Although feature selection for large data has been intensively investigated in data mining, machine learning, and pattern recognition, the challenges are not just to invent new algorithms to handle noisy and uncertain large data in applications, but rather to link the multiple relevant feature sources, structured, or unstructured, to develop an effective feature reduction method. In this paper, we propose a multiple relevant feature ensemble selection (MRFES) algorithm based on multilayer co-evolutionary consensus MapReduce (MCCM). We construct an effective MCCM model to handle feature ensemble selection of large-scale datasets with multiple relevant feature sources, and explore the unified consistency aggregation between the local solutions and global dominance solutions achieved by the co-evolutionary memeplexes, which participate in the cooperative feature ensemble selection process. This model attempts to reach a mutual decision agreement among co-evolutionary memeplexes, which calls for the need for mechanisms to detect some noncooperative co-evolutionary behaviors and achieve better Nash equilibrium resolutions. Extensive experimental comparative studies substantiate the effectiveness of MRFES to solve large-scale dataset problems with the complex noise and multiple relevant feature sources on some well-known benchmark datasets. The algorithm can greatly facilitate the selection of relevant feature subsets coming from the original feature space with better accuracy, efficiency, and interpretability. Moreover, we apply MRFES to human cerebral cortex-based classification prediction. Such successful applications are expected to significantly scale up classification prediction for large-scale and complex brain data in terms of efficiency and feasibility.

中文翻译：

---

基于多层协同进化MapReduce的多相关特征集合选择

尽管在数据挖掘，机器学习和模式识别中已经对大数据的特征选择进行了深入研究，但挑战不仅在于发明新算法来处理应用程序中嘈杂和不确定的大数据，而且还在于链接多个相关特征源，结构化或非结构化，以开发有效的特征约简方法。在本文中，我们提出了一种基于多层共进化共识MapReduce（MCCM）的多重相关特征集合选择（MRFES）算法。我们构建了一个有效的MCCM模型，以处理具有多个相关特征源的大规模数据集的特征集合选择，并探索了通过共进化Memeplexes实现的局部解和全局支配解之间的统一一致性聚合，参与合作特征集合选择过程。该模型试图在共同进化的memeplex之间达成一个共同的决策共识，这就要求需要一种机制来检测某些非合作的共同进化行为并获得更好的纳什均衡分辨率。广泛的实验比较研究证实了MRFES在解决一些知名基准数据集上具有复杂噪声和多个相关特征源的大规模数据集问题方面的有效性。该算法可以极大地方便从原始特征空间中选择相关的特征子集，并且具有更好的准确性，效率和可解释性。此外，我们将MRFES应用于基于人类大脑皮层的分类预测。