Search Results (149)

This study examines the interconnectedness of the Philippine banking system across three contagion channels: interbank loans, interbank deposits, and payment systems. Using network data from 481 banks supervised by the Bangko Sentral ng Pilipinas (BSP), the study applies topology-based measures to assess the structure and strength of interbank linkages. It introduces two metrics: the Overall Interconnectedness Index (OII), which measures the level of connectedness of the network, and the Core Connectivity Index (CCI), which identifies robustly linked banks within the system. The results show that payments are more interconnected than loans and deposits, but the overall interconnectedness remains very low across all channels. For the full banking system, OII values range from 0.06 to 0.65%, indicating a sparse network structure. In the core network of universal and commercial banks, loans and deposits show modestly higher interconnectedness, while payments display a much stronger core–periphery pattern. The CCI results are consistent with these findings, confirming weak connectedness in the loans and deposits networks and relatively stronger connectedness in the payments network. These findings suggest that the Philippine interbank network has limited potential for contagion through small shocks, but its sparse structure may also reduce risk-sharing capacity and weaken the system’s ability to absorb larger shocks. The proposed measures offer a useful framework for monitoring systemic risk and identifying banks that contribute most to interconnectedness. They also provide policy implications for financial regulators, like BSP, in strengthening financial stability through improved market access, payment system participation, and macroprudential surveillance. Full article

Improving the decoding accuracy and information transfer rate (ITR) of steady-state visual evoked potential brain–computer interface (SSVEP-BCI) systems, while enhancing cross-subject generalization and reducing calibration cost, is essential for practical deployment. This study proposes an end-to-end framework that integrates adaptive filtering with semi-supervised domain adaptation. The framework incorporates a Gabor adaptive filter bank (G-AFB) to optimize time–frequency representations and extract features matched to individual neural responses. It also introduces a three-stage semi-supervised domain-adversarial neural network (TriS-DANN), which combines unsupervised pre-alignment and supervised fine-tuning to align cross-subject feature distributions and enable lightweight calibration. On the 1.0 s public benchmark dataset, G-AFB-tCNN achieved 89.13% accuracy, a 4.63 percentage-point improvement over its conventional filter-bank counterpart. On the 0.4 s in-house dataset, G-AFB-tCNN achieved 91.85% accuracy, a 3.22 percentage-point improvement over the conventional fixed filter bank. In transfer learning, TriS-DANN reached 86.60% accuracy using 0.4 s segments extracted from the stimulation period and only 23.07% of the available target-domain training/calibration trials, demonstrating higher efficiency and stability than conventional fine-tuning. These results support the proposed framework as a feasible route toward reliable, low-calibration SSVEP-BCI systems. Full article

Financial fraud has become a critical challenge for modern financial systems due to the rapid growth of digital transactions, online banking services, and electronic payment platforms. Traditional rule-based fraud detection systems are increasingly inadequate in addressing the evolving and adaptive strategies employed by fraudsters. Consequently, Machine Learning (ML) and Deep Learning (DL) techniques have emerged as powerful tools for detecting fraudulent activities in large-scale financial datasets. This paper presents a comprehensive survey of ML/DL approaches for financial fraud detection. The survey systematically reviews existing research across multiple methodological paradigms, including classical supervised learning, anomaly detection, graph-based methods, deep neural networks, multimodal architectures, and cost-sensitive learning frameworks. Particular emphasis is placed on emerging techniques such as graph neural networks, transformer-based architectures, and federated learning approaches designed to address privacy and scalability challenges. In addition to reviewing model architectures, this work analyzes key challenges inherent to fraud detection systems, including extreme class imbalance, concept drift, adversarial behavior, data privacy constraints, and real-time deployment requirements. Furthermore, the survey examines evaluation methodologies, highlighting the limitations of commonly used metrics and discussing more realistic evaluation strategies that incorporate operational costs and risk management considerations. This paper also provides a structured taxonomy of fraud detection methods, comparative analyses of commonly used datasets, and a synthesis of current research trends. Finally, open challenges and promising research directions are identified, including adaptive learning systems, interpretable Artificial Intelligence models, graph-based behavioral modeling, and privacy-preserving collaborative fraud detection frameworks. Full article

