Improving SVM-Linear Predictions Using CART for Example Selection

Moreira, João Mendes; Jorge, Alípio Mário; Soares, Carlos; Sousa, Jorge Freire de

doi:10.1007/11875604_70

Cited by 9 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As previously mentioned, the leaf node approach is not problem dependent and, consequently, there is an open question: is the leaf node approach promising in other domains? The answer to this question is given in [38]. The leaf node approach is tested in eleven regression data sets [49] just for SVM -linear.…”

Section: Results On Example Selectionmentioning

confidence: 99%

Comparing state-of-the-art regression methods for long term travel time prediction

Mendes-Moreira

Jorge

Sousa

et al. 2012

IDA

Self Cite

View full text Add to dashboard Cite

Long-term travel time prediction (TTP) can be an important planning tool for both freight transport and public transport companies. In both cases it is expected that the use of long-term TTP can improve the quality of the planned services by reducing the error between the actual and the planned travel times. However, for reasons that we try to stretch out along this paper, long-term TTP is almost not mentioned in the scientific literature. In this paper we discuss the relevance of this study and compare three non-parametric state-of-the-art regression methods: Projection Pursuit Regression (PPR), Support Vector Machine (SVM) and Random Forests (RF). For each one of these methods we study the best combination of input parameters. We also study the impact of different methods for the pre-processing tasks (feature selection, example selection and domain values definition) in the accuracy of those algorithms. We use bus travel time's data from a bus dispatch system. From an off-the-shelf point-of-view, our experiments show that RF is the most promising approach from the three we have tested. However, it is possible to obtain more accurate results using PPR but with extra pre-processing work, namely on example selection and domain values definition.

show abstract

Section: Results On Example Selectionmentioning

confidence: 99%

Comparing state-of-the-art regression methods for long term travel time prediction

Mendes-Moreira

Jorge

Sousa

et al. 2012

IDA

Self Cite

View full text Add to dashboard Cite

show abstract

“…) comprise the pair of input and output vectors, w is the weight factor, b is the threshold value, C is the penalty parameter, kernel function Φ is used to map input samples to higher space, ε is the epsilon parameter, and the upper and lower training errors are i ξ and i ξ * , respectively. For the kernel function, there are three typical kernel functions which are RBF, polynomial function and linear function [22][23][24]. These kernel functions are used to map nonlinear between the input and feature space.…”

Section: Support Vector Regressionmentioning

confidence: 99%

A hybrid PSO-SVM-based method for predicting the friction coefficient between aircraft tire and coating

Zhan¹,

Li²

2016

Meas. Sci. Technol.

View full text Add to dashboard Cite

A hybrid PSO-SVM-based model is proposed to predict the friction coefficient between aircraft tire and coating. The presented hybrid model combines a support vector machine (SVM) with particle swarm optimization (PSO) technique. SVM has been adopted to solve regression problems successfully. Its regression accuracy is greatly related to optimizing parameters such as the regularization constant , the parameter gamma corresponding to RBF kernel and the epsilon parameter in the SVM training procedure. However, the friction coefficient which is predicted based on SVM has yet to be explored between aircraft tire and coating. The experiment reveals that drop height and tire rotational speed are the factors affecting friction coefficient. Bearing in mind, the friction coefficient can been predicted using the hybrid PSO-SVM-based model by the measured friction coefficient between aircraft tire and coating. To compare regression accuracy, a grid search (GS) method and a genetic algorithm (GA) are used to optimize the relevant parameters (, and ), respectively. The regression accuracy could be reflected by the coefficient of determination (). The result shows that the hybrid PSO-RBF-SVM-based model has better accuracy compared with the GS-RBF-SVM- and GA-RBF-SVM-based models. The agreement of this model (PSO-RBF-SVM) with experiment data confirms its good performance.

show abstract

“…Some of the first research in this area used neural networks to predict the Tokyo stock market (Mizuno, Kosaka, Yajima, Komoda, 1998;Kimoto, Asakawa, Yoda, Takeoka, 1990). Some other similar studies have used the Bayes classifier (Pop, 2006;Shin, Kil, 1998;Tsaih, Hsu, Lai, 1998;) and support vector machines (Ince, Trafalis, 2007;Moreira, Jorge, Soares, Sousa, 2006). Also, many studies compare the performance of different methods such as neural networks, support vector machines, k-nearest neighbours, naïve Bayes classifier, genetic algorithms, decision trees etc.…”

Section: Introductionmentioning

confidence: 99%

Comparing classification algorithms for prediction on CROBEX data

Jerić

2020

Croatian Review of Economic, Business and Social Statistics

View full text Add to dashboard Cite

The main objective of this analysis is to evaluate and compare the various classification algorithms for the automatic identification of favourable days for intraday trading using the Croatian stock index CROBEX data. Intra-day trading refers to the acquisition and sale of financial instruments on the same trading day. If the increase between the opening price and the closing price of the same day is substantial enough to earn a profit by purchasing at the opening price and selling at the closing price, the day is considered to be favourable for intra-day trading. The goal is to discover relation between selected financial indicators on a given day and the market situation on the following day i.e. to determine whether a day is favourable for day trading or not. The problem is modelled as a binary classification problem. The idea is to test different algorithms and to give greater attention to those that are more rarely used than traditional statistical methods. Thus, the following algorithms are used: neural network, support vector machine, random forest, as well as k-nearest neighbours and naïve Bayes classifier as classifiers that are more common. The work is an extension of authors’ previous work in which the algorithms are compared on resamples resulting from tuning the algorithms, while here, each derived model is used to make predictions on new data. The results should add to the increasing corpus of stock market prediction research efforts and try to fill some gaps in this field of research for the Croatian market, in particular by using machine learning algorithms.

show abstract

Improving SVM-Linear Predictions Using CART for Example Selection

Cited by 9 publications

References 8 publications

Comparing state-of-the-art regression methods for long term travel time prediction

Comparing state-of-the-art regression methods for long term travel time prediction

A hybrid PSO-SVM-based method for predicting the friction coefficient between aircraft tire and coating

Comparing classification algorithms for prediction on CROBEX data

Contact Info

Product

Resources

About