cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
,
INDONESIA
Emerging Science Journal
Published by Ital Publication
ISSN : 26109182     EISSN : -     DOI : -
Core Subject : Social,
Environmental Science
Emerging Science Journal is not limited to a specific aspect of science and engineering but is instead devoted to a wide range of subfields in the engineering and sciences. While it encourages a broad spectrum of contribution in the engineering and sciences. Articles of interdisciplinary nature are particularly welcome.
Arjuna Subject : -
Articles 1,093 Documents
 105   106   107   108   109 
HyDNN: A Hybrid Deep Learning Approach for Phishing URL Detection Divya J. Dsouza; Anisha P. Rodrigues; Roshan Fernandes; Vijaya Padmanabha; Mohamed S. Yoosuf
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-033

Abstract

Phishing is an online attack in which attackers trick victims into disclosing their sensitive information, such as credentials, financial portal pins, and OTPs, with the intention of identity or financial theft, jeopardizing reputations, and posing a risk to netizens. As the stakes are high, attackers invest considerable effort and time in committing organized crimes to steal valuable user information. The research carried out aims to detect phishing websites using machine learning and deep learning models. In this research, the classification models are applied to three different phishing website datasets, namely the Mendeley phishing dataset and the UCI dataset, which belong to binary classification, and one dataset that falls under multi-class classification. These datasets are publicly available for research. A custom data set is also prepared from recently available websites to reduce the potential bias in the already available data set. The reason for choosing a publicly available dataset is to validate and compare the results obtained from the custom dataset. To optimize the process, various feature selection techniques and dimensional reduction methods are applied, and a comparison of all approaches is summarized. Performance metrics are used for binary and multi-class classification, and then the outcomes obtained are summarized. The Random Forest model performs well with most feature selection techniques by achieving the best accuracy of 98.24% using the embedded feature selection approach for the Mendeley data set, 94.78% for the UCI data set, and 90.57% for the custom data set. Hence, using Random Forest as the base model, deep learning approaches, namely, CNN and LSTMs, are used to check the efficiency. This study shows that the proposed Hybrid Deep Neural Network approach, HyDNN, performs better, providing the best result with an accuracy of 98.87% for the Mendeley dataset, 97.63% for the UCI dataset, and 93.77% for the custom dataset.
Detecting Fake Images Generated by Artificial Intelligence Using Deep Learning Approach Ahmet E. Topcu; Yehia I. Alzoubi; Emre Camalan; Ersin Elbasi; Mohammad K. I. AlQallaf
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-07

Abstract

The rapid progress in artificial intelligence has enabled the creation of highly realistic images, leading to concerns about the credibility and genuineness of visual content. This study aims to address the growing challenge of verifying the authenticity of digital images in the era of advanced generative artificial intelligence by developing an effective method to detect AI-generated (deepfake) images. To achieve this objective, we employed a Machine Learning (ML) framework based on Convolutional Neural Networks (CNNs), evaluating five established architectures, VGG19, ResNet50, Xception, DenseNet-121, and InceptionV3, through a systematic pipeline involving dataset compilation, image preprocessing, feature extraction, model training, and rigorous validation. Our experimental analysis demonstrates that DenseNet-121 and InceptionV3 achieve state-of-the-art performance, both attaining 98% accuracy in distinguishing AI-synthesized images from real ones, despite a non-negligible error rate observed in other models. These findings highlight the viability of CNN-based approaches for reliable deepfake detection. The novelty of this work lies in its comparative assessment of multiple CNN architectures on a curated dataset of AI-generated imagery, offering practical insights into model selection for forensic and security applications. The proposed method contributes a robust, scalable solution with significant implications for digital content moderation, cybersecurity, and multimedia forensics, where timely and accurate identification of synthetic media is increasingly critical.
Gold Price Forecasting Using Machine Learning Models with Hyperparameter Optimization for Inflation Hedging Joan Sim Pei Suan; Kalaiarasi Sonai Muthu Anbananthen; Raj Kumar Kanan
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-016

