检索结果-内蒙古大学图书馆

37th IEEE International conference on Distributed Computing systems (ICDCS)

作者： Qiu, Shuang Luo, Qiong Hong Kong Univ Sci & Technol Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781538617915

De Bruijn graph construction is the first step in de novo assemblers to connect input reads into a complete sequence without a reference genome. This step is both time and memory space consuming. To address this problem, we develop ParaHash, a system that partitions the input data in a compact format, parallelizes the computation on both the CPUs and the GPUs in a single computer, and performs hash-based De Bruijn graph construction. This way, ParaHash utilizes all available processors to assemble big genomes that cannot fit into memory. Furthermore, we analyze the characteristics of genome data to set the hash table size, design concurrent hashing algorithms to handle the inherent multiplicity, and pipeline the data transfer and the computation for further efficiency. Our experiments on real-world genome datasets show that the workload was balanced across heterogeneous processors, and that ParaHash was able to construct billion-node graphs on a single machine with an overall performance up to 20 times faster than the state-of-theart shared-memory assemblers.

关键词： Genomics Bioinformatics Partitioning algorithms Graphics processing units Memory management image edge detection

来源：评论

学校读者我要写书评

暂无评论

Content Adaptive Embedded Compression

Content Adaptive Embedded Compression

引用

Data Compression conference (DCC)

作者： Shen, Yuxiang Wu, Xiaolin Shu, Xiao Hulu LLC Beijing 100084 Peoples R China McMaster Univ Hamilton ON L8S 4K1 Canada

ISBN: (纸本)9781509067213

image resolution in modern video processing and display systems are rocketing up in recent years. With the main stream video quality evolving from standard definition to high-definition, and further towards the emerging super high-definition, the bandwidth and power consumption of external memory are becoming serious bottlenecks. In this paper, frequency domain analysis is made on image down-sampling, which gives birth to the optimal sampling strategy for high-frequency energy protection. On that basis, we develop a new embedded compression (EC) technique, which encodes image frames through content-adaptive down-sampling and decodes them using side-information aided up-sampling. Apart from the low encoding complexity and even lower decoding complexity, the proposed EC algorithm also features high fidelity for images with sharp edges. Comparisons with some existing EC algorithms show the advantage of the new technique over its counterparts on a wide class of testing images.

关键词： embedded compression down sampling content adaptive single image compression

来源：评论

学校读者我要写书评

暂无评论

Algorithm sensitivity analysis and parameter tuning for tissue image segmentation pipelines

引用

BIOINFORMATICS 2017年第7期33卷 1064-1072页

作者： Teodoro, George Kurc, Tahsin M. Taveira, Luis F. R. Melo, Alba C. M. A. Gao, Yi Kong, Jun Saltz, Joel H. Univ Brasilia Dept Comp Sci BR-70910900 Brasilia DF Brazil Emory Univ Biomed Informat Dept Atlanta GA 30322 USA SUNY Stony Brook Biomed Informat Dept Stony Brook NY 11794 USA Oak Ridge Natl Lab Sci Data Grp Oak Ridge TN USA

Motivation: Sensitivity analysis and parameter tuning are important processes in large-scale image analysis. They are very costly because the image analysis workflows are required to be executed several times to systematically correlate output variations with parameter changes or to tune parameters. An integrated solution with minimum user interaction that uses effective methodologies and high performance computing is required to scale these studies to large imaging datasets and expensive analysis workflows. Results: The experiments with two segmentation workflows show that the proposed approach can (i) quickly identify and prune parameters that are non-influential;(ii) search a small fraction (about 100 points) of the parameter search space with billions to trillions of points and improve the quality of segmentation results (Dice and Jaccard metrics) by as much as 1.42 x compared to the results from the default parameters;(iii) attain good scalability on a high performance cluster with several effective optimizations. Conclusions: Our work demonstrates the feasibility of performing sensitivity analyses, parameter studies and auto-tuning with large datasets. The proposed framework can enable the quantification of error estimations and output variations in image segmentation pipelines.

关键词： SEGMENTATION (image processing) SENSITIVITY analysis SCALABILITY (systems engineering) FEASIBILITY studies image analysis algorithms

来源：评论

学校读者我要写书评

暂无评论

ULBP-RF: A Hybrid Approach for Malware image Classification

ULBP-RF: A Hybrid Approach for Malware Image Classification

引用

International conference on Parallel Distributed and Grid Computing (PDGC)

作者： Shakshi Gupta Priti Bansal Sumit Kumar Department of IT Netaji Subhas Institute of Technology New Delhi India Department of IT KIET Group of Institutions Ghaziabad India

ISBN: (纸本)9781728106489

The growing dependence on internet for performing critical activities in every domain has raised serious concerns about the security of the computer systems. Malwares have become a significant threat to computer systems and recently, a massive growth has been observed by experts in the number and sophistication of new malwares. Therefore, the task of malware detection and classification is of utmost importance. However, the task of classifying malwares has become more challenging since the introduction of code obfuscation and metamorphism techniques. These techniques easily alter the malwares' code signatures and make the static techniques of malware detection ineffective. Dynamic analysis is effective but time-consuming. Recently, image processing techniques along with machine learning techniques have been explored by researchers for visualization and classification of malwares. In this paper, we introduce a new approach ULBP-RF that uses Uniform local binary pattern with circular neighborhood strategy to extract features from the malware images dataset. The resulting datasets are classified using Random Forest. To assess the performance of the proposed approach, experiments are performed and a comparative analysis of the performance of various combinations of feature extraction techniques and classification algorithms is done. It has been found that ULBP-RF has the highest classification accuracy.

