检索结果-内蒙古大学图书馆

Hardware Accelerators for Real-Time Face Recognition: A Survey

IEEE ACCESS 2022年 10卷 83723-83739页

作者： Baobaid, Asma Meribout, Mahmoud Tiwari, Varun Kumar Pena, Juan Pablo Khalifa Univ Coll Engn Dept Elect Engn & Comp Sci Abu Dhabi U Arab Emirates

Real-time face recognition has been of great interest in the last decade due to its wide and varied critical applications which include biometrics, security in public places, and identification in login systems. This has encouraged researchers to design fast and accurate embedded and portable systems that are capable of detecting and recognizing a large number of faces at almost a video frame rate. Due to the increasing volume of reference faces, traditional general-purpose computing engines such as the ones based on Intel's Pentium processors have shown not to be adequate and various dedicated hardware accelerators based on either Graphical Processing Units (GPU), Field Programmable Gate Arrays (FPGA), Application Specific Integrated Circuits (ASIC), or even multi-core Central Processing Units (CPU) have emerged. Earlier published review papers on face detection/recognition have discussed face detection and face recognition algorithms enhancement that improve the detection accuracy. Nevertheless, none of them have reviewed the hardware accelerators used for this application. Accordingly, this paper aims to provide a comprehensive review of the most recent face recognition algorithms and associated embedded hardware systems targeting real-time performance. A detailed comparison between neural network and non-neural network-based algorithms in terms of accuracy and processing time is provided. Discussions on their suitability to be implemented into parallel hardware architectures such as Single Instruction Multiple Thread (SIMT) or Single Instruction Multiple Data (SIMD) is also discussed.

关键词： Face recognition Field programmable gate arrays Feature extraction Central Processing Unit Real-time systems Hardware acceleration Graphics processing units Face recognition face detection FPGA GPU multicore CPU neural network algorithms non-neural network algorithms

来源：评论

学校读者我要写书评

暂无评论

Formation and Prediction of the Properties of Ion-Plasma Diamond-Like Coatings under Nitrogen Stabilization

引用

JOURNAL OF FRICTION AND WEAR 2024年第1期45卷 9-17页

作者： Kolesnikov, V. I. Kudryakov, O. V. Voropaev, A. I. Kolesnikov, I. V. Varavka, V. N. Lifar, M. S. Guda, A. A. Manturov, D. S. Novikov, E. S. Rostov State Transport Univ Rostov Na Donu 344038 Russia Don State Tech Univ Rostov Na Donu 344000 Russia Southern Fed Univ SFU Int Res Inst Smart Mat Rostov Na Donu 344090 Russia

One of the options for solving the scientific and applied problem of the predicted formation of ion-plasma coating tribological characteristics is presented. The problem is solved by creating and analyzing a carbon coating database. The object of research in this work is ion-plasma diamond-like coatings (DLCs) deposited on a steel substrate. It is shown that the use of nitrogen instead of hydrogen to stabilize carbon coatings not only ensures stable thicknesses of DLCs at the level of 1.0-1.5 mu m, but also serves as an important and convenient technological parameter for regulating the tribological coating characteristics during deposition. Based on the predicted and experimental values of friction coefficient mu and data on sample path length L, the intervals of optimal values of technological parameters %N and lambda are determined. The studied ion-plasma DLCs, obtained according to the established optimal application modes, can be recommended for application under friction conditions equivalent to the tribological tests carried out at friction load F approximate to 10 N.