Abstract

Gold serves as a hedge against inflation, particularly in emerging markets such as Malaysia, where macroeconomic volatility is pronounced. This study evaluates the predictive performance of six machine learning models; comprising ensemble models (Random Forest, XGBoost, Gradient Boosting Machine, and LightGBM) and deep learning models (Long Short-Term Memory and Gated Recurrent Units) in forecasting Malaysia's gold prices using monthly macroeconomic data from 2009 to 2024. Key indicators include inflation rates, interest rates, exchange rates, oil prices, and stock indices. Hyperparameter tuning is performed using the Optuna framework by comparing three optimization strategies: Tree-structured Parzen Estimator (TPE), Grid Search, and Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Experimental results show that Gradient Boosting, optimized via CMA-ES, achieves the best performance (RMSE = 101.26, R² = 0.9972) using the complete feature set. While deep learning models demonstrate improvements following optimization, ensemble models consistently outperform them due to better alignment with the static, cross-sectional nature of the dataset. Feature importance analysis identifies GP_Low, GP_High, and both domestic and international inflation and interest rates as the most significant predictors. This study contributes by benchmarking ensemble and deep learning models, evaluating multiple hyperparameter optimization strategies, and identifying key macroeconomic indicators relevant to gold price forecasting. The findings provide valuable insights for investors, financial analysts, and policymakers in economies sensitive to inflation.
LeukocyteNet: An Explainable Transfer-Transformer Fusion Learning Model for Leukocyte Classification Tasnim Sakib Apon; Md. Golam Rabiul Alam; Md. Tanzim Reza; Sangita Baidya; Mohammad F. Tahmid; Md. Ashraful Alam; Farhan Faruk; H. M. Sarwer Alam; Muhammad Almoyad; Khondokar Fida Hasan; Mohammad Ali Moni
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-03

Abstract

White Blood Cells (WBCs), or leukocytes, are essential components of the immune system that protect the body against infections and malignant disorders. Even minor fluctuations in leukocyte count can indicate serious pathological conditions, including life-threatening malignancies such as leukemia, lymphoma, and myelodysplastic syndromes. Conventional diagnosis through manual microscopic examination is time-consuming, subjective, and heavily dependent on the pathologist’s expertise. To overcome these challenges, this study introduces LeukocyteNet, a transfer–transformer fusion model designed for the automated classification of ten malignant leukocyte categories. The model integrates convolutional feature extraction from VGG19 with the Swin Transformer’s global attention mechanism, enabling robust representations of both local morphology and global spatial dependencies. The LeukocyteNet model was trained on three publicly available datasets “ALL-IDB, the American Society of Hematology Image Bank, and Tehran Taleqani Hospital” and achieved an overall accuracy of 97.34%, a macro-averaged F1-score of 0.95, and a recall of 0.93, outperforming all evaluated baseline models. Furthermore, the inclusion of explainable AI techniques Grad-CAM, LIME, and Saliency Map enhances explainability by visualizing class-specific decision regions, thereby increasing clinical transparency and reliability. These findings demonstrate that LeukocyteNet not only achieves state-of-the-art predictive performance but also provides interpretable insights critical for trustworthy medical diagnostics.
Epistemological Beliefs, Digital Literacy, and Cultural Attitudes in Shaping Students Entrepreneurial Knowledge Marleni; Disman; Harri Mulyadi; Neiny Ratmaningsih; Cicilia Melinda; Suehartono Syam; Siti Fathimah; Siti Kulsum
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-029

