Article Per Year (5 Year)
p-Index From 2021 - 2026
5.002
P-Index
This Author published in this journals
All Journal Jurnal Teknologi JUITA : Jurnal Informatika JOIN (Jurnal Online Informatika) Science and Technology Indonesia JOIV : International Journal on Informatics Visualization Emerging Science Journal Jurnal Varian Journal of Robotics and Control (JRC) Journal of Applied Data Sciences International Journal for Applied Information Management Maritime Park: Journal Of Maritime Technology and Socienty Bulletin of Applied Mathematics and Mathematics Education Jurnal Pemberdayaan Masyarakat Journal of Current Research in Blockchain International Journal Research on Metaverse
Dewi, Deshinta Arrova
Unknown Affiliation
Aerospace Engineering Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Social Sciences Other

Published : 40 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 40 Documents
Search

 1   2   3   4 
Detecting Gender-Based Violence Discourse Using Deep Learning: A CNN-LSTM Hybrid Model Approach Kurniawan, Tri Basuki; Dewi, Deshinta Arrova; Henderi, Henderi; Hasibuan, M. Said; Zakaria, Mohd Zaki; Ismail, Abdul Azim Bin
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.v6i3.761

Abstract

Gender-Based Violence (GBV) is a critical social issue impacting millions worldwide. Social media discussions offer valuable insights into public awareness, sentiment, and advocacy, yet manually analyzing such vast textual data is highly challenging. Traditional text classification methods often struggle with contextual understanding and multi-class categorization, making it difficult to accurately identify discussions on Sexual Violence, Physical Violence, and other topics. To address this, the present study proposes a hybrid deep learning approach combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. CNN is utilized for extracting key linguistic features, while LSTM enhances the classification process by maintaining sequential dependencies. This hybrid CNN+LSTM model is evaluated against standalone CNN and LSTM models to assess its performance in classifying GBV-related tweets. The dataset was sourced from Kaggle, containing real-world Twitter discussions on GBV. Experimental results demonstrate that the hybrid model surpasses both CNN and LSTM models, achieving an accuracy of 89.6%, precision of 88.4%, recall of 89.1%, and F1-score of 88.7%. Confusion matrix and ROC curve analyses further confirm the hybrid model’s superior performance, correctly identifying Sexual Violence (82%), Physical Violence (15%), and Other (3%) cases with reduced misclassification rates. These results suggest that combining CNN’s feature extraction with LSTM’s contextual learning provides a more balanced and effective classification model for GBV-related text. This work supports the development of AI-based tools for social media monitoring, policy-making, and advocacy, helping stakeholders better understand and respond to GBV discussions. Future research could explore transformer-based models like BERT and real-time classification applications to further improve performance.
Navigating Heart Stroke Terrain: A Cutting-Edge Feed-Forward Neural Network Expedition Praveen, S Phani; Mantena, Jeevana Sujitha; Sirisha, Uddagiri; Dewi, Deshinta Arrova; Kurniawan, Tri Basuki; Onn, Choo Wou; Yorman, Yorman
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.v6i3.763

Abstract

Heart stroke remains one of the leading causes of death worldwide, necessitating early and accurate prediction systems to enable timely medical intervention. While a variety of machine learning approaches have been employed to address this issue, including Logistic Regression, Decision Trees, Random Forests, Support Vector Machines, and K-Nearest Neighbors, these models often suffer from limitations such as overfitting, insufficient generalization, poor performance on imbalanced datasets, and inability to capture complex nonlinear patterns in clinical data. Additionally, many existing works do not comprehensively integrate both clinical and demographic features or lack rigorous evaluation metrics beyond accuracy alone. This study proposes a novel Feed-Forward Neural Network (FFNN) model for heart stroke prediction, designed to overcome the shortcomings of conventional models. Unlike shallow classifiers, the FFNN architecture employed here leverages multiple hidden layers and nonlinear activation functions to learn intricate relationships within the dataset. The dataset used comprises various attributes such as age, hypertension, heart disease, BMI, and smoking status, which were preprocessed through normalization, one-hot encoding, and imputation techniques to ensure data quality and model performance. Experiments were conducted using a stratified train-test split, and the model was trained using the Adam optimizer with carefully tuned hyperparameters. Comparative evaluations against baseline models (Logistic Regression, Random Forest, and SVM) were carried out using precision, recall, F1-score, and ROC-AUC as performance metrics. The proposed FFNN achieved the highest accuracy of 96.47%, along with substantial improvements in recall and F1-score, highlighting its superior capability in identifying potential stroke cases even in imbalanced datasets. This work bridges a significant gap in heart stroke prediction by demonstrating the effectiveness of deep learning models—specifically FFNNs—in extracting complex patterns from diverse patient data. It also sets the stage for further exploration of deep learning-based clinical decision support systems.
Improving Classification Accuracy of Breast Ultrasound Images Using Wasserstein GAN for Synthetic Data Augmentation Mas Diyasa, I Gede Susrama; Humairah, Sayyidah; Puspaningrum, Eva Yulia; Durry, Fara Disa; Lestari, Wahyu Dwi; Caesarendra, Wahyu; Dewi, Deshinta Arrova; Aryananda, Rangga Laksana
Journal of Robotics and Control (JRC) Vol. 6 No. 4 (2025)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v6i4.25075

