Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Jurnal Pilar Nusa Mandiri Malcom: Indonesian Journal of Machine Learning and Computer Science
Marcelly, Frizca Fellicita
Unknown Affiliation
Computer Science & IT

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

Found 3 Documents
Search

 1 
AI-Powered: Leveraging Teachable Machine for Real-time Scanner Marcelly, Frizca Fellicita; Rianto, Yan
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 5 No. 3 (2025): MALCOM July 2025
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v5i3.1931

Abstract

Effective inventory control is essential in optimizing profitability through cost control and efficiency expectations. Conventional inventory techniques frequently find it difficult to adjust to the fast-changing restaurant setting, resulting in surplus stock, inventory deficits, and unnecessary food waste. Nonetheless, a notable shift is approaching, as the incorporation of artificial intelligence (AI) may help address this issue. AI-powered inventory management systems help restaurants optimize stock levels, reduce waste, and predict demand more accurately, leading to improved efficiency and increased profitability. This study explores how AI-driven inventory management enhances efficiency, reduces waste, and automates restocking in the restaurant sector, with a particular focus on TastyGo's integration of Teachable Machine and TensorFlow Lite. The suggested solution uses picture recognition for real-time inventory tracking, and machine learning models to predict demand and replenishment automation. TastyGo can expedite supply chain management, save waste through predictive analytics, and improve its inventory by employing these AI techniques. This study shows how AI-driven solutions may boost decision-making, reduce food waste, and greatly increase operational efficiency, all of which can result in higher profitability. The findings highlight how AI technologies have the potential to revolutionize conventional inventory management systems in the restaurant industry.
EVALUATING PREPROCESSING EFFECTS IN NAME RETRIEVAL USING CLASSICAL IR AND CNN-BASED MODELS Marcelly, Frizca Fellicita; Saputra, Irwansyah; Andra, Muhammad Bagus
Jurnal Pilar Nusa Mandiri Vol. 21 No. 2 (2025): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v21i2.6884

Abstract

Information Retrieval (IR) systems are pivotal for efficient data management, particularly in tasks involving name searches and entity identification. This study evaluates text preprocessing techniques, including case folding, phonetic normalization, and gender tagging, that affect the performance of classical (TF-IDF, LSI) and CNN-based retrieval models for multilingual name matching. Using a dataset of 365,468 globally diverse names, this study implements a preprocessing pipeline featuring: Double Metaphone phonetic preprocessing (92% validation accuracy), gender disambiguation for unisex names (92% accuracy), and optimized n-gram tokenization for short names. Evaluation metrics include precision, recall, F1-score, and our novel Name Similarity Score (NSS), combining orthographic and phonetic preprocessing. Results show our full pipeline improves recall to 1.00 and F1-score by 37% while reducing false negatives by 63%. Key findings reveal: TF-IDF achieves superior recall (0.98 vs CNN’s 0.85), LSI handles cultural variants effectively, and CNNs deliver the highest precision (0.91 vs TF-IDF’s 0.70), particularly for unisex names. This work contributes both a scalable multilingual preprocessing framework and the NSS evaluation metric for robust name retrieval systems.
EVALUATING PREPROCESSING EFFECTS IN NAME RETRIEVAL USING CLASSICAL IR AND CNN-BASED MODELS Marcelly, Frizca Fellicita; Saputra, Irwansyah; Andra, Muhammad Bagus
Jurnal Pilar Nusa Mandiri Vol. 21 No. 2 (2025): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v21i2.6884

Abstract

Information Retrieval (IR) systems are pivotal for efficient data management, particularly in tasks involving name searches and entity identification. This study evaluates text preprocessing techniques, including case folding, phonetic normalization, and gender tagging, that affect the performance of classical (TF-IDF, LSI) and CNN-based retrieval models for multilingual name matching. Using a dataset of 365,468 globally diverse names, this study implements a preprocessing pipeline featuring: Double Metaphone phonetic preprocessing (92% validation accuracy), gender disambiguation for unisex names (92% accuracy), and optimized n-gram tokenization for short names. Evaluation metrics include precision, recall, F1-score, and our novel Name Similarity Score (NSS), combining orthographic and phonetic preprocessing. Results show our full pipeline improves recall to 1.00 and F1-score by 37% while reducing false negatives by 63%. Key findings reveal: TF-IDF achieves superior recall (0.98 vs CNN’s 0.85), LSI handles cultural variants effectively, and CNNs deliver the highest precision (0.91 vs TF-IDF’s 0.70), particularly for unisex names. This work contributes both a scalable multilingual preprocessing framework and the NSS evaluation metric for robust name retrieval systems.
Co-Authors Andra, Muhammad Bagus Rianto, Yan Saputra, Irwansyah