检索结果-内蒙古大学图书馆

2010 IEEE International Conference on Information and Automation, ICIA 2010

作者： Jia, Di Yang, Jin-Zhu Zhang, Yi-Fei Key Laboratory of Medical Image Computing of Ministry of Educaion Northeast University ShenYang 110179 China

ISBN: (纸本)9781424457021

The paper presents a new efficient method for brain tissue extraction. Firstly, the speed of segmentation is enhanced through improving classical distance matrix. It can accelerate the distance function convergence faster, and the accuracy is not reduced simultaneously. Secondly, the uniqueness of classical result is changed through the improved method. The evolving lines will be stopped at the same level gray, so the primal fluid can be wiped off. White matter and gray matter are extracted more accurate. Finally, a dynamic condition for ending iteration is presented through comparing the interval frames. The improvement changes the flaw of setting evolving times to end iteration, so it can make the veracity and speed much better. The methods are generally applied to image 2D and 3D segmentation, and the results of experiment indicate that the improvements can make the brain tissue extraction more rapid and accurate, and will be very helpful for doctor to make a definite diagnosis. ©2010 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Towards large scale cross-media retrieval via modeling heterogeneous information and exploring an efficient indexing scheme

Towards large scale cross-media retrieval via modeling heter...

引用

1st International Conference on Computational Visual Media, CVM 2012

作者： Lu, Bo Wang, Guoren Yuan, Ye Key Laboratory of Medical Image Computing School of Information Science and Engineering Northeastern University China

ISBN: (纸本)9783642342622

With the rapid development of Internet and multimedia technology, cross-media retrieval is concerned to retrieve all the related media objects with multi-modality by submitting a query media object. In this paper, we propose a novel method which is dedicate to achieve effective and accurate cross-media retrieval. Firstly, a Multi-modality Semantic Relationship Graph (MSRG) is constructed by using the semantic correlation amongst the media objects with multi-modality. Secondly, all the media objects in MSRG are mapped onto an isomorphic semantic space. Further, an efficient indexing MK-tree based on heterogeneous data distribution is proposed to manage the media objects within the semantic space and improve the performance of cross-media retrieval. Extensive experiments on real large scale cross-media datasets indicate that our proposal dramatically improves the accuracy and efficiency of cross-media retrieval, outperforming the existing methods significantly. © 2012 Springer-Verlag.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel Registration Method of Brain PET images and Talairach Atlas 29

A Novel Registration Method of Brain PET Images and Talairac...

引用

第29届中国控制与决策会议

作者： Tan Wenjun Kang Ying Sun Xiaohan Guo Chan School of Computer Science and Engineering Northeastern University Key Laboratory of Medical Image Computing of Ministry of Education Northeastern University

ISBN: (纸本)9781509046584

In recent years,the PET as an important clinical examination imaging technology of radionuclide imaging has become the indispensable tool of for cancer and neurological diseases *** the defect of poor resolution and brain structural features are not clear on PET image,it is difficult to select the points accurately when brain PET image register for the brain *** CT image has good spatial resolution and high density *** a novel registration algorithm of PET and standard brain atlas is presented in this paper by transforming PET-CT-atlas multimodality image based on marking the feature points on the CT ***,the brain tissue,the minimum oriented bounding box and the mid-sagital plane are extracted from brain CT ***,the brain cortical landmarks is manually marked from CT images and transformed into PET images with mutual information matrix of PET-CT ***,the automatic registration of PET-Talairach atlas is realized with the spatial affine transformation matrix,which is calculated by using the brain cortical landmarks of PET image and Talairach *** experimental results show that the method of multi modality registration of PET-CT-T atlas greatly reduces the error of manual intervention,and is good accuracy and lower time complexity.

关键词： Talairach atlas PET image Multimodality Brain atlas Registration

来源：评论

学校读者我要写书评

暂无评论

Optimizing Empathetic Response by Generating and Integrating Emotion Feedback and Topic Discussion 28th

Optimizing Empathetic Response by Generating and Integrati...