Abstract

The development of higher education in the digital era presents new challenges for students, particularly in developing entrepreneurial competencies that are relevant to global needs while also rooted in local cultural values. The integration of cognitive aspects, digital skills, and cultural attitudes is becoming increasingly important in producing a young generation capable of innovating and competing in the face of globalization. Although various previous studies have highlighted the role of epistemological beliefs, digital literacy, and cultural attitudes separately, studies that integrate all three within the framework of strengthening entrepreneurial knowledge are still limited, especially in Indonesia. This study investigates the impact of epistemological beliefs and digital literacy on shaping students' cultural attitudes and entrepreneurial knowledge within the context of higher education in Indonesia. Using a quantitative approach and an explanatory survey method, data were collected from 398 students and analyzed using Structural Equation Modelling with Partial Least Squares (SEM-PLS). The results indicate that epistemological beliefs have a significant and positive impact on digital literacy, cultural attitudes, and entrepreneurial knowledge, thereby confirming their pivotal role in the development of entrepreneurial competencies. Digital literacy also has a significant, albeit relatively weaker, influence on cultural attitudes and entrepreneurial knowledge. Furthermore, cultural attitudes proved to be a significant mediator, strengthening the relationship between cognitive and digital factors and entrepreneurial achievement. This research model demonstrated high predictive power, accounting for 69.0% of the variance in entrepreneurial knowledge. These findings enrich the literature by integrating cognitive, technological, and cultural dimensions into a comprehensive framework for entrepreneurship education.
Determinants of Climate Change Disclosure in Carbon-Intensive Firms: Evidence from the GCC Region Razan Albaqali; Hessa Al-Fadhel
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-028

Abstract

This study examines Climate Change Disclosure (CCD) among carbon-intensive firms in the Gulf Cooperation Council (GCC) region and identifies the key firm- and country-level factors shaping such disclosure. Using cross-sectional data from 212 listed firms operating in carbon-intensive sectors in 2022, the study employs a disclosure index tailored to the GCC context and conducts a content analysis of annual and sustainability reports to measure disclosure practices. The results reveal low disclosure levels and limited external assurance of the disclosed information. A multiple regression model is developed to assess the effect of financial attributes, governance characteristics, and national environmental performance on CCD. The results confirm that firm size, leverage, Global Reporting Initiative (GRI) adoption, the presence of sustainability or environmental committees, and countries’ Environmental Performance Index (EPI) scores significantly and positively influence CCD, whereas firm age, profitability, and board independence do not have a significant impact on disclosure. To the best of the authors’ knowledge, this study provides the first empirical evidence of CCD determinants in the GCC, a carbon-reliant region with limited scholarly attention, and introduces a disclosure index adapted to regional reporting practices. The insights provided by the study offer practical value for regulators and stakeholders aiming to advance corporate transparency and climate accountability.
The Impact of Socio-Technical Determinants and Mediating Mechanisms on AI Adoption in Internal Auditing Sunanta Supapon; Kalyaporn Pan-Ma-Rerng
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-026

Abstract

This study examines how socio-technical factors shape the adoption of artificial intelligence (AI) in internal auditing. A theory-driven model links organisational readiness, management support, auditors’ perceptions, and attitudes to AI adoption through direct and mediated pathways. Survey data from 340 listed firms were analysed using covariance-based structural equation modelling (CB-SEM) in AMOS, employing bias-corrected bootstrapping with 5,000 resamples to assess construct validity, model fit, and mediation effects. The results indicate that management support is the strongest driver, enhancing auditors’ perceptions and attitudes. Attitude emerges as the most potent predictor of adoption, whereas perception affects adoption only indirectly through attitude, confirming indirect-only mediation. Organisational readiness is not statistically significant, implying that infrastructure alone does not ensure adoption without leadership commitment and behavioural alignment. By integrating the Resource-Based View and the Technology Acceptance Model with institutional insights, the study advances understanding of how organisational resources, behavioural mechanisms, and institutional pressures jointly influence sustainable AI adoption in internal auditing. The findings emphasise the importance of executive sponsorship, role-specific AI literacy, and participatory system design while informing policy on competency and governance frameworks for effective AI integration.
Bank Stability Under ESG Uncertainty: Evidence from Threshold Regression, Causal Forest and SHAP Explanations Phan Dien Vy; Pham Thuy Tu
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-06

