LACourtenay/Deep-Neural-Network-for-Cut-Mark-Classification

Stars
1
Language
Jupyter Notebook
License
GNU General Publi...
Created over 5 years ago
Updated over 1 year ago

LACourtenay/Deep-Neural-Network-for-Cut-Mark-Classification

LACourtenay

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Neural Networks are highly powerful and versatile algorithms that can be trained to complex and large datasets. Here lies the code and details used to design a Neural Network that differentiates anthropic butchery traces from naturally produced trampling damage on bones

GraphGMM

An extension to geometric morphometric libraries oriented towards the integration of Graph Theory into the analysis of landmark data. Graph-based Geometric Morphometrics is additionally accompanied by other non-linear dimensionality reduction algorithms.

Support-Vector-Machine-for-Morphological-Analysis

Support Vector Machines (SVM) are powerful Machine Learning algorithms that can provide efficient and high performing classifications of complex data sets. Here lies R-Code that can be used to process morphological data using SVMs that have been able to achieve 100% classification rates in some practical cases.

HyperSkinCare_DL

Code used for the training of Convolutional Neural Support Vector Machines (CNSVM) for the classification of Hyperspectral signatures obtained from Basal Cell Carcinoma Skin Cancer patients

Carnivore_Tooth_Pit_Classification

Source code and Datasets from the article "Developments in Data Science Solutions for Carnivore Tooth Pit Classification"

Jupyter Notebook

HyperSkinCare_Statistics

Code used for the robust statistical analysis of Hyperspectral signatures obtained from Non-Melanoma Skin Cancer patients

Handaxe_Simulation

Code used for the simulation of theoretical handaxes

GMM_Measurement_Accuracy_Tools

Statistical tools and methods for the evaluation of measurement error and accuracy in geometric morphometric analyses