检索结果-内蒙古大学图书馆

17th IFIP WG 11.9 International conference on Digital Forensics

作者： Lim, Myeong Jones, James Information Technology from George Mason University Fairfax VA United States Digital Forensics and Director of the Criminal Investigations and Network Analysis Center at George Mason University Fairfax VA United States

ISBN: (纸本)9783030883812;9783030883805

Digital forensic practitioners are constantly challenged to find the best allocation of their limited resources. While automation will continue to partially mitigate this problem, the preliminary question about which media should be prioritized for examination is largely unsolved. Previous research has developed methods for assessing digital media similarity that may aid in prioritization decisions. Similarity measures may also be used to establish links between media and, by extension, the individuals or organizations associated with the media. However, similarity measures have high computational costs that delay the identification of digital media warranting immediate attention and render link establishment across large collections of data impractical. This chapter presents and validates a method for parallelizing the computations of digital media similarity measures to reduce the time requirements. The proposed method partitions digital media and distributes the computations across multiple processors. It then combines the results as an overall similarity measure that preserves the accuracy of the original method executed on a single processor. Experiments on a limited dataset demonstrate reductions of up to 51% in processing time. The reductions vary based on the number of partitions chosen and specific digital media being examined, suggesting the need for additional testing and optimization strategies.

关键词： Drive similarity sector hashes Jaccard index parallel computation

来源：评论

学校读者我要写书评

暂无评论

A Fast Adversarial Sample Detection Approach for Industrial Internet-of-Things Applications

A Fast Adversarial Sample Detection Approach for Industrial ...

引用

International Workshop on Quality of Service

作者： Shigeng Zhang Yudong Li Shuxin Chen Xuan Li Jian Zhang School of Computer Science and Engineering Central South University College of Computer Science and Electronic Engineering Hunan University The Science and Technology on Parallel and Distributed Processing Laboratory (PDL) China

Adversarial attacks reveal the inherent vulnerability of deep neural networks, which face serious security issues for their security. Among them, the attack against the Deep Neural Network (DNN) application used in the Industrial Internet of Things (IIoT) is a key area in adversarial attacks. Adversarial examples generated by attackers by adding human-undetectable interference to legitimate examples may cause models to make wrong decision results, resulting in serious accidents. Many detection technologies have been proposed to mitigate the harm of adversarial examples to neural networks, among which the methods based on the difference of feature attribution between normal examples and adversarial examples show state-of-the-art detection performance, but they suffer from detection efficiency. In this work, we focus on improving the detection efficiency of the feature-attribution-based detection methods. We observe that there is still a significant difference in the feature attribution distribution of a normal image and an adversarial image even only some pixels in the image are processed, which can be verified by utilizing the Kolmogorov-Smirnov test. Based on this observation, we first adopt a variety of strategies to sample partial pixels in an image and then utilize the selected pixels to train a feature-attribution-based detector for detecting adversarial examples. Extensive experiments conducted on four datasets (MNIST, CIFAR-10, SVHN, CIFAR-100) against various attacks proved that the detection efficiency of the accelerated detection method is improved (for example, the average execution time was increased by 8.7 times on CIFAR-10) while the detection performance maintains state-of-the-art.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mask-Guided Transformer for Human-Object Interaction Detection

Mask-Guided Transformer for Human-Object Interaction Detecti...

引用

IEEE Visual Communications and image processing (VCIP)

作者： Daocheng Ying Hua Yang Jun Sun Shanghai Key Lab of Digital Media Processing and Transmission Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

ISBN: (纸本)9781665475938

Human-object interaction (HOI) detection is a meaningful research topic on human activity understanding. Recent works have made significant progress by focusing on efficient triplet matching and leveraging image-wide features based on encoder-decoder architecture. However, the ability to gather relevant contextual information about human is limited and different sub-tasks in HOI detection are not differentiated by specific decoupling in previous methods. To this end, we propose a new transformer-based method for HOI detection, namely, Mask-Guided Transformer (MGT). Our model, which is composed of five parallel decoders with a shared encoder, not only emphasizes interactive regions by applying body features, but also disentangles the prediction of instance and interaction. We achieve a favorable result at 63.3 mAP on the well-known HOI detection dataset V-COCO.

