检索结果-内蒙古大学图书馆

4th international conference on Systems and Informatics (ICSAI)

作者： Zhang, Guangwei Han, Xiaomang Shaanxi Normal Univ Sch Hist & Civilizat Xian Shaanxi Peoples R China

ISBN: (纸本)9781538611074

the Tangut script, a logographic writing system, was used for writing the extinct Tangut language of the West Xia Dynasty. the huge amount of Tangut historical documents are being mainly recognized by Tangut experts manually, because the Tangut language has not been used since 16th century and it was impossible to recognized automatically in the past. With the help of deep learning, we build an end-to-end Tangut character recognition system to reduce the labor of Tangut experts. the high accuracy of a deep learning system for character recognition is essentially guaranteed by a large training dataset of well-labeled data. We construct a training dataset containing more than 100,000 labeled Tangut images, which is used for training a deep convolutional neural network (DCNN) to recognize Tangut characters. the Tangut images in the training dataset are from Tangut historical documents and they are labeled in a cluster-and- label way to reduce the human efforts. Based on the training dataset, the validation accuracy of the DCNN is more than 94% according to our experiments. We will release the training dataset for further study and construct an OCR system for transcribing Tangut historical documents automatically in the future.

关键词： Character recognition Training Labeling machine learning Computer architecture Image recognition Optical character recognition software

来源：评论

学校读者我要写书评

暂无评论

Language recognition via Sparse Coding over Learned Dictionary 4

Language Recognition via Sparse Coding over Learned Dictiona...

引用

4th international conference on Signal Processing and Integrated Networks (SPIN)

作者： Singh, Om Prakash Sinha, Rohit Indian Inst Technol Guwahati Dept Elect & Elect Engn Gauhati India

ISBN: (纸本)9781509027972

In this work, we explore the use of sparse features derived using a learned dictionary for language recognition (LID. these sparse features are referred to as s-vector and are derived by sparse coding of the commonly used low-dimensional i-vector based representation of speech utterances over the learned dictionary. the orthogonal matching pursuit (OMP), least absolute shrinkage and selection operator (LASSO), and elastic net (ENet) based sparse coding algorithms have been investigated for deriving the s-vectors. Two classifiers namely cosine distance scoring (CDS) and support vector machine (SVM) have been applied on the s-vectors. Scores are calibrated using regularized multi-class logistic regression. the effectiveness of the proposed approach is empirically validated on NIST 2007 LRE data set in closed set condition on 30 seconds duration segments.

关键词： Dictionaries Encoding Support vector machines Speech Training machine learning Matching pursuit algorithms

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction via Representation and Affinity learning 4

Dimensionality Reduction via Representation and Affinity Lea...

引用

4th international conference on Systems and Informatics (ICSAI)

作者： Qi, Miao Lu, Shuang Huang, Xing Yang, Lin Gong, Chengrong Wang, Jianzhong Gu, Yuanyuan Northeast Normal Univ Sch Informat Sci & Technol Changchun Jilin Peoples R China Northeast Normal Univ Key Lab Appl Stat MOE Changchun Jilin Peoples R China Changchun Univ Technol Coll Humanities & Informat Changchun Jilin Peoples R China

ISBN: (纸本)9781538611074

Because graphs are crucial in modeling the data distribution or structure, graph-based dimensionality reduction methods have been widely employed in many machine learning and pattern recognition applications. However, in most existing graph-based dimensionality reduction techniques, the graph is usually specified empirically or learned from raw data, which may deteriorate their performances. In this paper, we propose a novel algorithm named Dimensionality Reduction via Representation and Affinity learning (DRRAL), which adaptively constructs graph and learns the projection matrix for dimensionality reduction. Our algorithm takes noise and different local structure of each sample into account. Moreover, an efficient optimization strategy based on the iterative updating Augmented Lagrange Multiplier (ALM) and eigenvectors is developed to solve the proposed DRRAL. Extensive experimental results on five databases are carried out to verify the feasibility and effectiveness of proposed approach.

关键词： dimensionality reduction graph construction adaptive graph

来源：评论

学校读者我要写书评

暂无评论

Combined neural network model for real estate market range value estimation 4

Combined neural network model for real estate market range v...

