检索结果-内蒙古大学图书馆

ieee symposium on computational intelligence in Healthcare and e-health

作者： Gelzinis, Adas Verikas, Antanas Vaiciukynas, Evaldas Bacauskiene, Marija Minelga, Jonas Hallander, Magnus Uloza, Virgilijus Padervinskis, Evaldas Kaunas Univ Technol Dept Elect Power Syst Kaunas Lithuania Halmstad Univ IS Lab Halmstad Sweden Lithuanian Univ Hlth Sci Dept Otolaryngol Kaunas Lithuania

ISBN: (纸本)9781479953752

Exploration of various features and different structures of data dependent random forests in screening for laryngeal disorders through analysis of sustained phonation recorded by acoustic and contact microphones is the main objective of this study. To obtain a versatile characterization of voice samples, 14 different sets of features were extracted and used to build an accurate classifier to distinguish between normal and pathological cases. We proposed a new, data dependent random forest-based, way to combine information available from the different feature sets. An approach to exploring data and decisions made by a random forest was also presented. Experimental investigations using a mixed gender database of 273 subjects have shown that the Perceptual linear predictive cepstral coefficients ( PLPCC) was the best feature set for both microphones. However, the LP-coefficients and LPCT-coefficients feature sets exhibited good performance in the acoustic microphone case only. Models designed using the acoustic microphone data significantly outperformed the ones built using data recorded by the contact microphone. The contact microphone did not bring any additional information useful for classification. The proposed data dependent random forest significantly outperformed traditional designs.

关键词： acoustic signal processing bioacoustics data recording decision making feature extraction medical disorders medical signal processing microphones signal classification LPCT-coefficients feature sets accurate classifier acoustic microphones contact microphones data dependent random forest structures feature exploration feature sets laryngeal disorder screening mixed gender database pathological cases perceptual linear predictive cepstral coefficients sustained phonation recording Accuracy Acoustics Feature extraction Microphones Pathology Radio frequency Vegetation

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Transient Errors on Systolic Arrays 26

A Comprehensive Analysis of Transient Errors on Systolic Arr...

引用

26th International symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS)

作者： Vacca, Eleonora Azimi, Sarah Sterpone, Luca Politecn Torino Dipartimento Automat & Informat Turin Italy

ISBN: (纸本)9798350332773

In recent years, the growth of interest in adopting deep neural network techniques across various domains led to new architectures for supporting the required computational effort. Tensor processing Units (TPUs), which are based on a systolic array matrix multiplication unit (MMU), became widely popular thanks to their specific structure suitable for Artificial intelligence. This work investigates Single Event Transient (SET) effects on TPU's MMU. The analysis demonstrates the impact of SETs on the functionality of MMU when executing digital image processing filtering. The experimental results identify the static and dynamic SET sensitivity of TPU and depict meaningful information on the data dependency of the filters' kernel values.

关键词： AI Hardware Accelerator Single Event Transient Soft Errors Tensor processing Unit

来源：评论

学校读者我要写书评

暂无评论

IMPATIENT MRI: ILLINOIS MASSIVELY PARALLEL ACCELERATION TOOLKIT FOR image RECONSTRUCTION WITH ENHANCED THROUGHPUT IN MRI

IMPATIENT MRI: ILLINOIS MASSIVELY PARALLEL ACCELERATION TOOL...

引用

8th ieee International symposium on Biomedical Imaging (ISBI) - From Nano to Macro

作者： Wu, Xiao-Long Gai, Jiading Lam, Fan Fu, Maojing Haldar, Justin P. Zhuo, Yue Liang, Zhi-Pei Hwu, Wen-Mei Sutton, Bradley P. Univ Illinois Dept Elect & Comp Engn 1406 W Green St Urbana IL 61801 USA Univ Illinois Beckman Inst Urbana IL 61801 USA Univ Illinois Dept Bioengn Urbana IL 61801 USA

ISBN: (纸本)9781424441280

Much progress has been made in the design of efficient acquisition trajectories for high spatial and temporal resolution in magnetic resonance imaging (MRI). Additionally, significant developments in image reconstruction have enabled the reconstruction of reasonable images from massively undersampled or noisy data that is corrupted by a variety of physical effects, including magnetic field inhomogeneity. Translation of these techniques into clinical imaging has been impeded by the need for expertise and computational facilities to realize the potential of these methods. We present the Illinois Massively Parallel Acceleration Toolkit for image reconstruction with ENhanced Throughput in MRI (IMPATIENT MRI), a reconstruction utility that enables advanced techniques within clinically relevant computation times by using the computational power available in low-cost graphics processing cards.

关键词： magnetic resonance imaging graphics processing cards field inhomogeneity image regularization

来源：评论

学校读者我要写书评

暂无评论

SEGMENTING NEURONAL STRUCTURE IN 3D OPTICAL MICROSCOPE imageS VIA KNOWLEDGE DISTILLATION WITH TEACHER-STUDENT NETWORK 16

SEGMENTING NEURONAL STRUCTURE IN 3D OPTICAL MICROSCOPE IMAGE...