关键词： vacuum ion-plasma technology diamond-like coatings (DLCs) coating microstructure mechanical properties sliding friction tests tribological properties machine learning neural network algorithms

来源：评论

学校读者我要写书评

暂无评论

Using microbial fuel cell output metrics and nonlinear modeling techniques for smart biosensing

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2013年 449卷 223-228页

作者： Feng, Yinghua Kayode, Olubanke Harper, Willie F., Jr. Univ Pittsburgh Dept Civil & Environm Engn Swanson Sch Engn Pittsburgh PA 15261 USA USAF Inst Technol Dept Syst & Engn Management Wright Patterson AFB OH 45433 USA

Microbial fuel cells (MFCs) are promising tools for water quality monitoring but the response peaks have not been characterized and the data processing methods require improvement. In this study MFC-based biosensing was integrated with two nonlinear programming methods, artificial neural networks (ANN) and time series analysis (TSA). During laboratory testing, the MFCs generated well-organized normally-distributed peaks when the influent chemical oxygen demand (COD) was 150 mg/L or less, and multi-peak signals when the influent COD was 200 mg/L The area under the response peak correlated well with the influent COD concentration. During field testing, we observed normally-distributed and multi-peak profiles at low COD concentrations. The ANN predicted the COD concentration without error with just one layer of hidden neurons, and the TSA model predicted the temporal trends present in properly functioning MFCs and in a device that was gradually failing. This report is the first to integrate ANN and TSA with MFC-based biosensing. Published by Elsevier B.V.

关键词： Microbial fuel cells Biosensing neural network algorithms Water quality Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Software reliability prediction: A survey

引用

QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL 2023年第1期39卷 412-453页

作者： Oveisi, Shahrzad Moeini, Ali Mirzaei, Sayeh Farsi, Mohammad Ali Univ Tehran Coll Engn Sch Engn Sci Dept Algorithms & Computat Tehran Iran Minist Sci Res & Technol Aerosp Res Inst Tehran Iran Univ Tehran Coll Engn Sch Engn Sci Dept Algorithms & Computat Tehran *** Iran

Softwares play an important role in controlling complex systems. Monitoring the proper functioning of the components of such systems is the principal role of softwares. Often, a petite fault in one of the subsystems may cause irreparable damages;therefore, it is of great importance to be able to predict software faults and estimate the reliability of softwares. In this survey, we present a classification of various methods proposed in the literature to predict software reliability. This study summarizes the results of more than 200 research papers in the field. We also discuss the challenges involved in prediction methods along with proposed partial solutions (i.e., Bayesian methods) to improve the accuracy of such predictions. Moreover, we review numerous evaluation measures introduced so far to assess the performance of prediction models, the datasets they are based on, and also the results they yield.

关键词： Bayesian methods fuzzy logic inference systems neural network algorithms software reliability SRGM supervised algorithms

来源：评论

学校读者我要写书评

暂无评论

Topic Detection Based on Sentence Embeddings and Agglomerative Clustering with Markov Moment

引用

FUTURE INTERNET 2020年第9期12卷 144页

作者： Bodrunova, Svetlana S. Orekhov, Andrey, V Blekanov, Ivan S. Lyudkevich, Nikolay S. Tarasov, Nikita A. St Petersburg State Univ Sch Journalism & Mass Commun 7-9 Univ Skaya Embankment St Petersburg 199034 Russia

The paper is dedicated to solving the problem of optimal text classification in the area of automated detection of typology of texts. In conventional approaches to topicality-based text classification (including topic modeling), the number of clusters is to be set up by the scholar, and the optimal number of clusters, as well as the quality of the model that designates proximity of texts to each other, remain unresolved questions. We propose a novel approach to the automated definition of the optimal number of clusters that also incorporates an assessment of word proximity of texts, combined with text encoding model that is based on the system of sentence embeddings. Our approach combines Universal Sentence Encoder (USE) data pre-processing, agglomerative hierarchical clustering by Ward's method, and the Markov stopping moment for optimal clustering. The preferred number of clusters is determined based on the "e-2" hypothesis. We set up an experiment on two datasets of real-world labeled data: News20 and BBC. The proposed model is tested against more traditional text representation methods, like bag-of-words and word2vec, to show that it provides a much better-resulting quality than the baseline DBSCAN and OPTICS models with different encoding methods. We use three quality metrics to demonstrate that clustering quality does not drop when the number of clusters grows. Thus, we get close to the convergence of text clustering and text classification.

