A SampleEncoding Generalization of the Kohonen Associative Memory and Application to Knee Kinematic Data Representation and Pathology Classification
Abstract
:1. Introduction
2. Materials and Methods
2.1. Knee Kinematic Data Collection
2.2. Classification by a SampleEncoding Generalization of the Kohonen Neural Network
2.2.1. Sample Similarity and the TwoSample Hotelling ${T}^{2}$ Statistic
2.2.2. SampleEncoding Kohonen Network Algorithm
Algorithm 1 Network algorithm 
Input$\mathbf{X}=\{{\mathbf{x}}_{1},\dots ,{\mathbf{x}}_{N}\}$, $i=1,\dots ,N$ 
Output${\mathbf{W}}_{j}=\{{\mathbf{w}}_{1j},\dots ,{\mathbf{w}}_{Nj}\}$, $j=1,\dots ,J$

2.3. Dimensionality Reduction
2.4. Evaluation of the SampleEncoding Kohonen Network Results
3. Results
4. Discussion
Author Contributions
Funding
Conflicts of Interest
References
 Nguyen, U.; Zhang, Y.; Zhu, Y.; Niu, J.; Zhang, B.; Felson, D. Increasing prevalence of knee pain and symptomatic knee osteoarthritis: Survey and cohort data. Ann. Intern. Med. 2011, 155, 725–732. [Google Scholar] [CrossRef]
 Peat, G.; McCarney, R.; Croft, P. Knee pain and osteoarthritis in older adults: A review of community burden and current use of primary health care. Ann. Rheum. Dis. 2001, 60, 91–97. [Google Scholar] [CrossRef] [PubMed]
 Mezghani, N.; Boivin, K.; Turcot, K.; Aissaoui, R.; Hagmeister, N.; De Guise, J. Hierarchical analysis and classification of asymptomatic and knee osteoarthritis gait patterns using a wavelet representation of kinetic data and the nearest neighbor classifier. J. Mech. Med. Biol. 2008, 8, 45–54. [Google Scholar] [CrossRef]
 Astephen, J.L.; Deluzio, K.J.; Caldwell, G.E.; Dunbar, M.J.; HubleyKozey, C.L. Gait and neuromuscular pattern changes are associated with differences in knee osteoarthritis severity levels. J. Biomech. 2008, 41, 868–876. [Google Scholar] [CrossRef] [PubMed]
 Elbaz, A.; Mor, A.; Segal, G.; Debi, R.; Shazar, N.; Herman, A. Classification of knee osteoarthritis according to spatiotemporal gait analysis. Osteoarthr. Cartil. 2013, 21, S63–S312. [Google Scholar] [CrossRef]
 Astephen, J.L.; Deluzio, K.J.; Caldwell, G.E.; Dunbar, M.J. Biomechanical changes at the hip, knee, and ankle joints during gait are associated with knee osteoarthritis severity. J. Orthop. Res. 2008, 26, 332–341. [Google Scholar] [CrossRef] [Green Version]
 Jones, L.; Holt, C.A.; Beynon, M.J. Reduction, classification and ranking of motion analysis data: An application to osteoarthritic and normal knee function data. Comput. Methods Biomech. Biomed. Eng. 2008, 11, 31–40. [Google Scholar] [CrossRef]
 Mezghani, N.; Ouakrim, Y.; Fuentes, A.; Mitiche, A.; Hagemeister, N.; Vendittoli, P.A.; de Guise, J.A. Mechanical biomarkers of medial compartment knee osteoarthritis diagnosis and severity grading: Discovery phase. J. Biomech. 2017, 52, 106–112. [Google Scholar] [CrossRef]
 Hagemeister, N.; Parent, G.; Van de Putte, M.; StOnge, N.; Duval, N.; De Guise, J. A reproducible method for studying threedimensional knee kinematics. J. Biomech. 2005, 38, 1926–1931. [Google Scholar] [CrossRef] [PubMed]
 Ben Nouma, B.; Mezghani, N.; Mitiche, A.; Ouakrim, Y. A variational method to determine the most representative shape of a set of curves and its application to knee kinematic data for pathology classification. MedPRAI 2018, 22–26. [Google Scholar] [CrossRef]
 Duda, R.; Hart, P.; Stork, D. Pattern Classification; A WileyInterscience Publication; John Wiley & Sons, Inc.: Hoboken, NJ, USA, 2012. [Google Scholar]
