检索结果-内蒙古大学图书馆

6th Information and Communication Technologies Innovations 2014 conference, ICT 2014

作者： Jackowski, Konrad Jankowski, Dariusz Simić, Dragan Simić, Svetlana IT4Innovations VSB - Technical University of Ostrava 17. listopadu 15/2172 708 33 Ostrava - Poruba Czech Republic Department of Systems and Computer Networks Wroclaw University of Technology Wybrzeze Wyspiańskiego 27 50-370 Wroclaw Poland University of Novi Sad Trg Dositeja Obradovića 6 21000 Novi Sad Serbia University of Novi Sad Hajduk Veljkova 1-9 21000 Novi Sad Serbia

A valid diagnosis of migraine is a non-trivial decision problem. this is due to the fact that migraine can manifest wide range of varied symptoms. thus, designing a computer aided diagnosis system for that problem remains still a very interesting topic. In this paper we present an ensemble classifier system designed for headache diagnosis. We assumed that the system should make fast initial diagnosis based on an analysis of data collected in the questionnaire only. Such an assumption eliminated possibility of application of most classical classification algorithms as they could not obtain decent level of accuracy. therefore, we decided to apply an ensemble solution. Although it is clear that ensemble should consists of complementary classifiers, there is no guidance on how to choose ensemble size and ensure its diversity. thus, we applied two stages strategy. Firstly, large pool of elementary classifiers were prepared. Its diversity was ensured by selecting algorithms of different types, structures, and learning algorithms. Secondly, we determined optimal size of the ensemble and selected its constituents using exhaustive search approaches. Results of experiments, which were carried on dataset collected in University of Novi Sad, shows that proposed system significantly outperformed all classical methods. Additionally we present analysis of diversity and accuracy correlation for tested systems. © Springer international Publishing Switzerland 2015.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

A new method for ECG biometric recognition using a hierarchical scheme classifier

A new method for ECG biometric recognition using a hierarchi...

引用

IEEE international conference on Software Engineering and Service Sciences (ICSESS)

作者： Yue Zhang Youqun Shi Department of Automation Tsinghua University Shenzhen Guangdong China

ISBN: (纸本)9781479983544

In this paper, a new method for ECG biometric recognition using a hierarchical scheme classifier is presented. the integral process of the method is introduced, including preprocessing, feature extraction and classification. To achieve a better performance of proposed method, cross-validation is applied to determine the parameters in the classifier. As a result, proposed method offers considerably high recognition rates when tested on MIT-BIH NSRDB. the total heartbeat recognition rate is 97.98%, and window recognition rate and subject recognition rate are both 100%.

关键词： Electrocardiography Heart beat Feature extraction discrete cosine transforms Radio frequency Vegetation Accuracy

来源：评论

学校读者我要写书评

暂无评论

Cluster and discover services in the Smart Campus platform for online programming contests

Cluster and discover services in the Smart Campus platform f...

引用

international conference on Cognitive Infocommunications (CogInfoCom)

作者： Attila Adamko Tamás Kádek Lajos Kollár Mark Kosa Robert Tóth Faculty of Informatics University of Debrecen Debrecen Hungary

ISBN: (纸本)9781467381307

Nowadays we can see and feel the technological change around us. Most of the tools are extended with online functionality, new online collaboration environments are appearing and bring along wide range of data for collection. Following this shift with the appearance of cognitive infocommunication we established a framework and created a usage scenario as an online system for supporting programmers in our Smart Campus platform. When we created the platform, extendibility and adaptivity were the primary goals to stand for efficient data collection through crowdsourced collectors. this paper is the continuation of our work and describes our online programming contest environment where services are applied to help the users solving assessments and grading them. the collected data help us to discover hidden correspondences and fine tune our problem suggestion service. While we continuously collect data, the applied clustering algorithms could help us to understand the problems arriving through the students' learning path and along these we could achieve a much more fine-grained solution for our services.