Abstract

Breast cancer remains one of the most prevalent cancers in Indonesia, and early detection plays a vital role in improving patient outcomes. Ultrasound imaging is a non-invasive and accessible technique used to classify breast conditions into normal, benign, or malignant categories. The advancement of deep learning, particularly Transfer Learning with Convolutional Neural Networks (CNNs), has significantly enhanced the performance of automated image classification. However, the effectiveness of CNNs heavily relies on large, balanced datasets—resources that are often limited and imbalanced in medical domains. To address this issue, this study explores the use of Wasserstein Generative Adversarial Networks (WGAN) for synthetic data augmentation. WGAN is capable of learning the underlying distribution of real ultrasound images and generating high-quality synthetic samples. The inclusion of the Wasserstein distance stabilizes training, with convergence observed around 2500–3000 epochs out of 5000. While synthetic data improves classifier performance, there remains a potential risk of overfitting, particularly when the synthetic images closely mirror the training data. Compared to traditional augmentation techniques such as rotation, flipping, and scaling, WGAN-generated data provides more diverse and realistic representations. Among the tested models, VGG16 achieved the highest accuracy of 83.33% after WGAN augmentation. Nonetheless, computational resource limitations posed challenges in training stability and duration. Furthermore, issues related to model generalizability, as well as ethical and patient privacy considerations in using synthetic medical data, must be addressed to ensure responsible deployment in real-world clinical settings.
Progressive Massive Fibrosis Detection Using Generative Adversarial Networks and Long Short-Term Memory Irianto, Suhendro Y.; Karnila, Sri; Hasibuan, M.S.; Dewi, Deshinta Arrova; Kurniawan, Tri Basuki; Kurniawan, Hendra
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.707

Abstract

Contribution: Progressive Massive Fibrosis (PMF) is a severe form of pneumoconiosis, affecting individuals exposed to mineral dust, such as coal miners and workers in the artificial stone industry. This condition causes significant pulmonary impairment and increased mortality. Early and accurate detection is vital for effective management, yet traditional diagnostic methods face challenges in differentiating PMF from other pulmonary diseases due to variability in clinical presentations and limitations in imaging techniques. Idea: The study introduces a novel diagnostic framework that integrates Generative Adversarial Networks (GAN) and Long Short-Term Memory (LSTM) networks to enhance the detection and monitoring of PMF. The GAN generates high-fidelity synthetic imaging data to address the issue of limited datasets, while the LSTM network captures temporal patterns in patient data, enabling real-time monitoring of disease progression. Objective: The primary objective of this research is to develop an AI-driven model that improves the accuracy and efficiency of PMF detection and monitoring, facilitating early diagnosis and better treatment planning. Findings: The integrated GAN-LSTM model significantly outperformed traditional diagnostic methods. It proved high accuracy, a Dice coefficient of 0.85, and an Area Under the Curve (AUC) of 0.92, showing precise differentiation of PMF from other pulmonary conditions, such as lung cancer and tuberculosis. Results: The GAN-LSTM framework achieved an accuracy of 91.3%, suggesting that the fusion of GAN and LSTM technologies can effectively address the challenges of limited datasets and heterogeneous disease progression. The model showed promise in enhancing the non-invasive detection and ongoing monitoring of PMF. Novelty: This research stands for a significant advancement in PMF diagnostics by combining GAN and LSTM technologies in a single framework. This approach improves diagnostic accuracy and eases continuous disease monitoring, offering a non-invasive and highly precise solution for PMF detection.
Multivariate Risk Analysis of Echotoxic Chemicals of Ballast Water Chemicals Based on PCA and DSS Using ECOTOX GISIS Data Setiawan, Ariyono; Widyaningsih , Upik; Pamungkas, Anjar; Bin Abdul Hadi, Abdul Razak; Dewi, Deshinta Arrova
Maritime Park: Journal of Maritime Technology and Society Volume 4, Issue 3, 2025
Publisher : Department of Ocean Engineering, Faculty of Engineering, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62012/mp.vi.44925

