Hi, I'm Owais Mujtaba

Machine Learning & Computer Vision Engineer

I develop and deploy advanced deep learning models for computer vision, neural signal processing and applied AI. My work bridges cutting-edge research with real-world applications.

View Projects GitHub

About Me

Research Focus

I'm an ML/DL engineer specializing in computer vision, neural signal processing, and model optimization. My work spans from developing lightweight DDoS detection models to pioneering EEG-based speech synthesis algorithms.

I bridge cutting-edge research with practical applications, focusing on model robustness, efficiency, and real-world deployment challenges.

6+

Years Research

10+

Published Works

5+

Universities

Deep Learning

Specializing in CNN, RNN architectures for vision and signal processing.

Computer Vision

Object detection, image forensics, and adversarial robustness.

Neural Signals

EEG data analysis and neural correlates of speech perception.

Statistical Analysis

Advanced time series analysis, hypothesis testing, and ANOVA.

Skills & Technologies

Machine Learning

PyTorch/TensorFlow 95%

Computer Vision 90%

Model Optimization 85%

Data Science

Statistical Analysis 92%

Time Series 88%

Data Visualization 90%

Tools

Python Ecosystem 95%

Azure ML 85%

Git/CI-CD 90%

Featured Projects

EEG Semantic Decoding

Achieved 77.89% accuracy in neural signal classification for speech perception vs imagination using deep learning.

PyTorch EEG CNN

Lightweight DDoS Detection

High-accuracy model optimized for resource-constrained environments with adversarial robustness testing.

TensorFlow Security Optimization

Fake Image Detection

Deep learning model for detecting manipulated images using image forensics and CNN classification.

Computer Vision PyTorch Forensics

EEG-Audio Annotation

Data synchronization system for neural and audio signals with precise time alignment.

Python Signal Processing Neuroscience

OCR Optimization

Hyperparameter tuning and transfer learning for improved text recognition in low-resource datasets.

Computer Vision Transfer Learning Optimization

EEG Speech Synthesis

Novel algorithm for speech synthesis from EEG neural activity recordings for individuals with speech impairments.

EEG CNN-GRU BCI

Neural Speech Encoding

Reconstructing high-gamma neural activity from speech and language model embeddings.

Neuroscience Signal Processing Deep Learning

View All Projects on GitHub