Article Per Year (5 Year)
p-Index From 2021 - 2026
1.789
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) DINAMIKA DOTCOM Teknik dan Ilmu Komputer Jurnal Teknologi Informasi dan Ilmu Komputer Journal of Information Systems Engineering and Business Intelligence Khazanah Informatika: Jurnal Ilmu Komputer dan Informatika Sistemasi: Jurnal Sistem Informasi Jurnal Sisfokom (Sistem Informasi dan Komputer) Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal Jurnal Teknik Informatika (JUTIF)
Cynthia Hayat
Universitas Kristen Krida Wacana - Jakarta Barat
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Social Sciences

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
DESIGN AND BUILD VEHICLE PLATE DETECTION SYSTEM USING YOU ONLY LOOK ONCE METHOD BASED ON ANDROID Usen, Yolan Anjani; Hayat, Cynthia
Jurnal Teknik Informatika (Jutif) Vol. 4 No. 4 (2023): JUTIF Volume 4, Number 4, August 2023
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2023.4.4.791

Abstract

The method of collecting the vehicle data is conducted conventionally by gathering data from each region to be converted into single, raw information in the form of vehicle plates for all regions, to be processed on a computer and sent to the Central Bureau of Statistics. It is then transformed into a form of national data file that provides information on vehicle plates for the Indonesian people. This kind of data gathering method requires a lot of time and effort. Therefore, it is a concern for researchers to detect vehicle plates using image processing by utilizing the Android-based You Only Look Once method. The YOLOv4 technique is used because it processes image data directly with optimal performance in order to produce faster predictions. In its application, the researchers use Google Collaboratory to create models and Android Studio for android applications. At the same time, the parameters studied were precision, recall, F1 score, average IoU, and mAP. By using the "Vehicle Registration Plate" dataset, the ratio of which is 70% in training data and 30% in data validation, an accuracy of 77% is obtained with a detection time of 0.05 seconds, whereas the average accuracy value is 86.82%. Therefore, it can be concluded that this study has an optimized performance for detecting vehicle plates using the Android application.
Hybrid Architecture Model of Genetic Algorithm and Learning Vector Quantization Neural Network for Early Identification of Ear, Nose, and Throat Diseases Hayat, Cynthia; Soenandi, Iwan Aang
Journal of Information Systems Engineering and Business Intelligence Vol. 10 No. 1 (2024): February
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.10.1.1-12

Abstract

Background: In 2020, the World Health Organization (WHO) estimated that 466 million people worldwide are affected by hearing loss, with 34 million of them being children. Indonesia is identified as one of the four Asian countries with a high prevalence of hearing loss, specifically at 4.6%. Previous research was conducted to identify diseases related to the Ear, Nose, and Throat, utilizing the certainty factor method with a test accuracy rate of 46.54%. The novelty of this research lies in the combination of two methods, the use of genetic algorithms for optimization and learning vector quantization to improve the level of accuracy for early identification of Ear, Nose, and Throat diseases. Objective: This research aims to produce a hybrid model between the genetic algorithm and the learning vector quantization neural network to be able to identify Ear, Nose, and Throat diseases with mild symptoms to improve accuracy. Methods: Implementing a 90:10 ratio means that 90% (186 data) of the data from the initial sequence is assigned for training purposes, while the remaining 10% (21 data) is allocated for testing. The procedural stages of genetic algorithm-learning vector quantization are population initialization, crossover, mutation, evaluation, selection elitism, and learning vector quantization training. Results The optimum hybrid genetic algorithm-learning vector quantization model for early identification of Ear, Nose, and Throat diseases was obtained with an accuracy of 82.12%. The parameter values with the population size 10, cr 0.9, mr 0.1, maximum epoch of 5000, error goal of 0.01, and learning rate (alpha) of 0.5. Better accuracy was obtained compared to backpropagation (64%), certainty factor 46.54%), and radial basic function (72%). Conclusion: Experiments in this research, successed identifying models by combining genetic algorithm-learning vector quantization to perform the early identification of Ear, Nose, and Throat diseases. For further research, it's very challenging to develop a model that automatically adapts the bandwidth parameters of the weighting functions during trainin   Keywords: Early Identification, Ear-Nose-Throat Diseases, Genetic Algorithm, Learning Vector Quantization
Membangun Platform Digital Desa Margamulya Tanjung Kait Untuk Menuju Masyarakat Society 5.0 Hayat, Cynthia; marcel, marcel; Putro, Endi; Windarto, Yudhi; Perangin Angin, Prasasti; Mudita, Damida Shu; Setiawan, Theodorous Stevanus; Christian, Juan; Putratama, Andhika; Christian, Neil
Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal Vol. 7 No. 2 (2024): April 2024
Publisher : STMIK Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurdimas.v7i2.2872

