IEEE

Memristor based Crossbar Array using CNN for Image Processing Applications

Abstract: Image processing has become one of the popular neuromorphic computing applications in recent years. Most of the application areas require an efficient and real time image processing system.
IEEE

Signal Processing for Cell-Free Massive MIMO: Techniques and Trends in Estimation, Detection, and Precoding

Abstract: Cell-free (CF) massive multiple-input multiple-output (mMIMO) is a promising state-of-the-art technology that has been developed to solve the inter-cell interference problem in mMIMO. In a ...
IEEE

CNN-Based EOG Signal Classification for Human Computer Interfaces

Abstract: Eye-movement-based communication is a new alternative for individuals who are unable to communicate through traditional means. This paper proposes a deep learning approach for ...
IEEE

Motor Signal Processing and Fault Diagnosis Based on an Analog Circuit Inspired by a Machine Learning Algorithm

Abstract: Vibration signal analysis methods based on digital signal processing (DSP) have been proven effective in motor fault diagnosis. However, DSP requires signal conversion from analog to digital ...
Frontiers

Transferable CNN-based data mining approaches for medical imaging: application to spine DXA scans for osteoporosis detection

Introduction: Osteoporosis is the leading cause of sudden bone fractures. This is a silent and deadly disease that can affect any part of the body, such as the spine, hips, and knee bones. Aim: To ...
IEEE

Processing accuracy of microcomb-based microwave photonic signal processors for different input signal waveforms

Abstract: We experimentally demonstrate the capability of microcomb-based microwave photonic signal processors to handle diverse input signal waveforms. We quantify the processing accuracy for ...
IEEE

Investigating SAR Data Denoising: A Comparative Analysis of CNN Models with Multi-Channel Signal Processing Features

Abstract: This paper investigates the necessity for denoising in Synthetic Aperture Radar (SAR) dataset, emphasizing the comparison of three distinct neural networks: U-Net, ResNet, and DeepDeblur.
IEEE

Impact of Signal Input Shape Variations on Performance of Deep Learning Models in ECG-Based Diabetes Prediction

Abstract: Diabetes is a chronic disease that requires early and effective detection to prevent long-term complications. Conventional diagnostic methods remain invasive, often causing discomfort, ...
Frontiers

1D-CNN for non-cooperative rotational Doppler signal extraction

The discovery of the rotational Doppler effect (RDE) has opened new opportunities for detecting parameters of rotating targets. In recent years, the physical mechanisms underlying this effect have ...
IEEE

CNN-LSTM for Dynamic Gesture Recognition in Hand Electrostatic Signal Processing

Abstract: As a ubiquitous interaction modality in daily life, hand gestures convey rich interactive information. Particularly under the evolving paradigm of Natural User Interface (NUI), gesture ...