Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Jurnal SASAK : Desain Visual dan Komunikasi Media Jurnal Informatika Jurnal Sisfotek Global
Fatimatuzzahra Fatimatuzzahra
Politeknik Negeri Jember
Arts Computer Science & IT Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Languange, Linguistic, Communication & Media

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Design of Interactive Augmented Reality Learning Media Using theVAKT Approach for Early Childhood Vegetable Recognition Wahyu Kurnia Dewanto; Zilvanhisna Emka Fitri; Achmad Amreza Alfarit; Arizal Mujibtamala Nanda Imron; Reski Yulina Widiastuti; Ery Setiyawan Jullev Atmadji; Fatimatuzzahra Fatimatuzzahra
Jurnal SASAK : Desain Visual dan Komunikasi Vol. 8 No. 1 (2026): SASAK (In Press)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/sasak.v8i1.6317

Abstract

Early childhood education requires adaptive media to facilitate cognitive and linguistic development. This study aims to evaluate the integration of the Visual-Auditory-Kinesthetic-Tactile (VAKT) frame work into an Augmented Reality (AR) application for vegetable recognition, balancing technical engineering with user-centric design paradigms. This research used a method developed with Unity and the Vuforia SDK; the application architecture incorporates real-time marker tracking, a dual-language localization database, and automated dynamic scoring algorithms. Usability was quantitatively measured with 12 respondents using the Technology Acceptance Model (TAM) and the System Usability Scale (SUS) frameworks. The results of this research yielded a high TAM utility score of 80.63% andan ”Excellent” (B+) SUS rating. Technically, the system effectively maps software constraints onto cognitive stimuli, utilizing single-story sans-serif typography and high-saturation color rendering to sustain attention and support emergent literacy. While nearly 90% of respondents affirmed the application’s learning efficacy, empirical logs exposed a critical friction point: asynchronous background audio caused sensory overstimulation for 41.67% of users. These findings support the Split Attention Effect theory, suggesting that in AR environments, multi-sensory inputs must be hierarchically ordered to prevent cognitive overload. This study concludes that a synchronous multimodal hierarchy is essential for successful interactive multimedia environments.
A Stock Demand Forecasting for MSME E-Commerce Using LSTM and Facebook Prophet: A Comparative Study Fatimatuzzahra Fatimatuzzahra; Akmal Amilunizar; Khen Dedes; Helyatin Nisyak; Nadzirotul Fitriyah
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6365

Abstract

Manual sales processes and stock management in micro, small, and medium enterprise (MSME) settings often lead to limited market reach and inefficient inventory management. The purpose of this research is to solve these operational problems by designing and developing a web-based e-commerce system equipped with an integrated monthly stock demand forecasting module to enhance the competitiveness of MSMEs in the roster industry. The system was developed following the waterfall methodology and it has a decoupled architecture to separate the artificial intelligence computational workloads from the core application. Two time series forecasting models Long Short-Term Memory (LSTM) and Facebook Prophet were applied and compared for forecasting stock requirements from intermittent, zero-inflated demand patterns of historical sales data. System functionality was validated using User Acceptance Testing and the forecasting accuracy was measured using Root Mean Square Error (RMSE) and Weighted Mean Absolute Percentage Error (WMAPE). The performance evaluation showed that the unscaled LSTM model outperformed the linear additive regression method of Facebook Prophet in terms of lower physical volume deviation and consistent operational error in the course of the evaluation period. The developed platform provides a reliable data-driven decision support for inventory management. The incorporation of forecasting using neural networks in the e-commerce system has reduced the risk of stockouts, expanded the market, and proved the increase in the business competitiveness of artisan MSMEs.
Extended LRFM-Based K-Means Clustering for Gym Member Segmentation and Engagement Analysis Mas'ud Hermansyah; Eka Yuniar; Muhammad Bahanan; Fatimatuzzahra Fatimatuzzahra; Khen Dedes
JURNAL SISFOTEK GLOBAL Vol 16, No 2 (2026): JURNAL SISFOTEK GLOBAL
Publisher : Institut Teknologi dan Bisnis Bina Sarana Global

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38101/sisfotek.v16i2.17024

Abstract

The increasing need for data-driven member management in the fitness center industry makes member segmentation important for identifying differences in activity, engagement, and financial contribution and supporting more targeted retention strategies. This study aims to group members of GYM JGM (Jaya Makmur Gym), Jember, based on Length, Recency, Frequency, and Monetary (LRFM) characteristics. The dataset used consists of 150 member data. The research process includes data preprocessing, LRFM feature selection, standardization using Z-Score, and the application of the K-Means algorithm. Determining the optimal number of clusters is done by comparing the Elbow Method, Davies-Bouldin Index (DBI), and Silhouette Score on candidate clusters k = 2 to k = 9. The evaluation results show that three clusters are the optimal configuration because they produce the lowest DBI value of 0.825 and the highest Silhouette Score of 0.430, and show a clear change point in the Elbow Method. The segmentation results produce three groups of members, namely Shorter-Term Moderate-Activity Members, High-Value Active Members, and Long-Term Low-Engagement Members. The segmentation shows that the K-Means algorithm based on LRFM features is able to identify differences in member characteristics and provide an analytical basis for developing retention strategies, increasing engagement, and reactivating GYM JGM members.
Co-Authors Achmad Amreza Alfarit Akmal Amilunizar Arizal Mujibtamala Nanda Imron Eka Yuniar Ery Setiyawan Jullev Atmadji Khen Dedes Mas'ud Hermansyah Muhammad Bahanan Nadzirotul Fitriyah Reski Yulina Widiastuti Wahyu Kurnia Dewanto Zilvanhisna Emka Fitri