Alloys selection based on the supervised learning technique for design of biocompatible medical materials

• Autorzy: Tepla T. L. , Izonin I. V. , Duriagina Z. A. , Tkachenko R. O. , Trostianchyn A. M. , Lemishka I. A. , Kulyk V. V. , Kovbasyuk T. M.

Identyfikatory

DOI

10.5604/01.3001.0012.6944

• Języki publikacji: EN

Abstrakty

EN

Purpose: The main aim of this paper is development, software implementation and use of the alloys selection method for the design of biocompatible materials in medical production. It is based on the use of Ito decomposition and Logistic Regression. Design/methodology/approach: The technology of machine learning is used to solve the task. The developed classification method is based on the application of multiclass Logistic Regression. In order to reduce the probability of incorrect alloy identification, expansion of the input characteristics based on the Ito decomposition of the second order has been made. On the one hand, it increased the dimension of the input features space, and as a result, it increased the time for training procedure, but on the other, it increased the solution accuracy of the alloys selection task. The accuracy evaluation of the method was carried out using different criteria. In particular, the method accuracy was estimated based on the ratio of correctly classified titanium alloys samples to the test sample dimension. This measure was used to assess the classification accuracy in the training and test modes. For a more detailed analysis of the classification method results, two additional measures were further used: Precision and Recall. Their calculation was based on the constructed confusion matrix. This made it possible to assess the ability of the developed method to find the instances of each individual alloy as a whole, as well as the ability to distinguish instances of one class from representatives on the other. The combination of these indicators allowed to evaluate the classification task accuracy in the conditions of the imbalance dataset for each class of the investigated material separately. Findings: The simulation results confirmed the effectiveness of the use of machine learning tools to solve this task. High indicators of the method’s accuracy based on the experimental results were established. In particular, the overall accuracy of the method is 96.875%, and the average values of Precision and Recall for all four classes are 94% and 98% respectively. Expansion of each vector's features from the training dataset by using Ito decomposition increased the method accuracy by more than 33% compared to the basic Logistic Regression. Research limitations/implications: The Logistic Regression's training procedure, as well as the increase of the space size of the investigated alloy's input features by using Ito decomposition, imposes a number of limitations on the application of the method in tasks that depend on the duration of the work. Practical implications: The proposed machine learning approach foralloys selection allows reducing the time, material and human resources needed to investigate the titanium alloys properties. The developed method increases the accuracy of the selection alloys task compared to the four known methods, an average of 14.5%. It can be used to select materials with appropriate properties for the design of biocompatible medical products. Originality/value: A method and software product for the titanium alloys classification task using a supervised learning technique has been developed. For this aim, the method of Logistic Regression with expanding inputs based on the second-order Ito decomposition is used.

Słowa kluczowe

EN

biocompatible material; titanium alloys; medical implants; supervised learning; Logistic Regression; Ito decomposition; classification task

PL

materiał biokompatybilny; stopy tytanu; implanty medyczne; nauka nadzorowana; regresja logistyczna; dekompozycja Ito

• Wydawca: International OCSCO World Press
• Czasopismo: Archives of Materials Science and Engineering
• Rocznik: 2018
• Tom: Vol. 93, nr 1
• Strony: 32--40
• Opis fizyczny: Bibliogr. 28 poz.

Twórcy

autor

Tepla T. L.

• Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

autor

Izonin I. V.

• Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

autor

Duriagina Z. A.

• Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine
• The John Paul II Catholic University of Lublin, Al. Racławickie 14, 20-950 Lublin, Poland

autor

Tkachenko R. O.

• Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

autor

Trostianchyn A. M.

• Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

autor

Lemishka I. A.

• Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

autor

Kulyk V. V.

• Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

autor

Kovbasyuk T. M.

