检索结果-内蒙古大学图书馆

Optimistic Multi-granulation Rough Set-Based Classification for Neonatal Jaundice Diagnosis 6th

6th international workshop on Soft Computing Applications (SOFA)

作者： Kumar, S. Senthil Inbarani, H. Hannah Azar, Ahmad Taher Own, Hala S. Balas, Valentina Emilia Olariu, Teodora Periyar Univ Dept Comp Sci Salem 636011 India Benha Univ Fac Comp & Informat Banha Egypt Natl Res Inst Astron & Geophys Helwan Egypt Aurel Vlaicu Univ Arad Arad Romania Vasile Goldis West Univ Arad Satu Mare Romania

ISBN: (纸本)9783319182964

Neonatal jaundice diagnosis has been approached by various machine learning techniques. pattern recognition algorithms are capable of improving the quality of prediction, early diagnosis of diseases, and disease classification. pattern recognition algorithm results in Neonatal jaundice diagnosis or description of jaundice treatment by the medical specialist. This research focuses on applying rough set-based data mining techniques for Neonatal jaundice data to discover locally frequent identification of jaundice diseases. This work applies Optimistic Multi-granulation rough set model (OMGRS) for Neonatal jaundice data classification. Multi-granulation rough set provides efficient results than single granulation rough set model and soft rough set-based classifier model. The performance of the proposed Multi-granulation rough set-based classification is compared with other Naive bayes, Back Propagation Neural Networks (BPN), and Kth Nearest Neighbor (KNN) approaches using various classification measures.

关键词： Rough set Optimistic multi-granulation rough set Neonatal jaundice data Classification Comparative analysis of classification measures

来源：评论

学校读者我要写书评

暂无评论

Effect of Multi-condition Training and Speech Enhancement Methods on Spoofing Detection 1

Effect of Multi-condition Training and Speech Enhancement Me...

引用

1st international workshop on Sensing, Processing and learning for Intelligent machines (SPLINE)

作者： Yu, Hong Sarkar, Achintya Thomsen, Dennis Alexander Lehmann Tan, Zheng-Hua Ma, Zhanyu Guo, Jun Beijing Univ Posts & Telecommun Pattern Recognit & Intelligent Syst Lab Beijing Peoples R China Aalborg Univ Dept Elect Syst Aalborg Denmark

ISBN: (纸本)9781467389174

Many researchers have demonstrated the good performance of spoofing detection systems under clean training and testing conditions. However, it is well known that the performance of speaker and speech recognition systems significantly degrades in noisy conditions. Therefore, it is of great interest to investigate the effect of noise on the performance of spoofing detection systems. In this paper, we investigate a multi-conditional training method where spoofing detection models are trained with a mix of clean and noisy data. In addition, we study the effect of different noise types as well as speech enhancement methods on a state-of-the-art spoofing detection system based on the dynamic linear frequency cepstral coefficients (LFCC) feature and a Gaussian mixture model maximum-likelihood (GMM-ML) classifier. In the experiment part we consider three additive noise types, Cantine, Babble and white Gaussian at different signal-to-noise ratios, and two mainstream speech enhancement methods, Wiener filtering and minimum mean-square error. The experimental results show that enhancement methods are not suitable for the spoofing detection task, as the spoofing detection accuracy will be reduced after speech enhancement. Multi-conditional training, however, shows potential at reducing error rates for spoofing detection.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

2016 23rd Iranian Conference on Biomedical Engineering and 2016 1st international Iranian Conference on Biomedical Engineering, ICBME 2016

2016 23rd Iranian Conference on Biomedical Engineering and 2...

引用

23rd Iranian Conference on Biomedical Engineering and 2016 1st international Iranian Conference on Biomedical Engineering, ICBME 2016

ISBN: (纸本)9781509034529

The proceedings contain 66 papers. The topics discussed include: performance evaluation of dopamine electrochemical sensor in presence of uric acid, ascorbic acid and serotonin as interferer agents;an instrumented electromechanical apparatus for mechanical characterization of human hand palm soft tissue;the effects of pre-indenting load on mechanical response of bovine meniscus;structural connectivity of temporal lobe structures detects temporal lobe epilepsy;classification of Alzheimer's disease and mild cognitive impairment: machine learning applied to rsfMRI brain graphs;network based analysis of cognitive related resting state networks in Alzheimer's disease;improvement of flexible design matrix in sparse Bayesian learning for multi task fMRI data analysis;brain computer interface design and implementation to identify overt and covert speech;effective connectivity measuring of ERP signals in recognition memory process by generalized partial directed coherence;analysis of brain connectivity patterns in autistic children during watching emotional faces;spatial filter bank based on probabilistic common spatial pattern in motor imagery BCI systems;a low cost, efficient method for chip fabrication in cell analysis;a novel microfluidic design for blood plasma separation;towards smart ehealth in the ultra large-scale Internet of Things era;estimation of brain tumour volume using expanded computed tomography scan images;retinal optic disk segmentation and analysis in fundus images using DBSCAN clustering algorithm;and automatic zone identification in blood smear images using optimal set of features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Looking for an MR? Try METWiki Today