This paper presents UM3D, an end-to-end unsupervised domain adaptation framework for monocular 3D object detection. Monocular 3D object detection is appealing due to its low cost, yet it suffers from limited depth cues and poor cross-domain generalization when labeled data are scarce. Existing Pseudo-LiDAR methods require supervised training and propagate depth estimation errors to downstream detection, while current unsupervised domain adaptation (UDA) approaches exploit only a single modality and lack effective pseudo-label quality control. UM3D addresses these limitations through two key designs: (1) a quality-aware pseudo-label generation strategy with object-level random scaling and a memory bank refinement mechanism; and (2) an end-to-end differentiable pipeline that integrates multimodal fusion of image and Pseudo-LiDAR features with a multi-network consistency loss, which jointly optimizes depth estimation and 3D detection via backpropagation. Notably, the entire pipeline requires only a single monocular camera at inference; the Pseudo-LiDAR representation is generated internally from the same image, and thus the multimodal fusion integrates image and Pseudo-LiDAR features without requiring additional sensors. Extensive experiments across KITTI, nuScenes, Waymo, and Lyft demonstrate that UM3D generally outperforms existing UDA methods. In particular, a 19.30% relative ${\mathrm{AP}}_{\mathrm{BEV}}$ improvement is achieved under easy conditions through end-to-end joint training compared to independent depth estimation, and up to 76.81% of the domain gap is closed on the WOD → KITTI benchmark. Full article

Adolescents and young people (AYP) experience a disproportionate burden of both mental health conditions and HIV, particularly in low- and middle-income countries (LMICs)-nations classified by the World Bank as having lower or middle economies. Mental health problems such as depression, anxiety, and substance use increase HIV (Human Immunodeficiency Virus that attacks the human immune system and leads to various illnesses when untreated) risk, and negatively affect treatment adherence and outcomes. However, mental health remains insufficiently integrated into HIV research and programming. Evidence on how mental health services are operationally integrated into HIV prevention and treatment for this population is limited and fragmented. This scoping review mapped existing evidence on the integration of mental health services into HIV treatment programs for AYP in LMICs, guided by PRISMA-ScR (a guideline used for reporting scoping reviews in research) and the Person–Concept–Context framework, a framework used to define specific research question in research. In this case, the population was adolescents and young people (10–24 years) receiving HIV prevention or treatment services, the concept referring to the integration of mental health interventions such as screening, assessment and counseling within HIV services, and the context focused on low- and middle-income countries (LMICs). PubMed, MEDLINE, Scopus and PsycINFO databases were searched for studies published between 2014 and 2024. Eligible studies reported mental health screening, assessment, treatment, or referral within HIV services for AYP in LMICs. Two reviewers independently screened studies, assessed full texts, and extracted data. Of 634 records identified, ten (10) studies met the inclusion criteria. All were conducted in Sub-Saharan Africa and primarily used qualitative or pilot designs. Four integration approaches were identified: routine mental health screening within HIV services, task-shifting to trained lay providers, peer-led and community-based psychosocial support, and culturally adapted, youth-centered psychological interventions. Common barriers included stigma, low mental health literacy, limited training and supervision, staffing constraints, and weak referral systems. Existing evidence is limited, remains exploratory, preliminary, and largely focused on feasibility and implementation experiences, suggesting that integrating mental health services within adolescent HIV care in LMICs may be feasible and acceptable when approaches are contextually adapted and participatory. Full article

As digital payment infrastructures expand, the incidence of card-not-present fraud has become a major source of operational and financial risk for banks, payment processors, and merchants. In response, financial institutions increasingly rely on data-driven decision systems, yet fraudsters continuously adapt their strategies to evade conventional rule-based controls. A promising way to strengthen risk management is to model transactional data so as to uncover non-trivial, high-dimensional patterns characteristic of fraudulent behavior and to embed these models into real-time decision pipelines. In this work, we develop and compare a suite of learning-based fraud detectors, including a convolutional neural network and several machine learning classifiers, within a unified quantitative risk-management framework. The problem is formulated as a supervised classification task within a quantitative risk management framework, where the cost of missed fraud is particularly critical. The mathematical contribution is methodological rather than architectural: we design a leakage-safe and prevalence-faithful evaluation protocol for extremely imbalanced binary classification, combine cross-validated hyperparameter optimization with risk-aligned model selection based on metrics such as recall and Matthews correlation coefficient, and quantify uncertainty by bootstrap confidence intervals and paired McNemar tests. In addition, we connect statistical evaluation with deployment-time decisioning through a decision-theoretic, cost-sensitive threshold rule, showing how institution-specific false-positive and false-negative costs determine the operating point of the classifier. Because fraudulent transactions constitute only a small proportion of the total volume, we employ resampling strategies to mitigate severe class imbalance and systematically calibrate the models via cross-validated hyperparameter optimization. The empirical analysis on real transaction data shows that carefully tuned deep and ensemble methods can achieve strong fraud-detection performance, while the proposed framework clarifies which performance differences are statistically meaningful and which operating points are most suitable under institution-specific false-positive and false-negative costs. Full article

