Uslab Published a Paper Recently in Elsevier Neurocomputing (USLab近期在Elsevier期刊Neurocomputing发表学术论文) [2017-02-16]

发布时间:2017-02-16
 
Coauthored with Prof. Nitesh Chawla @ University of Notre Dame, USA, a paper entitled ‘Automated Epileptic Seizure Detection Using Improved Correlation-based Feature Selection with Random Forest Classifier' has been published recently in Neurocomputing. Dr Yuan Zhang is the corresponding author. This paper can be accessed here.
 
Abstract: Analysis of electroencephalogram (EEG) signal is crucial due to its non-stationary characteristics, which could lead the way to proper detection method for the treatment of patients with neurological abnormalities, especially for epilepsy. The performance of EEG-based epileptic seizure detection relies largely on the quality of selected features from an EEG data that characterize seizure activity. This paper presents a novel analysis method for detecting epileptic seizure from EEG signal using Improved Correlation-based Feature Selection method (ICFS) with Random Forest classifier (RF). The analysis involves, first applying ICFS to select the most prominent features from the time domain, frequency domain, and entropy based features. An ensemble of Random Forest (RF) classifiers is then learned on the selected set of features. The experimental results demonstrate that the proposed method shows better performance compared to the conventional Correlation-based method and also outperforms some other state-of-the-art methods of epileptic seizure detection using the same benchmark EEG dataset.
 
 
  最近,USLab与美国University of Notre Dame的Nitesh Chawla教授合作,在Elsevier期刊Neurocomputing发表了论文“Automated Epileptic Seizure Detection Using Improved Correlation-based Feature Selection with Random Forest Classifier”。张远博士是该论文通讯作者,该论文提出了基于相关性特征选择的使用随机森林分类器的自动癫痫检测方法,全文可以在此处获取。
 
摘要:脑电图(EEG)信号由于它的非平稳特性而至关重要,它可能引领神经异常患者的正确检测方法,特别是癫痫的治疗方法。基于脑电图的癫痫发作检测的性能很大程度上依赖于从脑电图活动数据的特征来表征发作活动。本文提出了一种新的基于相关性的特征选择方法和随机森林算法检测癫痫发作的分析方法。分析中涉及首先应用ICFS选择最多来自时域、频域和熵的特征。然后,在选定的特征集上采用随机森林算法(RF)的集合。实验结果表明,与传统的方法相比,该方法具有更好的性能,并且优于使用相同的基准脑电图数据集进行癫痫发作检测的其他方法。