Review on Agricultural Big Data and Privacy Computing Technology
Abstract
In recent years, with the rapid development of sensors, remote sensing, and Internet technologies, agricultural big data has shown explosive growth. The traditional centralized processing methods integrated multi-party agricultural data for crop growth evaluation and yield prediction. However, these methods face great challenges with privacy leakage and low sharing efficiency in the process of data transmission. Moreover, multi-party data also faces data security issues such as data copyright protection. To address the above problems, privacy computing, an emerging data security technology, provides a feasible path to achieve multi-party collaborative analysis without disclosing the original data. Firstly, the landscape of agricultural big data was comprehensively reviewed from data acquisition, preprocessing, storage, and analysis to its key applications in precision farming, yield forecasting, pest monitoring, supply chain traceability, and agricultural finance. Then the principles and applicable scenarios of mainstream privacy computing technologies such as homomorphic encryption, secure multi-party computation, differential privacy, and federated learning were systematically summarized. To emphatically analyze the applications of privacy computing technology in the agricultural field, the advanced research of privacy computing was outlined in agricultural data transmission, pest and disease detection, crop monitoring, and yield prediction. Meanwhile, existing key challenges of the current privacy computing technology were summarized, including communication cost, computational complexity, heterogeneous adaptability, evaluation mechanism, and the trade-off between privacy protection and model performance. Finally, future directions of privacy computing technologies on communication compression, lightweight encryption, multimodal modeling, construction of evaluation systems, and privacy-performance optimization were explored to facilitate the intelligent development of agriculture.
Keywords: agricultural big data, smart agriculture, privacy computing, data security
Download Full Text:
PDFReferences
JANG Hou, YANG Yaping, SUN Jiulin. Research and application of big data in agriculture[ J ]. Journal of Agricultural Big Data, 2019, 1(1) ; 5 —10. (in Chinese)
GU Shenghao, WEN Weiliang, LU Xianju, et al. Smart crop cultivation; a new agricultural science toward deep integration of information, agronomy and machinery [ J ]. Journal of Agriculture, 2023, 13(2) : 67 -76. (in Chinese)
KAMILARIS A, KARTAKOULLIS A, PRENAFETA-BOLDU F X. A review on the practice of big data analysis in agriculture [J] . Computers and Electronics in Agriculture, 2017, 143; 23 -37.
COBLE К H, MISHRA A K, FERRELL S, et al. Big data in agriculture; a challenge for the future [j]. Applied Economic Perspectives and Policy, 2018, 40( 1 ) ; 79 -96.
OSINGA S A, PAUDEL D, MOUZAKITIS S A, et al. Big data in agriculture; between opportunity and solution [ J]. Agricultural Systems, 2022, 195; 103298.
YUAN Yanwei, XU Ling, JI Fuhua, et al. Experimental optimization of big data cleaning method for agricultural machinery J . Transactions of the Chinese Society for Agricultural Machinery, 2021 , 52(6) ;35 -42. ( in Chinese)
LIU Zhengyu. Data cleaning technology and application based on big data J]. Digital Technology and Application, 2019, 37(4) ;92 -94. (in Chinese)
WANG Zhandi. Research on data cleaning and preprocessing technology in big data environment [J]. Digital Insige, 2024(9) ; 73 -75. (in Chinese)
CHEN Kuavue, WANG Baovun. Fire image recognition based on improved ResnetlS network [J ]. Journal of Henan Normal University ( Natural Science Edition) , 2024, 52(4) ; 101 - 110. (in Chinese)
LI Guangsheng, ZHENG Jianli, CHE Xiajing. Timestamp alignment method of multi-dimensional time series sequence to reduce data sparsity [ J ]. Intelligent Computer and Applications, 2022, 12(4) : 135 - 139. ( in Chinese)
SIDDIQA A, KARIM A, GANI A. Big data storage technologies; a survey [ J ]. Frontiers of Information Technology & Electronic Engineering, 2017, 18; 1040 - 1070.
GUAN Y, MA Z, LI L. HDFS optimization strategy based on hierarchical storage of hot and cold data [J]. Procedia CIRP, 2019, 83: 415 -418.
ZHANG Jianho, XIA Dengcheng, ZHAO Jiaao, et al. Storage strategy of raster data under the distributed computing environment [J ]. Journal of National University of Defense Technology, 2017, 39(6) : 51 -58. (in Chinese)
HANNAN S A. An overview on big data and hadoop[ J ] . International Journal of Computer Applications, 2016, 154 ( 10) : 29 -35.
CHEBOTKO A, KASHLEV A, LU S. A big data modeling methodology for Apache Cassandra [С ]//2015 IEEE International Congress on Big Data. IEEE, 2015: 238 -245.
SHEN Zhihong, ZHAO Zihao, WANG Huajin, et al. PandaDB; intelligent management system for heterogeneous data [ J ] . Journal of Software, 2021 , 32(3) :763 -780. (in Chinese)
LI Yuepeng, WEN Liangming, LI Jianhui. Framework for heterogeneous data unified access based on language translating [J ] . Computer Systems & Applications, 2021 , 30(9) :53 —61. (in Chinese)
MAKRIS A, TSERPES K, SPILIOPOULOS G, et al. MongoDB Vs PostgreSQL: a comparative study on performance aspects [J] . Geolnformatica, 2021 , 25 ; 243 - 268.
MA Ze. Discussion on object storage service to spatial unstructured data storage—to Ali Cloud OSS as an example[J]. Jiangxi Science, 2018, 36(2) :347 -352. (in Chinese)
AIT ISSAD H, AOUDJIT R, RODRIGUES J J P C. A comprehensive review of data mining techniques in smart agriculture [J] . Engineering in Agriculture, Environment and Food, 2019, 12(4): 511 -525.
XU Chang, DING Junqi, ZHAO Dantong, et al. Tomato disease diagnosis method based on LightGBM and prescription data [J ]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(9) ;286 -294. (in Chinese)
Refbacks
- There are currently no refbacks.
