Producción científica y docente
Producción científica reciente
Cost-sensitive random forest with adaptive threshold optimization for imbalanced financial fraud detection
Background: Financial transaction fraud detection is a challenging binary classification problem characterized by severe class imbalance, rare fraudulent cases, and asymmetric misclassification costs. In real-world banking systems, failing to detect fraudulent transactions can lead to substantial financial losses, whereas false alarms mainly increase operational review costs. Therefore, fraud detection models should not be optimized only for overall accuracy, as accuracy-oriented classifiers may favor the majority non-fraud class and fail to identify minority fraud cases effectively. To address this issue, this study proposes a cost-sensitive ML framework for financial transaction fraud detection under class imbalance and asymmetric financial risk.Methods: In this study, a cost-sensitive RF framework with adaptive probability threshold optimization is proposed for binary fraud classification. Misclassification costs are incorporated during model training through class-weighted learning, allowing the classifier to assign greater importance to minority fraud cases. In addition, instead of using the default probability threshold of 0.5, the decision threshold is optimized using validation data to minimize the expected misclassification cost and improve minority-class detection. The proposed framework was evaluated on two publicly available financial fraud datasets with different transaction characteristics: the Credit Card Fraud Detection dataset and the Financial Fraud Prediction dataset. Its performance was compared with conventional ML baselines using fraud-oriented evaluation metrics, including precision, recall, F1-score, false-negative rate, false-positive rate, and expected misclassification cost.Results: The proposed framework achieved strong and consistent performance across both datasets. On the Credit Card Fraud Detection dataset, it achieved a precision of 94.4%, recall of 85.7%, and F1-score of 89.8%. On the Financial Fraud Prediction dataset, it achieved a precision of 93.1%, a recall of 83.8%, and an F1-score of 88.2%. Compared with conventional fixed-threshold ML models, the adaptive threshold strategy reduced false-negative predictions while maintaining high precision. These results indicate that the proposed cost-sensitive framework provides a more balanced decision strategy for fraud detection under highly imbalanced transaction distributions.Conclusion: The findings demonstrate that combining class-weighted learning with adaptive threshold optimization can improve fraud detection performance under asymmetric misclassification costs. The proposed framework offers a practical and interpretable decision-support approach for banking fraud detection systems, particularly in settings where reducing undetected fraudulent transactions is more important than maximizing overall accuracy alone.
Cross-Dataset Generalization of Deep Learning for Retinal Vessel Segmentation in Fundus Images: External Evaluation from DRIVE to CHASE_DB1
Automated retinal vessel segmentation can support quantitative analysis of fundus photographs and facilitate measurement of vascular characteristics associated with ocular and systemic disease. Although deep-learning methods achieve high segmentation performance on benchmark datasets, their reliability may decrease when applied to images obtained under different acquisition conditions. This study evaluated the cross-dataset generalizability of a U-Net segmentation architecture incorporating an ImageNet-pretrained ResNet34 encoder. Sixteen images from the DRIVE dataset were used for model training and four were retained for in-domain validation. Images were resized to 256 × 256 pixels and processed using a consistent normalization pipeline, while spatial and photometric augmentation was applied during training. Without target-domain retraining or domain adaptation, the trained model was subsequently evaluated on the independent CHASE_DB1 dataset. Segmentation performance was assessed using the Dice coefficient, intersection over union (IoU), and sensitivity, together with qualitative examination of predicted vessel maps. On the held-out DRIVE images, the model achieved a Dice coefficient of 0.7263, IoU of 0.5703, and sensitivity of 0.7201. On CHASE_DB1, performance decreased to 0.6269, 0.4573, and 0.5502, respectively. The disproportionately larger reduction in sensitivity indicated an increased frequency of missed vessel pixels under cross-dataset evaluation. Qualitative examination showed greater fragmentation and omission of fine and peripheral vascular structures in CHASE_DB1 images. These findings demonstrate that within-dataset performance may overestimate the robustness of retinal vessel segmentation models when transferred to a different imaging domain. External evaluation should therefore form an important component of retinal imaging artificial intelligence research. Future work should investigate higher-resolution processing, vessel-width-specific evaluation, multi-domain training, domain-adaptation strategies, and larger multicentre datasets to improve model generalizability.
