Sankt-Peterburg, St. Petersburg, Russian Federation
It is necessary to choose between several competing methodologies and techniques among the many methods of knowledge management analysis. The paper proposes using machine learning methods to evaluate knowledge management strategies. Due to the vast information on this subject, the main conclusions were obtained using the normative documentation on strategy evaluations. The tasks of choosing a strategy are solved using neural networks. Evaluation of the eff ectiveness of the strategy was found using a hybrid neurofuzzy system. The base of examples necessary for training neural networks was formed using the Monte Carlo method, and its quality was checked through the use of the principal components. Testing the work of the neural network in the form of a perceptron showed its suitability for choosing a knowledge management strategy. The eff ectiveness of the chosen strategy was evaluated using an ANFIS type system, which demonstrated the possibility of obtaining a quantitative scoring.
knowledge management, machine learning, factors influencing strategies, building a base of examples, neural network choice of evaluation strategies, neurofuzzy evaluation of eff ectiveness
1. Nadali A., Nosratabadi H., Pourdarab S. ANP-FIS Method for Determining the Knowledge Management Strategy. International Journal of Information and Education Technology, 2011, Vol. 1, No. 2, p. 107–113.
2. Ratnaparkhi P.S., Butey P.K. Summary: Smart Decision Making Using Fuzzy Logic For Knowledge Management System. International Journal of Computer Engineering and Technology, 2014, Vol. 5, No. 10, p. 41-50.
3. GOST R 53894-2016. Menedzhment znanij. Terminy i opredeleniya [GOST R 53894-2016. Knowledge management. Terms and Definitions]. Moscow: Standartinform Publ., 2016.
4. GOST R 57127-2016. Menedzhment znanij. Rukovodstvo po nailuchshej praktike [GOST R 57127-2016. Knowledge management. Best Practice Guide]. Moscow: Standartinform Publ., 2016.
5. Kim P. MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence., Soul-t\'ukpyolsi, Seoul, 2017.
6. Alpaydın E. Introduction to Machine Learning. MIT Press Cambridge, Massachusetts, 2010.
7. Jolliffe I.T. Principal component analysis. Springer, New York, 2002. p. 519
8. Haykin S. 2009. Neural Networks and Learning Machines. NY, Pearson Education. pp: 937.
9. Neural Network Toolbox™. User\'s Guide. The MathWorks, Inc., MA, 2015. pp: 410.
10. Mewada K.M., Sinhal A., Verma B. (2013) Adaptive Neuro-Fuzzy Inference System (ANFIS) based software evaluation. International Journal of Computer Science 10(1): 244–250
11. Ramsundar B., Zade R.B. TensorFlow dlya glubokogo obucheniya [TensorFlow for deep learning]. Moscos: BHV Publ., 2019. 250 p.
12. Shakla N. Mashinnoe obuchenie i TensorFlow [Machine Learning and TensorFlow]. St.-Petersburg: Piter Publ., 2019. 336 p.