Abstract

This paper investigates the nonlinear effects of ESG-related macroeconomic uncertainty on bank stability in Vietnam, an emerging market undergoing rapid financial transformation. Using an integrated empirical framework that combines panel threshold regression, Causal Forest estimation, and SHAP explanations, the analysis explores how ESG-related uncertainty interacts with income diversification and FinTech development to influence bank resilience. The results indicate an inverted U-shaped relationship between ESG uncertainty and bank stability, suggesting that moderate uncertainty enhances governance discipline, whereas excessive uncertainty erodes resilience. Income diversification (IDI) and FinTech growth (G_FINTECH) also display threshold-dependent and nonlinear impacts, where moderate diversification strengthens stability, and FinTech becomes stabilizing only beyond a maturity threshold. Robustness tests using alternative measures of bank stability (non-performing loans - NPL) and ownership heterogeneity confirm that private banks are more sensitive to ESG shocks than state-owned counterparts. The study contributes by introducing a novel hybrid framework integrating threshold models with causal machine learning to capture nonlinear and heterogeneous effects, providing new evidence from Vietnam’s nascent ESG and FinTech landscape, and offering policy implications for regulators and banks to manage ESG uncertainty, optimize diversification, and promote sustainable FinTech-driven stability.
Steady and Transient CFD Analysis of a Vertical Axis Ocean Current Turbine Rasgianti; Agus Suprianto; Ariyana D. Nugraha; Teguh Muttaqie; Ristiyanto Adiputra
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-04

Abstract

Vertical-axis turbines (VATs) are a promising hydrokinetic technology for harvesting renewable energy from ocean currents. Still, their performance depends strongly on design parameters and flow interaction at different azimuthal angles. This study evaluates the performance of a VAT using computational fluid dynamics (CFD) simulations carried out under both steady-state and transient flow conditions. ANSYS CFX is used in the steady-state analysis to estimate torque and power output at various flow velocities and rotational speeds (RPM). At the same time, ANSYS Fluent is applied in the transient analysis to examine time-dependent torque behavior and azimuthal effects under unsteady flow. The steady-state results show that torque and power increase with higher flow velocity and rotational speed, reaching maximum values of 37,079 Nm and 291.86 kW at 4 m/s and 40 RPM. The transient results indicate periodic torque oscillations that become more stable at higher flow velocities, with peak turbine efficiency at 3 m/s, followed by a decrease at 4 m/s due to possible hydrodynamic losses. These findings provide clearer insight into VAT performance under realistic operating conditions and may support future efforts to improve hydrokinetic turbine design.
A Synergistic Model of Technological Capacity, Institutions, and Culture in the Transition Towards Society 5.0: Cross-Country Evidence Ruslan Puzikov; Vadim Ponkratov; Victor Renobell; Nurlan Kaldibayev; Marina Vasiljeva; Maria Volkova; Larisa Ovcharenko; Dostonbek Eshpulatov; Elena Kireeva; Olesya Dudnik
Emerging Science Journal Vol. 10 No. 3 (2026): June
Publisher : Ital Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28991/ESJ-2026-010-03-035

Abstract

This study elucidates global variation in achieving Society 5.0 objectives by identifying the foundational requirements, thresholds, and synergistic configurations of technological and AI capacity, institutional quality, and cultural values across nations. The research develops a novel conceptual model that integrates core determinants while accounting for country-specific conditions in the transition towards a human-centered society. Utilizing a harmonized dataset encompassing 102 countries, this study employs hierarchical multiple regression and three-way interaction modeling to evaluate the direct, conditional, and higher-order effects of technological readiness and its interaction with institutional and cultural values on Human-Centered Outcomes (HCO). The empirical results demonstrate that technological advancement and AI readiness alone are insufficient to generate meaningful societal progress. Instead, institutional quality emerges as the most robust predictor, significantly amplifying the relationship between digital capacity and human-centered outcomes. Among cultural dimensions, power distance exhibits the most pronounced constraining effect, while individualism and long-term orientation display consistent but statistically weaker patterns. These findings elucidate the paradox of divergent national outcomes arising from AI integration, leading to a new country taxonomy based on empirical proximity to the Society 5.0 benchmark. Ultimately, the article challenges technocentric narratives and advances a co-evolving concept of socially embedded change, providing actionable insights into how technological, institutional, and cultural pillars must be aligned to foster inclusive and well-being-oriented digital transformation.

