检索结果-内蒙古大学图书馆

2021 International Russian Automation Conference, RusAutoCon 2021

作者： Sichkar, Valentyn N. Lyamin, Andrey V. Itmo University Faculty of Software Engineering and Computer Systems Saint-Petersburg Russia

ISBN: (纸本)9780738131566

In this paper, the method to design deep Convolutional Neural Network (CNN) architecture for the problem of traffic signs classification is proposed. The approach incorporates five main stages followed by each other: selecting the deepness of the network via the number of convolutional-pooling pairs, choosing the needed number of feature maps in every convolutional layer, identifying the sufficient number of neurons in the hidden fully connected layer, estimating the needed percentage of dropout after every layer. The last stage is aimed to analyse if replacing max pooling by convolution with strides 2 or by average pooling improves designed architecture. At each stage, every designed model is trained and evaluated 100 times. The choice of the best model to continue with at the next stage is based on the highest of the most frequent accuracy. The obtained final architecture is trained and tested with the original German Traffic Sign Recognition Benchmark (GTSRB) and its augmented version via geometric transformations: rotation around the centre point and projection to different sides that imitates capturing of images by the camera with some skew angle. Experimental results showed testing accuracy of more than 99.9% that enables to use designed architecture in real-life applications. © 2021 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Location Detection of an Object Non Line of Sight with Audio Signal

Location Detection of an Object Non Line of Sight with Audio...

引用

International Artificial Intelligence and Data Processing Symposium (IDAP)

作者： Nevzat Olgun Mücahit Çalişan Department of Software Engineering Afyon Kocatepe University Afyonkarahisar Türkiye Department of Computer Engineering Engineering and Architecture Faculty Bingöl Türkiye

ISBN: (数字)9798331531492

ISBN: (纸本)9798331531508

Locating objects Non-Line-of-Sight is an important challenge in many fields such as defense applications, autonomous vehicles, natural disasters, etc. With the advancement of signal processing techniques, there has been an increased interest in the detection of objects in hidden areas. In this respect, audio signals have a strong potential as a low-cost technology for object localization. This study presents an experimental application to detect the location of hidden objects Non-Line-of-Sight based on audio signals. The signals from the sound source strike the hidden object through a reflecting surface, such as a wall, and are received back from the reflecting surface as secondary signals. In this study, object detection can be performed with acoustic sound signals without physically intervening in an area beyond the line of sight and without locating any sensors in this area. The experimental results obtained from the study show that the position detection of an object located Non-Line-of-Sight can be done satisfactorily.

关键词： Location awareness Disasters Object detection Signal processing Data processing Acoustics Artificial intelligence Intelligent sensors Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Survey of Edge Computing Privacy and Security Threats and Their Countermeasures

A Survey of Edge Computing Privacy and Security Threats and ...

引用

IEEE computer Society Annual Symposium on VLSI

作者： Ahmed Shafee Tasneem A. Awaad Ahmed Moro Department of Engineering and Computer Science Adams State University Alamosa CO USA Department of Computer and Systems Engineering Faculty of Engineering Ain Shams University Cairo Egypt Siemens Digital Industries Software Lifecycle Collaboration Software Segment Cairo Egypt

ISBN: (数字)9798350354119

ISBN: (纸本)9798350354126

Recent advancements in Artificial Intelligence (AI) and the proliferation of the Internet of Things (loT) and mobile devices have generated enormous data volumes, necessitating advanced data processing closer to data sources through edge computing to enhance efficiency and reduce latency. Nonetheless, privacy concerns in cloud storage and data transmission, alongside the inadequacy of traditional privacy protections, have highlighted the vulnerability to sophisticated data breaches. This paper offers a survey on edge computing, emphasizing privacy and security challenges, evaluating threats, and exploring solutions to promote the development of secure, robust and privacy-preserving edge computing frameworks.

关键词： Surveys Data privacy Cloud computing Privacy Very large scale integration Data processing Security

来源：评论

学校读者我要写书评

暂无评论

Classification of Stakeholders of an Information System using Fuzzy based Adjusted Cosine Similarity Measure during Requirements Elicitation Process

引用

Procedia computer Science 2023年 230卷 620-628页

作者： Faiz Akram Tanvir Ahmad Mohd. Sadiq Department of Computer Engineering Faculty of Engineering and Technology Jamia Millia Islamia New Delhi-25 India Software Engineering Laboratory Computer Engineering Section UPFET Jamia Millia Islamia New Delhi-25 India

Requirements elicitation process is employed for the identification of stakeholders of an information system. A large number of stakeholders from different domains across the globe participate during the requirements elicitation process. Based on our review, we found that existing methods for the analysis of stakeholders do not support how to classify the stakeholders based on the similarity measures. These measures play an important role for the recommendation of an item/user in a recommendation system. Thus, the objective of this paper is to classify the stakeholders of an information system using fuzzy-based adjusted cosine similarity measure. We have identified the stakeholders of library information system and their opinions for different requirements are recorded. The identified stakeholders have been classified and analysed based on the following similarity measures under fuzzy environment, i.e., Cosine similarity measure, Euclidean distance, Pearson coefficient correlation etc., so that stakeholders having similar requirements can be recommended to strengthen the requirements elicitation process.