关键词： Malware Feature extraction Histograms Computer security Machine learning Static analysis

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks: Estimating Relations in the Ising Model on Overfitting

Convolutional Neural Networks: Estimating Relations in the I...

引用

IEEE International conference on Cognitive Informatics

作者： Andrei Gavrilov Alex Jordache Maya Vasdani Jack Deng Bachelor of Applied Science University of British Columbia Vancouver BC Canada Bachelor of Commerce University of British Columbia Vancouver BC Canada Bachelor of Arts University of British Columbia Vancouver BC Canada

ISBN: (纸本)9781538633618

A CNN (Convolutional Neural Network) is one of actively researched and broadly applied deep machine learning methods. A CNN is composed of a feed-forward neural network that takes in images as inputs, and outputs a probability value associated to a class that best describes the image. As well, it is constructed of multiple layers, which include convolutional, max-pooling and fully connected layers. However, the training set has a large influence on the accuracy of a network, and hence it is paramount to create a network architecture that prevents overfitting (when a trained model cannot differentiate newly input data from its test data) and underfitting (the inability of a model to find relationships among inputs). This paper addresses the above deficiencies by comparing the statistics of CNN image recognition algorithms to the Ising model. The Ising model consists of magnetic dipole moments that can be in one of two states: +1 or -1. Using a two-dimensional square-lattice array once a training set of such data is complete, we determine the impact that network parameters, specifically learning rate and regularization rate, have on the adaptability of convolutional neural networks for image classification. Our results not only contribute to a better theoretical understanding of a CNN, but also provide concrete guidance on preventing model overfitting and underfitting when a CNN is applied for image recognition.

关键词： Handheld computers Data models Cognitive systems Convolutional neural networks image processing Cognitive informatics Convolution

来源：评论

学校读者我要写书评

暂无评论

REMOVING BLUE SCREEN BACKGROUND UNDER NON-UNIFORM ILLUMINATION 4

REMOVING BLUE SCREEN BACKGROUND UNDER NON-UNIFORM ILLUMINATI...

引用

IEEE International conference on Consumer Electronics - Taiwan (ICCE-TW)

作者： Teng, Chin-Hung Liao, Yun-Hsuan Chou, Yi-Chia Lin, Sih-Yu Yuzn Ze Univ Dept Informat Commun Taoyuan Taiwan

ISBN: (纸本)9781509040179

In this paper, we develop a system to remove the background of an image captured in a blue screen environment under non-uniform illumination. We first collected some images as the training data and applied a watershed segmentation to extract a number of coherent regions from these images. With these extracted regions, two mixed Gaussian models for the foreground and background are trained using an expectation-maximization (EM) algorithm. With the trained models, for each input image we first segment the image using the watershed segmentation algorithm and then predict the associated foreground/background label for each extracted region. Finally, the regions labeled as background are removed. Some experiments were conducted and the results showed that the proposed system performs better than traditional chroma keying technique.

关键词： image segmentation image color analysis Lighting Prediction algorithms Training Hidden Markov models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Automatic Brightness Adjustment System by Fuzzy Inference System for Object Recognition 17

Automatic Brightness Adjustment System by Fuzzy Inference Sy...

引用

Joint 17th World Congress of International-Fuzzy-systems-Association / 9th International conference on Soft Computing and Intelligent systems (IFSA-SCIS)

作者： Kim, Eun Kyeong Lee, Hansoo Kim, Sungshin Cho, Hyunhak Pusan Natl Univ Dept Elect & Comp Engn Busan South Korea Pusan Natl Univ Dept Interdisciplinary Cooperat Course Robot Busan South Korea

ISBN: (纸本)9781509049172

A camera has been widely used in practical fields with a diversity of purposes recently. There is a variety purpose of photography: images for memory, medical images for diagnosis, images for object recognition, surveillance images, and so on. In case of images for object recognition, the clarity of images is necessary to analyze the images which are obtained using vision sensors. However, a brightness of the image highly depends on the intensity of illumination in the certain environment. Therefore, we propose a method to solve the problems mentioned above by adjusting brightness automatically by utilizing CIE L*a*b* color space and fuzzy inference system. At first, the proposed method adjusts the brightness of a given image by considering both RGB component and L component of CIE L*a*b* color space. Secondly, the proposed method applies the fuzzy inference system to determine adjustment coefficients of each pixel for adjusting brightness of the image. Through the processes as mentioned above, we can obtain the result which is adjusted its brightness. To verify the proposed method, we compare the result image with two different images, a reference image, and an adjusted image by using offset. It is confirmed that the proposed method can adjust a given image efficiently and automatically.

