Related Experiment Video
Updated: Apr 27, 2026
12:45
Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images
Published on: August 31, 2022
2.9K
An improved clustering algorithm of tunnel monitoring data for cloud computing
Luo Zhong1, KunHao Tang2, Lin Li3
1Department of Computer Science and Technology, Wuhan University of Technology, Wuhan 4300702, China.
Thescientificworldjournal
|July 2, 2014
Summary
An improved parallel clustering algorithm addresses complex urban tunnel data. This k-means-based approach uses MapReduce in cloud computing for efficient mass data processing and anomaly detection.
Area of Science:
- Civil Engineering
- Computer Science
- Data Science
Background:
- Urban construction growth leads to increasing numbers of urban tunnels.
- The complex data generated by tunnels challenges traditional clustering algorithms.
- Existing methods struggle to efficiently process and analyze large-scale tunnel data.
Purpose of the Study:
- To propose an improved parallel clustering algorithm for handling mass urban tunnel data.
- To enhance the efficiency of data processing in tunnel infrastructure management.
- To develop a method for identifying and cleaning abnormal data within tunnel datasets.
Main Methods:
- An improved parallel clustering algorithm based on k-means is developed.
- The algorithm leverages MapReduce within a cloud computing framework.
- It incorporates computation of average dissimilarity degree for anomaly detection.
Main Results:
- The proposed algorithm effectively handles mass data from urban tunnels.
- It demonstrates improved efficiency compared to traditional clustering methods.
- The algorithm successfully identifies and cleans abnormal data points.
Conclusions:
- The improved parallel k-means clustering algorithm is suitable for mass urban tunnel data.
- Cloud computing and MapReduce enhance the scalability and efficiency of tunnel data analysis.
- The method provides a robust solution for data cleaning and anomaly detection in tunnel engineering.