Abstract

This study proposes a multivariate risk classification model for ballast water treatment chemicals by integrating global datasets—ECOTOX (U.S. EPA) and GISIS (IMO). Using Principal Component Analysis (PCA), we analyze 37 substances based on acute toxicity (LC50), chronic toxicity (NOEC), and bioaccumulation potential (BCF). The aim is to provide a practical, data-driven tool to support ecological compliance, early warnings, and regulatory prioritization in maritime chemical management. Results show that 43.24% of substances fall into the high-risk category, while only 8.11% are low risk. PCA effectively reduces dimensionality, explaining 73.63% of variance with just two components. High-risk chemicals such as Dibromoacetic acid and Dichloroacetonitrile exhibit low NOEC and high BCF values—indicating significant ecotoxic potential, often underregulated. Some commonly used oxidants also reveal hidden chronic toxicity, suggesting gaps in current risk frameworks post-BWM Convention. We construct a risk-scoring matrix and chemical heatmap to visualize ecotoxic profiles, enabling real-time risk ranking and decision support. Unlike previous studies that focus solely on toxicity thresholds or narrative reviews, this approach integrates empirical data with decision logic to aid Port State Control (PSC) and IMO policy design. The method is replicable and adaptable to other maritime pollutants, especially in the ASEAN context, enhancing smart port readiness and ecological safeguarding.
MICE and ADASYN for Missing Data Imputation and Imbalanced Data Handling on Heart Disease Classification Desiani, Anita; Dewi, Deshinta Arrova; Amran, Ali; Pratiwi, Ananda; Andriani, Yuli; Cahyono, Endro Setyo
Science and Technology Indonesia Vol. 10 No. 4 (2025): October
Publisher : Research Center of Inorganic Materials and Coordination Complexes, FMIPA Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/sti.2025.10.4.1020-1030

Abstract

The quality of data is determined by several things, namely the completeness and balance data. The heart disease dataset from the University of California, Irvine (UCI) has missing and imbalanced data, which if it is not handled, can lead to a lack of accuracy in the prediction model and errors in interpreting the data. To overcome missing data, several methods can be used, one of which is data imputation. Attributes with missing data of 5% or less are handled using imputation methods such as Mean, Mode, and MICE. Attributes with numeric types are handled by Mean. Attributes with categorical types are imputed byMode. Attributes with more than 5% missing data are imputed using the MICE method. Imbalanced data can be handled by applying an oversampling method using the Adaptive Synthetic Sampling Approach (ADASYN). The effect of imputing missing data and addressing class imbalance on heart disease classification performance was tested using Random Forest, Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP) algorithms. After handling missing values and data imbalance, improvements were observed in the classification results. The accuracy, precision, recall, and F1-score showed excellent performance, above 90% on several classification methods. The results indicate that handling missing and imbalanced data through Mean, Mode, MICE, and ADASYN positively impacts the performance of classifiers on the UCI heart disease dataset.
Data Analysis of Social Media's Impact on COVID19 Pandemic Users' Mental Health Dewi, Deshinta Arrova
JOIN (Jurnal Online Informatika) Vol 7 No 1 (2022)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v7i1.912