关键词： Estimation Field programmable gate arrays OFDM Modulation Filtration Clocks Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Neuroimage-based clinical prediction using machine learning tools

引用

INTERNATIONAL JOURNAL OF IMAGING systems AND TECHNOLOGY 2017年第1期27卷 89-97页

作者： Demirhan, Ayse Gazi Univ Elect & Elect Engn Fac Technol Ankara Turkey

Classification of structural brain magnetic resonance (MR) images is a crucial task for many neurological phenotypes that machine learning tools are increasingly developed and applied to solve this problem in recent years. In this study binary classification of T1-weighted structural brain MR images are performed using state-of-the-art machine learning algorithms when there is no information about the clinical context or specifics of neuroimaging. image derived features and clinical labels that are provided by the International conference on Medical image Computing and Computer-Assisted Intervention 2014 machine learning challenge are used. These morphological summary features are obtained from four different datasets (each N > 70) with clinically relevant phenotypes and automatically extracted from the MR imaging scans using FreeSurfer, a freely distributed brain MR image processing software package. Widely used machine learning tools, namely;back-propagation neural network, self-organizing maps, support vector machines and k-nearest neighbors are used as classifiers. Clinical prediction accuracy is obtained via cross-validation on the training data (N = 150) and predictions are made on the test data (N = 100). Classification accuracy, the fraction of cases where prediction is accurate and area under the ROC curve are used as the performance metrics. Accuracy and area under curve metrics are used for tuning the training hyperparameters and the evaluation of the performance of the classifiers. Performed experiments revealed that support vector machines show a better success compared to the other methods on clinical predictions using summary morphological features in the absence of any information about the phenotype. Prediction accuracy would increase greatly if contextual information is integrated into the system. (C) 2017 Wiley Periodicals, Inc.

关键词： structural brain MR images image classification morphological features clinical prediction machine learning

来源：评论

学校读者我要写书评

暂无评论

An edge preserving IBP based super resolution image reconstruction using P-spline and MuCSO-QPSO algorithm

引用

MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOsystems-INFORMATION STORAGE AND processing systems 2017年第3期23卷 553-569页

作者： Nayak, Rajashree Patra, Dipti NIT Dept Elect Engn Image Proc & Comp Vis Lab Rourkela India NIT Dept Elect Engn Rourkela India

Super resolution (SR) reconstruction based on iterative back projection (IBP) is a widely used image reconstruction method. IBP approach is easy to implement and allows easy inclusion of the spatial domain with low computational complexity. However, local minima trapping;slow rate of convergence;sensitive to the initial guess;prone to ringing and jaggy artifacts are some major bottlenecks which restrict its performance. The present paper aims to enhance the performance of IBP based SR reconstruction (IBP-SRR) of image by exploring an effective method. The proposed method has fast convergence rate, a global optimal solution, capability to lessen the effect of artifacts and a noble generalization performance. In the present work, P-spline interpolation scheme imposes additional penalty in the inherently smooth B-spline interpolation process to provide a proper initial guess. An adaptive edge regularization technique is used in the constraint optimization of the reconstruction problem to minimize the effect of ringing artifacts. Finally, the overall reconstruction error of the reconstruction system is optimized using a hybrid meta-heuristic optimization technique. The optimization algorithm hybridizes the notion of Cuckoo search optimization (CSO) algorithm with a mutation operator (MuCSO) and the quantum behaved particle swarm optimization (QPSO). The MuCSO-QPSO algorithm is compared with other significant optimization algorithms such as GA, PSO, QPSO, CSO, MuCSO and found to be outperforming. Experimental results demonstrate the superiority of the proposed edge preserving IBP-SRR method in terms of enhanced spatial resolution, and more detail reconstruction.

关键词： image reconstruction HIGH resolution imaging ITERATIVE methods (Mathematics) MATHEMATICAL optimization PARTICLE swarm optimization

来源：评论

学校读者我要写书评

暂无评论

A model for data hiding system description

A model for data hiding system description

引用

2017 International conference Information Technology and Nanotechnology. Session image processing, Geoinformation Technology and Information Security, IPGTIS-ITNT 2017

作者： Fedoseev, Victor Samara National Research University 34 Moskovskoe Shosse Samara443086 Russia Image Processing Systems Institute Branch of the Federal Scientific Research Centre Crystallography and Photonics Russian Academy of Sciences 151 Molodogvardeyskaya st. Samara443001 Russia

The paper presents a new model for unified description of any information hiding systems which include both stegographic and watermarking systems. The model is based on considering three possible representations of information being embedded: a binary vector, a digital signal, and a feature matrix. Also we introduce a parametric description for information hiding systems according to the proposed model which completely defines all valuable algorithms used at the embedding and the extraction stages, as well as its parameters. Some examples of such descriptions a number of existing systems are presented.

关键词： Steganography

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：