Incremental learning with online SVMs on LiDAR sensory data
This research provides an incremental solution for efficiently processing high-volume LiDAR data, which is crucial for reducing maintenance costs in the energy industry's pipeline systems.
This paper addresses the challenge of processing large volumes of LiDAR sensory data for pipeline transmission system maintenance by proposing an incremental learning approach using online Support Vector Machines (SVMs). The method processes each sample instantly and computes the kernel simultaneously, aiming to mitigate the computational burden associated with large datasets in traditional SVMs.
The pipelines transmission system is one of the growing aspects, which has existed for a long time in the energy industry. The cost of in-pipe exploration for maintaining service always draws lots of attention in this industry. Normally exploration methods (e.g. Magnetic flux leakage and eddy current) will establish the sensors stationary for each pipe milestone or carry sensors to travel inside the pipe. It makes the maintenance process very difficult due to the massive amount of sensors. One of the solutions is to implement machine learning techniques for the analysis of sensory data. Although SVMs can resolve this issue with kernel trick, the problem is that computing the kernel depends on the data size too. It is because the process can be exaggerated quickly if the number of support vectors becomes really large. Particularly LiDAR spins with an extremely rapid rate and the flow of input data might eventually lead to massive expansion. In our proposed approach, each sample is learned in an instant way and the supported kernel is computed simultaneously. In this research, incremental learning approach with online support vector machines (SVMs) is presented, which aims to deal with LiDAR sensory data only.