检索结果-内蒙古大学图书馆

A spectrum-based support vector algorithm for relational data semi-supervised classification

13th International Conference on Neural Information Processing, ICONIP 2006

作者： Ping, Ling Zhe, Wang Chunguang, Zhou Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Changchun 130012 China School of Computer Science Xuzhou Normal University Xuzhou 221116 China

ISBN: (纸本)3540464794

A Spectrum-based Support Vector Algorithm (SSVA) to resolve semi-supervised classification for relational data is presented in this paper. SSVA extracts data representatives and groups them with spectral analysis. Label assignment is done according to affinities between data and data representatives. The Kernel function encoded in SSVA is defined to rear to relational version and parameterized by supervisory information. Another point is the selftuning of penalty coefficient and Kernel scale parameter to eliminate the need of searching parameter spaces. Experiments on real datasets demonstrate the performance and efficiency of SSVA. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Adaptive support vector clustering for multi-relational data mining

Adaptive support vector clustering for multi-relational data...

引用

3rd International Symposium on Neural Networks, ISNN 2006 - Advances in Neural Networks

作者： Ling, Ping Zhou, Chun-Guang Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Changchun 130012 China School of Computer Science Xuzhou Normal University Xuzhou 221116 China

ISBN: (纸本)354034439X

A novel self Adaptive Support Vector Clustering algorithm (ASVC) is proposed in this paper to cluster dataset with diverse dispersions. And a Kernel function is defined to measure affinity between multi-relational data. Task of clustering multi-relational data is addressed by integrating the designed Kernel into ASVC. Experimental results indicate that the designed Kernel can capture structured features well and ASVC is of fine performance. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

An hidden markov model-based transcription factor mining method

引用

Journal of Bionanoscience 2013年第1期7卷 66-71页

作者： Wu, Chunguo Li, Gaoyang Wu, Xiaozhou Han, Xiaosong Wang, Binghong Breis, Jesualdo Tomás Fernández Wang, Fei Liang, Yanchun Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University Changchun 130012 China Business School University of Shanghai for Science and Technology Shanghai 200093 China Shanghai Key Laboratory of Intelligent Information Processing Shanghai 200433 China Department of Informatics and Systems University of Murcia 30100 Murcia Spain

A text mining algorithm named HMM-TFM (Hidden Markov Model based transcription factor name mining) is presented. The proposed algorithm does not need a dictionary of transcription factor names. A small verb set is defined to filter sentences. Transcription factor names are mined according to the part of speech tagged by hidden Markov model. Experimental results show that the recall and precision of HMM-TFM achieve 74.2% and 77.9%, respectively. Copyright © 2013 American Scientific Publishers.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Fuzzy neural network optimization by a particle swarm optimization algorithm

Fuzzy neural network optimization by a particle swarm optimi...

引用

3rd International Symposium on Neural Networks, ISNN 2006 - Advances in Neural Networks

作者： Ma, Ming Zhang, Li-Biao Ma, Jie Zhou, Chun-Guang Key Laboratory for Symbol Computation and Knowledge Engineering Jilin University National Education Ministry of China Changchun 130012 China Information Manage Center Beihua University Jilin 132013 China

ISBN: (纸本)354034439X

Designing a set of fuzzy neural networks can be considered as solving a multi-objective optimization problem. An algorithm for solving the multi-objective optimization problem is presented based on particle swarm optimization through the improvement of the selection manner for global and individual extremum. The search for the Pareto Optimal Set of fuzzy neural networks optimization problems is performed, Numerical simulations for taste identification of tea show the effectiveness of the proposed algorithm. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

2.5D ASF-UNet: Adjacent Slice Spatial Feature Fusion Model for WMH Segmentation from 3D MR Brain Image

2.5D ASF-UNet: Adjacent Slice Spatial Feature Fusion Model f...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Huang, Lan Sun, Yinglu Zhao, Ziqi Guo, Chunjie Wang, Yan College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Changchun China The First Hospital of Jilin University Department of Radiology Changchun China

ISBN: (纸本)9798350386226

Segmenting brain white matter hyperintensities (WMH) from 3D Magnetic Resonance (MR) images is crucial for the diagnosis, treatment, and prognosis of Multiple Sclerosis (MS). Unlike common 2D images, this task is more challenging and time-consuming. Classical deep learning methods for 3D image segmentation face two main challenges: 1) Pure 3D networks have more parameters and are prone to overfitting. 2) When using 2D networks to segment slices of 3D images, the lack of 3D structural information results in suboptimal segmentation after reconstruction. To address these difficulties, we propose the 2.5D ASF-UNet, which employs the 2.5D workflow and uses adjacent slices as the input for 2D segmentation network ASF-UNet. In ASF-UNet, separate down-sampling paths are used for the adjacent slices, and the Local Spatial Attention Module (LSAM) is designed to more effectively integrate 3D spatial information into the 2D network. Additionally, the Conv-Spectral-Block (CSB) is designed to extract and integrate local and global features. It allows the model to capture global spatial structures while preserving detailed information. Experimental results on MICCAI MSSEG 2016 and Local MS datasets show that 2.5D ASF-UNet achieve better segmentation performance than other deep learning methods. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A modified integer-coding genetic algorithm for job shop scheduling problem

A modified integer-coding genetic algorithm for job shop sch...