Cross-age face analysis has emerged as an important topic in biometric recognition due to substantial facial appearance variations caused by aging. Nevertheless, most existing approaches primarily focus on face verification (1:1 matching) and frequently rely on explicit age annotations, which limit their applicability in large-scale retrieval scenarios. In this study, large-scale cross-age face retrieval (1:N matching) is investigated, and a Hybrid Metric Learning Framework (HMLF) is proposed to learn age-invariant and retrieval-oriented facial representations without requiring age labels. The proposed framework integrates Additive Angular Margin Loss (ArcFace) with supervised contrastive learning to enhance feature discriminability. Furthermore, a mixed triplet mining strategy is introduced to improve the effectiveness of hard sample selection. A memory bank-based InfoNCE formulation is incorporated to provide a large number of negative samples, and an uncertainty-based adaptive weighting scheme is designed to automatically balance multiple loss components during optimization. To better simulate realistic retrieval scenarios, an extended cross-age retrieval evaluation protocol is established. Extensive experimental results demonstrate that the proposed framework achieves superior retrieval performance across different backbone architectures. The results further provide systematic insights into the influence of backbone design, loss formulation, and optimization strategies on cross-age retrieval accuracy. Full article

The mathematical characterization of non-stationary signals remains a significant challenge, particularly when impulsive components are obscured by high-dimensional noise and structural coupling. This paper proposes an application-driven mathematical methodology for a learnable discrete wavelet transform (LDWT) that combines classical multi-resolution analysis with task-optimized data-driven adaptivity. Rather than introducing entirely new foundational theory, our approach strategically relaxes constraints from orthogonal wavelet theory within the non-perfect reconstruction filter bank framework, enabling controlled spectral decomposition optimized for supervised fault diagnosis. We introduce a specialized regularization term based on the half-band property to ensure spectral complementarity and minimize cross-band correlation, while a Jacobian-based stabilization approach is formulated to ensure the convergence of filter coefficients during optimization. The proposed algorithmic architecture, LDBRFnet, features a dual-branch encoder system designed to capture the mathematical synergy between sub-band-level global statistics and time-domain local morphology. This dual-view representation effectively mitigates feature leakage and overconfidence in classification. Theoretical analysis and numerical experiments demonstrate that the learned filters satisfy the frequency-shift property and maintain robust spectral partitioning even under low signal-to-noise ratios. Validation on complex vibration datasets confirms that the framework achieves superior diagnostic accuracy (over 95.5%) and computational efficiency, reducing model parameters by 96.7% compared to state-of-the-art baselines. This work provides a generalizable mathematical approach for adaptive signal decomposition and robust pattern recognition in interdisciplinary applications. Full article

The Basel Accords refer to a series of international banking regulatory frameworks developed by the Basel Committee on Banking Supervision to strengthen the stability and resilience of the global banking system. Introduced as Basel I, Basel II, and Basel III, these accords establish minimum capital requirements, risk management standards, and supervisory principles for internationally active banks. Their primary purpose is to reduce the risk of bank failure, promote financial stability, and enhance consistency in banking regulation across jurisdictions. The Basel III framework and its 2017 Final Reforms represent the most advanced stage of this regulatory evolution, addressing weaknesses revealed by the global financial crisis and subsequent regulatory experience. Banking institutions play a central role in economic development, making their stability essential. The global financial crisis that began in 2007 exposed significant weaknesses in existing regulatory frameworks and led to the failure of several major banks, despite the earlier establishment of Basel I and Basel II by the Basel Committee on Banking Supervision. These shortcomings prompted the development of the Basel III framework as a direct response to the crisis. However, early criticisms of the initial Basel III Accord, particularly regarding variability in risk-weighted assets, reliance on internal models, and opportunities for regulatory arbitrage, led the Basel Committee to issue the Basel III Final Reforms in 2017, which represented a substantial upgrade to the post-crisis regulatory architecture. This study reviews the evolution of the Basel Accords; examines the key components of Basel I, Basel II, and Basel III; and analyses the enhancements introduced through the Basel III Final Reforms. It also considers the major arguments and criticisms surrounding these accords, highlighting the persistent challenges of achieving global regulatory consistency. Given the inability of earlier Basel frameworks to prevent bank failures and the fact that many jurisdictions have yet to fully implement the 2017 reforms, the paper underscores the need for ongoing evaluation of international banking regulation as national authorities adapt and refine their supervisory approaches to strengthen financial stability. Full article

