Ensemble classifiers with improved overfitting

Pourtaheri, Zeinab Khatoun; Zahiri, Seyed Hamid

doi:10.1109/csiec.2016.7482130

Cited by 19 publications

(15 citation statements)

References 13 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The grid-search method is also used to determine parameters. Secondly, cross validation is used to prevent model overfitting [24]. The K-fold cross validation method is used in the study [25].…”

Section: Random Forest Methodsmentioning

confidence: 99%

Research on the Sustainable Development of Urban Housing Price Based on Transport Accessibility: A Case Study of Xi’an, China

Xue

et al. 2020

Sustainability

View full text Add to dashboard Cite

The development of a real estate economy is beneficial to urban stability. A method of real estate price prediction based on transport accessibility is proposed. The method adds bus accessibility and metro accessibility into the model, which has higher prediction accuracy than the traditional model. Firstly, bus accessibility and metro accessibility are calculated according to the space syntax theory. Then, four models, the traditional hedonic price model (HPM) with transport accessibility, the traditional hedonic price model without transport accessibility, the random forest (RF) model with transport accessibility, and the random forest model without transport accessibility, are introduced. Finally, the four models are compared and analyzed in terms of precision and importance of index contributions. Taking Xi 'an, China, as an example, the experimental results show that the transport accessibility calculated based on space syntax can accurately represent the transport convenience in an urban space structure. Furthermore, it has a great influence on the contribution of indexes in the model. With the introduction of bus accessibility and metro accessibility, the accuracy of the real estate price prediction model is greatly improved.

show abstract

Section: Random Forest Methodsmentioning

confidence: 99%

Research on the Sustainable Development of Urban Housing Price Based on Transport Accessibility: A Case Study of Xi’an, China

Xue

et al. 2020

Sustainability

View full text Add to dashboard Cite

show abstract

“…Overfitting is another problem caused when the model learns too much from the training dataset, which makes it unable to produce the desired performance and results on the test set. This is also solved if features are selected based on their relevance and contribution to improving the performance of the system [22], [27]. In this study, we used Ruzzo-Tompa for feature selection, which selects relevant features by following a series of steps that find the optimal subset of features and discard the irrelevant features.…”

Section: A Stacked Genetic Algorithm For Optimizationmentioning

confidence: 99%

“…Another problem is how to find the optimal configuration of the network so that the optimization problem can be resolved. When the model learns too much from the training data, it overfits because it picks even small details from the training data, and when applied to the testing data, the results are not adequate [6], [27]. On the other hand, when the model has not learned enough from the training data, it underfits, and as a result, both the training data and testing data show poor results.…”

Section: Introductionmentioning

confidence: 99%

An Optimally Configured and Improved Deep Belief Network (OCI-DBN) Approach for Heart Disease Prediction Based on Ruzzo–Tompa and Stacked Genetic Algorithm

et al. 2020

View full text Add to dashboard Cite

A rapid increase in heart disease has occurred in recent years, which might be the result of unhealthy food, mental stress, genetic issues, and a sedentary lifestyle. There are many advanced automated diagnosis systems for heart disease prediction proposed in recent studies, but most of them focus only on feature preprocessing, some focus on feature selection, and some only on improving the predictive accuracy. In this study, we focus on every aspect that may have an influence on the final performance of the system, i.e., to avoid overfitting and underfitting problems or to solve network configuration issues and optimization problems. We introduce an optimally configured and improved deep belief network named OCI-DBN to solve these problems and improve the performance of the system. We used the Ruzzo-Tompa approach to remove those features that are not contributing enough to improve system performance. To find an optimal network configuration, we proposed a stacked genetic algorithm that stacks two genetic algorithms to give an optimally configured DBN. An analysis of a RBM and DBN trained is performed to give an insight how the system works. Six metrics were used to evaluate the proposed method, including accuracy, sensitivity, specificity, precision, F1 score, and Matthew's correlation coefficient. The experimental results are compared with other state-of-the-art methods, and OCI-DBN shows a better performance. The validation results assure that the proposed method can provide reliable recommendations to heart disease patients by improving the accuracy of heart disease predictions by up to 94.61%.

show abstract

“…Overfitting is a circumstance where the neural network performs adequately on training data but deficient on generalization [52]. In other words, the network tends to learn the noise and irrelevant properties of training data which results in lower performance when tested with unseen data [53]. Cross-validation, early stopping and regularization are amongst the methods used in preventing overfitting [54].…”

Section: Stabilitymentioning

confidence: 99%

Rainfall-Runoff Model Based on ANN with LM, BR and PSO as Learning Algorithms

Romlay¹,

Rashid²,

Toha³

et al. 2019

IJRTE

View full text Add to dashboard Cite

Rainfall-runoff model requires comprehensive computation as its relation is a complex natural phenomenon. Various inter-related processes are involved with factors such as rainfall intensity, geomorphology, climatic and landscape are all affecting runoff response. In general there is no single rainfall-runoff model that can cater to all flood prediction system with varying topological area. Hence, there is a vital need to have custom-tailored prediction model with specific range of data, type of perimeter and antecedent hour of prediction to meet the necessity of the locality. In an attempt to model a reliable rainfall-runoff system for a flood-prone area in Malaysia, 3 different approach of Artificial Neural Networks (ANN) are modelled based on the data acquired from Sungai Pahang, Pekan. In this paper, the ANN rainfall-runoff models are trained by the Levenberg Marquardt (LM), Bayesian Regularization (BR) and Particle Swarm Optimization (PSO). The performances of the learning algorithms are compared and evaluated based on a 12-hour prediction model. The results demonstrate that LM produces the best model. It outperforms BR and PSO in terms of convergence rate, lowest mean square error (MSE) and optimum coefficeint of correlation. Furthermore, the LM approach are free from overfitting, which is a crucial concern in conventional ANN learning algorithm. Our case study takes the data of rainfall and runoff from the year 2012 to 2014. This is a case study in Pahang river basin, Pekan, Malaysia.

show abstract

Ensemble classifiers with improved overfitting

Cited by 19 publications

References 13 publications

Research on the Sustainable Development of Urban Housing Price Based on Transport Accessibility: A Case Study of Xi’an, China

Research on the Sustainable Development of Urban Housing Price Based on Transport Accessibility: A Case Study of Xi’an, China

An Optimally Configured and Improved Deep Belief Network (OCI-DBN) Approach for Heart Disease Prediction Based on Ruzzo–Tompa and Stacked Genetic Algorithm

Rainfall-Runoff Model Based on ANN with LM, BR and PSO as Learning Algorithms

Contact Info

Product

Resources

About