关键词： text classification text clustering clustering of short texts neural network algorithms distributive semantics sentence embeddings least squares method Markov moment DBSCAN

来源：评论

学校读者我要写书评

暂无评论

Beyond Probabilistic Record Linkage: Using neural networks and Complex Features to Improve Genealogical Record Linkage

Beyond Probabilistic Record Linkage: Using Neural Networks a...

引用

International Joint Conference on neural networks (IJCNN)

作者： Wilson, D. Randall FamilySearch Salt Lake City UT USA

ISBN: (纸本)9781424496365

Probabilistic record linkage has been used for many years in a variety of industries, including medical, government, private sector and research groups. The formulas used for probabilistic record linkage have been recognized by some as being equivalent to the naive Bayes classifier. While this method can produce useful results, it is not difficult to improve accuracy by using one of a host of other machine learning or neural network algorithms. Even a simple single-layer perceptron tends to outperform the naive Bayes classifier-and thus traditional probabilistic record linkage methods-by a substantial margin. Furthermore, many record linkage system use simple field comparisons rather than more complex features, partially due to the limits of the probabilistic formulas they use. This paper presents an overview of probabilistic record linkage, shows how to cast it in machine learning terms, and then shows that it is equivalent to a naive Bayes classifier. It then discusses how to use more complex features than simple field comparisons, and shows how probabilistic record linkage formulas can be modified to handle this. Finally, it demonstrates a huge improvement in accuracy through the use of neural networks and higher-level matching features, compared to traditional probabilistic record linkage on a large (80,000 pair) set of labeled pairs of genealogical records used by ***.

关键词： Accuracy Bayes methods Classification algorithms Couplings Fires neural networks Probabilistic logic Training genealogical record linkage method high-level matching features learning (artificial intelligence) machine learning naive Bayes classifier neural network algorithms pattern matching perceptrons probabilistic record linkage method records management single-layer perceptron

来源：评论

学校读者我要写书评

暂无评论

Use of Digital Twins and Digital Threads for Subway Infrastructure Monitoring 22nd

Use of Digital Twins and Digital Threads for Subway Infrastr...

引用

22nd International Conference on Computational Science and its Applications (ICCSA)

作者： Vodyaho, Alexander Stankova, Elena Zhukova, Nataly Subbotin, Alexey Chervontsev, Michael St Petersburg State Electrotech Univ Prof Popov St 5 St Petersburg 197376 Russia St Petersburg State Univ 7-9 Univ Skaya Nab St Petersburg 199034 Russia Russian Acad Sci St Petersburg Inst Informat & Automat Fed Res Ctr 14th Line VO 39 St Petersburg 199178 Russia

ISBN: (纸本)9783031105425;9783031105418

The article deals with the problem of using digital twins and digital threads in complex distributed cyber-physical systems with a high level of structural and functional dynamics. A three-level model of the life cycle of a complex cyber-physical system is proposed. At the upper level, the observed system is described in terms of a continuous architecture. At the middle level, the observed system is described in terms of an agile architecture. At the lower level, the observed system is described in terms of a multigraph, which allows describe both the observed system structure and behavior. In the case study the solution of the problem of monitoring the state of the subway infrastructure is considered. The proposed approach has shown its effectiveness and can be applied in other domains such as smart cities.

关键词： Digital twin Digital thread Event monitoring and visualization Smart city Machine learning neural network algorithms

来源：评论

学校读者我要写书评

暂无评论

network Presentation of Texts and Clustering of Messages 6th

Network Presentation of Texts and Clustering of Messages

引用

6th International Conference on Internet Science (INSCI)

作者： Orekhov, Andrey, V Kharlamov, Alexander A. Bodrunova, Svetlana S. St Petersburg State Univ 7-9 Univ Skaya Embankment St Petersburg 199034 Russia Russian Acad Sci Inst Higher Nervous Act & Neurophysiol 5A Butlerova St Moscow 117485 Russia Moscow State Linguist Univ 38 Ostozhenka St Moscow 119034 Russia Higher Sch Econ 20 Myasnitskaya St Moscow 101000 Russia

