检索结果-内蒙古大学图书馆

international conference on Frontiers of Signal Processing (ICFSP)

作者： Tomasz Hachaj Marek R. Ogiela Institute of Computer Science Pedagogical University of Krakow Krakow Poland Cryptography and Cognitive Informatics Research Group AGH University of Science and Technology Krakow Poland

Head motions classification applied to virtual reality (VR) systems is still an open problem without a leading pattern recognition solution. In contrary to typical motion capture pattern recognition problem in this case we use only single inertial measurement unit (IMU) sensor. Head motions that we want to recognize in VR systems might be both natural head motions like nodding or shaking head (they might be used while interacting with VR avatars) and also elements of head-based navigation system or interface. the second type of actions is more challenging because it might contains actions that generate motion trajectories that do not appear in real-life, though they have to be possible to execute only by using a head. In this paper we propose a trajectory-based motion features description that is utilized by dynamic time warping (DTW) classificator. the training of the classificator requires using modified dynamic time warping barycenter averaging (DBA) heuristic algorithm which utilizes quaternions to represents rotations. the proposed pattern recognition system together with its evaluation on the set of head motions acquired by VR system is our original contribution. We have evaluated our method on dataset consisted of 8 types of motions performed by two persons (there are 160 motions samples). In leave-one-out evaluation we have obtained very good results: only 10% of one and 15% of another action has been incorrectly classified, while remaining 6 actions classes had been 100% correctly classified. Both dataset and implementation of proposed method can be downloaded, due to this our experiment can be reproduced.

关键词： Magnetic heads Trajectory Dynamics Quaternions Heuristic algorithms pattern recognition Glass

来源：评论

学校读者我要写书评

暂无评论

Wrist Hand Vein recognition Using Local Line Binary pattern (LLBP)

Wrist Hand Vein Recognition Using Local Line Binary Pattern ...

引用

international conference on Science and Technology-Computer (ICST)

作者： Aspian Achban Hanung Adi Nugroho Prapto Nugroho Department of Electrical and Information Engineering Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (数字)9781728123691

ISBN: (纸本)9781728123707

the biometrics recognition system is now widely applied in various fields such as security systems and employee attendance. However, there are some weaknesses that the recognition system has, so that new biometrics recognition objects are developed, namely recognition based on the wrist hand vein image. Some feature extraction methods that have been used in vascular-based recognition systems such as Dense-LBP, RBF Network, Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM) and Hessian-based result in poor accuracy, so that this study tries to apply the Local Line Binary pattern (LLBP) method in the feature extraction stage because based on previous research, the Local Line Binary pattern (LLBP) method is able to process the image at the stage feature extraction very well. the results of individual recognition experiments using the LLBP method were carried out using 50 individual data from datasets taken directly using infrared cameras, resulting an accuracy of 96.50%. Accuracy obtained is influenced by the quality of the dataset used and in this study, it shows that the proposed LLBP method has good capability in individual recognition systems.

关键词： Veins Feature extraction Wrist pattern recognition Image recognition Wiener filters Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Uncover Product Review patterns via Weighted Motifs 5

Uncover Product Review Patterns via Weighted Motifs

引用

5th international conference on Systems and Informatics (ICSAI)

作者： Li, Jiandun Lv, Pin Ji, Chunlei Shanghai Dianji Univ Sch Elect & Informat Shanghai 201306 Peoples R China

ISBN: (纸本)9781728101200

In today's e-commercial websites, product reviews written by genuine users are commonly seen, which play a crucial role as customer feedbacks and planting seeds to trigger much more transactions. However, motivated by profits, fake reviews crafted by spammers are inevitable to promote or demote product reputations whereas misguiding potential buyers to make bad decisions. Until recently, the problem how to distinguish whether a review is fraudulent or a reviewer is a spammer has long been studied, but the question of general review pattern mining is still open. In this paper, we model online product review systems into bipartite networks and adopt a network technique, called the weighted motif to uncover underlying reviewing patterns. Experiments on Amazon's review dataset show that, our system is feasible and effective.

关键词： online product review color motif review spam pattern recognition

来源：评论

学校读者我要写书评

暂无评论

pattern recognition for water flooded layer based on ensemble classifier 5

Pattern recognition for water flooded layer based on ensembl...

引用

5th international conference on Control, Decision and Information Technologies (CoDIT)

作者： Geng, ZhiQiang Hu, Xuan Zhu, QunXiong Han, YongMing Xu, Yuan He, Yanlin Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China Minist Educ China Engn Res Ctr Intelligent PSE Beijing 100029 Peoples R China

ISBN: (纸本)9781538650653

In order to establish an effective water flooded layer recognition model to deal with complex chromatogram data and correctly identify the water flooded layer in the oil and gas reservoirs, this paper proposes a modeling approach based on ensemble classifier. First, the proposed approach utilizes the function fitting method to obtain the effective chromatogram characteristic information (CCIs). Moreover, in order to transform the sparse classification problem into a general classification problem, the synthetic minority oversampling technique (SMOTE) algorithm is used to process the unbalanced training sample as a general training sample. Compared with the traditional classification approach, the robustness and effectiveness of the ensemble classifier model composed of the model-free classification (MFBC) algorithm, the k-nearest neighbor (KNN) algorithm and the support vector machine (SVM) algorithm were validated through the standard data source from the UCI (University of California at Irvine) repository. Finally, the proposed model is validated through an application in a complex oil and gas recognition system of China petroleum industry. the CCIs and the prediction results are obtained to provide more reliable water flooded layer information, guide the process of reservoir exploration and development and improve the oil development efficiency.