关键词： software Requirements Elicitation Information System Similarity Measures Recommendation System Stakeholders

来源：评论

学校读者我要写书评

暂无评论

Using Pi Zero SBCs as a Low-Cost Driver Monitoring Solution

Using Pi Zero SBCs as a Low-Cost Driver Monitoring Solution

引用

Robotics, Automation and Artificial Intelligence (RAAI), IEEE International Conference on

作者： Hady A. Khalil Sherif A. Hammad Hossam E. Abdelmunim Shady A. Maged Department of Mechatronics Engineering Faculty of Engineering Ain Shams University Cairo Egypt Garraio for Software Innovations Cairo Egypt Computer and Systems Engineering Faculty of Engineering Ain Shams University Cairo Egypt

ISBN: (数字)9798331520038

ISBN: (纸本)9798331520045

Driver monitoring systems have become a vital component of Advanced Driver Assistance Systems (ADAS) for vehicle safety. According to the U.S. National Highway Traffic Safety Administration, drowsy driving contributes to nearly 100,000 accidents annually. Early driver monitoring systems relied on vehicle sensor data, and current systems often use eye-tracking technology. Recently, there has been a rising interest in applying machine vision and deep learning to driver monitoring systems. Machine vision allows for advanced driver monitoring, such as detecting driver attention states, smartphone use, and seat belts, but machine vision systems typically require high processing power, which increases the device cost. This paper introduces a cost-effective driver monitoring system utilizing Pi Zero Single Board computers (SBCs) like the Raspberry Pi Zero 2 W board, and Radxa Zero 3 W board, combined with a deep learning CNN, the system is capable of identifying various driver states, including safe driving, distraction, drowsiness, and smartphone use.

关键词： Deep learning YOLO Road transportation Performance evaluation Machine vision Lighting Artificial intelligence Monitoring Robots Vehicles

来源：评论

学校读者我要写书评

暂无评论

Research on Text Summarization Generator Method Based on Input Text Linguistic Features and Copy Mechanism 16

Research on Text Summarization Generator Method Based on Inp...

引用

16th IEEE International Conference on Intelligent Systems and Knowledge engineering, ISKE 2021

作者： Wang, Liuyang Yu, Yangxin Huaiyin Institute of Technology of China Faculty of Computer Software Engineering Huai'an China

ISBN: (纸本)9781665405539

The Sequence-to-Sequence (Seq2Seq) of neural network (NN) method based on recurrent neural network (RNN) and attention mechanism plays an important role in information extraction and automatic summarization. However, this method can't make full use of the text linguistic feature information, and there is a problem of unregistered words in the generated results, which affects the accuracy and readability of the text summarization. To solve this problem, the text linguistic feature is used to improve the input characteristics, and the copy mechanism is introduced to alleviate the problem of unregistered words in the summarization generation process. On this basis, a new method named Copy-Generator Model (CGM) based on Seq2Seq model is proposed to improve the effect of text summarization. The results of experiments using LCSTS (Large Scale Chinese Short Text Summarization) as the data source show that the proposed method in this paper can effectively improve the accuracy of summarization and can be applied to automatic text summarization. © 2021 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Review of Digital Watermarking Techniques, Characteristics and Attacks in Text Documents 2nd

A Review of Digital Watermarking Techniques, Characteristics...

引用

2nd International Conference on Innovative Technology, engineering and Sciences, iCITES 2020

作者： Usop, Nur Alya Afikah Hisham, Syifak Izhar Faculty of Computer Science and Software Engineering Universiti Malaysia Pahang Gambang Malaysia

ISBN: (纸本)9783030709167

Security plays an important role in many sectors and industries. Nowadays, scams and illegal movements are spreading around the world. Copyright protection for PDF documentation is one of the focus in digital watermarking. Hence, a study was conducted on the related research of digital watermarking on PDF which is text documentation. This paper shows a review of watermarking techniques, characteristics, and possibility of attacks in text document format. This paper also discusses the comparisons between the existing scheme with different domains. The results can be seen from the dominant approaches in text digital watermarking which are the structural approach and hybrid approach. Based on the experimental phase, attacks are in a few formats such as insertion attack and removal attack. These are frequently used to test the robustness of digital watermarks that are embedded into an object. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Digital watermarking

来源：评论

学校读者我要写书评

暂无评论

Inferring Custom Synthesizable Kernel for Generation of Coprocessors with Out-of-Order Execution 10

Inferring Custom Synthesizable Kernel for Generation of Copr...