引用

4th international conference on Artificial Intelligence and pattern recognition, AIPR 2017

作者： Yakubovskyi, V. Dimitrov, Georgi Petrov Bychkov, Oleksiy Panayotova, Galina Institute of International Relations Taras Shevchenko National University of Kyiv Ukraine Ukraine University of Library Studies and Information Technologies Sofia Bulgaria Taras Shevchenko National University of Kyiv Kiev Ukraine

ISBN: (纸本)9781941968437

this article describes the neural network model for solving problem of real estate market valuation. Results of this approach were compared to the ones of existing algorithms for this problem. Influence of the data parameters and structure of learning dataset on accuracy of algorithms for real estate market valuation is also analyzed in this article. © 2017 SDIWC.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Efficient and robust TWSVM classifier based on L1-norm distance metric for pattern classification 4

Efficient and robust TWSVM classifier based on L1-norm dista...

引用

4th IAPR Asian conference on pattern recognition (ACPR)

作者： Yan, He Ye, Qiao-Lin Zhang, Tian-An Yu, Dong-Jun Nanjing Univ Sci & Technol Sch Comp Sci & Engn Xiaolingwei 200 Nanjing 210094 Jiangsu Peoples R China Nanjing Forestry Univ Coll Informat Sci & Technol Longpan Rd 159 Nanjing 210037 Jiangsu Peoples R China Nanjing Forestry Univ Collaborat Innovat Ctr Sustainable Forestry South Longpan Rd 159 Nanjing 210037 Jiangsu Peoples R China

ISBN: (纸本)9781538633540

Twin support vector machine (TWSVM) is a classical distance metric learning method for classification problems. the formulation of TWSVM criterion is based on L2-norm distance, which makes TWSVM prone to being influenced by the presence of outliers. In this paper, to develop a robust distance metric learning method, we propose a new objective for TWSVM classifier using L1-norm distance metric, termed as L1-TWSVM. the optimization strategy is to maximize the ratio of the inter-class distance dispersion to the intra-class distance dispersion by using L1-norm distance rather than L2-norm distance. Besides, we design a simple and valid iterative algorithm to solve L1-norm optimal problems, which is easy to actualize and its convergence to an optimum is theoretically ensured. the efficiency and robustness of L1-TWSVM have been validated by experiments on UCI datasets and artificial datasets. the promising experimental results indicate that our proposals outperform relevant state-of-the-art methods in all kinds of experimental settings.

关键词： Support vector machines Optimization Measurement Classification algorithms Forestry Convergence Robustness

来源：评论

学校读者我要写书评

暂无评论

Extended Body-Angles Algorithm to recognize activities within intelligent environments

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2017年第4期8卷 531-549页

作者： Lopez de la Franca, Carlos Gutierrez Hervas, Ramon Johnson, Esperanza Mondejar, Tania Bravo, Jose Univ Castilla La Mancha MAmI Res Lab Paseo Univ 4 E-13071 Ciudad Real Spain eSmile Psychol Children & Adolescents Calle Toledo 791 E Ciudad Real Spain

machine learning methods have been proven to be a useful and powerful mechanism in classification problems and pattern recognition. It is possible to classify into different categories on the basis of a training set of data through a discrete number of characteristics and without knowing the whole intrinsic information. For that, those methods are widely extended to address Activity recognition. One of the limitations of traditional machine learning methods is the need of a large training dataset to get an effective model with high accuracy levels. this issue is the main motivation of the present work that proposes the named Extended Body-Angles Algorithm, a method able to recognize movements through single samples of modelled movements using Kinect. their functioning is based on the Body-Angles Algorithm. this manuscript deepens into the detection of postures (Body-Angles Algorithm) that has been generalized to movements (Extended Body-Angles Algorithm), describing also the results of the algorithm evaluation.

关键词： Activity recognition Kinect Ubiquitous computing Behaviour aware computing Ambient intelligence

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular disease detection using a new ensemble classifier 4

Cardiovascular disease detection using a new ensemble classi...

引用

IEEE 4th international conference on Knowledge-Based Engineering and Innovation (KBEI)

作者： Esfahani, Hamidreza Ashrafi Ghazanfari, Morteza Islamic Azad Univ Ramsar Ramsar Iran Univ Guilan Rasht Iran

ISBN: (纸本)9781538626405

one of the biggest problems in mechanical life is the lack of mobility that can cause thousands of problems in human health. In the last decade, along with the life of a machine, many diseases, including cancer and cardiovascular disease, have been common in many societies that kill many people every year. data mining is based on collected data and existing history to create a model that can be effective in predicting new cases of a disease, whether they are risky or not. the higher the accuracy of the prediction or recognition of a given pattern or model means the higher efficiency of the algorithm. In this study, data on cardiovascular patients collected from the UCI Laboratory is utilized for applying discovery pattern algorithms including Decision tree, Neural Networks, Rough Set, SVM, Naive Bayes, and compare their accuracy and prediction. Finally, we propose a hybrid algorithm to increase the accuracy of these algorithms. Based on the results, the proposed hybrid method achieved an F-measure of 86.8% which outperforms other competing methods.

