Buscar recursos académicos

Abstract Purpose This study introduces a new Convolutional Neural Network (CNN) architecture, EyeDiagNet, for the classification of fundus images into four classes: normal, cataract, diabetic retinopathy (DR), and glauco...

Abstract The publication of DeepSeek-R1 in Nature marks a significant moment as the first widely recognized large language model to undergo formal peer review. While acknowledging its technical ambitions and contribution...

Abstract Detecting epileptic seizures from electroencephalogram (EEG) signals presents a significant challenge due to the nonlinear and non-stationary nature of brain activity. In this study, we propose a hybrid classifi...

Abstract While multi-access edge computing (MEC) enables flexible task offloading, the inherent dynamism and complexity of real-world environments, accompanied by various uncertainties, exacerbate the challenges in offlo...

Abstract Accurate differentiation of pulmonary emphysema from chest X-rays remains challenging due to imbalanced data, image noise, and the limitations of traditional deep networks in managing diagnostic uncertainty. In ...

Abstract In terms of global health, cardiovascular diseases remain an emerging challenge, for which early estimation for timely medical treatment proves crucial. In this paper, an estimate of this challenge has been pres...

Abstract This research is concerned with the innovative use of AI in cross-cultural music learning, more particularly in the creation of a multimodal learning model that combines audio identification, image analysis, and...

Abstract Efficiently and accurately extracting key information from videos has become a core challenge in the current computer vision. Traditional methods rely on manual features and shallow models, making it difficult t...

Abstract The increasing number of Internet of Things (IoT) devices demands a rigid and adaptive routing methodologies to ensure the reliable communication especially for the low-power and lossy networks. The Routing Prot...

Abstract Breast cancer is still the most significant contributor to morbidity and mortality among women in China. Despite advances in imaging and molecular testing, few reliable biomarkers exist for early detection and d...

Abstract Financial institutions continue to face a significant challenge with money laundering and need intelligent, scalable ways to detect illegal financial activity. This paper introduces a machine learning-driven pla...

Abstract Single-image dehazing is essential for safety-critical vision systems, yet existing CNN-based methods are often too heavy for edge devices or fail to adapt to spatially varying haze density. This paper introduce...

Abstract The rapid development of China’s financial markets, particularly the expansion of the ETF ecosystem, has made dynamic sector rotation strategies increasingly feasible and cost-effective for investors. At the s...

Abstract This paper seeks to investigate the use of Natural Language Processing techniques in analyzing the Bhagavad Gita, a fundamental text in Hindu philosophy that has stood the test of time and centuries of interpret...

Abstract The integration of large-scale distributed power sources complicates grid topology and intensifies spatiotemporal coupling in power data. This complicates the analysis of intrinsic correlations and makes predict...

Abstract Long-range dependency processing is the core challenge of sequence modeling, and traditional sequence modeling algorithms suffer from information decay and low parallel computing efficiency in ultra long sequenc...

Abstract To solve the problem of poor effectiveness and efficiency in traditional urban and rural planning layout optimization methods, an innovative urban and rural planning layout optimization method combining ant colo...

Abstract In response to the dual challenges of complex static obstacles and frequent dynamic disturbances in the construction site environment, this paper proposes a hybrid path planning strategy that integrates global s...

Abstract Multi-label chest X-ray classification faces three critical challenges: (i) inadequate modeling of inter-pathology dependencies despite clinical co-occurrence patterns, (ii) severe class imbalance (11.2−47.6...

Abstract Recirculating aquaculture systems (RAS) and biofloc technology (BFT) are increasingly recognized as sustainable aquaculture approaches, as they enhance water-use efficiency, improve biosecurity, allow high produ...

Abstract With the evolution of interactive art installations towards 4 K/8 K ultra-high-definition streaming and large-scale multi-point interaction, existing 5G networks face challenges in maintaining the "flow state"...

Abstract Feature selection is a critical step in machine learning, as it helps minimize redundant features, thereby enhancing model performance and interpretability. In practice, partially labeled datasets are common. Wh...

Abstract The current English grammar error correction model still has low accuracy when dealing with complex sentences and long sentence dependencies. Therefore, this study proposes a Sequence-to-Sequence (Seq2Seq) model...

Abstract This study seeks to address persistent challenges in traditional music education, particularly the subjectivity inherent in assessment criteria and the frequent delays in feedback, by harnessing the capabilities...