IEEE

Deep Learning for Multi-Class DDoS Detection in SDNs: A CNN-LSTM Based Approach

Abstract: Recently Distributed Denial of Service (DDoS) attacks have increased extensively, taking about 35% of all cyber threats among which the attack characteristic rises around 300% within the ...
IEEE

Research on Pipeline Anomaly Detection Method Based on Multi-Head Cross-Attention Network with Dual-Channel 1D CNN

Abstract: Leaks in water supply pipelines lead to a large amount of water waste every year, so there is an urgent need to establish efficient and accurate leak detection methods. In recent years, ...
IEEE

Recognition of Stroke Level Based on EEG Signal Using Multi-networks of CNN-Transformer

Abstract: Stroke is a major cause of long-term neurological impairment, and continuous monitoring of post-stroke patients is essential for rehabilitation and relapse prevention. Electroencephalogram ...
IEEE

Diffusion-Augmented Industrial Anomaly Detection Leveraging Attention-Empowered Multi-CNN Transformer Fusion

Abstract: Deep learning models have demonstrated remarkable performance in anomaly detection tasks, particularly when large datasets with sufficient anomalous samples are available. However, in ...
Frontiers

A Hybrid CNN-LSTM approach for multi-step discharge forecasting with satellite data

The final, formatted version of the article will be published soon. An innovative hybrid forecasting model was developed to predict hourly river discharges up to 24 hours in advance. The proposed ...
IEEE

A Hybrid CNN-LSTM Model with Signal Decomposition for Multi-Step Electrical Load Forecasting

Abstract: Accurate power load forecasting is a cornerstone for the reliable operation and economic dispatch of modern power grids, particularly as the integration of Variable Renewable Energy ...
IEEE

MSCTA-Net: Multi-Scale CNN-Transformer for Multi-Class Arrhythmia Detection from PPG Signals

Abstract: The widespread adoption of wearable devices necessitates accurate multi-class arrhythmia detection from photoplethysmography (PPG) signals for early cardiovascular intervention. While ...
IEEE

PatchMSNet: A Multi-Scale Transformer-CNN Hybrid Network for Satellite Image Classification

Abstract: Accurate classification of satellite imagery is essential for numerous applications, including environmental monitoring, land-use analysis, and disaster management. The capability to ...
IEEE

A 28-nm 3.32-nJ/Frame Compute-in-Memory CNN Processor With Layer Fusion for Always-on Applications

Abstract: This work presents an always-on CNN processor featuring compute-in-memory (CIM) and layer-fusion (LF) techniques. It demonstrates an end-to-end neural network (NN) inference while ...
IEEE

Multi-level Wavelet-CNN for Image Restoration

Abstract: The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of ...
IEEE

Multi-IMU Fusion Method for Accurate Motion State Estimation Based on CNN and Kalman Filter

Abstract: The measurement accuracy of the inertial measurement unit (IMU) directly affects the motion state estimation performance of the robot in a dynamic environment. However, high-precision IMUs ...
IEEE

BrainViT: A Hybrid CNN-Vision Transformer Architecture for Multi-label Affective State Classification Using EEG

Abstract: This work presents a novel hybrid deep learning architecture combining Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) for automated mental health assessment using ...