Looking for an MR? Try METWiki Today

引用

IEEE/ACM international workshop on Metamorphic Testing (MET)

作者： Xiaoyuan Xie Jiahao Li Chen Wang Tsong Yueh Chen State Key Lab of Software Engineering Computer School Wuhan University China Department of Computer Science and Software Engineering Swinburne University of Technology Australia

ISBN: (纸本)9781509001309

Metamorphic Testing (MT) has been demonstrated to successfully alleviate oracle problems in many areas, including machine learning, compilers, bioinformatics, etc. However, given a new MT task, it is still very challenging to identify enough Metamorphic Relations (MRs) which are key components of MT. Aiming at this problem, we revisited previous MT applications and realized that they could form a very valuable database. Currently there is a lack of efficient link to get testers access these historical data. Therefore, in this paper, we propose to build METWiki, an MR repository, for collection and retrieval of these MRs. By providing exploration and search facilities, testers can find their desired MRs for reuse, reference, or inference. We also illustrate three sample usages of METWiki, which show important illuminations on how MRs can be obtained in practice.

关键词： Testing Software data mining Mathematics Software engineering Bioinformatics Libraries

来源：评论

学校读者我要写书评

暂无评论

Sequential pattern mining on multimedia data 1

Sequential pattern mining on multimedia data

引用

1st international workshop on Advanced Analytics and learning on Temporal data, AALTD 2015 - workshop co-located with The European Conference on machine learning and Principles and Practice of Knowledge Discovery in databases, ECML PKDD 2015

作者： Hardy, Corentin Amsaleg, Laurent Gravier, Guillaume Malinowski, Simon Reniniou IRISA Inria Rennes France

Analyzing multimedia data is a challenging problem due to the quantity and complexity of such data. mining for frequently recurring patterns is a task often ran to help discovering the underlying structure hidden in the data. In this article, we propose audio data symbolization and sequential pattern mining methods to extract patterns from audio streams. Experiments show that this task is hard and that the symbolization is a critical step for extracting relevant audio patterns. Copyright © 2015 for this paper by its authors. Copying permitted for private and academic purposes. Copyright © 2015 for This Paper by Its Authors.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Prediction of asynchronous dimensional emotion ratings from audiovisual and physiological data

引用

pattern recognition LETTERS 2015年第Nov.15期66卷 22-30页

作者： Ringeval, Fabien Eyben, Florian Kroupi, Eleni Yuce, Anil Thiran, Jean-Philippe Ebrahimi, Touradj Lalanne, Denis Schueller, Bjoern Tech Univ Munich Machine Intelligence & Signal Proc Grp MMK D-80333 Munich Germany Ecole Polytech Fed Lausanne Multimedia Signal Proc Grp CH-1015 Lausanne Switzerland Ecole Polytech Fed Lausanne Signal Proc Lab LTS5 CH-1015 Lausanne Switzerland Univ Fribourg Document Image & Voice Anal CH-1700 Fribourg Switzerland Univ London Imperial Coll Sci Technol & Med Dept Comp Machine Learning Grp London SW7 2AZ England Univ Passau Chair Complex Syst Engn D-94032 Passau Germany

Automatic emotion recognition systems based on supervised machine learning require reliable annotation of affective behaviours to build useful models. Whereas the dimensional approach is getting more and more popular for rating: affective behaviours in continuous time domains, e.g., arousal and valence, methodologies to take into account reaction lags of the human raters are still rare. We therefore investigate the relevance of using machine learning algorithms able to integrate contextual information in the modelling, like long short-term memory recurrent neural networks do, to automatically predict emotion from several (asynchronous) raters in continuous time domains, i.e., arousal and valence. Evaluations are performed on the recently proposed RECOLA multimodal database (27 subjects, 5 min of data and six raters for each), which includes audio, video, and physiological (ECG, EDA) data. In fact, studies uniting audiovisual and physiological information are still very rare. Features are extracted with various window sizes for each modality and performance for the automatic emotion prediction is compared for both different architectures of neural networks and fusion approaches (feature-level/decision-level). The results show that: (i) LstM network can deal with (asynchronous) dependencies found between continuous ratings of emotion with video data, (ii) the prediction of the emotional valence requires longer analysis window than for arousal and (iii) a decision-level fusion leads to better performance than a feature-level fusion. The best performance (concordance correlation coefficient) for the multimodal emotion prediction is 0.804 for arousal and 0.528 for valence. (C) 2014 Elsevier B.V. All rights reseived.

