Florentina Yuni Arini
Unknown Affiliation

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

Found 3 Documents
Search

Tantangan Etika dan Tanggung Jawab Robotics Engineer Dalam Pengembangan Robot Barista Berbasis IoT Muhammad Sulthonul Izza; Intan Permata Sari Fauziah; Sekar Tri Handayani; Farrel Athaillah Putra; Fittra Marga Ardana; Florentina Yuni Arini
Jurnal Ilmiah Informatika Global Vol. 16 No. 1: April 2025
Publisher : UNIVERSITAS INDO GLOBAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jiig.v16i1.5012

Abstract

Over the past few decades, technology has advanced at a tremendous pace, especially related to social robotics based on the Internet of Things has significantly influenced many aspects of human life. A concrete example of its application is a robot barista designed to interact and collaborate with humans, creating a new relationship between humans and machines. However, the presence of these robots also poses ethical challenges and professional responsibilities, especially regarding data privacy, security, and social impact. This research seeks to determine and assess the primary challenges robotics engineers face in designing safe and ethical robotics systems. Through a literature study approach that includes collecting, reviewing, and analyzing various relevant scientific sources related to ethical issues in robotics and IoT technology, it was found that robotics engineers must consider aspects of security and personal data protection as well as potential social impacts such as inequality and employment reduction. This research emphasizes the importance of ethics education and the establishment of high professional standards in addition to the need for clear ethical guidelines through cross-sector collaboration. Thus, the development of IoT-based barista robots is expected to not only drive technological progress, but also bring sustainable and responsible benefits to society.
Perancangan Antarmuka Pengguna Interaktif untuk Aplikasi UTBKing dengan Pengembangan Model Florentina Yuni Arini; Gerard Sean Dwayne; Aisyah Nathania Araminta; Inoru Nian Alfita; Ahmad Zidhan Ilmana; Nathania Adristina
Indonesian Journal of Mathematics and Natural Sciences Vol. 47 No. 2 (2024): Volume 47 Nomor 2 Tahun 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/04t8sj08

Abstract

Higher education is crucial for personal development, yet its accessibility often poses a challenge, especially for economically disadvantaged students. Apps like UTBKing aim to provide easily accessible learning resources, aiding students in preparing for college entrance. The development process involves three main stages: data collection, system development, and system design. The discussion will delve into the detailed flow of the UTBKing app, its UI/UX design, and implemented interactive features. Continuous efforts are required to develop and enhance the quality of learning applications in order to provide optimal benefits for students in facing future academic challenges.
Optimasi algoritma deteksi spam email dengan BERT-MI dan jaringan dense Florentina Yuni Arini
Computer Science and Information Technology Vol 6 No 2 (2025): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v6i2.9460

Abstract

Email spam detection is a critical challenge in maintaining the security and efficiency of digital communication. This research proposes and evaluates an optimized pipeline for email spam detection by integrating Bidirectional Encoder Representations from Transformers (BERT) for feature extraction, Mutual Information (MI) for feature selection to reduce dimensionality, and a dense neural network for classification. The Lingspam dataset, consisting of 2893 emails (2412 ham and 481 spam), was used in the experiments with an 80% training and 20% testing data split. Text features were extracted using BERT (bert-base-uncased), resulting in a 768-dimensional embedding, which was then reduced to the 200 most relevant features using MI. A dense neural network model with a 256-128-64-32-1 neuron architecture was trained using the Adam optimizer, binary cross-entropy loss function, and techniques such as early stopping and class weights to handle class imbalance. Evaluation results on the test data demonstrated very high performance, achieving an accuracy of 99.14%, precision of 0.9596, recall of 0.9896, F1-score of 0.9744, and ROC-AUC of 0.9995. This approach indicates that the combination of BERT-MI with a dense network can achieve accuracy comparable to more complex methods, but with the potential for a simpler and more efficient architecture.