====== Tutorial Overview ======

Get more comfortable with all that Sift has to offer by working through the following tutorials.


==== Tutorial Data Files ====

Sift's tutorials use real data sets wherever possible in order to demonstrate realistic scenarios and avoid overly simplistic examples. Download links to the tutorial datasets can be found [[Sift:Tutorials:Tutorial_Files|here]].

==== Getting Started ====

Working through these four tutorials will provide you with an overview of how Sift lets you analyse your motion capture data sets from start to finish.

  * **Tutorial 1: [[Sift:Tutorials:Load_and_View_Data|Load signals into Sift and view them]]**
  * **Tutorial 2: [[Sift:Tutorials:Clean_your_Data|Clean your data]]**
  * **Tutorial 3: [[Sift:Tutorials:Perform_Principal_Component_Analysis|Perform Principal Component Analysis]]**
  * **Tutorial 4: [[Sift:Tutorials:Export_Results|Export your results]]**

==== Principal Component Analysis ====

[[Sift:Principal_Component_Analysis:Using_Principal_Component_Analysis_in_Biomechanics|PCA]] is a key analytical feature in Sift, allowing you to represent complex biomechanicals waveforms in low-dimensional spaces while maintaining most of the waveforms' information. This tutorial will provide you with an overview of how to perform PCA in Sift and of your options for follow-on analysis.

  * **[[Sift:Tutorials:Perform_Principal_Component_Analysis|Perform Principal Component Analysis]]**: This tutorial provides an overview of performing PCA. This tutorial is the same as the PCA tutorial in the "Getting Started" section.

Once PCA has been performed, it is possible to run different quality assurance processes:
  * **[[Sift:Tutorials:Outlier_Detection_with_PCA|PCA Outlier Detection]]**: This tutorial shows how you can use outlier detection methods to find outliers from your PCA analysis.
  * **[[Sift:Tutorials:Run_K-Means|Run K-Means]]**: This tutorial shows how you can use the k-means algorithms to cluster the results of PCA analysis.
  * **[[sift:tutorials:using_kmeans_to_cluster_kinetic_features_in_above_the_knee_amputees|Using K-means to cluster kinetic features in above-knee amputees]]**: This tutorial shows how you can use the k-means algorithm to explore a public data set.


==== Statistical Parametric Mapping ====

  * **[[sift:tutorials:perform_statistical_parametric_mapping|Perform Statistical Parametric Mapping]]**: This tutorial explores the uses of SPM in Sift, and how you can use it to draw useful analysis.

==== Building a Normal Database ====
  * **[[sift:tutorials:build_normal_database|Build a Normal Database]]**: This tutorial explores the uses of the Normal Database builder in Sift to generate a reference dataset.
  * **[[sift:tutorials:compute_GPS_and_GDI|Compute Gait Profile Score (GPS) and Gait Deviation Index (GDI)]]**: This tutorial explores how to leverage Sift's Normal Database files to compute GPS and GDI for individual subjects.
  * **[[Sift:Tutorials:OpenBiomechanics_Project:Analysis_of_Shoulder_Angular_Velocity_Baseball_Pitching|Analysis of Shoulder Angular Velocity between Elite Level and Average Collegiate Pitchers]]**: This tutorial shows you how to compare two groups using the normal database feature.

==== Gait Scores ====

  * **[[sift:tutorials:compute_GPS_and_GDI|Compute Gait Profile Score (GPS) and Gait Deviation Index (GDI)]]**: This tutorial explores how to leverage Sift's Normal Database files to compute GPS and GDI for individual subjects.

==== Command Line Interface and Console Application ====

  * **[[sift:tutorials:command_line|Batch Processing through the Command Line]]**: This tutorial demonstrates how Sift's command line interface can be used to automate analysis tasks and how these tasks can be automated using the Windows operating system.
  * **[[sift:tutorials:using_directory_watchers| Automating Work Flow With Directory Watchers]]**: This tutorial demonstrates how Sift's directory watchers can be used to automate an entire processing pipeline via the command line.

==== Public Data Sets ====

Exploring publicly available data with Sift is a great way to understand the original paper, learn about Sift's features, and get ideas for your own work.

  * **[[Sift:Tutorials:Treadmill_Walking_in_Healthy_Individuals|Treadmill Walking In Healthy Individuals]]**: This tutorial shows how you can use Visual3D and Sift to automate the processing of large-scale data sets.
  * **[[Sift:Tutorials:OpenBiomechanics_Project:Build_CMZ_Files|OpenBiomechanics Project: Build CMZs Files]]**: This tutorial shows how you can combine .c3d files and metadata into CMZ files for analysis in Sift.
  * **[[Sift:Tutorials:OpenBiomechanics_Project:Analysis_of_Baseball_Hitters_at_Different_Levels_of_Competition|Analysis of Baseball Hitters at Different Levels of Competition]]**: This tutorial shows how you can use Sift to automate the processing of large-scale data sets, and how metadata can be used to help you refine queries.
  * **[[Sift:Tutorials:OpenBiomechanics_Project:Analysis_of_Shoulder_Angular_Velocity_Baseball_Pitching|Analysis of Shoulder Angular Velocity between Elite Level and Average Collegiate Pitchers]]**: This tutorial shows you how to compare two groups using the normal database feature.
  * **[[sift:tutorials:using_kmeans_to_cluster_kinetic_features_in_above_the_knee_amputees|Using K-means to cluster kinetic features in above-knee amputees]]**: This tutorial shows how you can use the k-means algorithm to explore kinetic features for individuals using prosthetics after above-knee amputation.