关键词： Visual communication image processing Focusing Predictive models Transformers Decoding

来源：评论

学校读者我要写书评

暂无评论

Disentangling Spatial and Temporal Learning for Efficient image-to-Video Transfer Learning

Disentangling Spatial and Temporal Learning for Efficient Im...

引用

International conference on Computer Vision (ICCV)

作者： Zhiwu Qing Shiwei Zhang Ziyuan Huang Yingya Zhang Changxin Gao Deli Zhao Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Alibaba Group ARC National University of Singapore

Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to video recognition still suffers from unsatisfactory temporal modeling capabilities. Existing methods insert tunable structures into or in parallel with the pre-trained model, which either requires back-propagation through the whole pre-trained model and is thus resource-demanding, or is limited by the temporal reasoning capability of the pre-trained structure. In this work, we present DiST, which disentangles the learning of spatial and temporal aspects of videos. Specifically, DiST uses a dual-encoder structure, where a pre-trained foundation model acts as the spatial encoder, and a lightweight network is introduced as the temporal encoder. An integration branch is inserted between the encoders to fuse spatio-temporal information. The disentangled spatial and temporal learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Meanwhile, we empirically show that disentangled learning with an extra network for integration benefits both spatial and temporal understanding. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps. When pre-training on the large-scale Kinetics-710, we achieve 89.7% on Kinetics-400 with a frozen ViT-L model, which verifies the scalability of DiST. Codes and models can be found in https://***/alibaba-mmai-research/DiST.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting Fake Political News on Social Media by Support Vector Machine Compared to Naive Bayes

Detecting Fake Political News on Social Media by Support Vec...

引用

International conference on Computational and Characterization Techniques in Engineering & Sciences (CCTES)

作者： M. Sireesha S. Tamilselvan Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Cloud Computing and Image Processing Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

The primary objective is to enhance the precision of the Support Vector Machine and evaluate it in comparison to the Naive Bayes algorithm in terms of its ability to forecast fake political news on social media networks. This research work focuses on two groups: Support Vector Machine and Naive Bayes Algorithm, where each group is executed for 10 times. The ClinCalc software was used in calculating samples in which the alpha value is considered as 0.05, and the confidence interval of 95%. Result: There is a statistically significant difference between the algorithm used by Improved Support Vector Machine and Naive Baye with P value as 0.001 (Independent Sample t-Test P<0.05) in SPSS statistical analysis. The accuracy of the Improved method Support Vector Machine is 98.12%, which appears to be superior to Naive Baye of 95.03% correspondingly. Conclusion: According to the results, the Support vector machine has an accuracy of 98.12%, which is higher than the Naive Bayes accuracy of 95.03%.

关键词： Support vector machines Cloud computing Accuracy Social networking (online) Statistical analysis distributed databases Prediction algorithms Vectors Naive Bayes methods Fake news

来源：评论

学校读者我要写书评

暂无评论

SMEGA2: distributed Asynchronous Deep Neural Network Training With a Single Momentum Buffer 22

SMEGA2: Distributed Asynchronous Deep Neural Network Trainin...

