A method to improve the stability and accuracy of ANN- and SVM-based time series models for long-term groundwater level predictions.
Heesung YoonYunjung HyunKyoochul HaKang-Kun LeeGyoo-Bum KimPublished in: Comput. Geosci. (2016)
Keyphrases
- long term
- high accuracy
- computational cost
- support vector machine
- machine learning methods
- computational efficiency
- high precision
- significant improvement
- support vector machine svm
- highly accurate
- autoregressive
- statistical model
- accuracy rate
- similarity measure
- probabilistic model
- objective function
- classification accuracy
- active learning
- prior knowledge
- artificial neural networks
- statistical methods
- stability analysis
- linear model
- moving average
- neural nets
- recurrent neural networks
- correlation coefficient
- error rate
- parameter estimation
- relevance feedback