Customization of Joint Articulations Using Soft Computing Methods

The wear of artificial joints, which is one of the main causes of re-implantation of the hip joint, can be minimized or entirely eliminated through a precise adjustment of artificial biobearing to individual conditions of the patient. This is possible through utilization of modern engineering tools for support of doctors in multi-aspect selection of head elements and acetabulum that work in the artificial joint. Despite a substantial number of materials used for the friction pair of both head and acetabulum, there is no perfect and universal set of biomaterials that allow for recreation of functionality of joints in all patients, while improperly selected joint articulation results in faster wear of components, migration of products of wear to soft tissue and, consequently numerous complications and necessity of repeated surgical interventions. An innovative approach that allows for customization of joint replacement, which is impossible to be achieved using conventional methods, is to utilize machine learning systems to adjust friction pair to anthropometric and goniometric characteristics of a patient. The internal elements which are used to train a fuzzy classifier ensemble are results of clinical, experimental and numerical studies that allow for prediction of the functional cycle for a patient.

[1]  Robert E. Schapire,et al.  A Brief Introduction to Boosting , 1999, IJCAI.

[2]  Rafal Scherer,et al.  Fuzzy Number-Based Hierarchical Fuzzy System , 2004, ICAISC.

[3]  Alexander I. Galushkin,et al.  The Parallel Approach to the Conjugate Gradient Learning Algorithm for the Feedforward Neural Networks , 2014, ICAISC.

[4]  Ataollah Abbasi,et al.  Fast FCM with Spatial Neighborhood Information for Brain Mr Image Segmentation , 2013, J. Artif. Intell. Soft Comput. Res..

[5]  Leszek Rutkowski,et al.  Computational intelligence - methods and techniques , 2008 .

[6]  Rafal Scherer,et al.  An ensemble of logical-type neuro-fuzzy systems , 2011, Expert Syst. Appl..

[7]  Jaroslaw Bilski,et al.  Parallel Architectures for Learning the RTRN and Elman Dynamic Neural Networks , 2015, IEEE Transactions on Parallel and Distributed Systems.

[8]  Thomas Fevens,et al.  Web–Based Framework For Breast Cancer Classification , 2014, J. Artif. Intell. Soft Comput. Res..

[9]  Rafal Scherer,et al.  New Methods for Uncertainty Representations in Neuro-Fuzzy Systems , 2003, PPAM.

[10]  Hoo Sang Ko,et al.  Application of Artificial Neural Network and Genetic Algorithm to Healthcarewaste Prediction , 2013, J. Artif. Intell. Soft Comput. Res..

[11]  Adam Krzyżak,et al.  A Novel Approach for Automatic Detection and Classification of Suspicious Lesions in Breast Ultrasound Images , 2013, J. Artif. Intell. Soft Comput. Res..

[12]  R. Scherer.  Neuro-fuzzy relational systems for nonlinear approximation and prediction , 2009 .

[13]  Lukasz Laskowski,et al.  A novel hybrid-maximum neural network in stereo-matching process , 2012, Neural Computing and Applications.

[14]  Krzysztof Cpalka,et al.  A New Method for Design and Reduction of Neuro-Fuzzy Classification Systems , 2009, IEEE Transactions on Neural Networks.

[15]  A. Szarek.  Ocena zużycia metalowych głów endoprotez stawu biodrowego usuniętych z organizmu ludzkiego z powodu aseptycznego obluzowania , 2008 .

[16]  Rafal Scherer.  Boosting Ensemble of Relational Neuro-fuzzy Systems , 2006, ICAISC.

[17]  Robert Nowicki,et al.  Rough-Neuro-Fuzzy System with MICOG Defuzzification , 2006, 2006 IEEE International Conference on Fuzzy Systems.

[18]  G. Stradomski,et al.  The Analysis of Hip Joint Prosthesis Head Microstructure Changes during Variable Stress State as a Result of Human Motor Activity , 2012 .

[19]  Krystian Lapa,et al.  A New Approach to Designing Interpretable Models of Dynamic Systems , 2013, ICAISC.

[20]  Ujjwal Maulik,et al.  Integrated Statistical and Rule-Mining Techniques for Dna Methylation and Gene Expression Data Analysis , 2013, J. Artif. Intell. Soft Comput. Res..