Mir Muhammad Abdullah mir-m-abdullah

Welcome to my GitHub page! I am a data scientist with experience in machine learning, deep learning, statistical modeling, and data visualization.

Technical Skills:

Programming Languages: Python, R, SQL, Java, MATLAB, C, SAS
Data Visualization: Python, R, Tableau, JMP, SAS
Machine Learning Frameworks: PyTorch, Scikit-learn
Deep Learning Techniques: Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Generative Adversarial Networks (GAN) (Learning)
Cloud Platforms/AWS Services: Athena, SageMaker, Rekognition, Lex, Polly, Translate, Transcribe, Kinesis, Lambda, Glue, Textract, S3
Development Environments and Versioning: Jupyter Notebook, Linux, GitLab, GitHub

Breast Cancer Classification with Machine Learning: A machine learning model to predict whether a breast cancer tumor is malignant or benign, using various statistical analysis tools. Identified the most accurate model and optimized its hyperparameters for better performance. Achieving 98.25% accuracy and 0.98 F1 score, the model can assist physicians in making accurate diagnoses and improving patient outcomes.
CNN Model Improvements on Thoracic X-Rays: This project involved developing and implementing CNN models on thoracic radiological images to predict various pathologies, with a focus on improving model accuracy through the use of binary classification models based on age and gender, as well as pre-processing filters on images, resulting in a final accuracy of 89.2%.

Thank you for visiting my page! Feel free to contact me for any collaborations or opportunities.