Pinned Repositories
Baseline-Correction
correct baseline for spectroscopy data with polynomial subtraction and asymmetric least square method
bionanoimaging.github.io
Repository for hosting the website files
Box_Plot_Statistic
Box Plot with Detailed Statistics in Python
Data_Extract
This script automates data collection from .mat files into an Excel sheet, streamlining data preparation for analysis. It traverses directories, extracts specified data, and compiles it, making dataset aggregation efficient and ready for analysis.
DualDataDistributionAnalysis
The DualDataDistributionAnalysis repo offers a Python script for comparing two datasets via statistical plots: boxplots, violin plots, histograms, KDEs, CDFs, and swarm plots. It leverages pandas, Matplotlib, and Seaborn to visualize and analyze data distributions, ideal for exploratory data analysis and insights.
Error_absolut_relative
This Python script calculates the absolute and relative errors between simulation results and a theoretical value. It takes a list of measured values and a true value, returning the errors for each simulation, showcasing the deviation from the expected outcome.
FRET-calculations
This repository contains the code necessary to simulate the fluorescence emission of an anisotropic ensemble of dye molecules when excited by polarized light.
spectral-detector
Supervised-Learning-Algorithms-diabetic-data
A comprehensive application of supervised learning methods on the Diabetes Dataset, including Linear, Ridge, Lasso, ElasticNet, SVR, KNN, Random Forest, Gradient Boosting, XGBoost, AdaBoost, Bayesian Ridge, and MLP Regression. Includes model training, evaluation, and comparison using metrics like MSE, RMSE, and R².
unsupervised_learning_MNIST
This repository applies various unsupervised learning methods to the MNIST dataset of handwritten digits. Techniques include k-Means, Hierarchical Clustering, DBSCAN, GMM, PCA, t-SNE, Autoencoders, Isolation Forest, One-Class SVM, LDA, SOM, Agglomerative Clustering, Mean Shift, and Spectral Clustering. Explore the code and visualizations here!
Msoltaninezhad's Repositories
Msoltaninezhad/Baseline-Correction
correct baseline for spectroscopy data with polynomial subtraction and asymmetric least square method
Msoltaninezhad/FRET-calculations
This repository contains the code necessary to simulate the fluorescence emission of an anisotropic ensemble of dye molecules when excited by polarized light.
Msoltaninezhad/spectral-detector
Msoltaninezhad/bionanoimaging.github.io
Repository for hosting the website files
Msoltaninezhad/Box_Plot_Statistic
Box Plot with Detailed Statistics in Python
Msoltaninezhad/Data_Extract
This script automates data collection from .mat files into an Excel sheet, streamlining data preparation for analysis. It traverses directories, extracts specified data, and compiles it, making dataset aggregation efficient and ready for analysis.
Msoltaninezhad/DualDataDistributionAnalysis
The DualDataDistributionAnalysis repo offers a Python script for comparing two datasets via statistical plots: boxplots, violin plots, histograms, KDEs, CDFs, and swarm plots. It leverages pandas, Matplotlib, and Seaborn to visualize and analyze data distributions, ideal for exploratory data analysis and insights.
Msoltaninezhad/Error_absolut_relative
This Python script calculates the absolute and relative errors between simulation results and a theoretical value. It takes a list of measured values and a true value, returning the errors for each simulation, showcasing the deviation from the expected outcome.
Msoltaninezhad/Supervised-Learning-Algorithms-diabetic-data
A comprehensive application of supervised learning methods on the Diabetes Dataset, including Linear, Ridge, Lasso, ElasticNet, SVR, KNN, Random Forest, Gradient Boosting, XGBoost, AdaBoost, Bayesian Ridge, and MLP Regression. Includes model training, evaluation, and comparison using metrics like MSE, RMSE, and R².
Msoltaninezhad/unsupervised_learning_MNIST
This repository applies various unsupervised learning methods to the MNIST dataset of handwritten digits. Techniques include k-Means, Hierarchical Clustering, DBSCAN, GMM, PCA, t-SNE, Autoencoders, Isolation Forest, One-Class SVM, LDA, SOM, Agglomerative Clustering, Mean Shift, and Spectral Clustering. Explore the code and visualizations here!
Msoltaninezhad/Machine_Vision
This repository provides an analysis of the ISIC skin lesion dataset using various machine vision methods, including CNNs, transfer learning, and segmentation techniques. Explore techniques for melanoma detection, classification, and lesion segmentation, with detailed code and Jupyter notebooks for easy understanding.
Msoltaninezhad/sina