Pezhman Zivari

Master’s Thesis: Lung Lobe Segmentation in Medical Images

Developed advanced deep learning models (U-Net, Attention Mechanisms) for accurate segmentation of lung lobes from medical images, aiming to enhance diagnostic precision.

Pattern Recognition Projects: Implemented pattern recognition techniques (SVM, Random Forests, CNNs) in various academic projects to classify and analyze image and textual data. Machine Learning & Deep Learning: Built predictive models and classification systems using machine learning (XGBoost, SVM, Random Forest) and deep learning (CNNs, LSTMs, GANs) techniques.

Big Data Analytics: Analyzed large-scale datasets using big data frameworks (Apache Spark, Hadoop) to extract actionable insights and trends.

Advanced Data Mining: Applied advanced data mining algorithms (Clustering, Association Rules, Anomaly Detection) to uncover hidden patterns in complex datasets.

Evolutionary Algorithms: Utilized evolutionary computation methods (Genetic Algorithms, Particle Swarm Optimization) for solving complex optimization problems.