in an average user satisfaction rate of 91.82%. These results demonstrate that the developed system functions effectively, is accurate, and easy to use. This application has the potential to serve as a tool for early detection of sugarcane leaf diseases, thereby supporting improved agricultural management and productivity.
Implementasi Metode Design Thinking pada Perancangan UI/UX Aplikasi FooYu: Future of Opportunities Youth University Putri Dia Lestari
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 paper presents the implementation of the Design Thinking method in designing the User Interface (UI) and User Experience (UX) of FooYu, a mobile application developed to connect students and alumni of UPN “Veteran” Jawa Timur with career opportunities and freelance projects. The research applies five stages of Design Thinking, namely Empathize, Define, Ideate, Prototype, and Testing. During the Empathize stage, user interviews were conducted to identify needs and challenges. The findings were translated into design requirements in the Define stage, while the Ideate and Prototype stages focused on generating and visualizing creative solutions using Figma. The Testing stage utilized the System Usability Scale (SUS) to measure usability, yielding a score of 34.5, indicating that the application demonstrates good usability. The results show that Design Thinking effectively supports user-centered product design, leading to a more intuitive and accessible interface for novice freelancers.
Klasifikasi Citra Emosi Wajah Menggunakan Convolutional Neural Network Untuk Penderita Depresi Hariyanto; Novianti Puspitasari; Anindita Septiarini
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

Facial analysis is widely used as information to determine a person's psychological condition, such as depression. Someone suffering from depression tends to have a face that looks sad, empty, or unhappy. The appearance of a depressed person's face is almost similar to that of someone experiencing sadness. However, facial appearance is not always perceived as depressed, so facial emotion recognition is needed for depression treatment. A Convolutional Neural Network (CNN) is often used in image processing to identify key features and patterns in images, particularly for facial emotion recognition. CNN can be used to learn the relationship between facial shape and related emotions. This study employs the CNN method to classify facial emotions from facial expression images collected from a dataset of 30,724 images. The training process uses seven classes: Angry, Disgust, Fear, Happy, Sad, Surprise, and Neutral. The accuracy results obtained a value of 67% with a training dataset of 21,507 images, a validation dataset of 6,143 images, and a testing dataset of 3,080 images.

Page 44 of 48 | Total Record : 471

 42   43   44   45   46 

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