关键词： Clustering algorithms Programming Informatics Databases Computer architecture Web services Collaboration

来源：评论

学校读者我要写书评

暂无评论

6th Asian Physics Symposium

引用

Journal of Physics: conference Series 2016年第1期739卷

Preface: the 6th Asian Physics Symposium 2015 (APS 2015) the 6th Asian Physics Symposium 2015 (APS 2015) is organized by the Physics Department, Faculty of mathematics and Natural Sciences, Bandung Institute of Technology, in collaboration with HFI (Indonesian Physical Society), PAPSI (Physics and applied Physics Society of Indonesia), HANI (Indonesian Nuclear Scientist Society), HRMI (Indonesian Material Research Society), HAGI (Indonesian Geophysicist Society) - West Java Chapter, and HFMBI (Indonesian Medical Physicist and Biophysicist Society). APS 2015 is aimed at providing a forum of scientific communication and interaction among distinguished scientists working in physics and its related fields. In this scientific event the latest research will be presented, and state-of-the-art developments in the field discussed, to help to guide our future research directions. It is also designed to offer the opportunity for young Indonesian scientists and students to make direct contacts with well-known scientists abroad and thereby foster the existing research collaborations and extend international research networking for the future. the scope of research presented and discussed in this symposium covers theoretical high energy physics, materials sciences and technology, biophysics and medical physics, nuclear science and engineering, earth and planetary sciences, computational physics, instrumentation and measurement, physics education, and interdisciplinary physics. the program of APS 2016 features 6 invited talks and 208 contributed oral presentations, which come from 7 different countries: Japan, South Korea, Singapore, Malaysia, Iraq, Ethiopia, and Indonesia. All papers have been reviewed after they are presented in this event. Selected papers are published in this Institute of Physics (IoP) conference Series. Finally, I would like to express my sincere appreciation to all of authors for their valuable contributions and also to the members of the committee for their

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real time textile defect detection using GLCM in DCT-based compressed images

Real time textile defect detection using GLCM in DCT-based c...

引用

international conference on Modeling, Simulation and applied Optimization (ICMSAO)

作者： Fitri Arnia Khairul Munadi Graduate Program in Electrical Engineering Syiah Kuala University Indonesia Department of Electrical Engineering Faculty of Engineering

this paper proposes a framework for textile defect detection on the basis of energy and contrast features of the gray-level co-occurrence matrix (GLCM). We calculate these features in DCT-based compressed image (DCTb-I), which was produced by using only a small number of DCT coefficients. the proposed detection approach complies with the Moving Picture Experts Group (MPEG) and Motion Joint Photographic Experts Group (MJPEG) video compression standards, which improves the defect detection efficiency, in terms of space and computational cost by replacing the frame grabbers with MPEG encoders and by only considering I-frames in the MPEG or specific frames in the MJPEG sequence. We determine (1) the detection accuracy of using DCTb-Is with various compression rates, and (2) the lowest DCTb-I rates that allow defect detection. the DCTb-Is are tiled into blocks from which the energy and contrast features are calculated. the highest energy and lowest contrast blocks are detected and located in the textile as defects. the proposed approach is suitable for real-time detection because, unlike common defect-detection approaches, prior feature extraction from reference images is not required. Simulation results suggest that holes, stains and drop stitches can be detected and located from DCTb-Is if the compression rate is greater than 25%.

关键词： Textiles discrete cosine transforms Image coding Transform coding Real-time systems Feature extraction Standards

来源：评论

学校读者我要写书评

暂无评论

Modeling and simulation of 2D-BinDCT based lifting scheme and its integration in a dynamically reconfigurable SOC

Modeling and simulation of 2D-BinDCT based lifting scheme an...

引用

international conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA)

作者： Ichraf Chatti Abdessalem Ben Abdelali Houda Ben Amor Abdellatif Mtibaa High Institute of Informatics and Mathematics of Monastir Tunisia Nationl Engineering School of Monatir University of Monastir Monastir Tunisia

ISBN: (纸本)9781467392358

the discrete Cosine Transform (DCT) is the most widely used transform for image compression. the DCT approximation or the Binary discrete Transform (BinDCT) [1] has shown to be a promising alternative to the DCT for its implementation simplicity, close performance and compatibility to the DCT. In this paper, we aim to present efficient VLSI architectures with a low BinDCT complexity implementation. We explore the design of a hardware BinDCT accelerator, the simulation and implementation of the different proposed architectures for a virtex6 FPGA device and its integration in a dynamically reconfigurable SOC. An IP interface was adopted to be able to integrate the proposed hardware accelerator in a SOC. the dynamic partial reconfiguration technique was applied to toggle between the original DCT and BinDCT versions depending on the application requirement. Complete hardware cores, which can be integrated directly in a SOC, was elaborated in order to accelerate the DCT or the BinDCT transform calculation.

