Next Article in Journal
Experimental Study on Storage and Maintenance Method of Ni-MH Battery Modules for Hybrid Electric Vehicles
Next Article in Special Issue
DC2Anet: Generating Lumbar Spine MR Images from CT Scan Data Based on Semi-Supervised Learning
Previous Article in Journal
Technical Evaluation Method for Physical Property Changes due to Environmental Degradation of Grout-Injection Repair Materials for Water-Leakage Cracks
Previous Article in Special Issue
Deep Learning in the Biomedical Applications: Recent and Future Status
Open AccessArticle

A Sample-Encoding Generalization of the Kohonen Associative Memory and Application to Knee Kinematic Data Representation and Pathology Classification

1
INRS-Énergie Matériaux et TéLécommunications, Montreal, QC J3X 1S2, Canada
2
Centre de Recherche LICEF, TELUQ University, Montreal, QC H2T 3E4, Canada
3
Laboratoire de Recherche en Imagerie et Orthopédie, Montreal, QC H2X 0A9, Canada
*
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(9), 1741; https://doi.org/10.3390/app9091741
Received: 2 March 2019 / Revised: 14 April 2019 / Accepted: 18 April 2019 / Published: 26 April 2019
(This article belongs to the Special Issue Machine Learning for Biomedical Data Analysis)
Knee kinematic data consist of a small sample of high-dimensional vectors recording repeated measurements of the temporal variation of each of the three fundamental angles of knee three-dimensional rotation during a walking cycle. In applications such as knee pathology classification, the notorious problems of high-dimensionality (the curse of dimensionality), high intra-class variability, and inter-class similarity make this data generally difficult to interpret. In the face of these difficulties, the purpose of this study is to investigate knee kinematic data classification by a Kohonen neural network generalized to encode samples of multidimensional data vectors rather than single such vectors as in the standard network. The network training algorithm and its ensuing classification function both use the Hotelling T 2 statistic to evaluate the underlying sample similarity, thus affording efficient use of training data for network development and robust classification of observed data. Applied to knee osteoarthritis pathology discrimination, namely the femoro-rotulian (FR) and femoro-tibial (FT) categories, the scheme improves on the state-of-the-art methods. View Full-Text
Keywords: Kohonen associative memory; kinematic data; knee pathologies classification Kohonen associative memory; kinematic data; knee pathologies classification
Show Figures

Figure 1

MDPI and ACS Style

Ben Nouma, B.; Mitiche, A.; Mezghani, N. A Sample-Encoding Generalization of the Kohonen Associative Memory and Application to Knee Kinematic Data Representation and Pathology Classification. Appl. Sci. 2019, 9, 1741.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

1
Back to TopTop