Abstract

Social media has a significant impact on people's daily lives and spread widely. Unrestrained usage of social media could have worsening consequences on mental health. The majority of COVID-19 users who were exposed to social media learned numerous facts, which made their anxiety and depression-related mental health disorders worse. This study aims to determine how social media usage affects users' mental health during the COVID19 pandemic. Through surveys and expert interviews, this study collects both quantitative and qualitative data. The total number of respondents involved was 106 with the average age group of 18-41-year-old. Using reliability testing (Cronbach alpha test) and inferential statistic (Pearson Correlation and Chi-Square), results show that during the COVID19 pandemic, there is a significant link between social media use and mental health. Anxiety and depression brought on by social media are more common among young adults, predominantly female, between the ages of 18 and 24 than in men. Additionally, correlation plot analysis with a variety of queries reveals the mental health issues and activities on social media.
Natural Disaster Mapping on Java Island Using Biplot Analysis Widyangga, Pressylia Aluisina Putri; Mardianto, M. Fariz Fadillah; Pratiwi, Firda Aulia; Putrie, Andi Vania Ghalliyah; Andriani, Putu Eka; Amelia, Dita; Dewi, Deshinta Arrova
Jurnal Varian Vol. 7 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v7i2.2634

Abstract

Indonesia is located in the ring of fire region. This condition causes Indonesia to have the potential to experience various disasters, such as volcano eruptions. In addition, rapid population growth has led to rampant land conversions that cause floods, landslides, tornadoes, droughts, and forest fires. The research aims to map natural disasters in Indonesia, especially Java Island to find out the provinces and their natural disasters tendency using Biplot analysis. Based on the results, Central Java, East Java, and West Java have a tendency to have floods and landslides. East Java tends to undergo earthquakes and Central Java has the potential to experience volcano eruptions. Through the natural disasters mapping, the government, especially the BMKG, will be able to find various solutions to overcome the natural disasters that have great potential to occur in provinces in Indonesia, especially Java Island as the manifestation toward SDGs Target 2030.
Predicting Throughput and Latency in Hyperledger Fabric Blockchains Using Random Forest Regression Dewi, Deshinta Arrova; Kurniawan, Tri Basuki
Journal of Current Research in Blockchain Vol. 2 No. 1 (2025): Regular Issue March
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jcrb.v2i1.27

Abstract

The study focuses on enhancing the performance optimization of Hyperledger Fabric blockchains through predictive modeling using Random Forest regression. It emphasizes the importance of accurately predicting two critical performance metrics—throughput (measured in transactions per second or TPS) and latency (defined as the time taken to confirm transactions). These metrics directly influence the efficiency and user experience of blockchain applications, making their accurate prediction essential for configuring blockchain networks effectively. The research leverages data collected through Hyperledger Caliper, a benchmarking tool, which provides detailed measurements of various configuration parameters, including block size, transaction arrival rate, and the number of orderer nodes. Through rigorous exploratory data analysis, the study identifies how these parameters impact throughput and latency, revealing complex interdependencies that challenge traditional optimization approaches. Using Random Forest regression, a robust ensemble learning method, the study demonstrates that the predictive model can achieve high accuracy. The performance of the model is assessed using metrics such as R-squared values, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE), which collectively underscore its ability to offer reliable predictions across varying configurations. The results of this research provide practical insights for blockchain administrators, allowing them to configure Hyperledger Fabric settings more efficiently, thereby reducing the trial-and-error process typically involved in performance tuning. Moreover, the study's findings contribute to the broader field of blockchain performance optimization by offering a data-driven framework that bridges theoretical analysis with practical application in real-world scenarios. Looking forward, the study suggests avenues for future research, including expanding the dataset to cover more diverse blockchain platforms and configurations, incorporating real-world deployment data for validation, and exploring additional machine learning algorithms for even greater predictive accuracy. This approach highlights the critical role of data-driven methodologies in optimizing blockchain network performance and encourages further collaboration and exploration in the domain.
Analyzing the Impact of Social Media and Influencer Endorsements on Game Revenue using Multiple Linear Regression in the Metaverse Dewi, Deshinta Arrova; Kurniawan, Tri Basuki
International Journal Research on Metaverse Vol. 2 No. 2 (2025): Regular Issue June 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijrm.v2i2.29