ISBN: (纸本)9783030347703;9783030347697

For the purposes of searching for various communities on the Internet, automatic typology of text messages defined via application of methods of cluster analysis may be used. In this paper, we address one of the significant issues in text classification via cluster analysis, namely determination of the number of clusters. For clustering based on semantics, text documents are typically represented in the form of vectors within n-dimensional linear space. What we suggest as a method for determining the number of clusters is the agglomerative clustering of vectors in the linear space. In our work, statistical analysis is combined with neural network algorithms to obtain a more accurate semantic portrait of a text. Then, using the techniques of distributive semantics, mapping of the derived network structures into a vector form is constructed. A statistical criterion for the completion of the clustering process is derived, defined as a Markovian moment. By obtaining automatic partitioning into clusters, one can compare texts that are closest to the centroids with actual content samples or evaluate such texts with the help of experts. If the display of texts in a vector form is adequate, all informational messages from a fixed cluster have the same meaning and the same emotional coloring. In addition, we discuss a possibility to use vector representation of texts for sentiment detection in short texts like search engines input or tweets.

关键词： Social network analysis Semantic network neural network algorithms Distributive semantics Cluster analysis Least squares method Markov moment

来源：评论

学校读者我要写书评

暂无评论

A Military Human Performance Management System Design using Machine Learning algorithms 31

A Military Human Performance Management System Design using ...

引用

31st International Telecommunication networks and Applications Conference (ITNAC)

作者： Kang, James Jin Edith Cowan Univ Sch Sci Joondalup WA Australia

ISBN: (纸本)9781665427845

The area of human performance improvement has become a greater focus in recent military contexts as evidenced by Australian Defence Force projects. The aim of the design proposed in this paper is to develop a Performance Management System using Machine Learning (PMSML) to enhance the physical human performance of individual warfighters in combat situations through 1) early recognition and self-management of acute health events in the field;2) forecasting of soldier (user) failure;and 3) proactive self-management of longer-term health outcomes during prolonged manoeuvres or combat situations. This paper proposes a high-level design and approach using machine learning algorithms to assess the feasibility of improving metrics such as health data accuracy and efficiency when transmitting data from sensors to the cloud in military networks. The significance of this design is to predict health conditions of users on a personalised basis for an individual's physical and mental health performance without compromising performance metrics using machine learning algorithms. Results show that machine learning algorithms outperformed other existing methods, which must compromise between certain metrics.

关键词： Machine Learning neural network algorithms Mobile Health (mHealth) Human Performance network Wireless Body Area network (WBAN) Military Mobile network

来源：评论

学校读者我要写书评

暂无评论

Research on Intrusion Detection Method Based on Machine Learning Algorithm and Big Data Technology 3

Research on Intrusion Detection Method Based on Machine Lear...

引用

3rd International Conference on Smart Generation Computing, Communication and networking, SMART GENCON 2023

作者： Li, Junhua Geely University of China Sichuan Province Chengdu city641423 China

ISBN: (纸本)9798350319125

With the popularization and application of Internet technology, people are easy to steal valuable information by cyber attackers in the process of using computer networks and electronic products. In order to maintain a good network environment and protect people's interests, network security issues need to be solved. The role of intrusion detection technology in big data platform and feature selection is particularly important, but there is a problem of inaccurate result evaluation. With the rapid development of network technology, the problem of network security has become increasingly prominent. As an important part of network security, intrusion detection plays an important role in preventing network attacks and maintaining system stability. In recent years, the application of machine learning algorithm and big data technology in the field of network intrusion detection has gradually attracted wide attention. This paper mainly discusses the role of these technologies in the process of intrusion detection and its impact on detection results. © 2023 IEEE.

关键词： Big data platform cybersecurity Machine learning algorithms neural network 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：