Projects
Automatic Detection of COVID-19 from CT-Scan Images Using Deep Learning
2025
This research presents a method for detecting COVID-19 from CT-scan images using deep learning algorithms, conducted at Ayatollah Kashani Hospital, Esfahan. By analyzing patterns in medical imaging data, the system can accurately identify COVID-19 infections. Leveraging convolutional neural networks and advanced image processing techniques, this approach enhances detection speed and accuracy, providing a reliable tool for healthcare professionals at Ayatollah Kashani Hospital and beyond for timely diagnosis and informed decision-making.
Breast Cancer Classification Using Machine Learning
2021
Utilized Resistin, glucose levels, age, and BMI as features to classify breast cancer presence through various machine learning classifiers, using the Breast Cancer Coimbra dataset. This project involved data preprocessing, feature selection, model training with algorithms like SVM, Random Forest, and Logistic Regression, and evaluation using metrics such as accuracy, precision, recall, and F1-score to identify the most effective classifier for early detection.
Emotion Detection Through Facial Expression Analysis
2023
Developed a system for emotion detection through facial expression analysis using a modified ResNet-18 architecture enhanced with attention mechanisms and transfer learning. The project included dataset preparation (e.g., using FER-2013 or similar), model customization to focus on key facial features via attention layers, fine-tuning with pre-trained weights, and performance assessment through confusion matrices and accuracy metrics. This work aimed to improve real-time emotion recognition for applications in healthcare and human-computer interaction.