Research on Agricultural Machinery Development and Grain Yield in Heilongjiang Province Based on Differential Privacy

Authors

  • Jinhua Ye College of Science, Heilongjiang Bayi Agricultural University, Daqing, Heilongjiang, 163319, China
  • Suipeng Hou College of Science, Heilongjiang Bayi Agricultural University, Daqing, Heilongjiang, 163319, China
  • Yuhan Sun College of Science, Heilongjiang Bayi Agricultural University, Daqing, Heilongjiang, 163319, China

DOI:

https://doi.org/10.54097/70ehpj50

Keywords:

Differential Privacy, Privacy Budget, Data Utility, Agricultural Machinery Development, Grain Yield

Abstract

With the continuous acceleration of the pace of agricultural informatization construction, the need for quantitative analysis of the improvement of agricultural machinery equipment level and the enhancement of grain production capacity is becoming increasingly urgent. Based on the relevant index data such as grain output, total power of agricultural machinery, the number of large and medium-sized agricultural tractors, and the number of combine harvesters in the Heilongjiang Statistical Yearbook from 2004 to 2024, this paper incorporates Laplacian noise of different scales to achieve differential privacy protection and selects a gradient privacy budget  ranging from 0.1 to 5.0. Explore the impact of different privacy budgets on the statistical analysis effect of agricultural production data from multiple perspectives. Research shows that in terms of the statistical data of agricultural machinery development and grain output in Heilongjiang Province, differential privacy has a distinct critical threshold: when , information such as agricultural machinery and grain output was seriously distorted, and no meaningful statistical conclusions could be drawn regarding the relationship between agricultural machinery development and grain output. When , it was a turning point when data availability began to improve, and to a certain extent, it could reflect the main connection between the development of agricultural machinery and grain output. When , it is possible to obtain as accurate research results as possible on the impact of agricultural machinery development on grain production while ensuring privacy and security, achieving the best balance between data availability and privacy protection.

Downloads

Download data is not yet available.

References

[1] Nkurunziza, P., & Umehara, D. (2026). Attention–based HAPS–to–ground nodes optimization for differential privacy towards secure semantic communications. Neural Computing and Applications, 38(5), 1–22.

[2] Roy, A., & Mahanta, L. B. (2026). Chaos-based noise mechanisms for enhanced differential privacy in deep learning. Applied Soft Computing, 196, 1–20.

[3] Alghamdi, A. D. (2026). An adaptive differential privacy framework for clinical LLMs with context-aware noise calibration, hierarchical budgeting, and real-time auditing. Scientific Reports, 1–35.

[4] Song, X., Wang, F., & Han, T. (2026). Research on differential privacy clustering algorithm based on dynamic adaptive sensitivity. Network Security Technology and Application, 3, 44–47.

[5] Jiang, Y. Y., Jiang, Z. F., et al. (2026). Edge computing method for semi-asynchronous federated learning based on differential privacy. Software Engineering, 29(3), 43–48.

[6] Wang, B., Chen, Y., et al. (2026). Privacy-preserving robust aggregation federated learning scheme. Computer Engineering and Design, 47(3), 743–751.

[7] Guo, Y. X., Xu, X. W., & Tan, Q. (2026). Research on communication data privacy protection and encrypted transmission technology in the era of big data. China Broadband, 22(5), 71–73.

[8] Zhang, X. F., & Jiang, H. (2026). Gradient privacy protection and secure aggregation method in deep learning model training. China New Technologies and Products, 4, 146–148.

[9] Xu, F. G., Li, L., & Chen, T. (2026). HADPK-means++ clustering algorithm for differential privacy. Fujian Computer, 42(2), 7–15.

[10] Li, L., Zhao, L. L., et al. (2026). Differential privacy text synthesis based on gradient direction screening. Journal of Information Security Research, 12(3), 220–227.

[11] Chen, Z., Lai, H. H., et al. (2025). Research on desensitization and cloud migration scheme for expressway toll data. China ITS Journal, 11, 62–66.

[12] Feng, J. Y., & Li, G. (2025). Design and implementation of internet of vehicles data privacy governance system. Information Recording Materials, 26(11), 188–190.

Downloads

Published

01-07-2026

Issue

Section

Articles

How to Cite

Ye, J., Hou, S., & Sun, Y. (2026). Research on Agricultural Machinery Development and Grain Yield in Heilongjiang Province Based on Differential Privacy. Frontiers in Computing and Intelligent Systems, 17(1), 49-56. https://doi.org/10.54097/70ehpj50