利用机器学习制定俄罗斯地区创新型工业发展战略

机器学习技术是分析大数据的有力工具，因此可以应用于俄罗斯各地区制定创新型工 业发展战略。为了比较预测质量的结果并选择最优方法，以无线电电子工业为例，我们应用了 k-近邻算法、“多层感知器”神经网络和自适应神经模糊推理系统（包括粒子群算法和多元自 适应回归样条法）。目标函数如下：1）创新产品的数量；2）先进生产技术的发展；3）平衡的 财务结果（信息化和通信）。该模型是在 2010 年至 2022 年期间俄罗斯 83 个地区的九项输入 指标和三项目标指标样本包的基础上进行训练的。为进一步验证训练后的模型，保留了 2023 年 的样本。结果发现，使用 k-近邻算法获得了最高质量的预测。在评估过程中发现，2023年预测 目标函数值在计划范围内的地区具有工业创新发展前景。评估仅在预测被认为质量最高的地区 进行，即平均绝对百分比误差小于 0.5 的地区，这些地区是克拉斯诺达尔边疆区和彼尔姆边疆 区、下诺夫哥罗德州、斯维尔德洛夫斯克州、车里雅宾斯克州和新西伯利亚州。在对多元自适 应回归样条法（目标 3）、粒子群算法（目标 2）、多层感知器算法（目标 1）进行类似分析后 发现下诺夫哥罗德州和斯维尔德洛夫斯克州在无线电电子工业领域处于领先地位，这在一定程 度上证实了使用机器学习方法得出的结论。

1. Гринев С.А., Квинт В.Л. Формирование стратегических приоритетов промышленного развития РФ как инновационный фактор преодоления кризисных периодов. Экономика промышленности. 2023;16(3):275–283. https://doi.org/10.17073/2072-1633-2023-3-275-283

2. Яшин С.Н., Кошелев Е.В., Суханов Д.А. Эволюционное нейросетевое моделирование импортозамещения в радиоэлектронной промышленности регионов. Финансы и кредит. 2024;30(4):765–787. https://doi.org/10.24891/fc.30.4.765

3. Yoosefzadeh-Najafabadi M., Earl Hugh J., Tulpan D., Sulik J., Eskandari M. Application of machine learning algorithms in plant breeding: Predicting yield from hyperspectral reflectance in soybean. Frontiers in Plant Science. 2021;11:2169. https://doi.org/10.3389/fpls.2020.624273

4. Ramezanpour A., Beam A.L., Chen J.H., Mashaghi A. Statistical physics for medical diagnostics: Learning, inference, and optimization algorithms. Diagnostics. 2020;10(11):972. https://doi.org/10.3390/diagnostics10110972

5. Okolie J.A., Savage Sh., Ogbaga C.C., Gunes B. Assessing the potential of machine learning methods to study the removal of pharmaceuticals from wastewater using biochar or activated carbon. Total Environment Research Themes. 2022;1-2:100001. https://doi.org/10.1016/j.totert.2022.100001

6. Jaiswal A., Babu A.R., Zadeh M.Z., Banerjee D., Makedon F. A survey on contrastive self-supervised learning. Technologies. 2021;9(1):2. https://doi.org/10.3390/technologies9010002

7. Fleer S., Moringen A., Klatzky R.L., Ritter H. Correction: Learning efficient haptic shape exploration with a rigid tactile sensor array. PLoS One. 2020;15(2):e0230054 https://doi.org/10.1371/journal.pone.0230054

8. Piryonesi S.M., El-Diraby T.E. Role of data analytics in infrastructure asset management: Overcoming data size and quality problems. Journal of Transportation Engineering, Part B: Pavements. 2020;146(2):04020022.

9. Uddin S., Haque I., Lu H., Moni M.A., Gide E. Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction. Scientific Reports. 2022;12:6256. https://doi.org/10.1038/s41598-022-10358-x

10. Halder R.K., Uddin M.N., Uddin M.A., Aryal S., Khraisat A. Enhancing K-nearest neighbor algorithm: A comprehensive review and performance analysis of modifications. Journal of Big Data. 2024;11:113. https://doi.org/10.1186/s40537-024-00973-y

11. Xiong L., Yao Y. Study on an adaptive thermal comfort model with K-nearest-neighbors (KNN) algorithm. Building and Environment. 2021;202:108026. https://doi.org/10.1016/j.buildenv.2021.108026

12. Patchanok S., Korn S. Random kernel k-nearest neighbors regression. Frontiers in Big Data. 2024;7:1402384. https://doi.org/10.3389/fdata.2024.1402384

13. Zardini E., Blanzieri E., Pastorello D. A quantum k-nearest neighbors algorithm based on the Eucli dean distance estimation. Quantum Machine Intelligence. 2024;6:23. https://doi.org/10.1007/s42484-024-00155-2

14. Boateng E., Otoo J., Abaye D. Basic tenets of classification algorithms K-nearest-neighbor, support vector machine, random forest and neural network: A review. Journal of Data Analysis and Information Processing. 2020;08(04):341–357. https://doi.org/10.4236/jdaip.2020.84020

15. Isabona J., Imoize A.L., Ojo S., Karunwi O., Kim Y., Lee C.-C., Li C.-T. Development of a multilayer perceptron neural network for optimal predictive mo deling in urban microcellular radio environments. Applied Sciences. 2022;12(11):5713. https://doi.org/10.3390/app12115713

16. Rashedi K.A., Ismail M.T., Al Wadi S., Serroukh A., Alshammari T.S., Jaber J.J. Multi-layer perceptronbased classification with application to outlier detection in Saudi Arabia stock returns. Journal of Risk and Financial Management. 2024;17(2):69. https://doi.org/10.3390/jrfm17020069

17. Sagias V.D., Zacharia P., Tempeloudis A., Stergiou C. Adaptive neuro-fuzzy inference system-based predictive modeling of mechanical properties in additive manufacturing. Machines. 2024;12(8):523. https://doi.org/10.3390/machines12080523

18. Putra V.G.V., Mohamad J.N. Adaptive neuro-fuzzy inference systems (ANFIS) and artificial neural networks (ANNs) for optimizing electrospun PVA/ TiO2 fiber diameter. The Journal of The Textile Institute. 2022;114(10):1898–1908. https://doi.org/10.1080/00405000.2022.2150954

19. Qiao J., Wang G., Yang Z., Luo X., Chen J., Li K., Liu P. A hybrid particle swarm optimization algorithm for solving engineering problem. Scientific Reports. 2024;14:8357. https://doi.org/10.1038/s41598-024-59034-2

20. Tang K., Meng C. Particle swarm optimization algorithm using velocity pausing and adaptive strategy. Symmetry. 2024;16(6):61. https://doi.org/10.3390/sym16060661

21. Adnan R.M., Liang Z., Heddam S., Zounemat-Kermani M., Kisi O., Li B. Least square support vector machine and multivariate adaptive regression splines for streamflow prediction in mountainous basin using hydro-meteorological data as inputs. Journal of Hydrology. 2020;586:124371. https://doi.org/10.1016/j.jhydrol.2019.124371

22. Hwaidi A., Badr A., Henedy S., Ostrowski K., Imran H. Application of multivariate adaptive regression splines (MARS) approach in prediction of compressive strength of eco-friendly concrete. Case Studies in Construction Materials. 2022;17:e01262. https://doi.org/10.1016/j.cscm.2022.e01262