Background/Objectives: Leishmaniasis is a group of diseases caused by obligate intracellular parasites of the Leishmania genus and is classified by the World Health Organization as a category I neglected tropical disease. Leishmania infantum predominantly affects children under five years of age and shows an increasing incidence of cutaneous and visceral forms. The development of new therapeutic alternatives remains challenging, making in silico approaches valuable for accelerating antileishmanial drug discovery. This study aimed to identify new compounds with potential activity against Leishmania infantum amastigotes using artificial intelligence-based classification models. Methods: A curated database of compounds with reported biological activity was constructed. Molecular representation employed zero- to two-dimensional descriptors calculated with Dragon software (v 7.0.10). Unsupervised k-means cluster analysis was applied to define training and external prediction sets. Supervised models were developed on the WEKA platform using IBk, J48, multilayer perceptron, and sequential minimal optimization algorithms. Model performance was assessed through internal cross-validation and external validation procedures. Results: All models achieved classification accuracies above eighty percent for both training and prediction sets, indicating consistent predictive performance and good generalization ability. The validated models were applied to virtual screening of the DrugBank database and a collection of synthetic compounds. This screening campaign enabled the identification of one hundred twenty compounds with potential activity against the amastigote form of Leishmania infantum. Conclusions: Artificial intelligence-based QSAR models proved to be useful tools for prioritizing antileishmanial candidates. The integration of molecular descriptors, machine learning, and virtual screening offers an efficient strategy for drug discovery. Full article

Small- and medium-sized commercial banks constitute a fundamental component of the financial system, and their corporate governance plays a critical role in the modernization of financial governance. Over the past two decades, these banks have largely established a modern enterprise framework, typically structured around shareholders’ meetings, boards of directors, supervisory boards, and senior management (SBSS). This governance arrangement has supported sustained institutional growth; however, persistent challenges have emerged, including the accumulation of non-performing assets and the increasing frequency of risk events. These problems cannot be attributed solely to market or operational factors, but are also closely related to limitations in the top-level design and practical functioning of the SBSS governance structure. In particular, a notable gap exists between the original design objectives of the modern enterprise system and its actual governance outcomes in practice. This study adopts an institutional and analytical approach, supported by descriptive regulatory statistics, to examine governance deficiencies in small- and medium-sized commercial banks. By introducing French state-led governance culture as an institutional reference, the paper conceptualizes non-shareholder-centered governance arrangements under strong public involvement and proposes an embedded governance framework emphasizing accountability, supervision, and information integration. Full article

The growing demand for personalized human–computer interaction calls for methods that jointly model emotional states and personality traits. However, large-scale multimodal corpora annotated for both tasks are still lacking. This challenge stems from integrating diverse, task-specific corpora with divergent modality informativeness and domain characteristics. To address it, we propose SSL-MEPR, a semi-supervised multi-task cross-domain learning framework for Multimodal Emotion and Personality Recognition, which enables cross-task knowledge transfer without jointly labeled data. SSL-MEPR employs a three-stage strategy, progressively integrating unimodal single-task, unimodal multi-task, and multimodal multi-task models. Key innovations include Graph Attention Fusion, task-specific query-based cross-attention, predict projectors, and guide banks, which enable robust fusion and effective use of semi-labeled data via a modified GradNorm method. Evaluated on MOSEI (emotion) and FIv2 (personality), SSL-MEPR achieves a mean Weighted Accuracy (mWACC) of 70.26 and a mean Accuracy (mACC) of 92.88 in single-task cross-domain settings, outperforming state-of-the-art methods. Multi-task learning reveals domain-induced misalignment in modality informativeness but still uncovers consistent psychological patterns: sadness correlates with lower personality trait scores, while happiness aligns with higher ones. This work establishes a new paradigm for extracting cross-task psychological knowledge from disjoint multimodal corpora, demonstrating that semi-supervised multi-task cross-domain learning can bridge annotation gaps while preserving theoretically grounded emotion–personality relationships. Full article

