Automated annotation of functional imaging experiments via multi-label classification.
Automated annotation of functional imaging experiments via multi-label classification.
复制标题
DOI：
10.3389/fnins.2013.00240
复制
发表时间：
2013
影响因子：
4.3
通讯作者：
Turner JA
中科院分区：
文献类型：
--
作者：
Turner MD;Chakrabarti C;Jones TB;Xu JF;Fox PT;Luger GF;Laird AR;Turner JA
识别人类神经影像学论文中的实验方法对于将有意义的相似实验分组进行荟萃分析非常重要。目前，这只能由人类读者完成。我们提出了常见的机器学习（文本挖掘）方法应用于自动分类或标记这篇文献的问题的性能。标签术语来自认知范式本体论（CogPO），文本语料库是已发表的功能性神经成像论文的摘要，并且该方法使用人类专家的表现作为训练数据。我们的目标是复制专家的注释的多个标签，每个抽象识别实验刺激，认知范式，反应类型，和其他相关方面的实验。我们使用几种标准的机器学习方法：朴素贝叶斯（NB），k-最近邻和支持向量机（特别是SMO或顺序最小优化）。精确匹配性能范围从最差情况下的15%到最佳情况下的78%。NB方法结合二进制相关性变换表现很强，并且对过拟合具有鲁棒性。这组结果展示了使用现成的软件组件和很少或根本没有对原始文本进行预处理可以实现的效果。
Identifying the experimental methods in human neuroimaging papers is important for grouping meaningfully similar experiments for meta-analyses. Currently, this can only be done by human readers. We present the performance of common machine learning (text mining) methods applied to the problem of automatically classifying or labeling this literature. Labeling terms are from the Cognitive Paradigm Ontology (CogPO), the text corpora are abstracts of published functional neuroimaging papers, and the methods use the performance of a human expert as training data. We aim to replicate the expert's annotation of multiple labels per abstract identifying the experimental stimuli, cognitive paradigms, response types, and other relevant dimensions of the experiments. We use several standard machine learning methods: naive Bayes (NB), k-nearest neighbor, and support vector machines (specifically SMO or sequential minimal optimization). Exact match performance ranged from only 15% in the worst cases to 78% in the best cases. NB methods combined with binary relevance transformations performed strongly and were robust to overfitting. This collection of results demonstrates what can be achieved with off-the-shelf software components and little to no pre-processing of raw text.
登录
查看更多内容
影响因子：
3
作者：
Bada M;Eckert M;Evans D;Garcia K;Shipley K;Sitnikov D;Baumgartner WA Jr;Cohen KB;Verspoor K;Blake JA;Hunter LE
通讯作者：
Hunter LE
影响因子：
64.8
作者：
Howe, Doug;Costanzo, Maria;Fey, Petra;Gojobori, Takashi;Hannick, Linda;Hide, Winston;Hill, David P.;Kania, Renate;Schaeffer, Mary;St Pierre, Susan;Twigger, Simon;White, Owen;Rhee, Seung Yon
通讯作者：
Rhee, Seung Yon
影响因子：
4.8
作者：
Lancaster, JL;Laird, AR;Fox, PT
通讯作者：
Fox, PT
DOI：
10.1523/jneurosci.4004-09.2009
发表时间：
2009-11-18
期刊：
The Journal of neuroscience : the official journal of the Society for Neuroscience
影响因子：
--
作者：
Laird AR;Eickhoff SB;Li K;Robin DA;Glahn DC;Fox PT
通讯作者：
Fox PT
影响因子：
3
作者：
Cohen KB;Johnson HL;Verspoor K;Roeder C;Hunter LE
通讯作者：
Hunter LE