A Multilevel Deep Learning Model for Automated Brain Tumor Segmentation Using Magnetic Resonance Images
Background/Objectives: Brain tumor segmentation from magnetic resonance imaging (MRI) plays an important role in clinical assessment and treatment planning. However, accurate segmentation remains challenging because of the complex anatomical structure of the brain, variations in tumor size and shape, and the imbalance between tumor and non-tumor regions in MRI datasets. These challenges highlight the need for reliable automated segmentation methods. Methods: This study proposes a multilevel deep learning model for automated brain tumor segmentation using MRI images. The BraTS dataset was used for model development and evaluation. To address class imbalance, a modified Synthetic Minority Oversampling Technique (SMOTE) was incorporated during preprocessing. A Multilevel Architecture-Based Modified U-Net was then employed to learn multiscale spatial features and generate pixel-wise tumor segmentation. The proposed framework was evaluated using the Dice coefficient, Jaccard coefficient, Matthews Correlation Coefficient (MCC), and accuracy. Results: The experimental results demonstrate that the proposed model consistently outperformed the Berkeley Wavelet Transform (BWT)-based method and the conventional U-Net across different tumor grades. Higher Dice, Jaccard, and MCC values indicate improved agreement between the predicted segmentation and the expert-annotated ground truth masks, demonstrating more accurate and consistent tumor delineation. Conclusions: The proposed multilevel deep learning model provides an effective framework for automated brain tumor segmentation from MRI images. By combining imbalance-aware preprocessing with a lightweight Modified U-Net architecture, the proposed method improves segmentation performance while maintaining a relatively simple network design. Future work will focus on validating the proposed framework using external clinical datasets and comparing it with recent state-of-the-art segmentation models.
Oral Microbiota, the Oral–Brain Axis, and Neurodegeneration: Mechanisms and Dietary Modulation
The oral microbiota represents a complex and dynamic microbial ecosystem that plays a critical role in preserving both oral and systemic homeostasis. Emerging evidence suggests that alterations in oral microbial milieu (dysbiosis) may contribute to the pathogenesis of neurodegenerative disorders, especially Alzheimer’s disease (AD), through the oral–brain axis. This review synthesizes current evidence on the pathways linking oral microbiota to cognitive decline, integrating microbial, immunological, and vascular perspectives. Oral pathogens may access the central nervous system via hematogenous dissemination or neural routes, including the trigeminal nerve, while simultaneously promoting systemic inflammation, immune activation, and blood–brain barrier disruption. These processes converge on key neurodegenerative mechanisms, including chronic neuroinflammation, amyloid-β accumulation, and tau pathology. In parallel, alterations in oral microbial composition have been linked to disease severity, supporting a potential role of dysbiosis in both initiation and progression of cognitive impairment. Diet emerges as a critical modifiable determinant of oral microbial ecology. Diets rich in refined sugars may promote dysbiosis and inflammatory signaling, whereas (poly)phenols, probiotics, and prebiotics may support microbial eubiosis and exert neuroprotective effects through modulation of host–microbe interactions. Although current evidence remains largely observational and mechanistic, the diet–oral microbiota–brain axis represents a promising target for preventive and therapeutic strategies aimed at mitigating cognitive decline and promoting healthy aging. Future longitudinal and interventional studies are required to establish causality and translate these insights into clinical practice.
Cryptocurrency Market Trends: A Machine Learning-Driven Time Series Forecasting with Twitter Sentiment Integration
Accurate forecasting of cryptocurrency prices remains an open challenge because classical statistical models cannot capture the non-linear, sentiment-driven dynamics of these markets. This study compares three hybrid deep learning architectures—VAR-LSTM, XGBoost-LSTM, and CNN-LSTM—to determine which best forecasts Bitcoin (BTC), Ethereum (ETH), and Dogecoin (DOGE) closing prices, and to quantify the marginal predictive value of Twitter sentiment integration. Six years of hourly OHLCV data (2017–2023) are augmented with VADER-scored Twitter sentiment polarity. Each model is formulated mathematically, implemented with documented hyperparameters (epochs, dropout, units;), and trained for one-step-ahead next-hour price prediction. Performance is measured by RMSE, MAE, MAPE, R 2 , and Directional Accuracy (DA) across five random seeds, with paired Wilcoxon significance tests. XGBoost-LSTM achieves the best performance (RMSE = 81.547, R 2 = 0.9254, DA = 80.0%), outperforming all nine literature baselines. Removing Twitter sentiment degrades DA by 14.3 percentage points ( p < 0.01 ), confirming that social media signals carry independent predictive information. Hybrid architectures consistently outperform single-model baselines; XGBoost-LSTM offers the best accuracy-to-compute ratio. VADER-enriched Twitter sentiment is a significant predictor beyond price history. Limitations include reliance on a single sentiment platform and a training window that predates several structural market events