基于机器学习算法的生态数据分析
Ecological Data Analysis Based on Machine Learning Algorithms
摘要:
分类是一种重要的有监督机器学习方法,是生态学研究中必不可少的挑战性课题。它提供了一种将数据集分类为共享共同模式的子集的方法。值得注意的是,有许多分类算法可供选择,每种算法都对数据和分类应该如何形成做出某些假设。本文应用决策树、随机森林、人工神经网络、支持向量机、线性判别分析、k-近邻、逻辑斯谛回归和朴素贝叶斯等八种机器学习分类算法对生态数据进行分类。本研究的目的是比较不同的机器学习分类算法在生态数据集。在此分析中,我们检查了算法之间的准确性测试。在我们的研究中,我们得出结论,线性判别分析和k-近邻是最好的方法,所有其他方法
英文摘要:
Classification is an important supervised machine learning method, which is necessary and challenging issue for ecological research. It offers a way to classify a dataset into subsets that share common patterns. Notably, there are many classification algorithms to choose from, each making certain assumptions about the data and about how classification should be formed. In this paper, we applied eight machine learning classification algorithms such as Decision Trees, Random Forest, Artificial Neural Network, Support Vector Machine, Linear Discriminant Analysis, k-nearest neighbors, Logistic Regression and Naive Bayes on ecological data. The goal of this study is to compare different machine learning classification algorithms in ecological dataset. In this analysis we have checked the accuracy test among the algorithms. In our study we conclude that Linear Discriminant Analysis and k-nearest neighbors are the best methods among all other methods
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。