关键词： data mining Accosiation rule mining Heart disease Early diagnosis

来源：评论

学校读者我要写书评

暂无评论

iWalk : Let Your Smartphone Remember You 4

iWalk : Let Your Smartphone Remember You

引用

4th international conference on Information Science and Control Engineering (ICISCE)

作者： Li, Guozhu Huang, Liusheng Xu, Hongli Univ Sci & Technol China Sch Software Engn Hefei 230027 Anhui Peoples R China Univ Sci & Technol China Sch Comp Sci Hefei 230027 Anhui Peoples R China

ISBN: (纸本)9781538630136

the advance of science and technology brings not only the convenience to people, but also the issues of the property and privacy security. therefore, the identity recognition technology is particularly important. Walking is one of the most common daily activity of a person, but everyone walks differently. So we designed a new system based on the data of walking called iWalk to identify the user's identity. the most challenging task is to choose the features of walking that can represent each person's identity. IWalk collects data based on accelerometers built into Commercial Off-the-Shelf (COTS) smartphones and uses the Human Activity recognition (HAR) method to determine whether the current user is the owner of the phone. the data we used for training and evaluation were collected by 16 volunteers from real activities. the results of our experiments show that iWalk can achieve 97. 80 % true positive (TP) rate in judging the identity of the user's segments. through the judgment of segments, it recognizes the user identity in the final.

关键词： Identity recognition Human Activity recognition Security machine learning Smartphone Sensing

来源：评论

学校读者我要写书评

暂无评论

Storytelling with signal injection: Focusing stories with domain knowledge 14th

Storytelling with signal injection: Focusing stories with do...

引用

14th international conference on machine learning and data Mining in pattern recognition, MLDM 2018

作者： Rigsby, J.T. Barbará, Daniel Naval Surface Warfare Center 18372 Frontage Road DahlgrenVA22448 United States CS Department George Mason University Mail Stop 4A5 FairfaxVA22030 United States

ISBN: (纸本)9783319961323

Given a beginning and ending document, automated storytelling attempts to fill in intermediary documents to form a coherent story. this is a common problem for analysts;they often have two snippets of information and want to find the other pieces that relate them. the goal of storytelling is to help the analysts limit the number of documents that must be sifted through and show connections between events, people, organizations, and places. But existing algorithms fail to allow for the insertion of analyst knowledge into the story generation process. Often times, analysts have an understanding of the situation or prior knowledge that could be used to focus the story in a better way. A storytelling algorithm is proposed as a multi-criteria optimization problem that allows for signal injection by the analyst while maintaining good story flow and content. © Springer international Publishing AG, part of Springer Nature 2018.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Accuracy Based Weighted Aging Ensemble (AB-WAE) - algorithm for data stream classification 4

Accuracy Based Weighted Aging Ensemble (AB-WAE) - algorithm ...

引用

4th IEEE international conference on Soft Computing & machine Intelligence (ISCMI)

作者： Wozniak, Michal Wroclaw Univ Sci & Technol Fac Elect Wybrzeze Wyspianskiego 27 PL-50370 Wroclaw Poland

ISBN: (纸本)9781538613146

Nowadays, most of the data comes continuously and its distribution may change over the time. Unfortunately, most of classifiers assume that statistical characteristics of used predicting model are not being changed. this work presents modification of the previously proposed Weighted Aging Classifier Ensemble (WAE), called Accuracy Based WAE (AB-WAE), which can easily adapt to the probability characteristic changes caused by so-called concept drift. the proposed model does not exploit a drift detection mechanism, but AB-WAE tries to change the line-up of the classifier ensemble and weights assigned to base classifiers. thus, one individual classifier is trained on the basis of the each incoming data chunk, then AB-WAE chooses the most valuable ensemble taking into consideration: fixed ensemble size, the previously trained models and new trained classifier. the discussed WAE modification uses the ensemble of homogeneous classifiers only, what allows to employ more sophisticated combination rule based on support functions, what should boost the classification accuracy, what was confirmed by the computer experiments.

关键词： classifier ensemble data stream classification pattern classification machine learning concept drift

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：