引用

16th ieee International symposium on Biomedical Imaging (ISBI)

作者： Wang, Heng Zhang, Donghao Song, Yang Liu, Siqi Wang, Yue Feng, Dagan Peng, Hanchuan Cai, Weidong Univ Sydney Sch Informat Technol Sydney NSW Australia Univ New South Wales Sch Comp Sci & Engn Sydney NSW Australia Siemens Healthineers Digital Technol & Innovat Digital Serv Princeton NJ USA Virginia Polytech Inst & State Univ Bradley Dept Elect & Comp Engn Blacksburg VA 24061 USA Allen Inst Brain Sci Seattle WA USA

ISBN: (纸本)9781538636411

Three-dimensional (3D) volumetric neural image segmentation is crucial to reconstructing accurate neuron structures. However, due to the structural complexity of neurons and the diverse imaging qualities of the microscopes, it is challenging to achieve both accuracy and efficiency. In this paper, we propose a teacher-student learning framework for fast neuron segmentation. The segmentation inference is performed using a light-weighted student network which benefits from knowledge distillation of a teacher network with a higher capacity. Evaluated on the Janelia dataset from the BigNeuron project, our proposed framework achieves competitive performance for segmentation accuracy while reducing the computational cost to facilitate large-scale processing.

关键词： Teacher-student Network Knowledge Distillation Neuronal image Segmentation BigNeuron

来源：评论

学校读者我要写书评

暂无评论

3D surface reconstruction of entomological specimens from uniform Multi-view image datasets 21

3D surface reconstruction of entomological specimens from un...

引用

21st symposium on signal processing, images and Artificial Vision (STSIVA)

作者： Sosa, German D. Rodriguez, Sebastian Guaje, Javier Victorino, Jorge Mejia, Manuel Fuentes, Luz Stella Ramirez, Angelica Franco, Hugo Univ Cent Bogota Colombia Univ Nacl Colombia Bogota Colombia Univ Jorge Tadeo Lozano Bogota Colombia

ISBN: (纸本)9781509037971

Modeling of 3D objects and scenes have become a common tool in different applied fields from simulationbased design in high-end engineering applications (aviation, civil structures, engine components, etc.) to entertainment (computer-based animation, video-game development, etc.). In Biology and related fields, 3D object modeling and reconstruction provide valuable tools to support the visualization, comparison and even morphometric analysis in both academical and applied tasks. Such computational tools, usually implemented as webbased virtual reality applications, significantly reduce the manipulation of fragile samples, preventing their damage and, even, their complete loss. On the other hand, they allow to take the morphological properties of physical specimens to the digital domain, giving support to common entomology tasks such as characterization, morphological taxonomy and teaching. This paper addresses the problem of producing reliable 3D point clouds from the surface of entomological specimens, based on a proved approach for multiview 3D reconstruction from high resolution pictures. Given the traditional issues of macro-photography for small sized objects (i.e. short depth of field, presence of subtle and complex structures, etc.), a pre-processing protocol, based on focus stacking, supported the generation of enhanced views obtained by an acquisition device specifically designed for this work. The proposed approach has been tested on a sample of six representative subjects from the Entomological Collection of the Centro de Biosistemas, Universidad Jorge Tadeo Lozano (Colombia). The resulting point clouds exhibit an overall good visual quality for the body structure the selected specimens, while file sizes are portable enough to support web based visualization.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Efficient Foreground Extraction From HEVC Compressed Video for Application to Real-Time Analysis of Surveillance 'Big' Data

引用

ieee TRANSACTIONS ON image processing 2015年第11期24卷 3574-3585页

作者： Dey, Bhaskar Kundu, Malay K. Indian Stat Inst Ctr Soft Comp Res Kolkata 700108 India Indian Stat Inst Machine Intelligence Unit Kolkata 700108 India

While surveillance video is the biggest source of unstructured Big Data today, the emergence of high-efficiency video coding (HEVC) standard is poised to have a huge role in lowering the costs associated with transmission and storage. Among the benefits of HEVC over the legacy MPEG-4 Advanced Video Coding (AVC), is a staggering 40 percent or more bitrate reduction at the same visual quality. Given the bandwidth limitations, video data are compressed essentially by removing spatial and temporal correlations that exist in its uncompressed form. This causes compressed data, which are already de-correlated, to serve as a vital resource for machine learning with significantly fewer samples for training. In this paper, an efficient approach to foreground extraction/segmentation is proposed using novel spatio-temporal de-correlated block features extracted directly from the HEVC compressed video. Most related techniques, in contrast, work on uncompressed images claiming significant storage and computational resources not only for the decoding process prior to initialization but also for the feature selection/extraction and background modeling stage following it. The proposed approach has been qualitatively and quantitatively evaluated against several other state-of-the-art methods.

