检索结果-内蒙古大学图书馆

pattern classification with missing data: a review

NEURAL computing & APPLICATIONS 2010年第2期19卷 263-282页

作者： Garcia-Laencina, Pedro J. Sancho-Gomez, Jose-Luis Figueiras-Vidal, Anibal R. Univ Politecn Cartagena Dpto Tecnol Informac & Comunicac Murcia 30202 Spain Univ Carlos III Madrid Dpto Teoria Senal & Comunicac Madrid 28911 Spain

pattern classification has been successfully applied in many problem domains, such as biometric recognition, document classification or medical diagnosis. Missing or unknown data are a common drawback that pattern recognition techniques need to deal with when solving real-life classification tasks. Machine learning approaches and methods imported from statistical learning theory have been most intensively studied and used in this subject. the aim of this work is to analyze the missing data problem in pattern classification tasks, and to summarize and compare some of the well-known methods used for handling missing values.

关键词： pattern classification Missing data Neural networks Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Algorithm Model of Power Grid Maintenance Ticket Based on Bert 12

An Algorithm Model of Power Grid Maintenance Ticket Based on...

引用

12th international conference of Information and Communication Technology, ICTech 2023

作者： Zhang, Guoqiang Wang, Qun Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350332919

A variety of semantic instructions are needed to implement operations in the daily operation of the grid. Among them, maintenance ticket language is the most important one among all grid semantics. However, because the semantic recognition of maintenance ticket is implemented in a strong scenario like power distribution network, there are problems such as low recognition efficiency and misclassification of recognition results. In this paper, we propose to use BERT algorithm model with Bi-LSTM and CRF to form a new type of algorithm model, and on this basis, we propose to improve the structure of the algorithm model. Finally, it is experimentally shown that not only can the algorithm improve the recognition effect of each classification, but also can give better overall recognition effect. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Finding Principal Semantics of Style in Art 12

Finding Principal Semantics of Style in Art

引用

12th IEEE international conference on Semantic computing (ICSC)

作者： Kim, Diana S. Liu, Bingchen Elgammal, Ahmed Mazzone, Marian Rutgers State Univ Dept Comp Sci New Brunswick NJ 08901 USA Coll Charleston Dept Art & Architectural Hist Charleston SC 29401 USA

ISBN: (纸本)9781538644072

We investigate a novel mechanism to interpret each coordinate of Deep Neural Network (DNN) activations with concepts aligned with art principles such as light, shape, pattern, line, and textures. After training state-of-the-art DNN architectures as paintings style classifiers, we collect activations from the second to last layer of DNN and conduct a data analysis. Based on the interpretation results, we can demonstrate which art principles are essential when machines understand styles and also can decipher each coordinates value in the context of relatedness to specific art principles.

关键词： pattern recognition Machine learning Deep neural network Unsupervised learning Semantic interpretation of DNN features Art principles

来源：评论

学校读者我要写书评

暂无评论

Research on Power Dispatching Speech recognition Based on Improved Transformer 12

Research on Power Dispatching Speech Recognition Based on Im...

引用

12th international conference of Information and Communication Technology, ICTech 2023

作者： Wang, HanJun Lin, HaoYang Shenyang Institute of Computing Technology University of Chinese Academy of Sciences Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798350332919

Now, speech recognition [1] has developed rapidly. Transformer network model architecture is constructed by encoder and decoder. has become popular and applied to speech recognition. the Transformer model has achieved very good results in ordinary daily scenes. In the production environment of power dispatching, speech recognition requires low error rate and faster recognition speed. therefore, some improvements have been made to the Transformer model. then, the core attention mechanism in Transformer is mainly introduced. According to the characteristics of voice dataset in power dispatching, the model is improved and the attention mechanism is lightweight. Finally, through experimental training, we use the improved model to train on the power dispatching voice dataset, and then evaluate the trained model. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Named Entity recognition in Fire Control Texts Based on BERT 12

Named Entity Recognition in Fire Control Texts Based on BERT

引用

12th international conference of Information and Communication Technology, ICTech 2023

作者： Meng, XiangRu Cao, PengFei Ma, ManNing Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798350332919

In order to extract named entities from fire control texts more accurately, a named entity corpus based on fire control related texts is constructed. Aiming at the traditional word vector or word vector can not better represent the context semantics and the disadvantages of recurrent neural network in using GPU parallel computing ability, a named entity recognition model of fire control related texts based on BERT is proposed. the word granularity vector matrix is obtained by using the BERT language model, and the use the IDCNN to abstract features from text. the text dependency on a long-distance of sentences is obtained through MA layer. At last, the global best sequence is extracted through CRF. By analyzing the final experimental findings, it is known that the accuracy, recall and F value increased 2.78%, 1.59% and 1.33% respectively. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Engineering Applications of Neural Networks 2011