Abstract

The village of Margamulya Tj. Kait is one of the foster villages of LPPM Ukrida. From the results of interviews and direct observations, there are several main issues faced by partners, including: limited access and dissemination of financial information and village profiles to external parties as well as to the villagers themselves. Community service is conducted by utilizing technology to develop a digital village community ecosystem where social media-based platforms serve as everyday communication, socialization, and collaboration tools. The implementation method is carried out through: (1) development of social media platforms; (2) training on platform usage. With the developed social media platform program, the target output is achieved through the evaluation of activities, where the benefit of interaction between village officials and villagers, as well as the dissemination and access to important information, becomes easier. Keywords: digital platform; village digitalization; digital village; margamulya village
Deep Learning Architecture with Attention-Enhanced U-Net for Analyzing Cell Nuclei in H&E-Stained Tissue Slides Hayat, Cynthia; Soenandi, Iwan Aang
Journal of Information Systems Engineering and Business Intelligence Vol. 12 No. 1 (2026): February
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Background: Accurate segmentation of cell nuclei in histopathological images plays a crucial role in computational pathology, as the results serve as a foundation for various clinical practices, including disease diagnosis, prediction, and prognosis. Deep learning methods like U-Net have greatly enhanced performance, but challenges such as tissue heterogeneity, cell nucleus overlap, and complex staining patterns still exist. Objective: This study aims to assess the effectiveness of the Attention Mechanism model within the U-Net architecture for cell nucleus segmentation in Hematoxylin and Eosin (H&E) stained histopathology images. By focusing on relevant spatial features, the Attention Mechanism is expected to improve the model’s ability to accurately distinguish and segment areas with overlapping cells. Specifically, this study also aims to examine whether the proposed model outperforms the conventional U-Net model. Methods: This study used a quantitative experimental approach, utilizing an H&E-stained histopathology image dataset from Saitama Medical University International Medical Center (SIMC). The Attention-Enhanced U-Net Model was trained and tested on pathologist-annotated cell nucleus data, then evaluated using performance metrics such as Dice Coefficient, Accuracy, Precision, Recall, F1-Score, AUROC Mean, and Intersection over Union (IoU). The experimental results showed that the model produced a Dice Coefficient of 0.927, Precision of 0.889, Recall of 0.861, F1-Score of 0.875, and IoU of 0.793. These findings indicate that the model can accurately capture the structure of a cell nucleus, even in challenging conditions such as different cell shapes and the presence of H&E staining. Results: Furthermore, integrating Attention Mechanisms allows the model to focus on extracting relevant features while reducing background noise. This improves its potential as a reliable segmentation solution in clinical pathology workflows. For future research, it is recommended to validate the model using a larger, more diverse dataset to improve its generalization and reliability in real-world clinical practice. Conclusion: The research concludes that the Attention-Enhanced U-Net model effectively achieves high-precision cell nucleus segmentation in H&E-stained histopathology images. It demonstrates strong performance across five metrics: Dice (0.927), Precision (0.889), Recall (0.861), F1-Score (0.875), and IoU (0.793). The model accurately detects nuclei, even in challenging conditions such as morphological variation, staining artifacts, and overlapping structures. Its attention mechanism improves feature extraction by focusing on relevant regions and reducing background noise, enhancing localization and delineation. The lightweight design supports clinical use with limited resources. Future studies should validate its generalizability on larger, more diverse datasets and clinical scenarios.   Keywords: Cell Nuclei Segmentation, Attention Enhanced U-Net, H&E Staining; Deep Learning, Medical Image Analysis.
Evaluasi Layanan Fintech Shopeepay Melalui Klasifikasi Sentimen Berbasis Support Vector Machine Hayat, Cynthia
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 13 No 1: Februari 2026
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2026131

