Development of Metaheuristic Optimization-based Machine Learning System for Solving Multi-Output Engineering Problems
碩士 === 國立臺灣科技大學 === 營建工程系 === 106 === This work develops a novel metaheuristic optimization-based least squares support vector regression (LSSVR) model with a multi-output (MO) algorithm for assessing natural hazards. The MO algorithm is more efficient than the single output algorithm because the re...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2018
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/zmv42d |
| Summary: | 碩士 === 國立臺灣科技大學 === 營建工程系 === 106 === This work develops a novel metaheuristic optimization-based least squares support vector regression (LSSVR) model with a multi-output (MO) algorithm for assessing natural hazards. The MO algorithm is more efficient than the single output algorithm because the relations among outputs can be estimated simultaneously by the proposed prediction model. Furthermore, the hyper-parameters in MOLSSVR are optimized using an accelerated particle swarm optimization (A-PSO) algorithm to generate the best predictions and the fastest convergence. The A-PSO algorithm is then validated by solving benchmark functions. The performance of PSO-MOLSSVR is verified by comparing its performance with those of hybrid and single models that yield from standard multi-input single-output algorithm. A graphical user interface was designed as a stand-alone application to provide a user-friendly system for executing advanced data mining techniques. For real-world engineering cases, PSO-MOLSSVR achieved an error rate that was up to 63.55% better than those achieved using prediction models that are proposed in the single output scheme. The system much more quickly and efficiently identified the optimal parameters and effectively solved multiple-output problems.
|
|---|