IEEE

Optimizing Hybrid Classification Using 1D-CNN and LSTM for EEG-Based Emotion Recognition

Abstract: This research aims to enhance the ability of computers to classify emotional states from brain signals using EEG data. Emotions are complex mental states that can significantly affect a ...
IEEE

Optimizing CNN-GRU Hybrid Ratios for Resource-Constrained Audio Classification: A Systematic Study From Parameter Efficiency to MCU Deployment

Abstract: Urban sound classification has become a critical enabling technology for Internet of Things (IoT) applications, smart cities, and environmental monitoring systems. Despite advances in deep ...
IEEE

Enhancing Medical Image Super-Resolution Using CNN and GAN Approaches

Abstract: Improving the resolution of medical images is an important task in ensuring trustworthy diagnosis and effective monitoring of diseases. Of the newest deep learning algorithms, Convolutional ...
IEEE

Enhancing Few-Shot Medical Image Classification with Supervised Patch-Token Knowledge Distillation

Abstract: Developing robust models for medical imaging that effectively generalize across diverse image characteristics remains a significant challenge, primarily due to the limited availability of ...
IEEE

CPGNet: Multimodal Graph Learning with Hierarchical Category Guidance for Multi-Label Whole Slide Image Classification

Abstract: The analysis of WSI categories in digital pathology is critical for clinician decision making regarding the diagnosis, treatment, and prognosis of cancer patients. However, current automated ...
IEEE

Spectral–Spatial Synergy Guided Attention Network for Hyperspectral Image Classification

Abstract: The attention mechanism has gained significant popularity in hyperspectral image classification (HSIC) for its ability to adaptively highlight key features. However, it often incurs ...
IEEE

Hierarchical Byte-Level Modeling via CNN and Mamba for Encrypted Traffic Classification

Abstract: Encrypted traffic classification, which aims to identify application-layer semantics without decrypting packet pay-loads, has emerged as a pivotal challenge in modern network intelligence ...
IEEE

Fully Perturbed Self-Ensemble Framework using Cascaded Parallel CNN-Transformer for Semi-Supervised Medical Image Segmentation

Abstract: Semi-supervised learning (SSL) has achieved remarkable progress in the field of medical image segmentation (MIS), but it still faces two main challenges. First, the consistency learning ...
IEEE

A CNN-Based Approach for Freshness Classification of Fruits and Vegetables

Abstract: Fresh storage of fruits and vegetables is crucial for minimising waste, consumer health, and quality of food. Produce freshness classification can greatly improve supply chain effectiveness ...
IEEE

Combine Meta-Learning With Feature Alignment for Cross-Domain Heterogeneous Hyperspectral Image Classification

Abstract: The scarcity of labeled samples results in the challenge of small sample size in hyperspectral image (HSI) classification. Transfer learning offers hope for solving this problem. In ...
IEEE

Query-Oriented Dynamic Multimodal Alignment for Few-Shot Hyperspectral Image Classification

Abstract: Deep learning (DL) has advanced hyperspectral image classification (HSIC), but label scarcity remains a significant challenge. Traditional unimodal methods usually produce unstable ...
IEEE

Weather Forecasting Using CNN and Image Streams

Abstract: This accurate forecasting is essential for public safety, agriculture, transportation. Traditional weather forecasting methods mostly depend on physical simulations and mathematical models.