 Mezghani, N.; Ouakrim, Y.; Fuentes, A.; Mitiche, A.; Hagemeister, N.; Vendittoli, P.; De Guise, J. An Analysis of 3D Knee Kinematic Data Complexity in Knee Osteoarthritis and Asymptomatic Controls. PLoS ONE 2018, 13, e0202348. [Google Scholar] [CrossRef] [PubMed]
 Lustig, S.; Magnussen, R.; Cheze, L.; Neyret, P. The KneeKG system: A review of the literature. Knee Surg. Sport Traumatol. Arthrosc. 2012, 20, 633–638. [Google Scholar] [CrossRef]
 Härdle, W.; Simar, L. Applied Multivariate Statistical Analysis; Springer: Berlin/Heidelberg, Germany, 2007. [Google Scholar]
 Kaski, S. Data exploration using selforganizing maps. In Acta Polytechnica Scandinavica: Mathematics, Computing and Management in Engineering Series No. 82; 1997. [Google Scholar]
 Ritter, H.; Martinetz, T.; Schulten, K. Neural Computation and SelfOrganizing Maps: An Introduction; AddisonWesley Publishing Company: Boston, MA, USA, 1992. [Google Scholar]
 Mitiche, A.; Aggarwal, J. Pattern category assignment by neural networks and nearest neighbors rule: A synopsis and a characterization. In Studies In Pattern Recognition: A Memorial to the Late Professor KingSun Fu; World Scientific: Singapore, 1996; pp. 3–18. [Google Scholar]
 Cottrell, M.; Rousset, P. The Kohonen algorithm: A powerful tool for analysing and representing multidimensional quantitative and qualitative data. In Proceedings of the International WorkConference on Artificial Neural Networks, Lanzarote, Spain, 12 June 1997; pp. 861–871. [Google Scholar]
 Deboeck, G.; Kohonen, T. (Eds.) Visual Explorations in Finance: With SelfOrganizing Maps; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2013. [Google Scholar]
 Kaski, S.; Oja, E. Kohonen Maps; Elsevier Science Inc.: Amsterdam, The Netherlands, 1999. [Google Scholar]
 Kohonen, T. SelfOrganizing Maps, 3rd ed.; Springer: Berlin/Heidelberg, Germany, 2001. [Google Scholar]
 Le Bail, E.; Mitiche, A. Quantification vectorielle d’images par le réseau neuronal de Kohonen. Trait. Signal 1989, 6, 529–539. [Google Scholar]
 Nasrabadi, N.; Feng, Y. Vector quantization of images based upon the Kohonen selforganizing feature maps. In Proceedings of the IEEE 1988 International Conference on Neural Networks, San Diego, CA, USA, 24–27 July 1988; pp. 101–105. [Google Scholar]
 Mezghani, N.; Mitiche, A.; Cheriet, M. Maximum Entropy Gibbs Density Modeling for Pattern Classification. Entropy 2012, 14, 2478–2491. [Google Scholar] [CrossRef] [Green Version]
 Mezghani, N.; Mitiche, A.; Cheriet, M. Bayes Classification of Online Arabic Characters by Gibbs Modeling of Class Conditional Densities. IEEE Trans. Pattern Anal. Mach. Intell. 2008, 30, 1121–1131. [Google Scholar] [CrossRef] [PubMed]
 González, I.; García, H. Fuzzy Labeled Selforganizing Map with KernelBased Topographic Map Formation. In Proceedings of the International Conference on Artificial Neural Networks, Porto, Portugal, 9–13 September 2007; pp. 341–348. [Google Scholar]
 Hotelling, H. The generalization of Student’s ratio. In Breakthroughs in Statistics; Springer: Berlin/Heidelberg, Germany, 1992; pp. 54–65. [Google Scholar]
 Johnson, R.; Wichern, D. Applied Multivariate Statistical Analysis, 6th ed.; PrenticeHall, Inc.: Upper Saddle River, NJ, USA, 2007. [Google Scholar]
 McLachlan, G. Mahalanobis distance. Resonance 1999, 4, 20–26. [Google Scholar] [CrossRef]