Page 107 of 110 | Total Record : 1093

 105   106   107   108   109 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol. 10 No. 3 (2026): June Vol. 10 No. 2 (2026): April Vol. 10 No. 1 (2026): February Vol. 9 No. 6 (2025): December Vol. 9 No. 5 (2025): October Vol. 9 No. 4 (2025): August Vol. 9 No. 3 (2025): June Vol 9, No 1 (2025): February Vol. 9 No. 1 (2025): February Vol. 9 (2025): Special Issue "Emerging Trends, Challenges, and Innovative Practices in Education" Vol 8, No 6 (2024): December Vol. 8 No. 5 (2024): October Vol 8, No 5 (2024): October Vol 8, No 4 (2024): August Vol 8, No 3 (2024): June Vol 8, No 2 (2024): April Vol 8, No 1 (2024): February Vol. 8 (2024): Special Issue "Current Issues, Trends, and New Ideas in Education" Vol 8 (2024): Special Issue "Current Issues, Trends, and New Ideas in Education" Vol. 7 (2023): Special Issue "COVID-19: Emerging Research" Vol 7 (2023): Special Issue "COVID-19: Emerging Research" Vol 7, No 6 (2023): December Vol 7, No 5 (2023): October Vol 7, No 4 (2023): August Vol 7, No 3 (2023): June Vol 7, No 2 (2023): April Vol 7, No 1 (2023): February Vol 7 (2023): Special Issue "Current Issues, Trends, and New Ideas in Education" Vol. 7 (2023): Special Issue "Current Issues, Trends, and New Ideas in Education" Vol. 6 (2022): Special Issue "COVID-19: Emerging Research" Vol 6 (2022): Special Issue "COVID-19: Emerging Research" Vol 6, No 6 (2022): December Vol 6, No 5 (2022): October Vol 6, No 4 (2022): August Vol 6, No 3 (2022): June Vol 6, No 2 (2022): April Vol 6, No 1 (2022): February Vol 6 (2022): Special Issue "Current Issues, Trends, and New Ideas in Education" Vol. 6 (2022): Special Issue "Current Issues, Trends, and New Ideas in Education" Vol 5 (2021): Special Issue "COVID-19: Emerging Research" Vol. 5 (2021): Special Issue "COVID-19: Emerging Research" Vol 5, No 6 (2021): December Vol 5, No 5 (2021): October Vol 5, No 4 (2021): August Vol 5, No 3 (2021): June Vol 5, No 2 (2021): April Vol 5, No 1 (2021): February Vol 4 (2020): Special Issue "IoT, IoV, and Blockchain" (2020-2021) Vol. 4 (2020): Special Issue "IoT, IoV, and Blockchain" (2020-2021) Vol 4, No 6 (2020): December Vol 4, No 5 (2020): October Vol 4, No 4 (2020): August Vol 4, No 3 (2020): June Vol 4, No 2 (2020): April Vol 4, No 1 (2020): February Vol 3, No 6 (2019): December Vol 3, No 5 (2019): October Vol 3, No 4 (2019): August Vol 3, No 3 (2019): June Vol 3, No 2 (2019): April Vol 3, No 1 (2019): February Vol 2, No 6 (2018): December Vol 2, No 5 (2018): October Vol 2, No 4 (2018): August Vol 2, No 3 (2018): June Vol 2, No 2 (2018): April Vol 2, No 1 (2018): February Vol 1, No 4 (2017): December Vol 1, No 3 (2017): October Vol 1, No 2 (2017): August Vol 1, No 1 (2017): June More Issue