RFID Data Analysis and Evaluation Based on Big Data and Data Clustering

Area of Science:

• Computer Science
• Data Science
• Signal Processing

Background:

• The proliferation of big data necessitates advanced analytical techniques.
• Radio-Frequency Identification (RFID) systems generate massive datasets requiring efficient processing.
• Existing clustering algorithms may not fully leverage the complexities of RFID data.

Purpose of the Study:

• To develop and evaluate a robust RFID data extraction technology.
• To propose an enhanced clustering algorithm for analyzing large-scale RFID data.
• To demonstrate the effectiveness of the proposed methods in reducing recognition errors.

Main Methods:

• Implementation of a joint Kalman filter fusion for RFID tag data extraction.
• Development of a novel KM-KL clustering algorithm integrating K-means advantages.
• Experimental validation of the proposed data extraction and clustering techniques.

Main Results:

• The joint Kalman filter fusion method achieved a recognition error rate as low as 2.7%.
• The improved KM-KL clustering algorithm demonstrated superior performance compared to traditional methods.
• Effective analysis and evaluation of RFID data were achieved using the proposed algorithms.

Conclusions:

• The proposed joint Kalman filter fusion technology significantly improves RFID data extraction accuracy.
• The enhanced KM-KL clustering algorithm offers a powerful tool for big data analysis in RFID systems.
• These advancements contribute to more reliable and efficient utilization of RFID data.