检索结果-内蒙古大学图书馆

International Conference on Artificial Intelligence and Computer Information Technology (AICIT)

作者： Fan Yang Shixuan Wang Wuhan Institute of Technology School of Electrical and Information Engineering Wuhan China

ISBN: (数字)9798350365443

ISBN: (纸本)9798350365450

In the field of image processing, the three-dimensional block matching algorithm (BM3D) algorithm combines the relevant characteristics of the spatial domain and the frequency domain, and it is one of the algorithms with the best image denoising effect at present, but its denoising thresholds are always qualitative thresholds for different noisy images, which often results in the loss of details in the process of image processing that requires high accuracy, and the noise of the image is not completely removed. This paper proposes a way to optimize the threshold value based on the sand cat swarm algorithm, through the optimization of the threshold value in BM3D, so that the generated threshold curve is more suitable for the threshold value needed by the actual image. The experimental results show that the optimization algorithm denoises the image with reduced running time and improved image quality compared to the original algorithm denoises the image, so that the peak signal-to-noise ratio of the image at a noise standard deviation of 25 is improved from 19.7256 to 21.7862.

关键词： PSNR Noise reduction Noise filtering algorithms Information filters Noise measurement Optimization Surface treatment Standards Image denoising

来源：评论

学校读者我要写书评

暂无评论

A Web-Based Recommender Application for Board Games Using OOP Design

A Web-Based Recommender Application for Board Games Using OO...

引用

Information Technology and Education Technology (ITET), International Conference on

作者： Emre Öner Tartan Baskent University Vocational School of Technical Sciences Etimesgut Ankara Turkey

ISBN: (数字)9798331540425

ISBN: (纸本)9798331540432

Today, board games are widely used for educational purposes. Scope of board games used in education covers various fields such as history, strategy, economy, and military. In this paper, we present an Object-Oriented Programming (OOP) design and online implementation of a web-based recommender application for board games, employing three popular recommendation techniques. The proposed system employs item-based collaborative filtering, user-based collaborative filtering, and content-based recommendation. We design the system's architecture exploiting OOP concepts such as inheritance and polymorphism. By utilizing OOP concepts, the proposed system achieves modularity, extensibility, and maintainability, harnessing three recommendation techniques in a compact structure. To the best of our knowledge, such a modular design for the conventional recommendation techniques has not been presented previously. Additionally, we implemented a data preprocessing pipeline to ensure the system's readiness for online deployment with the board games dataset. This pipeline encompasses strategic data design, data cleaning, and transformative data handling procedures. As a result, our system handles information retrieval from a vast dataset comprising approximately 19 million ratings for over 20,000 games. By integrating three different methodologies in the system, we aim to present a variety of game recommendations for educators, but for also board game players as well.

关键词： Collaborative filtering Source coding Pipelines Education Data preprocessing Collaboration Games filtering algorithms Information filters Extensibility

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Digital FIR Filter using Various Types of Modular Arithmetic algorithms

Comparative Analysis of Digital FIR Filter using Various Typ...

引用

Networking and Communications (ICNWC), International Conference on

作者： Haridoss G Jency Rubia Sivaranjani K Waswa John Department of Electronics and Communication Engineering M.A.M College of Engineering and Technology India Department of Electronics& Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology India Department of Electronics and Communication Engineering SRM TRP Engineering College India College of Science and Technology(CST) / African Center of Excellence in IoT(ACEIoT) University of Rwanda (UR)

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

Number theory algorithms are extensively required for many digital signal processing (DSP) systems. Over the last few decades, the science community has been discovering the practical applications of number theory. High-speed number manipulation for arithmetic operations is a key component in DSP *** that alternative arithmetic hardware may find a niche. This work consists of designing FIR filter using Residue number system and Logarithmic number system. Also, proposed novel RLNS scheme based on the merging of RNS and LNS. Compared to other number systems, the Residue Logarithmic Number System (RLNS) offers faster operation and more precision. Our prior work explains the creation of the Fixed-width multiplier utilizing the RLNS multiplier as well as the performance evaluation. Because of its distinct area and power compactness qualities, the fixed-width multiplier has been *** the Fixed-width multiplier has its attractive characteristics, it has a limitation of producing truncation error. Additionally, the truncation error was effectively decreased by 89% using the Taylor series expansion for the error approximation, which is significantly less than the orthodox truncated multiplier. The expansion of the earlier work is presented in this paper. The digital FIR filter uses a fixed-width multiplier that is based on RLNS *** the implemented FIR filter can be used for many image or video processing applications. The filter co-efficient has been processed via Fast Fourier Transform (FFT) considered a complicated algorithm for complex numbers. Finally, the comparative analysis of designed filter using RNS, LNS and RLNS has performed. From the investigation, we conclude that the proposed novel RLNS algorithm provides high performance for DSP *** parameter signal-to-noise (SNR) ratio is very significant to measure the value of the precision of the proposed filter. If the SNR value is higher than 25 dB, the filter performs

关键词： Power demand Finite impulse response filters Signal processing algorithms Digital signal processing filtering algorithms filtering theory Software

来源：评论

学校读者我要写书评

暂无评论

Fault Classification Method based on Self-paced Neighborhood Preserving Embedding

Fault Classification Method based on Self-paced Neighborhood...