引用

28th International Conference on Database Systems for Advanced Applications, DASFAA 2023

作者： Li, Jing Han, Donghong Feng, Shi Zhang, Yifei School of Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University Shenyang China

ISBN: (纸本)9783031306747

Expressing empathy is a trait in human daily conversation, in which people are willing to give responses containing appropriate emotions and topics on the basis of understanding the interlocutor’s situation. However, empathetic dialogue models trained by data-driven training method tend to generate general responses, which are usually monotonous and difficult to infuse emotions and topics concurrently. To solve this issue, we propose a novel model that generates two sub-responses, namely, emotion feedback and topic discussion, then integrates them to optimize empathetic responses. Specifically, in the sub-response generation stage, we introduce emotion lexicon and commonsense knowledge to make sub-responses focus on emotional words and topic-related words respectively, which drives the sub-responses to be contextually related from different perspectives. Afterward, we utilize cross attention to integrate the global information to optimize the final response. Our model is trained on the pre-trained language model BART. Experimental results show that our method can generate responses involving emotion and topic well, and compared with existing methods, empathy and relevance are improved. Our code is available at https://***/outsider-lj/edsgi_bart. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

A Bald Eagle Search Optimization Based Weighted Rank Aggregation Method for Microarray Data Classification 23

A Bald Eagle Search Optimization Based Weighted Rank Aggrega...

引用

15th International Conference on Bioinformatics and Biomedical Technology, ICBBT 2023

作者： Li, Wei Shi, Tengfei Wang, Linjie Xie, Weidong Key Laboratory of Intelligent Computing in Medical Image MIIC Northeastern University Ministry of Education China School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9798400700385

The rapid development of microarray technology has generated a large amount of microarray data, and the classification of these data is meaningful for cancer diagnosis, treatment and prognosis. The classification of high-dimensional microarray data with small samples is a challenging problem, which usually requires feature selection methods to reduce the data dimensionality first. However, different feature selection methods usually generate different feature lists for the same data. Researchers need to choose among many feature selection methods, which reduces the research efficiency. Therefore, rank aggregation method is used to generate a optimal list by aggregating all ordered feature lists generated by different feature selection methods. It can combine the advantages of multiple feature selection methods and does not prefer a particular method, so it is more robust to outliers, noises and errors. In this paper, we propose a weighted rank aggregation method based on the Bald Eagle Search optimization. A positional weight is designed to emphasize the importance of the top features in the list, so that the distance between lists can be measured more accurately. In addition, we improve the Bald Eagle Search algorithm for optimizing rank aggregation method to obtain a optimal ordered list. The experimental results on six public microarray datasets indicate that the features selected by our method can significantly improve the classification performance. © 2023 ACM.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Automatic Heart Segmentation Based On Convolutional Networks Using Attention Mechanism 14

Automatic Heart Segmentation Based On Convolutional Networks...

引用

14th International Conference on Digital image Processing, ICDIP 2022

作者： Zhang, Guodong Liu, Yu Guo, Wei Tan, Wenjun Gong, Zhaoxuan Farooq, Muhammad Azaz Shenyang Aerospace University Liaoning Shenyang110136 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Liaoning 110819 China

ISBN: (纸本)9781510657564

Heart segmentation is challenging due to the poor image contrast of heart in the CT images. Since manual segmentation of the heart is tedious and time-consuming, we propose an attention based- Convolution Neural Network(CNN) for heart segmentation. First, one-hot preprocessing is performed on the multi-tissue CT images. U-Net network with Attention-gate is then applied to obtain the heart region. We compared our method with several CNN methods in terms of dice coefficient. Results show that our method outperforms other methods for segmentation. © 2022 SPIE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

An approach of sentiment lexicon building and orientation analysis for chinese microblogs

引用

Journal of Computational Information Systems 2012年第3期8卷 1113-1120页

作者： Wang, Lin Feng, Shi Song, Kaisong Wang, Daling School of Information science and Engineering Northeastern University Shenyang 110819 China Key Laboratory of Medical Image Computing Northeastern University Ministry of Education Shenyang 110819 China

