检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Jin, Haibo Chen, Ruoxi Zheng, Haibin Chen, Jinyin Cheng, Yao Yu, Yue Liu, Xianglong College of Information Engineering Zhejiang University of Technology Hangzhou China Institute of Cyberspace Security Zhejiang University of Technology Hangzhou China Huawei International Singapore National Laboratory for Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha China State Key Laboratory of Software Development Environment Beihang University Beijing China

Despite impressive capabilities and outstanding performance, deep neural networks (DNNs) have captured increasing public concern about their security problems, due to their frequently occurred erroneous behaviors. Therefore, it is necessary to conduct a systematical testing for DNNs before they are deployed to real-world applications. Existing testing methods have provided fine-grained metrics based on neuron coverage and proposed various approaches to improve such metrics. However, it has been gradually realized that a higher neuron coverage does not necessarily represent better capabilities in identifying defects that lead to errors. Besides, coverage-guided methods cannot hunt errors due to faulty training procedure. So the robustness improvement of DNNs via retraining by these testing examples are unsatisfactory. To address this challenge, we introduce the concept of excitable neurons based on Shapley value and design a novel white-box testing framework for DNNs, namely DeepSensor. It is motivated by our observation that neurons with larger responsibility towards model loss changes due to small perturbations are more likely related to incorrect corner cases due to potential defects. By maximizing the number of excitable neurons concerning various wrong behaviors of models, DeepSensor can generate testing examples that effectively trigger more errors due to adversarial inputs, polluted data and incomplete training. Extensive experiments implemented on both image classification models and speaker recognition models have demonstrated the superiority of DeepSensor. Compared with the state-of-the-art testing approaches, DeepSensor can find more test errors due to adversarial inputs (∼ ×1.2), polluted data (∼ ×5) and incompletely-trained DNNs (∼ ×1.3). Additionally, it can help DNNs build larger l2-norm robustness bound (∼ ×3) via retraining according to CLEVER's certification. We further provide interpretable proofs for effectiveness of DeepSensor via excitable neuro

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Security Algorithms used in Cloud Computing

Comparative Analysis of Security Algorithms used in Cloud Co...

引用

International conference on Computing for Sustainable Global Development (INDIACom)

作者： Mohd Tajammul Rafat Parveen Iftikhar Aslam Tayubi Jamia Millia Islamia New Delhi India King Abdulaziz University Jeddah Saudi Arabia

Cloud computing is a technique that enables the users to access applications to infrastructure through subscription methods on remote location. Cloud computing, being collective technique, possesses features of various technologies like Virtual Private Network (VPN), distributed technology, parallel computing, grid computing as well as ubiquitous computing. Cloud storage is the infrastructure offered by the cloud computing in order to facilitate users to upload and access their data on cloud space. Due to multitenancy of cloud storage, the data uploaded on it is the more prone to security breaches. To secure the data on cloud, cryptographic technique is used which works like safeguard against data leakage. This research work focuses on cryptographic algorithms from most basic to advance and also presents their comparative analysis. Moreover, the paper focuses on the nature of the algorithms in context of cloud that is homogeneous and heterogeneous nature. In the cloud computing, homogeneous nature algorithm is used only if the encryptors and decryptors both are same while heterogeneous refers to the situation in which encryptors and decryptors are different entities.

关键词： Cloud computing parallel processing Ubiquitous computing Grid computing Virtual private networks Cryptography

来源：评论

学校读者我要写书评

暂无评论

Automatic Lid Segmentation in Meibography images 8th

Automatic Lid Segmentation in Meibography Images

引用

8th Latin American conference on Biomedical Engineering (CLAIB) / 42nd National conference on Biomedical Engineering (CNIB)

作者： DelaO-Arevalo, Luis Bojorges-Valdez, Erik Hernandez-Quintela, Everardo Ramos-Betancourt, Nallely Davila-Alquisiras, Jesus H. Univ Iberoamer Ciudad Mexico Mexico City 01219 DF Mexico Assoc Erradicar Ceguera IAP Mexico City 04030 DF Mexico

ISBN: (纸本)9783030306489;9783030306472

This work presents an evaluation of two machine learning schemes for lid segmentation on meibography images. Both schemes use same input features based on pixel gray levels, laplacian and entropy filters, and also distances to anatomical landmarks like pupil and eye lashes. The methods evaluated were support vector machines (SVM) with 4th degree polynomial kernel, a Neural Network (NN) with 60 neurons distributed on three layers and the intersection of both. Performance was evaluated with AUC on a bootstrapped cross validation (CV) tests of 20 folds. Dataset is conformed by 465 images for each fold entire dataset was split on 70% training and remainder for testing. Results of CV: SVM 0.851 +/- 0.103, NN 0.713 +/- 0.144 and SVM & NN 0.835 +/- 0.118, suggest that SVM is a suitable model to be used for this task.