Abstract

The gaming industry, particularly within the metaverse, has seen significant transformations driven by the integration of social media, influencer marketing, and player engagement metrics. These elements are crucial in shaping the success and revenue generation of games. This study explores the role of social media mentions and influencer endorsements in influencing game revenue, applying DBSCAN clustering to segment player engagement into distinct groups. By analyzing the "Gaming Trend 2024" dataset, which includes key metrics such as social media mentions, influencer endorsements, in-game purchases, and game revenue, we identify patterns in player behavior that directly impact revenue generation. The DBSCAN clustering method was employed to group players based on their social media interactions and influencer influence, identifying key segments that contribute to game success. The results reveal that certain clusters, characterized by higher social media engagement and influencer endorsements, are associated with increased game revenue. In contrast, other segments showed lower engagement and contributed less to overall revenue. The clustering analysis highlights the power of social media and influencers in driving player behavior, which in turn drives financial outcomes for game developers. This research provides insights into how targeted marketing strategies, personalized influencer campaigns, and tailored engagement efforts can enhance game revenue. This study offers practical applications for game developers and marketers in the metaverse, emphasizing the need to leverage clustering insights to optimize marketing strategies and increase revenue. Future research could expand on these findings by integrating sentiment analysis of social media mentions, exploring alternative clustering methods like hierarchical clustering, and developing hybrid models that combine clustering with predictive analytics to forecast game revenue trends.
Co-Authors - Kurniawan, - Achsan, Harry Tursulistyono Yani Adi Wijaya Afriyani, Sintia Alde Alanda, Alde Ali Amran Alqudah, Mashal Kasem Alqudah, Musab Kasim Andri Andri Andriani, Putu Eka Anita Desiani Aris Thobirin, Aris Armoogum, Sheeba Armoogum, Vinaye Aryananda, Rangga Laksana Asro, Asro Aziz, RZ. Abdul Azmi, Nurhafifi Binti Bappoo, Soodeshna Batumalay, Malathy Bin Abdul Hadi, Abdul Razak Bujang, Nurul Shaira Binti Chandra, Anurag Diana Diana Dita Amelia, Dita Elyakim Nova Supriyedi Patty, Elyakim Nova Supriyedi Endro Setyo Cahyono, Endro Setyo Eva Yulia Puspaningrum Fachry Abda El Rahman Fadly Fadly Fara Disa Durry Fatoni, Fatoni Fikri, Ruki Rizal Nul Firosha, Ardian Fuad, Eyna Fahera Binti Eddie Habib, Shabana Hanan, Nur Syuhana binti Abd Hasibuan, M.S. Hasibuan, Muhammad Siad Henderi . Hendra Kurniawan Heng, Chang Ding Hidayani, Nieta Hisham, Putri Aisha Athira binti Humairah, Sayyidah Irianto, Suhendro Y. Irwansyah Irwansyah Ismail, Abdul Azim Bin Isnawijaya, Isnawijaya Jayawarsa, A.A. Ketut Kezhilen, Motean Kijsomporn, Jureerat Kurniawan, Tri Basuki Larasati, Anggit Lexianingrum, Siti Rahayu Pratami Lin, Leong Chi M Said Hasibuan M. Fariz Fadillah Mardianto Maizary, Ary Mantena, Jeevana Sujitha MARIA BINTANG Mas Diyasa, I Gede Susrama Mashal Alqudah Melanie, Nicolas Misinem, Misinem Mohd Salikon, Mohd Zaki Motean, Kezhilen Muhammad Islam, Muhammad Muhammad Nasir Muhayeddin, Abdul Muniif Mohd Murnawan, Murnawan Nathan, Yogeswaran Nazmi, Che Mohd Alif Onn, Choo Wou Pamungkas, Anjar Periasamy, Jeyarani Pratiwi, Ananda Pratiwi, Firda Aulia Praveen, S Phani Putra, Muhammad Daffa Arviano Putrie, Andi Vania Ghalliyah R Rizal Isnanto Rahmadani, Olivia Samihardjo, Rosalim Saringat, Zainuri Setiawan, Ariyono Singh, Harprith Kaur Rajinder Sirisha, Uddagiri Slamet Riyadi Sri Karnila Sri Lestari Sugiyarto Surono, Sugiyarto Sulaiman, Agus Taqwa, Dwi Muhammad Thinakaran, Rajermani Triloka, Joko Trinawarman, Dedi Udariansyah, Devi Wahyu Caesarendra Wahyu Dwi Lestari Wahyuningdiah Trisari Harsanti Putri Wei, Aik Sam Wibaselppa, Anggawidia Widyangga, Pressylia Aluisina Putri Widyaningsih , Upik Wijayanti, Dian Eka Yeh, Ming-Lang Yorman Yuli Andriani Zakari, Mohd Zaki Zakaria, Mohd Zaki