Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorNarendra Utama
dc.description.abstractThis work aims to create an algorithm of gait pattern planning system. In this work, the algorithm is divided into two stages. First stage is to predict natural gait parameters (cadence and stride length) and the second stage is to construct or map the gait pattern based on gait parameters and anatomy parameters (thigh, calf and foot length). Two networks based on Neural Network model is built and trained to predict the gait parameters of a subject. Gait pattern waveform is analyzed by using Fourier Transform. Multiple Linear Regression (MLR) and Neural Network (NN) are created in order to study the relationship between fourier coefficients and the parameters (anatomy and gait parameters). It is found that Neural Network model has high accuracy to predict the gait parameters. It also found that gait and anatomy parameters have significant effect to the fourier coefficients of lower limb waveform, but the relationship is not linear. In conclusion, Neural Network model has high accuracy not only to predict the gait parameters but also to predict the fourier coefficients and gait pattern waveform can be predicted by substituting the predicted fourier coefficients into fourier series equation.en_US
dc.format.extent108 p.en_US
dc.rightsNanyang Technological University
dc.subjectDRNTU::Engineering::Mechanical engineeringen_US
dc.titleAlgorithm of gait pattern planning system for gait rehabilitation roboticen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorHoon Kay Hiangen_US
dc.contributor.supervisorLow Kin Huaten_US
dc.contributor.schoolSchool of Mechanical and Aerospace Engineeringen_US
dc.description.degreeBachelor of Engineering (Mechanical Engineering)en_US
item.fulltextWith Fulltext-
Appears in Collections:MAE Student Reports (FYP/IA/PA/PI)
Files in This Item:
File Description SizeFormat 
  Restricted Access
3.05 MBAdobe PDFView/Open

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.