• Lviv Polytechnic National University, 12 Bandera St., Lviv, 79013, Ukraine

Bibliografia

• [1] A.T. Sidambe, Biocompatibility of Advanced Manufactured Titanium Implants - A Review, Materials 7 (2014) 8168-8188, doi: https://doi.org/ 10.3390/ma7128168.
• [2] I. Yadroitsev, P. Krakhmalev, I. Yadroitsava, Selective laser melting of Ti6A14V alloy for biomedical applications: temperature monitoring and microstructural evolution, Journal of Alloys and Compounds 583 (2013) 404-409, doi: https://doi.org/ 10.1016/j.jallcom.2013.08.183.
• [3] L.A. Dobrzański, The concept of biologically active microporous engineering materials and composite biological-engineering materials for regenerative medicine and dentistry, Archives of Materials Science and Engineering 80/2 (2016) 64-85, doi: https //doi.org/10.5604/18972764.1229638.
• [4] Y.T. Sul, C. Johansson, A. Wennerberg, L.R. Cho, B.S. Chang, T. Albrektsson, Optimum surface properties of oxidized implants for reinforcement of osseointegration: surface chemistry, oxide thickness, porosity, roughness, and crystal structure, International Journal Oral Maxillofacial Implants 20/3 (2005) 349-359.
• [5] A. Jemat, M.J. Ghazali, M. Razali, and Y. Otsuka, Surface Modifications and Their Effects on Titanium Dental Implants, BioMed Research International 2015 (2015) , Article ID 791725, doi: https://doi.org/ 10.1155/2015/791725.
• [6] R.C. Petersen, Titanium implant osseointegration problems with alternate solutions using Epoxy/ Carbon-Fiber-Reinforced Composite, Metals (Basel) 4/4 (2014) 549-569, doi: https://doi.org/10.3390/ met4040549.
• [7] Y.T. Sul, C. Johansson, E. Byon, T. Albrektsson, The bone response of oxidized bioactive and nonbioactive titanium implants, Biomaterials 33/26 (2005) 6720-6730.
• [8] Y.T. Zhu, T.C. Lowe, T.G. Langdon, Performance and applications of nanostructured materials produced by severe plastic deformation, Scripta Materialia 51/8 (2004) 825-830, doi: https://doi.org/10.1016/j.scriptamat.2004.05.006.
• [9] I. Braceras, J.I. Alava, J.I. Onate, M. Brizuela, A. Garcia-Luis, N. Garagorri, J.L. Viviente, M.A. de Maeztu, Improved osseointegration in ion implantation-treated dental implants, Surface and Coatings Technology 158-159 (2002) 28-32, doi: https://doi.org/10.1016/S0257-897(02)00203-7.
• [10] M. Martinez-Calderon, M. Manso-Silvan, A. Rodriguez, M. Gómez-Aranzadi, J.P. Garcia-Ruiz, S.M. Olaizola, R.J. Martin-Palma, Surface micro-and nano- texturing of stainless steel by femtosecond laser for the control of cell migration, Scientific Reports 6 (2016) 36296, doi: https://doi.org/10.1038/srep36296.
• [11] J. Heinrichs, T. Jarmar, M. Rooth, H. Enqvist, In vitro bioactivity of Atomic Layer Deposited titanium dioxide on titanium and silicon substrates, Key Engineering Materials 361-363 (2008) 689-692, doi: https://doi.org/10.4028/www.scientific.net/KEM.361- 363.689.
• [12] A.A. Solovyev, D.V. Ovchinnikov, E.V. Korostelev, A.M. Markeev, Correlation between structural and bioactive properties of titanium dioxide formed by atomic layer deposition, Nanotechnologies in Russia 8/5-6 (2013) 388-391.
• [13] M. Huber, G. Reinisch, G. Trettenhahn, K. Zwey- muller, F. Lintner, Presence of corrosion products and hypersensitivity-associated reactions in periprosthetic tissue after aseptic loosening of total hip replacements with metal bearing surfaces, Acta Biomaterialia 1/5 (2009) 172-180, doi: https://doi.Org/10.1016/j.actbio. 2008.07.032.