引用

10th Mediterranean Conference on Embedded Computing, MECO 2021

作者： Antonov, Alexander Software Engineering and Computer Systems Faculty ITMO University Saint-Petersburg Russia

ISBN: (纸本)9780738133614

The research is devoted to the problem of project- specific steep learning curve when designing complex hardware microarchitectures. To address this issue, it is proposed to use custom synthesizable kernels that provide computational model inferred from specific properties of target microarchitectures. Using ActiveCore hardware generation framework, previously developed by the author, inference of such kernel for coprocessors with out-of-order (OoO) execution and register renaming is demonstrated. Hardware generator packaged with this kernel offers behavioral specification of execution pipelines functionality and provides decoupled latency-insensitive interface for execution units, which allows to generate designs both in RTL and HLS form in arbitrary combinations. Experimental OoO FPU coprocessor based on this kernel shows capability for concise, high-level, untimed specification, while having sufficient performance for integration with superscalar OoO CPU designs. © 2021 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Some Approximation Results on a Class of Szász-Mirakjan-Kantorovich Operators Including Non-negative parameter α

引用

Numerical Functional Analysis and Optimization 2025年第6期46卷

作者： Özger, Faruk Aslan, Reşat Ersoy, Merve Department of Computer Engineering Iğdır University Iğdır Turkey Faculty of Sciences Department of Mathematics Van Yuzuncu Yil University Van Turkey Faculty of Engineering Department of Software Engineering Istanbul Topkapi University Istanbul Turkey

Alternative proofs of the Weierstrass uniform approximation theorem have been provided by numerous mathematicians, including renowned ones. Among them, there was Bernstein that used a set of polynomials known as the Bernstein polynomials. Motivated by the advancements in computational disciplines, we propose a new type of Szász-Mirakjan-Kantorovich operators that incorporate a shape parameterα. Certain shape-preserving properties, such as monotonicity and convexity, are achieved by computing the first and second order derivatives of the proposed operators. Certain approximation properties, including the statistical rate of convergence, are also obtained using a regular summability matrix. Finally, theoretical results are supported by illustrative graphics and numerical experiments using the Mathematica computer program. The operators defined in this paper may be used in computer and computational sciences, including in robotic manipulator control.

关键词： computer graphics rate of convergence shape-preserving properties statistical convergence Stancu-Kantorovich operators Szász-Mirakjan operators 41A10 41A25 41A36

来源：评论

学校读者我要写书评

暂无评论

Explainability-based Trust Algorithm for electricity price forecasting models

引用

Energy and AI 2023年第4期14卷 141-158页

作者： Leena Heistrene Ram Machlev Michael Perl Juri Belikov Dmitry Baimel Kfir Levy Shie Mannor Yoash Levron Electrical Engineering Department School of TechnologyPandit Deendayal Energy UniversityGandhinagarGujarat382007India The Andrew and Erna Viterbi Faculty of Electrical&Computer Engineering Technion-Israel Institute of TechnologyHaifa3200003Israel Department of Software Science Tallinn University of TechnologyAkadeemia tee 15ATallinn12618Estonia Electrical&Electronics Engineering Department Sami Shamoon College of EngineeringBeer-Sheva84100Israel

Advanced machine learning(ML)algorithms have outperformed traditional approaches in various forecasting applications,especially electricity price forecasting(EPF).However,the prediction accuracy of ML reduces substantially if the input data is not similar to the ones seen by the model during *** is often observed in EPF problems when market dynamics change owing to a rise in fuel prices,an increase in renewable penetration,a change in operational policies,*** the dip in model accuracy for unseen data is a cause for concern,what is more,challenging is not knowing when the ML model would respond in such a *** uncertainty makes the power market participants,like bidding agents and retailers,vulnerable to substantial financial loss caused by the prediction errors of EPF ***,it becomes essential to identify whether or not the model prediction at a given instance is *** this light,this paper proposes a trust algorithm for EPF users based on explainable artificial intelligence *** suggested algorithm generates trust scores that reflect the model’s prediction quality for each new *** scores are formulated in two stages:in the first stage,the coarse version of the score is formed using correlations of local and global explanations,and in the second stage,the score is fine-tuned further by the Shapley additive explanations values of different *** score-based explanations are more straightforward than feature-based visual explanations for EPF users like asset managers and traders.A dataset from Italy’s and ERCOT’s electricity market validates the efficacy of the proposed *** show that the algorithm has more than 85%accuracy in identifying good predictions when the data distribution is similar to the training *** the case of distribution shift,the algorithm shows the same accuracy level in identifying bad predictions.

关键词： Electricity price forecasting EPF Explainable AI model XAI SHAP Explainability

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：