IEEE

Enabling Decoder-only Language Model Inference on a CNN Accelerator

Abstract: The remarkable success of Transformer architectures in Natural Language Processing (NLP) has led to increased demand for embedded systems capable of efficiently handling NLP tasks along with ...
IEEE

Diffusion Model Makes Remote Sensing Image Semantic Segmentation Better!

Abstract: Semantic segmentation represents a critical challenge in computer vision, holding significant importance for the application and understanding of remote sensing imagery. This task inherently ...
IEEE

Explainable Brain Tumor Classification using CNN and GradCAM

Abstract: One of the most critical neurological conditions is Brain tumors, timely and correct diagnosis is needed for effective treatment. Advances in neuroimaging technology such as MRI, limitations ...
IEEE

Hybrid Integration of CNN and Kolmogorov–Arnold Networks for Multispectral Image Super-Resolution

Abstract: This letter proposes KAN-based multispectral image super-resolution method (KMSR), a novel deep learning framework for multispectral image (MSI) super-resolution (SR) that integrates ...
IEEE

Accurate Metaphase Chromosome Classification Using Faster R-CNN and Deep LSTM Integration

Abstract: The precise classification of metaphase chromosomes is essential for cytogenetic analysis, facilitating the detection of genetic diseases and anomalies. This paper introduces an improved ...

WiMi Releases Hybrid Quantum-Classical Neural Network (H-QNN) Technology for Efficient MNIST Binary Image Classification

Beijing, Feb. 06, 2026 (GLOBE NEWSWIRE) -- WiMi Releases Hybrid Quantum-Classical Neural Network (H-QNN) Technology for Efficient MNIST Binary Image Classification ...
IEEE

PixTransNet: A Sensor-Aware CNN–Transformer Model for Magnetic Flux Leakage Defect Segmentation

Abstract: Magnetic flux leakage (MFL) is a widely used nondestructive evaluation technique for pipeline inspection. However, its signals are highly sensitive to noise and geometric distortions, ...
IEEE

Graph Signal Sampling-Based Active Learning for Hyperspectral Image Classification

Abstract: Active learning (AL) has achieved great success in remotely sensed hyperspectral image (HSI) classification due to its ability to select highly informative training samples. An appropriate ...
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

A Novel Alzheimer’s Disease Classification Framework Integrating 3D CNN With Bidirectional Feature Pyramid Network and Vision Transformers

Abstract: Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that severely affects memory and cognitive function, underscoring the need for accurate and early diagnostic tools. Deep ...
European Medical Journal

Lightweight Neural Networks Improve Lung Cancer Diagnosis

Lightweight convolutional neural networks improved lung cancer classification accuracy in histopathological images while ...
IEEE

Hyperspectral Image Classification Based on Normalized Grouping Fused Comprehensive Relative Position Transformer Network

Abstract: In hyperspectral image (HSI) classification, Transformer and CNN are widely used because they complement each other in extracting features. Nevertheless, existing Transformer-based methods ...