引用

International Symposium on Autonomous Systems (ISAS)

作者： Hongrui Gao Chuan Ma Yingwei Zhang College of Information Science and Engineering Northeastern University Shenyang China State Laboratory of Synthesis Automation of Process Industry Northeastern University Shenyang China

ISBN: (数字)9798350363173

ISBN: (纸本)9798350363180

In view of the large amount of faulty data in industrial systems, strong correlation between data, large redundancy, and high dimensionality, traditional classification methods can easily lead to the phenomenon of "dimensionality disaster". On the basis of the Neighborhood Preserving Embedding algorithm (NPE), a fault classification algorithm based on Self-paced NPE is proposed. First, the neighbor point set and adjacency matrix of the fault sample points are obtained through the NPE algorithm. Secondly, the function of solving the projection matrix in the NPE algorithm is used as the loss function in the Self-paced Learning model to construct the objective function of the Self-paced Neighborhood Preserving Embedding (Self-paced NPE) algorithm. By designing the loss function in the Self-paced Learning model, gradually select from easy to difficult samples with smaller loss are selected, samples with larger loss are discarded, and relatively simple samples are used for training. Finally, the objective function of the Self-paced NPE algorithm is solved and the proposed algorithm is tested with TE process data . The experimental results show that, compared with the NPE algorithm, the Self-paced NPE algorithm can extract features of high-dimensional fault data more effectively, achieve dimension reduction, and improve the accuracy of fault classification.

关键词： Training Dimensionality reduction Manifolds Sensitivity Redundancy filtering algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Design of an Optimal IIR Full-Band Digital Differentiator

Design of an Optimal IIR Full-Band Digital Differentiator

引用

Device Intelligence, Computing and Communication Technologies, (DICCT), International Conference on

作者： Abhay Sharma Mayank Saini Mridul Gupta Love Bargoti Graphic Era (Deemed to be University) Dehradun India Department of Electronics & Communication Engineering Graphic Era (Deemed to be University) Dehradun India

ISBN: (数字)9798350372847

ISBN: (纸本)9798350372854

In this paper a novel metaheuristic algorithm called the Coati optimization algorithm (COA) is used to design a 2 nd order infinite impulse response (IIR) full-band digital differentiator (DD) by optimizing the filter coefficients. The objective is to closely approximate the frequency response of the proposed filter so that it tries to meet the ideal frequency response characteristics of an ideal differentiator. COA is a population-based metaheuristic algorithm which imitates the natural behavior of coatis when they are attacking iguanas and evading from predators. Every member of the coati's population represents a possible optimal solution based on their positions in the search space. The COA based design of the IIR DD is compared with various other designs obtained with traditional algorithms and proved to be better in terms of various error performance parameters. Overall, these improved results for the proposed filter can become an inspiration for various digital signal processing applications.

关键词： Heuristic algorithms Metaheuristics Sociology Signal processing algorithms IIR filters filtering algorithms Frequency response

来源：评论

学校读者我要写书评

暂无评论

Efficient yield optimization of a 100 GHz filter using the novel combination of a performance guided random walk and NLPLS-based PCE

Efficient yield optimization of a 100 GHz filter using the n...

引用

European Conference on Microwave

作者： Leanne Johnson Dieter Klink Werner Steyn Petrie Meyer Stellenbosch University South Africa

ISBN: (数字)9782874870774

ISBN: (纸本)9798350385892

Yield optimization can be a crucial step in highvolume passive microwave component design, however it is typically a very expensive process, as a multitude of full-wave electromagnetic analyses are required for statistical analysis at each step of the optimization process. Metamodeling techniques have been shown to be useful solutions to this problem. In this paper yield optimization of a 43-variable passive 100 GHz ridged waveguide filter is done using the novel combination of a performance-guided random walk and Non-Linear Partial Least Squares based Polynomial Chaos Expansion (NLPLS-based PCE). It is shown that a substantial improvement of the yield is achieved with reduced model evaluations using this method.

关键词： Chaos Waveguide components Statistical analysis Metamodeling Europe filtering algorithms Microwave theory and techniques Polynomials Microwave filters Optimization

来源：评论

学校读者我要写书评

暂无评论

A Graph Neural Network Approach for Solving the Ranked Assignment Problem in Multi-Object Tracking

A Graph Neural Network Approach for Solving the Ranked Assig...