关键词： ensemble classifier model-free classification algorithm k-nearest neighbor support vector machine synthetic minority over-sampling technique water flooded layer identification

来源：评论

学校读者我要写书评

暂无评论

Environmental and Geo-Spatial Data Analytics (EnGeoData' 2018) 5

Environmental and Geo-Spatial Data Analytics (EnGeoData' 201...

引用

5th IEEE international conference on Data Science and Advanced Analytics (IEEE DSAA)

作者： Teisseire, Maguelonne Roche, Mathieu Inkpen, Diana Univ Montpellier AgroParisTech CNRS TETISIrsteaCirad Montpellier France Univ Ottawa Ottawa ON Canada

ISBN: (纸本)9781538650905

the special session "Environmental and Geospatial Data Analytics" (EnGeoData) brings together researchers interested by pre-and post-processing of environmental data, geographical information retrieval, spatial data mining and spatial data warehousing, knowledge discovery use-cases dedicated to environmental data, spatial text mining, spatial ontology, spatial recommendations and personalization, visual analytics for geospatial data, and dedicated applications. this year, the special session EnGeoData' 2018 of the 5th IEEE international conference on Data Science and Advanced Analytics (DSAA' 2018) contains a collection of four papers and provides high-quality research covering part of the challenges of Spatio-Temporal Data Science, from a theoretical or experimental point of view.

关键词： Geographic information systems Data mining Data processing Data visualization Machine learning Learning systems Knowledge based systems pattern recognition Digital systems Information systems Database systems Remote sensing Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Time Series Prediction and pattern recognition of Fault Decomposition Gas for High Voltage Composite Electrical Appliances Based on Grey System OBGM(1,N) Model

Time Series Prediction and Pattern Recognition of Fault Deco...

引用

IEEE international conference on Computer and Communications

作者： Zhang Shiling Wang Jianchao Se Grid Chongqing Eecric Power Cony Chongqing Eecric Power Reserch InsiueSe Grid Chongqing Eecric Power Cony Chongqing Eecric Power Reserch Insiue

ISBN: (数字)9781728147437

ISBN: (纸本)9781728147444

the GIL/GIS is widely used in the power system. the application of grey system to forecast and analyze the time series of gas decomposition and fault pattern recognition has good engineering value for its operation condition monitoring. Based on the programming of MATLAB software environment, time series prediction model based on grey system OBGM (1,N) is realized. Based on model, grey system time series analysis algorithm is applied to predict the time-varying sequence of the volume fraction of SF6 gas decomposition products and the characteristics of the partial discharge Atlas of the high-voltage combined electrical equipment GIL/GIS in fault state. Parametric time series, grey system is further applied to data mining and analysis of association rules of time series state change, and the time series set is applied to cluster analysis of typical fault types of high-voltage GIL/GIS power equipment. the grey time series prediction and grey relational clustering analysis of small sample test data can be carried out by using the grey system to analyze large data of high voltage GIL/GIS power equipment condition assessment. the multi-dimensional and the grey system information fusion technology proposed in this paper is especially suitable for the application of the small sample and the poor data in the high-voltage GIL/GIS power equipment operation condition detection technology. the time series prediction and the pattern recognition technology of the fault decomposition gas based on the grey system OBGM (1, N) model proposed can provide some technical support for the operation and maintenance of high voltage combinations. the characteristic parameters of partial discharge pattern and grey relational clustering analysis have the good engineering and the theoretical value.

关键词： Partial discharges Predictive models Discharges (electric) Time series analysis Mathematical model Monitoring Gas insulation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms for Complex pattern recognition in Ultrasonic Sensors Arrays 5th

Deep Learning Algorithms for Complex Pattern Recognition in ...

引用

5th international conference on Machine Learning, Optimization, and Data Science (LOD)

作者： Mazzia, Vittorio Tartaglia, Angelo Chiaberge, Marcello Gandini, Dario Politecn Torino Dept Elect & Telecommun Engn DET Turin Italy PIC4SeR Politecn Interdept Ctr Serv Robot Turin Italy SmartData PoliTo Big Data & Data Sci Lab Turin Italy

ISBN: (纸本)9783030375997;9783030375980

Nowadays, applications of ultrasonic proximity sensors are limited to a post-processing of the acquired signals with a pipeline of filters and threshold comparators. this article proposes two different and novel processing methodologies, based on machine learning algorithms, that outperform classical approaches. Indeed, noisy signals and presence of thin or soundproofing objects are likely sources of false positive detections that can make traditional approaches useless and unreliable. In order to take advantage of correlations among the data, multiple parallel signals, coming from a cluster of ultrasonic sensors, have been exploited, producing a number of different features that allowed to achieve more accurate and precise predictions for object detection. Firstly, model-based learning as well as instance-based learning systems have been investigated for an independent time correlation analysis of the different signals. Particular attention has been given to the training and testing of the deep fully connected network that showed, since the beginning, more promising results. In the second part, a recurrent neural network, based on long short term memory cells, has been devised. As a result of its intrinsic nature, time correlations between successive samples are not more overlooked, further improving the overall prediction capability of the system. Finally, cutting edge training methodologies and strategies to find the different hyperparameters have been adopted in order to obtain the best results and performance from the available data.

