检索结果-内蒙古大学图书馆

1st international conference on Next Generation Computing Technologies (NGCT)

作者： Maitra, Deeptaroop Rajan Singh, Niharika UPES CIT Dept Dehra Dun Uttar Pradesh India

ISBN: (纸本)9781467368094

Oil exploration mainly targets to the locations that are closed or below the salt bodies, in the underlying geologic structure. With time the computational tools which can help in interpreting, analysing and estimating the geometry with its position has been increased. But still at many time the data which is gathered using these computational tools is recognized with the lack of resolution and poor structural identification which create severe technical and economic problems. Under such circumstances, seismic interpretation based only on the humaneye is inaccurate. In such a situation, for making good decisions and production planning all things depend on good- quality seismic images that generally are not feasible in salt tectonics areas. Therefore, a generalization of the Hough transform is applied to build parabolic, line, circular and arbitrary shapes that are useful in the idealization and recognition of salt domes from 2D seismic profiles. The contribution of this project is oriented in providing the seismic interpreters with semi-automatic computational tool. Hence, the paper focuses on image processing technique namely Hough transform along with sobel as well as canny algorithm which are applied to detect and delineate complex salt bodies from seismic exploration profiles. The novel image processing approach presented here will be helpful in the identification of complex geological features from seismic images.

关键词： Hough transform image processing feature extraction salt bodies seismic exploration profiles canny Sobel pattern recognition

来源：评论

学校读者我要写书评

暂无评论

PARITY SYMMETRICAL SRC ALGORITHM FOR FACE recognition 14

PARITY SYMMETRICAL SRC ALGORITHM FOR FACE RECOGNITION

引用

international conference on machine learning and Cybernetics (ICMLC)

作者： Song, Xiaoning Yang, Xibei Jiangnan Univ Sch Internet Things Engn Wuxi 214122 Peoples R China Univ Surrey Ctr Vis Speech & Signal Proc Guildford GU2 7XH Surrey England Jiangsu Univ Sci & Technol Sch Comp Sci & Engn Zhenjiang 212003 Peoples R China

ISBN: (纸本)9781467372206

Although the criterion-based feature extraction algorithms provided a feasible strategy to deal with the classification of high-dimensional data, most of the existing algorithms are locality-oriented and generally suffer from many issues such as uncertainty information associated with dataset and small sample size problem. In this paper, we propose a novel sparse representation-based classification method using parity symmetry strategy for face recognition. First, a subspace learning algorithm based on the geometric symmetry of face image is developed by using odd-even decomposition theorem, from which a set of parity symmetrical basis are constructed simultaneously. Second, the proposed method aims to represent a query sample as a linear combination of the most competitive training samples, and exploits an optimal representation of training samples from the classes with major relevant contributions. Experimental results conducted on ORL, FERET and AR face databases demonstrate the effectiveness of the proposed method.

关键词： SRC Parity symmetry Major relevant contribution image recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Feature Extraction and Classification Technique for machine learning Using Time Series and statistical Approach 1

引用

1st international conference on Computational Intelligence in Data Mining (ICCIDM)

作者： Barik, R. C. Naik, B. Vikash Coll Engn Women Dept Comp Sci & Engn Bargarh Odisha India Govt SSD Intermediate Sci Coll Dept Informat Technol Sundergarh Odisha India

ISBN: (纸本)9788132222026;9788132222019

Curse of dimensionality is a major challenge for any arena of scientific research like data mining, machine learning, optimization, clustering etc. An optimized feature extraction or dimension reduction gives rise to better prediction and classification, which can be applied to various research areas such as Bioinformatics, Geographical Information System, Speech recognition, image processing, Biometric, Biomedical imaging, letter or character recognition etc. Extracting the informative feature as well as removing the redundant and unwanted feature by reducing the data dimension is a remarkable issue for many scientific communities. In this paper we have introduced a novel feature extraction with dimension reduction technique by using combined signal processing and statistical approach as Discrete Wavelet Transform (DWT) and Multidimensional Scaling (MDS) respectively then Support Vector machine (SVM) has played a major role for classification of nonlinear, heterogeneous dataset.

关键词： Computer aided diagnosis Discrete wavelet transform (DWT) Multidimensional scaling (MDS) Support vector machines (SVM) Geographical information system (GIS) Principal component analysis (PCA) Factor analysis(FA)

来源：评论

学校读者我要写书评

暂无评论

1st international conference on Computational Intelligence in Data Mining, ICCIDM-2014

1st International Conference on Computational Intelligence i...