关键词： Meibography Machine learning image processing

来源：评论

学校读者我要写书评

暂无评论

Supervised Multi-View distributed Hashing

Supervised Multi-View Distributed Hashing

引用

IEEE International conference on image processing

作者： Yunpeng Tang Xiaobo Shen Zexuan Ji Tao Wang Peng Fu Quan-Sen Sun School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Multi-view hashing efficiently integrates multi-view data for learning compact hash codes, and achieves impressive large-scale retrieval performance. In real-world applications, multi-view data are often stored or collected in different locations, where hash code learning is more challenging yet less studied. To fulfill this gap, this paper proposes a novel supervised multi-view distributed hashing (SMvDisH) for hash code learning from multi-view data in a distributed manner. SMvDisH yields the discriminative latent hash codes by joint learning of latent factor model and classifier. With local consistency assumption among neighbor nodes, the distributed learning problem is divided into a set of decentralized sub-problems. The sub-problems can be solved in parallel, and the computational and communication costs are low. Experimental results on three large-scale image datasets demonstrate that SMvDisH achieves competitive retrieval performance and trains faster than state-of-the-art multi-view hashing methods.

关键词： distributed databases Convex functions Benchmark testing Linear programming Computational modeling Binary codes Optimization

来源：评论

学校读者我要写书评

暂无评论

SINGLE image SUPER-RESOLUTION VIA CASCADED parallel MULTISIZE RECEPTIVE FIELD 26

SINGLE IMAGE SUPER-RESOLUTION VIA CASCADED PARALLEL MULTISIZ...

引用

26th IEEE International conference on image processing (ICIP)

作者： Chowdhury, Debjoy Androutsos, Dimitrios Ryerson Univ Dept Elect Comp & Biomed Engn Toronto ON Canada

ISBN: (纸本)9781538662496

Recovering a High-Resolution (HR) image from a Low-Resolution (LR) image is the main concept of image Super-Resolution(SR). These days Convolution Neural Networks(CNN) have become very popular and efficient in generating HR image from a LR image. Although CNNs are widely used with great performance improvements, there is still much room for improvement. There has always been a trade-off between the number of parameters and performance enhancement. Inspired by the Inception architecture of GoogleNet, we have developed a novel approach with an efficiently increased number of receptive field by cascading different kernel sizes to reconstruct the HR image. Experimental results shows that the proposed model outperforms the state-of-art methods.

关键词： image Super Resolution Convolution Neural Network Receptive Field Cascaded parallel Block Residual Block

来源：评论

学校读者我要写书评

暂无评论

A Heterogeneous Processor Design for CNN-Based AI Applications on IoT Devices 8

A Heterogeneous Processor Design for CNN-Based AI Applicatio...

引用

8th International conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2019

作者： Liu, Zhiqiang Jiang, Jingfei Lei, Guoqing Chen, Kai Qin, Buyue Zhao, Xiaoqiang Artificial Intelligence Research Center National Innovation Institute of Defense Technology Beijing China National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China College of System Engineering National University of Defense Technology Changsha China

This paper proposes a heterogeneous processor design for CNN-based AI applications on IoT devices. The heterogeneous processor contains an embedded RISC-V CPU that works as a general processor and an efficient CNN-accelerator that supports a variety of CNN models with a list of macro instructions. For demonstration, we implement a prototype on an FPGA platform with the RISC-V CPU working under 20 MHz and the CNN accelerator working under 100 MHz. As a case study, we run a CNN-based face detection and recognition application on this prototype. The prototype can process one image in 0.72 seconds and an ASIC implementation working under 400 MHz can process one image in less than 0.15 seconds by estimation, which can satisfy the needs for many IoT scenarios such as access control systems and check-in systems. © 2020 The Authors. Published by Elsevier B.V.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Efficient Spatio-Temporal-Data-Oriented Range Query processing for Air Traffic Flow Statistics

Efficient Spatio-Temporal-Data-Oriented Range Query Processi...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Huayan Yu Xin Li Ligang Yuan Xiaolin Qin College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China State Key Laboratory for Novel Software Technology Nanjing University China College of Civil Aviation Nanjing University of Aeronautics and Astronautics China

Timely and efficient air traffic flow statistics play a significant role in improving the accuracy and intelligence of air traffic flow management (ATFM). The enormous spatio-temporal data collected by location-based services (LBS) intensely aggravate the burden of the statistical tasks. The traditional approaches of calculating such tasks show their weakness in two parts: 1) they fail to capture the features of complicated three-dimensional time-dependent airspace, and 2) they are not optimized to deal with big volume spatio-temporal data covering high-dimensional features. Spatio-temporal range queries have advantages in calculating the eligible flow records. Therefore, exploring the efficiency of distributed range query processing methods helps improve the performance of air traffic flow statistics and gain insights into the rationality of the air traffic. To analyze the large-scale spatio-temporal aviation data efficiently, we propose two spatio-temporal range query MapReduce algorithms: 1) spatio-temporal polygon range query, which aims to find all records from a polygonal location in a time interval, 2) spatio-temporal k nearest neighbors query, which directly searches the k closest neighbors of the query point. Moreover, we design an air traffic flow statistic strategy to accurately calculate traffic flow in arbitrary airspace based on real-world aviation trajectory datasets. The experimental results demonstrate that our algorithms perform better in answering spatio-temporal range queries over counterpart algorithms and the average response time is reduced by 81%. The evaluation also proves the effectiveness of our algorithms concerning air traffic flow statistics.