引用

8th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2004

作者： Wu, Chunguo Xiang, Wei Liang, Yanchun Lee, Heow Pueh Zhou, Chunguang College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun130012 China Institute of High Performance Computing Singapore117528 Singapore

ISBN: (纸本)3540228179

An operation template is proposed in this paper for describing the mapping between operations and a subset of natural numbers. With such operation template, a job shop scheduling problem (JSSP) can be transformed into a traveling salesman problem (TSP), hence the integer-coding genetic algorithm for TSP can be easily applied and modified. A decoding strategy, called virtual job shop, is proposed to evaluate the fitness of the individual in GA population. The integration of the operation template and virtual job shop makes the existing integer-coding GA possible for solving an extension of a classical job shop scheduling problem. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

An effective dimensionality reduction method for text classification based on TFP-tree

An effective dimensionality reduction method for text classi...

引用

作者： Liu, Lu College of Software Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun China College of Computer Science and Technology Jilin University Changchun China

Obtaining interesting and topic-relevant information is a very important task in Web mining. Text classification using a small proportion of labeled data and a large proportion of unlabeled data, also called semi-supervised learning, is a well-known problem. Despite plenty of research on text classification, however, how to effectively and efficiently apply valuable frequent patterns and deal with high-dimensional data in text classification is still an open issue. Due to the increasing data volumes and plenty of high-dimensional data, both distance measures and time complexity could be influenced by the noisy data. This paper targets on this problem and presents a novel method for text classification called CTFP (Classification based on TFP-tree), which uses TFP-tree (Text-Frequent-Pattern-tree) to generate frequent patterns in tremendous amount of texts and conduct text classification in a relatively low dimensional data space. It effectively reduces the data dimensionality during constructing the classifier. Substantial experiments on three datasets (RCV1, SRAA and Reuters-21578) show that our proposed method can achieve better performance than many existing state-of-the-art methods on precision, efficiency and many other evaluation metrics. © 2018 - IOS Press and the authors. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Block-based normalized-cut algorithm for image segmentation

Block-based normalized-cut algorithm for image segmentation

引用

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Chen, Jingrun Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China Institute of Computer Graphics and Image Processing Dalian Nationalities University Dalian China State Key Laboratory of CAD and CG Zhejiang University Hangzhou China

ISBN: (纸本)9783642051722

Automatic image segmentation remains a challenging problem in the fields of computer vision, image analysis and understanding. A lot of algorithms and technologies have been proposed and developed for image segmentation, among which the N-cut has been a promising method and active research area due to better quality. But the N-cut can't process medium and large image dataset online due to incredible memory and time complexity. Moreover, the N-cut algorithm can't utilize texture information since its basic unit of clustering algorithm is pixel. To overcome the drawback and improve the description power, the paper proposes a block-based N-cut algorithm for image segmentation, whose basic unit of clustering is image block instead of individual pixel. Block-based algorithm not only decreases the time and storage complexity, but also improves the discrimination power of visual feature vector. The experiments demonstrate that proposed algorithm outperform the original N-cut algorithm in efficiency. Experiments show that the proposed block-based N-cut algorithm is more suitable for online processing large-scale data. © 2010 Springer-Verlag Berlin Heidelberg.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Clonal Selection Based Memetic Algorithm for Job Shop Scheduling Problems

引用

Journal of Bionic engineering 2008年第2期5卷 111-119页

作者： Jin-hui Yang Liang Sun Heow Pueh Lee Yun Qian Yan-chun Liang College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun 130012 P. R. China Institute of High Performance Computing Singapore 117528 Singapore Department of Mechanical Engineering National University of Singapore Singapore 117576 Singapore Institute of Electric and Information Engineering Beihua University Jilin 13202 l P. R. China

A clonal selection based memetic algorithm is proposed for solving job shop scheduling problems in this paper. In the proposed algorithm, the clonal selection and the local search mechanism are designed to enhance exploration and exploitation. In the clonal selection mechanism, clonal selection, hypermutation and receptor edit theories are presented to construct an evolutionary searching mechanism which is used for exploration. In the local search mechanism, a simulated annealing local search algorithm based on Nowicki and Smutnicki＇s neighborhood is presented to exploit local optima. The proposed algorithm is examined using some well-known benchmark problems. Numerical results validate the effectiveness of the proposed algorithm.

关键词： job shop scheduling problem clonal selection algorithm simulated annealing global search local search

来源：评论

学校读者我要写书评

暂无评论

Crossed-Time Delay Neural Network for Speaker Recognition

arXiv

引用

arXiv 2020年

作者： Chen, Liang Liang, Yanchun Shi, Xiaohu Zhou, You Wu, Chunguo Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China Zhuhai Laboratory of Key Laboratory of Symbol Computation Knowledge Engineering of Ministry of Education School of Computer Zhuhai College Jilin University Zhuhai519041 China

Time Delay Neural Network (TDNN) is a well-performing structure for deep neural network-based speaker recognition systems. In this paper we introduce a novel structure, named Crossed-Time Delay Neural Network (CTDNN) to enhance the performance of current TDNN for speaker recognition. Inspired by the multi-filters setting of convolution layers from convolution neural networks, we set multiple time delay units with different context size at the bottom layer and construct a multilayer parallel network. The proposed CTDNN gives significant improvements over original TDNN on both speaker verification and identification tasks. It outperforms in VoxCeleb1 dataset in verification experiment with a 2.6% absolute Equal Error Rate improvement. In few shots condition, CTDNN reaches 90.4% identification accuracy, which doubles the identification accuracy of original TDNN. We also compare the proposed CTDNN with another new variant of TDNN, Factorized-TDNN, which shows that our model has a 36% absolute identification accuracy improvement under few shots condition. Moreover, the proposed CTDNN can handle training with a larger batch more efficiently and hence, utilize calculation resources economically. The code of the new model is released at https://***/chenllliang/CTDNN. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

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：