引用

Proceedings of the 51st International conference on parallel processing

作者： Refael Cohen Ido Hakimi Assaf Schuster Department of Computer Science Technion - Israel Institute of Technology Israel

ISBN: (纸本)9781450397339

As the field of deep learning progresses, and neural networks become larger, training them has become a demanding and time consuming task. To tackle this problem, distributed deep learning must be used to scale the training of deep neural networks to many workers. Synchronous algorithms, commonly used for distributing the training, are susceptible to faulty or straggling workers. Asynchronous algorithms do not suffer from the problems of synchronization, but introduce a new problem known as staleness. Staleness is caused by applying out-of-date gradients, and it can greatly hinder the convergence process. Furthermore, asynchronous algorithms that incorporate momentum often require keeping a separate momentum buffer for each worker, which cost additional memory proportional to the number of workers. We introduce a new asynchronous method, SMEGA2, which requires a single momentum buffer regardless of the number of workers. Our method works in a way that lets us estimate the future position of the parameters, thereby minimizing the staleness effect. We evaluate our method on the CIFAR and imageNet datasets, and show that SMEGA2 outperforms existing methods in terms of final test accuracy while scaling up to as much as 64 asynchronous workers. Open-Source Code: https://***/rafi-cohen/SMEGA2

关键词： neural networks asynchronous gradient descent distributed deep learning

来源：评论

学校读者我要写书评

暂无评论

Suspicious Activity Detection and Classification in IoT Environment Using Machine Learning Approach

Suspicious Activity Detection and Classification in IoT Envi...

引用

International conference on parallel distributed and Grid Computing (PDGC)

作者： Veera Talukdar Dharmesh Dhabliya Bhupendra Kumar Suryansh Bhaskar Talukdar Shahanawaj Ahamad Ankur Gupta Dept. of IT and Management Shri Ram College of Commerce Science and Arts Maharashtra Department of IT Vishwakarma Institute of Information Technology Pune Maharashtra India College of Business … Economics Debre Tabor University Amhara Ethiopia East Africa School of CSE Vellore Institute of Technology Bhopal Madhya Pradesh India College of CSE University of Hail Hail City Saudi Arabia Department of CSE Vaish College of Engineering Rohtak Haryana India

ISBN: (纸本)9781665454025

Studies combining machine learning with the Internet of Things are now under process. The procedures for detecting fires are also described in depth. In order to be of any help, machine learning has to be able to identify and track the development of events that are equivalent to fires. The number of photos that must be analyzed by machine learning before a pattern may be found is decreased when data is captured and processed frame by frame. This information has been gathered for the express purpose of tracking a particular incident. Recent research has been given substantial treatment in this journal. Some of the constraints of the current state of the field have been discussed. The problem is identified, and suggestions on how to address it are provided. Using machine learning and image processing, we looked at one potentially suspicious IoT device. Many researchers have shown that the machine learning method can accurately classify and predict data. The authors of the present work have integrated machine learning with a compression method to further improve the security of the IoT ecosystem. Additionally, machine learning employs filtered datasets to improve the accuracy of attack classification. As a result of recent studies, it is possible to identify and classify suspicious events like fires, fake people, and other anomalies. Limiting the spread of misinformation relies on the ability to identify suspicious behavior.

关键词： Limiting image coding Decision making Neural networks Machine learning Pressing User interfaces

来源：评论

学校读者我要写书评

暂无评论

基于云计算的船舶图像网络数据低时延传输方法

引用

舰船科学技术 2024年第16期46卷 178-181页

作者：李小丽王磊河南开放大学信息工程与人工智能学院河南郑州450046 河南理工大学计算机科学与技术学院河南焦作454003

为实时传输海量船舶图像,为有效监控船舶实时航行状况提供保障,研究基于云计算的船舶图像网络数据低时延传输方法。结合云计算技术,构建船舶图像网络数据传输平台,通过平台数据接收单元将大量船舶网络数据存入云端服务器内;数据处理单... 详细信息

为实时传输海量船舶图像,为有效监控船舶实时航行状况提供保障,研究基于云计算的船舶图像网络数据低时延传输方法。结合云计算技术,构建船舶图像网络数据传输平台,通过平台数据接收单元将大量船舶网络数据存入云端服务器内;数据处理单元基于云计算的分布式处理特点,结合并行运行框架Map Reduce和并行化K-means聚类算法,并行挖掘云端服务器内的船舶图像网络数据;信道均衡单元结合所构建的船舶通信网络节点能量消耗模型,均衡船舶通信网络信道,运用均衡信道实现所挖掘船舶图像网络数据的传输。结果显示,该方法的数据挖掘速率高,数据传输过程中各信道能量开销均衡,且可低至3.5 k J,传输船舶图像网络数据的时延可低至10.23 ms,实现了数据的低时延传输。