关键词： Background subtraction HEVC statistical signal processing video surveillance transform coding

来源：评论

学校读者我要写书评

暂无评论

A Novel image Defogging Algorithm Based on Improved Bilateral Filtering

A Novel Image Defogging Algorithm Based on Improved Bilatera...

引用

10th International symposium on computational intelligence and Design (ISCID)

作者： Li, Aimin Li, Xiaocong Qilu Univ Technol Sch Informat Jinan Shandong Peoples R China

ISBN: (纸本)9781538636749

As we all know, haze and fog lead to decreasing of differentiation degree and definition in outdoor environment and reduce image processing performance. To recover image with fog, we propose a novel fast defogging approach from a gray or color image. First, we use dark channel statistics prior to illustrate the similar relationship between the dark channel and image with fog. Then, to conquer the shortcomings of the estimation methods of fog concentration, we put forward a new filter algorithm. Smoothing the concentration of mist with bilateral filtering can immensely keep the edge of a sudden mutation in the depth of the image. Using partial median filters to smooth the corners can avoid keeping a certain amount of fog around small objects and keep the edge of the corner of the building, which makes the result more robust.

关键词： defogging dark channel prior bilateral filter

来源：评论

学校读者我要写书评

暂无评论

A QUADRATIC MAJORIZE-MINIMIZE FRAMEWORK FOR STATISTICAL ESTIMATION WITH NOISY RICIAN- AND NONCENTRAL CHI-DISTRIBUTED MR imageS

A QUADRATIC MAJORIZE-MINIMIZE FRAMEWORK FOR STATISTICAL ESTI...

引用

ieee 10th International symposium on Biomedical Imaging - From Nano to Macro (ISBI)

作者： Varadarajan, Divya Haldar, Justin P. Univ So Calif Inst Signal & Image Proc Los Angeles CA 90089 USA

ISBN: (纸本)9781467364553

The statistics of noisy MR magnitude and square-root sum-of-squares MR images are well-described by the Rice and non-central chi distributions, respectively. Statistical estimation involving these distributions is complicated by the facts that they have first-and second-order moments that depend nonlinearly on the noiseless image, and can have nonconvex negative log-likelihoods. This paper proposes a new majorize-minimize framework to ease the computational burden associated with statistical estimation involving these distributions. We derive quadratic tangent majorants for the negative log-likelihoods, which enables statistical cost functions to be optimized using a sequence of much simpler least-squares or regularized least-squares surrogate problems. We demonstrate the use of this framework in the context of regularized MR image denoising, with both simulated and experimental data.

关键词： Statistical Estimation Magnetic Resonance Imaging Rice Distribution Noncentral Chi Distribution Majorize-Minimize Algorithms

来源：评论

学校读者我要写书评

暂无评论

image recovery based on effective image completion

Image recovery based on effective image completion

引用

4th International Conference on Intelligent Information Hiding and Multimedia signal processing

作者： Kuo, Chung-Ming Yang, Nai-Chung Chang, Wei-Han Wu, Chi-Lin I Shou Univ Dept Informat Engn Kaohsiung 840 Taiwan

ISBN: (纸本)9780769532783

Exemplar-based inpainting algorithm is a model used for large region removal. It combines the advantages of both inpainting and texture synthesis. This algorithm usually requires large amounts of computational cost for priority calculation and matching iteratively. However, for relatively flat damaged areas, the simple interpolation can work well for image restoration. Inspired by the advantages of the color interpolation and the exemplar-based inpainting methods, in this paper, we propose an adaptive restored approach based on gradient-based analysis. The evaluation shows that our method can avoid blurring artifacts and preserving correct propagated structures in the faster way.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

computational colour constancy by using two learning machines:: Contributions to Neural Networks and Ridge Regression for illuminant estimation

Computational colour constancy by using two learning machine...

引用

3rd ieee International symposium on Control, Communications and signal processing (ISCCSP 2008)

作者： Gomez, E. Loaiza, H. Caicedo, E. Univ Valle Sch Elect & Elect Engn Cali Colombia

ISBN: (纸本)9781424416875

Many applications of Colour image processing have problems with changes of the illuminant, in this work we present some contributions to the research line called computational Colour Constancy that could provide solutions to those problems. Colour Constancy is the ability through which colour perception remains almost constant despite changes in the illuminant and computational Colour Constancy can be defined as the emulation of this biological phenomenon through computer programs. There are a lot of paths to perform this task and one set of these propose to estimate the illuminant by learning machines before discounting the illuminant. In this work we present the results of some improvements to computational Colour Constancy by using Neural Networks and Ridge Regression approach to Colour Constancy. The main contribution is the extension of the original algorithms to a 3-D spectral spaces and additionally a cooperative approach between these two learning machines is commented and a stricter evaluation to Ridge Regression was performed. The experiments with a combination of synthetic data and real images showed the advantages of our proposal over some classical methods for illuminant estimation.

关键词： computational colour constancy illuminant estimation Neural Networks Ridge Regression

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：