关键词： discrete cosine transforms Registers Hardware Adders Computer architecture Multiplexing Simulation

来源：评论

学校读者我要写书评

暂无评论

Dolphin 1D: Improving automation of targeted metabolomics in multi-matrix datasets of1H-NMR spectra 1

引用

9th international conference on Practical Applications of Computational Biology and Bioinformatics, PACBB 2015

作者： Gómez, Josep Vinaixa, Maria Rodríguez, Miguel A. Salek, Reza M. Correig, Xavier Cañellas, Nicolau Metabolomics Platform IISPV Universitat Rovira I Virgili Campus Sescelades Carretera de Valls s/n Tarragona Catalonia43007 Spain CIBERDEM Spanish Biomedical Research Centre in Diabetes and Associated Metabolic Disorders Bonanova 69 6th Floor Barcelona Catalonia08017 Spain European Molecular Biology Laboratory Wellcome Trust Genome Campus Hinxton CambridgeCB10 1SD United Kingdom

ISBN: (数字)9783319197760

ISBN: (纸本)9783319197753

Nuclear magnetic resonance (NMR) is one of the main tools applied in the field ofmetabolomics. Extracting all the valuable information fromlarge datasets of1H-NMR spectra is a huge challenge for high throughput metabolomics analysis. the tools that currently exist to improve signal assignment and metabolite quantification do not have the versatility of allowing the quantification of unknown signals or choosing different quantification approaches in the same ***, graphical features and informative outputs are needed in order to be aware of the reliability of the final results in a field where position shifting, baseline masking and signal overlap may produce errors between samples. Here we present a software package called Dolphin 1D, which aim is to improve targeted metabolite analysis in large datasets of1H-NMR by combining user interactivity with automatic algorithms. Its performance has been tested on a multi-matrix set composed by total serum, urine, liver aqueous extracts and brain aqueous extracts of rat. Our strategy pretends to offer a useful solution for every kind of matrix, avoiding black-box processes and subjectivities user-user in automatic signal quantification. © Springer international Publishing Switzerland 2015.

关键词： Metabolites

来源：评论

学校读者我要写书评

暂无评论

A Patch-sized Wearable ECG/Respiration Recording Platform with DSP Capability

A Patch-sized Wearable ECG/Respiration Recording Platform wi...

引用

international conference on E-health Networking, Application & Services

作者： Jia-Wei Jhuang Hsi-Pin Ma Institute of Electronics Engineering National Tsing Hua University Department of Electrical Engineering National Tsing Hua University

ISBN: (纸本)9781467383264

In this paper, a healthcare platform is designed to establish a mobile telecare environment with the digital signal processing (DSP) ability. Although mobile health (mHealth) is not an innovative research topic, the improvements of wearable sensing technologies and today's mobile devices can make such systems more consummate and powerful than before. In the proposed platform, an electrocardiography (ECG)/respiration (RESP) prototype is developed to record single-lead ECG signal and thorax impedance variation caused by respiration of the users. the prototype weights about 8 g, and the size of prototype, which is 25×35×6 mm~3, is smaller than electrode. With easy-to-use user interface (UI), it could be applied in many kinds of platform such as mobile phone and tablet as a monitoring device. the recorded data can be uploaded to Dropbox automatically. the other thing that's worth mentioning is the ability to process digital data. With discrete wavelet transform (DWT) we can not only preprocess the biomedical signals for noise reduction but also detect P wave, QRS complex and T wave in real-time. By verifying with MIT-BIH QT database, the results show that the sensitivity of R peak achieves to 99.5%, P wave 97.87% and T wave 92.91%. Ignoring the data recorded from sudden death, the sensitivity of T wave can be up to 98.38%. Equipped with the developed DSP algorithms, the system can provide noise cancellation and motion artifact removal when moving, stretching and sleeping in user's daily life. According to the experiment results, the sensitivity of R wave still performs well even running on treadmill at speed of 15km/h. therefore, our design can be applied in various fields such as art, sport and medical care.

