Article Per Year (5 Year)
p-Index From 2020 - 2025
1.642
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Ilmiah Informatika Komputer MediaTor: Jurnal Komunikasi Jurnal KOMUNIKA TELKOMNIKA (Telecommunication Computing Electronics and Control) Bulletin of Electrical Engineering and Informatics Jurnal Ilmu Komunikasi Jurnal Kajian Komunikasi Jurnal Ilmiah FIFO Jurnal ASPIKOM Khadimul Ummah Journal of Social Dedication Journal of Applied Data Sciences Komunika: Jurnal Dakwah dan Komunikasi Jurnal Pengabdian Kepada Masyarakat Darma Saskara
Hustinawaty Hustinawaty, Hustinawaty
Universitas Gunadarma
Religion Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science Public Health Social Sciences Other

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of Applied Data Sciences

 1 
Multi-Label Classification of Indonesian Voice Phishing Conversations: A Comparative Study of XLM-RoBERTa and ELECTRA Hidayat, Ahmad; Madenda, Sarifuddin; Hustinawaty, Hustinawaty
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.858

Abstract

Mobile phones have become a primary means of communication, yet their advancement has also been exploited by cybercriminals, particularly through voice phishing schemes. Voice phishing is a form of social engineering fraud carried out via telephone conversations to illegally obtain personal or financial information. The complexity of voice phishing continues to increase, as a single conversation may involve multiple fraudulent schemes simultaneously, necessitating the application of multi-label classification to comprehensively identify all motives of fraud. Previous studies have predominantly utilized single-label approaches and foreign-language data, making them less relevant to the Indonesian language context and unable to produce speaker segmentation outputs for conversational analysis. This study contributes by developing a multi-label voice phishing classification system specifically for Indonesian telephone conversations to address this gap. Audio data were collected from open sources and simulated recordings, resulting in a total of 300 samples labeled into six categories: five phishing modes and one non-phishing category. The proposed system consists of a preprocessing pipeline that includes noise reduction, speaker segmentation, automatic transcription, and text cleaning to preserve the context of two-way conversations. Two machine learning models based on transformer architectures, XLM-RoBERTa and ELECTRA, are employed to identify various fraud schemes that may occur simultaneously within a single conversation. The dataset was split into training, validation, and testing sets with two division ratios for performance evaluation. Several combinations of hyperparameters were tested to obtain the most optimal model configuration. Evaluation was conducted using a supervised learning approach and various performance metrics. The experimental results show that XLM-RoBERTa achieved the highest average accuracy of 97.04 ± 1.15% and the highest average F1-score of 92.66 ± 2.59%. These results highlight the novelty of applying multi-label classification in the Indonesian language context for voice phishing detection, contributing to more effective fraud identification in real-world telephony systems.
Human Shoulder Posture Anthropometry System for Detecting Scoliosis Using Mediapipe Library Hustinawaty, Hustinawaty; Rumambi, Tavipia; Hermita, Matrissya
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.870

Abstract

The system proposed in this research is a posture detection system using real-time computer vision technology with system limitations aimed at detecting shoulder posture as part of anthropometric measurements, because if the shoulder posture is unbalanced and has a very significant height difference, it is called an indication of scoliosis. This research aims to facilitate the detection of scoliosis, especially in one of its symptoms, namely shoulder asymmetry with anthropometric measurements of the ‘Elbow-to-Elbow breadth’ position using the scoliomter method. In addition, common screening methods that can be used for scoliosis, especially in adolescents, include the Adams forward bend test, Cobb angle measurement, and Moire measurement. The anthropometric shoulder posture detection system includes the stages of preparation for detection using a webcam with T-position calibration, then MediaPipe Library processes 33 keypoints, OpenCV and Python to analyze body movements in real time, then this asymmetry is calculated using standard algorithms for pose prediction, vector projection and atan2 to obtain asymmetry angle information. The results of testing the shoulder detection system in the form of shoulder posture according to landmarks on one test subject and keypoint extraction on the user interface display in real time and provide information on the angle of asymmetry of the shoulder and hip in the front and rear facing positions. From testing 16 respondents, the shoulder tilt angle is obtained in the range of 7.42-19.84 degrees which will have a TRUE value if the angle is greater than 15 degrees. Information on the angle of more than 15 degrees can be used as a reference for scoliosis symptoms and further diagnosis by medical practitioners and through this detection system it will be easy to get information related to the results of shoulder posture detection accurately and in real time compared to using only a scoliometer.
Co-Authors Abdullah Abdullah Abdullah Abdullah Achmad Benny Mutiara Ahmad Hidayat Ary Bima Kurniawan Baby Lolita B., Baby Lolita Dewi Agushinta R. Dwiputra, Rama Al Azis Edy Prihantoro Eldianisa Adesita Eri Prasetyo Wibowo, Eri Prasetyo Faisal Arkan Henny Medyawati Ihsan Jatnika Matrissya Hermita Nur Sultan Salahuddin Purwoko, Agus Rifiana Arief Rila Setyaningsih Rila Setyaningsih Rizqi Basuki, Nurfadjri Akbar Sari, Sri Purnomo Sarifuddin Madenda Setyaningsih, Rila Suger, Herik Sulardi . Supiani Supiani, Supiani Suryarini Widodo Tavipia Rumambi Tavipia Rumambi, Tavipia Tubagus Maulana Kusuma Veithzal Rivai Zainal