A review of analytical techniques for gait data. Part 1: Fuzzy, statistical and fractal methods.

By Tom Chau. Gait & Posture, 2001

420 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/ed047227a98b20030e6bc67059612c6e90e25036

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Signal Processing

Citations in the corpus

Activity identification using body-mounted sensors—a review of classification techniques (2009, methodology): “PCA locates the directions of maximal variance and the data are projected onto those directions.”
A review of analytical techniques for gait data. Part 2: neural network and wavelet methods. (2001, methodology): “A number of technical challenges in quantitative analysis of gait data were identified in Part 1 of this review [1].”
Explaining the unique nature of individual gait patterns with deep learning (2018, methodology): “Due to benefits of machine learning methods in comparison to conventional approaches in gait analysis [54, 47], LRP appears highly promising to increase their transparency and therefore make them applicable and reliable for clinical diagnoses [11, 12, 76].”
Capturing human motion using body‐fixed sensors: outdoor measurement and clinical applications (2004, background): “The importance of the advanced signal processing is emphasized in several studies related to motion analysis.(39,40)”
The use of artificial neural networks in decision support in cancer: A systematic review (2006, background): “While parallel studies have identified neural network methods among the most prevalent non-traditional methodologies for data analysis (Chau, 2001), in realising their potential application needs to overcome obstacles including the need for expanded databases and the need to establish multidisciplin”
Physical Human Activity Recognition Using Wearable Sensors (2015, background): “Supervised learning approaches for classiﬁcation such as artiﬁcial neural networks [57], Support Vector Machines (SVM) [59], require entirely labeled activity data.”