2982 papers
This paper presents a hybrid deep learning framework that integrates CNN, Transformer, and BiLSTM layers with multi-feature fusion to achieve state-of-the-art speech emotion recognition performance across five benchmark datasets, demonstrating robust generalization and significant accuracy improvements over existing baselines.
This study proposes the StackPip Framework, a hybrid ensemble learning approach utilizing a Stacking Classifier on the SDSS DR-17 dataset, which achieved a 98% accuracy in classifying celestial objects into galaxies, stars, and quasars, outperforming various individual machine learning models.
The paper proposes BayesMem-CD, a Bayesian memory-based framework that integrates probabilistic inference with temporal regularization to achieve uncertainty-aware dynamic community detection, effectively balancing stability against noise with sensitivity to genuine structural changes.
The paper introduces AraCoT-Agent, a framework that distills structured reasoning capabilities into Arabic models using a high-quality, filtered dataset (AraCoT) and a reward-weighted training objective, achieving a 55.7% relative improvement on the new AraAgent-Bench and significantly narrowing the reasoning gap between Arabic and English LLMs.
The paper proposes CoDeR, a continuous degradation representation learning framework that integrates a Dual-axis Coupled Transformer Encoder and a Time-Aware Contrastive Learning module to overcome the limitations of fragmented representations in existing deep learning models, thereby achieving more accurate Remaining Useful Life predictions for aero-engines.
This systematic review evaluates the suitability of Kolmogorov-Arnold Networks (KANs) for time series analysis, concluding that while they excel in interpretable, short-horizon forecasting with smooth patterns across various domains, their current application is limited by heterogeneous evidence, challenges in handling long-range dependencies and regime shifts, and a need for standardized benchmarks and rigorous interpretability validation.
This paper introduces GRAD-Net, a unified pathology-guided deep learning framework that integrates lesion-aware attention mechanisms and multi-scale feature aggregation to achieve state-of-the-art accuracy and clinical interpretability in automated diabetic retinopathy grading.
This paper introduces CRC-LS-MOCBO, a sequential multi-objective causal Bayesian optimization framework that ensures safe interventions under uncertain causal structures by integrating candidate-graph uncertainty, stability-weighted priors, and conformal risk calibration to minimize constraint violations while maximizing objective gains.
This paper presents a low-cost, real-time earthquake early warning system that utilizes IoT hardware (ESP32, GPS, GSM) and embedded machine learning models trained on historical seismic data to detect patterns and instantly alert users via SMS, even in areas with limited connectivity.
This paper introduces HybridPII, a tunable hybrid ensemble model that combines weighted regex and multi-model NER to achieve superior recall for automated PII detection, specifically addressing the critical need to minimize false negatives in compliance-critical privacy applications.