As a new information media, microblog has more innovative features than traditional user-generated content. Straightforward emotion expression is one of the main characteristics which means users prefer to utilize emoticons, interjections to express their sentiments. However, there is a lack of study on such modifiers and related processing methods in existing sentiment lexicons. For solving this problem, we analyze and complement the content of the existing lexicons and knowledge bases for building a brand new sentiment lexicon with above words, and propose an algorithm for sentiment orientation analysis based on the new lexicon. Moreover, we develop a system of sentiment analysis. Experiments show the proposed lexicon building method can effectively improve the performance of microblog sentiment analysis, and the prototype system has implemented the functions from data download to result output. 1553-9105/Copyright © 2012 Binary Information Press.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A PSO-Based cost-sensitive neural network for imbalanced data classification

A PSO-Based cost-sensitive neural network for imbalanced dat...

引用

17th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2013

作者： Cao, Peng Zhao, Dazhe Zaïane, Osmar R. Key Laboratory of Medical Image Computing of Ministery of Education Northeastern University China Department of Computing Science University of Alberta Canada

ISBN: (纸本)9783642403187

Learning from imbalanced data is an important and common problem. Many methods have been proposed to address and attempt to solve the problem, including sampling and cost-sensitive learning. This paper presents an effective wrapper approach incorporating the evaluation measure directly into the objective function of cost-sensitive neural network to improve the performance of classification, by simultaneously optimizing the best pair of feature subset, intrinsic structure parameters and misclassification costs. The optimization is based on Particle Swarm Optimization. Our designed method can be applied on the binary class and multi-class classification. Experimental results on various standard benchmark datasets show that the proposed method is effective in comparison with commonly used sampling techniques. © Springer-Verlag 2013.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Efficient secure data publishing algorithms for supporting information sharing

引用

Science in China(Series F) 2009年第4期52卷 627-644页

作者： YANG XiaoChun Key Laboratory of Medical Image Computing (Northeastern University) Ministry of Education Shenyang 110004 China School of Information Science and Engineering Northeastern University Shenyang 110004 China

Many data sharing applications require that publishing data should protect sensitive information pertaining to individuals, such as diseases of patients, the credit rating of a customer, and the salary of an employee. Meanwhile, certain information is required to be published. In this paper, we consider data-publishing applications where the publisher specifies both sensitive information and shared information. An adversary can infer the real value of a sensitive entry with a high confidence by using publishing data. The goal is to protect sensitive information in the presence of data inference using derived association rules on publishing data. We formulate the inference attack framework, and develop complexity results. We show that computing a safe partial table is an NP-hard problem. We classify the general problem into subcases based on the requirements of publishing information, and propose algorithms for finding a safe partial table to publish. We have conducted an empirical study to evaluate these algorithms on real data. The test results show that the proposed algorithms can produce approximate maximal published data and improve the performance of existing algorithms.

关键词： Information sharing data publishing data privacy association rule inference attack

来源：评论

学校读者我要写书评

暂无评论

NiuTrans: An open source toolkit for phrase-based and syntax-based machine translation 50

NiuTrans: An open source toolkit for phrase-based and syntax...

引用

50th Annual Meeting of the Association for Computational Linguistics, ACL 2012

作者： Xiao, Tong Zhu, Jingbo Zhang, Hao Li, Qiang Natural Language Processing Lab Northeastern University Key Laboratory of Medical Image Computing Ministry of Education

ISBN: (纸本)9781937284275

We present a new open source toolkit for phrase-based and syntax-based machine translation. The toolkit supports several state-of-the-art models developed in statistical machine translation, including the phrase-based model, the hierachical phrase-based model, and various syntax-based models. The key innovation provided by the toolkit is that the decoder can work with various grammars and offers different choices of decoding algrithms, such as phrase-based decoding, decoding as parsing/tree-parsing and forest-based decoding. Moreover, several useful utilities were distributed with the toolkit, including a discriminative reordering model, a simple and fast language model, and an implementation of minimum error rate training for weight tuning. © 2012 Association for Computational Linguistics

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：