关键词： Deep learning Ultrasound sensors Industrial security

来源：评论

学校读者我要写书评

暂无评论

LBP vs SVD for Color Images Feature Extraction 5

LBP vs SVD for Color Images Feature Extraction

引用

5th IEEE international conference on Smart Instrumentation, Measurement and Application (ICSIMA)

作者： Faridah, Y. Nasir, Haida Nikolay, S. Kushsairy, A. K. Khan, Sheroz Univ Kuala Lumpur Malaysian Inst Informat Technol 1016 Jalan Sultan Ismail Kuala Lumpur 50250 Malaysia Int Islamic Univ Malaysia Batu 8Jalan Sg Pusu Gombak 53100 Selangor Malaysia Technion Israel Inst Technol Haifa Israel

ISBN: (纸本)9781538662885

Images are important element in our daily life. We use images to identify things or associate them with others that become important in decision making or correlate with other object for identification purpose. Feature extraction need to be applied to images for them to be useful for the mentioned purpose. By definition, feature extraction is the transformation of input data into a set of features, normally distinctive properties of input patterns that differentiate between many input of patterns. It is also the process to represent raw image (important criteria or parts of) to help in decision making such as pattern detection, classification, recognition or image processing or machine learning. the process of extracting information from images is one of the important elements in authenticating process of biometric system. Many techniques for extracting features have been emerging in the current research. LBP (Local Binary pattern) has been a popular technique in biometric systems used for feature extraction. LBP is a texture feature ex fraction method which produce clearer image result. Another favorite technique known as SVD (Single Value Decomposition) has been selected, discussed and compared with the latter. A sample of still color images were tested for both methods and the results are compared and discussed further in here. this paper concentrates on these two techniques for image processing in a biometric system.

关键词： Algorithm LBP (Local Binary pattern) SVD (Single Value Decomposition) Feature Extraction Texture

来源：评论

学校读者我要写书评

暂无评论

TR-LBP: A modified Local Binary Pattem-based technique for 3D face recognition 5

TR-LBP: A modified Local Binary Pattem-based technique for 3...

引用

5th international conference on Emerging Applications of Information Technology, EAIT 2018

作者： Dutta, Koushik Bhattacharjee, Debotosh Nasipuri, Mita Department of Computer Science and Engineering Jadavpur University Kolkata India

ISBN: (纸本)9781538637197

In this paper, a novel technique has been introduced for 3D face recognition based on the modified local binary pattern extracted from a 3D range image. the new LBP technique is applied to shape index of 3D facial surface data. the novelty of this technique illustrates that a modified local binary pattern termed as Triangular Local Binary pattern (TR-LBP), which gives new texture representation of 3D facial surface for improvement of facial texture classification performance compared to other variants of LBP. In this paper, authors have also described the TR-LBP technique by extending it on 2D intensity image of same subjects. Entropy-based feature extraction is used for feature vector creation. Further, KNN is used for calculating classification accuracy on two popular 3D face databases: Frav3D and Bosphorous. Here the classifications results are compared with other two existing LBP techniques applied to range images and shape index (SI) form of range image respectively. © 2018 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Optimal clustering with missing values

引用

BMC bioinformatics 2019年第12期20卷 321-321页

作者： Boluki, Shahin Dadaneh, Siamak Zamani Qian, Xiaoning Dougherty, Edward R. Texas A&M Univ Dept Elect & Comp Engn MS3128 TAMU College Stn TX 77843 USA TEES AgriLife Ctr Bioinformat & Genom Syst Engn College Stn TX 77843 USA

BackgroundMissing values frequently arise in modern biomedical studies due to various reasons, including missing tests or complex profiling technologies for different omics measurements. Missing values can complicate the application of clustering algorithms, whose goals are to group points based on some similarity criterion. A common practice for dealing with missing values in the context of clustering is to first impute the missing values, and then apply the clustering algorithm on the completed *** consider missing values in the context of optimal clustering, which finds an optimal clustering operator with reference to an underlying random labeled point process (RLPP). We show how the missing-value problem fits neatly into the overall framework of optimal clustering by incorporating the missing value mechanism into the random labeled point process and then marginalizing out the missing-value process. In particular, we demonstrate the proposed framework for the Gaussian model with arbitrary covariance structures. Comprehensive experimental studies on both synthetic and real-world RNA-seq data show the superior performance of the proposed optimal clustering with missing values when compared to various clustering *** clustering with missing values obviates the need for imputation-based pre-processing of the data, while at the same time possessing smaller clustering errors.

关键词： Clustering Missing data Optimal design pattern recognition

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：