<abstract xmlns="http://www.w3.org/1999/xhtml">

With the rapid rise of e-commerce platforms, in view of the sharp increase in the amount of data in the logistics system, the timely update and processing of relevant logistics information data have assumed a particular relevance. In this paper, we fully draw on the excellent performance of radio frequency identification (RFID) technology and data mining technology, begin by using RFID technology to authenticate logistics commodities, move on to extracting relevant feature information and finally carry out a detailed comparison between k-nearest neighbour algorithm, support vector machine (SVM) algorithm, logistic regression (LR) algorithm and improved LR algorithm. The algorithm provides a solution method for asset information collection channel and data mining classification algorithm. It meets the needs of different customers, and provides a variety of working modes, which helps to improve the time and operation efficiency of data processing algorithms. The results show that the SVM algorithm only achieves 93.8% accuracy when iterating 50 times for the classification results of the classification samples containing the objective functions of <italic>x</italic>1 and <italic>x</italic>2. The improved LR algorithm stochastic gradient descent algorithm has a classification accuracy of 94.6% after 50 iterations. The RFID-based logistics big data asset evaluation and data mining research identification algorithm has obvious advantages, and the accuracy rate reaches 97.3%.
</abstract>

With the rapid rise of e-commerce platforms, in view of the sharp increase in the amount of data in the logistics system, the timely update and processing of relevant logistics information data have assumed a particular relevance. In this paper, we fully draw on the excellent performance of radio frequency identification (RFID) technology and data mining technology, begin by using RFID technology to authenticate logistics commodities, move on to extracting relevant feature information and finally carry out a detailed comparison between k-nearest neighbour algorithm, support vector machine (SVM) algorithm, logistic regression (LR) algorithm and improved LR algorithm. The algorithm provides a solution method for asset information collection channel and data mining classification algorithm. It meets the needs of different customers, and provides a variety of working modes, which helps to improve the time and operation efficiency of data processing algorithms. The results show that the SVM algorithm only achieves 93.8% accuracy when iterating 50 times for the classification results of the classification samples containing the objective functions of x1 and x2. The improved LR algorithm stochastic gradient descent algorithm has a classification accuracy of 94.6% after 50 iterations. The RFID-based logistics big data asset evaluation and data mining research identification algorithm has obvious advantages, and the accuracy rate reaches 97.3%.

RFID-based logistics big data asset evaluation and data mining research

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"RFID-based logistics big data asset evaluation and data mining research"}

With the rapid rise of e-commerce platforms, in view of the sharp increase in the amount of data in the logistics system, the timely update and processing of...

RFID-based logistics big data asset evaluation and data mining research

Published Online: Jan 02, 2024

Page range: 665 - 676

DOI: https://doi.org/10.2478/amns.2021.2.00236

Keywords
logistics big data, data mining, RFID, algorithm

© 2023 Yufeng Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

RFID-based logistics big data asset evaluation and data mining research

Published Online: Jan 02, 2024

Page range: 665 - 676

DOI: https://doi.org/10.2478/amns.2021.2.00236

Keywordslogistics big data, data mining, RFID, algorithm

© 2023 Yufeng Li et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Keywords
logistics big data, data mining, RFID, algorithm