关键词： Query processing Trajectory Time factors Task analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Cascade image Correction System for the Large Solar Vacuum Telescope 7

Multi-Cascade Image Correction System for the Large Solar Va...

引用

conference on Adaptive Optics Systems VII

作者： Lukin, V. P. Botygina, N. N. Antoshkin, L., V Borzilov, A. G. Emaleev, O. N. Konyaev, P. A. Kovadlo, P. G. Kolobov, D. Yu Shikhovtsev, A. Yu Chuprakov, S. A. Russian Acad Sci VE Zuev Inst Atmospher Opt Siberian Branch Tomsk 634055 Russia Russian Acad Sci Inst Solar Terr Phys Siberian Branch Irkutsk 664033 Russia

ISBN: (纸本)9781510636842

A multi-cascade adaptive optical system for imaging and image stabilization for the Large Solar Vacuum Telescope is described. This system was created in 2017 by specialists of the V.E. Zuev Institute of Atmospheric Optics SB RAS, Tomsk, with the technical support of the Institute of Solar-Terrestrial Physics SB RAS, Irkutsk. The system has been tested at the Large Solar Vacuum Telescope (Baikal Astrophysical Observatory) and demonstrated its efficiency. Along with the first cascade of adaptive image stabilization by a tip-tilt corrected mirror, this system employs the second imaging cascade based on correction with a flexible mirror controlled by a specialized wavefront sensor, as well as the third cascade for real-time post-detector processing of video camera frames. Reliable experimental data confirming the efficiency of the multi-cascade adaptive system for image formation and stabilization have been obtained. Three high-rate digital video cameras recording simultaneously digital images with rates from 300 to 980 frames per second were used to test the system. The mirror correcting wavefront tilts and operating in a closed optical feedback loop was controlled by the specially developed software including the fast correlation tracking algorithm. The post-detector digital imaging was performed with a special software for processing of video camera frames in real time with the use of modern high-speed parallel algorithms based on the Intel MKL and IPP libraries.

关键词： astronomy solar telescope astroclimate turbulence adaptive optics tilt corrector correction cascade

来源：评论

学校读者我要写书评

暂无评论

Intelligent system of forest area recognition for tasks of geographically distributed economic systems 8

Intelligent system of forest area recognition for tasks of g...

引用

8th International Scientific conference on Computing in Physics and Technology, CPT 2020

作者： Kuzmenko, A.A. Kondrashov, D.. Sazonova, A.S. Filippova, L.B. Filippov, R.. Bryansk State Technical University Bryansk Russia

For a long period, our country has been in the process of radical transformations of the state economic system, associated with the final transition to a market system of management, the development of local self-government and the independence of economic entities. In the new conditions of the emerging market, the issues of ensuring the sustainable development of territorial economic systems and sectors of the economy, which are the source and guarantor of social stability, employment, a high level and quality of life of the population of the regions, come to the fore. The paper deals with an intelligent system for recognizing the dynamics of changes in forest areas based on automatic pattern recognition methods. The existing methods of processing graphical information, classification and clustering methods that are of value within the framework of the problems being solved are considered, and several original algorithms are proposed. LTP and FFT algorithms were selected as feature extractors of which the simplest and most productive option is LTP. Histogram equalization algorithms, median and Gaussian filters to eliminate noise and remove small image details are chosen to pre-process the image. Euclidean and Mahalanobis distances were used as separability measures. Naive Bayes classifier is proposed to use for classification. Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A Salient Object Detection Technique Based on Color Divergence 20

A Salient Object Detection Technique Based on Color Divergen...

引用

The 4th International conference on Future Networks and distributed Systems (ICFNDS)

作者： Sana Sahar Guia Abdelkader Laouid Reinhardt Euler Mohammed Amine Yagoub Ahcene Bounceur Mohammad Hammoudeh El Oued University University of Western Brittany UBO Manchester Metropolitan University

ISBN: (纸本)9781450388863

Nowadays, multimedia and visual computing advances in digital technology make a potential change in human life. Many applications exploit the captured images from autonomous entities as data sources for several goals. In fact, these captured images need to be interpreted in order to extract their external environment. The researchers of this domain will meet some challenges such as how to detect and interpret the images’ context. This paper is to propose an efficient technique that detects objects of a given image based on the color divergence. The results clearly show the accuracy and the computation speed of the proposed technique compared with other methods.

关键词： image processing Data Analysis. Object Detection

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：