 Daubechies, I. Ten Lectures on Wavelets; CBMSNSF Regional Conference Series in Applied Mathematics; Siam: Philadelphia, PA, USA, 1990. [Google Scholar]
 Mallat, S. A Wavelet Tour of Signal Processing: The Sparse Way, 3rd ed.; Academic Press: Cambridge, MA, USA, 2008. [Google Scholar]
 Cohen, A. Ten Lectures on Wavelets, CBMSNSF Regional Conference Series in Applied Mathematics, Vol. 61, I. Daubechies, SIAM, 1992, Xix + 357 Pp. J. Approx. Theory 1994, 78, 460–461. [Google Scholar] [CrossRef]
 Akanksha, N.; Mridu, S.; Shrish, V.; Raj, V. Dimensionality Reduction for Motor Imagery Signal Classification using Wavelet Analysis. Int. J. Control Theory Appl. 2017, 10, 65–76. [Google Scholar]
 Thepade, S.; Erandole, S. Extended performance comparison of tiling based image compression using wavelet transforms amp; hybrid wavelet transforms. In Proceedings of the IEEE Conference on Information Communication Technologies, Singapore, 1–2 December 2013; pp. 1150–1155. [Google Scholar]
 Taujuddin, N.; Ibrahim, R.; Sari, S. Wavelet Coefficients Reduction Method Based On Standard Deviation Concept For High Quality Compressed Image. J. Theor. Appl. Inf. Technol. 2015, 79, 380–388. [Google Scholar]
 Boix, M.; Canto, B. Wavelet Transform application to the compression of images. Math. Comput. Model. 2010, 52, 1265–1270. [Google Scholar] [CrossRef]
 Jolliffe, I.; Cadima, J. Principal component analysis: A review and recent developments. Phil. Trans. R. Soc. A 2016, 374, 20150202. [Google Scholar] [CrossRef]
 Shao, J. Linear model selection by crossvalidation. J. Am. Stat. Assoc. 1993, 88, 486–494. [Google Scholar] [CrossRef]
 Sharma, L.; Song, J.; Felson, D.; Cahue, S.; Shamiyeh, E.; Dunlop, D. The role of knee alignment in disease progression and functional decline in knee osteoarthritis. J. Am. Med. Assoc. 2001, 286, 188–195. [Google Scholar] [CrossRef]
 Thorp, L.; Sumner, D.; Block, J.; Moisio, K.; Shott, S.; Wimmer, M. Knee joint loading differs in individuals with mild compared with moderate medial knee osteoarthritis. Arthritis Rheumatol. 2006, 54, 3842–3849. [Google Scholar] [CrossRef] [PubMed] [Green Version]
Characteristics  C_{1}:FR  C_{2}:FT  C_{3}:FRFT 

Age (years)  46.1 * ± 11.7  59.5 * ± 10.1  59.6 ± 11.4 
Height (m)  1.71 ± 0.07  1.66 ± 0.09  1.66 ± 0.11 
Weight (kg)  82.9 ± 20.7  76.2 ± 11.2  84.3 ± 15.9 
BMI (kg/m^{2})  28.3 ± 7.1  27.4 ± 3.9  30.3 ± 5.5 
Men%  45  38  33.3 
Predicted  C_{1}:FR  C_{2}:FT  τ (%) 

Real  
${C}_{1}$:FR  20  1  90.47 
${C}_{2}$:FT  3  18 
Predicted  C_{1}:FR  C_{2}:FT  C_{3}:FRFT  τ (%) 

Real  
${C}_{1}$:FR  18  1  2  71.43 
${C}_{2}$:FT  3  14  4  
${C}_{3}$:FRFT  4  4  13 
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ben Nouma, B.; Mitiche, A.; Mezghani, N. A SampleEncoding Generalization of the Kohonen Associative Memory and Application to Knee Kinematic Data Representation and Pathology Classification. Appl. Sci. 2019, 9, 1741. https://doi.org/10.3390/app9091741
Ben Nouma B, Mitiche A, Mezghani N. A SampleEncoding Generalization of the Kohonen Associative Memory and Application to Knee Kinematic Data Representation and Pathology Classification. Applied Sciences. 2019; 9(9):1741. https://doi.org/10.3390/app9091741
Chicago/Turabian StyleBen Nouma, Badreddine, Amar Mitiche, and Neila Mezghani. 2019. "A SampleEncoding Generalization of the Kohonen Associative Memory and Application to Knee Kinematic Data Representation and Pathology Classification" Applied Sciences 9, no. 9: 1741. https://doi.org/10.3390/app9091741