引用

IEEE Symposium on Intelligent Vehicle

作者： Robin Dehler Martin Herrmann Jan Strohbeck Michael Buchholz Institute of Measurement Control and Microtechnology Ulm University Ulm Germany

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

Associating measurements with tracks is a crucial step in Multi-Object Tracking (MOT) to guarantee the safety of autonomous vehicles. To manage the exponentially growing number of track hypotheses, truncation becomes necessary. In the δ-Generalized Labeled Multi-Bernoulli (δ-GLMB) filter application, this truncation typically involves the ranked assignment problem, solved by Murty’s algorithm or the Gibbs sampling approach, both with limitations in terms of complexity or accuracy, respectively. With the motivation to improve these limitations, this paper addresses the ranked assignment problem arising from data association tasks with an approach that employs Graph Neural Networks (GNNs). The proposed Ranked Assignment Prediction Graph Neural Network (RAPNet) uses bipartite graphs to model the problem, harnessing the computational capabilities of deep learning. The conclusive evaluation compares the RAPNet with Murty’s algorithm and the Gibbs sampler, showing accuracy improvements compared to the Gibbs sampler.

关键词： Deep learning Accuracy Computational modeling Predictive models filtering algorithms Prediction algorithms Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

FRFT Based Parameter Estimation of the Quadratic FM Signal

引用

Chinese Journal of Electronics 2023年第3期19卷 463-467页

作者： Qiang Qu Minglu Jin Jae Moung Kim School of Electronic and Information Engineering Dalian University of Technology Dalian China School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan China Graduate School of IT&Telecommunications Inha University Incheon Korea

This paper generalizes the Fractional Fourier transform (FRFT) to estimate the parameters of the Quadratic frequency modulated (QFM) signal. Firstly, the proposed algorithm transforms the QFM signal into the Linear frequency modulated (LFM) signal by means of the instantaneous autocorrelation function, and then the parameter estimation of the QFM signal is performed by the FRFT and dechirping method. In order to calculate discrete sampling values of the FRFT, an adaptive FRFT algorithm based on the Least mean square (LMS) is proposed. Extension to the multicomponent and higher order frequency modulated signals is also discussed. Finally, the effects of delay parameter on estimation performances are investigated through Monte Carlo simulations and the results of simulations verify the effectiveness of the proposed algorithm.

关键词： Frequency modulation Fourier transforms Monte Carlo methods Simulation Estimation Adaptive filters filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Design of an Unknown Clutter Density Adaptive Target Nascent Enhancement Filter

Design of an Unknown Clutter Density Adaptive Target Nascent...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Peng Zhang Yan Liu Ordnance NCO Academy Army Engineering University of PLA Wuhan China Department of Economy and Management Wenhua College Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

When the intensity of the newborn target is unknown, the measurement-driven CPHD filter of the Adaptive Target Birth Intesity (ATBI) can track multiple targets. In order to solve the problem of the normalized imbalance between the newborn target intensity and the clutter intensity in this method, an adaptive target newborn intensity CPHD filter with unknown clutter density (UCR) was proposed. On the basis of the ATBI-CPHD filter, the recursive steps of the UCR-ATBI-CPHD filter and its Gaussian hybrid implementation are given. Experimental results show that the proposed algorithm can not only reduce the track lag phenomenon caused by the normalization imbalance, but also realize the stable tracking of multiple targets under the condition that the clutter density and the strength of the new target are unknown, which popularizes the application scope of the ATBI algorithm.

关键词： Pediatrics Target tracking Simulation Signal processing algorithms Estimation Adaptive filters filtering algorithms Signal processing Clutter

来源：评论

学校读者我要写书评

暂无评论

Enhanced Fake News Detection using Prediction algorithms

Enhanced Fake News Detection using Prediction Algorithms

引用

Recent Innovation in Smart and Sustainable Technology (ICRISST), International Conference on

作者： D. Rosy Salomi Victoria Gowtham G K. Arulan Sabari Ashwin Roberts R Gokul S Department of CSE St. Joseph’s College of Engineering Chennai India Department of CS St. Joseph’s College of Engineering Chennai India

ISBN: (数字)9798350309140

ISBN: (纸本)9798350309157

The advent of web-based media has provided a platform for individuals to express their opinions freely, facilitating easier communication compared to the past. This convenience comes with the risk of deliberate dissemination of misinformation. The ready access to a plethora of online information sources exacerbates the problem, as people may be exposed to and potentially believes false information. It is crucial for us to be aware of and flag such content on social media platforms. Given the rapid generation of information through online media, distinguishing between authentic news and fabrications is challenging without knowing the news source. The spread of fake news can have serious consequences, emphasizing the need for measures to reduce and differentiate between genuine and false messages. Term Frequency measures how often a word appears in a document, indicating its relevance. Inverse Document Frequency assesses the significance of a term in the entire corpus, helping filter out irrelevant words. An examination of spam detection is conducted by employing diverse classifiers, including BERT and RoBERTa to evaluate accuracy and furnish comparative findings.

关键词： Fabrication Technological innovation Social networking (online) Named entity recognition Predictive models filtering algorithms Prediction algorithms Frequency measurement Classification algorithms Fake news

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：