Article

Received 12.01.2023

Revised 07.05.2023

Accepted 14.06.2023

Retrieved from Iss. 113, P. 2, 2023

Pages 171 -179

Sysoiev, I., Gavrilenko, V., & Kovalchuk, O. (2023). USING NEURAL NETWORKS TO EVALUATE THE COMPLEXITY OF A JSONFORMATTED QUERY. Automobile Roads and Road Construction, (113.2), 171-179. https://doi.org/10.33744/0365-8171-2023-113.2-171-179

USING NEURAL NETWORKS TO EVALUATE THE COMPLEXITY OF A JSONFORMATTED QUERY

Illia Sysoiev Valeriy Gavrilenko Oksana Kovalchuk

This article focuses on the use of neural networks for assessing the complexity of JSON-formatted queries from both theoretical and practical perspectives. The theoretical description of neural networks, their components, and peculiarities is provided, and the issue of query complexity in JSON format is explored. Additionally, a systematic approach is proposed for evaluating and comparing the computational complexity of neural network levels in the test processing of JSON signals. The connection between software and hardware complexity indicators is established by defining them as hyperparameters of the neural network layers. The paper explains how to compute metrics for the forward and recurrent levels and determines the specific metrics to be used based on whether the focus is on software or hardware-oriented modules. This work can be valuable for obtaining different levels (goals) of complexity assessment related to the application of neural networks in real-time signal processing and for standardizing the evaluation of computational complexity. Overall, this research provides insights into the utilization of neural networks for assessing query complexity in the JSON format, offering a systematic approach to evaluating computational complexity in the context of neural network levels

neural networks, JSON, balancing, algorithm development
  1. Sysoiev, I.K., & Havrylenko, V.V. (2022). Adaptive load balancing algorithm in applications using containerization technology. Systems of Control, Navigation and Communication. Collection of Scientific Papers, 1(67), 81-83.
  2. Havrylenko, V.V., & Sysoiev, I.K. (2019). Design of auto-scalable high-load applications. In Proceedings of the VII international scientific and technical conference “Problems of informatization” (p. 15). Kharkiv.
  3. Sysoiev, I.K., & Havrylenko, V.V. (2021). Adaptive load balancing algorithm in applications using containerization technology. In Proceedings of the VIII international internet scientific and technical conference “Modern methods, information, software and technical support of control systems for organizational-technical and technological complexes” (p. 272). Kyiv: National University of Food Technologies.
  4. Havrylenko, V.V., & Sysoiev, I.K. (2019). Management of containers for high-load applications in IT systems. In Proceedings of the III All-Ukrainian scientific and technical conference “Problems of infocommunications”. Poltava-Kyiv-Kharkiv-Minsk.
  5. Havrylenko, V.V., Ivanchenko, H.F., & Shevchenko, H.Ye. (2015). Theory of pattern recognition: Textbook for students of National Transport University majoring in “Computer Science”. Kyiv: NTU.
  6. Crane, M., & Lin, J. (2017). An exploration of serverless architectures for information retrieval. In Proceedings of the 3rd ACM international conference on the theory of information retrieval (ICTIR 2017) (pp. 241-244). Amsterdam.
  7. DeCandia, G., Hastorun, D., Jampani, M., Kakulapati, G., Lakshman, A., Pilchin, A., Sivasubramanian, S., Vosshall, P., & Vogels, W. (2007). Dynamo: Amazon’s highly available key-value store. In Proceedings of the 21st ACM symposium on operating systems principles (SOSP 2007) (pp. 205-220). Stevenson.
  8. Kim, Y. (2014). Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on empirical methods in natural language processing (EMNLP 2014) (pp. 1746-1751). Doha.
  9. Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. doi: 10.48550/arXiv.1301.3781.
  10. Olston, C., Fiedel, N., Gorovoy, K., Harmsen, J., Lao, L., Li, F., Rajashekhar, V., Ramesh, S., & Soyke, J. (2017). TensorFlow-Serving: Flexible, high-performance ML serving. doi: 10.48550/arXiv.1712.06139.
  11. Rao, J., He, H., & Lin, J. (2017). Experiments with convolutional neural network models for answer selection. In Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval (pp. 1217-1220). New York: ACM.
  12. Severyn, A., & Moschitti, A. (2015). Learning to rank short text pairs with convolutional deep neural networks. In Proceedings of the 38th annual international ACM SIGIR conference on research and development in information retrieval (SIGIR 2015) (pp. 373-382). Santiago.
  13. Sysoiev, I.K., Havrylenko, V.V., Shumeiko, O.A., Rudoman, N.V., & Donets, V.V. (2022). Prospects of the Python algorithmic language in mastering machine learning disciplines by students. Bulletin of the National Transport University. Series “Technical Sciences”. Scientific and Technical Collection, 3(53), 337-343. 
  14. Havrylenko, V.V., Sysoiev, I.K., & Liashko, A.V. (2023). Use of artificial neural networks for query complexity assessment. In Proceedings of the V international scientific and practical conference “Modern trends in the development of information systems and telecommunication technologies”. Kyiv: National University of Food Technologies.

https://doi.org/10.33744/0365-8171-2023-113.2-171-179