引用

1st international conference on Computational Intelligence in Data Mining, ICCIDM 2014

ISBN: (纸本)9788132222071

The proceedings contain 70 papers. The special focus in this conference is on Computational Intelligence Techniques in Data Mining. The topics include: A context sensitive thresholding technique for automatic image segmentation;encryption for massive data storage in cloud;an integrated approach to improve the text categorization using semantic measures;FPGA implementation of various image processing algorithms using Xilinx system generator;efficient recognition of devanagari handwritten text;quality assessment of data using statistical and machine learning methods;position and orientation control of a mobile robot using neural networks;character recognition using firefly based back propagation neural network;analyzing data through data fusion using classification techniques;multi-objective particle swarm optimization in intrusion detection;optimization of the investment casting process using genetic algorithm;model based test case generation from UML sequence and interaction overview diagrams;efficient spread of influence in online social networks;a Pi-sigma higher order neural network for stock index forecasting;comparison of statistical approaches for Tamil to English translation;comparative study of on-demand and table-driven routing protocols in MANET;a novel fast FCM clustering for segmentation of salt and pepper noise corrupted images;theoretical analysis of expected population variance evolution for a differential evolution variant;application of particle swarm optimization and user clustering in web search;analyzing urban area land coverage using image classification algorithms;quantum based learning with binary neural network and dynamic slicing of object-oriented programs in presence of inheritance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discriminative feature learning from big data for visual recognition

引用

pattern recognition 2015年第10期48卷 2961-2963页

作者： Jiang, Zhuolin Lin, Zhe Ling, Haibin Porikli, Fatih Shao, Ling Turaga, Pavan Raytheon BBN Technol Cambridge MA 02138 USA Adobe Res Cambridge MA USA Temple Univ Philadelphia PA 19122 USA Australian Natl Univ Canberra ACT 0200 Australia Northumbria Univ Newcastle Upon Tyne NE1 8ST Tyne & Wear England Arizona State Univ Tempe AZ 85287 USA

来源：评论

学校读者我要写书评

暂无评论

4.6 A1.93TOPS/W scalable deep learning/inference processor with tetra-parallel MIMD architecture for big-data applications 62

4.6 A1.93TOPS/W scalable deep learning/inference processor w...

引用

2015 62nd IEEE international Solid-state Circuits conference, ISSCC 2015 - Digest of Technical Papers

作者： Park, Seongwook Bong, Kyeongryeol Shin, Dongjoo Lee, Jinmook Choi, Sungpill Yoo, Hoi-Jun KAIST Daejeon Korea Republic of

ISBN: (纸本)9781479962235

Recently, deep learning (DL) has become a popular approach for big-data analysis in image retrieval with high accuracy [1]. As Fig. 4.6.1 shows, various applications, such as text, 2D image and motion recognition use DL due to its best-in-class recognition accuracy. There are 2 types of DL: supervised DL with labeled data and unsupervised DL with unlabeled data. With unsupervised DL, most of learning time is spent in massively iterative weight updates for a restricted Boltzmann machine [2]. For a -100MB training dataset, >100 TOP computational capability and ∼40GB/s IO and SRAM data bandwidth is required. So, a 3.4GHz CPU needs >10 hours learning time with a -100K input-vector dataset and takes ∼1 second for recognition, which is far from real-time processing. Thus, DL is typically done using cloud servers or high-performance GPU environments with learning-on-server capability. However, the wide use of smart portable devices, such as smartphones and tablets, results in many applications which need big-data processing with machine learning, such as tagging private photos in personal devices. A high-performance and energy-efficient DL/DI (deep inference) processor is required to realize user-centric pattern recognition in portable devices. © 2015 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

The Notation Scanner Systems using Resilient Backpropagation Method 1st

The Notation Scanner Systems using Resilient Backpropagation...

引用

1st international conference on Computer Science and Computational Intelligence (ICCSCI)

作者： Christofer, Ariel Kusuma, Chandrasurya Pribadi, Vincent Budiharto, Widodo Bina Nusantara Univ Sch Comp Sci Dept Comp Sci Palmerah 11480 Jakarta Barat Indonesia

This research proposes anotation scanner system for numerical notation. This research was supported by using resilient backpropagation algorithm and uses the music application to get a melody of musical instruments. Objects used are designed to be focused on the numerical notation symbols. To be implemented, the input image from camera will be pre-processing, image segmentation, number and symbol recognition, output sound, and to read numerical notation symbols before entering resilient backpropagation algorithm resize the image will be 21x21 pixels. By using colour filtering can reduce errors in handwriting recognition. Success rate by using 15 new sample data with 100 sample data training, the test to get a successful outcome as much as 87.9% and 12.1% error while success rate by using 15 new sample data with 50 sample data training, the test to get a successful outcome as much as 74.4% and 25.6% error. (C) 2015 The Authors. Published by Elsevier B.V.