• [14] Z.A. Duriagina, R.O. Tkachenko, A.M. Trostianchyn, I.A. Lemishka, A.M. Kovalchuk, V.V. Kulyk, T.M. Kovbasyuk, Determination of the best microstructure and titanium alloy powders properties using neural network, Journal of Achievements in Materials and Manufacturing Engineering 87/1 (2018) 25-31, doi: https://doi.org/10.5604/01.3001.0012.0736.
• [15] R. Tkachenko, Z. Duriagina, I. Lemishka, I. Izonin, A. Trostianchyn, Development of machine learning method of titanium alloys properties identification in additive technologies, EastemEuropean Journal of Enterprise Technologies 3/12 (2018) 23-31, doi: https://doi.org/10 15587/1729-4061.2018.134319.
• [16] G. Setlak, Y. Bodyanskiy, O. Vynokurova, I. Pliss, Deep evolving GMDH-SVM-neural network and its learning for Data Mining tasks, Proceedings of the Federated Conference on Computer Science and Information Systems (FedCSIS), Gdansk, 2016, 141-145.
• [17] T.M. Cover, Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition, IEEE Transactions on Electronic Computers 14 (1965) 326-334, doi: https://doi.org/ 10.1109/PGEC.1965.264137.
• [18] S. Haykin, Neural networks and learning machines, 3rd Edition, 2009, 904.
• [19] A. Ng, Machine Learning. Lecture 7.1 - Regularization. The Problem Of Overfitting, URL: https://www.youtube.com/watch?v=u73PU6QwllI.
• [20] C-J. Lin, R.C. Weng, S.S. Keerthi, Trust Region Newton Method for Large-Scale Logistic, Regression Journal of Machine Learning Research, 9 (2008) 627-650, URL: https://www.csie.ntu.edu.tw/~cjlin/papers/ logistic.pdf.
• [21] N. Sadawi. Evaluating Classifiers: Confusion Matrix for Multiple Classes, URL: https://www.youtube.com/ watch?v=FAr2GmWNbT0.
• [22] Scikit-leam Machine Learning in Python, URL: http://scikit-leam.org/stable.
• [23] Data Mining Fruitful and Fun, URL: https://orange.biolab.si.
• [24] V. Lytvyn, V. Vysotska, I. Peleshchak, I. Rishnyak, R. Peleshchak, Time Dependence of the Output Signal Morphology for Nonlinear Oscillator Neuron Based on Van der Pol Model, International Journal of Intelligent Systems and Applications (IJISA) 10/4 (2018) 8-17, doi: https://doi.org/10.5815/ijisa. 2018.04.02.
• [25] N. Shakhovska, V. Vysotska, L. Chyrun, Features of E-leaming realization using virtual research laboratory, Proceedings of the XIth International Scientific and Technical Conference “Computer Sciences and Information Technologies”, CSIT, 2016, 143-148.
• [26] Ye. Bodyanskiy, O. Vynokurova, G. Setlak, D. Peleshko, P. Mulesa, Adaptive multivariate hybrid neuro-fuzzy system and its on-board fast learning, Neurocomputing 230 (2017) 409-416, doi: https://doi.Org/10.1016/j.neucom.2016.12.042.
• [27] Z.A. Duryagina, S.A. Bespalov, A.K. Borysyuk, V.Ya. Pidkova, Magnetometric analysis of surface layers of 12X18H10T steel after ion-beam nitriding, Metallofizika i Noveishie Tekhnologii 33/5 (2011) 615-622.
• [28] M.I. Pashechko, V.V. Shyrokov, Z.A. Duryahina, Kh.B. Vasyliv, Structure and corrosion-mechanical properties of the surface layers of steels after laser alloying, Materials Science 39/1 (2003) 108-117, doi: https://doi.org/10.1023/A:1026134714719.