引用

丛书名： IFIP Advances in Information and Communication Technology

2011年

作者： Lazaros S. Iliadis Chrisina Jayne

ISBN: (数字)9783642239571

ISBN: (纸本)9783642239564

the two-volume set IFIP AICT 363 and 364 constitutes the refereed proceedings of the 12th international conference on Engineering Applications of Neural Networks, EANN 2011, and the 7th IFIP WG 12.5 international conference, AIAI 2011, held jointly in Corfu, Greece, in September 2011. the 52 revised full papers and 28 revised short papers presented together with 31 workshop papers were carefully reviewed and selected from 150 submissions. the first volume includes the papers that were accepted for presentation at the EANN 2011 conference. they are organized in topical sections on computer vision and robotics, self organizing maps, classification/pattern recognition, financial and management applications of AI, fuzzy systems, support vector machines, learning and novel algorithms, reinforcement and radial basis function ANN, machine learning, evolutionary genetic algorithms optimization, Web applications of ANN, spiking ANN, feature extraction minimization, medical applications of AI, environmental and earth applications of AI, multi layer ANN, and bioinformatics. the volume also contains the accepted papers from the Workshop on Applications of Soft computing to Telecommunication (ASCOTE 2011), the Workshop on Computational Intelligence Applications in Bioinformatics (CIAB 2011), and the Second Workshop on Informatics and Intelligent Systems Applications for Quality of Life Information Services (ISQLIS 2011).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Convex Net: A Scalable Architecture for Speech pattern Classification

Deep Convex Net: A Scalable Architecture for Speech Pattern ...

引用

12th Annual conference of the international-Speech-Communication-Association 2011 (INTERSPEECH 2011)

作者： Deng, Li Yu, Dong Microsoft Res Redmond WA USA

ISBN: (纸本)9781618392701

We recently developed context-dependent DNN-HMM (Deep-Neural-Net/Hidden-Markov-Model) for large-vocabulary speech recognition. While achieving impressive recognition error rate reduction, we face the insurmountable problem of scalability in dealing with virtually unlimited amount of training data available nowadays. To overcome the scalability challenge, we have designed the deep convex network (DCN) architecture. the learning problem in DCN is convex within each module. Additional structure-exploited fine tuning further improves the quality of DCN. the full learning in DCN is batch-mode based instead of stochastic, naturally lending it amenable to parallel training that can be distributed over many machines. Experimental results on both MNIST and TIMIT tasks evaluated thus far demonstrate superior performance of DCN over the DBN (Deep Belief Network) counterpart that forms the basis of the DNN. the superiority is reflected not only in training scalability and CPU-only computation, but more importantly in classification accuracy in both tasks.

关键词： deep learning scalability convex optimization neural network deep belief network phone state classification batch-mode training parallel computing

来源：评论

学校读者我要写书评

暂无评论

Advantages of using a space filling curve for computing wavelet transforms of road traffic images

Advantages of using a space filling curve for computing wave...

引用

12th international conference on Image Analysis and Processing

作者： Pamula, W Silesian Tech Univ Fac Transport PL-40019 Katowice Poland

ISBN: (纸本)0769519482

the properties of computing wavelet transforms of road traffic image data are discussed. It is proposed to incorporate Hilbert scan of image data and a wavelet transform factorised into lifting steps. Scanning an image, in space filling curve order, brings together pixels that are highly correlated. this is a desirable property, because the objects of interest - vehicles comprise a bounded set of regular patches on an image. Applying a 1-dimensional wavelet transform requires a smaller number of processing steps than a separable two-dimensional transform. Such a solution is suitable for on site microcontroler or FPGA implementation.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Research on Intention recognition of Educational Counseling Combining BERT and Concept Map 12

Research on Intention Recognition of Educational Counseling ...

引用

12th international conference of Information and Communication Technology, ICTech 2023

作者： Gao, Sida Bao, Yuqian Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Nanjing Agricultural University Nanjing China

ISBN: (纸本)9798350332919

In the process of building a question answering system, the intention recognition of questions is an important step, and the accuracy of intention recognition has a great impact on the question answering system. In this method, the concepts of each entity in the concept graph are explicitly applied to the data processing process, and the entities are abstracted into a concept level. At the same time, in order to distinguish the subtle differences between concepts, different concepts of the same entity are further scored and ranked, and the concepts are sequentially applied. Incorporating the information of the concept map into the classification model can significantly improve the accuracy of the model in the domain, so that the model still has a good effect on a small-scale training set. Finally, experiments are carried out on the data of question answering in the college entrance examination field. the experimental results show that the method has good effect and good generalization. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Fuzzy Clustering for Cloud computing. Taking Web Service as a case

A Comparative Study on Fuzzy Clustering for Cloud Computing....

引用

12th international conference on Ambient Systems, Networks and Technologies (ANT) / 4th international conference on Emerging Data and Industry 4.0 (EDI40)

作者： Djellali, Choukri Adda, Mehdi Moutacalli, Mohamed Tarik Univ Quebec Rimouski Dept Comp Sci & Engn Rimouski PQ Canada

this study addresses the increasingly encountered challenge of data clustering. We present a comparative study to data clustering for cloud computing using Fuzzy C-MEANS and Adaptive Resonance theory. To reduce variance and improve generalization ability, we used a resampling method based on 10-fold cross-validation. the typical initialization scheme is applied to improve the convergence speed of training and thus, reach the optimal solution. Experimental results on cloud computing datasets showed that the typical initialization-based Fuzzy Adaptive Resonance theory model is effective and achieves improved accuracy for pattern recognition task compared to Fuzzy C-MEANS. (C) 2021 the Authors. Published by Elsevier B.V.

关键词： Data Mining Deep Learning Clustering Artificial Neural Network Fuzzy Logic Cross-Validation Cloud computing Web Service

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：