Decision tree model

About: Decision tree model is a research topic. Over the lifetime, 2256 publications have been published within this topic receiving 38142 citations.

Bayesian molecular dating as a “doubly intractable” problem

Abstract: This study focuses on a conceptual issue with Bayesian inference of divergence times using Markov chain Monte Carlo. The influence of fossil data on the probabilistic distribution of trees is the crux of the matter considered here. More specifically, among all the phylogenies that a tree model (e.g., the birth-death process) generates, only a fraction of them “agree” with the fossil data at hands. Bayesian inference of divergence times using Markov Chain Monte Carlo requires taking this fraction into account. Yet, doing so is challenging and most Bayesian samplers have simply overlooked this hurdle so far, thereby providing approximate estimates of divergence times and tree process parameters. A generic solution to this issue is presented here. This solution relies on an original technique, the so-called exchange algorithm, dedicated to drawing samples from “doubly intractable” distributions. A small example illustrates the problem of interest and the impact of the approximation aforementioned on tree parameter estimates. The analysis of land plant sequences and multiple fossils further illustrates the importance of proper mathematical handling of calibration data in order to derive accurate estimates of node age.

Cost Complexity Pruning of Ensemble Classifiers

Abstract: In this paper we study methods that combine multiple clas- sification models learned over separate data sets in a dis- tributed database setting. Numerous studies posit that such approaches provide the means to efficiently scale learning to large datasets, while also boosting the accuracy of individ- ual classifiers. These gains, however, come at the expense of an increased demand for run-time system resources. The fi- nal ensemble meta-classifier may consist of a large collection of base classifiers that require increased memory resources while also slowing down classification throughput. Here, we present a technique for measuring the tradeoff between pre- dictive performance and available run time system resources and we describe an algorithm for pruning (i.e. discarding a subset of the available base classifiers) the ensemble meta- classifier as a means to reduce its size while preserving its accuracy. The algorithm is independent of the method used initially when computing the meta-classifier. It is based on decision tree pruning methods and relies on the map- ping of an arbitrary ensemble meta-classifier to a decision tree model. Through an extensive empirical study on meta- classifiers computed over two real data sets, we illustrate our pruning algorithm to be a robust approach to discarding classification models without degrading the overall predic- tive performance of an ensemble computed over those that remain after pruning.

Using Restricted Additive Tree Model for Identifying the Large-Scale Gene Regulatory Networks

Abstract: S-system model has been proposed to identify gene regulatory network in the past years. However, due to the computation complexity, this model is only used for reconstruction of small-scale networks. In this paper, the restricted additive tree model (RAT) is proposed to infer the large-scale gene regulatory networks. In the method, restricted additive tree model is used to encode the S-system model, and the hybrid evolution approach is used to optimize the structure and parameters of restricted additive tree. The large-scale gene regulatory network containing 30 genes is used to test the performance of our method. The results reveal that our method could identify the large-scale gene regulatory network correctly.

An Empirical Analysis of Classifiers Using Ensemble Techniques

Abstract: Ensemble methods are algorithms that combine various models together to give higher accuracy than individual models. The ensemble methods used here are majority voting, XGBoost, and random forest. Several decision trees are combined using voting classifier, Random forest tree, and XGBoost. These are considered as the best universal models which are used here to compare the accuracies with other models. The datasets are being split randomly 9, 18, and 27 times, respectively. The decision tree model is applied and later combined with voting classifier. The descriptions of the methods are followed by an extensive empirical study over 10 publicly available datasets. An ensemble model with five classifiers is also implemented that give us the accuracy of the model, and later all the accuracies are compared. Finally, a comparison has been done with XGBoost and Random forest classifiers, which shows the effectiveness of the used ensemble methods for classification.

Generating Combinatorial Test Suite with Solution Space Tree for Configurations Testing of Sensors Networks

Abstract: There are many results about generating pair-wise covering arrays with strength τ=2 have been reported, but fewer results are published for high-strength covering arrays with a higher-strength τ>2. In configuration testing of sensor networks, high-strength covering array is required to construct combinatorial test cases. To generate combinatorial test suite with higher-strength, a backtracking algorithms, which is based on solution space tree, is proposed in this paper by extending an existing pair-wise combinatorial test suite generation algorithm. In solution space tree model, each test case is represented as a path from the root to a leaf node in the tree. And proposed algorithm generates test cases one by one, by backtracking depth-first searching in the solution space tree. Finally, to assess the efficiency of proposed algorithm, computational comparison with other published methods is reported. Copyright © 2013 IFSA.