Abstract

Pertumbuhan pesat layanan fintech di Indonesia mendorong perlunya evaluasi kualitas layanan yang objektif dan berbasis data. Penelitian ini bertujuan untuk mengevaluasi persepsi pengguna terhadap layanan ShopeePay dengan menggunakan pendekatan analisis sentimen berbasis algoritma Support Vector Machine (SVM). Data ulasan pengguna dikumpulkan dari platform digital dan melalui tahapan pra-pemrosesan teks serta ekstraksi fitur menggunakan metode Term Frequency–Inverse Document Frequency (TF–IDF). Dataset dibagi menjadi data latih (80%) dan data uji (20%) untuk membangun serta mengevaluasi model klasifikasi. Hasil pengujian menunjukkan bahwa model SVM mampu mengklasifikasikan sentimen pengguna dengan baik, dengan akurasi mencapai 84% dan F1-score tertinggi pada kategori sentimen positif. Analisis kata dominan mengungkap bahwa sentimen positif didominasi oleh kata seperti “mudah” dan “cepat”, sedangkan sentimen negatif terkait dengan “error” dan “saldo hilang”. Meskipun demikian, analisis kesalahan menunjukkan bahwa model masih menghadapi tantangan dalam menangani ulasan dengan unsur sarkasme, kritik implisit, dan opini campuran, yang dapat memengaruhi ketepatan klasifikasi. Secara praktis, hasil penelitian ini memberikan wawasan strategis bagi pengembang ShopeePay dalam meningkatkan kualitas layanan, terutama melalui optimalisasi fitur transaksi dan penanganan kendala teknis yang sering dikeluhkan pengguna. Dengan demikian, pendekatan analisis sentimen berbasis machine learning ini dapat menjadi alat evaluasi yang efektif untuk meningkatkan pengalaman pengguna dan daya saing layanan fintech di Indonesia.   Abstract The rapid growth of fintech services in Indonesia underscores the need for an objective and data-driven evaluation of service quality. This study aims to assess user perceptions of the ShopeePay service using a sentiment analysis approach based on the Support Vector Machine (SVM) algorithm. User review data were collected from digital platforms and underwent text preprocessing and feature extraction using the Term Frequency–Inverse Document Frequency (TF–IDF) method. The dataset was divided into training (80%) and testing (20%) subsets to build and evaluate the classification model. Experimental results indicate that the SVM model effectively classifies user sentiments, achieving an accuracy of 84% and the highest F1-score in the positive sentiment category. Dominant word analysis revealed that positive sentiments were associated with words such as “easy” and “fast,” while negative sentiments were related to “error” and “lost balance.” However, the error analysis showed that the model still faces challenges in handling reviews containing sarcasm, implicit criticism, and mixed opinions, which can affect classification accuracy. From a practical perspective, the findings provide strategic insights for ShopeePay developers to enhance service quality—particularly by optimizing transaction features and addressing common technical issues reported by users. Consequently, this machine learning-based sentiment analysis approach serves as an effective evaluation tool for improving user experience and strengthening the competitiveness of fintech services in Indonesia.
Extending TAM With Trust And Transparency To Examine AI Adoption In Higher Education Hayat, Cynthia
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 02 (2026): MAY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i02.2577

Abstract

The increasing use of AI in campuses has led to significant changes in the teaching and learning process. However, these changes are followed by several ethical issues related to transparency, trust, and accountability. This study aims to validate the Extended TAM through Trust and Transparency variables that explain the students’ behavioral intentions towards the adoption of AI-driven learning technology. The research design used was an explanatory quantitative design applying an online survey. The sample included 97 undergraduate students in UKRIDA. The collected data were then analyzed using the SEM–PLS method. The results of the model testing showed that cognitive variables (Perceived Usefulness and Perceived Ease of Use) and ethical variables (Trust and Transparency) contribute significantly to forming students’ behavioral intentions, with an R² of 0.66. The finding indicates that the Transparency variable has a positive influence on the Trust and Perceived Usefulness variables, with β values ​​of 0.54 and 0.32, respectively. This study also extends the conventional TAM model by incorporating ethical aspects into the Extended TAM model. The results emphasize the importance of developing transparent and explainable AI systems, strengthening accountability from universities, and increasing AI literacy to support responsible and sustainable AI adoption.
Real-time detection of rider fatigue: a comparative study of black-box and glass-box artificial intelligence approaches Hayat, Cynthia; Soenandi, Iwan Aang; Harsono, Budi
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i2.pp1409-1417

Abstract

Rider fatigue poses a critical safety challenge in two-wheeled vehicle operation due to limited physical protection, increased balance demands, and prolonged exposure to environmental stressors. Effective real-time fatigue detection is essential to mitigate accident risks, particularly in high-traffic regions such as Indonesia. This study presents a comparative analysis of black-box and glass-box artificial intelligence (AI) models for real-time detection of rider fatigue, evaluated through a human factor’s lens emphasizing interpretability, intrusiveness, and cognitive compatibility. Multimodal data comprising physiological signals, behavioral indicators, and environmental context were collected using wearable sensors and rider telemetry to train and assess the models. Experimental results reveal that black-box models, including convolutional neural network (CNN) + long short-term memory (LSTM), random forest (RF), and support vector machine (SVM), achieve superior predictive accuracy (94.3%, 91.5%, and 88.2%, respectively) but lack inherent transparency. Conversely, glass-box models such as decision tree (DT) and logistic regression (LR) offer greater interpretability, a critical factor in safety-sensitive applications, though with reduced accuracy (approximately 83–85%). These findings underscore the trade-off between predictive performance and explainability, highlighting the need to tailor model choice to specific operational requirements. This research advances the design of intelligent, human-centered rider support systems that balance accuracy, transparency, and user trust, fostering safer two-wheeled transportation.
Co-Authors Afrido V. Hutapea Budi Harsono Cancerita, Stefani Christian, Juan Christian, Neil Endi Putro Gisela Nina Sevani Iwan Aang Soenandi Jenny Rosenta Ulina Purba Limong, Samuel Marcel Marcel Mega Putri Oktaviani Mudita, Damida Shu Panggeso, David Perangin Angin, Prasasti Putratama, Andhika Sagala, Noviyanti Setiawan, Theodorous Stevanus Usen, Yolan Anjani Yudhi Windarto