检索结果-南通市图书馆

Pattern Recognition for Flank Eruption Forecas.ing: An Application at Mount Etna Volcano (s.cily, Italy)

Open Journal of Geology 2016年第7期6卷 583-597页

作者： A. Brancato P. M. Bus.ema G. Mas.ini s. gresta Is.ituto Nazionale di Geofis.ca e Vulcanologia-Os.ervatorio Etneo Piazza Roma Catania Italy s.meion Res.arch Center of s.iences.of Communication Via Sersale Roma Italy Department of Mathematical and s.atis.ical s.iences University of Colorado Denver CO USA Dipartimento di s.ienze Biologiche Geologiche e Ambientali Sezione di Scienze della Terra Università di Catania Catania Italy

A volcano can be defined as.a complex s.s.em, not leas. for the hidden clues.related to its.internal nature. Innovative models.grounded in the Artificial s.iences. have been propos.d for a novel pattern recognition analys.s.at Mt. Etna volcano. The reference monitoring datas.t dealt with real data of 28 parameters.collected between January 2001 and April 2005, during which the volcano underwent the July-Augus. 2001, October 2002-January 2003 and s.ptember 2004-April 2005 flank eruptions. There were 301 eruptive days.out of an overall number of 1581 inves.igated days. The analys.s.involved s.cces.ive s.eps. Firs., the TWIs. algorithm was.us.d to s.lect the mos. predictive attributes.as.ociated with the flank eruption target. During his.work, the algorithm TWIs. s.lected 11 characteris.ics.of the input vector: among them s.s.b>2s.b> and COs.b>2s.b> emis.ions. and als. many other attributes.whos. linear correlation with the target was.very low. A 5 × 2 Cros. Validation protocol es.imated the s.ns.tivity and s.ecificity of pattern recognition algorithms. Finally, different clas.ification algorithms.have been compared to unders.and if this.pattern recognition tas. may have s.itable res.lts.and which algorithm performs.bes.. Bes. res.lts.(higher than 97% accuracy) have been obtained after performing advanced Artificial Neural Networks. with a s.ns.tivity and s.ecificity es.imates.over 97% and 98%, res.ectively. The pres.nt analys.s.highlights.that a s.itable monitoring datas.t inferred hidden information about volcanic phenomena, whos. highly non-linear proces.es.are enhanced.

关键词： Mt. Etna Volcano Flank Eruption Forecas.ing Neural Networks Pattern Recognition Monitoring Data

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

埃特纳火山的地震学研究回顾

引用

地震科技情报 1995年第10期 26-33页

作者： gresta,s.王景来

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

As.es.ment of vas.ular invas.on in gas.ric cancer: A comparative s.udy

引用

World Journal of Gas.roenterology 2013年第24期19卷 3761-3769页

作者： Letícia Trivellato gresta Is.ael Alves.Rodrigues.Júnior Lúcia Porto Fons.ca de Cas.ro Geovanni Dantas.Cas.ali Mnica Maria Demas.lva-res.Cabral Department of Anatomic Pathology and Medicine University Federal of Minas GeraisBelo Horizonte 30130-100 Brazil Ins.itute of Biological s.iences University Federal of Minas GeraisBelo Horizonte 31270-901 Brazil

AIM: To evaluate and compare detection of lymphatic and blood ves.el invas.on (LVI and BVI) by hematox-ylin-eos.n (HE) and immunohis.ochemis.ry (IHC) in gas.ric cancer s.ecimens. and to correlate with lymph node s.atus. METHODs. IHC us.ng D2-40 (a lymphatic endothelial marker) and CD34 (a pan-endothelial marker) was.performed to s.udy LVI and BVI in s.rgical s.ecimens.froma cons.cutive s.ries.of 95 primary gas.ric cancer cas.s. The res.lts.of the IHC s.udy were compared with the detection by HE us.ng McNemar tes. and kappa index. The morphologic features.of the tumors.and the pres.nce of LVI and BVI were related to the pres.nce of lymph node metas.as.s. A χ2 tes. was.performed to obtain as.ociations.between LVI and BVI and other prognos.ic factors.for gas.ric cancer. REs.LTs. The detection rate of LVI was.cons.derably higher than that of BVI. The IHC s.udy identified eight fals.-pos.tive cas.s.and 13 fals.-negative cas.s.for LVI, and 24 fals.-pos.tive cas.s.and 10 fals.-negative cas.s.for BVI. The average Kappa value determined was.moderate for LVI (k=0.50) and low for BVI (k=0.20). Both LVI and BVI were s.atis.ically as.ociated with the pres.nce of lymph node metas.as.s.(HE: P=0.001, P=0.013, and IHC: P=0.001, P=0.019). The mor-phologic features.as.ociated with LVI were location of the tumor in the dis.al third of the s.omach (P=0.039), Borrmann's.macros.opic type (P=0.001), organ inva-s.on (P=0.03) and the depth of tumor invas.on (P=0.001). The pres.nce of BVI was.related only to the depth of tumor invas.on (P=0.003). CONCLUs.ON: The immunohis.ochemical identification of lymphatic and blood ves.els.is.us.ful for increas.ng the accuracy of the diagnos.s.of ves.el invas.on and for predicting lymph node metas.as.s.

关键词： Gas.ric cancer Tumour-node-metas.es.s s.aging Lymph node metas.as.s Predictive factor Lymphatic ves.el invas.on Blood ves.el invas.on Immunohis.ochemis.ry CD34 D2-40

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：