关键词： resilient backpropagation OpenCV pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An Architecture of Distributed Beta Wavelet Networks for large image classification on in MapReduce 15

An Architecture of Distributed Beta Wavelet Networks for lar...

引用

15th international conference on Intelligent Systems Design and Applications (ISDA)

作者： Sakkari, Mohamed Zaied, Mourad Univ Sfax Natl Engn Sch Sfax ENIS REGIM Res Grp Intelligent Machines BP 1173 Sfax 3038 Tunisia

ISBN: (纸本)9781467387095

MapReduce has become a dominant parallel computing paradigm for storing and processing massive data due to its excellent scalability, reliability, and elasticity. in this paper, we present a new architecture of Distributed Beta Wavelet Networks {DBWN} for large image classification in MapReduce model. First to prove the performance of wavelet networks, a parallelized learning algorithm based on the Beta Wavelet Transform is proposed. T hen the proposed structure of the {DBWN} is itemized. However the new algorithm is realized in MapReduce model. Comparisons with Fast Beta Wavelet Network {FBWN} are presented and discussed. Results of comparison have shown that the {DBWN} model performs better than {FBWN} model in classification rate and in the context of training run time.

关键词： large image classification distributed wavelet parallel processing in MapReduce

来源：评论

学校读者我要写书评

暂无评论

Increasing the Safety in Recycling of Construction and Demolition Waste by Using Supervised machine learning

Increasing the Safety in Recycling of Construction and Demol...

引用

Joint international-Measurement-Confederation (IMEKO) TC1-TC7-TC13 Symposium on Measurement Science Behind Safety and Security

作者： Kuritcyn, P. Anding, K. Linss, E. Latyev, S. M. Ilmenau Univ Technol Fac Mech Engn Dept Qual Assurance & Ind Image Proc Ilmenau Germany Bauhaus Univ Weimar Fac Civil Engn D-99423 Weimar Germany Natl Res Univ Informat Technol Mech & Opt Fac Photon & Opt Informat Technol Dept Comp Photon & Videomat St Petersburg Russia

This paper discusses the possibility of the optical identification of recycled aggregates of construction and demolition waste (CDW) using methods of image processing, spectral analysis and machine learning. The classification performances in colour images shown, that we have to use other added spectral information to solve the recognition task in a satisfactory manner. In addition to investigations on a large colour image dataset first investigations in visible (VIS) and infrared (IR) spectrum were done for analysing significant characteristics in spectrum, which are useful for classification the C&D aggregates.

关键词： Recycling

来源：评论

学校读者我要写书评

暂无评论

Multiple Instance learning-Based Birdsong Classification Using Unsupervised Recording Segmentation 24

Multiple Instance Learning-Based Birdsong Classification Usi...

引用

1st international Workshop on Social Influence Analysis / 24th international Joint conference on Artificial Intelligence (IJCAI)

作者： Ruiz-Munoz, J. F. Orozco-Alzate, Mauricio Castellanos-Dominguez, G. Univ Nacl Colombia Sede Manizales Manizales Colombia

ISBN: (纸本)9781577357384

Traditional techniques for monitoring wildlife populations are temporally and spatially limited. Alternatively, in order to quickly and accurately extract information about the current state of the environment, tools for processing and recognition of acoustic signals can be used. In the past, a number of research studies on automatic classification of species through their vocalizations have been undertaken. In many of them, however, the segmentation applied in the preprocessing stage either implies human effort or is insufficiently described to be reproduced. Therefore, it might be unfeasible in real conditions. Particularly, this paper is focused on the extraction of local information as units -called instances-from audio recordings. The methodology for instance extraction consists in the segmentation carried out using image processing techniques on spectrograms and the estimation of a needed threshold by the Otsu's method. The multiple instance classification (MIC) approach is used for the recognition of the sound units. A public data set was used for the experiments. The proposed unsupervised segmentation method has a practical advantage over the compared supervised method, which requires the training from manually segmented spectrograms. Results show that there is no significant difference between the proposed method and its baseline. Therefore, it is shown that the proposed approach is feasible to design an automatic recognition system of recordings which only requires, as training information, labeled examples of audio recordings.

关键词： Audio recordings

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：