关键词：云计算船舶图像网络数据低时延传输聚类算法信道均衡

来源：评论

学校读者我要写书评

暂无评论

Design optimisation of multiplier-free parallel pipelined FFT on field programmable gate array

引用

IET CIRCUITS DEVICES & SYSTEMS 2020年第7期14卷 995-1000页

作者： Godi, Prasanna Kumar Krishna, Battula Tirumala Kotipalli, Pushpa Jawaharlal Nehru Technol Univ Elect & Commun Engn Kakinada India Shri Vishnu Engn Coll Women Autonomous Elect & Commun Engn Bhimavaram India

Fast Fourier transform (FFT) is utilised to minimise the complexity of discrete Fourier transform by converting signals from frequency domain to time domain and conversely. Digital signal processing systems like image processing, general filtering, sonar, spread-spectrum communications and convolutions use this FFT operations. Radix-2 decimation in frequency (R2DIF) method is designed to execute an efficient FFT architecture in this study. Each and every state of the FFT stores the input and output the data using the R2DIF method. Also, the complex twiddle factors in FFT are replaced by the proposed uniform Montgomery algorithm. This technique simply performs the shift-add method instead of the multiplication process which also enhances the convergence of the calculation. So, the FFT implementation is done with the help of the proposed method which reduces the usage of chips in the process. Based on this approach, it performs the operation of FFT from 16 points to 1024 points and the performance of this proposed method is compared with existing approaches. Moreover, it does not require expensive dedicated functional blocks and uses only distributed logic resources. The simulation is carried out by the Xilinx platform using Verilog coding. The proposed design outperforms conventional methods in terms of less usage power and high speed.

关键词： discrete Fourier transforms hardware description languages pipeline processing digital signal processing chips fast Fourier transforms field programmable gate arrays mathematics computing design optimisation multiplier-free parallel field programmable gate array frequency domain time domain digital signal image processing general filtering spread-spectrum communications FFT operations radix-2 decimation frequency method efficient FFT architecture FFT stores R2DIF method complex twiddle factors uniform Montgomery algorithm shift-add method multiplication process FFT implementation

来源：评论

学校读者我要写书评

暂无评论

Digital processing of shadowgraph images taking into account the diffraction of light at a shock front 16

Digital processing of shadowgraph images taking into account...

引用

16th International conference Optical methods of Flow Investigation, OMFI 2021

作者： Mursenkova, I. Timokhin, M. Tikhonov, M. Militsina, A. Kuznetsov, A. Lomonosov Moscow State University 1-2 Leninskiye Gory Moscow119991 Russia Moscow Power Engineering Institute Krasnokazarmennaya 14 Moscow111250 Russia Moscow Aviation Institute Volokolamskoe shosse 4 Moscow125993 Russia Department of Mathematics University of Virginia CharlottesvilleVA22904 United States

The aim of the study is to determine the shock wave position in experimental shadowgraph images and to evaluate the accuracy by digital image processing. The experimental images were obtained with the shock tube with a rectangular channel. The shadowgraph optical system formed a parallel light beam. It passed through the plane-parallel quartz glasses of the shock tube test section. The process synchronization system at the facility allows registering the shadowgraph images of unsteady flows with shock waves with a high-speed camera or with a single frame camera. The obtained spatial intensity profiles were used to determine the coordinates of gas-dynamic discontinuities at different stages of the flow evolution. shadowgraph patterns were analysed taking into account diffraction at the shock front in case of a laser light source. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Shock tubes

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：