关键词： ECG Respiration P wave QRS complex T wave discrete wavelet transform

来源：评论

学校读者我要写书评

暂无评论

A COMPARISON OF MINIMUM CONSTRAINED WEIGHT AND FULLY STRESSED DESIGN PROBLEMS IN discrete CROSS-SECTION TYPE BAR STRUCTURES 11

A COMPARISON OF MINIMUM CONSTRAINED WEIGHT AND FULLY STRESSE...

引用

11th World Congress on Computational Mechanics (WCCM) / 5th European conference on Computational Mechanics (ECCM) / 6th European conference on Computational Fluid Dynamics (ECFD)

作者： Greiner, David Emperador, Jose M. Galvan, Blas Winter, Gabriel ULPGC Inst Univ Sistemas Inteligentes & Aplicac Numer I Las Palmas Gran Canaria 35017 Spain

ISBN: (纸本)9788494284472

the fully stressed design and the minimum constrained weight problems are frequently handled in the structural engineering field. Both are highly related problems and when applied in bar structures, even under certain circumstances they can share the design solution. In the case of the fully stressed design problem (FSD), see e.g. [1], we are handling an inverse problem [2] using the maximum admissible stresses of the bars of a structure as references, and aiming to be able to obtain the structure whose maximum stresses equal those considered references. In the case of the minimum constrained weight problem (MCW), see e.g. [3,4,5], the lightest structure (the one with lower cost in terms of raw material) which also does not violate certain constraints (which guarantee the right completion of the structural mission) is searched. Here, constraints in relation with limit stresses, limit displacements and limit slenderness are taken into account. When considering real engineering design of bar structures, where normalized cross section types belonging to national codes are required, the use of discrete variables in the search is needed. To solve the FSD and MCW problems is possible through the use of evolutionary algorithms [6]. they, as well as other metaheuristics, being population based search methods allow a global optimization without stagnating in local optima and they admit without constraints the use of discrete variables. their use in structural engineering, particularly in discrete bar structural optimization has been still widely researched in the recent years (see e.g. [7,8]). Even very recently, they also started to be considered as useful tools for extracting design knowledge in engineering problems, as in [9]. Nevertheless, the optimization process of both problems, FSD and MCW, can present noticeable differences, resulting in different number of fitness evaluations required to obtain the best solution. this difference in behaviour is shown in this work.

关键词： Structural design Frame optimization truss optimization evolutionary algorithms fully stressed design minimum constrained weight

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Pharmaceutical Modelling: A Comparison Between Synchronous and Asynchronous Cellular Automata 1

引用

10th international conference on Parallel Processing and applied mathematics (PPAM)

作者： Bezbradica, Marija Ruskin, Heather J. Crane, Martin Dublin City Univ Sch Comp Ctr Sci Res & Complex Syst Modelling Sci Sym Dublin 9 Ireland

ISBN: (数字)9783642551956

ISBN: (纸本)9783642551956

the field of pharmaceutical modelling has, in recent years, benefited from using probabilistic methods based on cellular automata, which seek to overcome some of the limitations of differential equation based models. By modelling discrete structural element interactions instead, these are able to provide data quality adequate for the early design phases in drug modelling. In relevant literature, both synchronous (CA) and asynchronous (ACA) types of automata have been used, without analysing their comparative impact on the model outputs. In this paper, we compare several variations of probabilistic CA and ACA update algorithms for building models of complex systems used in controlled drug delivery, analysing the advantages and disadvantages related to different modelling scenarios. Choosing the appropriate update mechanism, besides having an impact on the perceived realism of the simulation, also has practical benefits on the applicability of different model parallelisation algorithms and their performance when used in large-scale simulation contexts.

关键词： discrete systems Controlled drug delivery systems Complex modelling Parallel algorithms

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：