Applications of Signal Processing Lab (ASP-LAB)

Signal Processing for Audio Applicationss

Our research focuses on developing novel algorithms and techniques for audio signal processing with Applicationss in:

• Active Noise Control (ANC)
• Digital Hearing Aids
• Acoustic Echo Cancellation
• Audio Enhancement and Restoration

We employ adaptive filtering techniques, Fourier and Wavelet transformations, and deep learning approaches to solve complex audio processing challenges.

Biomedical Signal Processing

We develop methods for processing and analyzing biomedical signals including:

• EEG Signal Processing for Brain-Computer Interfaces
• Medical Image Analysis and Classification
• Prediction of Preterm Birth Using Machine Learning
• Surface Electromyography (sEMG) Signal Classification

Our work combines signal processing techniques with machine learning to extract meaningful information from complex biomedical data.

Machine Learning & Computer Vision

Our research explores advanced Applicationss of machine learning and computer vision:

• Image Segmentation and Object Detection
• Computer Vision in Autonomous Systems
• Deep Learning for Audio and Visual Data
• Histopathology Image Classification

We work on innovative approaches combining traditional signal processing with modern deep learning architectures.

Hardware Implementation

We focus on efficient hardware implementations of signal processing algorithms:

• FPGA-Based DSP Algorithm Implementation
• Distributed Arithmetic-based Hardware Implementation
• Low-Power Hardware for Wearable Devices
• Reconfigurable Intelligent Surfaces

Our research bridges the gap between theoretical signal processing algorithms and their practical real-time implementations.

Enhanced Signal Denoising Using Data-Driven Multiresolution Analysis

This project explores novel approaches to signal denoising by combining detrended-fluctuation-analysis-based thresholding with stationary wavelet transform in a data-driven framework. The technique offers superior performance compared to traditional methods in preserving signal features while effectively removing noise.

Machine Learning for Hearing Aids Applicationss

This research focuses on developing machine learning algorithms specifically tailored for digital hearing aids to improve acoustic feedback cancellation and provide adaptive noise reduction, enhancing the quality of life for hearing aid users.

EEG-based Stimuli Reconstruction

This project investigates methods to reconstruct visual and auditory stimuli from EEG recordings using advanced signal processing and deep learning techniques. The research aims to provide insights into brain-computer interfaces and neural decoding.