关键词： Context-learning long short-term memory recurrent neural networks Audiovisual and physiological data Continuous affect analysis Multi-task learning Multitime resolution features extraction Multimodal fusion

来源：评论

学校读者我要写书评

暂无评论

Extracting human attributes using a convolutional neural network approach

引用

pattern recognition LETTERS 2015年 68卷 250-259页

作者： Perlin, Hugo Alberto Lopes, Heitor Silverio Parana Fed Inst Parana Paranagua PR Brazil Univ Tecnol Fed Parana Curitiba Parana Brazil

Extracting high level information from digital images and videos is a hard problem frequently faced by the computer vision and machine learning communities. Modern surveillance systems can monitor people, cars or objects by using computer vision methods. The objective of this work is to propose a method for identifying soft biometrics, in the form of clothing and gender, from images containing people, as a previous step for further identifying people themselves. We propose a solution to this classification problem using a Convolutional Neural Network, working as an all-in-one feature extractor and classifier. This method allows the development of a high-level end-to-end clothing/gender classifier. Experiments were done comparing the CNN with hand-designed classifiers. Also, two different operating modes of CNN are proposed and coin pared each other. The results obtained were very promising, showing that is possible to extract soft-biometrics attributes using an end-to-end CNN classifier. The proposed method achieved a good generalization capability, classifying the three different attributes with good accuracy. This suggests the possibility to search images using soft biometrics as search terms. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Computer vision machine learning Soft-biometrics Convolutional Neural Network Gender recognition Clothes parsing

来源：评论

学校读者我要写书评

暂无评论

Regularized local metric learning for person re-identification

引用

pattern recognition LETTERS 2015年 68卷 288-296页

作者： Liong, Venice Erin Lu, Jiwen Ge, Yongxin Adv Digital Sci Ctr Singapore 138632 Singapore Minist Educ Key Lab Dependable Serv Comp Cyber Phys Soc Chongqing 430044 Peoples R China Chongqing Univ Sch Software Engn Chongqing 430044 Peoples R China

In this paper, we propose a regularized local metric learning (RLML) method for person re-identification. Unlike existing metric learning based person re-identification methods which learn a single distance metric to measure the similarity of each pair of human body images, our method combines global and local metrics to represent the within-class and between-class variances. By doing so, we utilize the local distribution of the training data to avoid the overfitting problem. In addition, to address the lacking of training samples in most person re-identification systems, our method also regulates the covariance matrices in a parametric manner, so that discriminative information can be better exploited. Experimental results on four widely used datasets demonstrate the advantage of our proposed RLML over both existing metric learning and state-of-the-art person re-identification methods. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Person re-identitication Metric learning Regularization

来源：评论

学校读者我要写书评

暂无评论

On the use of Kinect depth data for identity, gender and ethnicity classification from facial images

引用

pattern recognition LETTERS 2015年第Part2期68卷 270-277页

作者： Boutellaa, Elhocine Hadid, Abdenour Bengherabi, Messaoud Ait-Aoudia, Samy Ctr Dev Technol Avancees Algiers Algeria Ecole Natl Super Informat Algiers Algeria Univ Oulu Ctr Machine Vis Res SF-90100 Oulu Finland

This article explores the usefulness of the depth images provided by the current Microsoft Kinect sensors in different face analysis tasks including identity, gender and ethnicity. Four local feature extraction methods (LBP, LPQ, HOG and BSIF) are investigated for both face texture and shape description. Extensive experiments on three publicly available Kinect face databases are reported. The experimental analysis yields into interesting findings. Furthermore, a comprehensive review of the literature on the use of Kinect depth data in face analysis is provided along with the description of the available databases. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Face analysis Depth images Microsoft Kinect Soft biometrics

来源：评论

学校读者我要写书评

暂无评论

CEUR workshop Proceedings

CEUR Workshop Proceedings

引用

The proceedings contain 17 papers. The topics discussed include: capturing time-structures in earth observation data with Gaussian processes;monitoring short term changes of malaria incidence in Uganda with Gaussian processes;bag-of-temporal-sift-words for time series classification;an exploratory analysis of multiple multivariate time series;symbolic representation of time series: a hierarchical coclustering formalization;temporal and frequential metric learning for time series;estimating dynamic graphical models from multivariate time-series data;sequential pattern mining on multimedia data;time series classification in dissimilarity spaces;temporal density extrapolation;fuzzy clustering of series using quantile autocovariances;and causality on longitudinal data: stable specification search in constrained structural equation modeling.

关键词：

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：