Periocular recognition is essential when full-face images cannot be used because of occlusion, privacy constraints, or sensor limitations, yet in many deployments, only periocular images are available at run time, while richer evidence, such as archival face photos and textual metadata, exists offline. This mismatch makes it hard to deploy conventional multimodal fusion. This motivates the notion of conditional biometrics, where auxiliary modalities are used only during training to learn stronger periocular representations while keeping deployment strictly periocular-only. In this paper, we propose Multi-Anchor Conditional Periocular Embedding (MACPE), which maps periocular, facial, and textual features into a shared anchor-conditioned space via a learnable anchor bank that preserves periocular micro-textures while aligning higher-level semantics. Training combines identity classification losses on periocular and face branches with a symmetric InfoNCE loss over anchors and a pulling regularizer that jointly aligns periocular, facial, and textual embeddings without collapsing into face-dominated solutions; captions generated by a vision language model provide complementary semantic supervision. At deployment, only the periocular encoder is used. Experiments across five periocular datasets show that MACPE consistently improves Rank-1 identification and reduces EER at a fixed FAR compared with periocular-only baselines and alternative conditioning methods. Ablation studies verify the contributions of anchor-conditioned embeddings, textual supervision, and the proposed loss design. Full article

Financial crises increasingly exhibit complex, interconnected patterns that traditional risk models fail to capture. The 2008 global financial crisis, 2020 pandemic shock, and recent banking sector stress events demonstrate how systemic risks propagate through multiple channels simultaneously—e.g., network contagion, extreme co-movements, and information cascades—creating a multidimensional phenomenon that exceeds the capabilities of conventional actuarial or econometric approaches alone. This paper addresses the fundamental challenge of modeling this multidimensional systemic risk phenomenon by proposing a mathematically formalized three-tier integration framework that achieves 19.2% accuracy improvement over traditional models through the following: (1) dynamic network-copula coupling that captures 35% more tail dependencies than static approaches, (2) semantic-temporal alignment of textual signals with network evolution, and (3) economically optimized threshold calibration reducing false positives by 35% while maintaining 85% crisis detection sensitivity. Empirical validation on historical data (2000–2023) demonstrates significant improvements over traditional models: 19.2% increase in predictive accuracy (R² from 0.68 to 0.87), 2.7 months earlier crisis detection compared to Basel III credit-to-GDP indicators, and 35% reduction in false positive rates while maintaining 85% crisis detection sensitivity. Case studies of the 2008 crisis and 2020 market turbulence illustrate the model’s ability to identify subtle precursor signals through integrated analysis of network structure evolution and semantic changes in regulatory communications. These advances provide financial regulators and institutions with enhanced tools for macroprudential supervision and countercyclical capital buffer calibration, strengthening financial system resilience against multifaceted systemic risks. Full article

This study examines whether strengthened prudential supervision reduces the marginal influence of internal governance mechanisms on the performance of Saudi banks during the Vision 2030 reform period. Using a panel of ten listed Saudi banks from 2018 to 2024, governance measures are hand collected to align with Saudi Central Bank definitions, focusing on insider ownership and board independence. To address endogeneity arising from performance persistence and reverse causality, two-step system generalized method of moments with collapsed lagged internal instruments and Windmeijer-corrected standard errors are employed. The results reveal that insider ownership and board independence are statistically and economically insignificant for accounting performance and market valuation, whereas lagged performance remains the dominant predictor. Hansen J and Arellano–Bond AR(2) diagnostics support instrument validity, and robustness checks using alternative estimators and variable specifications produce consistent findings. The results suggest that in contexts where prudential oversight is comprehensive and consistently enforced, internal governance mechanisms may provide limited incremental monitoring value. However, they do not imply that boards or insiders are irrelevant during crises or when enforcement is uneven. Therefore, refining supervisory tools and disclosure practices should be prioritized over imposing additional structural mandates on boards or ownership configurations. Full article